Files
train_qnli_42_1779207272/trainer_log.jsonl
ModelHub XC 89779fca34 初始化项目,由ModelHub XC社区提供模型
Model: rbelanec/train_qnli_42_1779207272
Source: Original Platform
2026-06-11 01:10:36 +08:00

11806 lines
2.8 MiB

{"current_steps": 5, "total_steps": 58920, "loss": 0.8758, "lr": 1.3577732518669381e-09, "epoch": 0.0004243041412084182, "percentage": 0.01, "elapsed_time": "0:00:00", "remaining_time": "2:17:54", "throughput": 7108.51, "total_tokens": 4992}
{"current_steps": 10, "total_steps": 58920, "loss": 0.9516, "lr": 3.0549898167006107e-09, "epoch": 0.0008486082824168364, "percentage": 0.02, "elapsed_time": "0:00:01", "remaining_time": "1:46:41", "throughput": 8775.74, "total_tokens": 9536}
{"current_steps": 15, "total_steps": 58920, "loss": 0.8858, "lr": 4.752206381534284e-09, "epoch": 0.0012729124236252546, "percentage": 0.03, "elapsed_time": "0:00:01", "remaining_time": "1:36:03", "throughput": 9549.52, "total_tokens": 14016}
{"current_steps": 20, "total_steps": 58920, "loss": 0.8972, "lr": 6.449422946367957e-09, "epoch": 0.0016972165648336728, "percentage": 0.03, "elapsed_time": "0:00:01", "remaining_time": "1:32:55", "throughput": 10378.52, "total_tokens": 19648}
{"current_steps": 25, "total_steps": 58920, "loss": 0.8604, "lr": 8.146639511201628e-09, "epoch": 0.002121520706042091, "percentage": 0.04, "elapsed_time": "0:00:02", "remaining_time": "1:29:30", "throughput": 10865.24, "total_tokens": 24768}
{"current_steps": 30, "total_steps": 58920, "loss": 0.9138, "lr": 9.843856076035303e-09, "epoch": 0.0025458248472505093, "percentage": 0.05, "elapsed_time": "0:00:02", "remaining_time": "1:27:48", "throughput": 11160.29, "total_tokens": 29952}
{"current_steps": 35, "total_steps": 58920, "loss": 0.9519, "lr": 1.1541072640868975e-08, "epoch": 0.0029701289884589274, "percentage": 0.06, "elapsed_time": "0:00:03", "remaining_time": "1:25:45", "throughput": 11216.96, "total_tokens": 34304}
{"current_steps": 40, "total_steps": 58920, "loss": 0.9435, "lr": 1.3238289205702648e-08, "epoch": 0.0033944331296673455, "percentage": 0.07, "elapsed_time": "0:00:03", "remaining_time": "1:24:32", "throughput": 11422.54, "total_tokens": 39360}
{"current_steps": 45, "total_steps": 58920, "loss": 0.9904, "lr": 1.493550577053632e-08, "epoch": 0.0038187372708757637, "percentage": 0.08, "elapsed_time": "0:00:03", "remaining_time": "1:23:36", "throughput": 11600.62, "total_tokens": 44480}
{"current_steps": 50, "total_steps": 58920, "loss": 0.8952, "lr": 1.6632722335369995e-08, "epoch": 0.004243041412084182, "percentage": 0.08, "elapsed_time": "0:00:04", "remaining_time": "1:22:41", "throughput": 11663.2, "total_tokens": 49152}
{"current_steps": 55, "total_steps": 58920, "loss": 0.8879, "lr": 1.8329938900203663e-08, "epoch": 0.0046673455532926, "percentage": 0.09, "elapsed_time": "0:00:04", "remaining_time": "1:22:07", "throughput": 11663.73, "total_tokens": 53696}
{"current_steps": 60, "total_steps": 58920, "loss": 0.8968, "lr": 2.0027155465037338e-08, "epoch": 0.0050916496945010185, "percentage": 0.1, "elapsed_time": "0:00:04", "remaining_time": "1:21:31", "throughput": 11744.29, "total_tokens": 58560}
{"current_steps": 65, "total_steps": 58920, "loss": 0.8504, "lr": 2.172437202987101e-08, "epoch": 0.005515953835709436, "percentage": 0.11, "elapsed_time": "0:00:05", "remaining_time": "1:21:13", "throughput": 11855.47, "total_tokens": 63808}
{"current_steps": 70, "total_steps": 58920, "loss": 0.8985, "lr": 2.3421588594704685e-08, "epoch": 0.005940257976917855, "percentage": 0.12, "elapsed_time": "0:00:05", "remaining_time": "1:20:39", "throughput": 11829.52, "total_tokens": 68096}
{"current_steps": 75, "total_steps": 58920, "loss": 0.8855, "lr": 2.5118805159538353e-08, "epoch": 0.006364562118126273, "percentage": 0.13, "elapsed_time": "0:00:06", "remaining_time": "1:20:05", "throughput": 11828.38, "total_tokens": 72448}
{"current_steps": 80, "total_steps": 58920, "loss": 0.7931, "lr": 2.681602172437203e-08, "epoch": 0.006788866259334691, "percentage": 0.14, "elapsed_time": "0:00:06", "remaining_time": "1:20:07", "throughput": 11985.67, "total_tokens": 78336}
{"current_steps": 85, "total_steps": 58920, "loss": 0.7442, "lr": 2.8513238289205703e-08, "epoch": 0.00721317040054311, "percentage": 0.14, "elapsed_time": "0:00:06", "remaining_time": "1:19:45", "throughput": 12016.46, "total_tokens": 83072}
{"current_steps": 90, "total_steps": 58920, "loss": 0.8236, "lr": 3.0210454854039375e-08, "epoch": 0.007637474541751527, "percentage": 0.15, "elapsed_time": "0:00:07", "remaining_time": "1:19:40", "throughput": 12049.5, "total_tokens": 88128}
{"current_steps": 95, "total_steps": 58920, "loss": 0.7132, "lr": 3.190767141887305e-08, "epoch": 0.008061778682959946, "percentage": 0.16, "elapsed_time": "0:00:07", "remaining_time": "1:19:28", "throughput": 12076.17, "total_tokens": 92992}
{"current_steps": 100, "total_steps": 58920, "loss": 0.7652, "lr": 3.360488798370672e-08, "epoch": 0.008486082824168364, "percentage": 0.17, "elapsed_time": "0:00:08", "remaining_time": "1:19:18", "throughput": 12128.86, "total_tokens": 98112}
{"current_steps": 105, "total_steps": 58920, "loss": 0.7313, "lr": 3.530210454854039e-08, "epoch": 0.008910386965376781, "percentage": 0.18, "elapsed_time": "0:00:08", "remaining_time": "1:19:00", "throughput": 12136.37, "total_tokens": 102720}
{"current_steps": 110, "total_steps": 58920, "loss": 0.6254, "lr": 3.699932111337407e-08, "epoch": 0.0093346911065852, "percentage": 0.19, "elapsed_time": "0:00:08", "remaining_time": "1:18:48", "throughput": 12157.78, "total_tokens": 107520}
{"current_steps": 115, "total_steps": 58920, "loss": 0.5389, "lr": 3.8696537678207734e-08, "epoch": 0.009758995247793618, "percentage": 0.2, "elapsed_time": "0:00:09", "remaining_time": "1:18:34", "throughput": 12155.58, "total_tokens": 112064}
{"current_steps": 120, "total_steps": 58920, "loss": 0.4796, "lr": 4.0393754243041405e-08, "epoch": 0.010183299389002037, "percentage": 0.2, "elapsed_time": "0:00:09", "remaining_time": "1:18:28", "throughput": 12195.48, "total_tokens": 117184}
{"current_steps": 125, "total_steps": 58920, "loss": 0.4806, "lr": 4.2090970807875084e-08, "epoch": 0.010607603530210456, "percentage": 0.21, "elapsed_time": "0:00:09", "remaining_time": "1:18:18", "throughput": 12192.1, "total_tokens": 121792}
{"current_steps": 130, "total_steps": 58920, "loss": 0.4942, "lr": 4.3788187372708756e-08, "epoch": 0.011031907671418872, "percentage": 0.22, "elapsed_time": "0:00:10", "remaining_time": "1:18:07", "throughput": 12181.4, "total_tokens": 126272}
{"current_steps": 135, "total_steps": 58920, "loss": 0.4579, "lr": 4.5485403937542434e-08, "epoch": 0.011456211812627291, "percentage": 0.23, "elapsed_time": "0:00:10", "remaining_time": "1:17:59", "throughput": 12180.05, "total_tokens": 130880}
{"current_steps": 140, "total_steps": 58920, "loss": 0.483, "lr": 4.71826205023761e-08, "epoch": 0.01188051595383571, "percentage": 0.24, "elapsed_time": "0:00:11", "remaining_time": "1:17:50", "throughput": 12185.62, "total_tokens": 135552}
{"current_steps": 145, "total_steps": 58920, "loss": 0.4629, "lr": 4.887983706720977e-08, "epoch": 0.012304820095044128, "percentage": 0.25, "elapsed_time": "0:00:11", "remaining_time": "1:17:52", "throughput": 12225.17, "total_tokens": 140928}
{"current_steps": 150, "total_steps": 58920, "loss": 0.3571, "lr": 5.057705363204345e-08, "epoch": 0.012729124236252547, "percentage": 0.25, "elapsed_time": "0:00:11", "remaining_time": "1:17:52", "throughput": 12256.83, "total_tokens": 146176}
{"current_steps": 155, "total_steps": 58920, "loss": 0.2699, "lr": 5.227427019687712e-08, "epoch": 0.013153428377460964, "percentage": 0.26, "elapsed_time": "0:00:12", "remaining_time": "1:17:52", "throughput": 12307.19, "total_tokens": 151680}
{"current_steps": 160, "total_steps": 58920, "loss": 0.2673, "lr": 5.397148676171079e-08, "epoch": 0.013577732518669382, "percentage": 0.27, "elapsed_time": "0:00:12", "remaining_time": "1:17:47", "throughput": 12313.17, "total_tokens": 156480}
{"current_steps": 165, "total_steps": 58920, "loss": 0.1973, "lr": 5.5668703326544464e-08, "epoch": 0.0140020366598778, "percentage": 0.28, "elapsed_time": "0:00:13", "remaining_time": "1:17:40", "throughput": 12303.54, "total_tokens": 161024}
{"current_steps": 170, "total_steps": 58920, "loss": 0.1699, "lr": 5.7365919891378136e-08, "epoch": 0.01442634080108622, "percentage": 0.29, "elapsed_time": "0:00:13", "remaining_time": "1:17:34", "throughput": 12306.43, "total_tokens": 165760}
{"current_steps": 175, "total_steps": 58920, "loss": 0.1883, "lr": 5.906313645621181e-08, "epoch": 0.014850644942294636, "percentage": 0.3, "elapsed_time": "0:00:13", "remaining_time": "1:17:25", "throughput": 12281.8, "total_tokens": 169984}
{"current_steps": 180, "total_steps": 58920, "loss": 0.2024, "lr": 6.076035302104548e-08, "epoch": 0.015274949083503055, "percentage": 0.31, "elapsed_time": "0:00:14", "remaining_time": "1:17:20", "throughput": 12273.17, "total_tokens": 174528}
{"current_steps": 185, "total_steps": 58920, "loss": 0.1706, "lr": 6.245756958587915e-08, "epoch": 0.01569925322471147, "percentage": 0.31, "elapsed_time": "0:00:14", "remaining_time": "1:17:16", "throughput": 12265.13, "total_tokens": 179136}
{"current_steps": 190, "total_steps": 58920, "loss": 0.1962, "lr": 6.415478615071284e-08, "epoch": 0.016123557365919892, "percentage": 0.32, "elapsed_time": "0:00:14", "remaining_time": "1:17:10", "throughput": 12245.0, "total_tokens": 183424}
{"current_steps": 195, "total_steps": 58920, "loss": 0.1687, "lr": 6.58520027155465e-08, "epoch": 0.01654786150712831, "percentage": 0.33, "elapsed_time": "0:00:15", "remaining_time": "1:17:04", "throughput": 12241.62, "total_tokens": 187968}
{"current_steps": 200, "total_steps": 58920, "loss": 0.167, "lr": 6.754921928038017e-08, "epoch": 0.01697216564833673, "percentage": 0.34, "elapsed_time": "0:00:15", "remaining_time": "1:17:02", "throughput": 12266.9, "total_tokens": 193152}
{"current_steps": 205, "total_steps": 58920, "loss": 0.171, "lr": 6.924643584521385e-08, "epoch": 0.017396469789545146, "percentage": 0.35, "elapsed_time": "0:00:16", "remaining_time": "1:16:58", "throughput": 12256.62, "total_tokens": 197632}
{"current_steps": 210, "total_steps": 58920, "loss": 0.1644, "lr": 7.094365241004752e-08, "epoch": 0.017820773930753563, "percentage": 0.36, "elapsed_time": "0:00:16", "remaining_time": "1:16:53", "throughput": 12258.57, "total_tokens": 202304}
{"current_steps": 215, "total_steps": 58920, "loss": 0.1633, "lr": 7.26408689748812e-08, "epoch": 0.018245078071961983, "percentage": 0.36, "elapsed_time": "0:00:16", "remaining_time": "1:16:49", "throughput": 12263.45, "total_tokens": 207040}
{"current_steps": 220, "total_steps": 58920, "loss": 0.1588, "lr": 7.433808553971487e-08, "epoch": 0.0186693822131704, "percentage": 0.37, "elapsed_time": "0:00:17", "remaining_time": "1:16:50", "throughput": 12296.77, "total_tokens": 212480}
{"current_steps": 225, "total_steps": 58920, "loss": 0.1612, "lr": 7.603530210454854e-08, "epoch": 0.01909368635437882, "percentage": 0.38, "elapsed_time": "0:00:17", "remaining_time": "1:16:50", "throughput": 12320.43, "total_tokens": 217728}
{"current_steps": 230, "total_steps": 58920, "loss": 0.1653, "lr": 7.773251866938221e-08, "epoch": 0.019517990495587237, "percentage": 0.39, "elapsed_time": "0:00:18", "remaining_time": "1:16:43", "throughput": 12300.48, "total_tokens": 221888}
{"current_steps": 235, "total_steps": 58920, "loss": 0.155, "lr": 7.942973523421588e-08, "epoch": 0.019942294636795654, "percentage": 0.4, "elapsed_time": "0:00:18", "remaining_time": "1:16:39", "throughput": 12297.85, "total_tokens": 226496}
{"current_steps": 240, "total_steps": 58920, "loss": 0.1578, "lr": 8.112695179904957e-08, "epoch": 0.020366598778004074, "percentage": 0.41, "elapsed_time": "0:00:18", "remaining_time": "1:16:32", "throughput": 12282.2, "total_tokens": 230720}
{"current_steps": 245, "total_steps": 58920, "loss": 0.1882, "lr": 8.282416836388322e-08, "epoch": 0.02079090291921249, "percentage": 0.42, "elapsed_time": "0:00:19", "remaining_time": "1:16:30", "throughput": 12290.85, "total_tokens": 235584}
{"current_steps": 250, "total_steps": 58920, "loss": 0.1607, "lr": 8.45213849287169e-08, "epoch": 0.02121520706042091, "percentage": 0.42, "elapsed_time": "0:00:19", "remaining_time": "1:16:32", "throughput": 12319.06, "total_tokens": 241088}
{"current_steps": 255, "total_steps": 58920, "loss": 0.1562, "lr": 8.621860149355058e-08, "epoch": 0.021639511201629328, "percentage": 0.43, "elapsed_time": "0:00:19", "remaining_time": "1:16:29", "throughput": 12310.93, "total_tokens": 245568}
{"current_steps": 260, "total_steps": 58920, "loss": 0.1511, "lr": 8.791581805838424e-08, "epoch": 0.022063815342837745, "percentage": 0.44, "elapsed_time": "0:00:20", "remaining_time": "1:16:26", "throughput": 12312.24, "total_tokens": 250304}
{"current_steps": 265, "total_steps": 58920, "loss": 0.1549, "lr": 8.961303462321791e-08, "epoch": 0.022488119484046165, "percentage": 0.45, "elapsed_time": "0:00:20", "remaining_time": "1:16:25", "throughput": 12319.46, "total_tokens": 255232}
{"current_steps": 270, "total_steps": 58920, "loss": 0.1492, "lr": 9.13102511880516e-08, "epoch": 0.022912423625254582, "percentage": 0.46, "elapsed_time": "0:00:21", "remaining_time": "1:16:22", "throughput": 12317.1, "total_tokens": 259840}
{"current_steps": 275, "total_steps": 58920, "loss": 0.1475, "lr": 9.300746775288526e-08, "epoch": 0.023336727766463002, "percentage": 0.47, "elapsed_time": "0:00:21", "remaining_time": "1:16:21", "throughput": 12324.95, "total_tokens": 264768}
{"current_steps": 280, "total_steps": 58920, "loss": 0.148, "lr": 9.470468431771894e-08, "epoch": 0.02376103190767142, "percentage": 0.48, "elapsed_time": "0:00:21", "remaining_time": "1:16:20", "throughput": 12344.99, "total_tokens": 270016}
{"current_steps": 285, "total_steps": 58920, "loss": 0.1455, "lr": 9.640190088255261e-08, "epoch": 0.024185336048879836, "percentage": 0.48, "elapsed_time": "0:00:22", "remaining_time": "1:16:17", "throughput": 12338.04, "total_tokens": 274496}
{"current_steps": 290, "total_steps": 58920, "loss": 0.1462, "lr": 9.809911744738627e-08, "epoch": 0.024609640190088256, "percentage": 0.49, "elapsed_time": "0:00:22", "remaining_time": "1:16:15", "throughput": 12342.1, "total_tokens": 279296}
{"current_steps": 295, "total_steps": 58920, "loss": 0.1609, "lr": 9.979633401221996e-08, "epoch": 0.025033944331296673, "percentage": 0.5, "elapsed_time": "0:00:23", "remaining_time": "1:16:14", "throughput": 12350.58, "total_tokens": 284288}
{"current_steps": 300, "total_steps": 58920, "loss": 0.1414, "lr": 1.0149355057705363e-07, "epoch": 0.025458248472505093, "percentage": 0.51, "elapsed_time": "0:00:23", "remaining_time": "1:16:12", "throughput": 12353.24, "total_tokens": 289088}
{"current_steps": 305, "total_steps": 58920, "loss": 0.1485, "lr": 1.0319076714188731e-07, "epoch": 0.02588255261371351, "percentage": 0.52, "elapsed_time": "0:00:23", "remaining_time": "1:16:09", "throughput": 12348.09, "total_tokens": 293632}
{"current_steps": 310, "total_steps": 58920, "loss": 0.1491, "lr": 1.0488798370672097e-07, "epoch": 0.026306856754921927, "percentage": 0.53, "elapsed_time": "0:00:24", "remaining_time": "1:16:06", "throughput": 12344.73, "total_tokens": 298176}
{"current_steps": 315, "total_steps": 58920, "loss": 0.1584, "lr": 1.0658520027155464e-07, "epoch": 0.026731160896130347, "percentage": 0.53, "elapsed_time": "0:00:24", "remaining_time": "1:16:03", "throughput": 12341.48, "total_tokens": 302720}
{"current_steps": 320, "total_steps": 58920, "loss": 0.1284, "lr": 1.0828241683638833e-07, "epoch": 0.027155465037338764, "percentage": 0.54, "elapsed_time": "0:00:24", "remaining_time": "1:16:02", "throughput": 12348.39, "total_tokens": 307648}
{"current_steps": 325, "total_steps": 58920, "loss": 0.1347, "lr": 1.0997963340122199e-07, "epoch": 0.02757976917854718, "percentage": 0.55, "elapsed_time": "0:00:25", "remaining_time": "1:16:02", "throughput": 12360.79, "total_tokens": 312832}
{"current_steps": 330, "total_steps": 58920, "loss": 0.1287, "lr": 1.1167684996605567e-07, "epoch": 0.0280040733197556, "percentage": 0.56, "elapsed_time": "0:00:25", "remaining_time": "1:16:00", "throughput": 12356.21, "total_tokens": 317376}
{"current_steps": 335, "total_steps": 58920, "loss": 0.1131, "lr": 1.1337406653088934e-07, "epoch": 0.028428377460964018, "percentage": 0.57, "elapsed_time": "0:00:26", "remaining_time": "1:16:00", "throughput": 12369.3, "total_tokens": 322560}
{"current_steps": 340, "total_steps": 58920, "loss": 0.1388, "lr": 1.15071283095723e-07, "epoch": 0.02885268160217244, "percentage": 0.58, "elapsed_time": "0:00:26", "remaining_time": "1:15:57", "throughput": 12364.8, "total_tokens": 327104}
{"current_steps": 345, "total_steps": 58920, "loss": 0.1343, "lr": 1.1676849966055669e-07, "epoch": 0.029276985743380855, "percentage": 0.59, "elapsed_time": "0:00:26", "remaining_time": "1:15:58", "throughput": 12372.03, "total_tokens": 332160}
{"current_steps": 350, "total_steps": 58920, "loss": 0.1338, "lr": 1.1846571622539036e-07, "epoch": 0.029701289884589272, "percentage": 0.59, "elapsed_time": "0:00:27", "remaining_time": "1:15:57", "throughput": 12372.19, "total_tokens": 336960}
{"current_steps": 355, "total_steps": 58920, "loss": 0.143, "lr": 1.2016293279022404e-07, "epoch": 0.030125594025797692, "percentage": 0.6, "elapsed_time": "0:00:27", "remaining_time": "1:15:55", "throughput": 12372.83, "total_tokens": 341696}
{"current_steps": 360, "total_steps": 58920, "loss": 0.1486, "lr": 1.218601493550577e-07, "epoch": 0.03054989816700611, "percentage": 0.61, "elapsed_time": "0:00:28", "remaining_time": "1:15:56", "throughput": 12389.44, "total_tokens": 347008}
{"current_steps": 365, "total_steps": 58920, "loss": 0.1303, "lr": 1.2355736591989136e-07, "epoch": 0.03097420230821453, "percentage": 0.62, "elapsed_time": "0:00:28", "remaining_time": "1:15:56", "throughput": 12403.46, "total_tokens": 352256}
{"current_steps": 370, "total_steps": 58920, "loss": 0.1234, "lr": 1.2525458248472504e-07, "epoch": 0.03139850644942294, "percentage": 0.63, "elapsed_time": "0:00:28", "remaining_time": "1:15:55", "throughput": 12411.84, "total_tokens": 357312}
{"current_steps": 375, "total_steps": 58920, "loss": 0.1226, "lr": 1.2695179904955873e-07, "epoch": 0.03182281059063136, "percentage": 0.64, "elapsed_time": "0:00:29", "remaining_time": "1:15:53", "throughput": 12403.03, "total_tokens": 361728}
{"current_steps": 380, "total_steps": 58920, "loss": 0.1305, "lr": 1.286490156143924e-07, "epoch": 0.032247114731839784, "percentage": 0.64, "elapsed_time": "0:00:29", "remaining_time": "1:15:51", "throughput": 12406.92, "total_tokens": 366592}
{"current_steps": 385, "total_steps": 58920, "loss": 0.1614, "lr": 1.3034623217922605e-07, "epoch": 0.032671418873048204, "percentage": 0.65, "elapsed_time": "0:00:29", "remaining_time": "1:15:50", "throughput": 12409.0, "total_tokens": 371392}
{"current_steps": 390, "total_steps": 58920, "loss": 0.1319, "lr": 1.3204344874405973e-07, "epoch": 0.03309572301425662, "percentage": 0.66, "elapsed_time": "0:00:30", "remaining_time": "1:15:50", "throughput": 12420.61, "total_tokens": 376640}
{"current_steps": 395, "total_steps": 58920, "loss": 0.1727, "lr": 1.3374066530889342e-07, "epoch": 0.03352002715546504, "percentage": 0.67, "elapsed_time": "0:00:30", "remaining_time": "1:15:49", "throughput": 12423.87, "total_tokens": 381504}
{"current_steps": 400, "total_steps": 58920, "loss": 0.1345, "lr": 1.354378818737271e-07, "epoch": 0.03394433129667346, "percentage": 0.68, "elapsed_time": "0:00:31", "remaining_time": "1:15:47", "throughput": 12415.5, "total_tokens": 385920}
{"current_steps": 405, "total_steps": 58920, "loss": 0.1217, "lr": 1.3713509843856076e-07, "epoch": 0.03436863543788187, "percentage": 0.69, "elapsed_time": "0:00:31", "remaining_time": "1:15:45", "throughput": 12406.27, "total_tokens": 390272}
{"current_steps": 410, "total_steps": 58920, "loss": 0.1576, "lr": 1.3883231500339442e-07, "epoch": 0.03479293957909029, "percentage": 0.7, "elapsed_time": "0:00:31", "remaining_time": "1:15:47", "throughput": 12432.92, "total_tokens": 396160}
{"current_steps": 415, "total_steps": 58920, "loss": 0.101, "lr": 1.405295315682281e-07, "epoch": 0.03521724372029871, "percentage": 0.7, "elapsed_time": "0:00:32", "remaining_time": "1:15:45", "throughput": 12429.77, "total_tokens": 400768}
{"current_steps": 420, "total_steps": 58920, "loss": 0.1171, "lr": 1.4222674813306176e-07, "epoch": 0.035641547861507125, "percentage": 0.71, "elapsed_time": "0:00:32", "remaining_time": "1:15:44", "throughput": 12427.85, "total_tokens": 405504}
{"current_steps": 425, "total_steps": 58920, "loss": 0.1075, "lr": 1.4392396469789545e-07, "epoch": 0.036065852002715545, "percentage": 0.72, "elapsed_time": "0:00:33", "remaining_time": "1:15:43", "throughput": 12426.58, "total_tokens": 410176}
{"current_steps": 430, "total_steps": 58920, "loss": 0.1001, "lr": 1.4562118126272913e-07, "epoch": 0.036490156143923966, "percentage": 0.73, "elapsed_time": "0:00:33", "remaining_time": "1:15:41", "throughput": 12429.8, "total_tokens": 415040}
{"current_steps": 435, "total_steps": 58920, "loss": 0.0839, "lr": 1.473183978275628e-07, "epoch": 0.036914460285132386, "percentage": 0.74, "elapsed_time": "0:00:33", "remaining_time": "1:15:40", "throughput": 12434.32, "total_tokens": 419968}
{"current_steps": 440, "total_steps": 58920, "loss": 0.1083, "lr": 1.4901561439239645e-07, "epoch": 0.0373387644263408, "percentage": 0.75, "elapsed_time": "0:00:34", "remaining_time": "1:15:40", "throughput": 12436.14, "total_tokens": 424832}
{"current_steps": 445, "total_steps": 58920, "loss": 0.1508, "lr": 1.5071283095723013e-07, "epoch": 0.03776306856754922, "percentage": 0.76, "elapsed_time": "0:00:34", "remaining_time": "1:15:47", "throughput": 12483.72, "total_tokens": 432064}
{"current_steps": 450, "total_steps": 58920, "loss": 0.1073, "lr": 1.524100475220638e-07, "epoch": 0.03818737270875764, "percentage": 0.76, "elapsed_time": "0:00:35", "remaining_time": "1:15:47", "throughput": 12490.61, "total_tokens": 437184}
{"current_steps": 455, "total_steps": 58920, "loss": 0.1178, "lr": 1.5410726408689748e-07, "epoch": 0.03861167684996605, "percentage": 0.77, "elapsed_time": "0:00:35", "remaining_time": "1:15:47", "throughput": 12500.85, "total_tokens": 442432}
{"current_steps": 460, "total_steps": 58920, "loss": 0.0963, "lr": 1.5580448065173116e-07, "epoch": 0.039035980991174474, "percentage": 0.78, "elapsed_time": "0:00:35", "remaining_time": "1:15:45", "throughput": 12498.56, "total_tokens": 447040}
{"current_steps": 465, "total_steps": 58920, "loss": 0.1332, "lr": 1.5750169721656485e-07, "epoch": 0.039460285132382894, "percentage": 0.79, "elapsed_time": "0:00:36", "remaining_time": "1:15:44", "throughput": 12504.01, "total_tokens": 452032}
{"current_steps": 470, "total_steps": 58920, "loss": 0.0933, "lr": 1.5919891378139848e-07, "epoch": 0.03988458927359131, "percentage": 0.8, "elapsed_time": "0:00:36", "remaining_time": "1:15:45", "throughput": 12513.64, "total_tokens": 457344}
{"current_steps": 475, "total_steps": 58920, "loss": 0.1145, "lr": 1.6089613034623216e-07, "epoch": 0.04030889341479973, "percentage": 0.81, "elapsed_time": "0:00:36", "remaining_time": "1:15:44", "throughput": 12518.14, "total_tokens": 462336}
{"current_steps": 480, "total_steps": 58920, "loss": 0.1216, "lr": 1.6259334691106585e-07, "epoch": 0.04073319755600815, "percentage": 0.81, "elapsed_time": "0:00:37", "remaining_time": "1:15:43", "throughput": 12516.89, "total_tokens": 467072}
{"current_steps": 485, "total_steps": 58920, "loss": 0.107, "lr": 1.642905634758995e-07, "epoch": 0.04115750169721656, "percentage": 0.82, "elapsed_time": "0:00:37", "remaining_time": "1:15:41", "throughput": 12512.48, "total_tokens": 471616}
{"current_steps": 490, "total_steps": 58920, "loss": 0.0967, "lr": 1.659877800407332e-07, "epoch": 0.04158180583842498, "percentage": 0.83, "elapsed_time": "0:00:38", "remaining_time": "1:15:40", "throughput": 12514.43, "total_tokens": 476480}
{"current_steps": 495, "total_steps": 58920, "loss": 0.1191, "lr": 1.6768499660556688e-07, "epoch": 0.0420061099796334, "percentage": 0.84, "elapsed_time": "0:00:38", "remaining_time": "1:15:39", "throughput": 12519.37, "total_tokens": 481536}
{"current_steps": 500, "total_steps": 58920, "loss": 0.1348, "lr": 1.6938221317040054e-07, "epoch": 0.04243041412084182, "percentage": 0.85, "elapsed_time": "0:00:38", "remaining_time": "1:15:38", "throughput": 12519.72, "total_tokens": 486336}
{"current_steps": 505, "total_steps": 58920, "loss": 0.0997, "lr": 1.710794297352342e-07, "epoch": 0.042854718262050236, "percentage": 0.86, "elapsed_time": "0:00:39", "remaining_time": "1:15:37", "throughput": 12516.79, "total_tokens": 490944}
{"current_steps": 510, "total_steps": 58920, "loss": 0.0911, "lr": 1.7277664630006788e-07, "epoch": 0.043279022403258656, "percentage": 0.87, "elapsed_time": "0:00:39", "remaining_time": "1:15:35", "throughput": 12512.38, "total_tokens": 495488}
{"current_steps": 515, "total_steps": 58920, "loss": 0.1301, "lr": 1.7447386286490156e-07, "epoch": 0.043703326544467076, "percentage": 0.87, "elapsed_time": "0:00:39", "remaining_time": "1:15:33", "throughput": 12504.47, "total_tokens": 499840}
{"current_steps": 520, "total_steps": 58920, "loss": 0.1231, "lr": 1.7617107942973522e-07, "epoch": 0.04412763068567549, "percentage": 0.88, "elapsed_time": "0:00:40", "remaining_time": "1:15:31", "throughput": 12503.23, "total_tokens": 504512}
{"current_steps": 525, "total_steps": 58920, "loss": 0.0942, "lr": 1.778682959945689e-07, "epoch": 0.04455193482688391, "percentage": 0.89, "elapsed_time": "0:00:40", "remaining_time": "1:15:30", "throughput": 12505.02, "total_tokens": 509376}
{"current_steps": 530, "total_steps": 58920, "loss": 0.101, "lr": 1.795655125594026e-07, "epoch": 0.04497623896809233, "percentage": 0.9, "elapsed_time": "0:00:41", "remaining_time": "1:15:29", "throughput": 12499.6, "total_tokens": 513856}
{"current_steps": 535, "total_steps": 58920, "loss": 0.1023, "lr": 1.8126272912423622e-07, "epoch": 0.045400543109300744, "percentage": 0.91, "elapsed_time": "0:00:41", "remaining_time": "1:15:29", "throughput": 12504.36, "total_tokens": 518976}
{"current_steps": 540, "total_steps": 58920, "loss": 0.0578, "lr": 1.829599456890699e-07, "epoch": 0.045824847250509164, "percentage": 0.92, "elapsed_time": "0:00:41", "remaining_time": "1:15:29", "throughput": 12510.19, "total_tokens": 524160}
{"current_steps": 545, "total_steps": 58920, "loss": 0.1398, "lr": 1.846571622539036e-07, "epoch": 0.046249151391717584, "percentage": 0.92, "elapsed_time": "0:00:42", "remaining_time": "1:15:29", "throughput": 12513.71, "total_tokens": 529152}
{"current_steps": 550, "total_steps": 58920, "loss": 0.1645, "lr": 1.8635437881873725e-07, "epoch": 0.046673455532926005, "percentage": 0.93, "elapsed_time": "0:00:42", "remaining_time": "1:15:27", "throughput": 12513.07, "total_tokens": 533824}
{"current_steps": 555, "total_steps": 58920, "loss": 0.1281, "lr": 1.8805159538357094e-07, "epoch": 0.04709775967413442, "percentage": 0.94, "elapsed_time": "0:00:43", "remaining_time": "1:15:26", "throughput": 12512.05, "total_tokens": 538560}
{"current_steps": 560, "total_steps": 58920, "loss": 0.1303, "lr": 1.8974881194840462e-07, "epoch": 0.04752206381534284, "percentage": 0.95, "elapsed_time": "0:00:43", "remaining_time": "1:15:24", "throughput": 12502.6, "total_tokens": 542784}
{"current_steps": 565, "total_steps": 58920, "loss": 0.1161, "lr": 1.9144602851323825e-07, "epoch": 0.04794636795655126, "percentage": 0.96, "elapsed_time": "0:00:43", "remaining_time": "1:15:23", "throughput": 12507.79, "total_tokens": 547840}
{"current_steps": 570, "total_steps": 58920, "loss": 0.0964, "lr": 1.9314324507807194e-07, "epoch": 0.04837067209775967, "percentage": 0.97, "elapsed_time": "0:00:44", "remaining_time": "1:15:22", "throughput": 12505.97, "total_tokens": 552448}
{"current_steps": 575, "total_steps": 58920, "loss": 0.1339, "lr": 1.9484046164290562e-07, "epoch": 0.04879497623896809, "percentage": 0.98, "elapsed_time": "0:00:44", "remaining_time": "1:15:20", "throughput": 12504.7, "total_tokens": 557120}
{"current_steps": 580, "total_steps": 58920, "loss": 0.1407, "lr": 1.965376782077393e-07, "epoch": 0.04921928038017651, "percentage": 0.98, "elapsed_time": "0:00:44", "remaining_time": "1:15:18", "throughput": 12499.11, "total_tokens": 561536}
{"current_steps": 585, "total_steps": 58920, "loss": 0.0563, "lr": 1.9823489477257297e-07, "epoch": 0.049643584521384926, "percentage": 0.99, "elapsed_time": "0:00:45", "remaining_time": "1:15:18", "throughput": 12499.06, "total_tokens": 566336}
{"current_steps": 590, "total_steps": 58920, "loss": 0.1164, "lr": 1.9993211133740665e-07, "epoch": 0.050067888662593346, "percentage": 1.0, "elapsed_time": "0:00:45", "remaining_time": "1:15:16", "throughput": 12499.25, "total_tokens": 571072}
{"current_steps": 595, "total_steps": 58920, "loss": 0.0618, "lr": 2.0162932790224034e-07, "epoch": 0.050492192803801766, "percentage": 1.01, "elapsed_time": "0:00:46", "remaining_time": "1:15:16", "throughput": 12504.97, "total_tokens": 576192}
{"current_steps": 600, "total_steps": 58920, "loss": 0.1309, "lr": 2.0332654446707397e-07, "epoch": 0.05091649694501019, "percentage": 1.02, "elapsed_time": "0:00:46", "remaining_time": "1:15:15", "throughput": 12504.34, "total_tokens": 580928}
{"current_steps": 605, "total_steps": 58920, "loss": 0.1254, "lr": 2.0502376103190766e-07, "epoch": 0.0513408010862186, "percentage": 1.03, "elapsed_time": "0:00:46", "remaining_time": "1:15:14", "throughput": 12504.98, "total_tokens": 585728}
{"current_steps": 610, "total_steps": 58920, "loss": 0.0694, "lr": 2.0672097759674134e-07, "epoch": 0.05176510522742702, "percentage": 1.04, "elapsed_time": "0:00:47", "remaining_time": "1:15:15", "throughput": 12512.15, "total_tokens": 591040}
{"current_steps": 615, "total_steps": 58920, "loss": 0.1455, "lr": 2.08418194161575e-07, "epoch": 0.05218940936863544, "percentage": 1.04, "elapsed_time": "0:00:47", "remaining_time": "1:15:13", "throughput": 12509.21, "total_tokens": 595584}
{"current_steps": 620, "total_steps": 58920, "loss": 0.1226, "lr": 2.1011541072640868e-07, "epoch": 0.052613713509843854, "percentage": 1.05, "elapsed_time": "0:00:47", "remaining_time": "1:15:13", "throughput": 12509.4, "total_tokens": 600384}
{"current_steps": 625, "total_steps": 58920, "loss": 0.1016, "lr": 2.1181262729124237e-07, "epoch": 0.053038017651052274, "percentage": 1.06, "elapsed_time": "0:00:48", "remaining_time": "1:15:12", "throughput": 12510.0, "total_tokens": 605248}
{"current_steps": 630, "total_steps": 58920, "loss": 0.0921, "lr": 2.1350984385607603e-07, "epoch": 0.053462321792260695, "percentage": 1.07, "elapsed_time": "0:00:48", "remaining_time": "1:15:11", "throughput": 12506.95, "total_tokens": 609856}
{"current_steps": 635, "total_steps": 58920, "loss": 0.0801, "lr": 2.1520706042090969e-07, "epoch": 0.05388662593346911, "percentage": 1.08, "elapsed_time": "0:00:49", "remaining_time": "1:15:11", "throughput": 12512.79, "total_tokens": 614976}
{"current_steps": 640, "total_steps": 58920, "loss": 0.1061, "lr": 2.1690427698574337e-07, "epoch": 0.05431093007467753, "percentage": 1.09, "elapsed_time": "0:00:49", "remaining_time": "1:15:10", "throughput": 12511.37, "total_tokens": 619648}
{"current_steps": 645, "total_steps": 58920, "loss": 0.0882, "lr": 2.1860149355057706e-07, "epoch": 0.05473523421588595, "percentage": 1.09, "elapsed_time": "0:00:49", "remaining_time": "1:15:09", "throughput": 12518.67, "total_tokens": 624896}
{"current_steps": 650, "total_steps": 58920, "loss": 0.1271, "lr": 2.2029871011541071e-07, "epoch": 0.05515953835709436, "percentage": 1.1, "elapsed_time": "0:00:50", "remaining_time": "1:15:08", "throughput": 12518.71, "total_tokens": 629632}
{"current_steps": 655, "total_steps": 58920, "loss": 0.1189, "lr": 2.219959266802444e-07, "epoch": 0.05558384249830278, "percentage": 1.11, "elapsed_time": "0:00:50", "remaining_time": "1:15:08", "throughput": 12521.06, "total_tokens": 634624}
{"current_steps": 660, "total_steps": 58920, "loss": 0.1647, "lr": 2.2369314324507806e-07, "epoch": 0.0560081466395112, "percentage": 1.12, "elapsed_time": "0:00:51", "remaining_time": "1:15:07", "throughput": 12519.97, "total_tokens": 639360}
{"current_steps": 665, "total_steps": 58920, "loss": 0.0933, "lr": 2.2539035980991172e-07, "epoch": 0.05643245078071962, "percentage": 1.13, "elapsed_time": "0:00:51", "remaining_time": "1:15:06", "throughput": 12518.2, "total_tokens": 644032}
{"current_steps": 670, "total_steps": 58920, "loss": 0.0896, "lr": 2.270875763747454e-07, "epoch": 0.056856754921928036, "percentage": 1.14, "elapsed_time": "0:00:51", "remaining_time": "1:15:04", "throughput": 12510.44, "total_tokens": 648256}
{"current_steps": 675, "total_steps": 58920, "loss": 0.0969, "lr": 2.2878479293957909e-07, "epoch": 0.05728105906313646, "percentage": 1.15, "elapsed_time": "0:00:52", "remaining_time": "1:15:04", "throughput": 12510.95, "total_tokens": 653056}
{"current_steps": 680, "total_steps": 58920, "loss": 0.1041, "lr": 2.3048200950441274e-07, "epoch": 0.05770536320434488, "percentage": 1.15, "elapsed_time": "0:00:52", "remaining_time": "1:15:02", "throughput": 12509.35, "total_tokens": 657664}
{"current_steps": 685, "total_steps": 58920, "loss": 0.0619, "lr": 2.3217922606924643e-07, "epoch": 0.05812966734555329, "percentage": 1.16, "elapsed_time": "0:00:52", "remaining_time": "1:15:01", "throughput": 12503.69, "total_tokens": 662016}
{"current_steps": 690, "total_steps": 58920, "loss": 0.1002, "lr": 2.3387644263408011e-07, "epoch": 0.05855397148676171, "percentage": 1.17, "elapsed_time": "0:00:53", "remaining_time": "1:14:59", "throughput": 12497.81, "total_tokens": 666368}
{"current_steps": 695, "total_steps": 58920, "loss": 0.1112, "lr": 2.3557365919891377e-07, "epoch": 0.05897827562797013, "percentage": 1.18, "elapsed_time": "0:00:53", "remaining_time": "1:14:59", "throughput": 12503.76, "total_tokens": 671616}
{"current_steps": 700, "total_steps": 58920, "loss": 0.0712, "lr": 2.3727087576374743e-07, "epoch": 0.059402579769178544, "percentage": 1.19, "elapsed_time": "0:00:54", "remaining_time": "1:14:59", "throughput": 12502.23, "total_tokens": 676288}
{"current_steps": 705, "total_steps": 58920, "loss": 0.0998, "lr": 2.389680923285811e-07, "epoch": 0.059826883910386965, "percentage": 1.2, "elapsed_time": "0:00:54", "remaining_time": "1:14:58", "throughput": 12500.12, "total_tokens": 680960}
{"current_steps": 710, "total_steps": 58920, "loss": 0.0711, "lr": 2.406653088934148e-07, "epoch": 0.060251188051595385, "percentage": 1.21, "elapsed_time": "0:00:54", "remaining_time": "1:14:57", "throughput": 12495.19, "total_tokens": 685440}
{"current_steps": 715, "total_steps": 58920, "loss": 0.0986, "lr": 2.4236252545824843e-07, "epoch": 0.060675492192803805, "percentage": 1.21, "elapsed_time": "0:00:55", "remaining_time": "1:14:57", "throughput": 12495.77, "total_tokens": 690304}
{"current_steps": 720, "total_steps": 58920, "loss": 0.0945, "lr": 2.440597420230821e-07, "epoch": 0.06109979633401222, "percentage": 1.22, "elapsed_time": "0:00:55", "remaining_time": "1:14:56", "throughput": 12495.91, "total_tokens": 695040}
{"current_steps": 725, "total_steps": 58920, "loss": 0.0729, "lr": 2.457569585879158e-07, "epoch": 0.06152410047522064, "percentage": 1.23, "elapsed_time": "0:00:55", "remaining_time": "1:14:54", "throughput": 12491.17, "total_tokens": 699456}
{"current_steps": 730, "total_steps": 58920, "loss": 0.1192, "lr": 2.474541751527495e-07, "epoch": 0.06194840461642906, "percentage": 1.24, "elapsed_time": "0:00:56", "remaining_time": "1:14:53", "throughput": 12488.63, "total_tokens": 704064}
{"current_steps": 735, "total_steps": 58920, "loss": 0.0626, "lr": 2.4915139171758317e-07, "epoch": 0.06237270875763747, "percentage": 1.25, "elapsed_time": "0:00:56", "remaining_time": "1:14:52", "throughput": 12484.94, "total_tokens": 708544}
{"current_steps": 740, "total_steps": 58920, "loss": 0.1557, "lr": 2.508486082824168e-07, "epoch": 0.06279701289884589, "percentage": 1.26, "elapsed_time": "0:00:57", "remaining_time": "1:14:51", "throughput": 12481.56, "total_tokens": 713088}
{"current_steps": 745, "total_steps": 58920, "loss": 0.1232, "lr": 2.525458248472505e-07, "epoch": 0.0632213170400543, "percentage": 1.26, "elapsed_time": "0:00:57", "remaining_time": "1:14:51", "throughput": 12483.73, "total_tokens": 718016}
{"current_steps": 750, "total_steps": 58920, "loss": 0.0623, "lr": 2.542430414120842e-07, "epoch": 0.06364562118126273, "percentage": 1.27, "elapsed_time": "0:00:57", "remaining_time": "1:14:50", "throughput": 12483.11, "total_tokens": 722752}
{"current_steps": 755, "total_steps": 58920, "loss": 0.1044, "lr": 2.559402579769178e-07, "epoch": 0.06406992532247115, "percentage": 1.28, "elapsed_time": "0:00:58", "remaining_time": "1:14:50", "throughput": 12487.64, "total_tokens": 727872}
{"current_steps": 760, "total_steps": 58920, "loss": 0.0923, "lr": 2.576374745417515e-07, "epoch": 0.06449422946367957, "percentage": 1.29, "elapsed_time": "0:00:58", "remaining_time": "1:14:49", "throughput": 12486.21, "total_tokens": 732480}
{"current_steps": 765, "total_steps": 58920, "loss": 0.0754, "lr": 2.593346911065852e-07, "epoch": 0.06491853360488799, "percentage": 1.3, "elapsed_time": "0:00:59", "remaining_time": "1:14:47", "throughput": 12479.47, "total_tokens": 736704}
{"current_steps": 770, "total_steps": 58920, "loss": 0.0617, "lr": 2.6103190767141886e-07, "epoch": 0.06534283774609641, "percentage": 1.31, "elapsed_time": "0:00:59", "remaining_time": "1:14:49", "throughput": 12494.63, "total_tokens": 742848}
{"current_steps": 775, "total_steps": 58920, "loss": 0.0998, "lr": 2.6272912423625255e-07, "epoch": 0.06576714188730481, "percentage": 1.32, "elapsed_time": "0:00:59", "remaining_time": "1:14:48", "throughput": 12487.62, "total_tokens": 747072}
{"current_steps": 780, "total_steps": 58920, "loss": 0.0611, "lr": 2.6442634080108623e-07, "epoch": 0.06619144602851323, "percentage": 1.32, "elapsed_time": "0:01:00", "remaining_time": "1:14:47", "throughput": 12487.37, "total_tokens": 751808}
{"current_steps": 785, "total_steps": 58920, "loss": 0.0802, "lr": 2.661235573659199e-07, "epoch": 0.06661575016972165, "percentage": 1.33, "elapsed_time": "0:01:00", "remaining_time": "1:14:47", "throughput": 12489.89, "total_tokens": 756800}
{"current_steps": 790, "total_steps": 58920, "loss": 0.1115, "lr": 2.6782077393075355e-07, "epoch": 0.06704005431093008, "percentage": 1.34, "elapsed_time": "0:01:00", "remaining_time": "1:14:46", "throughput": 12490.11, "total_tokens": 761536}
{"current_steps": 795, "total_steps": 58920, "loss": 0.1041, "lr": 2.6951799049558723e-07, "epoch": 0.0674643584521385, "percentage": 1.35, "elapsed_time": "0:01:01", "remaining_time": "1:14:45", "throughput": 12484.01, "total_tokens": 765824}
{"current_steps": 800, "total_steps": 58920, "loss": 0.1324, "lr": 2.712152070604209e-07, "epoch": 0.06788866259334692, "percentage": 1.36, "elapsed_time": "0:01:01", "remaining_time": "1:14:43", "throughput": 12480.0, "total_tokens": 770240}
{"current_steps": 805, "total_steps": 58920, "loss": 0.1325, "lr": 2.7291242362525455e-07, "epoch": 0.06831296673455534, "percentage": 1.37, "elapsed_time": "0:01:02", "remaining_time": "1:14:43", "throughput": 12484.58, "total_tokens": 775424}
{"current_steps": 810, "total_steps": 58920, "loss": 0.1042, "lr": 2.7460964019008824e-07, "epoch": 0.06873727087576374, "percentage": 1.37, "elapsed_time": "0:01:02", "remaining_time": "1:14:43", "throughput": 12480.62, "total_tokens": 779904}
{"current_steps": 815, "total_steps": 58920, "loss": 0.0682, "lr": 2.763068567549219e-07, "epoch": 0.06916157501697216, "percentage": 1.38, "elapsed_time": "0:01:02", "remaining_time": "1:14:42", "throughput": 12479.03, "total_tokens": 784512}
{"current_steps": 820, "total_steps": 58920, "loss": 0.0915, "lr": 2.7800407331975555e-07, "epoch": 0.06958587915818058, "percentage": 1.39, "elapsed_time": "0:01:03", "remaining_time": "1:14:41", "throughput": 12480.44, "total_tokens": 789440}
{"current_steps": 825, "total_steps": 58920, "loss": 0.1285, "lr": 2.7970128988458924e-07, "epoch": 0.070010183299389, "percentage": 1.4, "elapsed_time": "0:01:03", "remaining_time": "1:14:41", "throughput": 12481.07, "total_tokens": 794240}
{"current_steps": 830, "total_steps": 58920, "loss": 0.1246, "lr": 2.813985064494229e-07, "epoch": 0.07043448744059742, "percentage": 1.41, "elapsed_time": "0:01:04", "remaining_time": "1:14:39", "throughput": 12476.39, "total_tokens": 798592}
{"current_steps": 835, "total_steps": 58920, "loss": 0.1209, "lr": 2.830957230142566e-07, "epoch": 0.07085879158180584, "percentage": 1.42, "elapsed_time": "0:01:04", "remaining_time": "1:14:39", "throughput": 12480.9, "total_tokens": 803776}
{"current_steps": 840, "total_steps": 58920, "loss": 0.0957, "lr": 2.847929395790903e-07, "epoch": 0.07128309572301425, "percentage": 1.43, "elapsed_time": "0:01:04", "remaining_time": "1:14:39", "throughput": 12487.26, "total_tokens": 809088}
{"current_steps": 845, "total_steps": 58920, "loss": 0.0735, "lr": 2.86490156143924e-07, "epoch": 0.07170739986422267, "percentage": 1.43, "elapsed_time": "0:01:05", "remaining_time": "1:14:39", "throughput": 12487.21, "total_tokens": 813824}
{"current_steps": 850, "total_steps": 58920, "loss": 0.0772, "lr": 2.8818737270875766e-07, "epoch": 0.07213170400543109, "percentage": 1.44, "elapsed_time": "0:01:05", "remaining_time": "1:14:37", "throughput": 12483.49, "total_tokens": 818240}
{"current_steps": 855, "total_steps": 58920, "loss": 0.1177, "lr": 2.898845892735913e-07, "epoch": 0.07255600814663951, "percentage": 1.45, "elapsed_time": "0:01:05", "remaining_time": "1:14:36", "throughput": 12476.77, "total_tokens": 822400}
{"current_steps": 860, "total_steps": 58920, "loss": 0.1027, "lr": 2.91581805838425e-07, "epoch": 0.07298031228784793, "percentage": 1.46, "elapsed_time": "0:01:06", "remaining_time": "1:14:36", "throughput": 12478.49, "total_tokens": 827328}
{"current_steps": 865, "total_steps": 58920, "loss": 0.1483, "lr": 2.932790224032586e-07, "epoch": 0.07340461642905635, "percentage": 1.47, "elapsed_time": "0:01:06", "remaining_time": "1:14:35", "throughput": 12480.86, "total_tokens": 832320}
{"current_steps": 870, "total_steps": 58920, "loss": 0.0978, "lr": 2.949762389680923e-07, "epoch": 0.07382892057026477, "percentage": 1.48, "elapsed_time": "0:01:07", "remaining_time": "1:14:35", "throughput": 12483.62, "total_tokens": 837376}
{"current_steps": 875, "total_steps": 58920, "loss": 0.0891, "lr": 2.96673455532926e-07, "epoch": 0.07425322471147318, "percentage": 1.49, "elapsed_time": "0:01:07", "remaining_time": "1:14:36", "throughput": 12492.19, "total_tokens": 843008}
{"current_steps": 880, "total_steps": 58920, "loss": 0.1419, "lr": 2.9837067209775967e-07, "epoch": 0.0746775288526816, "percentage": 1.49, "elapsed_time": "0:01:07", "remaining_time": "1:14:35", "throughput": 12491.04, "total_tokens": 847680}
{"current_steps": 885, "total_steps": 58920, "loss": 0.1057, "lr": 3.0006788866259335e-07, "epoch": 0.07510183299389002, "percentage": 1.5, "elapsed_time": "0:01:08", "remaining_time": "1:14:34", "throughput": 12489.7, "total_tokens": 852288}
{"current_steps": 890, "total_steps": 58920, "loss": 0.086, "lr": 3.01765105227427e-07, "epoch": 0.07552613713509844, "percentage": 1.51, "elapsed_time": "0:01:08", "remaining_time": "1:14:34", "throughput": 12492.24, "total_tokens": 857280}
{"current_steps": 895, "total_steps": 58920, "loss": 0.0894, "lr": 3.0346232179226067e-07, "epoch": 0.07595044127630686, "percentage": 1.52, "elapsed_time": "0:01:09", "remaining_time": "1:14:33", "throughput": 12492.34, "total_tokens": 862080}
{"current_steps": 900, "total_steps": 58920, "loss": 0.1257, "lr": 3.0515953835709435e-07, "epoch": 0.07637474541751528, "percentage": 1.53, "elapsed_time": "0:01:09", "remaining_time": "1:14:32", "throughput": 12490.8, "total_tokens": 866624}
{"current_steps": 905, "total_steps": 58920, "loss": 0.0888, "lr": 3.0685675492192804e-07, "epoch": 0.07679904955872369, "percentage": 1.54, "elapsed_time": "0:01:09", "remaining_time": "1:14:31", "throughput": 12490.79, "total_tokens": 871360}
{"current_steps": 910, "total_steps": 58920, "loss": 0.1423, "lr": 3.085539714867617e-07, "epoch": 0.0772233536999321, "percentage": 1.54, "elapsed_time": "0:01:10", "remaining_time": "1:14:33", "throughput": 12505.83, "total_tokens": 877632}
{"current_steps": 915, "total_steps": 58920, "loss": 0.0796, "lr": 3.102511880515954e-07, "epoch": 0.07764765784114053, "percentage": 1.55, "elapsed_time": "0:01:10", "remaining_time": "1:14:32", "throughput": 12497.17, "total_tokens": 881600}
{"current_steps": 920, "total_steps": 58920, "loss": 0.1092, "lr": 3.1194840461642904e-07, "epoch": 0.07807196198234895, "percentage": 1.56, "elapsed_time": "0:01:10", "remaining_time": "1:14:31", "throughput": 12497.83, "total_tokens": 886400}
{"current_steps": 925, "total_steps": 58920, "loss": 0.0809, "lr": 3.136456211812627e-07, "epoch": 0.07849626612355737, "percentage": 1.57, "elapsed_time": "0:01:11", "remaining_time": "1:14:30", "throughput": 12494.66, "total_tokens": 890880}
{"current_steps": 930, "total_steps": 58920, "loss": 0.0902, "lr": 3.1534283774609636e-07, "epoch": 0.07892057026476579, "percentage": 1.58, "elapsed_time": "0:01:11", "remaining_time": "1:14:29", "throughput": 12495.73, "total_tokens": 895744}
{"current_steps": 935, "total_steps": 58920, "loss": 0.1039, "lr": 3.1704005431093004e-07, "epoch": 0.07934487440597421, "percentage": 1.59, "elapsed_time": "0:01:12", "remaining_time": "1:14:28", "throughput": 12492.76, "total_tokens": 900224}
{"current_steps": 940, "total_steps": 58920, "loss": 0.0473, "lr": 3.187372708757637e-07, "epoch": 0.07976917854718261, "percentage": 1.6, "elapsed_time": "0:01:12", "remaining_time": "1:14:28", "throughput": 12495.33, "total_tokens": 905280}
{"current_steps": 945, "total_steps": 58920, "loss": 0.072, "lr": 3.204344874405974e-07, "epoch": 0.08019348268839104, "percentage": 1.6, "elapsed_time": "0:01:12", "remaining_time": "1:14:28", "throughput": 12498.53, "total_tokens": 910336}
{"current_steps": 950, "total_steps": 58920, "loss": 0.068, "lr": 3.221317040054311e-07, "epoch": 0.08061778682959946, "percentage": 1.61, "elapsed_time": "0:01:13", "remaining_time": "1:14:29", "throughput": 12504.2, "total_tokens": 915776}
{"current_steps": 955, "total_steps": 58920, "loss": 0.0754, "lr": 3.2382892057026473e-07, "epoch": 0.08104209097080788, "percentage": 1.62, "elapsed_time": "0:01:13", "remaining_time": "1:14:28", "throughput": 12503.65, "total_tokens": 920512}
{"current_steps": 960, "total_steps": 58920, "loss": 0.1031, "lr": 3.255261371350984e-07, "epoch": 0.0814663951120163, "percentage": 1.63, "elapsed_time": "0:01:13", "remaining_time": "1:14:27", "throughput": 12500.52, "total_tokens": 924992}
{"current_steps": 965, "total_steps": 58920, "loss": 0.1285, "lr": 3.272233536999321e-07, "epoch": 0.08189069925322472, "percentage": 1.64, "elapsed_time": "0:01:14", "remaining_time": "1:14:27", "throughput": 12500.6, "total_tokens": 929792}
{"current_steps": 970, "total_steps": 58920, "loss": 0.1453, "lr": 3.289205702647658e-07, "epoch": 0.08231500339443312, "percentage": 1.65, "elapsed_time": "0:01:14", "remaining_time": "1:14:26", "throughput": 12496.91, "total_tokens": 934208}
{"current_steps": 975, "total_steps": 58920, "loss": 0.0797, "lr": 3.3061778682959947e-07, "epoch": 0.08273930753564154, "percentage": 1.65, "elapsed_time": "0:01:15", "remaining_time": "1:14:24", "throughput": 12493.5, "total_tokens": 938624}
{"current_steps": 980, "total_steps": 58920, "loss": 0.0373, "lr": 3.3231500339443315e-07, "epoch": 0.08316361167684996, "percentage": 1.66, "elapsed_time": "0:01:15", "remaining_time": "1:14:24", "throughput": 12491.18, "total_tokens": 943168}
{"current_steps": 985, "total_steps": 58920, "loss": 0.097, "lr": 3.340122199592668e-07, "epoch": 0.08358791581805838, "percentage": 1.67, "elapsed_time": "0:01:15", "remaining_time": "1:14:23", "throughput": 12492.59, "total_tokens": 948032}
{"current_steps": 990, "total_steps": 58920, "loss": 0.1016, "lr": 3.357094365241004e-07, "epoch": 0.0840122199592668, "percentage": 1.68, "elapsed_time": "0:01:16", "remaining_time": "1:14:24", "throughput": 12505.32, "total_tokens": 954176}
{"current_steps": 995, "total_steps": 58920, "loss": 0.0802, "lr": 3.374066530889341e-07, "epoch": 0.08443652410047522, "percentage": 1.69, "elapsed_time": "0:01:16", "remaining_time": "1:14:24", "throughput": 12504.76, "total_tokens": 958912}
{"current_steps": 1000, "total_steps": 58920, "loss": 0.1573, "lr": 3.391038696537678e-07, "epoch": 0.08486082824168364, "percentage": 1.7, "elapsed_time": "0:01:17", "remaining_time": "1:14:23", "throughput": 12500.39, "total_tokens": 963264}
{"current_steps": 1005, "total_steps": 58920, "loss": 0.0871, "lr": 3.4080108621860147e-07, "epoch": 0.08528513238289205, "percentage": 1.71, "elapsed_time": "0:01:17", "remaining_time": "1:14:22", "throughput": 12502.26, "total_tokens": 968256}
{"current_steps": 1010, "total_steps": 58920, "loss": 0.0702, "lr": 3.4249830278343516e-07, "epoch": 0.08570943652410047, "percentage": 1.71, "elapsed_time": "0:01:17", "remaining_time": "1:14:21", "throughput": 12498.33, "total_tokens": 972608}
{"current_steps": 1015, "total_steps": 58920, "loss": 0.0636, "lr": 3.4419551934826884e-07, "epoch": 0.08613374066530889, "percentage": 1.72, "elapsed_time": "0:01:18", "remaining_time": "1:14:21", "throughput": 12503.02, "total_tokens": 977856}
{"current_steps": 1020, "total_steps": 58920, "loss": 0.0967, "lr": 3.458927359131025e-07, "epoch": 0.08655804480651731, "percentage": 1.73, "elapsed_time": "0:01:18", "remaining_time": "1:14:21", "throughput": 12503.83, "total_tokens": 982720}
{"current_steps": 1025, "total_steps": 58920, "loss": 0.1358, "lr": 3.4758995247793616e-07, "epoch": 0.08698234894772573, "percentage": 1.74, "elapsed_time": "0:01:18", "remaining_time": "1:14:20", "throughput": 12504.52, "total_tokens": 987584}
{"current_steps": 1030, "total_steps": 58920, "loss": 0.1627, "lr": 3.4928716904276984e-07, "epoch": 0.08740665308893415, "percentage": 1.75, "elapsed_time": "0:01:19", "remaining_time": "1:14:20", "throughput": 12505.31, "total_tokens": 992448}
{"current_steps": 1035, "total_steps": 58920, "loss": 0.1005, "lr": 3.5098438560760353e-07, "epoch": 0.08783095723014257, "percentage": 1.76, "elapsed_time": "0:01:19", "remaining_time": "1:14:19", "throughput": 12505.33, "total_tokens": 997184}
{"current_steps": 1040, "total_steps": 58920, "loss": 0.1252, "lr": 3.526816021724372e-07, "epoch": 0.08825526137135098, "percentage": 1.77, "elapsed_time": "0:01:20", "remaining_time": "1:14:19", "throughput": 12509.43, "total_tokens": 1002432}
{"current_steps": 1045, "total_steps": 58920, "loss": 0.0698, "lr": 3.543788187372709e-07, "epoch": 0.0886795655125594, "percentage": 1.77, "elapsed_time": "0:01:20", "remaining_time": "1:14:19", "throughput": 12510.67, "total_tokens": 1007360}
{"current_steps": 1050, "total_steps": 58920, "loss": 0.0621, "lr": 3.5607603530210453e-07, "epoch": 0.08910386965376782, "percentage": 1.78, "elapsed_time": "0:01:20", "remaining_time": "1:14:18", "throughput": 12509.22, "total_tokens": 1011968}
{"current_steps": 1055, "total_steps": 58920, "loss": 0.0652, "lr": 3.5777325186693816e-07, "epoch": 0.08952817379497624, "percentage": 1.79, "elapsed_time": "0:01:21", "remaining_time": "1:14:18", "throughput": 12510.69, "total_tokens": 1016896}
{"current_steps": 1060, "total_steps": 58920, "loss": 0.0537, "lr": 3.5947046843177185e-07, "epoch": 0.08995247793618466, "percentage": 1.8, "elapsed_time": "0:01:21", "remaining_time": "1:14:18", "throughput": 12512.87, "total_tokens": 1021952}
{"current_steps": 1065, "total_steps": 58920, "loss": 0.121, "lr": 3.6116768499660553e-07, "epoch": 0.09037678207739308, "percentage": 1.81, "elapsed_time": "0:01:22", "remaining_time": "1:14:17", "throughput": 12510.84, "total_tokens": 1026560}
{"current_steps": 1070, "total_steps": 58920, "loss": 0.0645, "lr": 3.628649015614392e-07, "epoch": 0.09080108621860149, "percentage": 1.82, "elapsed_time": "0:01:22", "remaining_time": "1:14:16", "throughput": 12511.04, "total_tokens": 1031360}
{"current_steps": 1075, "total_steps": 58920, "loss": 0.0966, "lr": 3.645621181262729e-07, "epoch": 0.09122539035980991, "percentage": 1.82, "elapsed_time": "0:01:22", "remaining_time": "1:14:16", "throughput": 12513.95, "total_tokens": 1036480}
{"current_steps": 1080, "total_steps": 58920, "loss": 0.1524, "lr": 3.662593346911066e-07, "epoch": 0.09164969450101833, "percentage": 1.83, "elapsed_time": "0:01:23", "remaining_time": "1:14:16", "throughput": 12511.73, "total_tokens": 1041024}
{"current_steps": 1085, "total_steps": 58920, "loss": 0.0891, "lr": 3.679565512559402e-07, "epoch": 0.09207399864222675, "percentage": 1.84, "elapsed_time": "0:01:23", "remaining_time": "1:14:14", "throughput": 12507.18, "total_tokens": 1045312}
{"current_steps": 1090, "total_steps": 58920, "loss": 0.0788, "lr": 3.696537678207739e-07, "epoch": 0.09249830278343517, "percentage": 1.85, "elapsed_time": "0:01:23", "remaining_time": "1:14:14", "throughput": 12508.43, "total_tokens": 1050240}
{"current_steps": 1095, "total_steps": 58920, "loss": 0.114, "lr": 3.713509843856076e-07, "epoch": 0.09292260692464359, "percentage": 1.86, "elapsed_time": "0:01:24", "remaining_time": "1:14:15", "throughput": 12513.83, "total_tokens": 1055744}
{"current_steps": 1100, "total_steps": 58920, "loss": 0.0807, "lr": 3.730482009504413e-07, "epoch": 0.09334691106585201, "percentage": 1.87, "elapsed_time": "0:01:24", "remaining_time": "1:14:14", "throughput": 12511.74, "total_tokens": 1060352}
{"current_steps": 1105, "total_steps": 58920, "loss": 0.0886, "lr": 3.7474541751527496e-07, "epoch": 0.09377121520706042, "percentage": 1.88, "elapsed_time": "0:01:25", "remaining_time": "1:14:14", "throughput": 12513.89, "total_tokens": 1065472}
{"current_steps": 1110, "total_steps": 58920, "loss": 0.068, "lr": 3.7644263408010864e-07, "epoch": 0.09419551934826884, "percentage": 1.88, "elapsed_time": "0:01:25", "remaining_time": "1:14:13", "throughput": 12513.4, "total_tokens": 1070144}
{"current_steps": 1115, "total_steps": 58920, "loss": 0.0406, "lr": 3.7813985064494233e-07, "epoch": 0.09461982348947726, "percentage": 1.89, "elapsed_time": "0:01:25", "remaining_time": "1:14:13", "throughput": 12511.54, "total_tokens": 1074688}
{"current_steps": 1120, "total_steps": 58920, "loss": 0.0397, "lr": 3.798370672097759e-07, "epoch": 0.09504412763068568, "percentage": 1.9, "elapsed_time": "0:01:26", "remaining_time": "1:14:12", "throughput": 12507.46, "total_tokens": 1079040}
{"current_steps": 1125, "total_steps": 58920, "loss": 0.0854, "lr": 3.815342837746096e-07, "epoch": 0.0954684317718941, "percentage": 1.91, "elapsed_time": "0:01:26", "remaining_time": "1:14:11", "throughput": 12503.88, "total_tokens": 1083456}
{"current_steps": 1130, "total_steps": 58920, "loss": 0.114, "lr": 3.832315003394433e-07, "epoch": 0.09589273591310252, "percentage": 1.92, "elapsed_time": "0:01:27", "remaining_time": "1:14:10", "throughput": 12502.49, "total_tokens": 1088064}
{"current_steps": 1135, "total_steps": 58920, "loss": 0.103, "lr": 3.8492871690427696e-07, "epoch": 0.09631704005431092, "percentage": 1.93, "elapsed_time": "0:01:27", "remaining_time": "1:14:09", "throughput": 12500.1, "total_tokens": 1092544}
{"current_steps": 1140, "total_steps": 58920, "loss": 0.065, "lr": 3.8662593346911065e-07, "epoch": 0.09674134419551934, "percentage": 1.93, "elapsed_time": "0:01:27", "remaining_time": "1:14:10", "throughput": 12503.46, "total_tokens": 1097792}
{"current_steps": 1145, "total_steps": 58920, "loss": 0.1336, "lr": 3.8832315003394433e-07, "epoch": 0.09716564833672776, "percentage": 1.94, "elapsed_time": "0:01:28", "remaining_time": "1:14:09", "throughput": 12506.21, "total_tokens": 1102912}
{"current_steps": 1150, "total_steps": 58920, "loss": 0.1032, "lr": 3.9002036659877797e-07, "epoch": 0.09758995247793618, "percentage": 1.95, "elapsed_time": "0:01:28", "remaining_time": "1:14:09", "throughput": 12507.35, "total_tokens": 1107840}
{"current_steps": 1155, "total_steps": 58920, "loss": 0.0767, "lr": 3.9171758316361165e-07, "epoch": 0.0980142566191446, "percentage": 1.96, "elapsed_time": "0:01:28", "remaining_time": "1:14:08", "throughput": 12506.33, "total_tokens": 1112448}
{"current_steps": 1160, "total_steps": 58920, "loss": 0.1079, "lr": 3.9341479972844534e-07, "epoch": 0.09843856076035302, "percentage": 1.97, "elapsed_time": "0:01:29", "remaining_time": "1:14:08", "throughput": 12506.41, "total_tokens": 1117248}
{"current_steps": 1165, "total_steps": 58920, "loss": 0.1374, "lr": 3.95112016293279e-07, "epoch": 0.09886286490156145, "percentage": 1.98, "elapsed_time": "0:01:29", "remaining_time": "1:14:07", "throughput": 12506.15, "total_tokens": 1121984}
{"current_steps": 1170, "total_steps": 58920, "loss": 0.1244, "lr": 3.968092328581127e-07, "epoch": 0.09928716904276985, "percentage": 1.99, "elapsed_time": "0:01:30", "remaining_time": "1:14:07", "throughput": 12508.03, "total_tokens": 1127040}
{"current_steps": 1175, "total_steps": 58920, "loss": 0.0826, "lr": 3.985064494229464e-07, "epoch": 0.09971147318397827, "percentage": 1.99, "elapsed_time": "0:01:30", "remaining_time": "1:14:07", "throughput": 12508.71, "total_tokens": 1131904}
{"current_steps": 1180, "total_steps": 58920, "loss": 0.0816, "lr": 4.0020366598778e-07, "epoch": 0.10013577732518669, "percentage": 2.0, "elapsed_time": "0:01:30", "remaining_time": "1:14:06", "throughput": 12506.3, "total_tokens": 1136384}
{"current_steps": 1185, "total_steps": 58920, "loss": 0.1169, "lr": 4.0190088255261365e-07, "epoch": 0.10056008146639511, "percentage": 2.01, "elapsed_time": "0:01:31", "remaining_time": "1:14:05", "throughput": 12503.6, "total_tokens": 1140864}
{"current_steps": 1190, "total_steps": 58920, "loss": 0.1032, "lr": 4.0359809911744734e-07, "epoch": 0.10098438560760353, "percentage": 2.02, "elapsed_time": "0:01:31", "remaining_time": "1:14:04", "throughput": 12501.62, "total_tokens": 1145408}
{"current_steps": 1195, "total_steps": 58920, "loss": 0.0866, "lr": 4.05295315682281e-07, "epoch": 0.10140868974881195, "percentage": 2.03, "elapsed_time": "0:01:32", "remaining_time": "1:14:04", "throughput": 12503.58, "total_tokens": 1150400}
{"current_steps": 1200, "total_steps": 58920, "loss": 0.1094, "lr": 4.069925322471147e-07, "epoch": 0.10183299389002037, "percentage": 2.04, "elapsed_time": "0:01:32", "remaining_time": "1:14:03", "throughput": 12500.96, "total_tokens": 1154880}
{"current_steps": 1205, "total_steps": 58920, "loss": 0.082, "lr": 4.086897488119484e-07, "epoch": 0.10225729803122878, "percentage": 2.05, "elapsed_time": "0:01:32", "remaining_time": "1:14:02", "throughput": 12500.43, "total_tokens": 1159552}
{"current_steps": 1210, "total_steps": 58920, "loss": 0.0816, "lr": 4.103869653767821e-07, "epoch": 0.1026816021724372, "percentage": 2.05, "elapsed_time": "0:01:33", "remaining_time": "1:14:03", "throughput": 12503.61, "total_tokens": 1164800}
{"current_steps": 1215, "total_steps": 58920, "loss": 0.0691, "lr": 4.120841819416157e-07, "epoch": 0.10310590631364562, "percentage": 2.06, "elapsed_time": "0:01:33", "remaining_time": "1:14:03", "throughput": 12509.34, "total_tokens": 1170304}
{"current_steps": 1220, "total_steps": 58920, "loss": 0.0878, "lr": 4.137813985064494e-07, "epoch": 0.10353021045485404, "percentage": 2.07, "elapsed_time": "0:01:33", "remaining_time": "1:14:02", "throughput": 12509.33, "total_tokens": 1175040}
{"current_steps": 1225, "total_steps": 58920, "loss": 0.0287, "lr": 4.154786150712831e-07, "epoch": 0.10395451459606246, "percentage": 2.08, "elapsed_time": "0:01:34", "remaining_time": "1:14:02", "throughput": 12513.05, "total_tokens": 1180288}
{"current_steps": 1230, "total_steps": 58920, "loss": 0.0731, "lr": 4.1717583163611677e-07, "epoch": 0.10437881873727088, "percentage": 2.09, "elapsed_time": "0:01:34", "remaining_time": "1:14:02", "throughput": 12513.07, "total_tokens": 1185088}
{"current_steps": 1235, "total_steps": 58920, "loss": 0.1011, "lr": 4.1887304820095045e-07, "epoch": 0.10480312287847929, "percentage": 2.1, "elapsed_time": "0:01:35", "remaining_time": "1:14:01", "throughput": 12510.65, "total_tokens": 1189504}
{"current_steps": 1240, "total_steps": 58920, "loss": 0.1568, "lr": 4.2057026476578414e-07, "epoch": 0.10522742701968771, "percentage": 2.1, "elapsed_time": "0:01:35", "remaining_time": "1:14:00", "throughput": 12510.73, "total_tokens": 1194304}
{"current_steps": 1245, "total_steps": 58920, "loss": 0.0418, "lr": 4.2226748133061777e-07, "epoch": 0.10565173116089613, "percentage": 2.11, "elapsed_time": "0:01:35", "remaining_time": "1:13:59", "throughput": 12509.67, "total_tokens": 1198976}
{"current_steps": 1250, "total_steps": 58920, "loss": 0.0724, "lr": 4.239646978954514e-07, "epoch": 0.10607603530210455, "percentage": 2.12, "elapsed_time": "0:01:36", "remaining_time": "1:13:59", "throughput": 12507.96, "total_tokens": 1203520}
{"current_steps": 1255, "total_steps": 58920, "loss": 0.1762, "lr": 4.256619144602851e-07, "epoch": 0.10650033944331297, "percentage": 2.13, "elapsed_time": "0:01:36", "remaining_time": "1:13:58", "throughput": 12504.4, "total_tokens": 1207808}
{"current_steps": 1260, "total_steps": 58920, "loss": 0.1101, "lr": 4.2735913102511877e-07, "epoch": 0.10692464358452139, "percentage": 2.14, "elapsed_time": "0:01:36", "remaining_time": "1:13:58", "throughput": 12507.38, "total_tokens": 1212992}
{"current_steps": 1265, "total_steps": 58920, "loss": 0.1291, "lr": 4.2905634758995245e-07, "epoch": 0.10734894772572981, "percentage": 2.15, "elapsed_time": "0:01:37", "remaining_time": "1:13:57", "throughput": 12504.26, "total_tokens": 1217344}
{"current_steps": 1270, "total_steps": 58920, "loss": 0.0415, "lr": 4.3075356415478614e-07, "epoch": 0.10777325186693822, "percentage": 2.16, "elapsed_time": "0:01:37", "remaining_time": "1:13:56", "throughput": 12504.61, "total_tokens": 1222080}
{"current_steps": 1275, "total_steps": 58920, "loss": 0.1305, "lr": 4.324507807196198e-07, "epoch": 0.10819755600814664, "percentage": 2.16, "elapsed_time": "0:01:38", "remaining_time": "1:13:55", "throughput": 12503.8, "total_tokens": 1226752}
{"current_steps": 1280, "total_steps": 58920, "loss": 0.1153, "lr": 4.341479972844535e-07, "epoch": 0.10862186014935506, "percentage": 2.17, "elapsed_time": "0:01:38", "remaining_time": "1:13:55", "throughput": 12505.48, "total_tokens": 1231808}
{"current_steps": 1285, "total_steps": 58920, "loss": 0.0923, "lr": 4.3584521384928714e-07, "epoch": 0.10904616429056348, "percentage": 2.18, "elapsed_time": "0:01:38", "remaining_time": "1:13:54", "throughput": 12504.16, "total_tokens": 1236352}
{"current_steps": 1290, "total_steps": 58920, "loss": 0.0831, "lr": 4.375424304141208e-07, "epoch": 0.1094704684317719, "percentage": 2.19, "elapsed_time": "0:01:39", "remaining_time": "1:13:54", "throughput": 12504.23, "total_tokens": 1241088}
{"current_steps": 1295, "total_steps": 58920, "loss": 0.0524, "lr": 4.392396469789545e-07, "epoch": 0.10989477257298032, "percentage": 2.2, "elapsed_time": "0:01:39", "remaining_time": "1:13:54", "throughput": 12507.43, "total_tokens": 1246336}
{"current_steps": 1300, "total_steps": 58920, "loss": 0.0826, "lr": 4.409368635437882e-07, "epoch": 0.11031907671418872, "percentage": 2.21, "elapsed_time": "0:01:40", "remaining_time": "1:13:54", "throughput": 12511.5, "total_tokens": 1251648}
{"current_steps": 1305, "total_steps": 58920, "loss": 0.0692, "lr": 4.4263408010862183e-07, "epoch": 0.11074338085539714, "percentage": 2.21, "elapsed_time": "0:01:40", "remaining_time": "1:13:53", "throughput": 12511.57, "total_tokens": 1256448}
{"current_steps": 1310, "total_steps": 58920, "loss": 0.0991, "lr": 4.443312966734555e-07, "epoch": 0.11116768499660556, "percentage": 2.22, "elapsed_time": "0:01:40", "remaining_time": "1:13:53", "throughput": 12510.93, "total_tokens": 1261184}
{"current_steps": 1315, "total_steps": 58920, "loss": 0.0544, "lr": 4.4602851323828915e-07, "epoch": 0.11159198913781398, "percentage": 2.23, "elapsed_time": "0:01:41", "remaining_time": "1:13:53", "throughput": 12513.27, "total_tokens": 1266304}
{"current_steps": 1320, "total_steps": 58920, "loss": 0.0949, "lr": 4.4772572980312283e-07, "epoch": 0.1120162932790224, "percentage": 2.24, "elapsed_time": "0:01:41", "remaining_time": "1:13:52", "throughput": 12511.23, "total_tokens": 1270848}
{"current_steps": 1325, "total_steps": 58920, "loss": 0.1104, "lr": 4.494229463679565e-07, "epoch": 0.11244059742023083, "percentage": 2.25, "elapsed_time": "0:01:41", "remaining_time": "1:13:52", "throughput": 12509.65, "total_tokens": 1275712}
{"current_steps": 1330, "total_steps": 58920, "loss": 0.0823, "lr": 4.511201629327902e-07, "epoch": 0.11286490156143925, "percentage": 2.26, "elapsed_time": "0:01:42", "remaining_time": "1:13:52", "throughput": 12505.38, "total_tokens": 1280000}
{"current_steps": 1335, "total_steps": 58920, "loss": 0.0671, "lr": 4.528173794976239e-07, "epoch": 0.11328920570264765, "percentage": 2.27, "elapsed_time": "0:01:42", "remaining_time": "1:13:52", "throughput": 12510.03, "total_tokens": 1285440}
{"current_steps": 1340, "total_steps": 58920, "loss": 0.0894, "lr": 4.5451459606245757e-07, "epoch": 0.11371350984385607, "percentage": 2.27, "elapsed_time": "0:01:43", "remaining_time": "1:13:51", "throughput": 12509.63, "total_tokens": 1290176}
{"current_steps": 1345, "total_steps": 58920, "loss": 0.1452, "lr": 4.5621181262729125e-07, "epoch": 0.11413781398506449, "percentage": 2.28, "elapsed_time": "0:01:43", "remaining_time": "1:13:51", "throughput": 12508.15, "total_tokens": 1294912}
{"current_steps": 1350, "total_steps": 58920, "loss": 0.0981, "lr": 4.579090291921249e-07, "epoch": 0.11456211812627291, "percentage": 2.29, "elapsed_time": "0:01:43", "remaining_time": "1:13:51", "throughput": 12501.92, "total_tokens": 1299136}
{"current_steps": 1355, "total_steps": 58920, "loss": 0.0965, "lr": 4.5960624575695857e-07, "epoch": 0.11498642226748133, "percentage": 2.3, "elapsed_time": "0:01:44", "remaining_time": "1:13:52", "throughput": 12496.83, "total_tokens": 1303936}
{"current_steps": 1360, "total_steps": 58920, "loss": 0.044, "lr": 4.6130346232179226e-07, "epoch": 0.11541072640868975, "percentage": 2.31, "elapsed_time": "0:01:44", "remaining_time": "1:13:53", "throughput": 12494.36, "total_tokens": 1308928}
{"current_steps": 1365, "total_steps": 58920, "loss": 0.0923, "lr": 4.6300067888662594e-07, "epoch": 0.11583503054989816, "percentage": 2.32, "elapsed_time": "0:01:45", "remaining_time": "1:13:53", "throughput": 12493.2, "total_tokens": 1313728}
{"current_steps": 1370, "total_steps": 58920, "loss": 0.0897, "lr": 4.646978954514596e-07, "epoch": 0.11625933469110658, "percentage": 2.33, "elapsed_time": "0:01:45", "remaining_time": "1:13:53", "throughput": 12492.02, "total_tokens": 1318400}
{"current_steps": 1375, "total_steps": 58920, "loss": 0.0784, "lr": 4.6639511201629326e-07, "epoch": 0.116683638832315, "percentage": 2.33, "elapsed_time": "0:01:45", "remaining_time": "1:13:52", "throughput": 12489.04, "total_tokens": 1322752}
{"current_steps": 1380, "total_steps": 58920, "loss": 0.0871, "lr": 4.680923285811269e-07, "epoch": 0.11710794297352342, "percentage": 2.34, "elapsed_time": "0:01:46", "remaining_time": "1:13:52", "throughput": 12489.35, "total_tokens": 1327552}
{"current_steps": 1385, "total_steps": 58920, "loss": 0.0894, "lr": 4.697895451459606e-07, "epoch": 0.11753224711473184, "percentage": 2.35, "elapsed_time": "0:01:46", "remaining_time": "1:13:51", "throughput": 12485.03, "total_tokens": 1331776}
{"current_steps": 1390, "total_steps": 58920, "loss": 0.0531, "lr": 4.7148676171079426e-07, "epoch": 0.11795655125594026, "percentage": 2.36, "elapsed_time": "0:01:47", "remaining_time": "1:13:50", "throughput": 12481.83, "total_tokens": 1336128}
{"current_steps": 1395, "total_steps": 58920, "loss": 0.0852, "lr": 4.7318397827562795e-07, "epoch": 0.11838085539714868, "percentage": 2.37, "elapsed_time": "0:01:47", "remaining_time": "1:13:50", "throughput": 12480.73, "total_tokens": 1340800}
{"current_steps": 1400, "total_steps": 58920, "loss": 0.105, "lr": 4.7488119484046163e-07, "epoch": 0.11880515953835709, "percentage": 2.38, "elapsed_time": "0:01:47", "remaining_time": "1:13:49", "throughput": 12479.11, "total_tokens": 1345408}
{"current_steps": 1405, "total_steps": 58920, "loss": 0.1095, "lr": 4.765784114052953e-07, "epoch": 0.11922946367956551, "percentage": 2.38, "elapsed_time": "0:01:48", "remaining_time": "1:13:49", "throughput": 12478.82, "total_tokens": 1350208}
{"current_steps": 1410, "total_steps": 58920, "loss": 0.0629, "lr": 4.78275627970129e-07, "epoch": 0.11965376782077393, "percentage": 2.39, "elapsed_time": "0:01:48", "remaining_time": "1:13:48", "throughput": 12476.21, "total_tokens": 1354624}
{"current_steps": 1415, "total_steps": 58920, "loss": 0.0904, "lr": 4.799728445349626e-07, "epoch": 0.12007807196198235, "percentage": 2.4, "elapsed_time": "0:01:48", "remaining_time": "1:13:48", "throughput": 12474.21, "total_tokens": 1359232}
{"current_steps": 1420, "total_steps": 58920, "loss": 0.0765, "lr": 4.816700610997963e-07, "epoch": 0.12050237610319077, "percentage": 2.41, "elapsed_time": "0:01:49", "remaining_time": "1:13:47", "throughput": 12473.26, "total_tokens": 1363904}
{"current_steps": 1425, "total_steps": 58920, "loss": 0.0483, "lr": 4.8336727766463e-07, "epoch": 0.12092668024439919, "percentage": 2.42, "elapsed_time": "0:01:49", "remaining_time": "1:13:47", "throughput": 12471.38, "total_tokens": 1368448}
{"current_steps": 1430, "total_steps": 58920, "loss": 0.0752, "lr": 4.850644942294636e-07, "epoch": 0.12135098438560761, "percentage": 2.43, "elapsed_time": "0:01:50", "remaining_time": "1:13:46", "throughput": 12468.67, "total_tokens": 1372864}
{"current_steps": 1435, "total_steps": 58920, "loss": 0.0716, "lr": 4.867617107942974e-07, "epoch": 0.12177528852681602, "percentage": 2.44, "elapsed_time": "0:01:50", "remaining_time": "1:13:46", "throughput": 12469.83, "total_tokens": 1377920}
{"current_steps": 1440, "total_steps": 58920, "loss": 0.1023, "lr": 4.88458927359131e-07, "epoch": 0.12219959266802444, "percentage": 2.44, "elapsed_time": "0:01:50", "remaining_time": "1:13:46", "throughput": 12466.58, "total_tokens": 1382464}
{"current_steps": 1445, "total_steps": 58920, "loss": 0.0557, "lr": 4.901561439239646e-07, "epoch": 0.12262389680923286, "percentage": 2.45, "elapsed_time": "0:01:51", "remaining_time": "1:13:46", "throughput": 12463.67, "total_tokens": 1387072}
{"current_steps": 1450, "total_steps": 58920, "loss": 0.0862, "lr": 4.918533604887984e-07, "epoch": 0.12304820095044128, "percentage": 2.46, "elapsed_time": "0:01:51", "remaining_time": "1:13:45", "throughput": 12461.39, "total_tokens": 1391488}
{"current_steps": 1455, "total_steps": 58920, "loss": 0.0776, "lr": 4.93550577053632e-07, "epoch": 0.1234725050916497, "percentage": 2.47, "elapsed_time": "0:01:52", "remaining_time": "1:13:46", "throughput": 12468.59, "total_tokens": 1397440}
{"current_steps": 1460, "total_steps": 58920, "loss": 0.0577, "lr": 4.952477936184657e-07, "epoch": 0.12389680923285812, "percentage": 2.48, "elapsed_time": "0:01:52", "remaining_time": "1:13:45", "throughput": 12467.39, "total_tokens": 1402048}
{"current_steps": 1465, "total_steps": 58920, "loss": 0.0261, "lr": 4.969450101832994e-07, "epoch": 0.12432111337406652, "percentage": 2.49, "elapsed_time": "0:01:52", "remaining_time": "1:13:45", "throughput": 12467.43, "total_tokens": 1406784}
{"current_steps": 1470, "total_steps": 58920, "loss": 0.1302, "lr": 4.98642226748133e-07, "epoch": 0.12474541751527495, "percentage": 2.49, "elapsed_time": "0:01:53", "remaining_time": "1:13:44", "throughput": 12465.81, "total_tokens": 1411328}
{"current_steps": 1475, "total_steps": 58920, "loss": 0.1615, "lr": 5.003394433129667e-07, "epoch": 0.12516972165648338, "percentage": 2.5, "elapsed_time": "0:01:53", "remaining_time": "1:13:44", "throughput": 12464.72, "total_tokens": 1415936}
{"current_steps": 1480, "total_steps": 58920, "loss": 0.1144, "lr": 5.020366598778004e-07, "epoch": 0.12559402579769177, "percentage": 2.51, "elapsed_time": "0:01:53", "remaining_time": "1:13:44", "throughput": 12467.76, "total_tokens": 1421248}
{"current_steps": 1485, "total_steps": 58920, "loss": 0.0786, "lr": 5.037338764426341e-07, "epoch": 0.1260183299389002, "percentage": 2.52, "elapsed_time": "0:01:54", "remaining_time": "1:13:43", "throughput": 12465.91, "total_tokens": 1425728}
{"current_steps": 1490, "total_steps": 58920, "loss": 0.0712, "lr": 5.054310930074677e-07, "epoch": 0.1264426340801086, "percentage": 2.53, "elapsed_time": "0:01:54", "remaining_time": "1:13:48", "throughput": 12458.06, "total_tokens": 1431296}
{"current_steps": 1495, "total_steps": 58920, "loss": 0.0812, "lr": 5.071283095723014e-07, "epoch": 0.12686693822131703, "percentage": 2.54, "elapsed_time": "0:01:55", "remaining_time": "1:13:47", "throughput": 12458.55, "total_tokens": 1436160}
{"current_steps": 1500, "total_steps": 58920, "loss": 0.0884, "lr": 5.08825526137135e-07, "epoch": 0.12729124236252545, "percentage": 2.55, "elapsed_time": "0:01:55", "remaining_time": "1:13:47", "throughput": 12458.92, "total_tokens": 1440960}
{"current_steps": 1505, "total_steps": 58920, "loss": 0.0944, "lr": 5.105227427019687e-07, "epoch": 0.12771554650373387, "percentage": 2.55, "elapsed_time": "0:01:56", "remaining_time": "1:13:46", "throughput": 12459.22, "total_tokens": 1445760}
{"current_steps": 1510, "total_steps": 58920, "loss": 0.0794, "lr": 5.122199592668024e-07, "epoch": 0.1281398506449423, "percentage": 2.56, "elapsed_time": "0:01:56", "remaining_time": "1:13:46", "throughput": 12460.4, "total_tokens": 1450688}
{"current_steps": 1515, "total_steps": 58920, "loss": 0.1101, "lr": 5.139171758316361e-07, "epoch": 0.12856415478615071, "percentage": 2.57, "elapsed_time": "0:01:56", "remaining_time": "1:13:45", "throughput": 12461.2, "total_tokens": 1455552}
{"current_steps": 1520, "total_steps": 58920, "loss": 0.0965, "lr": 5.156143923964698e-07, "epoch": 0.12898845892735913, "percentage": 2.58, "elapsed_time": "0:01:57", "remaining_time": "1:13:45", "throughput": 12462.01, "total_tokens": 1460416}
{"current_steps": 1525, "total_steps": 58920, "loss": 0.0803, "lr": 5.173116089613034e-07, "epoch": 0.12941276306856755, "percentage": 2.59, "elapsed_time": "0:01:57", "remaining_time": "1:13:46", "throughput": 12468.11, "total_tokens": 1466432}
{"current_steps": 1530, "total_steps": 58920, "loss": 0.0944, "lr": 5.190088255261371e-07, "epoch": 0.12983706720977597, "percentage": 2.6, "elapsed_time": "0:01:57", "remaining_time": "1:13:45", "throughput": 12468.81, "total_tokens": 1471232}
{"current_steps": 1535, "total_steps": 58920, "loss": 0.0789, "lr": 5.207060420909708e-07, "epoch": 0.1302613713509844, "percentage": 2.61, "elapsed_time": "0:01:58", "remaining_time": "1:13:45", "throughput": 12469.99, "total_tokens": 1476160}
{"current_steps": 1540, "total_steps": 58920, "loss": 0.0748, "lr": 5.224032586558045e-07, "epoch": 0.13068567549219282, "percentage": 2.61, "elapsed_time": "0:01:58", "remaining_time": "1:13:45", "throughput": 12471.12, "total_tokens": 1481152}
{"current_steps": 1545, "total_steps": 58920, "loss": 0.1709, "lr": 5.241004752206381e-07, "epoch": 0.13110997963340124, "percentage": 2.62, "elapsed_time": "0:01:59", "remaining_time": "1:13:45", "throughput": 12473.59, "total_tokens": 1486336}
{"current_steps": 1550, "total_steps": 58920, "loss": 0.0529, "lr": 5.257976917854719e-07, "epoch": 0.13153428377460963, "percentage": 2.63, "elapsed_time": "0:01:59", "remaining_time": "1:13:44", "throughput": 12474.68, "total_tokens": 1491264}
{"current_steps": 1555, "total_steps": 58920, "loss": 0.0801, "lr": 5.274949083503055e-07, "epoch": 0.13195858791581805, "percentage": 2.64, "elapsed_time": "0:01:59", "remaining_time": "1:13:43", "throughput": 12472.41, "total_tokens": 1495680}
{"current_steps": 1560, "total_steps": 58920, "loss": 0.107, "lr": 5.291921249151391e-07, "epoch": 0.13238289205702647, "percentage": 2.65, "elapsed_time": "0:02:00", "remaining_time": "1:13:44", "throughput": 12478.28, "total_tokens": 1501376}
{"current_steps": 1565, "total_steps": 58920, "loss": 0.0886, "lr": 5.308893414799728e-07, "epoch": 0.1328071961982349, "percentage": 2.66, "elapsed_time": "0:02:00", "remaining_time": "1:13:43", "throughput": 12478.75, "total_tokens": 1506176}
{"current_steps": 1570, "total_steps": 58920, "loss": 0.0809, "lr": 5.325865580448065e-07, "epoch": 0.1332315003394433, "percentage": 2.66, "elapsed_time": "0:02:01", "remaining_time": "1:13:43", "throughput": 12484.04, "total_tokens": 1511808}
{"current_steps": 1575, "total_steps": 58920, "loss": 0.0686, "lr": 5.342837746096401e-07, "epoch": 0.13365580448065173, "percentage": 2.67, "elapsed_time": "0:02:01", "remaining_time": "1:13:43", "throughput": 12484.03, "total_tokens": 1516608}
{"current_steps": 1580, "total_steps": 58920, "loss": 0.0802, "lr": 5.359809911744739e-07, "epoch": 0.13408010862186015, "percentage": 2.68, "elapsed_time": "0:02:01", "remaining_time": "1:13:42", "throughput": 12483.73, "total_tokens": 1521280}
{"current_steps": 1585, "total_steps": 58920, "loss": 0.0723, "lr": 5.376782077393075e-07, "epoch": 0.13450441276306857, "percentage": 2.69, "elapsed_time": "0:02:02", "remaining_time": "1:13:41", "throughput": 12483.95, "total_tokens": 1526080}
{"current_steps": 1590, "total_steps": 58920, "loss": 0.035, "lr": 5.393754243041411e-07, "epoch": 0.134928716904277, "percentage": 2.7, "elapsed_time": "0:02:02", "remaining_time": "1:13:41", "throughput": 12484.64, "total_tokens": 1530944}
{"current_steps": 1595, "total_steps": 58920, "loss": 0.0967, "lr": 5.410726408689749e-07, "epoch": 0.1353530210454854, "percentage": 2.71, "elapsed_time": "0:02:03", "remaining_time": "1:13:41", "throughput": 12487.82, "total_tokens": 1536256}
{"current_steps": 1600, "total_steps": 58920, "loss": 0.0699, "lr": 5.427698574338085e-07, "epoch": 0.13577732518669383, "percentage": 2.72, "elapsed_time": "0:02:03", "remaining_time": "1:13:40", "throughput": 12486.68, "total_tokens": 1540864}
{"current_steps": 1605, "total_steps": 58920, "loss": 0.0804, "lr": 5.444670739986422e-07, "epoch": 0.13620162932790225, "percentage": 2.72, "elapsed_time": "0:02:03", "remaining_time": "1:13:40", "throughput": 12485.87, "total_tokens": 1545536}
{"current_steps": 1610, "total_steps": 58920, "loss": 0.0951, "lr": 5.461642905634759e-07, "epoch": 0.13662593346911067, "percentage": 2.73, "elapsed_time": "0:02:04", "remaining_time": "1:13:39", "throughput": 12485.13, "total_tokens": 1550144}
{"current_steps": 1615, "total_steps": 58920, "loss": 0.075, "lr": 5.478615071283096e-07, "epoch": 0.13705023761031906, "percentage": 2.74, "elapsed_time": "0:02:04", "remaining_time": "1:13:38", "throughput": 12483.45, "total_tokens": 1554624}
{"current_steps": 1620, "total_steps": 58920, "loss": 0.1103, "lr": 5.495587236931432e-07, "epoch": 0.13747454175152748, "percentage": 2.75, "elapsed_time": "0:02:04", "remaining_time": "1:13:38", "throughput": 12480.76, "total_tokens": 1559168}
{"current_steps": 1625, "total_steps": 58920, "loss": 0.1112, "lr": 5.51255940257977e-07, "epoch": 0.1378988458927359, "percentage": 2.76, "elapsed_time": "0:02:05", "remaining_time": "1:13:38", "throughput": 12481.5, "total_tokens": 1564032}
{"current_steps": 1630, "total_steps": 58920, "loss": 0.101, "lr": 5.529531568228105e-07, "epoch": 0.13832315003394433, "percentage": 2.77, "elapsed_time": "0:02:05", "remaining_time": "1:13:37", "throughput": 12482.54, "total_tokens": 1568896}
{"current_steps": 1635, "total_steps": 58920, "loss": 0.1228, "lr": 5.546503733876442e-07, "epoch": 0.13874745417515275, "percentage": 2.77, "elapsed_time": "0:02:06", "remaining_time": "1:13:37", "throughput": 12483.69, "total_tokens": 1573888}
{"current_steps": 1640, "total_steps": 58920, "loss": 0.0829, "lr": 5.563475899524779e-07, "epoch": 0.13917175831636117, "percentage": 2.78, "elapsed_time": "0:02:06", "remaining_time": "1:13:36", "throughput": 12482.95, "total_tokens": 1578496}
{"current_steps": 1645, "total_steps": 58920, "loss": 0.033, "lr": 5.580448065173116e-07, "epoch": 0.1395960624575696, "percentage": 2.79, "elapsed_time": "0:02:06", "remaining_time": "1:13:35", "throughput": 12482.18, "total_tokens": 1583104}
{"current_steps": 1650, "total_steps": 58920, "loss": 0.1208, "lr": 5.597420230821452e-07, "epoch": 0.140020366598778, "percentage": 2.8, "elapsed_time": "0:02:07", "remaining_time": "1:13:35", "throughput": 12480.96, "total_tokens": 1587648}
{"current_steps": 1655, "total_steps": 58920, "loss": 0.1174, "lr": 5.614392396469789e-07, "epoch": 0.14044467073998643, "percentage": 2.81, "elapsed_time": "0:02:07", "remaining_time": "1:13:35", "throughput": 12485.16, "total_tokens": 1593216}
{"current_steps": 1660, "total_steps": 58920, "loss": 0.0303, "lr": 5.631364562118126e-07, "epoch": 0.14086897488119485, "percentage": 2.82, "elapsed_time": "0:02:07", "remaining_time": "1:13:35", "throughput": 12486.53, "total_tokens": 1598208}
{"current_steps": 1665, "total_steps": 58920, "loss": 0.0186, "lr": 5.648336727766462e-07, "epoch": 0.14129327902240327, "percentage": 2.83, "elapsed_time": "0:02:08", "remaining_time": "1:13:34", "throughput": 12485.09, "total_tokens": 1602688}
{"current_steps": 1670, "total_steps": 58920, "loss": 0.0734, "lr": 5.6653088934148e-07, "epoch": 0.1417175831636117, "percentage": 2.83, "elapsed_time": "0:02:08", "remaining_time": "1:13:33", "throughput": 12481.17, "total_tokens": 1606784}
{"current_steps": 1675, "total_steps": 58920, "loss": 0.1587, "lr": 5.682281059063136e-07, "epoch": 0.1421418873048201, "percentage": 2.84, "elapsed_time": "0:02:09", "remaining_time": "1:13:33", "throughput": 12480.27, "total_tokens": 1611584}
{"current_steps": 1680, "total_steps": 58920, "loss": 0.0745, "lr": 5.699253224711474e-07, "epoch": 0.1425661914460285, "percentage": 2.85, "elapsed_time": "0:02:09", "remaining_time": "1:13:32", "throughput": 12481.79, "total_tokens": 1616576}
{"current_steps": 1685, "total_steps": 58920, "loss": 0.0824, "lr": 5.71622539035981e-07, "epoch": 0.14299049558723692, "percentage": 2.86, "elapsed_time": "0:02:09", "remaining_time": "1:13:32", "throughput": 12482.29, "total_tokens": 1621440}
{"current_steps": 1690, "total_steps": 58920, "loss": 0.0828, "lr": 5.733197556008147e-07, "epoch": 0.14341479972844534, "percentage": 2.87, "elapsed_time": "0:02:10", "remaining_time": "1:13:31", "throughput": 12483.36, "total_tokens": 1626368}
{"current_steps": 1695, "total_steps": 58920, "loss": 0.0548, "lr": 5.750169721656482e-07, "epoch": 0.14383910386965376, "percentage": 2.88, "elapsed_time": "0:02:10", "remaining_time": "1:13:31", "throughput": 12481.11, "total_tokens": 1630784}
{"current_steps": 1700, "total_steps": 58920, "loss": 0.0667, "lr": 5.76714188730482e-07, "epoch": 0.14426340801086218, "percentage": 2.89, "elapsed_time": "0:02:11", "remaining_time": "1:13:30", "throughput": 12482.22, "total_tokens": 1635776}
{"current_steps": 1705, "total_steps": 58920, "loss": 0.1417, "lr": 5.784114052953156e-07, "epoch": 0.1446877121520706, "percentage": 2.89, "elapsed_time": "0:02:11", "remaining_time": "1:13:30", "throughput": 12482.12, "total_tokens": 1640448}
{"current_steps": 1710, "total_steps": 58920, "loss": 0.0668, "lr": 5.801086218601494e-07, "epoch": 0.14511201629327902, "percentage": 2.9, "elapsed_time": "0:02:11", "remaining_time": "1:13:29", "throughput": 12483.05, "total_tokens": 1645440}
{"current_steps": 1715, "total_steps": 58920, "loss": 0.0719, "lr": 5.81805838424983e-07, "epoch": 0.14553632043448744, "percentage": 2.91, "elapsed_time": "0:02:12", "remaining_time": "1:13:29", "throughput": 12481.59, "total_tokens": 1649984}
{"current_steps": 1720, "total_steps": 58920, "loss": 0.1024, "lr": 5.835030549898166e-07, "epoch": 0.14596062457569586, "percentage": 2.92, "elapsed_time": "0:02:12", "remaining_time": "1:13:28", "throughput": 12481.35, "total_tokens": 1654720}
{"current_steps": 1725, "total_steps": 58920, "loss": 0.1065, "lr": 5.852002715546504e-07, "epoch": 0.14638492871690428, "percentage": 2.93, "elapsed_time": "0:02:12", "remaining_time": "1:13:28", "throughput": 12482.16, "total_tokens": 1659648}
{"current_steps": 1730, "total_steps": 58920, "loss": 0.0815, "lr": 5.86897488119484e-07, "epoch": 0.1468092328581127, "percentage": 2.94, "elapsed_time": "0:02:13", "remaining_time": "1:13:28", "throughput": 12484.44, "total_tokens": 1664896}
{"current_steps": 1735, "total_steps": 58920, "loss": 0.0933, "lr": 5.885947046843177e-07, "epoch": 0.14723353699932112, "percentage": 2.94, "elapsed_time": "0:02:13", "remaining_time": "1:13:27", "throughput": 12483.96, "total_tokens": 1669568}
{"current_steps": 1740, "total_steps": 58920, "loss": 0.071, "lr": 5.902919212491514e-07, "epoch": 0.14765784114052954, "percentage": 2.95, "elapsed_time": "0:02:14", "remaining_time": "1:13:27", "throughput": 12484.5, "total_tokens": 1674432}
{"current_steps": 1745, "total_steps": 58920, "loss": 0.0324, "lr": 5.919891378139851e-07, "epoch": 0.14808214528173794, "percentage": 2.96, "elapsed_time": "0:02:14", "remaining_time": "1:13:26", "throughput": 12482.06, "total_tokens": 1678720}
{"current_steps": 1750, "total_steps": 58920, "loss": 0.0326, "lr": 5.936863543788187e-07, "epoch": 0.14850644942294636, "percentage": 2.97, "elapsed_time": "0:02:14", "remaining_time": "1:13:26", "throughput": 12484.11, "total_tokens": 1683904}
{"current_steps": 1755, "total_steps": 58920, "loss": 0.0887, "lr": 5.953835709436525e-07, "epoch": 0.14893075356415478, "percentage": 2.98, "elapsed_time": "0:02:15", "remaining_time": "1:13:26", "throughput": 12486.18, "total_tokens": 1689024}
{"current_steps": 1760, "total_steps": 58920, "loss": 0.1158, "lr": 5.97080787508486e-07, "epoch": 0.1493550577053632, "percentage": 2.99, "elapsed_time": "0:02:15", "remaining_time": "1:13:25", "throughput": 12485.63, "total_tokens": 1693632}
{"current_steps": 1765, "total_steps": 58920, "loss": 0.0472, "lr": 5.987780040733197e-07, "epoch": 0.14977936184657162, "percentage": 3.0, "elapsed_time": "0:02:16", "remaining_time": "1:13:25", "throughput": 12484.56, "total_tokens": 1698304}
{"current_steps": 1770, "total_steps": 58920, "loss": 0.1613, "lr": 6.004752206381534e-07, "epoch": 0.15020366598778004, "percentage": 3.0, "elapsed_time": "0:02:16", "remaining_time": "1:13:25", "throughput": 12487.46, "total_tokens": 1703808}
{"current_steps": 1775, "total_steps": 58920, "loss": 0.0764, "lr": 6.02172437202987e-07, "epoch": 0.15062797012898846, "percentage": 3.01, "elapsed_time": "0:02:16", "remaining_time": "1:13:25", "throughput": 12489.44, "total_tokens": 1708992}
{"current_steps": 1780, "total_steps": 58920, "loss": 0.0574, "lr": 6.038696537678207e-07, "epoch": 0.15105227427019688, "percentage": 3.02, "elapsed_time": "0:02:17", "remaining_time": "1:13:24", "throughput": 12488.71, "total_tokens": 1713600}
{"current_steps": 1785, "total_steps": 58920, "loss": 0.0909, "lr": 6.055668703326544e-07, "epoch": 0.1514765784114053, "percentage": 3.03, "elapsed_time": "0:02:17", "remaining_time": "1:13:24", "throughput": 12487.96, "total_tokens": 1718208}
{"current_steps": 1790, "total_steps": 58920, "loss": 0.1471, "lr": 6.072640868974881e-07, "epoch": 0.15190088255261372, "percentage": 3.04, "elapsed_time": "0:02:17", "remaining_time": "1:13:23", "throughput": 12485.78, "total_tokens": 1722560}
{"current_steps": 1795, "total_steps": 58920, "loss": 0.0916, "lr": 6.089613034623217e-07, "epoch": 0.15232518669382214, "percentage": 3.05, "elapsed_time": "0:02:18", "remaining_time": "1:13:22", "throughput": 12485.75, "total_tokens": 1727296}
{"current_steps": 1800, "total_steps": 58920, "loss": 0.096, "lr": 6.106585200271555e-07, "epoch": 0.15274949083503056, "percentage": 3.05, "elapsed_time": "0:02:18", "remaining_time": "1:13:22", "throughput": 12488.58, "total_tokens": 1732608}
{"current_steps": 1805, "total_steps": 58920, "loss": 0.0847, "lr": 6.123557365919891e-07, "epoch": 0.15317379497623898, "percentage": 3.06, "elapsed_time": "0:02:19", "remaining_time": "1:13:28", "throughput": 12469.73, "total_tokens": 1737280}
{"current_steps": 1810, "total_steps": 58920, "loss": 0.0723, "lr": 6.140529531568228e-07, "epoch": 0.15359809911744737, "percentage": 3.07, "elapsed_time": "0:02:20", "remaining_time": "1:13:43", "throughput": 12422.86, "total_tokens": 1741440}
{"current_steps": 1815, "total_steps": 58920, "loss": 0.0433, "lr": 6.157501697216565e-07, "epoch": 0.1540224032586558, "percentage": 3.08, "elapsed_time": "0:02:21", "remaining_time": "1:13:58", "throughput": 12379.13, "total_tokens": 1746176}
{"current_steps": 1820, "total_steps": 58920, "loss": 0.1229, "lr": 6.174473862864902e-07, "epoch": 0.1544467073998642, "percentage": 3.09, "elapsed_time": "0:02:21", "remaining_time": "1:14:07", "throughput": 12356.49, "total_tokens": 1751680}
{"current_steps": 1825, "total_steps": 58920, "loss": 0.0653, "lr": 6.191446028513237e-07, "epoch": 0.15487101154107263, "percentage": 3.1, "elapsed_time": "0:02:22", "remaining_time": "1:14:12", "throughput": 12340.16, "total_tokens": 1756416}
{"current_steps": 1830, "total_steps": 58920, "loss": 0.0923, "lr": 6.208418194161575e-07, "epoch": 0.15529531568228105, "percentage": 3.11, "elapsed_time": "0:02:22", "remaining_time": "1:14:17", "throughput": 12323.76, "total_tokens": 1760960}
{"current_steps": 1835, "total_steps": 58920, "loss": 0.071, "lr": 6.225390359809911e-07, "epoch": 0.15571961982348947, "percentage": 3.11, "elapsed_time": "0:02:23", "remaining_time": "1:14:23", "throughput": 12310.61, "total_tokens": 1766208}
{"current_steps": 1840, "total_steps": 58920, "loss": 0.049, "lr": 6.242362525458247e-07, "epoch": 0.1561439239646979, "percentage": 3.12, "elapsed_time": "0:02:24", "remaining_time": "1:14:28", "throughput": 12296.61, "total_tokens": 1771264}
{"current_steps": 1845, "total_steps": 58920, "loss": 0.1237, "lr": 6.259334691106585e-07, "epoch": 0.15656822810590632, "percentage": 3.13, "elapsed_time": "0:02:24", "remaining_time": "1:14:33", "throughput": 12282.56, "total_tokens": 1776192}
{"current_steps": 1850, "total_steps": 58920, "loss": 0.0798, "lr": 6.276306856754921e-07, "epoch": 0.15699253224711474, "percentage": 3.14, "elapsed_time": "0:02:25", "remaining_time": "1:14:38", "throughput": 12268.25, "total_tokens": 1780992}
{"current_steps": 1855, "total_steps": 58920, "loss": 0.0854, "lr": 6.293279022403258e-07, "epoch": 0.15741683638832316, "percentage": 3.15, "elapsed_time": "0:02:25", "remaining_time": "1:14:42", "throughput": 12252.03, "total_tokens": 1785408}
{"current_steps": 1860, "total_steps": 58920, "loss": 0.079, "lr": 6.310251188051595e-07, "epoch": 0.15784114052953158, "percentage": 3.16, "elapsed_time": "0:02:26", "remaining_time": "1:14:47", "throughput": 12237.49, "total_tokens": 1790208}
{"current_steps": 1865, "total_steps": 58920, "loss": 0.029, "lr": 6.327223353699932e-07, "epoch": 0.15826544467074, "percentage": 3.17, "elapsed_time": "0:02:26", "remaining_time": "1:14:52", "throughput": 12224.02, "total_tokens": 1795264}
{"current_steps": 1870, "total_steps": 58920, "loss": 0.0898, "lr": 6.344195519348269e-07, "epoch": 0.15868974881194842, "percentage": 3.17, "elapsed_time": "0:02:27", "remaining_time": "1:14:57", "throughput": 12210.6, "total_tokens": 1800064}
{"current_steps": 1875, "total_steps": 58920, "loss": 0.042, "lr": 6.361167684996606e-07, "epoch": 0.1591140529531568, "percentage": 3.18, "elapsed_time": "0:02:27", "remaining_time": "1:15:02", "throughput": 12195.52, "total_tokens": 1804672}
{"current_steps": 1880, "total_steps": 58920, "loss": 0.0726, "lr": 6.378139850644942e-07, "epoch": 0.15953835709436523, "percentage": 3.19, "elapsed_time": "0:02:28", "remaining_time": "1:15:06", "throughput": 12180.79, "total_tokens": 1809408}
{"current_steps": 1885, "total_steps": 58920, "loss": 0.1097, "lr": 6.39511201629328e-07, "epoch": 0.15996266123557365, "percentage": 3.2, "elapsed_time": "0:02:29", "remaining_time": "1:15:11", "throughput": 12164.92, "total_tokens": 1813824}
{"current_steps": 1890, "total_steps": 58920, "loss": 0.0824, "lr": 6.412084181941615e-07, "epoch": 0.16038696537678207, "percentage": 3.21, "elapsed_time": "0:02:29", "remaining_time": "1:15:15", "throughput": 12148.83, "total_tokens": 1818176}
{"current_steps": 1895, "total_steps": 58920, "loss": 0.087, "lr": 6.429056347589952e-07, "epoch": 0.1608112695179905, "percentage": 3.22, "elapsed_time": "0:02:30", "remaining_time": "1:15:20", "throughput": 12134.62, "total_tokens": 1822784}
{"current_steps": 1900, "total_steps": 58920, "loss": 0.0901, "lr": 6.446028513238289e-07, "epoch": 0.1612355736591989, "percentage": 3.22, "elapsed_time": "0:02:30", "remaining_time": "1:15:24", "throughput": 12120.57, "total_tokens": 1827520}
{"current_steps": 1905, "total_steps": 58920, "loss": 0.1115, "lr": 6.463000678886625e-07, "epoch": 0.16165987780040733, "percentage": 3.23, "elapsed_time": "0:02:31", "remaining_time": "1:15:29", "throughput": 12107.17, "total_tokens": 1832256}
{"current_steps": 1910, "total_steps": 58920, "loss": 0.0806, "lr": 6.479972844534962e-07, "epoch": 0.16208418194161575, "percentage": 3.24, "elapsed_time": "0:02:31", "remaining_time": "1:15:33", "throughput": 12093.1, "total_tokens": 1836864}
{"current_steps": 1915, "total_steps": 58920, "loss": 0.0685, "lr": 6.496945010183299e-07, "epoch": 0.16250848608282417, "percentage": 3.25, "elapsed_time": "0:02:32", "remaining_time": "1:15:38", "throughput": 12078.07, "total_tokens": 1841280}
{"current_steps": 1920, "total_steps": 58920, "loss": 0.0709, "lr": 6.513917175831636e-07, "epoch": 0.1629327902240326, "percentage": 3.26, "elapsed_time": "0:02:33", "remaining_time": "1:15:42", "throughput": 12064.82, "total_tokens": 1846080}
{"current_steps": 1925, "total_steps": 58920, "loss": 0.0608, "lr": 6.530889341479972e-07, "epoch": 0.163357094365241, "percentage": 3.27, "elapsed_time": "0:02:33", "remaining_time": "1:15:47", "throughput": 12050.92, "total_tokens": 1850816}
{"current_steps": 1930, "total_steps": 58920, "loss": 0.0424, "lr": 6.54786150712831e-07, "epoch": 0.16378139850644943, "percentage": 3.28, "elapsed_time": "0:02:34", "remaining_time": "1:15:51", "throughput": 12035.38, "total_tokens": 1855232}
{"current_steps": 1935, "total_steps": 58920, "loss": 0.0643, "lr": 6.564833672776646e-07, "epoch": 0.16420570264765785, "percentage": 3.28, "elapsed_time": "0:02:34", "remaining_time": "1:15:56", "throughput": 12022.94, "total_tokens": 1860160}
{"current_steps": 1940, "total_steps": 58920, "loss": 0.058, "lr": 6.581805838424983e-07, "epoch": 0.16463000678886625, "percentage": 3.29, "elapsed_time": "0:02:35", "remaining_time": "1:16:00", "throughput": 12010.33, "total_tokens": 1865024}
{"current_steps": 1945, "total_steps": 58920, "loss": 0.0763, "lr": 6.59877800407332e-07, "epoch": 0.16505431093007467, "percentage": 3.3, "elapsed_time": "0:02:35", "remaining_time": "1:16:05", "throughput": 11997.64, "total_tokens": 1869888}
{"current_steps": 1950, "total_steps": 58920, "loss": 0.065, "lr": 6.615750169721657e-07, "epoch": 0.16547861507128309, "percentage": 3.31, "elapsed_time": "0:02:36", "remaining_time": "1:16:10", "throughput": 11984.19, "total_tokens": 1874624}
{"current_steps": 1955, "total_steps": 58920, "loss": 0.0525, "lr": 6.632722335369992e-07, "epoch": 0.1659029192124915, "percentage": 3.32, "elapsed_time": "0:02:36", "remaining_time": "1:16:14", "throughput": 11970.59, "total_tokens": 1879168}
{"current_steps": 1960, "total_steps": 58920, "loss": 0.2103, "lr": 6.64969450101833e-07, "epoch": 0.16632722335369993, "percentage": 3.33, "elapsed_time": "0:02:37", "remaining_time": "1:16:18", "throughput": 11958.31, "total_tokens": 1884096}
{"current_steps": 1965, "total_steps": 58920, "loss": 0.1151, "lr": 6.666666666666666e-07, "epoch": 0.16675152749490835, "percentage": 3.34, "elapsed_time": "0:02:38", "remaining_time": "1:16:23", "throughput": 11945.64, "total_tokens": 1888832}
{"current_steps": 1970, "total_steps": 58920, "loss": 0.0608, "lr": 6.683638832315002e-07, "epoch": 0.16717583163611677, "percentage": 3.34, "elapsed_time": "0:02:38", "remaining_time": "1:16:27", "throughput": 11933.78, "total_tokens": 1893696}
{"current_steps": 1975, "total_steps": 58920, "loss": 0.079, "lr": 6.70061099796334e-07, "epoch": 0.1676001357773252, "percentage": 3.35, "elapsed_time": "0:02:39", "remaining_time": "1:16:31", "throughput": 11920.3, "total_tokens": 1898176}
{"current_steps": 1980, "total_steps": 58920, "loss": 0.0552, "lr": 6.717583163611676e-07, "epoch": 0.1680244399185336, "percentage": 3.36, "elapsed_time": "0:02:39", "remaining_time": "1:16:35", "throughput": 11907.27, "total_tokens": 1902720}
{"current_steps": 1985, "total_steps": 58920, "loss": 0.0586, "lr": 6.734555329260013e-07, "epoch": 0.16844874405974203, "percentage": 3.37, "elapsed_time": "0:02:40", "remaining_time": "1:16:39", "throughput": 11895.11, "total_tokens": 1907520}
{"current_steps": 1990, "total_steps": 58920, "loss": 0.0776, "lr": 6.75152749490835e-07, "epoch": 0.16887304820095045, "percentage": 3.38, "elapsed_time": "0:02:40", "remaining_time": "1:16:43", "throughput": 11881.91, "total_tokens": 1912000}
{"current_steps": 1995, "total_steps": 58920, "loss": 0.0732, "lr": 6.768499660556687e-07, "epoch": 0.16929735234215887, "percentage": 3.39, "elapsed_time": "0:02:41", "remaining_time": "1:16:47", "throughput": 11867.3, "total_tokens": 1916224}
{"current_steps": 2000, "total_steps": 58920, "loss": 0.0566, "lr": 6.785471826205023e-07, "epoch": 0.1697216564833673, "percentage": 3.39, "elapsed_time": "0:02:42", "remaining_time": "1:16:51", "throughput": 11855.07, "total_tokens": 1920896}
{"current_steps": 2005, "total_steps": 58920, "loss": 0.0693, "lr": 6.802443991853361e-07, "epoch": 0.1701459606245757, "percentage": 3.4, "elapsed_time": "0:02:42", "remaining_time": "1:16:55", "throughput": 11841.96, "total_tokens": 1925312}
{"current_steps": 2010, "total_steps": 58920, "loss": 0.1311, "lr": 6.819416157501697e-07, "epoch": 0.1705702647657841, "percentage": 3.41, "elapsed_time": "0:02:43", "remaining_time": "1:16:59", "throughput": 11829.21, "total_tokens": 1929920}
{"current_steps": 2015, "total_steps": 58920, "loss": 0.0724, "lr": 6.836388323150035e-07, "epoch": 0.17099456890699252, "percentage": 3.42, "elapsed_time": "0:02:43", "remaining_time": "1:17:03", "throughput": 11817.71, "total_tokens": 1934720}
{"current_steps": 2020, "total_steps": 58920, "loss": 0.0566, "lr": 6.85336048879837e-07, "epoch": 0.17141887304820094, "percentage": 3.43, "elapsed_time": "0:02:44", "remaining_time": "1:17:07", "throughput": 11806.53, "total_tokens": 1939584}
{"current_steps": 2025, "total_steps": 58920, "loss": 0.1327, "lr": 6.870332654446707e-07, "epoch": 0.17184317718940936, "percentage": 3.44, "elapsed_time": "0:02:44", "remaining_time": "1:17:11", "throughput": 11795.57, "total_tokens": 1944576}
{"current_steps": 2030, "total_steps": 58920, "loss": 0.0611, "lr": 6.887304820095043e-07, "epoch": 0.17226748133061778, "percentage": 3.45, "elapsed_time": "0:02:45", "remaining_time": "1:17:15", "throughput": 11782.46, "total_tokens": 1948928}
{"current_steps": 2035, "total_steps": 58920, "loss": 0.1031, "lr": 6.90427698574338e-07, "epoch": 0.1726917854718262, "percentage": 3.45, "elapsed_time": "0:02:45", "remaining_time": "1:17:19", "throughput": 11770.41, "total_tokens": 1953600}
{"current_steps": 2040, "total_steps": 58920, "loss": 0.0724, "lr": 6.921249151391717e-07, "epoch": 0.17311608961303462, "percentage": 3.46, "elapsed_time": "0:02:46", "remaining_time": "1:17:23", "throughput": 11759.7, "total_tokens": 1958592}
{"current_steps": 2045, "total_steps": 58920, "loss": 0.0583, "lr": 6.938221317040053e-07, "epoch": 0.17354039375424304, "percentage": 3.47, "elapsed_time": "0:02:47", "remaining_time": "1:17:27", "throughput": 11745.95, "total_tokens": 1962752}
{"current_steps": 2050, "total_steps": 58920, "loss": 0.1333, "lr": 6.955193482688391e-07, "epoch": 0.17396469789545146, "percentage": 3.48, "elapsed_time": "0:02:47", "remaining_time": "1:17:31", "throughput": 11734.14, "total_tokens": 1967424}
{"current_steps": 2055, "total_steps": 58920, "loss": 0.1107, "lr": 6.972165648336727e-07, "epoch": 0.17438900203665988, "percentage": 3.49, "elapsed_time": "0:02:48", "remaining_time": "1:17:35", "throughput": 11725.26, "total_tokens": 1972736}
{"current_steps": 2060, "total_steps": 58920, "loss": 0.0453, "lr": 6.989137813985065e-07, "epoch": 0.1748133061778683, "percentage": 3.5, "elapsed_time": "0:02:48", "remaining_time": "1:17:39", "throughput": 11713.29, "total_tokens": 1977408}
{"current_steps": 2065, "total_steps": 58920, "loss": 0.0279, "lr": 7.006109979633401e-07, "epoch": 0.17523761031907673, "percentage": 3.5, "elapsed_time": "0:02:49", "remaining_time": "1:17:43", "throughput": 11701.83, "total_tokens": 1982016}
{"current_steps": 2070, "total_steps": 58920, "loss": 0.0896, "lr": 7.023082145281738e-07, "epoch": 0.17566191446028515, "percentage": 3.51, "elapsed_time": "0:02:49", "remaining_time": "1:17:47", "throughput": 11693.67, "total_tokens": 1987392}
{"current_steps": 2075, "total_steps": 58920, "loss": 0.0851, "lr": 7.040054310930075e-07, "epoch": 0.17608621860149354, "percentage": 3.52, "elapsed_time": "0:02:50", "remaining_time": "1:17:51", "throughput": 11682.69, "total_tokens": 1992064}
{"current_steps": 2080, "total_steps": 58920, "loss": 0.0606, "lr": 7.057026476578412e-07, "epoch": 0.17651052274270196, "percentage": 3.53, "elapsed_time": "0:02:51", "remaining_time": "1:17:55", "throughput": 11672.92, "total_tokens": 1997120}
{"current_steps": 2085, "total_steps": 58920, "loss": 0.0551, "lr": 7.073998642226748e-07, "epoch": 0.17693482688391038, "percentage": 3.54, "elapsed_time": "0:02:51", "remaining_time": "1:17:58", "throughput": 11661.38, "total_tokens": 2001664}
{"current_steps": 2090, "total_steps": 58920, "loss": 0.0865, "lr": 7.090970807875084e-07, "epoch": 0.1773591310251188, "percentage": 3.55, "elapsed_time": "0:02:52", "remaining_time": "1:18:02", "throughput": 11650.3, "total_tokens": 2006336}
{"current_steps": 2095, "total_steps": 58920, "loss": 0.0762, "lr": 7.107942973523421e-07, "epoch": 0.17778343516632722, "percentage": 3.56, "elapsed_time": "0:02:52", "remaining_time": "1:18:06", "throughput": 11640.12, "total_tokens": 2011264}
{"current_steps": 2100, "total_steps": 58920, "loss": 0.1098, "lr": 7.124915139171757e-07, "epoch": 0.17820773930753564, "percentage": 3.56, "elapsed_time": "0:02:53", "remaining_time": "1:18:10", "throughput": 11628.55, "total_tokens": 2015680}
{"current_steps": 2105, "total_steps": 58920, "loss": 0.1773, "lr": 7.141887304820095e-07, "epoch": 0.17863204344874406, "percentage": 3.57, "elapsed_time": "0:02:53", "remaining_time": "1:18:13", "throughput": 11617.91, "total_tokens": 2020352}
{"current_steps": 2110, "total_steps": 58920, "loss": 0.0507, "lr": 7.158859470468431e-07, "epoch": 0.17905634758995248, "percentage": 3.58, "elapsed_time": "0:02:54", "remaining_time": "1:18:17", "throughput": 11606.34, "total_tokens": 2024832}
{"current_steps": 2115, "total_steps": 58920, "loss": 0.0466, "lr": 7.175831636116768e-07, "epoch": 0.1794806517311609, "percentage": 3.59, "elapsed_time": "0:02:55", "remaining_time": "1:18:20", "throughput": 11595.04, "total_tokens": 2029184}
{"current_steps": 2120, "total_steps": 58920, "loss": 0.0741, "lr": 7.192803801765105e-07, "epoch": 0.17990495587236932, "percentage": 3.6, "elapsed_time": "0:02:55", "remaining_time": "1:18:24", "throughput": 11585.11, "total_tokens": 2034048}
{"current_steps": 2125, "total_steps": 58920, "loss": 0.0536, "lr": 7.209775967413442e-07, "epoch": 0.18032926001357774, "percentage": 3.61, "elapsed_time": "0:02:56", "remaining_time": "1:18:28", "throughput": 11576.23, "total_tokens": 2039232}
{"current_steps": 2130, "total_steps": 58920, "loss": 0.1064, "lr": 7.226748133061778e-07, "epoch": 0.18075356415478616, "percentage": 3.62, "elapsed_time": "0:02:56", "remaining_time": "1:18:31", "throughput": 11565.79, "total_tokens": 2043712}
{"current_steps": 2135, "total_steps": 58920, "loss": 0.0674, "lr": 7.243720298710116e-07, "epoch": 0.18117786829599458, "percentage": 3.62, "elapsed_time": "0:02:57", "remaining_time": "1:18:34", "throughput": 11556.37, "total_tokens": 2048576}
{"current_steps": 2140, "total_steps": 58920, "loss": 0.0944, "lr": 7.260692464358452e-07, "epoch": 0.18160217243720297, "percentage": 3.63, "elapsed_time": "0:02:57", "remaining_time": "1:18:38", "throughput": 11547.05, "total_tokens": 2053440}
{"current_steps": 2145, "total_steps": 58920, "loss": 0.0607, "lr": 7.277664630006789e-07, "epoch": 0.1820264765784114, "percentage": 3.64, "elapsed_time": "0:02:58", "remaining_time": "1:18:42", "throughput": 11537.19, "total_tokens": 2058304}
{"current_steps": 2150, "total_steps": 58920, "loss": 0.0657, "lr": 7.294636795655126e-07, "epoch": 0.18245078071961982, "percentage": 3.65, "elapsed_time": "0:02:58", "remaining_time": "1:18:45", "throughput": 11526.31, "total_tokens": 2062720}
{"current_steps": 2155, "total_steps": 58920, "loss": 0.0968, "lr": 7.311608961303461e-07, "epoch": 0.18287508486082824, "percentage": 3.66, "elapsed_time": "0:02:59", "remaining_time": "1:18:48", "throughput": 11516.15, "total_tokens": 2067264}
{"current_steps": 2160, "total_steps": 58920, "loss": 0.1136, "lr": 7.328581126951798e-07, "epoch": 0.18329938900203666, "percentage": 3.67, "elapsed_time": "0:03:00", "remaining_time": "1:18:51", "throughput": 11505.64, "total_tokens": 2071744}
{"current_steps": 2165, "total_steps": 58920, "loss": 0.0895, "lr": 7.345553292600135e-07, "epoch": 0.18372369314324508, "percentage": 3.67, "elapsed_time": "0:03:00", "remaining_time": "1:18:54", "throughput": 11495.8, "total_tokens": 2076352}
{"current_steps": 2170, "total_steps": 58920, "loss": 0.0583, "lr": 7.362525458248472e-07, "epoch": 0.1841479972844535, "percentage": 3.68, "elapsed_time": "0:03:01", "remaining_time": "1:18:58", "throughput": 11486.21, "total_tokens": 2081088}
{"current_steps": 2175, "total_steps": 58920, "loss": 0.0883, "lr": 7.379497623896808e-07, "epoch": 0.18457230142566192, "percentage": 3.69, "elapsed_time": "0:03:01", "remaining_time": "1:19:01", "throughput": 11476.05, "total_tokens": 2085760}
{"current_steps": 2180, "total_steps": 58920, "loss": 0.1022, "lr": 7.396469789545146e-07, "epoch": 0.18499660556687034, "percentage": 3.7, "elapsed_time": "0:03:02", "remaining_time": "1:19:05", "throughput": 11466.91, "total_tokens": 2090624}
{"current_steps": 2185, "total_steps": 58920, "loss": 0.1145, "lr": 7.413441955193482e-07, "epoch": 0.18542090970807876, "percentage": 3.71, "elapsed_time": "0:03:02", "remaining_time": "1:19:09", "throughput": 11459.33, "total_tokens": 2095936}
{"current_steps": 2190, "total_steps": 58920, "loss": 0.0918, "lr": 7.43041412084182e-07, "epoch": 0.18584521384928718, "percentage": 3.72, "elapsed_time": "0:03:03", "remaining_time": "1:19:12", "throughput": 11449.7, "total_tokens": 2100608}
{"current_steps": 2195, "total_steps": 58920, "loss": 0.0701, "lr": 7.447386286490156e-07, "epoch": 0.1862695179904956, "percentage": 3.73, "elapsed_time": "0:03:04", "remaining_time": "1:19:16", "throughput": 11441.94, "total_tokens": 2105856}
{"current_steps": 2200, "total_steps": 58920, "loss": 0.0567, "lr": 7.464358452138493e-07, "epoch": 0.18669382213170402, "percentage": 3.73, "elapsed_time": "0:03:04", "remaining_time": "1:19:19", "throughput": 11432.59, "total_tokens": 2110464}
{"current_steps": 2205, "total_steps": 58920, "loss": 0.0853, "lr": 7.48133061778683e-07, "epoch": 0.1871181262729124, "percentage": 3.74, "elapsed_time": "0:03:05", "remaining_time": "1:19:23", "throughput": 11424.66, "total_tokens": 2115648}
{"current_steps": 2210, "total_steps": 58920, "loss": 0.0565, "lr": 7.498302783435167e-07, "epoch": 0.18754243041412083, "percentage": 3.75, "elapsed_time": "0:03:05", "remaining_time": "1:19:26", "throughput": 11415.18, "total_tokens": 2120256}
{"current_steps": 2215, "total_steps": 58920, "loss": 0.1346, "lr": 7.515274949083503e-07, "epoch": 0.18796673455532925, "percentage": 3.76, "elapsed_time": "0:03:06", "remaining_time": "1:19:29", "throughput": 11405.04, "total_tokens": 2124672}
{"current_steps": 2220, "total_steps": 58920, "loss": 0.0943, "lr": 7.532247114731838e-07, "epoch": 0.18839103869653767, "percentage": 3.77, "elapsed_time": "0:03:06", "remaining_time": "1:19:32", "throughput": 11395.34, "total_tokens": 2129344}
{"current_steps": 2225, "total_steps": 58920, "loss": 0.0906, "lr": 7.549219280380176e-07, "epoch": 0.1888153428377461, "percentage": 3.78, "elapsed_time": "0:03:07", "remaining_time": "1:19:36", "throughput": 11386.95, "total_tokens": 2134336}
{"current_steps": 2230, "total_steps": 58920, "loss": 0.0732, "lr": 7.566191446028512e-07, "epoch": 0.1892396469789545, "percentage": 3.78, "elapsed_time": "0:03:08", "remaining_time": "1:19:39", "throughput": 11379.11, "total_tokens": 2139456}
{"current_steps": 2235, "total_steps": 58920, "loss": 0.1082, "lr": 7.58316361167685e-07, "epoch": 0.18966395112016293, "percentage": 3.79, "elapsed_time": "0:03:08", "remaining_time": "1:19:43", "throughput": 11371.7, "total_tokens": 2144640}
{"current_steps": 2240, "total_steps": 58920, "loss": 0.0885, "lr": 7.600135777325186e-07, "epoch": 0.19008825526137135, "percentage": 3.8, "elapsed_time": "0:03:09", "remaining_time": "1:19:46", "throughput": 11364.35, "total_tokens": 2149760}
{"current_steps": 2245, "total_steps": 58920, "loss": 0.1258, "lr": 7.617107942973523e-07, "epoch": 0.19051255940257977, "percentage": 3.81, "elapsed_time": "0:03:09", "remaining_time": "1:19:50", "throughput": 11357.97, "total_tokens": 2155200}
{"current_steps": 2250, "total_steps": 58920, "loss": 0.0962, "lr": 7.63408010862186e-07, "epoch": 0.1909368635437882, "percentage": 3.82, "elapsed_time": "0:03:10", "remaining_time": "1:19:53", "throughput": 11349.18, "total_tokens": 2159872}
{"current_steps": 2255, "total_steps": 58920, "loss": 0.117, "lr": 7.651052274270197e-07, "epoch": 0.1913611676849966, "percentage": 3.83, "elapsed_time": "0:03:10", "remaining_time": "1:19:56", "throughput": 11340.58, "total_tokens": 2164544}
{"current_steps": 2260, "total_steps": 58920, "loss": 0.0543, "lr": 7.668024439918533e-07, "epoch": 0.19178547182620503, "percentage": 3.84, "elapsed_time": "0:03:11", "remaining_time": "1:19:59", "throughput": 11333.58, "total_tokens": 2169856}
{"current_steps": 2265, "total_steps": 58920, "loss": 0.0602, "lr": 7.684996605566871e-07, "epoch": 0.19220977596741345, "percentage": 3.84, "elapsed_time": "0:03:12", "remaining_time": "1:20:10", "throughput": 11305.91, "total_tokens": 2174400}
{"current_steps": 2270, "total_steps": 58920, "loss": 0.0781, "lr": 7.701968771215207e-07, "epoch": 0.19263408010862185, "percentage": 3.85, "elapsed_time": "0:03:13", "remaining_time": "1:20:21", "throughput": 11278.51, "total_tokens": 2179200}
{"current_steps": 2275, "total_steps": 58920, "loss": 0.0883, "lr": 7.718940936863544e-07, "epoch": 0.19305838424983027, "percentage": 3.86, "elapsed_time": "0:03:14", "remaining_time": "1:20:33", "throughput": 11253.82, "total_tokens": 2184768}
{"current_steps": 2280, "total_steps": 58920, "loss": 0.0604, "lr": 7.735913102511881e-07, "epoch": 0.1934826883910387, "percentage": 3.87, "elapsed_time": "0:03:14", "remaining_time": "1:20:38", "throughput": 11243.05, "total_tokens": 2189824}
{"current_steps": 2285, "total_steps": 58920, "loss": 0.0682, "lr": 7.752885268160216e-07, "epoch": 0.1939069925322471, "percentage": 3.88, "elapsed_time": "0:03:15", "remaining_time": "1:20:41", "throughput": 11234.97, "total_tokens": 2194752}
{"current_steps": 2290, "total_steps": 58920, "loss": 0.1117, "lr": 7.769857433808553e-07, "epoch": 0.19433129667345553, "percentage": 3.89, "elapsed_time": "0:03:15", "remaining_time": "1:20:45", "throughput": 11226.59, "total_tokens": 2199552}
{"current_steps": 2295, "total_steps": 58920, "loss": 0.174, "lr": 7.78682959945689e-07, "epoch": 0.19475560081466395, "percentage": 3.9, "elapsed_time": "0:03:16", "remaining_time": "1:20:48", "throughput": 11218.3, "total_tokens": 2204288}
{"current_steps": 2300, "total_steps": 58920, "loss": 0.074, "lr": 7.803801765105227e-07, "epoch": 0.19517990495587237, "percentage": 3.9, "elapsed_time": "0:03:17", "remaining_time": "1:20:51", "throughput": 11210.93, "total_tokens": 2209344}
{"current_steps": 2305, "total_steps": 58920, "loss": 0.0997, "lr": 7.820773930753563e-07, "epoch": 0.1956042090970808, "percentage": 3.91, "elapsed_time": "0:03:17", "remaining_time": "1:20:54", "throughput": 11203.35, "total_tokens": 2214208}
{"current_steps": 2310, "total_steps": 58920, "loss": 0.08, "lr": 7.837746096401901e-07, "epoch": 0.1960285132382892, "percentage": 3.92, "elapsed_time": "0:03:18", "remaining_time": "1:20:56", "throughput": 11194.78, "total_tokens": 2218624}
{"current_steps": 2315, "total_steps": 58920, "loss": 0.0682, "lr": 7.854718262050237e-07, "epoch": 0.19645281737949763, "percentage": 3.93, "elapsed_time": "0:03:18", "remaining_time": "1:21:00", "throughput": 11188.32, "total_tokens": 2223872}
{"current_steps": 2320, "total_steps": 58920, "loss": 0.0537, "lr": 7.871690427698574e-07, "epoch": 0.19687712152070605, "percentage": 3.94, "elapsed_time": "0:03:19", "remaining_time": "1:21:02", "throughput": 11178.56, "total_tokens": 2228096}
{"current_steps": 2325, "total_steps": 58920, "loss": 0.1049, "lr": 7.888662593346911e-07, "epoch": 0.19730142566191447, "percentage": 3.95, "elapsed_time": "0:03:19", "remaining_time": "1:21:05", "throughput": 11169.08, "total_tokens": 2232384}
{"current_steps": 2330, "total_steps": 58920, "loss": 0.0548, "lr": 7.905634758995248e-07, "epoch": 0.1977257298031229, "percentage": 3.95, "elapsed_time": "0:03:20", "remaining_time": "1:21:08", "throughput": 11161.46, "total_tokens": 2237184}
{"current_steps": 2335, "total_steps": 58920, "loss": 0.0839, "lr": 7.922606924643584e-07, "epoch": 0.19815003394433128, "percentage": 3.96, "elapsed_time": "0:03:21", "remaining_time": "1:21:11", "throughput": 11154.09, "total_tokens": 2242048}
{"current_steps": 2340, "total_steps": 58920, "loss": 0.0476, "lr": 7.939579090291922e-07, "epoch": 0.1985743380855397, "percentage": 3.97, "elapsed_time": "0:03:21", "remaining_time": "1:21:14", "throughput": 11147.5, "total_tokens": 2247104}
{"current_steps": 2345, "total_steps": 58920, "loss": 0.0877, "lr": 7.956551255940258e-07, "epoch": 0.19899864222674812, "percentage": 3.98, "elapsed_time": "0:03:22", "remaining_time": "1:21:16", "throughput": 11140.17, "total_tokens": 2251840}
{"current_steps": 2350, "total_steps": 58920, "loss": 0.1035, "lr": 7.973523421588593e-07, "epoch": 0.19942294636795654, "percentage": 3.99, "elapsed_time": "0:03:22", "remaining_time": "1:21:19", "throughput": 11133.76, "total_tokens": 2256832}
{"current_steps": 2355, "total_steps": 58920, "loss": 0.0205, "lr": 7.990495587236931e-07, "epoch": 0.19984725050916496, "percentage": 4.0, "elapsed_time": "0:03:23", "remaining_time": "1:21:20", "throughput": 11128.08, "total_tokens": 2261120}
{"current_steps": 2360, "total_steps": 58920, "loss": 0.1332, "lr": 8.007467752885267e-07, "epoch": 0.20027155465037338, "percentage": 4.01, "elapsed_time": "0:03:23", "remaining_time": "1:21:19", "throughput": 11132.72, "total_tokens": 2266496}
{"current_steps": 2365, "total_steps": 58920, "loss": 0.0507, "lr": 8.024439918533604e-07, "epoch": 0.2006958587915818, "percentage": 4.01, "elapsed_time": "0:03:23", "remaining_time": "1:21:17", "throughput": 11134.27, "total_tokens": 2271040}
{"current_steps": 2370, "total_steps": 58920, "loss": 0.0547, "lr": 8.041412084181941e-07, "epoch": 0.20112016293279023, "percentage": 4.02, "elapsed_time": "0:03:24", "remaining_time": "1:21:16", "throughput": 11137.82, "total_tokens": 2276096}
{"current_steps": 2375, "total_steps": 58920, "loss": 0.0428, "lr": 8.058384249830278e-07, "epoch": 0.20154446707399865, "percentage": 4.03, "elapsed_time": "0:03:24", "remaining_time": "1:21:14", "throughput": 11137.68, "total_tokens": 2280192}
{"current_steps": 2380, "total_steps": 58920, "loss": 0.0616, "lr": 8.075356415478614e-07, "epoch": 0.20196877121520707, "percentage": 4.04, "elapsed_time": "0:03:25", "remaining_time": "1:21:12", "throughput": 11139.25, "total_tokens": 2284672}
{"current_steps": 2385, "total_steps": 58920, "loss": 0.0943, "lr": 8.092328581126952e-07, "epoch": 0.20239307535641549, "percentage": 4.05, "elapsed_time": "0:03:25", "remaining_time": "1:21:10", "throughput": 11142.67, "total_tokens": 2289664}
{"current_steps": 2390, "total_steps": 58920, "loss": 0.1601, "lr": 8.109300746775288e-07, "epoch": 0.2028173794976239, "percentage": 4.06, "elapsed_time": "0:03:25", "remaining_time": "1:21:09", "throughput": 11146.5, "total_tokens": 2294976}
{"current_steps": 2395, "total_steps": 58920, "loss": 0.0451, "lr": 8.126272912423626e-07, "epoch": 0.20324168363883233, "percentage": 4.06, "elapsed_time": "0:03:26", "remaining_time": "1:21:08", "throughput": 11148.58, "total_tokens": 2299584}
{"current_steps": 2400, "total_steps": 58920, "loss": 0.0709, "lr": 8.143245078071962e-07, "epoch": 0.20366598778004075, "percentage": 4.07, "elapsed_time": "0:03:26", "remaining_time": "1:21:06", "throughput": 11150.91, "total_tokens": 2304320}
{"current_steps": 2405, "total_steps": 58920, "loss": 0.1505, "lr": 8.160217243720299e-07, "epoch": 0.20409029192124914, "percentage": 4.08, "elapsed_time": "0:03:27", "remaining_time": "1:21:04", "throughput": 11152.8, "total_tokens": 2308928}
{"current_steps": 2410, "total_steps": 58920, "loss": 0.0358, "lr": 8.177189409368636e-07, "epoch": 0.20451459606245756, "percentage": 4.09, "elapsed_time": "0:03:27", "remaining_time": "1:21:03", "throughput": 11153.11, "total_tokens": 2313280}
{"current_steps": 2415, "total_steps": 58920, "loss": 0.1044, "lr": 8.194161575016971e-07, "epoch": 0.20493890020366598, "percentage": 4.1, "elapsed_time": "0:03:27", "remaining_time": "1:21:02", "throughput": 11156.67, "total_tokens": 2318400}
{"current_steps": 2420, "total_steps": 58920, "loss": 0.0764, "lr": 8.211133740665308e-07, "epoch": 0.2053632043448744, "percentage": 4.11, "elapsed_time": "0:03:28", "remaining_time": "1:21:00", "throughput": 11161.05, "total_tokens": 2323712}
{"current_steps": 2425, "total_steps": 58920, "loss": 0.0306, "lr": 8.228105906313645e-07, "epoch": 0.20578750848608282, "percentage": 4.12, "elapsed_time": "0:03:28", "remaining_time": "1:20:59", "throughput": 11161.43, "total_tokens": 2327936}
{"current_steps": 2430, "total_steps": 58920, "loss": 0.0529, "lr": 8.245078071961982e-07, "epoch": 0.20621181262729124, "percentage": 4.12, "elapsed_time": "0:03:28", "remaining_time": "1:20:57", "throughput": 11162.08, "total_tokens": 2332224}
{"current_steps": 2435, "total_steps": 58920, "loss": 0.088, "lr": 8.262050237610318e-07, "epoch": 0.20663611676849966, "percentage": 4.13, "elapsed_time": "0:03:29", "remaining_time": "1:20:55", "throughput": 11163.46, "total_tokens": 2336704}
{"current_steps": 2440, "total_steps": 58920, "loss": 0.0535, "lr": 8.279022403258656e-07, "epoch": 0.20706042090970808, "percentage": 4.14, "elapsed_time": "0:03:29", "remaining_time": "1:20:54", "throughput": 11167.38, "total_tokens": 2341888}
{"current_steps": 2445, "total_steps": 58920, "loss": 0.0715, "lr": 8.295994568906992e-07, "epoch": 0.2074847250509165, "percentage": 4.15, "elapsed_time": "0:03:30", "remaining_time": "1:20:52", "throughput": 11168.93, "total_tokens": 2346432}
{"current_steps": 2450, "total_steps": 58920, "loss": 0.0498, "lr": 8.312966734555329e-07, "epoch": 0.20790902919212492, "percentage": 4.16, "elapsed_time": "0:03:30", "remaining_time": "1:20:50", "throughput": 11169.23, "total_tokens": 2350656}
{"current_steps": 2455, "total_steps": 58920, "loss": 0.0572, "lr": 8.329938900203666e-07, "epoch": 0.20833333333333334, "percentage": 4.17, "elapsed_time": "0:03:30", "remaining_time": "1:20:49", "throughput": 11171.49, "total_tokens": 2355392}
{"current_steps": 2460, "total_steps": 58920, "loss": 0.0297, "lr": 8.346911065852003e-07, "epoch": 0.20875763747454176, "percentage": 4.18, "elapsed_time": "0:03:31", "remaining_time": "1:20:47", "throughput": 11174.37, "total_tokens": 2360320}
{"current_steps": 2465, "total_steps": 58920, "loss": 0.0099, "lr": 8.363883231500339e-07, "epoch": 0.20918194161575018, "percentage": 4.18, "elapsed_time": "0:03:31", "remaining_time": "1:20:46", "throughput": 11176.97, "total_tokens": 2365120}
{"current_steps": 2470, "total_steps": 58920, "loss": 0.1446, "lr": 8.380855397148677e-07, "epoch": 0.20960624575695858, "percentage": 4.19, "elapsed_time": "0:03:31", "remaining_time": "1:20:44", "throughput": 11179.32, "total_tokens": 2369920}
{"current_steps": 2475, "total_steps": 58920, "loss": 0.1496, "lr": 8.397827562797013e-07, "epoch": 0.210030549898167, "percentage": 4.2, "elapsed_time": "0:03:32", "remaining_time": "1:20:43", "throughput": 11182.12, "total_tokens": 2374848}
{"current_steps": 2480, "total_steps": 58920, "loss": 0.0684, "lr": 8.414799728445349e-07, "epoch": 0.21045485403937542, "percentage": 4.21, "elapsed_time": "0:03:32", "remaining_time": "1:20:42", "throughput": 11185.86, "total_tokens": 2380032}
{"current_steps": 2485, "total_steps": 58920, "loss": 0.1308, "lr": 8.431771894093686e-07, "epoch": 0.21087915818058384, "percentage": 4.22, "elapsed_time": "0:03:33", "remaining_time": "1:20:40", "throughput": 11187.79, "total_tokens": 2384704}
{"current_steps": 2490, "total_steps": 58920, "loss": 0.0978, "lr": 8.448744059742022e-07, "epoch": 0.21130346232179226, "percentage": 4.23, "elapsed_time": "0:03:33", "remaining_time": "1:20:39", "throughput": 11190.65, "total_tokens": 2389568}
{"current_steps": 2495, "total_steps": 58920, "loss": 0.1443, "lr": 8.465716225390359e-07, "epoch": 0.21172776646300068, "percentage": 4.23, "elapsed_time": "0:03:33", "remaining_time": "1:20:37", "throughput": 11193.63, "total_tokens": 2394560}
{"current_steps": 2500, "total_steps": 58920, "loss": 0.0647, "lr": 8.482688391038696e-07, "epoch": 0.2121520706042091, "percentage": 4.24, "elapsed_time": "0:03:34", "remaining_time": "1:20:36", "throughput": 11194.96, "total_tokens": 2399232}
{"current_steps": 2505, "total_steps": 58920, "loss": 0.1339, "lr": 8.499660556687033e-07, "epoch": 0.21257637474541752, "percentage": 4.25, "elapsed_time": "0:03:34", "remaining_time": "1:20:35", "throughput": 11197.38, "total_tokens": 2404032}
{"current_steps": 2510, "total_steps": 58920, "loss": 0.0863, "lr": 8.516632722335369e-07, "epoch": 0.21300067888662594, "percentage": 4.26, "elapsed_time": "0:03:35", "remaining_time": "1:20:33", "throughput": 11198.84, "total_tokens": 2408576}
{"current_steps": 2515, "total_steps": 58920, "loss": 0.0584, "lr": 8.533604887983707e-07, "epoch": 0.21342498302783436, "percentage": 4.27, "elapsed_time": "0:03:35", "remaining_time": "1:20:32", "throughput": 11201.32, "total_tokens": 2413440}
{"current_steps": 2520, "total_steps": 58920, "loss": 0.0651, "lr": 8.550577053632043e-07, "epoch": 0.21384928716904278, "percentage": 4.28, "elapsed_time": "0:03:35", "remaining_time": "1:20:30", "throughput": 11201.68, "total_tokens": 2417664}
{"current_steps": 2525, "total_steps": 58920, "loss": 0.1096, "lr": 8.56754921928038e-07, "epoch": 0.2142735913102512, "percentage": 4.29, "elapsed_time": "0:03:36", "remaining_time": "1:20:29", "throughput": 11204.08, "total_tokens": 2422464}
{"current_steps": 2530, "total_steps": 58920, "loss": 0.0522, "lr": 8.584521384928717e-07, "epoch": 0.21469789545145962, "percentage": 4.29, "elapsed_time": "0:03:36", "remaining_time": "1:20:27", "throughput": 11206.23, "total_tokens": 2427200}
{"current_steps": 2535, "total_steps": 58920, "loss": 0.0411, "lr": 8.601493550577053e-07, "epoch": 0.215122199592668, "percentage": 4.3, "elapsed_time": "0:03:36", "remaining_time": "1:20:25", "throughput": 11207.32, "total_tokens": 2431616}
{"current_steps": 2540, "total_steps": 58920, "loss": 0.0528, "lr": 8.61846571622539e-07, "epoch": 0.21554650373387643, "percentage": 4.31, "elapsed_time": "0:03:37", "remaining_time": "1:20:24", "throughput": 11209.49, "total_tokens": 2436352}
{"current_steps": 2545, "total_steps": 58920, "loss": 0.0508, "lr": 8.635437881873727e-07, "epoch": 0.21597080787508485, "percentage": 4.32, "elapsed_time": "0:03:37", "remaining_time": "1:20:22", "throughput": 11210.31, "total_tokens": 2440704}
{"current_steps": 2550, "total_steps": 58920, "loss": 0.028, "lr": 8.652410047522063e-07, "epoch": 0.21639511201629327, "percentage": 4.33, "elapsed_time": "0:03:38", "remaining_time": "1:20:21", "throughput": 11215.37, "total_tokens": 2446272}
{"current_steps": 2555, "total_steps": 58920, "loss": 0.064, "lr": 8.669382213170399e-07, "epoch": 0.2168194161575017, "percentage": 4.34, "elapsed_time": "0:03:38", "remaining_time": "1:20:20", "throughput": 11215.67, "total_tokens": 2450496}
{"current_steps": 2560, "total_steps": 58920, "loss": 0.0409, "lr": 8.686354378818737e-07, "epoch": 0.2172437202987101, "percentage": 4.34, "elapsed_time": "0:03:38", "remaining_time": "1:20:18", "throughput": 11218.55, "total_tokens": 2455424}
{"current_steps": 2565, "total_steps": 58920, "loss": 0.0902, "lr": 8.703326544467073e-07, "epoch": 0.21766802443991853, "percentage": 4.35, "elapsed_time": "0:03:39", "remaining_time": "1:20:17", "throughput": 11221.34, "total_tokens": 2460352}
{"current_steps": 2570, "total_steps": 58920, "loss": 0.1553, "lr": 8.72029871011541e-07, "epoch": 0.21809232858112695, "percentage": 4.36, "elapsed_time": "0:03:39", "remaining_time": "1:20:15", "throughput": 11222.95, "total_tokens": 2464896}
{"current_steps": 2575, "total_steps": 58920, "loss": 0.1566, "lr": 8.737270875763747e-07, "epoch": 0.21851663272233537, "percentage": 4.37, "elapsed_time": "0:03:40", "remaining_time": "1:20:14", "throughput": 11225.66, "total_tokens": 2469824}
{"current_steps": 2580, "total_steps": 58920, "loss": 0.1308, "lr": 8.754243041412084e-07, "epoch": 0.2189409368635438, "percentage": 4.38, "elapsed_time": "0:03:40", "remaining_time": "1:20:12", "throughput": 11226.48, "total_tokens": 2474176}
{"current_steps": 2585, "total_steps": 58920, "loss": 0.2157, "lr": 8.771215207060421e-07, "epoch": 0.21936524100475221, "percentage": 4.39, "elapsed_time": "0:03:40", "remaining_time": "1:20:11", "throughput": 11229.79, "total_tokens": 2479232}
{"current_steps": 2590, "total_steps": 58920, "loss": 0.1075, "lr": 8.788187372708758e-07, "epoch": 0.21978954514596064, "percentage": 4.4, "elapsed_time": "0:03:41", "remaining_time": "1:20:09", "throughput": 11230.74, "total_tokens": 2483648}
{"current_steps": 2595, "total_steps": 58920, "loss": 0.056, "lr": 8.805159538357094e-07, "epoch": 0.22021384928716906, "percentage": 4.4, "elapsed_time": "0:03:41", "remaining_time": "1:20:08", "throughput": 11231.65, "total_tokens": 2488064}
{"current_steps": 2600, "total_steps": 58920, "loss": 0.065, "lr": 8.822131704005431e-07, "epoch": 0.22063815342837745, "percentage": 4.41, "elapsed_time": "0:03:41", "remaining_time": "1:20:06", "throughput": 11234.96, "total_tokens": 2493184}
{"current_steps": 2605, "total_steps": 58920, "loss": 0.1061, "lr": 8.839103869653768e-07, "epoch": 0.22106245756958587, "percentage": 4.42, "elapsed_time": "0:03:42", "remaining_time": "1:20:05", "throughput": 11236.76, "total_tokens": 2498048}
{"current_steps": 2610, "total_steps": 58920, "loss": 0.1285, "lr": 8.856076035302104e-07, "epoch": 0.2214867617107943, "percentage": 4.43, "elapsed_time": "0:03:42", "remaining_time": "1:20:05", "throughput": 11242.83, "total_tokens": 2504064}
{"current_steps": 2615, "total_steps": 58920, "loss": 0.0746, "lr": 8.873048200950441e-07, "epoch": 0.2219110658520027, "percentage": 4.44, "elapsed_time": "0:03:43", "remaining_time": "1:20:03", "throughput": 11244.9, "total_tokens": 2508800}
{"current_steps": 2620, "total_steps": 58920, "loss": 0.0371, "lr": 8.890020366598777e-07, "epoch": 0.22233536999321113, "percentage": 4.45, "elapsed_time": "0:03:43", "remaining_time": "1:20:02", "throughput": 11245.94, "total_tokens": 2513280}
{"current_steps": 2625, "total_steps": 58920, "loss": 0.0694, "lr": 8.906992532247114e-07, "epoch": 0.22275967413441955, "percentage": 4.46, "elapsed_time": "0:03:43", "remaining_time": "1:20:00", "throughput": 11248.19, "total_tokens": 2518080}
{"current_steps": 2630, "total_steps": 58920, "loss": 0.0772, "lr": 8.923964697895451e-07, "epoch": 0.22318397827562797, "percentage": 4.46, "elapsed_time": "0:03:44", "remaining_time": "1:19:59", "throughput": 11249.81, "total_tokens": 2522688}
{"current_steps": 2635, "total_steps": 58920, "loss": 0.0623, "lr": 8.940936863543788e-07, "epoch": 0.2236082824168364, "percentage": 4.47, "elapsed_time": "0:03:44", "remaining_time": "1:19:57", "throughput": 11250.57, "total_tokens": 2527040}
{"current_steps": 2640, "total_steps": 58920, "loss": 0.0958, "lr": 8.957909029192124e-07, "epoch": 0.2240325865580448, "percentage": 4.48, "elapsed_time": "0:03:44", "remaining_time": "1:19:56", "throughput": 11251.98, "total_tokens": 2531584}
{"current_steps": 2645, "total_steps": 58920, "loss": 0.1412, "lr": 8.974881194840462e-07, "epoch": 0.22445689069925323, "percentage": 4.49, "elapsed_time": "0:03:45", "remaining_time": "1:19:55", "throughput": 11254.09, "total_tokens": 2536384}
{"current_steps": 2650, "total_steps": 58920, "loss": 0.1138, "lr": 8.991853360488798e-07, "epoch": 0.22488119484046165, "percentage": 4.5, "elapsed_time": "0:03:45", "remaining_time": "1:19:53", "throughput": 11254.92, "total_tokens": 2540800}
{"current_steps": 2655, "total_steps": 58920, "loss": 0.0188, "lr": 9.008825526137135e-07, "epoch": 0.22530549898167007, "percentage": 4.51, "elapsed_time": "0:03:46", "remaining_time": "1:19:52", "throughput": 11257.13, "total_tokens": 2545600}
{"current_steps": 2660, "total_steps": 58920, "loss": 0.1499, "lr": 9.025797691785472e-07, "epoch": 0.2257298031228785, "percentage": 4.51, "elapsed_time": "0:03:46", "remaining_time": "1:19:50", "throughput": 11259.82, "total_tokens": 2550528}
{"current_steps": 2665, "total_steps": 58920, "loss": 0.0871, "lr": 9.042769857433808e-07, "epoch": 0.22615410726408688, "percentage": 4.52, "elapsed_time": "0:03:46", "remaining_time": "1:19:49", "throughput": 11262.15, "total_tokens": 2555328}
{"current_steps": 2670, "total_steps": 58920, "loss": 0.1205, "lr": 9.059742023082145e-07, "epoch": 0.2265784114052953, "percentage": 4.53, "elapsed_time": "0:03:47", "remaining_time": "1:19:48", "throughput": 11265.01, "total_tokens": 2560320}
{"current_steps": 2675, "total_steps": 58920, "loss": 0.0513, "lr": 9.076714188730482e-07, "epoch": 0.22700271554650372, "percentage": 4.54, "elapsed_time": "0:03:47", "remaining_time": "1:19:46", "throughput": 11266.21, "total_tokens": 2564800}
{"current_steps": 2680, "total_steps": 58920, "loss": 0.065, "lr": 9.093686354378818e-07, "epoch": 0.22742701968771215, "percentage": 4.55, "elapsed_time": "0:03:48", "remaining_time": "1:19:45", "throughput": 11268.47, "total_tokens": 2569664}
{"current_steps": 2685, "total_steps": 58920, "loss": 0.0421, "lr": 9.110658520027154e-07, "epoch": 0.22785132382892057, "percentage": 4.56, "elapsed_time": "0:03:48", "remaining_time": "1:19:44", "throughput": 11271.04, "total_tokens": 2574592}
{"current_steps": 2690, "total_steps": 58920, "loss": 0.1114, "lr": 9.127630685675492e-07, "epoch": 0.22827562797012899, "percentage": 4.57, "elapsed_time": "0:03:48", "remaining_time": "1:19:42", "throughput": 11273.01, "total_tokens": 2579328}
{"current_steps": 2695, "total_steps": 58920, "loss": 0.0255, "lr": 9.144602851323828e-07, "epoch": 0.2286999321113374, "percentage": 4.57, "elapsed_time": "0:03:49", "remaining_time": "1:19:41", "throughput": 11277.57, "total_tokens": 2584896}
{"current_steps": 2700, "total_steps": 58920, "loss": 0.1233, "lr": 9.161575016972165e-07, "epoch": 0.22912423625254583, "percentage": 4.58, "elapsed_time": "0:03:49", "remaining_time": "1:19:40", "throughput": 11279.08, "total_tokens": 2589504}
{"current_steps": 2705, "total_steps": 58920, "loss": 0.0942, "lr": 9.178547182620502e-07, "epoch": 0.22954854039375425, "percentage": 4.59, "elapsed_time": "0:03:49", "remaining_time": "1:19:39", "throughput": 11281.13, "total_tokens": 2594304}
{"current_steps": 2710, "total_steps": 58920, "loss": 0.0754, "lr": 9.195519348268839e-07, "epoch": 0.22997284453496267, "percentage": 4.6, "elapsed_time": "0:03:50", "remaining_time": "1:19:37", "throughput": 11282.12, "total_tokens": 2598784}
{"current_steps": 2715, "total_steps": 58920, "loss": 0.1075, "lr": 9.212491513917175e-07, "epoch": 0.2303971486761711, "percentage": 4.61, "elapsed_time": "0:03:50", "remaining_time": "1:19:36", "throughput": 11284.57, "total_tokens": 2603712}
{"current_steps": 2720, "total_steps": 58920, "loss": 0.0692, "lr": 9.229463679565513e-07, "epoch": 0.2308214528173795, "percentage": 4.62, "elapsed_time": "0:03:51", "remaining_time": "1:19:35", "throughput": 11286.12, "total_tokens": 2608320}
{"current_steps": 2725, "total_steps": 58920, "loss": 0.0281, "lr": 9.246435845213849e-07, "epoch": 0.23124575695858793, "percentage": 4.62, "elapsed_time": "0:03:51", "remaining_time": "1:19:33", "throughput": 11288.65, "total_tokens": 2613248}
{"current_steps": 2730, "total_steps": 58920, "loss": 0.0922, "lr": 9.263408010862185e-07, "epoch": 0.23167006109979632, "percentage": 4.63, "elapsed_time": "0:03:51", "remaining_time": "1:19:32", "throughput": 11289.43, "total_tokens": 2617664}
{"current_steps": 2735, "total_steps": 58920, "loss": 0.0539, "lr": 9.280380176510523e-07, "epoch": 0.23209436524100474, "percentage": 4.64, "elapsed_time": "0:03:52", "remaining_time": "1:19:30", "throughput": 11289.93, "total_tokens": 2622016}
{"current_steps": 2740, "total_steps": 58920, "loss": 0.0521, "lr": 9.297352342158859e-07, "epoch": 0.23251866938221316, "percentage": 4.65, "elapsed_time": "0:03:52", "remaining_time": "1:19:29", "throughput": 11290.6, "total_tokens": 2626368}
{"current_steps": 2745, "total_steps": 58920, "loss": 0.0036, "lr": 9.314324507807195e-07, "epoch": 0.23294297352342158, "percentage": 4.66, "elapsed_time": "0:03:52", "remaining_time": "1:19:27", "throughput": 11291.24, "total_tokens": 2630720}
{"current_steps": 2750, "total_steps": 58920, "loss": 0.1086, "lr": 9.331296673455532e-07, "epoch": 0.23336727766463, "percentage": 4.67, "elapsed_time": "0:03:53", "remaining_time": "1:19:26", "throughput": 11293.04, "total_tokens": 2635456}
{"current_steps": 2755, "total_steps": 58920, "loss": 0.1003, "lr": 9.348268839103869e-07, "epoch": 0.23379158180583842, "percentage": 4.68, "elapsed_time": "0:03:53", "remaining_time": "1:19:25", "throughput": 11293.39, "total_tokens": 2639744}
{"current_steps": 2760, "total_steps": 58920, "loss": 0.1101, "lr": 9.365241004752206e-07, "epoch": 0.23421588594704684, "percentage": 4.68, "elapsed_time": "0:03:54", "remaining_time": "1:19:23", "throughput": 11293.44, "total_tokens": 2643904}
{"current_steps": 2765, "total_steps": 58920, "loss": 0.0551, "lr": 9.382213170400543e-07, "epoch": 0.23464019008825526, "percentage": 4.69, "elapsed_time": "0:03:54", "remaining_time": "1:19:22", "throughput": 11295.86, "total_tokens": 2648768}
{"current_steps": 2770, "total_steps": 58920, "loss": 0.0511, "lr": 9.399185336048879e-07, "epoch": 0.23506449422946368, "percentage": 4.7, "elapsed_time": "0:03:54", "remaining_time": "1:19:21", "throughput": 11299.04, "total_tokens": 2653952}
{"current_steps": 2775, "total_steps": 58920, "loss": 0.0259, "lr": 9.416157501697217e-07, "epoch": 0.2354887983706721, "percentage": 4.71, "elapsed_time": "0:03:55", "remaining_time": "1:19:19", "throughput": 11299.93, "total_tokens": 2658432}
{"current_steps": 2780, "total_steps": 58920, "loss": 0.0534, "lr": 9.433129667345553e-07, "epoch": 0.23591310251188052, "percentage": 4.72, "elapsed_time": "0:03:55", "remaining_time": "1:19:18", "throughput": 11301.69, "total_tokens": 2663168}
{"current_steps": 2785, "total_steps": 58920, "loss": 0.1091, "lr": 9.450101832993889e-07, "epoch": 0.23633740665308894, "percentage": 4.73, "elapsed_time": "0:03:56", "remaining_time": "1:19:17", "throughput": 11303.92, "total_tokens": 2668096}
{"current_steps": 2790, "total_steps": 58920, "loss": 0.2111, "lr": 9.467073998642227e-07, "epoch": 0.23676171079429736, "percentage": 4.74, "elapsed_time": "0:03:56", "remaining_time": "1:19:16", "throughput": 11304.93, "total_tokens": 2672576}
{"current_steps": 2795, "total_steps": 58920, "loss": 0.0961, "lr": 9.484046164290563e-07, "epoch": 0.23718601493550576, "percentage": 4.74, "elapsed_time": "0:03:56", "remaining_time": "1:19:15", "throughput": 11309.91, "total_tokens": 2678336}
{"current_steps": 2800, "total_steps": 58920, "loss": 0.099, "lr": 9.5010183299389e-07, "epoch": 0.23761031907671418, "percentage": 4.75, "elapsed_time": "0:03:57", "remaining_time": "1:19:14", "throughput": 11315.42, "total_tokens": 2684288}
{"current_steps": 2805, "total_steps": 58920, "loss": 0.0542, "lr": 9.517990495587237e-07, "epoch": 0.2380346232179226, "percentage": 4.76, "elapsed_time": "0:03:57", "remaining_time": "1:19:13", "throughput": 11316.13, "total_tokens": 2688704}
{"current_steps": 2810, "total_steps": 58920, "loss": 0.0533, "lr": 9.534962661235573e-07, "epoch": 0.23845892735913102, "percentage": 4.77, "elapsed_time": "0:03:57", "remaining_time": "1:19:11", "throughput": 11316.81, "total_tokens": 2693056}
{"current_steps": 2815, "total_steps": 58920, "loss": 0.1039, "lr": 9.55193482688391e-07, "epoch": 0.23888323150033944, "percentage": 4.78, "elapsed_time": "0:03:58", "remaining_time": "1:19:10", "throughput": 11316.87, "total_tokens": 2697280}
{"current_steps": 2820, "total_steps": 58920, "loss": 0.0789, "lr": 9.568906992532247e-07, "epoch": 0.23930753564154786, "percentage": 4.79, "elapsed_time": "0:03:58", "remaining_time": "1:19:08", "throughput": 11316.7, "total_tokens": 2701440}
{"current_steps": 2825, "total_steps": 58920, "loss": 0.0796, "lr": 9.585879158180584e-07, "epoch": 0.23973183978275628, "percentage": 4.79, "elapsed_time": "0:03:59", "remaining_time": "1:19:08", "throughput": 11321.65, "total_tokens": 2707264}
{"current_steps": 2830, "total_steps": 58920, "loss": 0.1553, "lr": 9.60285132382892e-07, "epoch": 0.2401561439239647, "percentage": 4.8, "elapsed_time": "0:03:59", "remaining_time": "1:19:06", "throughput": 11322.34, "total_tokens": 2711680}
{"current_steps": 2835, "total_steps": 58920, "loss": 0.0363, "lr": 9.619823489477257e-07, "epoch": 0.24058044806517312, "percentage": 4.81, "elapsed_time": "0:03:59", "remaining_time": "1:19:05", "throughput": 11323.82, "total_tokens": 2716352}
{"current_steps": 2840, "total_steps": 58920, "loss": 0.1048, "lr": 9.636795655125594e-07, "epoch": 0.24100475220638154, "percentage": 4.82, "elapsed_time": "0:04:00", "remaining_time": "1:19:04", "throughput": 11325.26, "total_tokens": 2721024}
{"current_steps": 2845, "total_steps": 58920, "loss": 0.0697, "lr": 9.653767820773931e-07, "epoch": 0.24142905634758996, "percentage": 4.83, "elapsed_time": "0:04:00", "remaining_time": "1:19:03", "throughput": 11326.72, "total_tokens": 2725696}
{"current_steps": 2850, "total_steps": 58920, "loss": 0.0141, "lr": 9.670739986422267e-07, "epoch": 0.24185336048879838, "percentage": 4.84, "elapsed_time": "0:04:01", "remaining_time": "1:19:02", "throughput": 11331.12, "total_tokens": 2731328}
{"current_steps": 2855, "total_steps": 58920, "loss": 0.0928, "lr": 9.687712152070604e-07, "epoch": 0.2422776646300068, "percentage": 4.85, "elapsed_time": "0:04:01", "remaining_time": "1:19:01", "throughput": 11333.21, "total_tokens": 2736192}
{"current_steps": 2860, "total_steps": 58920, "loss": 0.114, "lr": 9.704684317718941e-07, "epoch": 0.24270196877121522, "percentage": 4.85, "elapsed_time": "0:04:01", "remaining_time": "1:18:59", "throughput": 11333.81, "total_tokens": 2740544}
{"current_steps": 2865, "total_steps": 58920, "loss": 0.0822, "lr": 9.721656483367277e-07, "epoch": 0.2431262729124236, "percentage": 4.86, "elapsed_time": "0:04:02", "remaining_time": "1:18:58", "throughput": 11335.97, "total_tokens": 2745472}
{"current_steps": 2870, "total_steps": 58920, "loss": 0.0208, "lr": 9.738628649015614e-07, "epoch": 0.24355057705363203, "percentage": 4.87, "elapsed_time": "0:04:02", "remaining_time": "1:18:57", "throughput": 11338.85, "total_tokens": 2750528}
{"current_steps": 2875, "total_steps": 58920, "loss": 0.0867, "lr": 9.75560081466395e-07, "epoch": 0.24397488119484045, "percentage": 4.88, "elapsed_time": "0:04:02", "remaining_time": "1:18:56", "throughput": 11340.86, "total_tokens": 2755328}
{"current_steps": 2880, "total_steps": 58920, "loss": 0.0817, "lr": 9.772572980312287e-07, "epoch": 0.24439918533604887, "percentage": 4.89, "elapsed_time": "0:04:03", "remaining_time": "1:18:55", "throughput": 11342.54, "total_tokens": 2760128}
{"current_steps": 2885, "total_steps": 58920, "loss": 0.0312, "lr": 9.789545145960624e-07, "epoch": 0.2448234894772573, "percentage": 4.9, "elapsed_time": "0:04:03", "remaining_time": "1:18:53", "throughput": 11344.52, "total_tokens": 2764992}
{"current_steps": 2890, "total_steps": 58920, "loss": 0.0753, "lr": 9.806517311608961e-07, "epoch": 0.24524779361846571, "percentage": 4.9, "elapsed_time": "0:04:04", "remaining_time": "1:18:52", "throughput": 11345.21, "total_tokens": 2769408}
{"current_steps": 2895, "total_steps": 58920, "loss": 0.1167, "lr": 9.823489477257297e-07, "epoch": 0.24567209775967414, "percentage": 4.91, "elapsed_time": "0:04:04", "remaining_time": "1:18:51", "throughput": 11347.36, "total_tokens": 2774336}
{"current_steps": 2900, "total_steps": 58920, "loss": 0.1386, "lr": 9.840461642905634e-07, "epoch": 0.24609640190088256, "percentage": 4.92, "elapsed_time": "0:04:04", "remaining_time": "1:18:50", "throughput": 11349.23, "total_tokens": 2779136}
{"current_steps": 2905, "total_steps": 58920, "loss": 0.0926, "lr": 9.857433808553971e-07, "epoch": 0.24652070604209098, "percentage": 4.93, "elapsed_time": "0:04:05", "remaining_time": "1:18:49", "throughput": 11352.06, "total_tokens": 2784256}
{"current_steps": 2910, "total_steps": 58920, "loss": 0.1149, "lr": 9.874405974202307e-07, "epoch": 0.2469450101832994, "percentage": 4.94, "elapsed_time": "0:04:05", "remaining_time": "1:18:47", "throughput": 11353.37, "total_tokens": 2788864}
{"current_steps": 2915, "total_steps": 58920, "loss": 0.055, "lr": 9.891378139850644e-07, "epoch": 0.24736931432450782, "percentage": 4.95, "elapsed_time": "0:04:06", "remaining_time": "1:18:46", "throughput": 11353.66, "total_tokens": 2793152}
{"current_steps": 2920, "total_steps": 58920, "loss": 0.0816, "lr": 9.908350305498982e-07, "epoch": 0.24779361846571624, "percentage": 4.96, "elapsed_time": "0:04:06", "remaining_time": "1:18:45", "throughput": 11356.12, "total_tokens": 2798144}
{"current_steps": 2925, "total_steps": 58920, "loss": 0.0882, "lr": 9.925322471147319e-07, "epoch": 0.24821792260692466, "percentage": 4.96, "elapsed_time": "0:04:06", "remaining_time": "1:18:44", "throughput": 11358.4, "total_tokens": 2803136}
{"current_steps": 2930, "total_steps": 58920, "loss": 0.0675, "lr": 9.942294636795654e-07, "epoch": 0.24864222674813305, "percentage": 4.97, "elapsed_time": "0:04:07", "remaining_time": "1:18:43", "throughput": 11359.8, "total_tokens": 2807744}
{"current_steps": 2935, "total_steps": 58920, "loss": 0.0672, "lr": 9.959266802443992e-07, "epoch": 0.24906653088934147, "percentage": 4.98, "elapsed_time": "0:04:07", "remaining_time": "1:18:42", "throughput": 11362.67, "total_tokens": 2812928}
{"current_steps": 2940, "total_steps": 58920, "loss": 0.0417, "lr": 9.976238968092329e-07, "epoch": 0.2494908350305499, "percentage": 4.99, "elapsed_time": "0:04:07", "remaining_time": "1:18:40", "throughput": 11363.75, "total_tokens": 2817536}
{"current_steps": 2945, "total_steps": 58920, "loss": 0.0827, "lr": 9.993211133740664e-07, "epoch": 0.2499151391717583, "percentage": 5.0, "elapsed_time": "0:04:08", "remaining_time": "1:18:39", "throughput": 11366.96, "total_tokens": 2822784}
{"current_steps": 2946, "total_steps": 58920, "eval_loss": 0.07831459492444992, "epoch": 0.25, "percentage": 5.0, "elapsed_time": "0:04:24", "remaining_time": "1:23:50", "throughput": 10663.96, "total_tokens": 2823680}
{"current_steps": 2950, "total_steps": 58920, "loss": 0.0765, "lr": 1.0010183299389002e-06, "epoch": 0.25033944331296676, "percentage": 5.01, "elapsed_time": "0:04:58", "remaining_time": "1:34:22", "throughput": 9473.66, "total_tokens": 2827328}
{"current_steps": 2955, "total_steps": 58920, "loss": 0.0638, "lr": 1.0027155465037339e-06, "epoch": 0.2507637474541752, "percentage": 5.02, "elapsed_time": "0:04:58", "remaining_time": "1:34:19", "throughput": 9477.58, "total_tokens": 2832128}
{"current_steps": 2960, "total_steps": 58920, "loss": 0.0978, "lr": 1.0044127630685674e-06, "epoch": 0.25118805159538354, "percentage": 5.02, "elapsed_time": "0:04:59", "remaining_time": "1:34:17", "throughput": 9483.84, "total_tokens": 2837824}
{"current_steps": 2965, "total_steps": 58920, "loss": 0.0913, "lr": 1.0061099796334012e-06, "epoch": 0.25161235573659196, "percentage": 5.03, "elapsed_time": "0:04:59", "remaining_time": "1:34:14", "throughput": 9486.74, "total_tokens": 2842240}
{"current_steps": 2970, "total_steps": 58920, "loss": 0.0418, "lr": 1.007807196198235e-06, "epoch": 0.2520366598778004, "percentage": 5.04, "elapsed_time": "0:04:59", "remaining_time": "1:34:11", "throughput": 9490.13, "total_tokens": 2846848}
{"current_steps": 2975, "total_steps": 58920, "loss": 0.11, "lr": 1.0095044127630684e-06, "epoch": 0.2524609640190088, "percentage": 5.05, "elapsed_time": "0:05:00", "remaining_time": "1:34:08", "throughput": 9493.2, "total_tokens": 2851392}
{"current_steps": 2980, "total_steps": 58920, "loss": 0.0754, "lr": 1.0112016293279022e-06, "epoch": 0.2528852681602172, "percentage": 5.06, "elapsed_time": "0:05:00", "remaining_time": "1:34:05", "throughput": 9495.58, "total_tokens": 2855680}
{"current_steps": 2985, "total_steps": 58920, "loss": 0.0761, "lr": 1.012898845892736e-06, "epoch": 0.25330957230142565, "percentage": 5.07, "elapsed_time": "0:05:01", "remaining_time": "1:34:02", "throughput": 9499.61, "total_tokens": 2860544}
{"current_steps": 2990, "total_steps": 58920, "loss": 0.0743, "lr": 1.0145960624575696e-06, "epoch": 0.25373387644263407, "percentage": 5.07, "elapsed_time": "0:05:01", "remaining_time": "1:33:59", "throughput": 9502.87, "total_tokens": 2865152}
{"current_steps": 2995, "total_steps": 58920, "loss": 0.0615, "lr": 1.0162932790224032e-06, "epoch": 0.2541581805838425, "percentage": 5.08, "elapsed_time": "0:05:01", "remaining_time": "1:33:57", "throughput": 9507.25, "total_tokens": 2870144}
{"current_steps": 3000, "total_steps": 58920, "loss": 0.0731, "lr": 1.017990495587237e-06, "epoch": 0.2545824847250509, "percentage": 5.09, "elapsed_time": "0:05:02", "remaining_time": "1:33:54", "throughput": 9511.67, "total_tokens": 2875200}
{"current_steps": 3005, "total_steps": 58920, "loss": 0.0738, "lr": 1.0196877121520706e-06, "epoch": 0.2550067888662593, "percentage": 5.1, "elapsed_time": "0:05:02", "remaining_time": "1:33:51", "throughput": 9515.93, "total_tokens": 2880192}
{"current_steps": 3010, "total_steps": 58920, "loss": 0.1574, "lr": 1.0213849287169044e-06, "epoch": 0.25543109300746775, "percentage": 5.11, "elapsed_time": "0:05:03", "remaining_time": "1:33:49", "throughput": 9519.26, "total_tokens": 2884800}
{"current_steps": 3015, "total_steps": 58920, "loss": 0.1005, "lr": 1.023082145281738e-06, "epoch": 0.25585539714867617, "percentage": 5.12, "elapsed_time": "0:05:03", "remaining_time": "1:33:46", "throughput": 9524.62, "total_tokens": 2890176}
{"current_steps": 3020, "total_steps": 58920, "loss": 0.1076, "lr": 1.0247793618465716e-06, "epoch": 0.2562797012898846, "percentage": 5.13, "elapsed_time": "0:05:03", "remaining_time": "1:33:43", "throughput": 9528.48, "total_tokens": 2895040}
{"current_steps": 3025, "total_steps": 58920, "loss": 0.037, "lr": 1.0264765784114054e-06, "epoch": 0.256704005431093, "percentage": 5.13, "elapsed_time": "0:05:04", "remaining_time": "1:33:41", "throughput": 9532.11, "total_tokens": 2899776}
{"current_steps": 3030, "total_steps": 58920, "loss": 0.077, "lr": 1.0281737949762391e-06, "epoch": 0.25712830957230143, "percentage": 5.14, "elapsed_time": "0:05:04", "remaining_time": "1:33:38", "throughput": 9534.62, "total_tokens": 2904064}
{"current_steps": 3035, "total_steps": 58920, "loss": 0.0559, "lr": 1.0298710115410726e-06, "epoch": 0.25755261371350985, "percentage": 5.15, "elapsed_time": "0:05:04", "remaining_time": "1:33:35", "throughput": 9538.29, "total_tokens": 2908800}
{"current_steps": 3040, "total_steps": 58920, "loss": 0.0891, "lr": 1.0315682281059062e-06, "epoch": 0.25797691785471827, "percentage": 5.16, "elapsed_time": "0:05:05", "remaining_time": "1:33:32", "throughput": 9541.05, "total_tokens": 2913216}
{"current_steps": 3045, "total_steps": 58920, "loss": 0.0822, "lr": 1.03326544467074e-06, "epoch": 0.2584012219959267, "percentage": 5.17, "elapsed_time": "0:05:05", "remaining_time": "1:33:29", "throughput": 9543.39, "total_tokens": 2917504}
{"current_steps": 3050, "total_steps": 58920, "loss": 0.0912, "lr": 1.0349626612355734e-06, "epoch": 0.2588255261371351, "percentage": 5.18, "elapsed_time": "0:05:06", "remaining_time": "1:33:27", "throughput": 9548.29, "total_tokens": 2922752}
{"current_steps": 3055, "total_steps": 58920, "loss": 0.0748, "lr": 1.0366598778004072e-06, "epoch": 0.25924983027834353, "percentage": 5.18, "elapsed_time": "0:05:06", "remaining_time": "1:33:24", "throughput": 9553.08, "total_tokens": 2928000}
{"current_steps": 3060, "total_steps": 58920, "loss": 0.0357, "lr": 1.038357094365241e-06, "epoch": 0.25967413441955195, "percentage": 5.19, "elapsed_time": "0:05:06", "remaining_time": "1:33:22", "throughput": 9556.71, "total_tokens": 2932736}
{"current_steps": 3065, "total_steps": 58920, "loss": 0.1036, "lr": 1.0400543109300746e-06, "epoch": 0.26009843856076037, "percentage": 5.2, "elapsed_time": "0:05:07", "remaining_time": "1:33:19", "throughput": 9560.63, "total_tokens": 2937664}
{"current_steps": 3070, "total_steps": 58920, "loss": 0.1051, "lr": 1.0417515274949082e-06, "epoch": 0.2605227427019688, "percentage": 5.21, "elapsed_time": "0:05:07", "remaining_time": "1:33:16", "throughput": 9565.13, "total_tokens": 2942784}
{"current_steps": 3075, "total_steps": 58920, "loss": 0.1395, "lr": 1.043448744059742e-06, "epoch": 0.2609470468431772, "percentage": 5.22, "elapsed_time": "0:05:08", "remaining_time": "1:33:14", "throughput": 9569.44, "total_tokens": 2947840}
{"current_steps": 3080, "total_steps": 58920, "loss": 0.0834, "lr": 1.0451459606245756e-06, "epoch": 0.26137135098438563, "percentage": 5.23, "elapsed_time": "0:05:08", "remaining_time": "1:33:11", "throughput": 9572.63, "total_tokens": 2952448}
{"current_steps": 3085, "total_steps": 58920, "loss": 0.047, "lr": 1.0468431771894094e-06, "epoch": 0.26179565512559405, "percentage": 5.24, "elapsed_time": "0:05:08", "remaining_time": "1:33:09", "throughput": 9575.86, "total_tokens": 2957120}
{"current_steps": 3090, "total_steps": 58920, "loss": 0.0628, "lr": 1.048540393754243e-06, "epoch": 0.26221995926680247, "percentage": 5.24, "elapsed_time": "0:05:09", "remaining_time": "1:33:06", "throughput": 9578.99, "total_tokens": 2961728}
{"current_steps": 3095, "total_steps": 58920, "loss": 0.0589, "lr": 1.0502376103190766e-06, "epoch": 0.26264426340801084, "percentage": 5.25, "elapsed_time": "0:05:09", "remaining_time": "1:33:03", "throughput": 9581.78, "total_tokens": 2966208}
{"current_steps": 3100, "total_steps": 58920, "loss": 0.0186, "lr": 1.0519348268839104e-06, "epoch": 0.26306856754921926, "percentage": 5.26, "elapsed_time": "0:05:09", "remaining_time": "1:33:01", "throughput": 9588.49, "total_tokens": 2972288}
{"current_steps": 3105, "total_steps": 58920, "loss": 0.0947, "lr": 1.053632043448744e-06, "epoch": 0.2634928716904277, "percentage": 5.27, "elapsed_time": "0:05:10", "remaining_time": "1:32:58", "throughput": 9590.66, "total_tokens": 2976512}
{"current_steps": 3110, "total_steps": 58920, "loss": 0.0815, "lr": 1.0553292600135777e-06, "epoch": 0.2639171758316361, "percentage": 5.28, "elapsed_time": "0:05:10", "remaining_time": "1:32:56", "throughput": 9594.11, "total_tokens": 2981248}
{"current_steps": 3115, "total_steps": 58920, "loss": 0.1039, "lr": 1.0570264765784114e-06, "epoch": 0.2643414799728445, "percentage": 5.29, "elapsed_time": "0:05:11", "remaining_time": "1:32:53", "throughput": 9596.82, "total_tokens": 2985728}
{"current_steps": 3120, "total_steps": 58920, "loss": 0.0963, "lr": 1.0587236931432451e-06, "epoch": 0.26476578411405294, "percentage": 5.3, "elapsed_time": "0:05:11", "remaining_time": "1:32:51", "throughput": 9599.25, "total_tokens": 2990144}
{"current_steps": 3125, "total_steps": 58920, "loss": 0.0742, "lr": 1.0604209097080787e-06, "epoch": 0.26519008825526136, "percentage": 5.3, "elapsed_time": "0:05:11", "remaining_time": "1:32:48", "throughput": 9601.83, "total_tokens": 2994560}
{"current_steps": 3130, "total_steps": 58920, "loss": 0.0634, "lr": 1.0621181262729124e-06, "epoch": 0.2656143923964698, "percentage": 5.31, "elapsed_time": "0:05:12", "remaining_time": "1:32:45", "throughput": 9605.63, "total_tokens": 2999488}
{"current_steps": 3135, "total_steps": 58920, "loss": 0.0726, "lr": 1.0638153428377461e-06, "epoch": 0.2660386965376782, "percentage": 5.32, "elapsed_time": "0:05:12", "remaining_time": "1:32:43", "throughput": 9608.63, "total_tokens": 3004096}
{"current_steps": 3140, "total_steps": 58920, "loss": 0.1055, "lr": 1.0655125594025799e-06, "epoch": 0.2664630006788866, "percentage": 5.33, "elapsed_time": "0:05:13", "remaining_time": "1:32:40", "throughput": 9611.25, "total_tokens": 3008512}
{"current_steps": 3145, "total_steps": 58920, "loss": 0.0751, "lr": 1.0672097759674134e-06, "epoch": 0.26688730482009504, "percentage": 5.34, "elapsed_time": "0:05:13", "remaining_time": "1:32:38", "throughput": 9615.31, "total_tokens": 3013504}
{"current_steps": 3150, "total_steps": 58920, "loss": 0.0325, "lr": 1.0689069925322471e-06, "epoch": 0.26731160896130346, "percentage": 5.35, "elapsed_time": "0:05:13", "remaining_time": "1:32:35", "throughput": 9618.41, "total_tokens": 3018112}
{"current_steps": 3155, "total_steps": 58920, "loss": 0.1058, "lr": 1.0706042090970809e-06, "epoch": 0.2677359131025119, "percentage": 5.35, "elapsed_time": "0:05:14", "remaining_time": "1:32:33", "throughput": 9622.57, "total_tokens": 3023168}
{"current_steps": 3160, "total_steps": 58920, "loss": 0.0775, "lr": 1.0723014256619146e-06, "epoch": 0.2681602172437203, "percentage": 5.36, "elapsed_time": "0:05:14", "remaining_time": "1:32:30", "throughput": 9625.79, "total_tokens": 3027840}
{"current_steps": 3165, "total_steps": 58920, "loss": 0.1264, "lr": 1.0739986422267481e-06, "epoch": 0.2685845213849287, "percentage": 5.37, "elapsed_time": "0:05:14", "remaining_time": "1:32:28", "throughput": 9633.05, "total_tokens": 3034176}
{"current_steps": 3170, "total_steps": 58920, "loss": 0.0592, "lr": 1.0756958587915819e-06, "epoch": 0.26900882552613714, "percentage": 5.38, "elapsed_time": "0:05:15", "remaining_time": "1:32:25", "throughput": 9635.23, "total_tokens": 3038464}
{"current_steps": 3175, "total_steps": 58920, "loss": 0.0825, "lr": 1.0773930753564154e-06, "epoch": 0.26943312966734556, "percentage": 5.39, "elapsed_time": "0:05:15", "remaining_time": "1:32:23", "throughput": 9637.9, "total_tokens": 3042944}
{"current_steps": 3180, "total_steps": 58920, "loss": 0.0888, "lr": 1.079090291921249e-06, "epoch": 0.269857433808554, "percentage": 5.4, "elapsed_time": "0:05:16", "remaining_time": "1:32:20", "throughput": 9642.03, "total_tokens": 3048000}
{"current_steps": 3185, "total_steps": 58920, "loss": 0.0848, "lr": 1.0807875084860827e-06, "epoch": 0.2702817379497624, "percentage": 5.41, "elapsed_time": "0:05:16", "remaining_time": "1:32:18", "throughput": 9646.11, "total_tokens": 3053056}
{"current_steps": 3190, "total_steps": 58920, "loss": 0.0998, "lr": 1.0824847250509164e-06, "epoch": 0.2707060420909708, "percentage": 5.41, "elapsed_time": "0:05:16", "remaining_time": "1:32:16", "throughput": 9649.23, "total_tokens": 3057792}
{"current_steps": 3195, "total_steps": 58920, "loss": 0.1282, "lr": 1.0841819416157501e-06, "epoch": 0.27113034623217924, "percentage": 5.42, "elapsed_time": "0:05:17", "remaining_time": "1:32:13", "throughput": 9653.14, "total_tokens": 3062784}
{"current_steps": 3200, "total_steps": 58920, "loss": 0.0891, "lr": 1.0858791581805837e-06, "epoch": 0.27155465037338766, "percentage": 5.43, "elapsed_time": "0:05:17", "remaining_time": "1:32:11", "throughput": 9656.95, "total_tokens": 3067712}
{"current_steps": 3205, "total_steps": 58920, "loss": 0.0451, "lr": 1.0875763747454174e-06, "epoch": 0.2719789545145961, "percentage": 5.44, "elapsed_time": "0:05:18", "remaining_time": "1:32:08", "throughput": 9658.95, "total_tokens": 3072000}
{"current_steps": 3210, "total_steps": 58920, "loss": 0.0568, "lr": 1.0892735913102511e-06, "epoch": 0.2724032586558045, "percentage": 5.45, "elapsed_time": "0:05:18", "remaining_time": "1:32:06", "throughput": 9661.45, "total_tokens": 3076416}
{"current_steps": 3215, "total_steps": 58920, "loss": 0.0964, "lr": 1.0909708078750849e-06, "epoch": 0.2728275627970129, "percentage": 5.46, "elapsed_time": "0:05:18", "remaining_time": "1:32:04", "throughput": 9666.0, "total_tokens": 3081792}
{"current_steps": 3220, "total_steps": 58920, "loss": 0.1252, "lr": 1.0926680244399184e-06, "epoch": 0.27325186693822134, "percentage": 5.47, "elapsed_time": "0:05:19", "remaining_time": "1:32:01", "throughput": 9669.47, "total_tokens": 3086656}
{"current_steps": 3225, "total_steps": 58920, "loss": 0.0754, "lr": 1.0943652410047521e-06, "epoch": 0.2736761710794297, "percentage": 5.47, "elapsed_time": "0:05:19", "remaining_time": "1:31:59", "throughput": 9672.58, "total_tokens": 3091328}
{"current_steps": 3230, "total_steps": 58920, "loss": 0.0193, "lr": 1.0960624575695859e-06, "epoch": 0.27410047522063813, "percentage": 5.48, "elapsed_time": "0:05:19", "remaining_time": "1:31:57", "throughput": 9676.75, "total_tokens": 3096448}
{"current_steps": 3235, "total_steps": 58920, "loss": 0.0707, "lr": 1.0977596741344194e-06, "epoch": 0.27452477936184655, "percentage": 5.49, "elapsed_time": "0:05:20", "remaining_time": "1:31:55", "throughput": 9682.84, "total_tokens": 3102400}
{"current_steps": 3240, "total_steps": 58920, "loss": 0.0532, "lr": 1.0994568906992531e-06, "epoch": 0.27494908350305497, "percentage": 5.5, "elapsed_time": "0:05:20", "remaining_time": "1:31:52", "throughput": 9685.74, "total_tokens": 3107008}
{"current_steps": 3245, "total_steps": 58920, "loss": 0.0485, "lr": 1.1011541072640869e-06, "epoch": 0.2753733876442634, "percentage": 5.51, "elapsed_time": "0:05:21", "remaining_time": "1:31:50", "throughput": 9689.12, "total_tokens": 3111872}
{"current_steps": 3250, "total_steps": 58920, "loss": 0.0452, "lr": 1.1028513238289206e-06, "epoch": 0.2757976917854718, "percentage": 5.52, "elapsed_time": "0:05:21", "remaining_time": "1:31:48", "throughput": 9692.08, "total_tokens": 3116544}
{"current_steps": 3255, "total_steps": 58920, "loss": 0.1239, "lr": 1.1045485403937541e-06, "epoch": 0.27622199592668023, "percentage": 5.52, "elapsed_time": "0:05:21", "remaining_time": "1:31:45", "throughput": 9694.36, "total_tokens": 3121024}
{"current_steps": 3260, "total_steps": 58920, "loss": 0.0754, "lr": 1.1062457569585879e-06, "epoch": 0.27664630006788865, "percentage": 5.53, "elapsed_time": "0:05:22", "remaining_time": "1:31:43", "throughput": 9697.24, "total_tokens": 3125696}
{"current_steps": 3265, "total_steps": 58920, "loss": 0.1002, "lr": 1.1079429735234216e-06, "epoch": 0.27707060420909707, "percentage": 5.54, "elapsed_time": "0:05:22", "remaining_time": "1:31:41", "throughput": 9701.05, "total_tokens": 3130752}
{"current_steps": 3270, "total_steps": 58920, "loss": 0.1092, "lr": 1.1096401900882554e-06, "epoch": 0.2774949083503055, "percentage": 5.55, "elapsed_time": "0:05:23", "remaining_time": "1:31:38", "throughput": 9703.61, "total_tokens": 3135360}
{"current_steps": 3275, "total_steps": 58920, "loss": 0.1145, "lr": 1.1113374066530889e-06, "epoch": 0.2779192124915139, "percentage": 5.56, "elapsed_time": "0:05:23", "remaining_time": "1:31:36", "throughput": 9706.37, "total_tokens": 3140032}
{"current_steps": 3280, "total_steps": 58920, "loss": 0.074, "lr": 1.1130346232179226e-06, "epoch": 0.27834351663272233, "percentage": 5.57, "elapsed_time": "0:05:23", "remaining_time": "1:31:34", "throughput": 9709.81, "total_tokens": 3144960}
{"current_steps": 3285, "total_steps": 58920, "loss": 0.0626, "lr": 1.1147318397827564e-06, "epoch": 0.27876782077393075, "percentage": 5.58, "elapsed_time": "0:05:24", "remaining_time": "1:31:32", "throughput": 9713.56, "total_tokens": 3150016}
{"current_steps": 3290, "total_steps": 58920, "loss": 0.0892, "lr": 1.11642905634759e-06, "epoch": 0.2791921249151392, "percentage": 5.58, "elapsed_time": "0:05:24", "remaining_time": "1:31:30", "throughput": 9717.52, "total_tokens": 3155200}
{"current_steps": 3295, "total_steps": 58920, "loss": 0.062, "lr": 1.1181262729124236e-06, "epoch": 0.2796164290563476, "percentage": 5.59, "elapsed_time": "0:05:25", "remaining_time": "1:31:27", "throughput": 9720.82, "total_tokens": 3160000}
{"current_steps": 3300, "total_steps": 58920, "loss": 0.0383, "lr": 1.1198234894772574e-06, "epoch": 0.280040733197556, "percentage": 5.6, "elapsed_time": "0:05:25", "remaining_time": "1:31:25", "throughput": 9723.35, "total_tokens": 3164672}
{"current_steps": 3305, "total_steps": 58920, "loss": 0.0443, "lr": 1.1215207060420909e-06, "epoch": 0.28046503733876443, "percentage": 5.61, "elapsed_time": "0:05:25", "remaining_time": "1:31:23", "throughput": 9725.86, "total_tokens": 3169152}
{"current_steps": 3310, "total_steps": 58920, "loss": 0.0464, "lr": 1.1232179226069244e-06, "epoch": 0.28088934147997285, "percentage": 5.62, "elapsed_time": "0:05:26", "remaining_time": "1:31:20", "throughput": 9728.94, "total_tokens": 3173888}
{"current_steps": 3315, "total_steps": 58920, "loss": 0.0585, "lr": 1.1249151391717582e-06, "epoch": 0.2813136456211813, "percentage": 5.63, "elapsed_time": "0:05:26", "remaining_time": "1:31:18", "throughput": 9733.0, "total_tokens": 3179072}
{"current_steps": 3320, "total_steps": 58920, "loss": 0.0945, "lr": 1.1266123557365919e-06, "epoch": 0.2817379497623897, "percentage": 5.63, "elapsed_time": "0:05:27", "remaining_time": "1:31:16", "throughput": 9735.47, "total_tokens": 3183552}
{"current_steps": 3325, "total_steps": 58920, "loss": 0.0144, "lr": 1.1283095723014256e-06, "epoch": 0.2821622539035981, "percentage": 5.64, "elapsed_time": "0:05:27", "remaining_time": "1:31:13", "throughput": 9737.69, "total_tokens": 3187968}
{"current_steps": 3330, "total_steps": 58920, "loss": 0.0989, "lr": 1.1300067888662592e-06, "epoch": 0.28258655804480654, "percentage": 5.65, "elapsed_time": "0:05:27", "remaining_time": "1:31:11", "throughput": 9740.55, "total_tokens": 3192704}
{"current_steps": 3335, "total_steps": 58920, "loss": 0.0961, "lr": 1.1317040054310929e-06, "epoch": 0.28301086218601496, "percentage": 5.66, "elapsed_time": "0:05:28", "remaining_time": "1:31:09", "throughput": 9744.28, "total_tokens": 3197760}
{"current_steps": 3340, "total_steps": 58920, "loss": 0.057, "lr": 1.1334012219959266e-06, "epoch": 0.2834351663272234, "percentage": 5.67, "elapsed_time": "0:05:28", "remaining_time": "1:31:07", "throughput": 9746.86, "total_tokens": 3202368}
{"current_steps": 3345, "total_steps": 58920, "loss": 0.242, "lr": 1.1350984385607604e-06, "epoch": 0.2838594704684318, "percentage": 5.68, "elapsed_time": "0:05:28", "remaining_time": "1:31:05", "throughput": 9750.49, "total_tokens": 3207360}
{"current_steps": 3350, "total_steps": 58920, "loss": 0.1313, "lr": 1.1367956551255939e-06, "epoch": 0.2842837746096402, "percentage": 5.69, "elapsed_time": "0:05:29", "remaining_time": "1:31:03", "throughput": 9756.69, "total_tokens": 3213632}
{"current_steps": 3355, "total_steps": 58920, "loss": 0.054, "lr": 1.1384928716904276e-06, "epoch": 0.2847080787508486, "percentage": 5.69, "elapsed_time": "0:05:29", "remaining_time": "1:31:01", "throughput": 9761.36, "total_tokens": 3219136}
{"current_steps": 3360, "total_steps": 58920, "loss": 0.0932, "lr": 1.1401900882552614e-06, "epoch": 0.285132382892057, "percentage": 5.7, "elapsed_time": "0:05:30", "remaining_time": "1:31:00", "throughput": 9767.11, "total_tokens": 3225088}
{"current_steps": 3365, "total_steps": 58920, "loss": 0.0803, "lr": 1.141887304820095e-06, "epoch": 0.2855566870332654, "percentage": 5.71, "elapsed_time": "0:05:30", "remaining_time": "1:30:57", "throughput": 9769.19, "total_tokens": 3229504}
{"current_steps": 3370, "total_steps": 58920, "loss": 0.0507, "lr": 1.1435845213849286e-06, "epoch": 0.28598099117447384, "percentage": 5.72, "elapsed_time": "0:05:30", "remaining_time": "1:30:55", "throughput": 9772.48, "total_tokens": 3234368}
{"current_steps": 3375, "total_steps": 58920, "loss": 0.0784, "lr": 1.1452817379497624e-06, "epoch": 0.28640529531568226, "percentage": 5.73, "elapsed_time": "0:05:31", "remaining_time": "1:30:53", "throughput": 9775.81, "total_tokens": 3239232}
{"current_steps": 3380, "total_steps": 58920, "loss": 0.0728, "lr": 1.1469789545145961e-06, "epoch": 0.2868295994568907, "percentage": 5.74, "elapsed_time": "0:05:31", "remaining_time": "1:30:51", "throughput": 9779.52, "total_tokens": 3244288}
{"current_steps": 3385, "total_steps": 58920, "loss": 0.1304, "lr": 1.1486761710794296e-06, "epoch": 0.2872539035980991, "percentage": 5.75, "elapsed_time": "0:05:32", "remaining_time": "1:30:49", "throughput": 9781.19, "total_tokens": 3248640}
{"current_steps": 3390, "total_steps": 58920, "loss": 0.0257, "lr": 1.1503733876442634e-06, "epoch": 0.2876782077393075, "percentage": 5.75, "elapsed_time": "0:05:32", "remaining_time": "1:30:46", "throughput": 9784.27, "total_tokens": 3253440}
{"current_steps": 3395, "total_steps": 58920, "loss": 0.0663, "lr": 1.1520706042090971e-06, "epoch": 0.28810251188051594, "percentage": 5.76, "elapsed_time": "0:05:32", "remaining_time": "1:30:44", "throughput": 9786.99, "total_tokens": 3258048}
{"current_steps": 3400, "total_steps": 58920, "loss": 0.0442, "lr": 1.1537678207739308e-06, "epoch": 0.28852681602172436, "percentage": 5.77, "elapsed_time": "0:05:33", "remaining_time": "1:30:42", "throughput": 9790.19, "total_tokens": 3262912}
{"current_steps": 3405, "total_steps": 58920, "loss": 0.0566, "lr": 1.1554650373387644e-06, "epoch": 0.2889511201629328, "percentage": 5.78, "elapsed_time": "0:05:33", "remaining_time": "1:30:40", "throughput": 9793.42, "total_tokens": 3267776}
{"current_steps": 3410, "total_steps": 58920, "loss": 0.062, "lr": 1.1571622539035981e-06, "epoch": 0.2893754243041412, "percentage": 5.79, "elapsed_time": "0:05:34", "remaining_time": "1:30:37", "throughput": 9796.12, "total_tokens": 3272448}
{"current_steps": 3415, "total_steps": 58920, "loss": 0.0946, "lr": 1.1588594704684319e-06, "epoch": 0.2897997284453496, "percentage": 5.8, "elapsed_time": "0:05:34", "remaining_time": "1:30:35", "throughput": 9798.76, "total_tokens": 3277056}
{"current_steps": 3420, "total_steps": 58920, "loss": 0.07, "lr": 1.1605566870332654e-06, "epoch": 0.29022403258655805, "percentage": 5.8, "elapsed_time": "0:05:34", "remaining_time": "1:30:33", "throughput": 9802.19, "total_tokens": 3282048}
{"current_steps": 3425, "total_steps": 58920, "loss": 0.0988, "lr": 1.1622539035980991e-06, "epoch": 0.29064833672776647, "percentage": 5.81, "elapsed_time": "0:05:35", "remaining_time": "1:30:31", "throughput": 9803.88, "total_tokens": 3286336}
{"current_steps": 3430, "total_steps": 58920, "loss": 0.0293, "lr": 1.1639511201629329e-06, "epoch": 0.2910726408689749, "percentage": 5.82, "elapsed_time": "0:05:35", "remaining_time": "1:30:29", "throughput": 9806.16, "total_tokens": 3290880}
{"current_steps": 3435, "total_steps": 58920, "loss": 0.0469, "lr": 1.1656483367277664e-06, "epoch": 0.2914969450101833, "percentage": 5.83, "elapsed_time": "0:05:35", "remaining_time": "1:30:26", "throughput": 9808.38, "total_tokens": 3295360}
{"current_steps": 3440, "total_steps": 58920, "loss": 0.0216, "lr": 1.1673455532926e-06, "epoch": 0.2919212491513917, "percentage": 5.84, "elapsed_time": "0:05:36", "remaining_time": "1:30:24", "throughput": 9810.27, "total_tokens": 3299840}
{"current_steps": 3445, "total_steps": 58920, "loss": 0.0595, "lr": 1.1690427698574336e-06, "epoch": 0.29234555329260015, "percentage": 5.85, "elapsed_time": "0:05:36", "remaining_time": "1:30:22", "throughput": 9812.74, "total_tokens": 3304448}
{"current_steps": 3450, "total_steps": 58920, "loss": 0.1056, "lr": 1.1707399864222674e-06, "epoch": 0.29276985743380857, "percentage": 5.86, "elapsed_time": "0:05:37", "remaining_time": "1:30:20", "throughput": 9814.93, "total_tokens": 3308928}
{"current_steps": 3455, "total_steps": 58920, "loss": 0.1056, "lr": 1.1724372029871011e-06, "epoch": 0.293194161575017, "percentage": 5.86, "elapsed_time": "0:05:37", "remaining_time": "1:30:18", "throughput": 9817.18, "total_tokens": 3313408}
{"current_steps": 3460, "total_steps": 58920, "loss": 0.1278, "lr": 1.1741344195519346e-06, "epoch": 0.2936184657162254, "percentage": 5.87, "elapsed_time": "0:05:37", "remaining_time": "1:30:16", "throughput": 9819.97, "total_tokens": 3318080}
{"current_steps": 3465, "total_steps": 58920, "loss": 0.0555, "lr": 1.1758316361167684e-06, "epoch": 0.29404276985743383, "percentage": 5.88, "elapsed_time": "0:05:38", "remaining_time": "1:30:14", "throughput": 9823.43, "total_tokens": 3323136}
{"current_steps": 3470, "total_steps": 58920, "loss": 0.0459, "lr": 1.1775288526816021e-06, "epoch": 0.29446707399864225, "percentage": 5.89, "elapsed_time": "0:05:38", "remaining_time": "1:30:11", "throughput": 9826.31, "total_tokens": 3327936}
{"current_steps": 3475, "total_steps": 58920, "loss": 0.0591, "lr": 1.1792260692464356e-06, "epoch": 0.29489137813985067, "percentage": 5.9, "elapsed_time": "0:05:39", "remaining_time": "1:30:09", "throughput": 9829.44, "total_tokens": 3332864}
{"current_steps": 3480, "total_steps": 58920, "loss": 0.0966, "lr": 1.1809232858112694e-06, "epoch": 0.2953156822810591, "percentage": 5.91, "elapsed_time": "0:05:39", "remaining_time": "1:30:08", "throughput": 9833.28, "total_tokens": 3338048}
{"current_steps": 3485, "total_steps": 58920, "loss": 0.1845, "lr": 1.1826205023761031e-06, "epoch": 0.2957399864222675, "percentage": 5.91, "elapsed_time": "0:05:39", "remaining_time": "1:30:06", "throughput": 9836.75, "total_tokens": 3343104}
{"current_steps": 3490, "total_steps": 58920, "loss": 0.0754, "lr": 1.1843177189409369e-06, "epoch": 0.2961642905634759, "percentage": 5.92, "elapsed_time": "0:05:40", "remaining_time": "1:30:03", "throughput": 9839.13, "total_tokens": 3347712}
{"current_steps": 3495, "total_steps": 58920, "loss": 0.0586, "lr": 1.1860149355057704e-06, "epoch": 0.2965885947046843, "percentage": 5.93, "elapsed_time": "0:05:40", "remaining_time": "1:30:01", "throughput": 9840.83, "total_tokens": 3352000}
{"current_steps": 3500, "total_steps": 58920, "loss": 0.056, "lr": 1.1877121520706041e-06, "epoch": 0.2970128988458927, "percentage": 5.94, "elapsed_time": "0:05:41", "remaining_time": "1:29:59", "throughput": 9842.96, "total_tokens": 3356480}
{"current_steps": 3505, "total_steps": 58920, "loss": 0.1251, "lr": 1.1894093686354379e-06, "epoch": 0.29743720298710113, "percentage": 5.95, "elapsed_time": "0:05:41", "remaining_time": "1:29:57", "throughput": 9846.37, "total_tokens": 3361536}
{"current_steps": 3510, "total_steps": 58920, "loss": 0.122, "lr": 1.1911065852002716e-06, "epoch": 0.29786150712830956, "percentage": 5.96, "elapsed_time": "0:05:41", "remaining_time": "1:29:55", "throughput": 9851.35, "total_tokens": 3367296}
{"current_steps": 3515, "total_steps": 58920, "loss": 0.0874, "lr": 1.1928038017651051e-06, "epoch": 0.298285811269518, "percentage": 5.97, "elapsed_time": "0:05:42", "remaining_time": "1:29:53", "throughput": 9854.31, "total_tokens": 3372096}
{"current_steps": 3520, "total_steps": 58920, "loss": 0.0882, "lr": 1.1945010183299389e-06, "epoch": 0.2987101154107264, "percentage": 5.97, "elapsed_time": "0:05:42", "remaining_time": "1:29:51", "throughput": 9856.14, "total_tokens": 3376384}
{"current_steps": 3525, "total_steps": 58920, "loss": 0.0496, "lr": 1.1961982348947726e-06, "epoch": 0.2991344195519348, "percentage": 5.98, "elapsed_time": "0:05:42", "remaining_time": "1:29:49", "throughput": 9859.81, "total_tokens": 3381504}
{"current_steps": 3530, "total_steps": 58920, "loss": 0.0353, "lr": 1.1978954514596063e-06, "epoch": 0.29955872369314324, "percentage": 5.99, "elapsed_time": "0:05:43", "remaining_time": "1:29:47", "throughput": 9862.25, "total_tokens": 3386112}
{"current_steps": 3535, "total_steps": 58920, "loss": 0.1275, "lr": 1.1995926680244399e-06, "epoch": 0.29998302783435166, "percentage": 6.0, "elapsed_time": "0:05:43", "remaining_time": "1:29:47", "throughput": 9873.27, "total_tokens": 3395072}
{"current_steps": 3540, "total_steps": 58920, "loss": 0.0908, "lr": 1.2012898845892736e-06, "epoch": 0.3004073319755601, "percentage": 6.01, "elapsed_time": "0:05:44", "remaining_time": "1:29:45", "throughput": 9876.06, "total_tokens": 3399808}
{"current_steps": 3545, "total_steps": 58920, "loss": 0.0687, "lr": 1.2029871011541073e-06, "epoch": 0.3008316361167685, "percentage": 6.02, "elapsed_time": "0:05:44", "remaining_time": "1:29:43", "throughput": 9878.76, "total_tokens": 3404544}
{"current_steps": 3550, "total_steps": 58920, "loss": 0.1105, "lr": 1.2046843177189409e-06, "epoch": 0.3012559402579769, "percentage": 6.03, "elapsed_time": "0:05:45", "remaining_time": "1:29:41", "throughput": 9880.65, "total_tokens": 3408896}
{"current_steps": 3555, "total_steps": 58920, "loss": 0.0772, "lr": 1.2063815342837746e-06, "epoch": 0.30168024439918534, "percentage": 6.03, "elapsed_time": "0:05:45", "remaining_time": "1:29:39", "throughput": 9883.84, "total_tokens": 3413824}
{"current_steps": 3560, "total_steps": 58920, "loss": 0.1011, "lr": 1.2080787508486083e-06, "epoch": 0.30210454854039376, "percentage": 6.04, "elapsed_time": "0:05:45", "remaining_time": "1:29:36", "throughput": 9885.84, "total_tokens": 3418240}
{"current_steps": 3565, "total_steps": 58920, "loss": 0.1194, "lr": 1.209775967413442e-06, "epoch": 0.3025288526816022, "percentage": 6.05, "elapsed_time": "0:05:46", "remaining_time": "1:29:34", "throughput": 9889.07, "total_tokens": 3423168}
{"current_steps": 3570, "total_steps": 58920, "loss": 0.0942, "lr": 1.2114731839782754e-06, "epoch": 0.3029531568228106, "percentage": 6.06, "elapsed_time": "0:05:46", "remaining_time": "1:29:32", "throughput": 9892.54, "total_tokens": 3428224}
{"current_steps": 3575, "total_steps": 58920, "loss": 0.0476, "lr": 1.2131704005431091e-06, "epoch": 0.303377460964019, "percentage": 6.07, "elapsed_time": "0:05:46", "remaining_time": "1:29:31", "throughput": 9894.77, "total_tokens": 3432896}
{"current_steps": 3580, "total_steps": 58920, "loss": 0.0673, "lr": 1.2148676171079429e-06, "epoch": 0.30380176510522744, "percentage": 6.08, "elapsed_time": "0:05:47", "remaining_time": "1:29:28", "throughput": 9897.5, "total_tokens": 3437632}
{"current_steps": 3585, "total_steps": 58920, "loss": 0.0686, "lr": 1.2165648336727766e-06, "epoch": 0.30422606924643586, "percentage": 6.08, "elapsed_time": "0:05:47", "remaining_time": "1:29:26", "throughput": 9899.67, "total_tokens": 3442112}
{"current_steps": 3590, "total_steps": 58920, "loss": 0.0608, "lr": 1.2182620502376101e-06, "epoch": 0.3046503733876443, "percentage": 6.09, "elapsed_time": "0:05:48", "remaining_time": "1:29:25", "throughput": 9905.1, "total_tokens": 3448064}
{"current_steps": 3595, "total_steps": 58920, "loss": 0.1308, "lr": 1.2199592668024439e-06, "epoch": 0.3050746775288527, "percentage": 6.1, "elapsed_time": "0:05:48", "remaining_time": "1:29:23", "throughput": 9907.83, "total_tokens": 3452800}
{"current_steps": 3600, "total_steps": 58920, "loss": 0.1155, "lr": 1.2216564833672776e-06, "epoch": 0.3054989816700611, "percentage": 6.11, "elapsed_time": "0:05:48", "remaining_time": "1:29:21", "throughput": 9911.18, "total_tokens": 3457856}
{"current_steps": 3605, "total_steps": 58920, "loss": 0.0319, "lr": 1.2233536999321111e-06, "epoch": 0.30592328581126954, "percentage": 6.12, "elapsed_time": "0:05:49", "remaining_time": "1:29:19", "throughput": 9914.14, "total_tokens": 3462720}
{"current_steps": 3610, "total_steps": 58920, "loss": 0.1292, "lr": 1.2250509164969449e-06, "epoch": 0.30634758995247796, "percentage": 6.13, "elapsed_time": "0:05:49", "remaining_time": "1:29:17", "throughput": 9916.37, "total_tokens": 3467264}
{"current_steps": 3615, "total_steps": 58920, "loss": 0.1002, "lr": 1.2267481330617786e-06, "epoch": 0.3067718940936864, "percentage": 6.14, "elapsed_time": "0:05:50", "remaining_time": "1:29:15", "throughput": 9920.88, "total_tokens": 3472832}
{"current_steps": 3620, "total_steps": 58920, "loss": 0.0479, "lr": 1.2284453496266124e-06, "epoch": 0.30719619823489475, "percentage": 6.14, "elapsed_time": "0:05:50", "remaining_time": "1:29:13", "throughput": 9924.66, "total_tokens": 3478016}
{"current_steps": 3625, "total_steps": 58920, "loss": 0.0472, "lr": 1.2301425661914459e-06, "epoch": 0.30762050237610317, "percentage": 6.15, "elapsed_time": "0:05:50", "remaining_time": "1:29:11", "throughput": 9927.21, "total_tokens": 3482688}
{"current_steps": 3630, "total_steps": 58920, "loss": 0.0364, "lr": 1.2318397827562796e-06, "epoch": 0.3080448065173116, "percentage": 6.16, "elapsed_time": "0:05:51", "remaining_time": "1:29:09", "throughput": 9929.26, "total_tokens": 3487296}
{"current_steps": 3635, "total_steps": 58920, "loss": 0.0593, "lr": 1.2335369993211134e-06, "epoch": 0.30846911065852, "percentage": 6.17, "elapsed_time": "0:05:51", "remaining_time": "1:29:07", "throughput": 9931.27, "total_tokens": 3491712}
{"current_steps": 3640, "total_steps": 58920, "loss": 0.0919, "lr": 1.235234215885947e-06, "epoch": 0.3088934147997284, "percentage": 6.18, "elapsed_time": "0:05:51", "remaining_time": "1:29:05", "throughput": 9933.49, "total_tokens": 3496256}
{"current_steps": 3645, "total_steps": 58920, "loss": 0.0973, "lr": 1.2369314324507806e-06, "epoch": 0.30931771894093685, "percentage": 6.19, "elapsed_time": "0:05:52", "remaining_time": "1:29:03", "throughput": 9935.48, "total_tokens": 3500672}
{"current_steps": 3650, "total_steps": 58920, "loss": 0.0046, "lr": 1.2386286490156144e-06, "epoch": 0.30974202308214527, "percentage": 6.19, "elapsed_time": "0:05:52", "remaining_time": "1:29:01", "throughput": 9938.49, "total_tokens": 3505536}
{"current_steps": 3655, "total_steps": 58920, "loss": 0.0734, "lr": 1.240325865580448e-06, "epoch": 0.3101663272233537, "percentage": 6.2, "elapsed_time": "0:05:53", "remaining_time": "1:28:59", "throughput": 9941.31, "total_tokens": 3510400}
{"current_steps": 3660, "total_steps": 58920, "loss": 0.0327, "lr": 1.2420230821452818e-06, "epoch": 0.3105906313645621, "percentage": 6.21, "elapsed_time": "0:05:53", "remaining_time": "1:28:57", "throughput": 9943.45, "total_tokens": 3514880}
{"current_steps": 3665, "total_steps": 58920, "loss": 0.1202, "lr": 1.2437202987101154e-06, "epoch": 0.31101493550577053, "percentage": 6.22, "elapsed_time": "0:05:53", "remaining_time": "1:28:55", "throughput": 9947.45, "total_tokens": 3520192}
{"current_steps": 3670, "total_steps": 58920, "loss": 0.0546, "lr": 1.245417515274949e-06, "epoch": 0.31143923964697895, "percentage": 6.23, "elapsed_time": "0:05:54", "remaining_time": "1:28:53", "throughput": 9949.18, "total_tokens": 3524544}
{"current_steps": 3675, "total_steps": 58920, "loss": 0.0403, "lr": 1.2471147318397828e-06, "epoch": 0.31186354378818737, "percentage": 6.24, "elapsed_time": "0:05:54", "remaining_time": "1:28:51", "throughput": 9950.97, "total_tokens": 3528896}
{"current_steps": 3680, "total_steps": 58920, "loss": 0.0677, "lr": 1.2488119484046164e-06, "epoch": 0.3122878479293958, "percentage": 6.25, "elapsed_time": "0:05:55", "remaining_time": "1:28:49", "throughput": 9953.44, "total_tokens": 3533568}
{"current_steps": 3685, "total_steps": 58920, "loss": 0.0414, "lr": 1.25050916496945e-06, "epoch": 0.3127121520706042, "percentage": 6.25, "elapsed_time": "0:05:55", "remaining_time": "1:28:47", "throughput": 9957.61, "total_tokens": 3539008}
{"current_steps": 3690, "total_steps": 58920, "loss": 0.017, "lr": 1.2522063815342838e-06, "epoch": 0.31313645621181263, "percentage": 6.26, "elapsed_time": "0:05:55", "remaining_time": "1:28:45", "throughput": 9961.76, "total_tokens": 3544448}
{"current_steps": 3695, "total_steps": 58920, "loss": 0.1779, "lr": 1.2539035980991176e-06, "epoch": 0.31356076035302105, "percentage": 6.27, "elapsed_time": "0:05:56", "remaining_time": "1:28:43", "throughput": 9964.44, "total_tokens": 3549184}
{"current_steps": 3700, "total_steps": 58920, "loss": 0.0615, "lr": 1.2556008146639509e-06, "epoch": 0.31398506449422947, "percentage": 6.28, "elapsed_time": "0:05:56", "remaining_time": "1:28:41", "throughput": 9967.64, "total_tokens": 3554176}
{"current_steps": 3705, "total_steps": 58920, "loss": 0.0534, "lr": 1.2572980312287846e-06, "epoch": 0.3144093686354379, "percentage": 6.29, "elapsed_time": "0:05:56", "remaining_time": "1:28:39", "throughput": 9969.83, "total_tokens": 3558720}
{"current_steps": 3710, "total_steps": 58920, "loss": 0.1226, "lr": 1.2589952477936184e-06, "epoch": 0.3148336727766463, "percentage": 6.3, "elapsed_time": "0:05:57", "remaining_time": "1:28:37", "throughput": 9972.87, "total_tokens": 3563648}
{"current_steps": 3715, "total_steps": 58920, "loss": 0.0503, "lr": 1.260692464358452e-06, "epoch": 0.31525797691785473, "percentage": 6.31, "elapsed_time": "0:05:57", "remaining_time": "1:28:35", "throughput": 9976.06, "total_tokens": 3568704}
{"current_steps": 3720, "total_steps": 58920, "loss": 0.0466, "lr": 1.2623896809232856e-06, "epoch": 0.31568228105906315, "percentage": 6.31, "elapsed_time": "0:05:58", "remaining_time": "1:28:33", "throughput": 9978.11, "total_tokens": 3573184}
{"current_steps": 3725, "total_steps": 58920, "loss": 0.0839, "lr": 1.2640868974881194e-06, "epoch": 0.3161065852002716, "percentage": 6.32, "elapsed_time": "0:05:58", "remaining_time": "1:28:32", "throughput": 9981.76, "total_tokens": 3578432}
{"current_steps": 3730, "total_steps": 58920, "loss": 0.0234, "lr": 1.265784114052953e-06, "epoch": 0.31653088934148, "percentage": 6.33, "elapsed_time": "0:05:58", "remaining_time": "1:28:30", "throughput": 9983.34, "total_tokens": 3582848}
{"current_steps": 3735, "total_steps": 58920, "loss": 0.0805, "lr": 1.2674813306177866e-06, "epoch": 0.3169551934826884, "percentage": 6.34, "elapsed_time": "0:05:59", "remaining_time": "1:28:28", "throughput": 9986.42, "total_tokens": 3587840}
{"current_steps": 3740, "total_steps": 58920, "loss": 0.0743, "lr": 1.2691785471826204e-06, "epoch": 0.31737949762389683, "percentage": 6.35, "elapsed_time": "0:05:59", "remaining_time": "1:28:26", "throughput": 9988.91, "total_tokens": 3592576}
{"current_steps": 3745, "total_steps": 58920, "loss": 0.0772, "lr": 1.270875763747454e-06, "epoch": 0.31780380176510525, "percentage": 6.36, "elapsed_time": "0:06:00", "remaining_time": "1:28:24", "throughput": 9991.59, "total_tokens": 3597376}
{"current_steps": 3750, "total_steps": 58920, "loss": 0.1081, "lr": 1.2725729803122878e-06, "epoch": 0.3182281059063136, "percentage": 6.36, "elapsed_time": "0:06:00", "remaining_time": "1:28:22", "throughput": 9993.35, "total_tokens": 3601728}
{"current_steps": 3755, "total_steps": 58920, "loss": 0.117, "lr": 1.2742701968771214e-06, "epoch": 0.31865241004752204, "percentage": 6.37, "elapsed_time": "0:06:00", "remaining_time": "1:28:20", "throughput": 9996.11, "total_tokens": 3606592}
{"current_steps": 3760, "total_steps": 58920, "loss": 0.0745, "lr": 1.2759674134419551e-06, "epoch": 0.31907671418873046, "percentage": 6.38, "elapsed_time": "0:06:01", "remaining_time": "1:28:18", "throughput": 9998.64, "total_tokens": 3611328}
{"current_steps": 3765, "total_steps": 58920, "loss": 0.0336, "lr": 1.2776646300067888e-06, "epoch": 0.3195010183299389, "percentage": 6.39, "elapsed_time": "0:06:01", "remaining_time": "1:28:16", "throughput": 10001.09, "total_tokens": 3616000}
{"current_steps": 3770, "total_steps": 58920, "loss": 0.0344, "lr": 1.2793618465716226e-06, "epoch": 0.3199253224711473, "percentage": 6.4, "elapsed_time": "0:06:01", "remaining_time": "1:28:14", "throughput": 10002.64, "total_tokens": 3620288}
{"current_steps": 3775, "total_steps": 58920, "loss": 0.0729, "lr": 1.2810590631364561e-06, "epoch": 0.3203496266123557, "percentage": 6.41, "elapsed_time": "0:06:02", "remaining_time": "1:28:12", "throughput": 10004.35, "total_tokens": 3624704}
{"current_steps": 3780, "total_steps": 58920, "loss": 0.0941, "lr": 1.2827562797012898e-06, "epoch": 0.32077393075356414, "percentage": 6.42, "elapsed_time": "0:06:02", "remaining_time": "1:28:10", "throughput": 10005.33, "total_tokens": 3628736}
{"current_steps": 3785, "total_steps": 58920, "loss": 0.0741, "lr": 1.2844534962661236e-06, "epoch": 0.32119823489477256, "percentage": 6.42, "elapsed_time": "0:06:03", "remaining_time": "1:28:08", "throughput": 10008.17, "total_tokens": 3633664}
{"current_steps": 3790, "total_steps": 58920, "loss": 0.0968, "lr": 1.2861507128309573e-06, "epoch": 0.321622539035981, "percentage": 6.43, "elapsed_time": "0:06:03", "remaining_time": "1:28:06", "throughput": 10010.6, "total_tokens": 3638400}
{"current_steps": 3795, "total_steps": 58920, "loss": 0.1201, "lr": 1.2878479293957908e-06, "epoch": 0.3220468431771894, "percentage": 6.44, "elapsed_time": "0:06:03", "remaining_time": "1:28:04", "throughput": 10013.32, "total_tokens": 3643200}
{"current_steps": 3800, "total_steps": 58920, "loss": 0.1473, "lr": 1.2895451459606246e-06, "epoch": 0.3224711473183978, "percentage": 6.45, "elapsed_time": "0:06:04", "remaining_time": "1:28:03", "throughput": 10015.24, "total_tokens": 3647680}
{"current_steps": 3805, "total_steps": 58920, "loss": 0.0333, "lr": 1.2912423625254583e-06, "epoch": 0.32289545145960624, "percentage": 6.46, "elapsed_time": "0:06:04", "remaining_time": "1:28:01", "throughput": 10019.12, "total_tokens": 3653120}
{"current_steps": 3810, "total_steps": 58920, "loss": 0.1093, "lr": 1.2929395790902918e-06, "epoch": 0.32331975560081466, "percentage": 6.47, "elapsed_time": "0:06:04", "remaining_time": "1:27:59", "throughput": 10021.6, "total_tokens": 3657856}
{"current_steps": 3815, "total_steps": 58920, "loss": 0.0697, "lr": 1.2946367956551256e-06, "epoch": 0.3237440597420231, "percentage": 6.47, "elapsed_time": "0:06:05", "remaining_time": "1:27:57", "throughput": 10024.29, "total_tokens": 3662656}
{"current_steps": 3820, "total_steps": 58920, "loss": 0.0985, "lr": 1.2963340122199593e-06, "epoch": 0.3241683638832315, "percentage": 6.48, "elapsed_time": "0:06:05", "remaining_time": "1:27:56", "throughput": 10028.22, "total_tokens": 3668096}
{"current_steps": 3825, "total_steps": 58920, "loss": 0.0416, "lr": 1.298031228784793e-06, "epoch": 0.3245926680244399, "percentage": 6.49, "elapsed_time": "0:06:06", "remaining_time": "1:27:54", "throughput": 10031.53, "total_tokens": 3673280}
{"current_steps": 3830, "total_steps": 58920, "loss": 0.0825, "lr": 1.2997284453496264e-06, "epoch": 0.32501697216564834, "percentage": 6.5, "elapsed_time": "0:06:06", "remaining_time": "1:27:52", "throughput": 10033.51, "total_tokens": 3677824}
{"current_steps": 3835, "total_steps": 58920, "loss": 0.0698, "lr": 1.3014256619144601e-06, "epoch": 0.32544127630685676, "percentage": 6.51, "elapsed_time": "0:06:06", "remaining_time": "1:27:50", "throughput": 10036.15, "total_tokens": 3682624}
{"current_steps": 3840, "total_steps": 58920, "loss": 0.12, "lr": 1.3031228784792939e-06, "epoch": 0.3258655804480652, "percentage": 6.52, "elapsed_time": "0:06:07", "remaining_time": "1:27:48", "throughput": 10038.5, "total_tokens": 3687296}
{"current_steps": 3845, "total_steps": 58920, "loss": 0.092, "lr": 1.3048200950441276e-06, "epoch": 0.3262898845892736, "percentage": 6.53, "elapsed_time": "0:06:07", "remaining_time": "1:27:46", "throughput": 10041.71, "total_tokens": 3692352}
{"current_steps": 3850, "total_steps": 58920, "loss": 0.0612, "lr": 1.3065173116089611e-06, "epoch": 0.326714188730482, "percentage": 6.53, "elapsed_time": "0:06:08", "remaining_time": "1:27:45", "throughput": 10044.95, "total_tokens": 3697472}
{"current_steps": 3855, "total_steps": 58920, "loss": 0.0745, "lr": 1.3082145281737949e-06, "epoch": 0.32713849287169044, "percentage": 6.54, "elapsed_time": "0:06:08", "remaining_time": "1:27:43", "throughput": 10048.04, "total_tokens": 3702528}
{"current_steps": 3860, "total_steps": 58920, "loss": 0.1202, "lr": 1.3099117447386286e-06, "epoch": 0.32756279701289887, "percentage": 6.55, "elapsed_time": "0:06:08", "remaining_time": "1:27:41", "throughput": 10048.93, "total_tokens": 3706560}
{"current_steps": 3865, "total_steps": 58920, "loss": 0.0857, "lr": 1.3116089613034621e-06, "epoch": 0.3279871011541073, "percentage": 6.56, "elapsed_time": "0:06:09", "remaining_time": "1:27:39", "throughput": 10051.0, "total_tokens": 3711104}
{"current_steps": 3870, "total_steps": 58920, "loss": 0.0785, "lr": 1.3133061778682959e-06, "epoch": 0.3284114052953157, "percentage": 6.57, "elapsed_time": "0:06:09", "remaining_time": "1:27:37", "throughput": 10053.15, "total_tokens": 3715712}
{"current_steps": 3875, "total_steps": 58920, "loss": 0.0043, "lr": 1.3150033944331296e-06, "epoch": 0.3288357094365241, "percentage": 6.58, "elapsed_time": "0:06:10", "remaining_time": "1:27:35", "throughput": 10056.55, "total_tokens": 3720960}
{"current_steps": 3880, "total_steps": 58920, "loss": 0.0607, "lr": 1.3167006109979633e-06, "epoch": 0.3292600135777325, "percentage": 6.59, "elapsed_time": "0:06:10", "remaining_time": "1:27:34", "throughput": 10058.6, "total_tokens": 3725504}
{"current_steps": 3885, "total_steps": 58920, "loss": 0.0598, "lr": 1.3183978275627969e-06, "epoch": 0.3296843177189409, "percentage": 6.59, "elapsed_time": "0:06:10", "remaining_time": "1:27:32", "throughput": 10060.21, "total_tokens": 3729856}
{"current_steps": 3890, "total_steps": 58920, "loss": 0.1319, "lr": 1.3200950441276306e-06, "epoch": 0.33010862186014933, "percentage": 6.6, "elapsed_time": "0:06:11", "remaining_time": "1:27:30", "throughput": 10063.61, "total_tokens": 3735040}
{"current_steps": 3895, "total_steps": 58920, "loss": 0.0357, "lr": 1.3217922606924643e-06, "epoch": 0.33053292600135775, "percentage": 6.61, "elapsed_time": "0:06:11", "remaining_time": "1:27:28", "throughput": 10067.05, "total_tokens": 3740288}
{"current_steps": 3900, "total_steps": 58920, "loss": 0.0863, "lr": 1.323489477257298e-06, "epoch": 0.33095723014256617, "percentage": 6.62, "elapsed_time": "0:06:11", "remaining_time": "1:27:26", "throughput": 10069.2, "total_tokens": 3744960}
{"current_steps": 3905, "total_steps": 58920, "loss": 0.094, "lr": 1.3251866938221316e-06, "epoch": 0.3313815342837746, "percentage": 6.63, "elapsed_time": "0:06:12", "remaining_time": "1:27:24", "throughput": 10070.34, "total_tokens": 3749120}
{"current_steps": 3910, "total_steps": 58920, "loss": 0.0703, "lr": 1.3268839103869653e-06, "epoch": 0.331805838424983, "percentage": 6.64, "elapsed_time": "0:06:12", "remaining_time": "1:27:23", "throughput": 10072.95, "total_tokens": 3753984}
{"current_steps": 3915, "total_steps": 58920, "loss": 0.0662, "lr": 1.328581126951799e-06, "epoch": 0.33223014256619143, "percentage": 6.64, "elapsed_time": "0:06:13", "remaining_time": "1:27:21", "throughput": 10074.73, "total_tokens": 3758464}
{"current_steps": 3920, "total_steps": 58920, "loss": 0.0934, "lr": 1.3302783435166326e-06, "epoch": 0.33265444670739985, "percentage": 6.65, "elapsed_time": "0:06:13", "remaining_time": "1:27:19", "throughput": 10075.85, "total_tokens": 3762624}
{"current_steps": 3925, "total_steps": 58920, "loss": 0.1093, "lr": 1.3319755600814663e-06, "epoch": 0.3330787508486083, "percentage": 6.66, "elapsed_time": "0:06:13", "remaining_time": "1:27:17", "throughput": 10078.71, "total_tokens": 3767616}
{"current_steps": 3930, "total_steps": 58920, "loss": 0.0252, "lr": 1.3336727766463e-06, "epoch": 0.3335030549898167, "percentage": 6.67, "elapsed_time": "0:06:14", "remaining_time": "1:27:16", "throughput": 10082.21, "total_tokens": 3772864}
{"current_steps": 3935, "total_steps": 58920, "loss": 0.0931, "lr": 1.3353699932111338e-06, "epoch": 0.3339273591310251, "percentage": 6.68, "elapsed_time": "0:06:14", "remaining_time": "1:27:14", "throughput": 10084.87, "total_tokens": 3777728}
{"current_steps": 3940, "total_steps": 58920, "loss": 0.0571, "lr": 1.3370672097759673e-06, "epoch": 0.33435166327223353, "percentage": 6.69, "elapsed_time": "0:06:14", "remaining_time": "1:27:12", "throughput": 10088.15, "total_tokens": 3782912}
{"current_steps": 3945, "total_steps": 58920, "loss": 0.072, "lr": 1.338764426340801e-06, "epoch": 0.33477596741344195, "percentage": 6.7, "elapsed_time": "0:06:15", "remaining_time": "1:27:11", "throughput": 10091.42, "total_tokens": 3788160}
{"current_steps": 3950, "total_steps": 58920, "loss": 0.0666, "lr": 1.3404616429056348e-06, "epoch": 0.3352002715546504, "percentage": 6.7, "elapsed_time": "0:06:15", "remaining_time": "1:27:09", "throughput": 10092.89, "total_tokens": 3792448}
{"current_steps": 3955, "total_steps": 58920, "loss": 0.0595, "lr": 1.3421588594704686e-06, "epoch": 0.3356245756958588, "percentage": 6.71, "elapsed_time": "0:06:16", "remaining_time": "1:27:07", "throughput": 10095.62, "total_tokens": 3797376}
{"current_steps": 3960, "total_steps": 58920, "loss": 0.1053, "lr": 1.3438560760353019e-06, "epoch": 0.3360488798370672, "percentage": 6.72, "elapsed_time": "0:06:16", "remaining_time": "1:27:05", "throughput": 10098.83, "total_tokens": 3802496}
{"current_steps": 3965, "total_steps": 58920, "loss": 0.0499, "lr": 1.3455532926001356e-06, "epoch": 0.33647318397827564, "percentage": 6.73, "elapsed_time": "0:06:16", "remaining_time": "1:27:03", "throughput": 10100.48, "total_tokens": 3806912}
{"current_steps": 3970, "total_steps": 58920, "loss": 0.0745, "lr": 1.3472505091649693e-06, "epoch": 0.33689748811948406, "percentage": 6.74, "elapsed_time": "0:06:17", "remaining_time": "1:27:02", "throughput": 10102.92, "total_tokens": 3811648}
{"current_steps": 3975, "total_steps": 58920, "loss": 0.0783, "lr": 1.3489477257298029e-06, "epoch": 0.3373217922606925, "percentage": 6.75, "elapsed_time": "0:06:17", "remaining_time": "1:27:00", "throughput": 10106.52, "total_tokens": 3817024}
{"current_steps": 3980, "total_steps": 58920, "loss": 0.0566, "lr": 1.3506449422946366e-06, "epoch": 0.3377460964019009, "percentage": 6.75, "elapsed_time": "0:06:18", "remaining_time": "1:26:58", "throughput": 10108.16, "total_tokens": 3821440}
{"current_steps": 3985, "total_steps": 58920, "loss": 0.0366, "lr": 1.3523421588594703e-06, "epoch": 0.3381704005431093, "percentage": 6.76, "elapsed_time": "0:06:18", "remaining_time": "1:26:56", "throughput": 10110.17, "total_tokens": 3825984}
{"current_steps": 3990, "total_steps": 58920, "loss": 0.0715, "lr": 1.354039375424304e-06, "epoch": 0.33859470468431774, "percentage": 6.77, "elapsed_time": "0:06:18", "remaining_time": "1:26:55", "throughput": 10113.32, "total_tokens": 3831104}
{"current_steps": 3995, "total_steps": 58920, "loss": 0.0846, "lr": 1.3557365919891376e-06, "epoch": 0.33901900882552616, "percentage": 6.78, "elapsed_time": "0:06:19", "remaining_time": "1:26:53", "throughput": 10116.25, "total_tokens": 3836160}
{"current_steps": 4000, "total_steps": 58920, "loss": 0.0903, "lr": 1.3574338085539713e-06, "epoch": 0.3394433129667346, "percentage": 6.79, "elapsed_time": "0:06:19", "remaining_time": "1:26:51", "throughput": 10118.0, "total_tokens": 3840640}
{"current_steps": 4005, "total_steps": 58920, "loss": 0.0482, "lr": 1.359131025118805e-06, "epoch": 0.339867617107943, "percentage": 6.8, "elapsed_time": "0:06:19", "remaining_time": "1:26:49", "throughput": 10120.53, "total_tokens": 3845440}
{"current_steps": 4010, "total_steps": 58920, "loss": 0.1198, "lr": 1.3608282416836388e-06, "epoch": 0.3402919212491514, "percentage": 6.81, "elapsed_time": "0:06:20", "remaining_time": "1:26:48", "throughput": 10123.23, "total_tokens": 3850368}
{"current_steps": 4015, "total_steps": 58920, "loss": 0.057, "lr": 1.3625254582484724e-06, "epoch": 0.3407162253903598, "percentage": 6.81, "elapsed_time": "0:06:20", "remaining_time": "1:26:46", "throughput": 10125.98, "total_tokens": 3855296}
{"current_steps": 4020, "total_steps": 58920, "loss": 0.0606, "lr": 1.364222674813306e-06, "epoch": 0.3411405295315682, "percentage": 6.82, "elapsed_time": "0:06:21", "remaining_time": "1:26:44", "throughput": 10127.45, "total_tokens": 3859648}
{"current_steps": 4025, "total_steps": 58920, "loss": 0.0275, "lr": 1.3659198913781398e-06, "epoch": 0.3415648336727766, "percentage": 6.83, "elapsed_time": "0:06:21", "remaining_time": "1:26:42", "throughput": 10130.14, "total_tokens": 3864512}
{"current_steps": 4030, "total_steps": 58920, "loss": 0.0659, "lr": 1.3676171079429736e-06, "epoch": 0.34198913781398504, "percentage": 6.84, "elapsed_time": "0:06:21", "remaining_time": "1:26:41", "throughput": 10131.55, "total_tokens": 3868800}
{"current_steps": 4035, "total_steps": 58920, "loss": 0.0767, "lr": 1.369314324507807e-06, "epoch": 0.34241344195519346, "percentage": 6.85, "elapsed_time": "0:06:22", "remaining_time": "1:26:39", "throughput": 10134.12, "total_tokens": 3873664}
{"current_steps": 4040, "total_steps": 58920, "loss": 0.0957, "lr": 1.3710115410726408e-06, "epoch": 0.3428377460964019, "percentage": 6.86, "elapsed_time": "0:06:22", "remaining_time": "1:26:37", "throughput": 10136.52, "total_tokens": 3878528}
{"current_steps": 4045, "total_steps": 58920, "loss": 0.075, "lr": 1.3727087576374746e-06, "epoch": 0.3432620502376103, "percentage": 6.87, "elapsed_time": "0:06:23", "remaining_time": "1:26:35", "throughput": 10138.43, "total_tokens": 3883136}
{"current_steps": 4050, "total_steps": 58920, "loss": 0.0678, "lr": 1.374405974202308e-06, "epoch": 0.3436863543788187, "percentage": 6.87, "elapsed_time": "0:06:23", "remaining_time": "1:26:34", "throughput": 10141.65, "total_tokens": 3888384}
{"current_steps": 4055, "total_steps": 58920, "loss": 0.0065, "lr": 1.3761031907671418e-06, "epoch": 0.34411065852002715, "percentage": 6.88, "elapsed_time": "0:06:23", "remaining_time": "1:26:32", "throughput": 10143.7, "total_tokens": 3893056}
{"current_steps": 4060, "total_steps": 58920, "loss": 0.0764, "lr": 1.3778004073319756e-06, "epoch": 0.34453496266123557, "percentage": 6.89, "elapsed_time": "0:06:24", "remaining_time": "1:26:31", "throughput": 10145.55, "total_tokens": 3897600}
{"current_steps": 4065, "total_steps": 58920, "loss": 0.0637, "lr": 1.3794976238968093e-06, "epoch": 0.344959266802444, "percentage": 6.9, "elapsed_time": "0:06:24", "remaining_time": "1:26:29", "throughput": 10147.23, "total_tokens": 3902080}
{"current_steps": 4070, "total_steps": 58920, "loss": 0.0521, "lr": 1.3811948404616428e-06, "epoch": 0.3453835709436524, "percentage": 6.91, "elapsed_time": "0:06:24", "remaining_time": "1:26:27", "throughput": 10149.59, "total_tokens": 3906880}
{"current_steps": 4075, "total_steps": 58920, "loss": 0.1336, "lr": 1.3828920570264766e-06, "epoch": 0.3458078750848608, "percentage": 6.92, "elapsed_time": "0:06:25", "remaining_time": "1:26:25", "throughput": 10150.52, "total_tokens": 3911040}
{"current_steps": 4080, "total_steps": 58920, "loss": 0.0619, "lr": 1.3845892735913103e-06, "epoch": 0.34623217922606925, "percentage": 6.92, "elapsed_time": "0:06:25", "remaining_time": "1:26:24", "throughput": 10152.64, "total_tokens": 3915712}
{"current_steps": 4085, "total_steps": 58920, "loss": 0.0876, "lr": 1.386286490156144e-06, "epoch": 0.34665648336727767, "percentage": 6.93, "elapsed_time": "0:06:26", "remaining_time": "1:26:22", "throughput": 10153.77, "total_tokens": 3919936}
{"current_steps": 4090, "total_steps": 58920, "loss": 0.132, "lr": 1.3879837067209776e-06, "epoch": 0.3470807875084861, "percentage": 6.94, "elapsed_time": "0:06:26", "remaining_time": "1:26:20", "throughput": 10155.66, "total_tokens": 3924480}
{"current_steps": 4095, "total_steps": 58920, "loss": 0.1276, "lr": 1.389680923285811e-06, "epoch": 0.3475050916496945, "percentage": 6.95, "elapsed_time": "0:06:26", "remaining_time": "1:26:18", "throughput": 10158.92, "total_tokens": 3929728}
{"current_steps": 4100, "total_steps": 58920, "loss": 0.0431, "lr": 1.3913781398506448e-06, "epoch": 0.34792939579090293, "percentage": 6.96, "elapsed_time": "0:06:27", "remaining_time": "1:26:17", "throughput": 10160.28, "total_tokens": 3934080}
{"current_steps": 4105, "total_steps": 58920, "loss": 0.1045, "lr": 1.3930753564154784e-06, "epoch": 0.34835369993211135, "percentage": 6.97, "elapsed_time": "0:06:27", "remaining_time": "1:26:15", "throughput": 10162.12, "total_tokens": 3938624}
{"current_steps": 4110, "total_steps": 58920, "loss": 0.1011, "lr": 1.394772572980312e-06, "epoch": 0.34877800407331977, "percentage": 6.98, "elapsed_time": "0:06:27", "remaining_time": "1:26:14", "throughput": 10166.34, "total_tokens": 3944448}
{"current_steps": 4115, "total_steps": 58920, "loss": 0.0386, "lr": 1.3964697895451458e-06, "epoch": 0.3492023082145282, "percentage": 6.98, "elapsed_time": "0:06:28", "remaining_time": "1:26:12", "throughput": 10168.56, "total_tokens": 3949184}
{"current_steps": 4120, "total_steps": 58920, "loss": 0.062, "lr": 1.3981670061099796e-06, "epoch": 0.3496266123557366, "percentage": 6.99, "elapsed_time": "0:06:28", "remaining_time": "1:26:10", "throughput": 10170.27, "total_tokens": 3953664}
{"current_steps": 4125, "total_steps": 58920, "loss": 0.0672, "lr": 1.399864222674813e-06, "epoch": 0.35005091649694503, "percentage": 7.0, "elapsed_time": "0:06:29", "remaining_time": "1:26:08", "throughput": 10172.4, "total_tokens": 3958336}
{"current_steps": 4130, "total_steps": 58920, "loss": 0.0172, "lr": 1.4015614392396468e-06, "epoch": 0.35047522063815345, "percentage": 7.01, "elapsed_time": "0:06:29", "remaining_time": "1:26:07", "throughput": 10175.68, "total_tokens": 3963584}
{"current_steps": 4135, "total_steps": 58920, "loss": 0.0791, "lr": 1.4032586558044806e-06, "epoch": 0.35089952477936187, "percentage": 7.02, "elapsed_time": "0:06:29", "remaining_time": "1:26:05", "throughput": 10179.02, "total_tokens": 3968896}
{"current_steps": 4140, "total_steps": 58920, "loss": 0.11, "lr": 1.4049558723693143e-06, "epoch": 0.3513238289205703, "percentage": 7.03, "elapsed_time": "0:06:30", "remaining_time": "1:26:04", "throughput": 10180.79, "total_tokens": 3973440}
{"current_steps": 4145, "total_steps": 58920, "loss": 0.064, "lr": 1.4066530889341478e-06, "epoch": 0.35174813306177866, "percentage": 7.03, "elapsed_time": "0:06:30", "remaining_time": "1:26:02", "throughput": 10183.03, "total_tokens": 3978176}
{"current_steps": 4150, "total_steps": 58920, "loss": 0.0726, "lr": 1.4083503054989816e-06, "epoch": 0.3521724372029871, "percentage": 7.04, "elapsed_time": "0:06:31", "remaining_time": "1:26:01", "throughput": 10186.09, "total_tokens": 3983360}
{"current_steps": 4155, "total_steps": 58920, "loss": 0.0671, "lr": 1.4100475220638153e-06, "epoch": 0.3525967413441955, "percentage": 7.05, "elapsed_time": "0:06:31", "remaining_time": "1:25:59", "throughput": 10187.29, "total_tokens": 3987584}
{"current_steps": 4160, "total_steps": 58920, "loss": 0.0615, "lr": 1.411744738628649e-06, "epoch": 0.3530210454854039, "percentage": 7.06, "elapsed_time": "0:06:31", "remaining_time": "1:25:57", "throughput": 10189.88, "total_tokens": 3992576}
{"current_steps": 4165, "total_steps": 58920, "loss": 0.0532, "lr": 1.4134419551934826e-06, "epoch": 0.35344534962661234, "percentage": 7.07, "elapsed_time": "0:06:32", "remaining_time": "1:25:56", "throughput": 10192.95, "total_tokens": 3997824}
{"current_steps": 4170, "total_steps": 58920, "loss": 0.1066, "lr": 1.4151391717583163e-06, "epoch": 0.35386965376782076, "percentage": 7.08, "elapsed_time": "0:06:32", "remaining_time": "1:25:54", "throughput": 10194.1, "total_tokens": 4002048}
{"current_steps": 4175, "total_steps": 58920, "loss": 0.0721, "lr": 1.41683638832315e-06, "epoch": 0.3542939579090292, "percentage": 7.09, "elapsed_time": "0:06:32", "remaining_time": "1:25:52", "throughput": 10196.02, "total_tokens": 4006656}
{"current_steps": 4180, "total_steps": 58920, "loss": 0.0291, "lr": 1.4185336048879836e-06, "epoch": 0.3547182620502376, "percentage": 7.09, "elapsed_time": "0:06:33", "remaining_time": "1:25:51", "throughput": 10197.57, "total_tokens": 4011136}
{"current_steps": 4185, "total_steps": 58920, "loss": 0.0667, "lr": 1.4202308214528173e-06, "epoch": 0.355142566191446, "percentage": 7.1, "elapsed_time": "0:06:33", "remaining_time": "1:25:49", "throughput": 10199.57, "total_tokens": 4015808}
{"current_steps": 4190, "total_steps": 58920, "loss": 0.061, "lr": 1.421928038017651e-06, "epoch": 0.35556687033265444, "percentage": 7.11, "elapsed_time": "0:06:34", "remaining_time": "1:25:47", "throughput": 10201.62, "total_tokens": 4020480}
{"current_steps": 4195, "total_steps": 58920, "loss": 0.0352, "lr": 1.4236252545824848e-06, "epoch": 0.35599117447386286, "percentage": 7.12, "elapsed_time": "0:06:34", "remaining_time": "1:25:46", "throughput": 10203.59, "total_tokens": 4025088}
{"current_steps": 4200, "total_steps": 58920, "loss": 0.0854, "lr": 1.4253224711473183e-06, "epoch": 0.3564154786150713, "percentage": 7.13, "elapsed_time": "0:06:34", "remaining_time": "1:25:44", "throughput": 10206.64, "total_tokens": 4030272}
{"current_steps": 4205, "total_steps": 58920, "loss": 0.0848, "lr": 1.427019687712152e-06, "epoch": 0.3568397827562797, "percentage": 7.14, "elapsed_time": "0:06:35", "remaining_time": "1:25:42", "throughput": 10208.86, "total_tokens": 4035072}
{"current_steps": 4210, "total_steps": 58920, "loss": 0.077, "lr": 1.4287169042769858e-06, "epoch": 0.3572640868974881, "percentage": 7.15, "elapsed_time": "0:06:35", "remaining_time": "1:25:41", "throughput": 10210.3, "total_tokens": 4039488}
{"current_steps": 4215, "total_steps": 58920, "loss": 0.1488, "lr": 1.4304141208418195e-06, "epoch": 0.35768839103869654, "percentage": 7.15, "elapsed_time": "0:06:36", "remaining_time": "1:25:39", "throughput": 10212.96, "total_tokens": 4044480}
{"current_steps": 4220, "total_steps": 58920, "loss": 0.084, "lr": 1.432111337406653e-06, "epoch": 0.35811269517990496, "percentage": 7.16, "elapsed_time": "0:06:36", "remaining_time": "1:25:37", "throughput": 10214.24, "total_tokens": 4048768}
{"current_steps": 4225, "total_steps": 58920, "loss": 0.0379, "lr": 1.4338085539714866e-06, "epoch": 0.3585369993211134, "percentage": 7.17, "elapsed_time": "0:06:36", "remaining_time": "1:25:36", "throughput": 10216.29, "total_tokens": 4053504}
{"current_steps": 4230, "total_steps": 58920, "loss": 0.0333, "lr": 1.4355057705363203e-06, "epoch": 0.3589613034623218, "percentage": 7.18, "elapsed_time": "0:06:37", "remaining_time": "1:25:34", "throughput": 10217.66, "total_tokens": 4057856}
{"current_steps": 4235, "total_steps": 58920, "loss": 0.0357, "lr": 1.4372029871011539e-06, "epoch": 0.3593856076035302, "percentage": 7.19, "elapsed_time": "0:06:37", "remaining_time": "1:25:33", "throughput": 10220.17, "total_tokens": 4062784}
{"current_steps": 4240, "total_steps": 58920, "loss": 0.0351, "lr": 1.4389002036659876e-06, "epoch": 0.35980991174473864, "percentage": 7.2, "elapsed_time": "0:06:37", "remaining_time": "1:25:31", "throughput": 10221.92, "total_tokens": 4067328}
{"current_steps": 4245, "total_steps": 58920, "loss": 0.0609, "lr": 1.4405974202308213e-06, "epoch": 0.36023421588594706, "percentage": 7.2, "elapsed_time": "0:06:38", "remaining_time": "1:25:30", "throughput": 10225.29, "total_tokens": 4072704}
{"current_steps": 4250, "total_steps": 58920, "loss": 0.1231, "lr": 1.442294636795655e-06, "epoch": 0.3606585200271555, "percentage": 7.21, "elapsed_time": "0:06:38", "remaining_time": "1:25:28", "throughput": 10227.5, "total_tokens": 4077504}
{"current_steps": 4255, "total_steps": 58920, "loss": 0.1242, "lr": 1.4439918533604886e-06, "epoch": 0.3610828241683639, "percentage": 7.22, "elapsed_time": "0:06:39", "remaining_time": "1:25:26", "throughput": 10229.58, "total_tokens": 4082240}
{"current_steps": 4260, "total_steps": 58920, "loss": 0.0586, "lr": 1.4456890699253223e-06, "epoch": 0.3615071283095723, "percentage": 7.23, "elapsed_time": "0:06:39", "remaining_time": "1:25:25", "throughput": 10230.24, "total_tokens": 4086272}
{"current_steps": 4265, "total_steps": 58920, "loss": 0.054, "lr": 1.447386286490156e-06, "epoch": 0.36193143245078074, "percentage": 7.24, "elapsed_time": "0:06:39", "remaining_time": "1:25:23", "throughput": 10232.14, "total_tokens": 4090880}
{"current_steps": 4270, "total_steps": 58920, "loss": 0.074, "lr": 1.4490835030549898e-06, "epoch": 0.36235573659198916, "percentage": 7.25, "elapsed_time": "0:06:40", "remaining_time": "1:25:21", "throughput": 10233.96, "total_tokens": 4095552}
{"current_steps": 4275, "total_steps": 58920, "loss": 0.1098, "lr": 1.4507807196198233e-06, "epoch": 0.36278004073319753, "percentage": 7.26, "elapsed_time": "0:06:40", "remaining_time": "1:25:20", "throughput": 10236.09, "total_tokens": 4100352}
{"current_steps": 4280, "total_steps": 58920, "loss": 0.0431, "lr": 1.452477936184657e-06, "epoch": 0.36320434487440595, "percentage": 7.26, "elapsed_time": "0:06:40", "remaining_time": "1:25:18", "throughput": 10237.42, "total_tokens": 4104704}
{"current_steps": 4285, "total_steps": 58920, "loss": 0.1277, "lr": 1.4541751527494908e-06, "epoch": 0.36362864901561437, "percentage": 7.27, "elapsed_time": "0:06:41", "remaining_time": "1:25:17", "throughput": 10239.25, "total_tokens": 4109376}
{"current_steps": 4290, "total_steps": 58920, "loss": 0.1199, "lr": 1.4558723693143245e-06, "epoch": 0.3640529531568228, "percentage": 7.28, "elapsed_time": "0:06:41", "remaining_time": "1:25:15", "throughput": 10242.05, "total_tokens": 4114496}
{"current_steps": 4295, "total_steps": 58920, "loss": 0.0196, "lr": 1.457569585879158e-06, "epoch": 0.3644772572980312, "percentage": 7.29, "elapsed_time": "0:06:42", "remaining_time": "1:25:14", "throughput": 10244.63, "total_tokens": 4119552}
{"current_steps": 4300, "total_steps": 58920, "loss": 0.0473, "lr": 1.4592668024439918e-06, "epoch": 0.36490156143923963, "percentage": 7.3, "elapsed_time": "0:06:42", "remaining_time": "1:25:12", "throughput": 10246.79, "total_tokens": 4124352}
{"current_steps": 4305, "total_steps": 58920, "loss": 0.0619, "lr": 1.4609640190088255e-06, "epoch": 0.36532586558044805, "percentage": 7.31, "elapsed_time": "0:06:42", "remaining_time": "1:25:11", "throughput": 10248.93, "total_tokens": 4129152}
{"current_steps": 4310, "total_steps": 58920, "loss": 0.0731, "lr": 1.462661235573659e-06, "epoch": 0.36575016972165647, "percentage": 7.32, "elapsed_time": "0:06:43", "remaining_time": "1:25:09", "throughput": 10251.44, "total_tokens": 4134144}
{"current_steps": 4315, "total_steps": 58920, "loss": 0.1377, "lr": 1.4643584521384928e-06, "epoch": 0.3661744738628649, "percentage": 7.32, "elapsed_time": "0:06:43", "remaining_time": "1:25:08", "throughput": 10253.32, "total_tokens": 4138816}
{"current_steps": 4320, "total_steps": 58920, "loss": 0.0741, "lr": 1.4660556687033266e-06, "epoch": 0.3665987780040733, "percentage": 7.33, "elapsed_time": "0:06:44", "remaining_time": "1:25:06", "throughput": 10255.61, "total_tokens": 4143680}
{"current_steps": 4325, "total_steps": 58920, "loss": 0.0708, "lr": 1.4677528852681603e-06, "epoch": 0.36702308214528173, "percentage": 7.34, "elapsed_time": "0:06:44", "remaining_time": "1:25:05", "throughput": 10258.92, "total_tokens": 4149120}
{"current_steps": 4330, "total_steps": 58920, "loss": 0.0381, "lr": 1.4694501018329938e-06, "epoch": 0.36744738628649015, "percentage": 7.35, "elapsed_time": "0:06:44", "remaining_time": "1:25:03", "throughput": 10261.96, "total_tokens": 4154432}
{"current_steps": 4335, "total_steps": 58920, "loss": 0.0546, "lr": 1.4711473183978276e-06, "epoch": 0.36787169042769857, "percentage": 7.36, "elapsed_time": "0:06:45", "remaining_time": "1:25:02", "throughput": 10264.37, "total_tokens": 4159360}
{"current_steps": 4340, "total_steps": 58920, "loss": 0.0461, "lr": 1.4728445349626613e-06, "epoch": 0.368295994568907, "percentage": 7.37, "elapsed_time": "0:06:45", "remaining_time": "1:25:00", "throughput": 10265.24, "total_tokens": 4163520}
{"current_steps": 4345, "total_steps": 58920, "loss": 0.0616, "lr": 1.474541751527495e-06, "epoch": 0.3687202987101154, "percentage": 7.37, "elapsed_time": "0:06:45", "remaining_time": "1:24:59", "throughput": 10268.04, "total_tokens": 4168640}
{"current_steps": 4350, "total_steps": 58920, "loss": 0.1095, "lr": 1.4762389680923286e-06, "epoch": 0.36914460285132383, "percentage": 7.38, "elapsed_time": "0:06:46", "remaining_time": "1:24:57", "throughput": 10269.95, "total_tokens": 4173312}
{"current_steps": 4355, "total_steps": 58920, "loss": 0.1281, "lr": 1.477936184657162e-06, "epoch": 0.36956890699253225, "percentage": 7.39, "elapsed_time": "0:06:46", "remaining_time": "1:24:56", "throughput": 10271.24, "total_tokens": 4177664}
{"current_steps": 4360, "total_steps": 58920, "loss": 0.0241, "lr": 1.4796334012219958e-06, "epoch": 0.3699932111337407, "percentage": 7.4, "elapsed_time": "0:06:47", "remaining_time": "1:24:54", "throughput": 10272.43, "total_tokens": 4182016}
{"current_steps": 4365, "total_steps": 58920, "loss": 0.0093, "lr": 1.4813306177868293e-06, "epoch": 0.3704175152749491, "percentage": 7.41, "elapsed_time": "0:06:47", "remaining_time": "1:24:52", "throughput": 10274.19, "total_tokens": 4186624}
{"current_steps": 4370, "total_steps": 58920, "loss": 0.0999, "lr": 1.483027834351663e-06, "epoch": 0.3708418194161575, "percentage": 7.42, "elapsed_time": "0:06:47", "remaining_time": "1:24:51", "throughput": 10277.29, "total_tokens": 4191936}
{"current_steps": 4375, "total_steps": 58920, "loss": 0.1032, "lr": 1.4847250509164968e-06, "epoch": 0.37126612355736593, "percentage": 7.43, "elapsed_time": "0:06:48", "remaining_time": "1:24:49", "throughput": 10278.69, "total_tokens": 4196352}
{"current_steps": 4380, "total_steps": 58920, "loss": 0.0804, "lr": 1.4864222674813306e-06, "epoch": 0.37169042769857435, "percentage": 7.43, "elapsed_time": "0:06:48", "remaining_time": "1:24:48", "throughput": 10280.16, "total_tokens": 4200960}
{"current_steps": 4385, "total_steps": 58920, "loss": 0.0684, "lr": 1.488119484046164e-06, "epoch": 0.3721147318397828, "percentage": 7.44, "elapsed_time": "0:06:49", "remaining_time": "1:24:47", "throughput": 10283.04, "total_tokens": 4206208}
{"current_steps": 4390, "total_steps": 58920, "loss": 0.0608, "lr": 1.4898167006109978e-06, "epoch": 0.3725390359809912, "percentage": 7.45, "elapsed_time": "0:06:49", "remaining_time": "1:24:45", "throughput": 10284.56, "total_tokens": 4210688}
{"current_steps": 4395, "total_steps": 58920, "loss": 0.0405, "lr": 1.4915139171758316e-06, "epoch": 0.3729633401221996, "percentage": 7.46, "elapsed_time": "0:06:49", "remaining_time": "1:24:44", "throughput": 10286.6, "total_tokens": 4215424}
{"current_steps": 4400, "total_steps": 58920, "loss": 0.0125, "lr": 1.4932111337406653e-06, "epoch": 0.37338764426340804, "percentage": 7.47, "elapsed_time": "0:06:50", "remaining_time": "1:24:42", "throughput": 10288.67, "total_tokens": 4220160}
{"current_steps": 4405, "total_steps": 58920, "loss": 0.1011, "lr": 1.4949083503054988e-06, "epoch": 0.37381194840461646, "percentage": 7.48, "elapsed_time": "0:06:50", "remaining_time": "1:24:40", "throughput": 10290.56, "total_tokens": 4224832}
{"current_steps": 4410, "total_steps": 58920, "loss": 0.0857, "lr": 1.4966055668703326e-06, "epoch": 0.3742362525458248, "percentage": 7.48, "elapsed_time": "0:06:50", "remaining_time": "1:24:39", "throughput": 10294.23, "total_tokens": 4230464}
{"current_steps": 4415, "total_steps": 58920, "loss": 0.1167, "lr": 1.4983027834351663e-06, "epoch": 0.37466055668703324, "percentage": 7.49, "elapsed_time": "0:06:51", "remaining_time": "1:24:37", "throughput": 10295.51, "total_tokens": 4234816}
{"current_steps": 4420, "total_steps": 58920, "loss": 0.0952, "lr": 1.5e-06, "epoch": 0.37508486082824166, "percentage": 7.5, "elapsed_time": "0:06:51", "remaining_time": "1:24:36", "throughput": 10297.25, "total_tokens": 4239424}
{"current_steps": 4425, "total_steps": 58920, "loss": 0.0813, "lr": 1.5016972165648336e-06, "epoch": 0.3755091649694501, "percentage": 7.51, "elapsed_time": "0:06:52", "remaining_time": "1:24:34", "throughput": 10299.22, "total_tokens": 4244160}
{"current_steps": 4430, "total_steps": 58920, "loss": 0.0814, "lr": 1.5033944331296673e-06, "epoch": 0.3759334691106585, "percentage": 7.52, "elapsed_time": "0:06:52", "remaining_time": "1:24:33", "throughput": 10300.11, "total_tokens": 4248320}
{"current_steps": 4435, "total_steps": 58920, "loss": 0.0249, "lr": 1.505091649694501e-06, "epoch": 0.3763577732518669, "percentage": 7.53, "elapsed_time": "0:06:52", "remaining_time": "1:24:31", "throughput": 10301.36, "total_tokens": 4252672}
{"current_steps": 4440, "total_steps": 58920, "loss": 0.1028, "lr": 1.5067888662593346e-06, "epoch": 0.37678207739307534, "percentage": 7.54, "elapsed_time": "0:06:53", "remaining_time": "1:24:30", "throughput": 10303.03, "total_tokens": 4257280}
{"current_steps": 4445, "total_steps": 58920, "loss": 0.0219, "lr": 1.5084860828241683e-06, "epoch": 0.37720638153428376, "percentage": 7.54, "elapsed_time": "0:06:53", "remaining_time": "1:24:28", "throughput": 10306.06, "total_tokens": 4262592}
{"current_steps": 4450, "total_steps": 58920, "loss": 0.0963, "lr": 1.510183299389002e-06, "epoch": 0.3776306856754922, "percentage": 7.55, "elapsed_time": "0:06:53", "remaining_time": "1:24:27", "throughput": 10308.93, "total_tokens": 4267840}
{"current_steps": 4455, "total_steps": 58920, "loss": 0.0895, "lr": 1.5118805159538358e-06, "epoch": 0.3780549898167006, "percentage": 7.56, "elapsed_time": "0:06:54", "remaining_time": "1:24:26", "throughput": 10310.82, "total_tokens": 4272576}
{"current_steps": 4460, "total_steps": 58920, "loss": 0.0605, "lr": 1.5135777325186693e-06, "epoch": 0.378479293957909, "percentage": 7.57, "elapsed_time": "0:06:54", "remaining_time": "1:24:24", "throughput": 10313.32, "total_tokens": 4277568}
{"current_steps": 4465, "total_steps": 58920, "loss": 0.0868, "lr": 1.515274949083503e-06, "epoch": 0.37890359809911744, "percentage": 7.58, "elapsed_time": "0:06:55", "remaining_time": "1:24:23", "throughput": 10316.35, "total_tokens": 4282880}
{"current_steps": 4470, "total_steps": 58920, "loss": 0.1136, "lr": 1.5169721656483368e-06, "epoch": 0.37932790224032586, "percentage": 7.59, "elapsed_time": "0:06:55", "remaining_time": "1:24:21", "throughput": 10317.62, "total_tokens": 4287296}
{"current_steps": 4475, "total_steps": 58920, "loss": 0.0732, "lr": 1.5186693822131705e-06, "epoch": 0.3797522063815343, "percentage": 7.6, "elapsed_time": "0:06:55", "remaining_time": "1:24:20", "throughput": 10318.96, "total_tokens": 4291712}
{"current_steps": 4480, "total_steps": 58920, "loss": 0.1006, "lr": 1.520366598778004e-06, "epoch": 0.3801765105227427, "percentage": 7.6, "elapsed_time": "0:06:56", "remaining_time": "1:24:18", "throughput": 10322.01, "total_tokens": 4297088}
{"current_steps": 4485, "total_steps": 58920, "loss": 0.0591, "lr": 1.5220638153428378e-06, "epoch": 0.3806008146639511, "percentage": 7.61, "elapsed_time": "0:06:56", "remaining_time": "1:24:17", "throughput": 10325.34, "total_tokens": 4302784}
{"current_steps": 4490, "total_steps": 58920, "loss": 0.0233, "lr": 1.5237610319076713e-06, "epoch": 0.38102511880515955, "percentage": 7.62, "elapsed_time": "0:06:57", "remaining_time": "1:24:16", "throughput": 10327.45, "total_tokens": 4307584}
{"current_steps": 4495, "total_steps": 58920, "loss": 0.0233, "lr": 1.5254582484725048e-06, "epoch": 0.38144942294636797, "percentage": 7.63, "elapsed_time": "0:06:57", "remaining_time": "1:24:14", "throughput": 10328.93, "total_tokens": 4312064}
{"current_steps": 4500, "total_steps": 58920, "loss": 0.0328, "lr": 1.5271554650373386e-06, "epoch": 0.3818737270875764, "percentage": 7.64, "elapsed_time": "0:06:57", "remaining_time": "1:24:13", "throughput": 10330.59, "total_tokens": 4316672}
{"current_steps": 4505, "total_steps": 58920, "loss": 0.0532, "lr": 1.5288526816021723e-06, "epoch": 0.3822980312287848, "percentage": 7.65, "elapsed_time": "0:06:58", "remaining_time": "1:24:11", "throughput": 10331.96, "total_tokens": 4321088}
{"current_steps": 4510, "total_steps": 58920, "loss": 0.1004, "lr": 1.530549898167006e-06, "epoch": 0.3827223353699932, "percentage": 7.65, "elapsed_time": "0:06:58", "remaining_time": "1:24:10", "throughput": 10334.63, "total_tokens": 4326208}
{"current_steps": 4515, "total_steps": 58920, "loss": 0.1048, "lr": 1.5322471147318396e-06, "epoch": 0.38314663951120165, "percentage": 7.66, "elapsed_time": "0:06:58", "remaining_time": "1:24:08", "throughput": 10336.66, "total_tokens": 4331008}
{"current_steps": 4520, "total_steps": 58920, "loss": 0.0404, "lr": 1.5339443312966733e-06, "epoch": 0.38357094365241007, "percentage": 7.67, "elapsed_time": "0:06:59", "remaining_time": "1:24:07", "throughput": 10338.98, "total_tokens": 4335936}
{"current_steps": 4525, "total_steps": 58920, "loss": 0.0421, "lr": 1.535641547861507e-06, "epoch": 0.3839952477936185, "percentage": 7.68, "elapsed_time": "0:06:59", "remaining_time": "1:24:05", "throughput": 10340.75, "total_tokens": 4340608}
{"current_steps": 4530, "total_steps": 58920, "loss": 0.0699, "lr": 1.5373387644263408e-06, "epoch": 0.3844195519348269, "percentage": 7.69, "elapsed_time": "0:07:00", "remaining_time": "1:24:04", "throughput": 10342.65, "total_tokens": 4345344}
{"current_steps": 4535, "total_steps": 58920, "loss": 0.0573, "lr": 1.5390359809911743e-06, "epoch": 0.38484385607603533, "percentage": 7.7, "elapsed_time": "0:07:00", "remaining_time": "1:24:03", "throughput": 10347.38, "total_tokens": 4351680}
{"current_steps": 4540, "total_steps": 58920, "loss": 0.1396, "lr": 1.540733197556008e-06, "epoch": 0.3852681602172437, "percentage": 7.71, "elapsed_time": "0:07:00", "remaining_time": "1:24:01", "throughput": 10348.52, "total_tokens": 4356032}
{"current_steps": 4545, "total_steps": 58920, "loss": 0.0505, "lr": 1.5424304141208418e-06, "epoch": 0.3856924643584521, "percentage": 7.71, "elapsed_time": "0:07:01", "remaining_time": "1:24:00", "throughput": 10350.03, "total_tokens": 4360576}
{"current_steps": 4550, "total_steps": 58920, "loss": 0.1124, "lr": 1.5441276306856753e-06, "epoch": 0.38611676849966053, "percentage": 7.72, "elapsed_time": "0:07:01", "remaining_time": "1:23:58", "throughput": 10352.03, "total_tokens": 4365376}
{"current_steps": 4555, "total_steps": 58920, "loss": 0.0339, "lr": 1.545824847250509e-06, "epoch": 0.38654107264086895, "percentage": 7.73, "elapsed_time": "0:07:02", "remaining_time": "1:23:57", "throughput": 10354.42, "total_tokens": 4370368}
{"current_steps": 4560, "total_steps": 58920, "loss": 0.1167, "lr": 1.5475220638153428e-06, "epoch": 0.3869653767820774, "percentage": 7.74, "elapsed_time": "0:07:02", "remaining_time": "1:23:56", "throughput": 10357.01, "total_tokens": 4375488}
{"current_steps": 4565, "total_steps": 58920, "loss": 0.1501, "lr": 1.5492192803801765e-06, "epoch": 0.3873896809232858, "percentage": 7.75, "elapsed_time": "0:07:02", "remaining_time": "1:23:54", "throughput": 10359.15, "total_tokens": 4380352}
{"current_steps": 4570, "total_steps": 58920, "loss": 0.0813, "lr": 1.55091649694501e-06, "epoch": 0.3878139850644942, "percentage": 7.76, "elapsed_time": "0:07:03", "remaining_time": "1:23:53", "throughput": 10362.05, "total_tokens": 4385664}
{"current_steps": 4575, "total_steps": 58920, "loss": 0.1504, "lr": 1.5526137135098438e-06, "epoch": 0.38823828920570264, "percentage": 7.76, "elapsed_time": "0:07:03", "remaining_time": "1:23:52", "throughput": 10364.14, "total_tokens": 4390528}
{"current_steps": 4580, "total_steps": 58920, "loss": 0.0303, "lr": 1.5543109300746775e-06, "epoch": 0.38866259334691106, "percentage": 7.77, "elapsed_time": "0:07:04", "remaining_time": "1:23:50", "throughput": 10365.8, "total_tokens": 4395136}
{"current_steps": 4585, "total_steps": 58920, "loss": 0.0585, "lr": 1.5560081466395113e-06, "epoch": 0.3890868974881195, "percentage": 7.78, "elapsed_time": "0:07:04", "remaining_time": "1:23:49", "throughput": 10368.4, "total_tokens": 4400320}
{"current_steps": 4590, "total_steps": 58920, "loss": 0.031, "lr": 1.5577053632043448e-06, "epoch": 0.3895112016293279, "percentage": 7.79, "elapsed_time": "0:07:04", "remaining_time": "1:23:48", "throughput": 10369.93, "total_tokens": 4405056}
{"current_steps": 4595, "total_steps": 58920, "loss": 0.0901, "lr": 1.5594025797691785e-06, "epoch": 0.3899355057705363, "percentage": 7.8, "elapsed_time": "0:07:05", "remaining_time": "1:23:46", "throughput": 10373.23, "total_tokens": 4410624}
{"current_steps": 4600, "total_steps": 58920, "loss": 0.0222, "lr": 1.5610997963340123e-06, "epoch": 0.39035980991174474, "percentage": 7.81, "elapsed_time": "0:07:05", "remaining_time": "1:23:45", "throughput": 10375.27, "total_tokens": 4415424}
{"current_steps": 4605, "total_steps": 58920, "loss": 0.0516, "lr": 1.562797012898846e-06, "epoch": 0.39078411405295316, "percentage": 7.82, "elapsed_time": "0:07:05", "remaining_time": "1:23:44", "throughput": 10377.24, "total_tokens": 4420224}
{"current_steps": 4610, "total_steps": 58920, "loss": 0.1012, "lr": 1.5644942294636795e-06, "epoch": 0.3912084181941616, "percentage": 7.82, "elapsed_time": "0:07:06", "remaining_time": "1:23:42", "throughput": 10378.98, "total_tokens": 4424896}
{"current_steps": 4615, "total_steps": 58920, "loss": 0.0562, "lr": 1.5661914460285133e-06, "epoch": 0.39163272233537, "percentage": 7.83, "elapsed_time": "0:07:06", "remaining_time": "1:23:41", "throughput": 10380.25, "total_tokens": 4429312}
{"current_steps": 4620, "total_steps": 58920, "loss": 0.1264, "lr": 1.5678886625933468e-06, "epoch": 0.3920570264765784, "percentage": 7.84, "elapsed_time": "0:07:07", "remaining_time": "1:23:39", "throughput": 10381.88, "total_tokens": 4433920}
{"current_steps": 4625, "total_steps": 58920, "loss": 0.0664, "lr": 1.5695858791581803e-06, "epoch": 0.39248133061778684, "percentage": 7.85, "elapsed_time": "0:07:07", "remaining_time": "1:23:38", "throughput": 10383.31, "total_tokens": 4438464}
{"current_steps": 4630, "total_steps": 58920, "loss": 0.0705, "lr": 1.571283095723014e-06, "epoch": 0.39290563475899526, "percentage": 7.86, "elapsed_time": "0:07:07", "remaining_time": "1:23:36", "throughput": 10385.82, "total_tokens": 4443584}
{"current_steps": 4635, "total_steps": 58920, "loss": 0.0693, "lr": 1.5729803122878478e-06, "epoch": 0.3933299389002037, "percentage": 7.87, "elapsed_time": "0:07:08", "remaining_time": "1:23:35", "throughput": 10388.84, "total_tokens": 4448960}
{"current_steps": 4640, "total_steps": 58920, "loss": 0.041, "lr": 1.5746775288526815e-06, "epoch": 0.3937542430414121, "percentage": 7.88, "elapsed_time": "0:07:08", "remaining_time": "1:23:34", "throughput": 10390.27, "total_tokens": 4453504}
{"current_steps": 4645, "total_steps": 58920, "loss": 0.1052, "lr": 1.576374745417515e-06, "epoch": 0.3941785471826205, "percentage": 7.88, "elapsed_time": "0:07:08", "remaining_time": "1:23:32", "throughput": 10391.73, "total_tokens": 4458048}
{"current_steps": 4650, "total_steps": 58920, "loss": 0.0985, "lr": 1.5780719619823488e-06, "epoch": 0.39460285132382894, "percentage": 7.89, "elapsed_time": "0:07:09", "remaining_time": "1:23:31", "throughput": 10394.14, "total_tokens": 4463168}
{"current_steps": 4655, "total_steps": 58920, "loss": 0.1483, "lr": 1.5797691785471825e-06, "epoch": 0.39502715546503736, "percentage": 7.9, "elapsed_time": "0:07:09", "remaining_time": "1:23:29", "throughput": 10395.3, "total_tokens": 4467520}
{"current_steps": 4660, "total_steps": 58920, "loss": 0.0839, "lr": 1.5814663951120163e-06, "epoch": 0.3954514596062458, "percentage": 7.91, "elapsed_time": "0:07:10", "remaining_time": "1:23:28", "throughput": 10398.25, "total_tokens": 4472960}
{"current_steps": 4665, "total_steps": 58920, "loss": 0.0777, "lr": 1.5831636116768498e-06, "epoch": 0.3958757637474542, "percentage": 7.92, "elapsed_time": "0:07:10", "remaining_time": "1:23:27", "throughput": 10399.45, "total_tokens": 4477312}
{"current_steps": 4670, "total_steps": 58920, "loss": 0.0324, "lr": 1.5848608282416835e-06, "epoch": 0.39630006788866257, "percentage": 7.93, "elapsed_time": "0:07:10", "remaining_time": "1:23:25", "throughput": 10401.92, "total_tokens": 4482432}
{"current_steps": 4675, "total_steps": 58920, "loss": 0.0524, "lr": 1.5865580448065173e-06, "epoch": 0.396724372029871, "percentage": 7.93, "elapsed_time": "0:07:11", "remaining_time": "1:23:24", "throughput": 10402.43, "total_tokens": 4486464}
{"current_steps": 4680, "total_steps": 58920, "loss": 0.0972, "lr": 1.5882552613713508e-06, "epoch": 0.3971486761710794, "percentage": 7.94, "elapsed_time": "0:07:11", "remaining_time": "1:23:23", "throughput": 10404.77, "total_tokens": 4491520}
{"current_steps": 4685, "total_steps": 58920, "loss": 0.1026, "lr": 1.5899524779361845e-06, "epoch": 0.3975729803122878, "percentage": 7.95, "elapsed_time": "0:07:12", "remaining_time": "1:23:21", "throughput": 10406.54, "total_tokens": 4496256}
{"current_steps": 4690, "total_steps": 58920, "loss": 0.0745, "lr": 1.5916496945010183e-06, "epoch": 0.39799728445349625, "percentage": 7.96, "elapsed_time": "0:07:12", "remaining_time": "1:23:20", "throughput": 10407.23, "total_tokens": 4500416}
{"current_steps": 4695, "total_steps": 58920, "loss": 0.037, "lr": 1.593346911065852e-06, "epoch": 0.39842158859470467, "percentage": 7.97, "elapsed_time": "0:07:12", "remaining_time": "1:23:18", "throughput": 10409.76, "total_tokens": 4505536}
{"current_steps": 4700, "total_steps": 58920, "loss": 0.147, "lr": 1.5950441276306855e-06, "epoch": 0.3988458927359131, "percentage": 7.98, "elapsed_time": "0:07:13", "remaining_time": "1:23:17", "throughput": 10411.76, "total_tokens": 4510400}
{"current_steps": 4705, "total_steps": 58920, "loss": 0.1147, "lr": 1.5967413441955193e-06, "epoch": 0.3992701968771215, "percentage": 7.99, "elapsed_time": "0:07:13", "remaining_time": "1:23:16", "throughput": 10414.92, "total_tokens": 4515904}
{"current_steps": 4710, "total_steps": 58920, "loss": 0.1116, "lr": 1.598438560760353e-06, "epoch": 0.39969450101832993, "percentage": 7.99, "elapsed_time": "0:07:13", "remaining_time": "1:23:14", "throughput": 10416.33, "total_tokens": 4520448}
{"current_steps": 4715, "total_steps": 58920, "loss": 0.0886, "lr": 1.6001357773251868e-06, "epoch": 0.40011880515953835, "percentage": 8.0, "elapsed_time": "0:07:14", "remaining_time": "1:23:13", "throughput": 10419.17, "total_tokens": 4525824}
{"current_steps": 4720, "total_steps": 58920, "loss": 0.0669, "lr": 1.6018329938900203e-06, "epoch": 0.40054310930074677, "percentage": 8.01, "elapsed_time": "0:07:14", "remaining_time": "1:23:12", "throughput": 10420.48, "total_tokens": 4530304}
{"current_steps": 4725, "total_steps": 58920, "loss": 0.0957, "lr": 1.603530210454854e-06, "epoch": 0.4009674134419552, "percentage": 8.02, "elapsed_time": "0:07:15", "remaining_time": "1:23:10", "throughput": 10421.74, "total_tokens": 4534720}
{"current_steps": 4730, "total_steps": 58920, "loss": 0.1052, "lr": 1.6052274270196878e-06, "epoch": 0.4013917175831636, "percentage": 8.03, "elapsed_time": "0:07:15", "remaining_time": "1:23:09", "throughput": 10423.61, "total_tokens": 4539520}
{"current_steps": 4735, "total_steps": 58920, "loss": 0.0066, "lr": 1.6069246435845215e-06, "epoch": 0.40181602172437203, "percentage": 8.04, "elapsed_time": "0:07:15", "remaining_time": "1:23:08", "throughput": 10425.65, "total_tokens": 4544448}
{"current_steps": 4740, "total_steps": 58920, "loss": 0.0484, "lr": 1.608621860149355e-06, "epoch": 0.40224032586558045, "percentage": 8.04, "elapsed_time": "0:07:16", "remaining_time": "1:23:06", "throughput": 10428.12, "total_tokens": 4549632}
{"current_steps": 4745, "total_steps": 58920, "loss": 0.0661, "lr": 1.6103190767141888e-06, "epoch": 0.40266463000678887, "percentage": 8.05, "elapsed_time": "0:07:16", "remaining_time": "1:23:05", "throughput": 10430.25, "total_tokens": 4554560}
{"current_steps": 4750, "total_steps": 58920, "loss": 0.0816, "lr": 1.6120162932790223e-06, "epoch": 0.4030889341479973, "percentage": 8.06, "elapsed_time": "0:07:17", "remaining_time": "1:23:04", "throughput": 10431.8, "total_tokens": 4559168}
{"current_steps": 4755, "total_steps": 58920, "loss": 0.0389, "lr": 1.6137135098438558e-06, "epoch": 0.4035132382892057, "percentage": 8.07, "elapsed_time": "0:07:17", "remaining_time": "1:23:02", "throughput": 10433.56, "total_tokens": 4563968}
{"current_steps": 4760, "total_steps": 58920, "loss": 0.0374, "lr": 1.6154107264086896e-06, "epoch": 0.40393754243041413, "percentage": 8.08, "elapsed_time": "0:07:17", "remaining_time": "1:23:01", "throughput": 10436.48, "total_tokens": 4569408}
{"current_steps": 4765, "total_steps": 58920, "loss": 0.065, "lr": 1.6171079429735233e-06, "epoch": 0.40436184657162255, "percentage": 8.09, "elapsed_time": "0:07:18", "remaining_time": "1:23:00", "throughput": 10437.7, "total_tokens": 4573824}
{"current_steps": 4770, "total_steps": 58920, "loss": 0.1362, "lr": 1.618805159538357e-06, "epoch": 0.40478615071283097, "percentage": 8.1, "elapsed_time": "0:07:18", "remaining_time": "1:22:58", "throughput": 10439.15, "total_tokens": 4578368}
{"current_steps": 4775, "total_steps": 58920, "loss": 0.1177, "lr": 1.6205023761031906e-06, "epoch": 0.4052104548540394, "percentage": 8.1, "elapsed_time": "0:07:18", "remaining_time": "1:22:57", "throughput": 10440.81, "total_tokens": 4583040}
{"current_steps": 4780, "total_steps": 58920, "loss": 0.1581, "lr": 1.6221995926680243e-06, "epoch": 0.4056347589952478, "percentage": 8.11, "elapsed_time": "0:07:19", "remaining_time": "1:22:56", "throughput": 10442.91, "total_tokens": 4587968}
{"current_steps": 4785, "total_steps": 58920, "loss": 0.1585, "lr": 1.623896809232858e-06, "epoch": 0.40605906313645623, "percentage": 8.12, "elapsed_time": "0:07:19", "remaining_time": "1:22:54", "throughput": 10445.57, "total_tokens": 4593216}
{"current_steps": 4790, "total_steps": 58920, "loss": 0.0925, "lr": 1.6255940257976918e-06, "epoch": 0.40648336727766465, "percentage": 8.13, "elapsed_time": "0:07:20", "remaining_time": "1:22:53", "throughput": 10447.1, "total_tokens": 4597824}
{"current_steps": 4795, "total_steps": 58920, "loss": 0.0848, "lr": 1.6272912423625253e-06, "epoch": 0.4069076714188731, "percentage": 8.14, "elapsed_time": "0:07:20", "remaining_time": "1:22:52", "throughput": 10449.36, "total_tokens": 4602880}
{"current_steps": 4800, "total_steps": 58920, "loss": 0.0308, "lr": 1.628988458927359e-06, "epoch": 0.4073319755600815, "percentage": 8.15, "elapsed_time": "0:07:20", "remaining_time": "1:22:50", "throughput": 10451.4, "total_tokens": 4607744}
{"current_steps": 4805, "total_steps": 58920, "loss": 0.1097, "lr": 1.6306856754921928e-06, "epoch": 0.40775627970128986, "percentage": 8.16, "elapsed_time": "0:07:21", "remaining_time": "1:22:49", "throughput": 10452.72, "total_tokens": 4612224}
{"current_steps": 4810, "total_steps": 58920, "loss": 0.0673, "lr": 1.6323828920570263e-06, "epoch": 0.4081805838424983, "percentage": 8.16, "elapsed_time": "0:07:21", "remaining_time": "1:22:48", "throughput": 10453.98, "total_tokens": 4616704}
{"current_steps": 4815, "total_steps": 58920, "loss": 0.0896, "lr": 1.63408010862186e-06, "epoch": 0.4086048879837067, "percentage": 8.17, "elapsed_time": "0:07:22", "remaining_time": "1:22:46", "throughput": 10455.9, "total_tokens": 4621568}
{"current_steps": 4820, "total_steps": 58920, "loss": 0.0326, "lr": 1.6357773251866938e-06, "epoch": 0.4090291921249151, "percentage": 8.18, "elapsed_time": "0:07:22", "remaining_time": "1:22:45", "throughput": 10457.41, "total_tokens": 4626176}
{"current_steps": 4825, "total_steps": 58920, "loss": 0.07, "lr": 1.6374745417515275e-06, "epoch": 0.40945349626612354, "percentage": 8.19, "elapsed_time": "0:07:22", "remaining_time": "1:22:43", "throughput": 10458.17, "total_tokens": 4630400}
{"current_steps": 4830, "total_steps": 58920, "loss": 0.0522, "lr": 1.639171758316361e-06, "epoch": 0.40987780040733196, "percentage": 8.2, "elapsed_time": "0:07:23", "remaining_time": "1:22:42", "throughput": 10459.08, "total_tokens": 4634688}
{"current_steps": 4835, "total_steps": 58920, "loss": 0.0511, "lr": 1.6408689748811948e-06, "epoch": 0.4103021045485404, "percentage": 8.21, "elapsed_time": "0:07:23", "remaining_time": "1:22:41", "throughput": 10460.25, "total_tokens": 4639104}
{"current_steps": 4840, "total_steps": 58920, "loss": 0.0676, "lr": 1.6425661914460285e-06, "epoch": 0.4107264086897488, "percentage": 8.21, "elapsed_time": "0:07:23", "remaining_time": "1:22:39", "throughput": 10460.99, "total_tokens": 4643328}
{"current_steps": 4845, "total_steps": 58920, "loss": 0.0958, "lr": 1.6442634080108623e-06, "epoch": 0.4111507128309572, "percentage": 8.22, "elapsed_time": "0:07:24", "remaining_time": "1:22:38", "throughput": 10463.1, "total_tokens": 4648320}
{"current_steps": 4850, "total_steps": 58920, "loss": 0.0967, "lr": 1.6459606245756958e-06, "epoch": 0.41157501697216564, "percentage": 8.23, "elapsed_time": "0:07:24", "remaining_time": "1:22:37", "throughput": 10464.92, "total_tokens": 4653120}
{"current_steps": 4855, "total_steps": 58920, "loss": 0.0761, "lr": 1.6476578411405295e-06, "epoch": 0.41199932111337406, "percentage": 8.24, "elapsed_time": "0:07:25", "remaining_time": "1:22:35", "throughput": 10466.86, "total_tokens": 4658048}
{"current_steps": 4860, "total_steps": 58920, "loss": 0.0275, "lr": 1.6493550577053633e-06, "epoch": 0.4124236252545825, "percentage": 8.25, "elapsed_time": "0:07:25", "remaining_time": "1:22:34", "throughput": 10468.79, "total_tokens": 4662976}
{"current_steps": 4865, "total_steps": 58920, "loss": 0.0323, "lr": 1.651052274270197e-06, "epoch": 0.4128479293957909, "percentage": 8.26, "elapsed_time": "0:07:25", "remaining_time": "1:22:33", "throughput": 10470.64, "total_tokens": 4667840}
{"current_steps": 4870, "total_steps": 58920, "loss": 0.1064, "lr": 1.6527494908350305e-06, "epoch": 0.4132722335369993, "percentage": 8.27, "elapsed_time": "0:07:26", "remaining_time": "1:22:32", "throughput": 10473.73, "total_tokens": 4673408}
{"current_steps": 4875, "total_steps": 58920, "loss": 0.1685, "lr": 1.6544467073998643e-06, "epoch": 0.41369653767820774, "percentage": 8.27, "elapsed_time": "0:07:26", "remaining_time": "1:22:31", "throughput": 10477.74, "total_tokens": 4679552}
{"current_steps": 4880, "total_steps": 58920, "loss": 0.1117, "lr": 1.656143923964698e-06, "epoch": 0.41412084181941616, "percentage": 8.28, "elapsed_time": "0:07:26", "remaining_time": "1:22:29", "throughput": 10479.54, "total_tokens": 4684352}
{"current_steps": 4885, "total_steps": 58920, "loss": 0.1051, "lr": 1.6578411405295313e-06, "epoch": 0.4145451459606246, "percentage": 8.29, "elapsed_time": "0:07:27", "remaining_time": "1:22:28", "throughput": 10480.52, "total_tokens": 4688704}
{"current_steps": 4890, "total_steps": 58920, "loss": 0.0345, "lr": 1.659538357094365e-06, "epoch": 0.414969450101833, "percentage": 8.3, "elapsed_time": "0:07:27", "remaining_time": "1:22:27", "throughput": 10482.12, "total_tokens": 4693440}
{"current_steps": 4895, "total_steps": 58920, "loss": 0.1205, "lr": 1.6612355736591988e-06, "epoch": 0.4153937542430414, "percentage": 8.31, "elapsed_time": "0:07:28", "remaining_time": "1:22:26", "throughput": 10484.29, "total_tokens": 4698496}
{"current_steps": 4900, "total_steps": 58920, "loss": 0.1078, "lr": 1.6629327902240325e-06, "epoch": 0.41581805838424984, "percentage": 8.32, "elapsed_time": "0:07:28", "remaining_time": "1:22:24", "throughput": 10486.61, "total_tokens": 4703616}
{"current_steps": 4905, "total_steps": 58920, "loss": 0.0841, "lr": 1.664630006788866e-06, "epoch": 0.41624236252545826, "percentage": 8.32, "elapsed_time": "0:07:28", "remaining_time": "1:22:23", "throughput": 10486.92, "total_tokens": 4707584}
{"current_steps": 4910, "total_steps": 58920, "loss": 0.1383, "lr": 1.6663272233536998e-06, "epoch": 0.4166666666666667, "percentage": 8.33, "elapsed_time": "0:07:29", "remaining_time": "1:22:22", "throughput": 10487.9, "total_tokens": 4711936}
{"current_steps": 4915, "total_steps": 58920, "loss": 0.1147, "lr": 1.6680244399185335e-06, "epoch": 0.4170909708078751, "percentage": 8.34, "elapsed_time": "0:07:29", "remaining_time": "1:22:20", "throughput": 10490.05, "total_tokens": 4716992}
{"current_steps": 4920, "total_steps": 58920, "loss": 0.0597, "lr": 1.6697216564833673e-06, "epoch": 0.4175152749490835, "percentage": 8.35, "elapsed_time": "0:07:30", "remaining_time": "1:22:19", "throughput": 10491.89, "total_tokens": 4721792}
{"current_steps": 4925, "total_steps": 58920, "loss": 0.0443, "lr": 1.6714188730482008e-06, "epoch": 0.41793957909029195, "percentage": 8.36, "elapsed_time": "0:07:30", "remaining_time": "1:22:18", "throughput": 10493.02, "total_tokens": 4726208}
{"current_steps": 4930, "total_steps": 58920, "loss": 0.084, "lr": 1.6731160896130345e-06, "epoch": 0.41836388323150037, "percentage": 8.37, "elapsed_time": "0:07:30", "remaining_time": "1:22:16", "throughput": 10494.56, "total_tokens": 4730880}
{"current_steps": 4935, "total_steps": 58920, "loss": 0.0853, "lr": 1.6748133061778683e-06, "epoch": 0.41878818737270873, "percentage": 8.38, "elapsed_time": "0:07:31", "remaining_time": "1:22:15", "throughput": 10496.99, "total_tokens": 4736128}
{"current_steps": 4940, "total_steps": 58920, "loss": 0.0603, "lr": 1.6765105227427018e-06, "epoch": 0.41921249151391715, "percentage": 8.38, "elapsed_time": "0:07:31", "remaining_time": "1:22:14", "throughput": 10498.17, "total_tokens": 4740608}
{"current_steps": 4945, "total_steps": 58920, "loss": 0.0857, "lr": 1.6782077393075355e-06, "epoch": 0.41963679565512557, "percentage": 8.39, "elapsed_time": "0:07:31", "remaining_time": "1:22:13", "throughput": 10499.85, "total_tokens": 4745408}
{"current_steps": 4950, "total_steps": 58920, "loss": 0.0095, "lr": 1.6799049558723693e-06, "epoch": 0.420061099796334, "percentage": 8.4, "elapsed_time": "0:07:32", "remaining_time": "1:22:11", "throughput": 10501.89, "total_tokens": 4750400}
{"current_steps": 4955, "total_steps": 58920, "loss": 0.0514, "lr": 1.681602172437203e-06, "epoch": 0.4204854039375424, "percentage": 8.41, "elapsed_time": "0:07:32", "remaining_time": "1:22:10", "throughput": 10503.33, "total_tokens": 4755008}
{"current_steps": 4960, "total_steps": 58920, "loss": 0.1523, "lr": 1.6832993890020365e-06, "epoch": 0.42090970807875083, "percentage": 8.42, "elapsed_time": "0:07:33", "remaining_time": "1:22:09", "throughput": 10504.38, "total_tokens": 4759424}
{"current_steps": 4965, "total_steps": 58920, "loss": 0.0425, "lr": 1.6849966055668703e-06, "epoch": 0.42133401221995925, "percentage": 8.43, "elapsed_time": "0:07:33", "remaining_time": "1:22:07", "throughput": 10505.66, "total_tokens": 4763968}
{"current_steps": 4970, "total_steps": 58920, "loss": 0.1132, "lr": 1.686693822131704e-06, "epoch": 0.4217583163611677, "percentage": 8.44, "elapsed_time": "0:07:33", "remaining_time": "1:22:06", "throughput": 10507.73, "total_tokens": 4768960}
{"current_steps": 4975, "total_steps": 58920, "loss": 0.0845, "lr": 1.6883910386965377e-06, "epoch": 0.4221826205023761, "percentage": 8.44, "elapsed_time": "0:07:34", "remaining_time": "1:22:05", "throughput": 10510.75, "total_tokens": 4774592}
{"current_steps": 4980, "total_steps": 58920, "loss": 0.0976, "lr": 1.6900882552613713e-06, "epoch": 0.4226069246435845, "percentage": 8.45, "elapsed_time": "0:07:34", "remaining_time": "1:22:04", "throughput": 10511.76, "total_tokens": 4778944}
{"current_steps": 4985, "total_steps": 58920, "loss": 0.1049, "lr": 1.691785471826205e-06, "epoch": 0.42303122878479293, "percentage": 8.46, "elapsed_time": "0:07:35", "remaining_time": "1:22:02", "throughput": 10513.08, "total_tokens": 4783488}
{"current_steps": 4990, "total_steps": 58920, "loss": 0.0531, "lr": 1.6934826883910387e-06, "epoch": 0.42345553292600135, "percentage": 8.47, "elapsed_time": "0:07:35", "remaining_time": "1:22:01", "throughput": 10514.72, "total_tokens": 4788288}
{"current_steps": 4995, "total_steps": 58920, "loss": 0.0304, "lr": 1.6951799049558723e-06, "epoch": 0.4238798370672098, "percentage": 8.48, "elapsed_time": "0:07:35", "remaining_time": "1:22:00", "throughput": 10516.06, "total_tokens": 4792896}
{"current_steps": 5000, "total_steps": 58920, "loss": 0.1212, "lr": 1.696877121520706e-06, "epoch": 0.4243041412084182, "percentage": 8.49, "elapsed_time": "0:07:36", "remaining_time": "1:21:59", "throughput": 10516.62, "total_tokens": 4797056}
{"current_steps": 5005, "total_steps": 58920, "loss": 0.0453, "lr": 1.6985743380855397e-06, "epoch": 0.4247284453496266, "percentage": 8.49, "elapsed_time": "0:07:36", "remaining_time": "1:21:57", "throughput": 10519.06, "total_tokens": 4802304}
{"current_steps": 5010, "total_steps": 58920, "loss": 0.0502, "lr": 1.7002715546503735e-06, "epoch": 0.42515274949083504, "percentage": 8.5, "elapsed_time": "0:07:36", "remaining_time": "1:21:56", "throughput": 10521.27, "total_tokens": 4807424}
{"current_steps": 5015, "total_steps": 58920, "loss": 0.0885, "lr": 1.7019687712152068e-06, "epoch": 0.42557705363204346, "percentage": 8.51, "elapsed_time": "0:07:37", "remaining_time": "1:21:55", "throughput": 10522.89, "total_tokens": 4812224}
{"current_steps": 5020, "total_steps": 58920, "loss": 0.177, "lr": 1.7036659877800405e-06, "epoch": 0.4260013577732519, "percentage": 8.52, "elapsed_time": "0:07:37", "remaining_time": "1:21:54", "throughput": 10524.96, "total_tokens": 4817216}
{"current_steps": 5025, "total_steps": 58920, "loss": 0.0444, "lr": 1.7053632043448743e-06, "epoch": 0.4264256619144603, "percentage": 8.53, "elapsed_time": "0:07:38", "remaining_time": "1:21:53", "throughput": 10527.14, "total_tokens": 4822336}
{"current_steps": 5030, "total_steps": 58920, "loss": 0.0618, "lr": 1.707060420909708e-06, "epoch": 0.4268499660556687, "percentage": 8.54, "elapsed_time": "0:07:38", "remaining_time": "1:21:51", "throughput": 10529.17, "total_tokens": 4827328}
{"current_steps": 5035, "total_steps": 58920, "loss": 0.0617, "lr": 1.7087576374745415e-06, "epoch": 0.42727427019687714, "percentage": 8.55, "elapsed_time": "0:07:38", "remaining_time": "1:21:50", "throughput": 10530.32, "total_tokens": 4831808}
{"current_steps": 5040, "total_steps": 58920, "loss": 0.0263, "lr": 1.7104548540393753e-06, "epoch": 0.42769857433808556, "percentage": 8.55, "elapsed_time": "0:07:39", "remaining_time": "1:21:49", "throughput": 10531.15, "total_tokens": 4836096}
{"current_steps": 5045, "total_steps": 58920, "loss": 0.0479, "lr": 1.712152070604209e-06, "epoch": 0.428122878479294, "percentage": 8.56, "elapsed_time": "0:07:39", "remaining_time": "1:21:47", "throughput": 10532.07, "total_tokens": 4840448}
{"current_steps": 5050, "total_steps": 58920, "loss": 0.0344, "lr": 1.7138492871690425e-06, "epoch": 0.4285471826205024, "percentage": 8.57, "elapsed_time": "0:07:39", "remaining_time": "1:21:46", "throughput": 10533.65, "total_tokens": 4845184}
{"current_steps": 5055, "total_steps": 58920, "loss": 0.1507, "lr": 1.7155465037338763e-06, "epoch": 0.4289714867617108, "percentage": 8.58, "elapsed_time": "0:07:40", "remaining_time": "1:21:45", "throughput": 10535.25, "total_tokens": 4849920}
{"current_steps": 5060, "total_steps": 58920, "loss": 0.0987, "lr": 1.71724372029871e-06, "epoch": 0.42939579090291924, "percentage": 8.59, "elapsed_time": "0:07:40", "remaining_time": "1:21:44", "throughput": 10536.35, "total_tokens": 4854400}
{"current_steps": 5065, "total_steps": 58920, "loss": 0.0324, "lr": 1.7189409368635438e-06, "epoch": 0.4298200950441276, "percentage": 8.6, "elapsed_time": "0:07:41", "remaining_time": "1:21:42", "throughput": 10538.4, "total_tokens": 4859392}
{"current_steps": 5070, "total_steps": 58920, "loss": 0.1048, "lr": 1.7206381534283773e-06, "epoch": 0.430244399185336, "percentage": 8.6, "elapsed_time": "0:07:41", "remaining_time": "1:21:41", "throughput": 10540.66, "total_tokens": 4864512}
{"current_steps": 5075, "total_steps": 58920, "loss": 0.0964, "lr": 1.722335369993211e-06, "epoch": 0.43066870332654444, "percentage": 8.61, "elapsed_time": "0:07:41", "remaining_time": "1:21:40", "throughput": 10543.3, "total_tokens": 4869888}
{"current_steps": 5080, "total_steps": 58920, "loss": 0.0702, "lr": 1.7240325865580448e-06, "epoch": 0.43109300746775286, "percentage": 8.62, "elapsed_time": "0:07:42", "remaining_time": "1:21:39", "throughput": 10544.3, "total_tokens": 4874304}
{"current_steps": 5085, "total_steps": 58920, "loss": 0.1212, "lr": 1.7257298031228785e-06, "epoch": 0.4315173116089613, "percentage": 8.63, "elapsed_time": "0:07:42", "remaining_time": "1:21:38", "throughput": 10546.38, "total_tokens": 4879360}
{"current_steps": 5090, "total_steps": 58920, "loss": 0.0642, "lr": 1.727427019687712e-06, "epoch": 0.4319416157501697, "percentage": 8.64, "elapsed_time": "0:07:43", "remaining_time": "1:21:36", "throughput": 10546.96, "total_tokens": 4883520}
{"current_steps": 5095, "total_steps": 58920, "loss": 0.0251, "lr": 1.7291242362525458e-06, "epoch": 0.4323659198913781, "percentage": 8.65, "elapsed_time": "0:07:43", "remaining_time": "1:21:35", "throughput": 10548.62, "total_tokens": 4888320}
{"current_steps": 5100, "total_steps": 58920, "loss": 0.0136, "lr": 1.7308214528173795e-06, "epoch": 0.43279022403258655, "percentage": 8.66, "elapsed_time": "0:07:43", "remaining_time": "1:21:34", "throughput": 10551.35, "total_tokens": 4893824}
{"current_steps": 5105, "total_steps": 58920, "loss": 0.0936, "lr": 1.7325186693822132e-06, "epoch": 0.43321452817379497, "percentage": 8.66, "elapsed_time": "0:07:44", "remaining_time": "1:21:33", "throughput": 10552.72, "total_tokens": 4898432}
{"current_steps": 5110, "total_steps": 58920, "loss": 0.1059, "lr": 1.7342158859470468e-06, "epoch": 0.4336388323150034, "percentage": 8.67, "elapsed_time": "0:07:44", "remaining_time": "1:21:32", "throughput": 10554.08, "total_tokens": 4903040}
{"current_steps": 5115, "total_steps": 58920, "loss": 0.0796, "lr": 1.7359131025118805e-06, "epoch": 0.4340631364562118, "percentage": 8.68, "elapsed_time": "0:07:44", "remaining_time": "1:21:30", "throughput": 10556.13, "total_tokens": 4908096}
{"current_steps": 5120, "total_steps": 58920, "loss": 0.0701, "lr": 1.7376103190767142e-06, "epoch": 0.4344874405974202, "percentage": 8.69, "elapsed_time": "0:07:45", "remaining_time": "1:21:29", "throughput": 10557.36, "total_tokens": 4912640}
{"current_steps": 5125, "total_steps": 58920, "loss": 0.0451, "lr": 1.7393075356415478e-06, "epoch": 0.43491174473862865, "percentage": 8.7, "elapsed_time": "0:07:45", "remaining_time": "1:21:28", "throughput": 10559.13, "total_tokens": 4917504}
{"current_steps": 5130, "total_steps": 58920, "loss": 0.0171, "lr": 1.7410047522063815e-06, "epoch": 0.43533604887983707, "percentage": 8.71, "elapsed_time": "0:07:46", "remaining_time": "1:21:27", "throughput": 10561.38, "total_tokens": 4922688}
{"current_steps": 5135, "total_steps": 58920, "loss": 0.0563, "lr": 1.7427019687712152e-06, "epoch": 0.4357603530210455, "percentage": 8.72, "elapsed_time": "0:07:46", "remaining_time": "1:21:25", "throughput": 10562.19, "total_tokens": 4926976}
{"current_steps": 5140, "total_steps": 58920, "loss": 0.0619, "lr": 1.744399185336049e-06, "epoch": 0.4361846571622539, "percentage": 8.72, "elapsed_time": "0:07:46", "remaining_time": "1:21:24", "throughput": 10563.28, "total_tokens": 4931456}
{"current_steps": 5145, "total_steps": 58920, "loss": 0.0989, "lr": 1.7460964019008823e-06, "epoch": 0.43660896130346233, "percentage": 8.73, "elapsed_time": "0:07:47", "remaining_time": "1:21:23", "throughput": 10564.54, "total_tokens": 4936000}
{"current_steps": 5150, "total_steps": 58920, "loss": 0.0856, "lr": 1.747793618465716e-06, "epoch": 0.43703326544467075, "percentage": 8.74, "elapsed_time": "0:07:47", "remaining_time": "1:21:22", "throughput": 10565.3, "total_tokens": 4940288}
{"current_steps": 5155, "total_steps": 58920, "loss": 0.0577, "lr": 1.7494908350305498e-06, "epoch": 0.43745756958587917, "percentage": 8.75, "elapsed_time": "0:07:47", "remaining_time": "1:21:20", "throughput": 10566.1, "total_tokens": 4944576}
{"current_steps": 5160, "total_steps": 58920, "loss": 0.0673, "lr": 1.7511880515953835e-06, "epoch": 0.4378818737270876, "percentage": 8.76, "elapsed_time": "0:07:48", "remaining_time": "1:21:19", "throughput": 10567.07, "total_tokens": 4948992}
{"current_steps": 5165, "total_steps": 58920, "loss": 0.0659, "lr": 1.752885268160217e-06, "epoch": 0.438306177868296, "percentage": 8.77, "elapsed_time": "0:07:48", "remaining_time": "1:21:18", "throughput": 10568.55, "total_tokens": 4953728}
{"current_steps": 5170, "total_steps": 58920, "loss": 0.0617, "lr": 1.7545824847250508e-06, "epoch": 0.43873048200950443, "percentage": 8.77, "elapsed_time": "0:07:49", "remaining_time": "1:21:17", "throughput": 10570.47, "total_tokens": 4958720}
{"current_steps": 5175, "total_steps": 58920, "loss": 0.0978, "lr": 1.7562797012898845e-06, "epoch": 0.43915478615071285, "percentage": 8.78, "elapsed_time": "0:07:49", "remaining_time": "1:21:16", "throughput": 10572.55, "total_tokens": 4963840}
{"current_steps": 5180, "total_steps": 58920, "loss": 0.0411, "lr": 1.757976917854718e-06, "epoch": 0.43957909029192127, "percentage": 8.79, "elapsed_time": "0:07:49", "remaining_time": "1:21:14", "throughput": 10573.99, "total_tokens": 4968512}
{"current_steps": 5185, "total_steps": 58920, "loss": 0.1255, "lr": 1.7596741344195518e-06, "epoch": 0.4400033944331297, "percentage": 8.8, "elapsed_time": "0:07:50", "remaining_time": "1:21:13", "throughput": 10574.96, "total_tokens": 4972928}
{"current_steps": 5190, "total_steps": 58920, "loss": 0.1183, "lr": 1.7613713509843855e-06, "epoch": 0.4404276985743381, "percentage": 8.81, "elapsed_time": "0:07:50", "remaining_time": "1:21:12", "throughput": 10576.45, "total_tokens": 4977664}
{"current_steps": 5195, "total_steps": 58920, "loss": 0.1145, "lr": 1.7630685675492192e-06, "epoch": 0.4408520027155465, "percentage": 8.82, "elapsed_time": "0:07:51", "remaining_time": "1:21:11", "throughput": 10578.75, "total_tokens": 4982912}
{"current_steps": 5200, "total_steps": 58920, "loss": 0.0717, "lr": 1.7647657841140528e-06, "epoch": 0.4412763068567549, "percentage": 8.83, "elapsed_time": "0:07:51", "remaining_time": "1:21:10", "throughput": 10581.5, "total_tokens": 4988416}
{"current_steps": 5205, "total_steps": 58920, "loss": 0.0945, "lr": 1.7664630006788865e-06, "epoch": 0.4417006109979633, "percentage": 8.83, "elapsed_time": "0:07:51", "remaining_time": "1:21:09", "throughput": 10583.55, "total_tokens": 4993472}
{"current_steps": 5210, "total_steps": 58920, "loss": 0.0418, "lr": 1.7681602172437202e-06, "epoch": 0.44212491513917174, "percentage": 8.84, "elapsed_time": "0:07:52", "remaining_time": "1:21:07", "throughput": 10585.09, "total_tokens": 4998208}
{"current_steps": 5215, "total_steps": 58920, "loss": 0.0573, "lr": 1.769857433808554e-06, "epoch": 0.44254921928038016, "percentage": 8.85, "elapsed_time": "0:07:52", "remaining_time": "1:21:06", "throughput": 10586.7, "total_tokens": 5003008}
{"current_steps": 5220, "total_steps": 58920, "loss": 0.0519, "lr": 1.7715546503733875e-06, "epoch": 0.4429735234215886, "percentage": 8.86, "elapsed_time": "0:07:52", "remaining_time": "1:21:05", "throughput": 10589.67, "total_tokens": 5008704}
{"current_steps": 5225, "total_steps": 58920, "loss": 0.1377, "lr": 1.7732518669382213e-06, "epoch": 0.443397827562797, "percentage": 8.87, "elapsed_time": "0:07:53", "remaining_time": "1:21:04", "throughput": 10590.62, "total_tokens": 5013120}
{"current_steps": 5230, "total_steps": 58920, "loss": 0.0351, "lr": 1.774949083503055e-06, "epoch": 0.4438221317040054, "percentage": 8.88, "elapsed_time": "0:07:53", "remaining_time": "1:21:03", "throughput": 10591.82, "total_tokens": 5017664}
{"current_steps": 5235, "total_steps": 58920, "loss": 0.0803, "lr": 1.7766463000678887e-06, "epoch": 0.44424643584521384, "percentage": 8.88, "elapsed_time": "0:07:54", "remaining_time": "1:21:02", "throughput": 10593.56, "total_tokens": 5022528}
{"current_steps": 5240, "total_steps": 58920, "loss": 0.0906, "lr": 1.7783435166327223e-06, "epoch": 0.44467073998642226, "percentage": 8.89, "elapsed_time": "0:07:54", "remaining_time": "1:21:00", "throughput": 10594.72, "total_tokens": 5027072}
{"current_steps": 5245, "total_steps": 58920, "loss": 0.0313, "lr": 1.780040733197556e-06, "epoch": 0.4450950441276307, "percentage": 8.9, "elapsed_time": "0:07:54", "remaining_time": "1:20:59", "throughput": 10595.53, "total_tokens": 5031424}
{"current_steps": 5250, "total_steps": 58920, "loss": 0.0475, "lr": 1.7817379497623897e-06, "epoch": 0.4455193482688391, "percentage": 8.91, "elapsed_time": "0:07:55", "remaining_time": "1:20:58", "throughput": 10597.44, "total_tokens": 5036480}
{"current_steps": 5255, "total_steps": 58920, "loss": 0.0817, "lr": 1.7834351663272233e-06, "epoch": 0.4459436524100475, "percentage": 8.92, "elapsed_time": "0:07:55", "remaining_time": "1:20:57", "throughput": 10599.77, "total_tokens": 5041792}
{"current_steps": 5260, "total_steps": 58920, "loss": 0.0154, "lr": 1.785132382892057e-06, "epoch": 0.44636795655125594, "percentage": 8.93, "elapsed_time": "0:07:56", "remaining_time": "1:20:56", "throughput": 10601.31, "total_tokens": 5046592}
{"current_steps": 5265, "total_steps": 58920, "loss": 0.1067, "lr": 1.7868295994568907e-06, "epoch": 0.44679226069246436, "percentage": 8.94, "elapsed_time": "0:07:56", "remaining_time": "1:20:55", "throughput": 10603.02, "total_tokens": 5051456}
{"current_steps": 5270, "total_steps": 58920, "loss": 0.0988, "lr": 1.7885268160217245e-06, "epoch": 0.4472165648336728, "percentage": 8.94, "elapsed_time": "0:07:56", "remaining_time": "1:20:53", "throughput": 10604.67, "total_tokens": 5056320}
{"current_steps": 5275, "total_steps": 58920, "loss": 0.0189, "lr": 1.7902240325865578e-06, "epoch": 0.4476408689748812, "percentage": 8.95, "elapsed_time": "0:07:57", "remaining_time": "1:20:52", "throughput": 10606.37, "total_tokens": 5061248}
{"current_steps": 5280, "total_steps": 58920, "loss": 0.102, "lr": 1.7919212491513915e-06, "epoch": 0.4480651731160896, "percentage": 8.96, "elapsed_time": "0:07:57", "remaining_time": "1:20:51", "throughput": 10607.35, "total_tokens": 5065664}
{"current_steps": 5285, "total_steps": 58920, "loss": 0.1272, "lr": 1.7936184657162253e-06, "epoch": 0.44848947725729804, "percentage": 8.97, "elapsed_time": "0:07:57", "remaining_time": "1:20:50", "throughput": 10610.69, "total_tokens": 5071552}
{"current_steps": 5290, "total_steps": 58920, "loss": 0.0672, "lr": 1.795315682281059e-06, "epoch": 0.44891378139850646, "percentage": 8.98, "elapsed_time": "0:07:58", "remaining_time": "1:20:49", "throughput": 10611.78, "total_tokens": 5076032}
{"current_steps": 5295, "total_steps": 58920, "loss": 0.0582, "lr": 1.7970128988458925e-06, "epoch": 0.4493380855397149, "percentage": 8.99, "elapsed_time": "0:07:58", "remaining_time": "1:20:48", "throughput": 10612.62, "total_tokens": 5080384}
{"current_steps": 5300, "total_steps": 58920, "loss": 0.0612, "lr": 1.7987101154107263e-06, "epoch": 0.4497623896809233, "percentage": 9.0, "elapsed_time": "0:07:59", "remaining_time": "1:20:47", "throughput": 10614.39, "total_tokens": 5085376}
{"current_steps": 5305, "total_steps": 58920, "loss": 0.0265, "lr": 1.80040733197556e-06, "epoch": 0.4501866938221317, "percentage": 9.0, "elapsed_time": "0:07:59", "remaining_time": "1:20:45", "throughput": 10615.82, "total_tokens": 5090112}
{"current_steps": 5310, "total_steps": 58920, "loss": 0.0451, "lr": 1.8021045485403935e-06, "epoch": 0.45061099796334014, "percentage": 9.01, "elapsed_time": "0:07:59", "remaining_time": "1:20:44", "throughput": 10618.11, "total_tokens": 5095424}
{"current_steps": 5315, "total_steps": 58920, "loss": 0.0743, "lr": 1.8038017651052273e-06, "epoch": 0.45103530210454856, "percentage": 9.02, "elapsed_time": "0:08:00", "remaining_time": "1:20:43", "throughput": 10620.67, "total_tokens": 5100864}
{"current_steps": 5320, "total_steps": 58920, "loss": 0.1048, "lr": 1.805498981670061e-06, "epoch": 0.451459606245757, "percentage": 9.03, "elapsed_time": "0:08:00", "remaining_time": "1:20:42", "throughput": 10621.26, "total_tokens": 5105088}
{"current_steps": 5325, "total_steps": 58920, "loss": 0.0582, "lr": 1.8071961982348947e-06, "epoch": 0.4518839103869654, "percentage": 9.04, "elapsed_time": "0:08:01", "remaining_time": "1:20:41", "throughput": 10622.62, "total_tokens": 5109760}
{"current_steps": 5330, "total_steps": 58920, "loss": 0.1443, "lr": 1.8088934147997283e-06, "epoch": 0.45230821452817377, "percentage": 9.05, "elapsed_time": "0:08:01", "remaining_time": "1:20:40", "throughput": 10623.55, "total_tokens": 5114176}
{"current_steps": 5335, "total_steps": 58920, "loss": 0.0224, "lr": 1.810590631364562e-06, "epoch": 0.4527325186693822, "percentage": 9.05, "elapsed_time": "0:08:01", "remaining_time": "1:20:38", "throughput": 10624.41, "total_tokens": 5118592}
{"current_steps": 5340, "total_steps": 58920, "loss": 0.1212, "lr": 1.8122878479293957e-06, "epoch": 0.4531568228105906, "percentage": 9.06, "elapsed_time": "0:08:02", "remaining_time": "1:20:37", "throughput": 10626.2, "total_tokens": 5123584}
{"current_steps": 5345, "total_steps": 58920, "loss": 0.0299, "lr": 1.8139850644942295e-06, "epoch": 0.45358112695179903, "percentage": 9.07, "elapsed_time": "0:08:02", "remaining_time": "1:20:36", "throughput": 10627.46, "total_tokens": 5128192}
{"current_steps": 5350, "total_steps": 58920, "loss": 0.118, "lr": 1.815682281059063e-06, "epoch": 0.45400543109300745, "percentage": 9.08, "elapsed_time": "0:08:02", "remaining_time": "1:20:35", "throughput": 10628.75, "total_tokens": 5132864}
{"current_steps": 5355, "total_steps": 58920, "loss": 0.0197, "lr": 1.8173794976238967e-06, "epoch": 0.45442973523421587, "percentage": 9.09, "elapsed_time": "0:08:03", "remaining_time": "1:20:34", "throughput": 10629.61, "total_tokens": 5137216}
{"current_steps": 5360, "total_steps": 58920, "loss": 0.05, "lr": 1.8190767141887305e-06, "epoch": 0.4548540393754243, "percentage": 9.1, "elapsed_time": "0:08:03", "remaining_time": "1:20:33", "throughput": 10631.85, "total_tokens": 5142528}
{"current_steps": 5365, "total_steps": 58920, "loss": 0.0134, "lr": 1.8207739307535642e-06, "epoch": 0.4552783435166327, "percentage": 9.11, "elapsed_time": "0:08:04", "remaining_time": "1:20:32", "throughput": 10634.31, "total_tokens": 5147968}
{"current_steps": 5370, "total_steps": 58920, "loss": 0.0254, "lr": 1.8224711473183977e-06, "epoch": 0.45570264765784113, "percentage": 9.11, "elapsed_time": "0:08:04", "remaining_time": "1:20:31", "throughput": 10635.2, "total_tokens": 5152384}
{"current_steps": 5375, "total_steps": 58920, "loss": 0.1566, "lr": 1.8241683638832315e-06, "epoch": 0.45612695179904955, "percentage": 9.12, "elapsed_time": "0:08:04", "remaining_time": "1:20:29", "throughput": 10636.38, "total_tokens": 5156992}
{"current_steps": 5380, "total_steps": 58920, "loss": 0.1002, "lr": 1.8258655804480652e-06, "epoch": 0.45655125594025797, "percentage": 9.13, "elapsed_time": "0:08:05", "remaining_time": "1:20:28", "throughput": 10638.24, "total_tokens": 5161984}
{"current_steps": 5385, "total_steps": 58920, "loss": 0.0534, "lr": 1.8275627970128987e-06, "epoch": 0.4569755600814664, "percentage": 9.14, "elapsed_time": "0:08:05", "remaining_time": "1:20:27", "throughput": 10640.13, "total_tokens": 5167040}
{"current_steps": 5390, "total_steps": 58920, "loss": 0.0653, "lr": 1.8292600135777325e-06, "epoch": 0.4573998642226748, "percentage": 9.15, "elapsed_time": "0:08:06", "remaining_time": "1:20:26", "throughput": 10641.51, "total_tokens": 5171776}
{"current_steps": 5395, "total_steps": 58920, "loss": 0.1275, "lr": 1.8309572301425662e-06, "epoch": 0.45782416836388323, "percentage": 9.16, "elapsed_time": "0:08:06", "remaining_time": "1:20:25", "throughput": 10643.52, "total_tokens": 5176896}
{"current_steps": 5400, "total_steps": 58920, "loss": 0.0451, "lr": 1.8326544467074e-06, "epoch": 0.45824847250509165, "percentage": 9.16, "elapsed_time": "0:08:06", "remaining_time": "1:20:24", "throughput": 10644.42, "total_tokens": 5181312}
{"current_steps": 5405, "total_steps": 58920, "loss": 0.0411, "lr": 1.8343516632722335e-06, "epoch": 0.4586727766463001, "percentage": 9.17, "elapsed_time": "0:08:07", "remaining_time": "1:20:23", "throughput": 10645.92, "total_tokens": 5186112}
{"current_steps": 5410, "total_steps": 58920, "loss": 0.0388, "lr": 1.836048879837067e-06, "epoch": 0.4590970807875085, "percentage": 9.18, "elapsed_time": "0:08:07", "remaining_time": "1:20:22", "throughput": 10647.57, "total_tokens": 5191040}
{"current_steps": 5415, "total_steps": 58920, "loss": 0.0458, "lr": 1.8377460964019008e-06, "epoch": 0.4595213849287169, "percentage": 9.19, "elapsed_time": "0:08:07", "remaining_time": "1:20:20", "throughput": 10648.65, "total_tokens": 5195584}
{"current_steps": 5420, "total_steps": 58920, "loss": 0.0495, "lr": 1.8394433129667345e-06, "epoch": 0.45994568906992533, "percentage": 9.2, "elapsed_time": "0:08:08", "remaining_time": "1:20:19", "throughput": 10649.91, "total_tokens": 5200256}
{"current_steps": 5425, "total_steps": 58920, "loss": 0.0437, "lr": 1.841140529531568e-06, "epoch": 0.46036999321113375, "percentage": 9.21, "elapsed_time": "0:08:08", "remaining_time": "1:20:18", "throughput": 10651.98, "total_tokens": 5205376}
{"current_steps": 5430, "total_steps": 58920, "loss": 0.0289, "lr": 1.8428377460964018e-06, "epoch": 0.4607942973523422, "percentage": 9.22, "elapsed_time": "0:08:09", "remaining_time": "1:20:17", "throughput": 10655.25, "total_tokens": 5211392}
{"current_steps": 5435, "total_steps": 58920, "loss": 0.0769, "lr": 1.8445349626612355e-06, "epoch": 0.4612186014935506, "percentage": 9.22, "elapsed_time": "0:08:09", "remaining_time": "1:20:16", "throughput": 10655.84, "total_tokens": 5215616}
{"current_steps": 5440, "total_steps": 58920, "loss": 0.0834, "lr": 1.846232179226069e-06, "epoch": 0.461642905634759, "percentage": 9.23, "elapsed_time": "0:08:09", "remaining_time": "1:20:15", "throughput": 10657.61, "total_tokens": 5220608}
{"current_steps": 5445, "total_steps": 58920, "loss": 0.1164, "lr": 1.8479293957909028e-06, "epoch": 0.46206720977596744, "percentage": 9.24, "elapsed_time": "0:08:10", "remaining_time": "1:20:14", "throughput": 10659.05, "total_tokens": 5225344}
{"current_steps": 5450, "total_steps": 58920, "loss": 0.1101, "lr": 1.8496266123557365e-06, "epoch": 0.46249151391717586, "percentage": 9.25, "elapsed_time": "0:08:10", "remaining_time": "1:20:13", "throughput": 10661.11, "total_tokens": 5230464}
{"current_steps": 5455, "total_steps": 58920, "loss": 0.0828, "lr": 1.8513238289205702e-06, "epoch": 0.4629158180583843, "percentage": 9.26, "elapsed_time": "0:08:10", "remaining_time": "1:20:12", "throughput": 10662.59, "total_tokens": 5235264}
{"current_steps": 5460, "total_steps": 58920, "loss": 0.0507, "lr": 1.8530210454854038e-06, "epoch": 0.46334012219959264, "percentage": 9.27, "elapsed_time": "0:08:11", "remaining_time": "1:20:11", "throughput": 10663.63, "total_tokens": 5239808}
{"current_steps": 5465, "total_steps": 58920, "loss": 0.085, "lr": 1.8547182620502375e-06, "epoch": 0.46376442634080106, "percentage": 9.28, "elapsed_time": "0:08:11", "remaining_time": "1:20:09", "throughput": 10664.75, "total_tokens": 5244416}
{"current_steps": 5470, "total_steps": 58920, "loss": 0.0813, "lr": 1.8564154786150712e-06, "epoch": 0.4641887304820095, "percentage": 9.28, "elapsed_time": "0:08:12", "remaining_time": "1:20:08", "throughput": 10666.28, "total_tokens": 5249280}
{"current_steps": 5475, "total_steps": 58920, "loss": 0.0821, "lr": 1.858112695179905e-06, "epoch": 0.4646130346232179, "percentage": 9.29, "elapsed_time": "0:08:12", "remaining_time": "1:20:07", "throughput": 10667.84, "total_tokens": 5254080}
{"current_steps": 5480, "total_steps": 58920, "loss": 0.0471, "lr": 1.8598099117447385e-06, "epoch": 0.4650373387644263, "percentage": 9.3, "elapsed_time": "0:08:12", "remaining_time": "1:20:06", "throughput": 10669.75, "total_tokens": 5259136}
{"current_steps": 5485, "total_steps": 58920, "loss": 0.0528, "lr": 1.8615071283095722e-06, "epoch": 0.46546164290563474, "percentage": 9.31, "elapsed_time": "0:08:13", "remaining_time": "1:20:05", "throughput": 10670.89, "total_tokens": 5263744}
{"current_steps": 5490, "total_steps": 58920, "loss": 0.0665, "lr": 1.863204344874406e-06, "epoch": 0.46588594704684316, "percentage": 9.32, "elapsed_time": "0:08:13", "remaining_time": "1:20:04", "throughput": 10672.32, "total_tokens": 5268544}
{"current_steps": 5495, "total_steps": 58920, "loss": 0.0355, "lr": 1.8649015614392395e-06, "epoch": 0.4663102511880516, "percentage": 9.33, "elapsed_time": "0:08:14", "remaining_time": "1:20:03", "throughput": 10673.64, "total_tokens": 5273280}
{"current_steps": 5500, "total_steps": 58920, "loss": 0.03, "lr": 1.8665987780040732e-06, "epoch": 0.46673455532926, "percentage": 9.33, "elapsed_time": "0:08:14", "remaining_time": "1:20:02", "throughput": 10674.8, "total_tokens": 5277888}
{"current_steps": 5505, "total_steps": 58920, "loss": 0.1157, "lr": 1.868295994568907e-06, "epoch": 0.4671588594704684, "percentage": 9.34, "elapsed_time": "0:08:14", "remaining_time": "1:20:01", "throughput": 10675.75, "total_tokens": 5282432}
{"current_steps": 5510, "total_steps": 58920, "loss": 0.0235, "lr": 1.8699932111337407e-06, "epoch": 0.46758316361167684, "percentage": 9.35, "elapsed_time": "0:08:15", "remaining_time": "1:20:00", "throughput": 10679.15, "total_tokens": 5288512}
{"current_steps": 5515, "total_steps": 58920, "loss": 0.0127, "lr": 1.8716904276985742e-06, "epoch": 0.46800746775288526, "percentage": 9.36, "elapsed_time": "0:08:15", "remaining_time": "1:19:59", "throughput": 10679.74, "total_tokens": 5292800}
{"current_steps": 5520, "total_steps": 58920, "loss": 0.0555, "lr": 1.873387644263408e-06, "epoch": 0.4684317718940937, "percentage": 9.37, "elapsed_time": "0:08:15", "remaining_time": "1:19:58", "throughput": 10681.61, "total_tokens": 5297856}
{"current_steps": 5525, "total_steps": 58920, "loss": 0.1075, "lr": 1.8750848608282417e-06, "epoch": 0.4688560760353021, "percentage": 9.38, "elapsed_time": "0:08:16", "remaining_time": "1:19:56", "throughput": 10683.29, "total_tokens": 5302784}
{"current_steps": 5530, "total_steps": 58920, "loss": 0.0704, "lr": 1.8767820773930755e-06, "epoch": 0.4692803801765105, "percentage": 9.39, "elapsed_time": "0:08:16", "remaining_time": "1:19:55", "throughput": 10684.81, "total_tokens": 5307648}
{"current_steps": 5535, "total_steps": 58920, "loss": 0.0398, "lr": 1.878479293957909e-06, "epoch": 0.46970468431771895, "percentage": 9.39, "elapsed_time": "0:08:17", "remaining_time": "1:19:54", "throughput": 10685.03, "total_tokens": 5311680}
{"current_steps": 5540, "total_steps": 58920, "loss": 0.0578, "lr": 1.8801765105227425e-06, "epoch": 0.47012898845892737, "percentage": 9.4, "elapsed_time": "0:08:17", "remaining_time": "1:19:53", "throughput": 10686.17, "total_tokens": 5316288}
{"current_steps": 5545, "total_steps": 58920, "loss": 0.0364, "lr": 1.8818737270875762e-06, "epoch": 0.4705532926001358, "percentage": 9.41, "elapsed_time": "0:08:17", "remaining_time": "1:19:52", "throughput": 10686.63, "total_tokens": 5320448}
{"current_steps": 5550, "total_steps": 58920, "loss": 0.0641, "lr": 1.8835709436524098e-06, "epoch": 0.4709775967413442, "percentage": 9.42, "elapsed_time": "0:08:18", "remaining_time": "1:19:51", "throughput": 10687.49, "total_tokens": 5324928}
{"current_steps": 5555, "total_steps": 58920, "loss": 0.0397, "lr": 1.8852681602172435e-06, "epoch": 0.4714019008825526, "percentage": 9.43, "elapsed_time": "0:08:18", "remaining_time": "1:19:50", "throughput": 10689.03, "total_tokens": 5329792}
{"current_steps": 5560, "total_steps": 58920, "loss": 0.1052, "lr": 1.8869653767820772e-06, "epoch": 0.47182620502376105, "percentage": 9.44, "elapsed_time": "0:08:19", "remaining_time": "1:19:49", "throughput": 10690.63, "total_tokens": 5334720}
{"current_steps": 5565, "total_steps": 58920, "loss": 0.1533, "lr": 1.888662593346911e-06, "epoch": 0.47225050916496947, "percentage": 9.45, "elapsed_time": "0:08:19", "remaining_time": "1:19:48", "throughput": 10692.75, "total_tokens": 5339968}
{"current_steps": 5570, "total_steps": 58920, "loss": 0.0449, "lr": 1.8903598099117445e-06, "epoch": 0.4726748133061779, "percentage": 9.45, "elapsed_time": "0:08:19", "remaining_time": "1:19:47", "throughput": 10694.84, "total_tokens": 5345216}
{"current_steps": 5575, "total_steps": 58920, "loss": 0.1118, "lr": 1.8920570264765782e-06, "epoch": 0.4730991174473863, "percentage": 9.46, "elapsed_time": "0:08:20", "remaining_time": "1:19:46", "throughput": 10696.88, "total_tokens": 5350400}
{"current_steps": 5580, "total_steps": 58920, "loss": 0.1063, "lr": 1.893754243041412e-06, "epoch": 0.47352342158859473, "percentage": 9.47, "elapsed_time": "0:08:20", "remaining_time": "1:19:44", "throughput": 10697.93, "total_tokens": 5354944}
{"current_steps": 5585, "total_steps": 58920, "loss": 0.1454, "lr": 1.8954514596062457e-06, "epoch": 0.47394772572980315, "percentage": 9.48, "elapsed_time": "0:08:20", "remaining_time": "1:19:43", "throughput": 10698.25, "total_tokens": 5359040}
{"current_steps": 5590, "total_steps": 58920, "loss": 0.0723, "lr": 1.8971486761710792e-06, "epoch": 0.4743720298710115, "percentage": 9.49, "elapsed_time": "0:08:21", "remaining_time": "1:19:42", "throughput": 10699.3, "total_tokens": 5363584}
{"current_steps": 5595, "total_steps": 58920, "loss": 0.0184, "lr": 1.898845892735913e-06, "epoch": 0.47479633401221993, "percentage": 9.5, "elapsed_time": "0:08:21", "remaining_time": "1:19:41", "throughput": 10700.55, "total_tokens": 5368256}
{"current_steps": 5600, "total_steps": 58920, "loss": 0.0561, "lr": 1.9005431093007467e-06, "epoch": 0.47522063815342835, "percentage": 9.5, "elapsed_time": "0:08:22", "remaining_time": "1:19:40", "throughput": 10701.58, "total_tokens": 5372800}
{"current_steps": 5605, "total_steps": 58920, "loss": 0.043, "lr": 1.9022403258655805e-06, "epoch": 0.4756449422946368, "percentage": 9.51, "elapsed_time": "0:08:22", "remaining_time": "1:19:39", "throughput": 10702.54, "total_tokens": 5377280}
{"current_steps": 5610, "total_steps": 58920, "loss": 0.1064, "lr": 1.903937542430414e-06, "epoch": 0.4760692464358452, "percentage": 9.52, "elapsed_time": "0:08:22", "remaining_time": "1:19:38", "throughput": 10704.15, "total_tokens": 5382208}
{"current_steps": 5615, "total_steps": 58920, "loss": 0.0758, "lr": 1.9056347589952477e-06, "epoch": 0.4764935505770536, "percentage": 9.53, "elapsed_time": "0:08:23", "remaining_time": "1:19:36", "throughput": 10705.29, "total_tokens": 5386816}
{"current_steps": 5620, "total_steps": 58920, "loss": 0.0871, "lr": 1.9073319755600815e-06, "epoch": 0.47691785471826204, "percentage": 9.54, "elapsed_time": "0:08:23", "remaining_time": "1:19:35", "throughput": 10706.31, "total_tokens": 5391360}
{"current_steps": 5625, "total_steps": 58920, "loss": 0.0658, "lr": 1.909029192124915e-06, "epoch": 0.47734215885947046, "percentage": 9.55, "elapsed_time": "0:08:23", "remaining_time": "1:19:34", "throughput": 10707.35, "total_tokens": 5395904}
{"current_steps": 5630, "total_steps": 58920, "loss": 0.0631, "lr": 1.910726408689749e-06, "epoch": 0.4777664630006789, "percentage": 9.56, "elapsed_time": "0:08:24", "remaining_time": "1:19:33", "throughput": 10708.32, "total_tokens": 5400448}
{"current_steps": 5635, "total_steps": 58920, "loss": 0.0729, "lr": 1.9124236252545823e-06, "epoch": 0.4781907671418873, "percentage": 9.56, "elapsed_time": "0:08:24", "remaining_time": "1:19:32", "throughput": 10710.56, "total_tokens": 5405824}
{"current_steps": 5640, "total_steps": 58920, "loss": 0.0456, "lr": 1.914120841819416e-06, "epoch": 0.4786150712830957, "percentage": 9.57, "elapsed_time": "0:08:25", "remaining_time": "1:19:31", "throughput": 10712.04, "total_tokens": 5410688}
{"current_steps": 5645, "total_steps": 58920, "loss": 0.069, "lr": 1.9158180583842497e-06, "epoch": 0.47903937542430414, "percentage": 9.58, "elapsed_time": "0:08:25", "remaining_time": "1:19:30", "throughput": 10713.14, "total_tokens": 5415296}
{"current_steps": 5650, "total_steps": 58920, "loss": 0.0988, "lr": 1.9175152749490835e-06, "epoch": 0.47946367956551256, "percentage": 9.59, "elapsed_time": "0:08:25", "remaining_time": "1:19:29", "throughput": 10713.76, "total_tokens": 5419648}
{"current_steps": 5655, "total_steps": 58920, "loss": 0.0515, "lr": 1.919212491513917e-06, "epoch": 0.479887983706721, "percentage": 9.6, "elapsed_time": "0:08:26", "remaining_time": "1:19:28", "throughput": 10715.29, "total_tokens": 5424576}
{"current_steps": 5660, "total_steps": 58920, "loss": 0.036, "lr": 1.920909708078751e-06, "epoch": 0.4803122878479294, "percentage": 9.61, "elapsed_time": "0:08:26", "remaining_time": "1:19:27", "throughput": 10716.31, "total_tokens": 5429184}
{"current_steps": 5665, "total_steps": 58920, "loss": 0.0606, "lr": 1.9226069246435847e-06, "epoch": 0.4807365919891378, "percentage": 9.61, "elapsed_time": "0:08:27", "remaining_time": "1:19:26", "throughput": 10716.97, "total_tokens": 5433536}
{"current_steps": 5670, "total_steps": 58920, "loss": 0.0976, "lr": 1.924304141208418e-06, "epoch": 0.48116089613034624, "percentage": 9.62, "elapsed_time": "0:08:27", "remaining_time": "1:19:25", "throughput": 10718.58, "total_tokens": 5438464}
{"current_steps": 5675, "total_steps": 58920, "loss": 0.0814, "lr": 1.9260013577732517e-06, "epoch": 0.48158520027155466, "percentage": 9.63, "elapsed_time": "0:08:27", "remaining_time": "1:19:24", "throughput": 10719.81, "total_tokens": 5443136}
{"current_steps": 5680, "total_steps": 58920, "loss": 0.0326, "lr": 1.9276985743380855e-06, "epoch": 0.4820095044127631, "percentage": 9.64, "elapsed_time": "0:08:28", "remaining_time": "1:19:22", "throughput": 10720.93, "total_tokens": 5447744}
{"current_steps": 5685, "total_steps": 58920, "loss": 0.0923, "lr": 1.929395790902919e-06, "epoch": 0.4824338085539715, "percentage": 9.65, "elapsed_time": "0:08:28", "remaining_time": "1:19:21", "throughput": 10722.75, "total_tokens": 5452800}
{"current_steps": 5690, "total_steps": 58920, "loss": 0.0733, "lr": 1.9310930074677525e-06, "epoch": 0.4828581126951799, "percentage": 9.66, "elapsed_time": "0:08:28", "remaining_time": "1:19:20", "throughput": 10723.99, "total_tokens": 5457472}
{"current_steps": 5695, "total_steps": 58920, "loss": 0.0707, "lr": 1.9327902240325863e-06, "epoch": 0.48328241683638834, "percentage": 9.67, "elapsed_time": "0:08:29", "remaining_time": "1:19:19", "throughput": 10725.43, "total_tokens": 5462272}
{"current_steps": 5700, "total_steps": 58920, "loss": 0.0318, "lr": 1.93448744059742e-06, "epoch": 0.48370672097759676, "percentage": 9.67, "elapsed_time": "0:08:29", "remaining_time": "1:19:18", "throughput": 10726.5, "total_tokens": 5466880}
{"current_steps": 5705, "total_steps": 58920, "loss": 0.0467, "lr": 1.9361846571622537e-06, "epoch": 0.4841310251188052, "percentage": 9.68, "elapsed_time": "0:08:30", "remaining_time": "1:19:17", "throughput": 10727.77, "total_tokens": 5471616}
{"current_steps": 5710, "total_steps": 58920, "loss": 0.0924, "lr": 1.9378818737270875e-06, "epoch": 0.4845553292600136, "percentage": 9.69, "elapsed_time": "0:08:30", "remaining_time": "1:19:16", "throughput": 10728.67, "total_tokens": 5476160}
{"current_steps": 5715, "total_steps": 58920, "loss": 0.1676, "lr": 1.9395790902919212e-06, "epoch": 0.484979633401222, "percentage": 9.7, "elapsed_time": "0:08:30", "remaining_time": "1:19:15", "throughput": 10730.05, "total_tokens": 5480960}
{"current_steps": 5720, "total_steps": 58920, "loss": 0.0631, "lr": 1.941276306856755e-06, "epoch": 0.48540393754243044, "percentage": 9.71, "elapsed_time": "0:08:31", "remaining_time": "1:19:14", "throughput": 10732.5, "total_tokens": 5486528}
{"current_steps": 5725, "total_steps": 58920, "loss": 0.06, "lr": 1.9429735234215887e-06, "epoch": 0.4858282416836388, "percentage": 9.72, "elapsed_time": "0:08:31", "remaining_time": "1:19:13", "throughput": 10734.03, "total_tokens": 5491456}
{"current_steps": 5730, "total_steps": 58920, "loss": 0.0778, "lr": 1.944670739986422e-06, "epoch": 0.4862525458248472, "percentage": 9.73, "elapsed_time": "0:08:31", "remaining_time": "1:19:12", "throughput": 10735.89, "total_tokens": 5496640}
{"current_steps": 5735, "total_steps": 58920, "loss": 0.0423, "lr": 1.9463679565512557e-06, "epoch": 0.48667684996605565, "percentage": 9.73, "elapsed_time": "0:08:32", "remaining_time": "1:19:11", "throughput": 10737.12, "total_tokens": 5501376}
{"current_steps": 5740, "total_steps": 58920, "loss": 0.052, "lr": 1.9480651731160895e-06, "epoch": 0.48710115410726407, "percentage": 9.74, "elapsed_time": "0:08:32", "remaining_time": "1:19:10", "throughput": 10737.99, "total_tokens": 5505856}
{"current_steps": 5745, "total_steps": 58920, "loss": 0.0963, "lr": 1.9497623896809232e-06, "epoch": 0.4875254582484725, "percentage": 9.75, "elapsed_time": "0:08:33", "remaining_time": "1:19:09", "throughput": 10739.47, "total_tokens": 5510720}
{"current_steps": 5750, "total_steps": 58920, "loss": 0.0772, "lr": 1.951459606245757e-06, "epoch": 0.4879497623896809, "percentage": 9.76, "elapsed_time": "0:08:33", "remaining_time": "1:19:08", "throughput": 10739.85, "total_tokens": 5514880}
{"current_steps": 5755, "total_steps": 58920, "loss": 0.0682, "lr": 1.9531568228105907e-06, "epoch": 0.48837406653088933, "percentage": 9.77, "elapsed_time": "0:08:33", "remaining_time": "1:19:07", "throughput": 10741.09, "total_tokens": 5519616}
{"current_steps": 5760, "total_steps": 58920, "loss": 0.0924, "lr": 1.9548540393754244e-06, "epoch": 0.48879837067209775, "percentage": 9.78, "elapsed_time": "0:08:34", "remaining_time": "1:19:06", "throughput": 10741.77, "total_tokens": 5523968}
{"current_steps": 5765, "total_steps": 58920, "loss": 0.0593, "lr": 1.9565512559402577e-06, "epoch": 0.48922267481330617, "percentage": 9.78, "elapsed_time": "0:08:34", "remaining_time": "1:19:05", "throughput": 10743.45, "total_tokens": 5528960}
{"current_steps": 5770, "total_steps": 58920, "loss": 0.0752, "lr": 1.9582484725050915e-06, "epoch": 0.4896469789545146, "percentage": 9.79, "elapsed_time": "0:08:35", "remaining_time": "1:19:04", "throughput": 10747.21, "total_tokens": 5535488}
{"current_steps": 5775, "total_steps": 58920, "loss": 0.0933, "lr": 1.9599456890699252e-06, "epoch": 0.490071283095723, "percentage": 9.8, "elapsed_time": "0:08:35", "remaining_time": "1:19:03", "throughput": 10748.5, "total_tokens": 5540288}
{"current_steps": 5780, "total_steps": 58920, "loss": 0.088, "lr": 1.961642905634759e-06, "epoch": 0.49049558723693143, "percentage": 9.81, "elapsed_time": "0:08:35", "remaining_time": "1:19:02", "throughput": 10750.86, "total_tokens": 5545792}
{"current_steps": 5785, "total_steps": 58920, "loss": 0.1164, "lr": 1.9633401221995927e-06, "epoch": 0.49091989137813985, "percentage": 9.82, "elapsed_time": "0:08:36", "remaining_time": "1:19:01", "throughput": 10751.85, "total_tokens": 5550336}
{"current_steps": 5790, "total_steps": 58920, "loss": 0.0628, "lr": 1.9650373387644264e-06, "epoch": 0.49134419551934827, "percentage": 9.83, "elapsed_time": "0:08:36", "remaining_time": "1:19:00", "throughput": 10753.51, "total_tokens": 5555328}
{"current_steps": 5795, "total_steps": 58920, "loss": 0.0509, "lr": 1.96673455532926e-06, "epoch": 0.4917684996605567, "percentage": 9.84, "elapsed_time": "0:08:37", "remaining_time": "1:18:59", "throughput": 10755.93, "total_tokens": 5560896}
{"current_steps": 5800, "total_steps": 58920, "loss": 0.0621, "lr": 1.968431771894094e-06, "epoch": 0.4921928038017651, "percentage": 9.84, "elapsed_time": "0:08:37", "remaining_time": "1:18:58", "throughput": 10757.45, "total_tokens": 5565824}
{"current_steps": 5805, "total_steps": 58920, "loss": 0.0465, "lr": 1.9701289884589272e-06, "epoch": 0.49261710794297353, "percentage": 9.85, "elapsed_time": "0:08:37", "remaining_time": "1:18:57", "throughput": 10758.33, "total_tokens": 5570368}
{"current_steps": 5810, "total_steps": 58920, "loss": 0.0773, "lr": 1.971826205023761e-06, "epoch": 0.49304141208418195, "percentage": 9.86, "elapsed_time": "0:08:38", "remaining_time": "1:18:56", "throughput": 10759.2, "total_tokens": 5574848}
{"current_steps": 5815, "total_steps": 58920, "loss": 0.0623, "lr": 1.9735234215885947e-06, "epoch": 0.49346571622539037, "percentage": 9.87, "elapsed_time": "0:08:38", "remaining_time": "1:18:55", "throughput": 10760.21, "total_tokens": 5579456}
{"current_steps": 5820, "total_steps": 58920, "loss": 0.0347, "lr": 1.975220638153428e-06, "epoch": 0.4938900203665988, "percentage": 9.88, "elapsed_time": "0:08:38", "remaining_time": "1:18:54", "throughput": 10761.75, "total_tokens": 5584384}
{"current_steps": 5825, "total_steps": 58920, "loss": 0.1719, "lr": 1.9769178547182618e-06, "epoch": 0.4943143245078072, "percentage": 9.89, "elapsed_time": "0:08:39", "remaining_time": "1:18:53", "throughput": 10763.74, "total_tokens": 5589632}
{"current_steps": 5830, "total_steps": 58920, "loss": 0.0245, "lr": 1.9786150712830955e-06, "epoch": 0.49473862864901563, "percentage": 9.89, "elapsed_time": "0:08:39", "remaining_time": "1:18:52", "throughput": 10764.5, "total_tokens": 5594048}
{"current_steps": 5835, "total_steps": 58920, "loss": 0.0598, "lr": 1.9803122878479292e-06, "epoch": 0.49516293279022405, "percentage": 9.9, "elapsed_time": "0:08:40", "remaining_time": "1:18:51", "throughput": 10765.58, "total_tokens": 5598720}
{"current_steps": 5840, "total_steps": 58920, "loss": 0.1264, "lr": 1.982009504412763e-06, "epoch": 0.4955872369314325, "percentage": 9.91, "elapsed_time": "0:08:40", "remaining_time": "1:18:50", "throughput": 10766.29, "total_tokens": 5603136}
{"current_steps": 5845, "total_steps": 58920, "loss": 0.0503, "lr": 1.9837067209775967e-06, "epoch": 0.4960115410726409, "percentage": 9.92, "elapsed_time": "0:08:40", "remaining_time": "1:18:49", "throughput": 10767.52, "total_tokens": 5607872}
{"current_steps": 5850, "total_steps": 58920, "loss": 0.0581, "lr": 1.9854039375424304e-06, "epoch": 0.4964358452138493, "percentage": 9.93, "elapsed_time": "0:08:41", "remaining_time": "1:18:48", "throughput": 10768.38, "total_tokens": 5612352}
{"current_steps": 5855, "total_steps": 58920, "loss": 0.0702, "lr": 1.987101154107264e-06, "epoch": 0.4968601493550577, "percentage": 9.94, "elapsed_time": "0:08:41", "remaining_time": "1:18:47", "throughput": 10770.16, "total_tokens": 5617472}
{"current_steps": 5860, "total_steps": 58920, "loss": 0.1154, "lr": 1.9887983706720975e-06, "epoch": 0.4972844534962661, "percentage": 9.95, "elapsed_time": "0:08:41", "remaining_time": "1:18:46", "throughput": 10770.79, "total_tokens": 5621824}
{"current_steps": 5865, "total_steps": 58920, "loss": 0.0316, "lr": 1.9904955872369312e-06, "epoch": 0.4977087576374745, "percentage": 9.95, "elapsed_time": "0:08:42", "remaining_time": "1:18:44", "throughput": 10771.6, "total_tokens": 5626304}
{"current_steps": 5870, "total_steps": 58920, "loss": 0.0748, "lr": 1.992192803801765e-06, "epoch": 0.49813306177868294, "percentage": 9.96, "elapsed_time": "0:08:42", "remaining_time": "1:18:44", "throughput": 10773.73, "total_tokens": 5631680}
{"current_steps": 5875, "total_steps": 58920, "loss": 0.166, "lr": 1.9938900203665987e-06, "epoch": 0.49855736591989136, "percentage": 9.97, "elapsed_time": "0:08:43", "remaining_time": "1:18:42", "throughput": 10774.19, "total_tokens": 5635904}
{"current_steps": 5880, "total_steps": 58920, "loss": 0.0504, "lr": 1.9955872369314324e-06, "epoch": 0.4989816700610998, "percentage": 9.98, "elapsed_time": "0:08:43", "remaining_time": "1:18:41", "throughput": 10775.27, "total_tokens": 5640512}
{"current_steps": 5885, "total_steps": 58920, "loss": 0.1017, "lr": 1.997284453496266e-06, "epoch": 0.4994059742023082, "percentage": 9.99, "elapsed_time": "0:08:43", "remaining_time": "1:18:41", "throughput": 10778.1, "total_tokens": 5646464}
{"current_steps": 5890, "total_steps": 58920, "loss": 0.0452, "lr": 1.9989816700611e-06, "epoch": 0.4998302783435166, "percentage": 10.0, "elapsed_time": "0:08:44", "remaining_time": "1:18:40", "throughput": 10779.04, "total_tokens": 5651008}
{"current_steps": 5892, "total_steps": 58920, "eval_loss": 0.06119616702198982, "epoch": 0.5, "percentage": 10.0, "elapsed_time": "0:09:00", "remaining_time": "1:21:06", "throughput": 10453.2, "total_tokens": 5652800}
{"current_steps": 5895, "total_steps": 58920, "loss": 0.0513, "lr": 1.9999999929802885e-06, "epoch": 0.5002545824847251, "percentage": 10.01, "elapsed_time": "0:09:34", "remaining_time": "1:26:03", "throughput": 9851.95, "total_tokens": 5655616}
{"current_steps": 5900, "total_steps": 58920, "loss": 0.0109, "lr": 1.9999999140085387e-06, "epoch": 0.5006788866259335, "percentage": 10.01, "elapsed_time": "0:09:34", "remaining_time": "1:26:02", "throughput": 9853.59, "total_tokens": 5660352}
{"current_steps": 5905, "total_steps": 58920, "loss": 0.0539, "lr": 1.999999747290407e-06, "epoch": 0.5011031907671419, "percentage": 10.02, "elapsed_time": "0:09:34", "remaining_time": "1:26:00", "throughput": 9854.94, "total_tokens": 5664832}
{"current_steps": 5910, "total_steps": 58920, "loss": 0.1527, "lr": 1.9999994928259077e-06, "epoch": 0.5015274949083504, "percentage": 10.03, "elapsed_time": "0:09:35", "remaining_time": "1:25:59", "throughput": 9856.98, "total_tokens": 5669824}
{"current_steps": 5915, "total_steps": 58920, "loss": 0.0757, "lr": 1.9999991506150632e-06, "epoch": 0.5019517990495588, "percentage": 10.04, "elapsed_time": "0:09:35", "remaining_time": "1:25:57", "throughput": 9858.21, "total_tokens": 5674240}
{"current_steps": 5920, "total_steps": 58920, "loss": 0.1383, "lr": 1.999998720657904e-06, "epoch": 0.5023761031907671, "percentage": 10.05, "elapsed_time": "0:09:35", "remaining_time": "1:25:56", "throughput": 9860.28, "total_tokens": 5679296}
{"current_steps": 5925, "total_steps": 58920, "loss": 0.057, "lr": 1.9999982029544676e-06, "epoch": 0.5028004073319755, "percentage": 10.06, "elapsed_time": "0:09:36", "remaining_time": "1:25:55", "throughput": 9861.73, "total_tokens": 5683840}
{"current_steps": 5930, "total_steps": 58920, "loss": 0.0798, "lr": 1.9999975975047994e-06, "epoch": 0.5032247114731839, "percentage": 10.06, "elapsed_time": "0:09:36", "remaining_time": "1:25:53", "throughput": 9863.82, "total_tokens": 5688896}
{"current_steps": 5935, "total_steps": 58920, "loss": 0.047, "lr": 1.9999969043089524e-06, "epoch": 0.5036490156143923, "percentage": 10.07, "elapsed_time": "0:09:37", "remaining_time": "1:25:52", "throughput": 9865.25, "total_tokens": 5693440}
{"current_steps": 5940, "total_steps": 58920, "loss": 0.0507, "lr": 1.9999961233669875e-06, "epoch": 0.5040733197556008, "percentage": 10.08, "elapsed_time": "0:09:37", "remaining_time": "1:25:50", "throughput": 9866.61, "total_tokens": 5697920}
{"current_steps": 5945, "total_steps": 58920, "loss": 0.0525, "lr": 1.9999952546789734e-06, "epoch": 0.5044976238968092, "percentage": 10.09, "elapsed_time": "0:09:37", "remaining_time": "1:25:49", "throughput": 9868.13, "total_tokens": 5702528}
{"current_steps": 5950, "total_steps": 58920, "loss": 0.0691, "lr": 1.999994298244986e-06, "epoch": 0.5049219280380176, "percentage": 10.1, "elapsed_time": "0:09:38", "remaining_time": "1:25:48", "throughput": 9870.2, "total_tokens": 5707584}
{"current_steps": 5955, "total_steps": 58920, "loss": 0.059, "lr": 1.999993254065109e-06, "epoch": 0.505346232179226, "percentage": 10.11, "elapsed_time": "0:09:38", "remaining_time": "1:25:46", "throughput": 9871.62, "total_tokens": 5712192}
{"current_steps": 5960, "total_steps": 58920, "loss": 0.169, "lr": 1.999992122139435e-06, "epoch": 0.5057705363204344, "percentage": 10.12, "elapsed_time": "0:09:39", "remaining_time": "1:25:45", "throughput": 9874.21, "total_tokens": 5717632}
{"current_steps": 5965, "total_steps": 58920, "loss": 0.0914, "lr": 1.999990902468063e-06, "epoch": 0.5061948404616429, "percentage": 10.12, "elapsed_time": "0:09:39", "remaining_time": "1:25:43", "throughput": 9875.65, "total_tokens": 5722176}
{"current_steps": 5970, "total_steps": 58920, "loss": 0.0894, "lr": 1.9999895950510993e-06, "epoch": 0.5066191446028513, "percentage": 10.13, "elapsed_time": "0:09:39", "remaining_time": "1:25:42", "throughput": 9877.06, "total_tokens": 5726720}
{"current_steps": 5975, "total_steps": 58920, "loss": 0.0713, "lr": 1.999988199888659e-06, "epoch": 0.5070434487440597, "percentage": 10.14, "elapsed_time": "0:09:40", "remaining_time": "1:25:41", "throughput": 9878.58, "total_tokens": 5731328}
{"current_steps": 5980, "total_steps": 58920, "loss": 0.0722, "lr": 1.9999867169808646e-06, "epoch": 0.5074677528852681, "percentage": 10.15, "elapsed_time": "0:09:40", "remaining_time": "1:25:39", "throughput": 9880.46, "total_tokens": 5736256}
{"current_steps": 5985, "total_steps": 58920, "loss": 0.0689, "lr": 1.9999851463278462e-06, "epoch": 0.5078920570264766, "percentage": 10.16, "elapsed_time": "0:09:40", "remaining_time": "1:25:38", "throughput": 9882.37, "total_tokens": 5741248}
{"current_steps": 5990, "total_steps": 58920, "loss": 0.0506, "lr": 1.9999834879297417e-06, "epoch": 0.508316361167685, "percentage": 10.17, "elapsed_time": "0:09:41", "remaining_time": "1:25:37", "throughput": 9884.42, "total_tokens": 5746304}
{"current_steps": 5995, "total_steps": 58920, "loss": 0.0842, "lr": 1.9999817417866967e-06, "epoch": 0.5087406653088934, "percentage": 10.17, "elapsed_time": "0:09:41", "remaining_time": "1:25:35", "throughput": 9886.72, "total_tokens": 5751552}
{"current_steps": 6000, "total_steps": 58920, "loss": 0.0566, "lr": 1.9999799078988646e-06, "epoch": 0.5091649694501018, "percentage": 10.18, "elapsed_time": "0:09:42", "remaining_time": "1:25:34", "throughput": 9888.04, "total_tokens": 5756032}
{"current_steps": 6005, "total_steps": 58920, "loss": 0.1246, "lr": 1.9999779862664053e-06, "epoch": 0.5095892735913102, "percentage": 10.19, "elapsed_time": "0:09:42", "remaining_time": "1:25:33", "throughput": 9890.72, "total_tokens": 5761600}
{"current_steps": 6010, "total_steps": 58920, "loss": 0.0277, "lr": 1.9999759768894888e-06, "epoch": 0.5100135777325187, "percentage": 10.2, "elapsed_time": "0:09:42", "remaining_time": "1:25:31", "throughput": 9892.35, "total_tokens": 5766336}
{"current_steps": 6015, "total_steps": 58920, "loss": 0.1046, "lr": 1.99997387976829e-06, "epoch": 0.5104378818737271, "percentage": 10.21, "elapsed_time": "0:09:43", "remaining_time": "1:25:30", "throughput": 9894.41, "total_tokens": 5771392}
{"current_steps": 6020, "total_steps": 58920, "loss": 0.0326, "lr": 1.9999716949029942e-06, "epoch": 0.5108621860149355, "percentage": 10.22, "elapsed_time": "0:09:43", "remaining_time": "1:25:28", "throughput": 9895.63, "total_tokens": 5775808}
{"current_steps": 6025, "total_steps": 58920, "loss": 0.0446, "lr": 1.9999694222937923e-06, "epoch": 0.5112864901561439, "percentage": 10.23, "elapsed_time": "0:09:44", "remaining_time": "1:25:27", "throughput": 9897.57, "total_tokens": 5780800}
{"current_steps": 6030, "total_steps": 58920, "loss": 0.0328, "lr": 1.9999670619408844e-06, "epoch": 0.5117107942973523, "percentage": 10.23, "elapsed_time": "0:09:44", "remaining_time": "1:25:26", "throughput": 9900.13, "total_tokens": 5786304}
{"current_steps": 6035, "total_steps": 58920, "loss": 0.0566, "lr": 1.9999646138444764e-06, "epoch": 0.5121350984385608, "percentage": 10.24, "elapsed_time": "0:09:44", "remaining_time": "1:25:25", "throughput": 9902.22, "total_tokens": 5791360}
{"current_steps": 6040, "total_steps": 58920, "loss": 0.0283, "lr": 1.9999620780047842e-06, "epoch": 0.5125594025797692, "percentage": 10.25, "elapsed_time": "0:09:45", "remaining_time": "1:25:23", "throughput": 9903.46, "total_tokens": 5795840}
{"current_steps": 6045, "total_steps": 58920, "loss": 0.0531, "lr": 1.9999594544220304e-06, "epoch": 0.5129837067209776, "percentage": 10.26, "elapsed_time": "0:09:45", "remaining_time": "1:25:22", "throughput": 9905.07, "total_tokens": 5800576}
{"current_steps": 6050, "total_steps": 58920, "loss": 0.0562, "lr": 1.9999567430964442e-06, "epoch": 0.513408010862186, "percentage": 10.27, "elapsed_time": "0:09:46", "remaining_time": "1:25:21", "throughput": 9907.11, "total_tokens": 5805632}
{"current_steps": 6055, "total_steps": 58920, "loss": 0.04, "lr": 1.9999539440282643e-06, "epoch": 0.5138323150033944, "percentage": 10.28, "elapsed_time": "0:09:46", "remaining_time": "1:25:21", "throughput": 9904.77, "total_tokens": 5810688}
{"current_steps": 6060, "total_steps": 58920, "loss": 0.0958, "lr": 1.9999510572177363e-06, "epoch": 0.5142566191446029, "percentage": 10.29, "elapsed_time": "0:09:47", "remaining_time": "1:25:20", "throughput": 9906.61, "total_tokens": 5815616}
{"current_steps": 6065, "total_steps": 58920, "loss": 0.1023, "lr": 1.999948082665114e-06, "epoch": 0.5146809232858113, "percentage": 10.29, "elapsed_time": "0:09:47", "remaining_time": "1:25:19", "throughput": 9908.6, "total_tokens": 5820672}
{"current_steps": 6070, "total_steps": 58920, "loss": 0.1239, "lr": 1.9999450203706565e-06, "epoch": 0.5151052274270197, "percentage": 10.3, "elapsed_time": "0:09:47", "remaining_time": "1:25:17", "throughput": 9909.56, "total_tokens": 5824896}
{"current_steps": 6075, "total_steps": 58920, "loss": 0.0485, "lr": 1.9999418703346345e-06, "epoch": 0.5155295315682281, "percentage": 10.31, "elapsed_time": "0:09:48", "remaining_time": "1:25:16", "throughput": 9911.14, "total_tokens": 5829632}
{"current_steps": 6080, "total_steps": 58920, "loss": 0.0511, "lr": 1.9999386325573236e-06, "epoch": 0.5159538357094365, "percentage": 10.32, "elapsed_time": "0:09:48", "remaining_time": "1:25:15", "throughput": 9912.56, "total_tokens": 5834240}
{"current_steps": 6085, "total_steps": 58920, "loss": 0.0721, "lr": 1.9999353070390075e-06, "epoch": 0.516378139850645, "percentage": 10.33, "elapsed_time": "0:09:48", "remaining_time": "1:25:13", "throughput": 9913.97, "total_tokens": 5838784}
{"current_steps": 6090, "total_steps": 58920, "loss": 0.1227, "lr": 1.999931893779979e-06, "epoch": 0.5168024439918534, "percentage": 10.34, "elapsed_time": "0:09:49", "remaining_time": "1:25:12", "throughput": 9914.96, "total_tokens": 5843072}
{"current_steps": 6095, "total_steps": 58920, "loss": 0.0443, "lr": 1.9999283927805364e-06, "epoch": 0.5172267481330618, "percentage": 10.34, "elapsed_time": "0:09:49", "remaining_time": "1:25:10", "throughput": 9915.98, "total_tokens": 5847360}
{"current_steps": 6100, "total_steps": 58920, "loss": 0.0244, "lr": 1.9999248040409882e-06, "epoch": 0.5176510522742702, "percentage": 10.35, "elapsed_time": "0:09:50", "remaining_time": "1:25:09", "throughput": 9917.7, "total_tokens": 5852224}
{"current_steps": 6105, "total_steps": 58920, "loss": 0.0211, "lr": 1.9999211275616487e-06, "epoch": 0.5180753564154786, "percentage": 10.36, "elapsed_time": "0:09:50", "remaining_time": "1:25:08", "throughput": 9919.52, "total_tokens": 5857152}
{"current_steps": 6110, "total_steps": 58920, "loss": 0.1117, "lr": 1.99991736334284e-06, "epoch": 0.5184996605566871, "percentage": 10.37, "elapsed_time": "0:09:50", "remaining_time": "1:25:06", "throughput": 9921.15, "total_tokens": 5861888}
{"current_steps": 6115, "total_steps": 58920, "loss": 0.1384, "lr": 1.999913511384893e-06, "epoch": 0.5189239646978955, "percentage": 10.38, "elapsed_time": "0:09:51", "remaining_time": "1:25:05", "throughput": 9922.61, "total_tokens": 5866496}
{"current_steps": 6120, "total_steps": 58920, "loss": 0.0593, "lr": 1.999909571688146e-06, "epoch": 0.5193482688391039, "percentage": 10.39, "elapsed_time": "0:09:51", "remaining_time": "1:25:04", "throughput": 9923.77, "total_tokens": 5870912}
{"current_steps": 6125, "total_steps": 58920, "loss": 0.0953, "lr": 1.9999055442529434e-06, "epoch": 0.5197725729803123, "percentage": 10.4, "elapsed_time": "0:09:52", "remaining_time": "1:25:02", "throughput": 9926.66, "total_tokens": 5876672}
{"current_steps": 6130, "total_steps": 58920, "loss": 0.0259, "lr": 1.9999014290796403e-06, "epoch": 0.5201968771215207, "percentage": 10.4, "elapsed_time": "0:09:52", "remaining_time": "1:25:01", "throughput": 9927.67, "total_tokens": 5881024}
{"current_steps": 6135, "total_steps": 58920, "loss": 0.1808, "lr": 1.9998972261685964e-06, "epoch": 0.5206211812627292, "percentage": 10.41, "elapsed_time": "0:09:52", "remaining_time": "1:25:00", "throughput": 9929.67, "total_tokens": 5886080}
{"current_steps": 6140, "total_steps": 58920, "loss": 0.0591, "lr": 1.999892935520181e-06, "epoch": 0.5210454854039376, "percentage": 10.42, "elapsed_time": "0:09:53", "remaining_time": "1:24:58", "throughput": 9931.31, "total_tokens": 5890880}
{"current_steps": 6145, "total_steps": 58920, "loss": 0.012, "lr": 1.999888557134771e-06, "epoch": 0.521469789545146, "percentage": 10.43, "elapsed_time": "0:09:53", "remaining_time": "1:24:57", "throughput": 9932.62, "total_tokens": 5895424}
{"current_steps": 6150, "total_steps": 58920, "loss": 0.0751, "lr": 1.99988409101275e-06, "epoch": 0.5218940936863544, "percentage": 10.44, "elapsed_time": "0:09:53", "remaining_time": "1:24:56", "throughput": 9934.39, "total_tokens": 5900352}
{"current_steps": 6155, "total_steps": 58920, "loss": 0.1006, "lr": 1.9998795371545097e-06, "epoch": 0.5223183978275628, "percentage": 10.45, "elapsed_time": "0:09:54", "remaining_time": "1:24:54", "throughput": 9935.79, "total_tokens": 5904960}
{"current_steps": 6160, "total_steps": 58920, "loss": 0.0971, "lr": 1.9998748955604506e-06, "epoch": 0.5227427019687713, "percentage": 10.45, "elapsed_time": "0:09:54", "remaining_time": "1:24:53", "throughput": 9937.74, "total_tokens": 5910016}
{"current_steps": 6165, "total_steps": 58920, "loss": 0.0824, "lr": 1.999870166230979e-06, "epoch": 0.5231670061099797, "percentage": 10.46, "elapsed_time": "0:09:55", "remaining_time": "1:24:52", "throughput": 9939.55, "total_tokens": 5914944}
{"current_steps": 6170, "total_steps": 58920, "loss": 0.0613, "lr": 1.9998653491665107e-06, "epoch": 0.5235913102511881, "percentage": 10.47, "elapsed_time": "0:09:55", "remaining_time": "1:24:51", "throughput": 9942.04, "total_tokens": 5920448}
{"current_steps": 6175, "total_steps": 58920, "loss": 0.0321, "lr": 1.999860444367468e-06, "epoch": 0.5240156143923965, "percentage": 10.48, "elapsed_time": "0:09:55", "remaining_time": "1:24:49", "throughput": 9944.21, "total_tokens": 5925696}
{"current_steps": 6180, "total_steps": 58920, "loss": 0.0502, "lr": 1.9998554518342813e-06, "epoch": 0.5244399185336049, "percentage": 10.49, "elapsed_time": "0:09:56", "remaining_time": "1:24:48", "throughput": 9946.0, "total_tokens": 5930624}
{"current_steps": 6185, "total_steps": 58920, "loss": 0.0786, "lr": 1.999850371567388e-06, "epoch": 0.5248642226748133, "percentage": 10.5, "elapsed_time": "0:09:56", "remaining_time": "1:24:47", "throughput": 9947.34, "total_tokens": 5935168}
{"current_steps": 6190, "total_steps": 58920, "loss": 0.0557, "lr": 1.9998452035672356e-06, "epoch": 0.5252885268160217, "percentage": 10.51, "elapsed_time": "0:09:57", "remaining_time": "1:24:45", "throughput": 9948.68, "total_tokens": 5939712}
{"current_steps": 6195, "total_steps": 58920, "loss": 0.0357, "lr": 1.999839947834276e-06, "epoch": 0.5257128309572301, "percentage": 10.51, "elapsed_time": "0:09:57", "remaining_time": "1:24:44", "throughput": 9950.39, "total_tokens": 5944576}
{"current_steps": 6200, "total_steps": 58920, "loss": 0.0636, "lr": 1.9998346043689706e-06, "epoch": 0.5261371350984385, "percentage": 10.52, "elapsed_time": "0:09:57", "remaining_time": "1:24:43", "throughput": 9951.72, "total_tokens": 5949184}
{"current_steps": 6205, "total_steps": 58920, "loss": 0.051, "lr": 1.999829173171789e-06, "epoch": 0.5265614392396469, "percentage": 10.53, "elapsed_time": "0:09:58", "remaining_time": "1:24:41", "throughput": 9953.6, "total_tokens": 5954176}
{"current_steps": 6210, "total_steps": 58920, "loss": 0.1273, "lr": 1.999823654243207e-06, "epoch": 0.5269857433808554, "percentage": 10.54, "elapsed_time": "0:09:58", "remaining_time": "1:24:40", "throughput": 9954.85, "total_tokens": 5958656}
{"current_steps": 6215, "total_steps": 58920, "loss": 0.1188, "lr": 1.9998180475837093e-06, "epoch": 0.5274100475220638, "percentage": 10.55, "elapsed_time": "0:09:58", "remaining_time": "1:24:39", "throughput": 9956.21, "total_tokens": 5963264}
{"current_steps": 6220, "total_steps": 58920, "loss": 0.1456, "lr": 1.9998123531937877e-06, "epoch": 0.5278343516632722, "percentage": 10.56, "elapsed_time": "0:09:59", "remaining_time": "1:24:38", "throughput": 9958.44, "total_tokens": 5968576}
{"current_steps": 6225, "total_steps": 58920, "loss": 0.0116, "lr": 1.9998065710739423e-06, "epoch": 0.5282586558044806, "percentage": 10.57, "elapsed_time": "0:09:59", "remaining_time": "1:24:36", "throughput": 9959.93, "total_tokens": 5973248}
{"current_steps": 6230, "total_steps": 58920, "loss": 0.0503, "lr": 1.9998007012246795e-06, "epoch": 0.528682959945689, "percentage": 10.57, "elapsed_time": "0:10:00", "remaining_time": "1:24:35", "throughput": 9961.32, "total_tokens": 5977920}
{"current_steps": 6235, "total_steps": 58920, "loss": 0.0747, "lr": 1.9997947436465153e-06, "epoch": 0.5291072640868975, "percentage": 10.58, "elapsed_time": "0:10:00", "remaining_time": "1:24:34", "throughput": 9962.8, "total_tokens": 5982656}
{"current_steps": 6240, "total_steps": 58920, "loss": 0.085, "lr": 1.999788698339972e-06, "epoch": 0.5295315682281059, "percentage": 10.59, "elapsed_time": "0:10:00", "remaining_time": "1:24:32", "throughput": 9964.31, "total_tokens": 5987392}
{"current_steps": 6245, "total_steps": 58920, "loss": 0.0656, "lr": 1.9997825653055803e-06, "epoch": 0.5299558723693143, "percentage": 10.6, "elapsed_time": "0:10:01", "remaining_time": "1:24:31", "throughput": 9967.3, "total_tokens": 5993280}
{"current_steps": 6250, "total_steps": 58920, "loss": 0.0325, "lr": 1.999776344543878e-06, "epoch": 0.5303801765105227, "percentage": 10.61, "elapsed_time": "0:10:01", "remaining_time": "1:24:30", "throughput": 9969.09, "total_tokens": 5998272}
{"current_steps": 6255, "total_steps": 58920, "loss": 0.0565, "lr": 1.9997700360554112e-06, "epoch": 0.5308044806517311, "percentage": 10.62, "elapsed_time": "0:10:02", "remaining_time": "1:24:29", "throughput": 9970.32, "total_tokens": 6002816}
{"current_steps": 6260, "total_steps": 58920, "loss": 0.027, "lr": 1.9997636398407334e-06, "epoch": 0.5312287847929396, "percentage": 10.62, "elapsed_time": "0:10:02", "remaining_time": "1:24:27", "throughput": 9972.09, "total_tokens": 6007744}
{"current_steps": 6265, "total_steps": 58920, "loss": 0.071, "lr": 1.9997571559004058e-06, "epoch": 0.531653088934148, "percentage": 10.63, "elapsed_time": "0:10:02", "remaining_time": "1:24:26", "throughput": 9972.65, "total_tokens": 6011776}
{"current_steps": 6270, "total_steps": 58920, "loss": 0.1191, "lr": 1.9997505842349972e-06, "epoch": 0.5320773930753564, "percentage": 10.64, "elapsed_time": "0:10:03", "remaining_time": "1:24:25", "throughput": 9975.12, "total_tokens": 6017344}
{"current_steps": 6275, "total_steps": 58920, "loss": 0.0538, "lr": 1.999743924845085e-06, "epoch": 0.5325016972165648, "percentage": 10.65, "elapsed_time": "0:10:03", "remaining_time": "1:24:24", "throughput": 9976.68, "total_tokens": 6022144}
{"current_steps": 6280, "total_steps": 58920, "loss": 0.0275, "lr": 1.999737177731252e-06, "epoch": 0.5329260013577732, "percentage": 10.66, "elapsed_time": "0:10:04", "remaining_time": "1:24:23", "throughput": 9979.23, "total_tokens": 6027712}
{"current_steps": 6285, "total_steps": 58920, "loss": 0.082, "lr": 1.9997303428940922e-06, "epoch": 0.5333503054989817, "percentage": 10.67, "elapsed_time": "0:10:04", "remaining_time": "1:24:21", "throughput": 9980.15, "total_tokens": 6032064}
{"current_steps": 6290, "total_steps": 58920, "loss": 0.0354, "lr": 1.9997234203342036e-06, "epoch": 0.5337746096401901, "percentage": 10.68, "elapsed_time": "0:10:04", "remaining_time": "1:24:20", "throughput": 9981.01, "total_tokens": 6036288}
{"current_steps": 6295, "total_steps": 58920, "loss": 0.1078, "lr": 1.9997164100521947e-06, "epoch": 0.5341989137813985, "percentage": 10.68, "elapsed_time": "0:10:05", "remaining_time": "1:24:18", "throughput": 9982.48, "total_tokens": 6040960}
{"current_steps": 6300, "total_steps": 58920, "loss": 0.0659, "lr": 1.9997093120486803e-06, "epoch": 0.5346232179226069, "percentage": 10.69, "elapsed_time": "0:10:05", "remaining_time": "1:24:17", "throughput": 9983.54, "total_tokens": 6045376}
{"current_steps": 6305, "total_steps": 58920, "loss": 0.0916, "lr": 1.999702126324283e-06, "epoch": 0.5350475220638153, "percentage": 10.7, "elapsed_time": "0:10:05", "remaining_time": "1:24:16", "throughput": 9984.71, "total_tokens": 6049856}
{"current_steps": 6310, "total_steps": 58920, "loss": 0.0356, "lr": 1.9996948528796336e-06, "epoch": 0.5354718262050238, "percentage": 10.71, "elapsed_time": "0:10:06", "remaining_time": "1:24:14", "throughput": 9985.63, "total_tokens": 6054144}
{"current_steps": 6315, "total_steps": 58920, "loss": 0.0269, "lr": 1.9996874917153703e-06, "epoch": 0.5358961303462322, "percentage": 10.72, "elapsed_time": "0:10:06", "remaining_time": "1:24:13", "throughput": 9988.51, "total_tokens": 6060032}
{"current_steps": 6320, "total_steps": 58920, "loss": 0.1489, "lr": 1.999680042832139e-06, "epoch": 0.5363204344874406, "percentage": 10.73, "elapsed_time": "0:10:07", "remaining_time": "1:24:12", "throughput": 9990.53, "total_tokens": 6065280}
{"current_steps": 6325, "total_steps": 58920, "loss": 0.1127, "lr": 1.9996725062305934e-06, "epoch": 0.536744738628649, "percentage": 10.73, "elapsed_time": "0:10:07", "remaining_time": "1:24:11", "throughput": 9992.03, "total_tokens": 6070080}
{"current_steps": 6330, "total_steps": 58920, "loss": 0.065, "lr": 1.9996648819113944e-06, "epoch": 0.5371690427698574, "percentage": 10.74, "elapsed_time": "0:10:07", "remaining_time": "1:24:10", "throughput": 9994.99, "total_tokens": 6076032}
{"current_steps": 6335, "total_steps": 58920, "loss": 0.06, "lr": 1.9996571698752117e-06, "epoch": 0.5375933469110659, "percentage": 10.75, "elapsed_time": "0:10:08", "remaining_time": "1:24:09", "throughput": 9996.39, "total_tokens": 6080768}
{"current_steps": 6340, "total_steps": 58920, "loss": 0.0467, "lr": 1.999649370122721e-06, "epoch": 0.5380176510522743, "percentage": 10.76, "elapsed_time": "0:10:08", "remaining_time": "1:24:07", "throughput": 9997.64, "total_tokens": 6085312}
{"current_steps": 6345, "total_steps": 58920, "loss": 0.0267, "lr": 1.9996414826546076e-06, "epoch": 0.5384419551934827, "percentage": 10.77, "elapsed_time": "0:10:09", "remaining_time": "1:24:06", "throughput": 9999.11, "total_tokens": 6090048}
{"current_steps": 6350, "total_steps": 58920, "loss": 0.1028, "lr": 1.999633507471563e-06, "epoch": 0.5388662593346911, "percentage": 10.78, "elapsed_time": "0:10:09", "remaining_time": "1:24:05", "throughput": 10000.43, "total_tokens": 6094720}
{"current_steps": 6355, "total_steps": 58920, "loss": 0.0905, "lr": 1.9996254445742878e-06, "epoch": 0.5392905634758995, "percentage": 10.79, "elapsed_time": "0:10:09", "remaining_time": "1:24:04", "throughput": 10001.83, "total_tokens": 6099456}
{"current_steps": 6360, "total_steps": 58920, "loss": 0.0268, "lr": 1.999617293963489e-06, "epoch": 0.539714867617108, "percentage": 10.79, "elapsed_time": "0:10:10", "remaining_time": "1:24:03", "throughput": 10003.34, "total_tokens": 6104448}
{"current_steps": 6365, "total_steps": 58920, "loss": 0.0249, "lr": 1.999609055639881e-06, "epoch": 0.5401391717583164, "percentage": 10.8, "elapsed_time": "0:10:10", "remaining_time": "1:24:01", "throughput": 10004.57, "total_tokens": 6109056}
{"current_steps": 6370, "total_steps": 58920, "loss": 0.1074, "lr": 1.999600729604188e-06, "epoch": 0.5405634758995248, "percentage": 10.81, "elapsed_time": "0:10:11", "remaining_time": "1:24:00", "throughput": 10006.88, "total_tokens": 6114496}
{"current_steps": 6375, "total_steps": 58920, "loss": 0.1076, "lr": 1.9995923158571402e-06, "epoch": 0.5409877800407332, "percentage": 10.82, "elapsed_time": "0:10:11", "remaining_time": "1:23:59", "throughput": 10008.42, "total_tokens": 6119360}
{"current_steps": 6380, "total_steps": 58920, "loss": 0.1263, "lr": 1.9995838143994754e-06, "epoch": 0.5414120841819416, "percentage": 10.83, "elapsed_time": "0:10:11", "remaining_time": "1:23:58", "throughput": 10010.2, "total_tokens": 6124352}
{"current_steps": 6385, "total_steps": 58920, "loss": 0.0232, "lr": 1.9995752252319398e-06, "epoch": 0.5418363883231501, "percentage": 10.84, "elapsed_time": "0:10:12", "remaining_time": "1:23:57", "throughput": 10011.35, "total_tokens": 6128832}
{"current_steps": 6390, "total_steps": 58920, "loss": 0.0619, "lr": 1.999566548355287e-06, "epoch": 0.5422606924643585, "percentage": 10.85, "elapsed_time": "0:10:12", "remaining_time": "1:23:55", "throughput": 10012.51, "total_tokens": 6133312}
{"current_steps": 6395, "total_steps": 58920, "loss": 0.1077, "lr": 1.9995577837702792e-06, "epoch": 0.5426849966055669, "percentage": 10.85, "elapsed_time": "0:10:12", "remaining_time": "1:23:54", "throughput": 10013.35, "total_tokens": 6137600}
{"current_steps": 6400, "total_steps": 58920, "loss": 0.0654, "lr": 1.999548931477684e-06, "epoch": 0.5431093007467753, "percentage": 10.86, "elapsed_time": "0:10:13", "remaining_time": "1:23:53", "throughput": 10014.93, "total_tokens": 6142464}
{"current_steps": 6405, "total_steps": 58920, "loss": 0.0648, "lr": 1.9995399914782793e-06, "epoch": 0.5435336048879837, "percentage": 10.87, "elapsed_time": "0:10:13", "remaining_time": "1:23:51", "throughput": 10016.24, "total_tokens": 6147072}
{"current_steps": 6410, "total_steps": 58920, "loss": 0.0496, "lr": 1.9995309637728492e-06, "epoch": 0.5439579090291922, "percentage": 10.88, "elapsed_time": "0:10:14", "remaining_time": "1:23:50", "throughput": 10017.59, "total_tokens": 6151744}
{"current_steps": 6415, "total_steps": 58920, "loss": 0.1224, "lr": 1.9995218483621855e-06, "epoch": 0.5443822131704006, "percentage": 10.89, "elapsed_time": "0:10:14", "remaining_time": "1:23:49", "throughput": 10019.3, "total_tokens": 6156672}
{"current_steps": 6420, "total_steps": 58920, "loss": 0.0671, "lr": 1.999512645247089e-06, "epoch": 0.544806517311609, "percentage": 10.9, "elapsed_time": "0:10:14", "remaining_time": "1:23:48", "throughput": 10020.91, "total_tokens": 6161600}
{"current_steps": 6425, "total_steps": 58920, "loss": 0.0494, "lr": 1.999503354428366e-06, "epoch": 0.5452308214528174, "percentage": 10.9, "elapsed_time": "0:10:15", "remaining_time": "1:23:46", "throughput": 10021.59, "total_tokens": 6165760}
{"current_steps": 6430, "total_steps": 58920, "loss": 0.0202, "lr": 1.999493975906832e-06, "epoch": 0.5456551255940258, "percentage": 10.91, "elapsed_time": "0:10:15", "remaining_time": "1:23:46", "throughput": 10028.24, "total_tokens": 6174912}
{"current_steps": 6435, "total_steps": 58920, "loss": 0.0751, "lr": 1.9994845096833113e-06, "epoch": 0.5460794297352343, "percentage": 10.92, "elapsed_time": "0:10:16", "remaining_time": "1:23:45", "throughput": 10029.03, "total_tokens": 6179136}
{"current_steps": 6440, "total_steps": 58920, "loss": 0.1663, "lr": 1.999474955758633e-06, "epoch": 0.5465037338764427, "percentage": 10.93, "elapsed_time": "0:10:16", "remaining_time": "1:23:44", "throughput": 10030.02, "total_tokens": 6183680}
{"current_steps": 6445, "total_steps": 58920, "loss": 0.0685, "lr": 1.999465314133636e-06, "epoch": 0.546928038017651, "percentage": 10.94, "elapsed_time": "0:10:16", "remaining_time": "1:23:42", "throughput": 10031.69, "total_tokens": 6188608}
{"current_steps": 6450, "total_steps": 58920, "loss": 0.0584, "lr": 1.9994555848091662e-06, "epoch": 0.5473523421588594, "percentage": 10.95, "elapsed_time": "0:10:17", "remaining_time": "1:23:41", "throughput": 10033.46, "total_tokens": 6193600}
{"current_steps": 6455, "total_steps": 58920, "loss": 0.0447, "lr": 1.999445767786077e-06, "epoch": 0.5477766463000678, "percentage": 10.96, "elapsed_time": "0:10:17", "remaining_time": "1:23:40", "throughput": 10035.15, "total_tokens": 6198528}
{"current_steps": 6460, "total_steps": 58920, "loss": 0.0567, "lr": 1.999435863065231e-06, "epoch": 0.5482009504412763, "percentage": 10.96, "elapsed_time": "0:10:18", "remaining_time": "1:23:39", "throughput": 10037.56, "total_tokens": 6204096}
{"current_steps": 6465, "total_steps": 58920, "loss": 0.0295, "lr": 1.9994258706474956e-06, "epoch": 0.5486252545824847, "percentage": 10.97, "elapsed_time": "0:10:18", "remaining_time": "1:23:38", "throughput": 10038.78, "total_tokens": 6208704}
{"current_steps": 6470, "total_steps": 58920, "loss": 0.1037, "lr": 1.999415790533749e-06, "epoch": 0.5490495587236931, "percentage": 10.98, "elapsed_time": "0:10:18", "remaining_time": "1:23:36", "throughput": 10040.19, "total_tokens": 6213440}
{"current_steps": 6475, "total_steps": 58920, "loss": 0.0208, "lr": 1.999405622724875e-06, "epoch": 0.5494738628649015, "percentage": 10.99, "elapsed_time": "0:10:19", "remaining_time": "1:23:35", "throughput": 10041.86, "total_tokens": 6218368}
{"current_steps": 6480, "total_steps": 58920, "loss": 0.11, "lr": 1.9993953672217656e-06, "epoch": 0.5498981670061099, "percentage": 11.0, "elapsed_time": "0:10:19", "remaining_time": "1:23:34", "throughput": 10043.85, "total_tokens": 6223616}
{"current_steps": 6485, "total_steps": 58920, "loss": 0.1082, "lr": 1.9993850240253214e-06, "epoch": 0.5503224711473184, "percentage": 11.01, "elapsed_time": "0:10:20", "remaining_time": "1:23:33", "throughput": 10045.39, "total_tokens": 6228480}
{"current_steps": 6490, "total_steps": 58920, "loss": 0.0562, "lr": 1.9993745931364497e-06, "epoch": 0.5507467752885268, "percentage": 11.01, "elapsed_time": "0:10:20", "remaining_time": "1:23:32", "throughput": 10046.39, "total_tokens": 6232896}
{"current_steps": 6495, "total_steps": 58920, "loss": 0.1146, "lr": 1.9993640745560655e-06, "epoch": 0.5511710794297352, "percentage": 11.02, "elapsed_time": "0:10:20", "remaining_time": "1:23:30", "throughput": 10047.69, "total_tokens": 6237696}
{"current_steps": 6500, "total_steps": 58920, "loss": 0.0324, "lr": 1.999353468285092e-06, "epoch": 0.5515953835709436, "percentage": 11.03, "elapsed_time": "0:10:21", "remaining_time": "1:23:29", "throughput": 10049.02, "total_tokens": 6242304}
{"current_steps": 6505, "total_steps": 58920, "loss": 0.0358, "lr": 1.99934277432446e-06, "epoch": 0.552019687712152, "percentage": 11.04, "elapsed_time": "0:10:21", "remaining_time": "1:23:28", "throughput": 10050.45, "total_tokens": 6246976}
{"current_steps": 6510, "total_steps": 58920, "loss": 0.0819, "lr": 1.999331992675107e-06, "epoch": 0.5524439918533605, "percentage": 11.05, "elapsed_time": "0:10:21", "remaining_time": "1:23:26", "throughput": 10051.33, "total_tokens": 6251264}
{"current_steps": 6515, "total_steps": 58920, "loss": 0.017, "lr": 1.9993211233379803e-06, "epoch": 0.5528682959945689, "percentage": 11.06, "elapsed_time": "0:10:22", "remaining_time": "1:23:25", "throughput": 10052.57, "total_tokens": 6255872}
{"current_steps": 6520, "total_steps": 58920, "loss": 0.0553, "lr": 1.999310166314033e-06, "epoch": 0.5532926001357773, "percentage": 11.07, "elapsed_time": "0:10:22", "remaining_time": "1:23:24", "throughput": 10054.42, "total_tokens": 6260928}
{"current_steps": 6525, "total_steps": 58920, "loss": 0.0269, "lr": 1.9992991216042265e-06, "epoch": 0.5537169042769857, "percentage": 11.07, "elapsed_time": "0:10:23", "remaining_time": "1:23:23", "throughput": 10055.75, "total_tokens": 6265600}
{"current_steps": 6530, "total_steps": 58920, "loss": 0.1644, "lr": 1.99928798920953e-06, "epoch": 0.5541412084181941, "percentage": 11.08, "elapsed_time": "0:10:23", "remaining_time": "1:23:22", "throughput": 10057.3, "total_tokens": 6270464}
{"current_steps": 6535, "total_steps": 58920, "loss": 0.1423, "lr": 1.9992767691309203e-06, "epoch": 0.5545655125594026, "percentage": 11.09, "elapsed_time": "0:10:23", "remaining_time": "1:23:20", "throughput": 10058.3, "total_tokens": 6274944}
{"current_steps": 6540, "total_steps": 58920, "loss": 0.0724, "lr": 1.9992654613693826e-06, "epoch": 0.554989816700611, "percentage": 11.1, "elapsed_time": "0:10:24", "remaining_time": "1:23:19", "throughput": 10059.36, "total_tokens": 6279424}
{"current_steps": 6545, "total_steps": 58920, "loss": 0.1581, "lr": 1.999254065925908e-06, "epoch": 0.5554141208418194, "percentage": 11.11, "elapsed_time": "0:10:24", "remaining_time": "1:23:18", "throughput": 10060.65, "total_tokens": 6284096}
{"current_steps": 6550, "total_steps": 58920, "loss": 0.0379, "lr": 1.9992425828014964e-06, "epoch": 0.5558384249830278, "percentage": 11.12, "elapsed_time": "0:10:25", "remaining_time": "1:23:17", "throughput": 10063.05, "total_tokens": 6289728}
{"current_steps": 6555, "total_steps": 58920, "loss": 0.0257, "lr": 1.9992310119971566e-06, "epoch": 0.5562627291242362, "percentage": 11.13, "elapsed_time": "0:10:25", "remaining_time": "1:23:16", "throughput": 10064.4, "total_tokens": 6294400}
{"current_steps": 6560, "total_steps": 58920, "loss": 0.0373, "lr": 1.999219353513903e-06, "epoch": 0.5566870332654447, "percentage": 11.13, "elapsed_time": "0:10:25", "remaining_time": "1:23:14", "throughput": 10065.47, "total_tokens": 6298880}
{"current_steps": 6565, "total_steps": 58920, "loss": 0.0717, "lr": 1.9992076073527588e-06, "epoch": 0.5571113374066531, "percentage": 11.14, "elapsed_time": "0:10:26", "remaining_time": "1:23:13", "throughput": 10066.56, "total_tokens": 6303424}
{"current_steps": 6570, "total_steps": 58920, "loss": 0.0706, "lr": 1.9991957735147547e-06, "epoch": 0.5575356415478615, "percentage": 11.15, "elapsed_time": "0:10:26", "remaining_time": "1:23:12", "throughput": 10067.79, "total_tokens": 6308032}
{"current_steps": 6575, "total_steps": 58920, "loss": 0.0431, "lr": 1.9991838520009293e-06, "epoch": 0.5579599456890699, "percentage": 11.16, "elapsed_time": "0:10:26", "remaining_time": "1:23:11", "throughput": 10069.29, "total_tokens": 6312832}
{"current_steps": 6580, "total_steps": 58920, "loss": 0.0493, "lr": 1.9991718428123283e-06, "epoch": 0.5583842498302783, "percentage": 11.17, "elapsed_time": "0:10:27", "remaining_time": "1:23:09", "throughput": 10070.38, "total_tokens": 6317312}
{"current_steps": 6585, "total_steps": 58920, "loss": 0.0424, "lr": 1.9991597459500053e-06, "epoch": 0.5588085539714868, "percentage": 11.18, "elapsed_time": "0:10:27", "remaining_time": "1:23:08", "throughput": 10071.57, "total_tokens": 6321920}
{"current_steps": 6590, "total_steps": 58920, "loss": 0.1273, "lr": 1.999147561415022e-06, "epoch": 0.5592328581126952, "percentage": 11.18, "elapsed_time": "0:10:28", "remaining_time": "1:23:07", "throughput": 10072.57, "total_tokens": 6326336}
{"current_steps": 6595, "total_steps": 58920, "loss": 0.1, "lr": 1.999135289208448e-06, "epoch": 0.5596571622539036, "percentage": 11.19, "elapsed_time": "0:10:28", "remaining_time": "1:23:06", "throughput": 10073.82, "total_tokens": 6331008}
{"current_steps": 6600, "total_steps": 58920, "loss": 0.102, "lr": 1.99912292933136e-06, "epoch": 0.560081466395112, "percentage": 11.2, "elapsed_time": "0:10:28", "remaining_time": "1:23:05", "throughput": 10075.17, "total_tokens": 6335744}
{"current_steps": 6605, "total_steps": 58920, "loss": 0.0538, "lr": 1.9991104817848415e-06, "epoch": 0.5605057705363204, "percentage": 11.21, "elapsed_time": "0:10:29", "remaining_time": "1:23:03", "throughput": 10076.93, "total_tokens": 6340736}
{"current_steps": 6610, "total_steps": 58920, "loss": 0.0953, "lr": 1.999097946569986e-06, "epoch": 0.5609300746775289, "percentage": 11.22, "elapsed_time": "0:10:29", "remaining_time": "1:23:02", "throughput": 10078.03, "total_tokens": 6345216}
{"current_steps": 6615, "total_steps": 58920, "loss": 0.0442, "lr": 1.9990853236878923e-06, "epoch": 0.5613543788187373, "percentage": 11.23, "elapsed_time": "0:10:29", "remaining_time": "1:23:01", "throughput": 10079.58, "total_tokens": 6350080}
{"current_steps": 6620, "total_steps": 58920, "loss": 0.0495, "lr": 1.999072613139669e-06, "epoch": 0.5617786829599457, "percentage": 11.24, "elapsed_time": "0:10:30", "remaining_time": "1:23:00", "throughput": 10081.06, "total_tokens": 6354816}
{"current_steps": 6625, "total_steps": 58920, "loss": 0.0809, "lr": 1.9990598149264315e-06, "epoch": 0.5622029871011541, "percentage": 11.24, "elapsed_time": "0:10:30", "remaining_time": "1:22:59", "throughput": 10082.98, "total_tokens": 6360000}
{"current_steps": 6630, "total_steps": 58920, "loss": 0.1232, "lr": 1.9990469290493017e-06, "epoch": 0.5626272912423625, "percentage": 11.25, "elapsed_time": "0:10:31", "remaining_time": "1:22:57", "throughput": 10084.26, "total_tokens": 6364672}
{"current_steps": 6635, "total_steps": 58920, "loss": 0.0852, "lr": 1.9990339555094114e-06, "epoch": 0.563051595383571, "percentage": 11.26, "elapsed_time": "0:10:31", "remaining_time": "1:22:56", "throughput": 10085.52, "total_tokens": 6369408}
{"current_steps": 6640, "total_steps": 58920, "loss": 0.048, "lr": 1.999020894307898e-06, "epoch": 0.5634758995247794, "percentage": 11.27, "elapsed_time": "0:10:31", "remaining_time": "1:22:55", "throughput": 10086.86, "total_tokens": 6374080}
{"current_steps": 6645, "total_steps": 58920, "loss": 0.0583, "lr": 1.9990077454459085e-06, "epoch": 0.5639002036659878, "percentage": 11.28, "elapsed_time": "0:10:32", "remaining_time": "1:22:54", "throughput": 10088.71, "total_tokens": 6379200}
{"current_steps": 6650, "total_steps": 58920, "loss": 0.0501, "lr": 1.998994508924596e-06, "epoch": 0.5643245078071962, "percentage": 11.29, "elapsed_time": "0:10:32", "remaining_time": "1:22:53", "throughput": 10090.87, "total_tokens": 6384576}
{"current_steps": 6655, "total_steps": 58920, "loss": 0.0855, "lr": 1.9989811847451224e-06, "epoch": 0.5647488119484046, "percentage": 11.29, "elapsed_time": "0:10:33", "remaining_time": "1:22:52", "throughput": 10092.79, "total_tokens": 6389760}
{"current_steps": 6660, "total_steps": 58920, "loss": 0.0656, "lr": 1.9989677729086565e-06, "epoch": 0.5651731160896131, "percentage": 11.3, "elapsed_time": "0:10:33", "remaining_time": "1:22:50", "throughput": 10093.79, "total_tokens": 6394176}
{"current_steps": 6665, "total_steps": 58920, "loss": 0.0809, "lr": 1.998954273416375e-06, "epoch": 0.5655974202308215, "percentage": 11.31, "elapsed_time": "0:10:33", "remaining_time": "1:22:49", "throughput": 10095.32, "total_tokens": 6398976}
{"current_steps": 6670, "total_steps": 58920, "loss": 0.0255, "lr": 1.9989406862694632e-06, "epoch": 0.5660217243720299, "percentage": 11.32, "elapsed_time": "0:10:34", "remaining_time": "1:22:48", "throughput": 10096.12, "total_tokens": 6403264}
{"current_steps": 6675, "total_steps": 58920, "loss": 0.0778, "lr": 1.998927011469113e-06, "epoch": 0.5664460285132383, "percentage": 11.33, "elapsed_time": "0:10:34", "remaining_time": "1:22:47", "throughput": 10097.68, "total_tokens": 6408128}
{"current_steps": 6680, "total_steps": 58920, "loss": 0.0867, "lr": 1.9989132490165236e-06, "epoch": 0.5668703326544468, "percentage": 11.34, "elapsed_time": "0:10:34", "remaining_time": "1:22:45", "throughput": 10098.81, "total_tokens": 6412672}
{"current_steps": 6685, "total_steps": 58920, "loss": 0.0747, "lr": 1.998899398912903e-06, "epoch": 0.5672946367956552, "percentage": 11.35, "elapsed_time": "0:10:35", "remaining_time": "1:22:44", "throughput": 10099.82, "total_tokens": 6417088}
{"current_steps": 6690, "total_steps": 58920, "loss": 0.0953, "lr": 1.9988854611594676e-06, "epoch": 0.5677189409368636, "percentage": 11.35, "elapsed_time": "0:10:35", "remaining_time": "1:22:43", "throughput": 10101.21, "total_tokens": 6421824}
{"current_steps": 6695, "total_steps": 58920, "loss": 0.0501, "lr": 1.9988714357574387e-06, "epoch": 0.568143245078072, "percentage": 11.36, "elapsed_time": "0:10:36", "remaining_time": "1:22:42", "throughput": 10102.56, "total_tokens": 6426560}
{"current_steps": 6700, "total_steps": 58920, "loss": 0.1365, "lr": 1.998857322708048e-06, "epoch": 0.5685675492192804, "percentage": 11.37, "elapsed_time": "0:10:36", "remaining_time": "1:22:41", "throughput": 10103.43, "total_tokens": 6431040}
{"current_steps": 6705, "total_steps": 58920, "loss": 0.0708, "lr": 1.9988431220125333e-06, "epoch": 0.5689918533604889, "percentage": 11.38, "elapsed_time": "0:10:36", "remaining_time": "1:22:39", "throughput": 10105.06, "total_tokens": 6435968}
{"current_steps": 6710, "total_steps": 58920, "loss": 0.0874, "lr": 1.998828833672141e-06, "epoch": 0.5694161575016972, "percentage": 11.39, "elapsed_time": "0:10:37", "remaining_time": "1:22:38", "throughput": 10106.31, "total_tokens": 6440640}
{"current_steps": 6715, "total_steps": 58920, "loss": 0.0504, "lr": 1.998814457688125e-06, "epoch": 0.5698404616429056, "percentage": 11.4, "elapsed_time": "0:10:37", "remaining_time": "1:22:37", "throughput": 10107.8, "total_tokens": 6445504}
{"current_steps": 6720, "total_steps": 58920, "loss": 0.0426, "lr": 1.9987999940617466e-06, "epoch": 0.570264765784114, "percentage": 11.41, "elapsed_time": "0:10:38", "remaining_time": "1:22:36", "throughput": 10108.37, "total_tokens": 6449600}
{"current_steps": 6725, "total_steps": 58920, "loss": 0.0563, "lr": 1.998785442794275e-06, "epoch": 0.5706890699253224, "percentage": 11.41, "elapsed_time": "0:10:38", "remaining_time": "1:22:35", "throughput": 10110.0, "total_tokens": 6454528}
{"current_steps": 6730, "total_steps": 58920, "loss": 0.0816, "lr": 1.9987708038869865e-06, "epoch": 0.5711133740665308, "percentage": 11.42, "elapsed_time": "0:10:38", "remaining_time": "1:22:33", "throughput": 10111.41, "total_tokens": 6459264}
{"current_steps": 6735, "total_steps": 58920, "loss": 0.0615, "lr": 1.998756077341166e-06, "epoch": 0.5715376782077393, "percentage": 11.43, "elapsed_time": "0:10:39", "remaining_time": "1:22:32", "throughput": 10112.18, "total_tokens": 6463552}
{"current_steps": 6740, "total_steps": 58920, "loss": 0.0057, "lr": 1.9987412631581058e-06, "epoch": 0.5719619823489477, "percentage": 11.44, "elapsed_time": "0:10:39", "remaining_time": "1:22:31", "throughput": 10113.91, "total_tokens": 6468608}
{"current_steps": 6745, "total_steps": 58920, "loss": 0.0588, "lr": 1.998726361339106e-06, "epoch": 0.5723862864901561, "percentage": 11.45, "elapsed_time": "0:10:39", "remaining_time": "1:22:30", "throughput": 10115.4, "total_tokens": 6473408}
{"current_steps": 6750, "total_steps": 58920, "loss": 0.0573, "lr": 1.9987113718854737e-06, "epoch": 0.5728105906313645, "percentage": 11.46, "elapsed_time": "0:10:40", "remaining_time": "1:22:29", "throughput": 10117.41, "total_tokens": 6478656}
{"current_steps": 6755, "total_steps": 58920, "loss": 0.1476, "lr": 1.998696294798524e-06, "epoch": 0.573234894772573, "percentage": 11.46, "elapsed_time": "0:10:40", "remaining_time": "1:22:28", "throughput": 10118.62, "total_tokens": 6483328}
{"current_steps": 6760, "total_steps": 58920, "loss": 0.0076, "lr": 1.998681130079581e-06, "epoch": 0.5736591989137814, "percentage": 11.47, "elapsed_time": "0:10:41", "remaining_time": "1:22:26", "throughput": 10119.97, "total_tokens": 6488064}
{"current_steps": 6765, "total_steps": 58920, "loss": 0.1889, "lr": 1.998665877729974e-06, "epoch": 0.5740835030549898, "percentage": 11.48, "elapsed_time": "0:10:41", "remaining_time": "1:22:25", "throughput": 10121.48, "total_tokens": 6492864}
{"current_steps": 6770, "total_steps": 58920, "loss": 0.0551, "lr": 1.9986505377510417e-06, "epoch": 0.5745078071961982, "percentage": 11.49, "elapsed_time": "0:10:41", "remaining_time": "1:22:24", "throughput": 10122.37, "total_tokens": 6497216}
{"current_steps": 6775, "total_steps": 58920, "loss": 0.0397, "lr": 1.9986351101441306e-06, "epoch": 0.5749321113374066, "percentage": 11.5, "elapsed_time": "0:10:42", "remaining_time": "1:22:23", "throughput": 10123.7, "total_tokens": 6501888}
{"current_steps": 6780, "total_steps": 58920, "loss": 0.1027, "lr": 1.9986195949105942e-06, "epoch": 0.575356415478615, "percentage": 11.51, "elapsed_time": "0:10:42", "remaining_time": "1:22:22", "throughput": 10125.74, "total_tokens": 6507200}
{"current_steps": 6785, "total_steps": 58920, "loss": 0.0483, "lr": 1.998603992051794e-06, "epoch": 0.5757807196198235, "percentage": 11.52, "elapsed_time": "0:10:43", "remaining_time": "1:22:21", "throughput": 10131.22, "total_tokens": 6515840}
{"current_steps": 6790, "total_steps": 58920, "loss": 0.1074, "lr": 1.998588301569098e-06, "epoch": 0.5762050237610319, "percentage": 11.52, "elapsed_time": "0:10:43", "remaining_time": "1:22:20", "throughput": 10132.3, "total_tokens": 6520384}
{"current_steps": 6795, "total_steps": 58920, "loss": 0.0709, "lr": 1.9985725234638854e-06, "epoch": 0.5766293279022403, "percentage": 11.53, "elapsed_time": "0:10:43", "remaining_time": "1:22:19", "throughput": 10133.53, "total_tokens": 6524992}
{"current_steps": 6800, "total_steps": 58920, "loss": 0.0915, "lr": 1.9985566577375383e-06, "epoch": 0.5770536320434487, "percentage": 11.54, "elapsed_time": "0:10:44", "remaining_time": "1:22:18", "throughput": 10137.66, "total_tokens": 6532160}
{"current_steps": 6805, "total_steps": 58920, "loss": 0.0298, "lr": 1.9985407043914498e-06, "epoch": 0.5774779361846571, "percentage": 11.55, "elapsed_time": "0:10:44", "remaining_time": "1:22:17", "throughput": 10138.36, "total_tokens": 6536384}
{"current_steps": 6810, "total_steps": 58920, "loss": 0.0334, "lr": 1.99852466342702e-06, "epoch": 0.5779022403258656, "percentage": 11.56, "elapsed_time": "0:10:45", "remaining_time": "1:22:16", "throughput": 10139.27, "total_tokens": 6540800}
{"current_steps": 6815, "total_steps": 58920, "loss": 0.137, "lr": 1.998508534845656e-06, "epoch": 0.578326544467074, "percentage": 11.57, "elapsed_time": "0:10:45", "remaining_time": "1:22:15", "throughput": 10140.19, "total_tokens": 6545216}
{"current_steps": 6820, "total_steps": 58920, "loss": 0.0534, "lr": 1.998492318648773e-06, "epoch": 0.5787508486082824, "percentage": 11.58, "elapsed_time": "0:10:45", "remaining_time": "1:22:13", "throughput": 10142.05, "total_tokens": 6550400}
{"current_steps": 6825, "total_steps": 58920, "loss": 0.033, "lr": 1.998476014837794e-06, "epoch": 0.5791751527494908, "percentage": 11.58, "elapsed_time": "0:10:46", "remaining_time": "1:22:12", "throughput": 10142.91, "total_tokens": 6554752}
{"current_steps": 6830, "total_steps": 58920, "loss": 0.0425, "lr": 1.99845962341415e-06, "epoch": 0.5795994568906992, "percentage": 11.59, "elapsed_time": "0:10:46", "remaining_time": "1:22:11", "throughput": 10144.4, "total_tokens": 6559616}
{"current_steps": 6835, "total_steps": 58920, "loss": 0.049, "lr": 1.998443144379279e-06, "epoch": 0.5800237610319077, "percentage": 11.6, "elapsed_time": "0:10:47", "remaining_time": "1:22:10", "throughput": 10146.04, "total_tokens": 6564608}
{"current_steps": 6840, "total_steps": 58920, "loss": 0.0251, "lr": 1.9984265777346265e-06, "epoch": 0.5804480651731161, "percentage": 11.61, "elapsed_time": "0:10:47", "remaining_time": "1:22:09", "throughput": 10147.04, "total_tokens": 6569024}
{"current_steps": 6845, "total_steps": 58920, "loss": 0.035, "lr": 1.998409923481647e-06, "epoch": 0.5808723693143245, "percentage": 11.62, "elapsed_time": "0:10:47", "remaining_time": "1:22:08", "throughput": 10148.72, "total_tokens": 6574016}
{"current_steps": 6850, "total_steps": 58920, "loss": 0.0385, "lr": 1.9983931816218017e-06, "epoch": 0.5812966734555329, "percentage": 11.63, "elapsed_time": "0:10:48", "remaining_time": "1:22:06", "throughput": 10150.26, "total_tokens": 6578944}
{"current_steps": 6855, "total_steps": 58920, "loss": 0.051, "lr": 1.9983763521565588e-06, "epoch": 0.5817209775967414, "percentage": 11.63, "elapsed_time": "0:10:48", "remaining_time": "1:22:05", "throughput": 10152.19, "total_tokens": 6584192}
{"current_steps": 6860, "total_steps": 58920, "loss": 0.0746, "lr": 1.998359435087396e-06, "epoch": 0.5821452817379498, "percentage": 11.64, "elapsed_time": "0:10:48", "remaining_time": "1:22:04", "throughput": 10153.69, "total_tokens": 6589056}
{"current_steps": 6865, "total_steps": 58920, "loss": 0.0899, "lr": 1.998342430415797e-06, "epoch": 0.5825695858791582, "percentage": 11.65, "elapsed_time": "0:10:49", "remaining_time": "1:22:03", "throughput": 10154.69, "total_tokens": 6593536}
{"current_steps": 6870, "total_steps": 58920, "loss": 0.0889, "lr": 1.9983253381432547e-06, "epoch": 0.5829938900203666, "percentage": 11.66, "elapsed_time": "0:10:49", "remaining_time": "1:22:02", "throughput": 10158.08, "total_tokens": 6600128}
{"current_steps": 6875, "total_steps": 58920, "loss": 0.0686, "lr": 1.9983081582712684e-06, "epoch": 0.583418194161575, "percentage": 11.67, "elapsed_time": "0:10:50", "remaining_time": "1:22:01", "throughput": 10159.44, "total_tokens": 6604864}
{"current_steps": 6880, "total_steps": 58920, "loss": 0.0206, "lr": 1.998290890801345e-06, "epoch": 0.5838424983027835, "percentage": 11.68, "elapsed_time": "0:10:50", "remaining_time": "1:22:00", "throughput": 10160.92, "total_tokens": 6609728}
{"current_steps": 6885, "total_steps": 58920, "loss": 0.0335, "lr": 1.998273535735001e-06, "epoch": 0.5842668024439919, "percentage": 11.69, "elapsed_time": "0:10:50", "remaining_time": "1:21:59", "throughput": 10162.91, "total_tokens": 6615104}
{"current_steps": 6890, "total_steps": 58920, "loss": 0.0377, "lr": 1.998256093073758e-06, "epoch": 0.5846911065852003, "percentage": 11.69, "elapsed_time": "0:10:51", "remaining_time": "1:21:58", "throughput": 10164.56, "total_tokens": 6620096}
{"current_steps": 6895, "total_steps": 58920, "loss": 0.1328, "lr": 1.998238562819147e-06, "epoch": 0.5851154107264087, "percentage": 11.7, "elapsed_time": "0:10:51", "remaining_time": "1:21:57", "throughput": 10165.42, "total_tokens": 6624448}
{"current_steps": 6900, "total_steps": 58920, "loss": 0.0889, "lr": 1.9982209449727063e-06, "epoch": 0.5855397148676171, "percentage": 11.71, "elapsed_time": "0:10:52", "remaining_time": "1:21:55", "throughput": 10166.31, "total_tokens": 6628800}
{"current_steps": 6905, "total_steps": 58920, "loss": 0.065, "lr": 1.998203239535982e-06, "epoch": 0.5859640190088256, "percentage": 11.72, "elapsed_time": "0:10:52", "remaining_time": "1:21:54", "throughput": 10167.8, "total_tokens": 6633664}
{"current_steps": 6910, "total_steps": 58920, "loss": 0.0928, "lr": 1.9981854465105272e-06, "epoch": 0.586388323150034, "percentage": 11.73, "elapsed_time": "0:10:52", "remaining_time": "1:21:53", "throughput": 10169.54, "total_tokens": 6638720}
{"current_steps": 6915, "total_steps": 58920, "loss": 0.0245, "lr": 1.998167565897903e-06, "epoch": 0.5868126272912424, "percentage": 11.74, "elapsed_time": "0:10:53", "remaining_time": "1:21:52", "throughput": 10170.34, "total_tokens": 6643008}
{"current_steps": 6920, "total_steps": 58920, "loss": 0.0651, "lr": 1.9981495976996795e-06, "epoch": 0.5872369314324508, "percentage": 11.74, "elapsed_time": "0:10:53", "remaining_time": "1:21:51", "throughput": 10171.2, "total_tokens": 6647360}
{"current_steps": 6925, "total_steps": 58920, "loss": 0.0406, "lr": 1.9981315419174323e-06, "epoch": 0.5876612355736592, "percentage": 11.75, "elapsed_time": "0:10:53", "remaining_time": "1:21:49", "throughput": 10172.45, "total_tokens": 6652032}
{"current_steps": 6930, "total_steps": 58920, "loss": 0.1009, "lr": 1.9981133985527463e-06, "epoch": 0.5880855397148677, "percentage": 11.76, "elapsed_time": "0:10:54", "remaining_time": "1:21:48", "throughput": 10173.24, "total_tokens": 6656320}
{"current_steps": 6935, "total_steps": 58920, "loss": 0.0573, "lr": 1.998095167607213e-06, "epoch": 0.5885098438560761, "percentage": 11.77, "elapsed_time": "0:10:54", "remaining_time": "1:21:47", "throughput": 10174.41, "total_tokens": 6660928}
{"current_steps": 6940, "total_steps": 58920, "loss": 0.0702, "lr": 1.998076849082432e-06, "epoch": 0.5889341479972845, "percentage": 11.78, "elapsed_time": "0:10:55", "remaining_time": "1:21:46", "throughput": 10175.98, "total_tokens": 6665856}
{"current_steps": 6945, "total_steps": 58920, "loss": 0.0838, "lr": 1.9980584429800114e-06, "epoch": 0.5893584521384929, "percentage": 11.79, "elapsed_time": "0:10:55", "remaining_time": "1:21:45", "throughput": 10176.75, "total_tokens": 6670144}
{"current_steps": 6950, "total_steps": 58920, "loss": 0.1138, "lr": 1.998039949301566e-06, "epoch": 0.5897827562797013, "percentage": 11.8, "elapsed_time": "0:10:55", "remaining_time": "1:21:44", "throughput": 10178.52, "total_tokens": 6675264}
{"current_steps": 6955, "total_steps": 58920, "loss": 0.1319, "lr": 1.998021368048718e-06, "epoch": 0.5902070604209098, "percentage": 11.8, "elapsed_time": "0:10:56", "remaining_time": "1:21:42", "throughput": 10179.3, "total_tokens": 6679552}
{"current_steps": 6960, "total_steps": 58920, "loss": 0.0457, "lr": 1.998002699223099e-06, "epoch": 0.5906313645621182, "percentage": 11.81, "elapsed_time": "0:10:56", "remaining_time": "1:21:41", "throughput": 10180.09, "total_tokens": 6683904}
{"current_steps": 6965, "total_steps": 58920, "loss": 0.0716, "lr": 1.997983942826346e-06, "epoch": 0.5910556687033266, "percentage": 11.82, "elapsed_time": "0:10:56", "remaining_time": "1:21:40", "throughput": 10181.06, "total_tokens": 6688320}
{"current_steps": 6970, "total_steps": 58920, "loss": 0.04, "lr": 1.997965098860105e-06, "epoch": 0.591479972844535, "percentage": 11.83, "elapsed_time": "0:10:57", "remaining_time": "1:21:39", "throughput": 10183.09, "total_tokens": 6693696}
{"current_steps": 6975, "total_steps": 58920, "loss": 0.0449, "lr": 1.9979461673260304e-06, "epoch": 0.5919042769857433, "percentage": 11.84, "elapsed_time": "0:10:57", "remaining_time": "1:21:38", "throughput": 10184.46, "total_tokens": 6698496}
{"current_steps": 6980, "total_steps": 58920, "loss": 0.0748, "lr": 1.997927148225782e-06, "epoch": 0.5923285811269517, "percentage": 11.85, "elapsed_time": "0:10:58", "remaining_time": "1:21:37", "throughput": 10186.87, "total_tokens": 6704192}
{"current_steps": 6985, "total_steps": 58920, "loss": 0.0257, "lr": 1.99790804156103e-06, "epoch": 0.5927528852681602, "percentage": 11.86, "elapsed_time": "0:10:58", "remaining_time": "1:21:36", "throughput": 10187.66, "total_tokens": 6708480}
{"current_steps": 6990, "total_steps": 58920, "loss": 0.0673, "lr": 1.9978888473334496e-06, "epoch": 0.5931771894093686, "percentage": 11.86, "elapsed_time": "0:10:58", "remaining_time": "1:21:34", "throughput": 10189.76, "total_tokens": 6713856}
{"current_steps": 6995, "total_steps": 58920, "loss": 0.1183, "lr": 1.997869565544726e-06, "epoch": 0.593601493550577, "percentage": 11.87, "elapsed_time": "0:10:59", "remaining_time": "1:21:33", "throughput": 10191.6, "total_tokens": 6719104}
{"current_steps": 7000, "total_steps": 58920, "loss": 0.065, "lr": 1.997850196196551e-06, "epoch": 0.5940257976917854, "percentage": 11.88, "elapsed_time": "0:10:59", "remaining_time": "1:21:32", "throughput": 10192.3, "total_tokens": 6723328}
{"current_steps": 7005, "total_steps": 58920, "loss": 0.0431, "lr": 1.9978307392906238e-06, "epoch": 0.5944501018329938, "percentage": 11.89, "elapsed_time": "0:11:00", "remaining_time": "1:21:31", "throughput": 10193.62, "total_tokens": 6728064}
{"current_steps": 7010, "total_steps": 58920, "loss": 0.1119, "lr": 1.997811194828652e-06, "epoch": 0.5948744059742023, "percentage": 11.9, "elapsed_time": "0:11:00", "remaining_time": "1:21:30", "throughput": 10194.99, "total_tokens": 6732864}
{"current_steps": 7015, "total_steps": 58920, "loss": 0.0281, "lr": 1.99779156281235e-06, "epoch": 0.5952987101154107, "percentage": 11.91, "elapsed_time": "0:11:00", "remaining_time": "1:21:29", "throughput": 10196.53, "total_tokens": 6737792}
{"current_steps": 7020, "total_steps": 58920, "loss": 0.0537, "lr": 1.9977718432434413e-06, "epoch": 0.5957230142566191, "percentage": 11.91, "elapsed_time": "0:11:01", "remaining_time": "1:21:28", "throughput": 10198.25, "total_tokens": 6742848}
{"current_steps": 7025, "total_steps": 58920, "loss": 0.0902, "lr": 1.997752036123656e-06, "epoch": 0.5961473183978275, "percentage": 11.92, "elapsed_time": "0:11:01", "remaining_time": "1:21:27", "throughput": 10200.18, "total_tokens": 6748160}
{"current_steps": 7030, "total_steps": 58920, "loss": 0.0971, "lr": 1.9977321414547313e-06, "epoch": 0.596571622539036, "percentage": 11.93, "elapsed_time": "0:11:01", "remaining_time": "1:21:26", "throughput": 10201.54, "total_tokens": 6752960}
{"current_steps": 7035, "total_steps": 58920, "loss": 0.0603, "lr": 1.997712159238414e-06, "epoch": 0.5969959266802444, "percentage": 11.94, "elapsed_time": "0:11:02", "remaining_time": "1:21:24", "throughput": 10203.2, "total_tokens": 6758016}
{"current_steps": 7040, "total_steps": 58920, "loss": 0.0996, "lr": 1.997692089476457e-06, "epoch": 0.5974202308214528, "percentage": 11.95, "elapsed_time": "0:11:02", "remaining_time": "1:21:23", "throughput": 10204.44, "total_tokens": 6762688}
{"current_steps": 7045, "total_steps": 58920, "loss": 0.0549, "lr": 1.997671932170621e-06, "epoch": 0.5978445349626612, "percentage": 11.96, "elapsed_time": "0:11:03", "remaining_time": "1:21:22", "throughput": 10205.67, "total_tokens": 6767424}
{"current_steps": 7050, "total_steps": 58920, "loss": 0.0703, "lr": 1.997651687322675e-06, "epoch": 0.5982688391038696, "percentage": 11.97, "elapsed_time": "0:11:03", "remaining_time": "1:21:21", "throughput": 10206.32, "total_tokens": 6771648}
{"current_steps": 7055, "total_steps": 58920, "loss": 0.0763, "lr": 1.9976313549343957e-06, "epoch": 0.598693143245078, "percentage": 11.97, "elapsed_time": "0:11:03", "remaining_time": "1:21:20", "throughput": 10208.08, "total_tokens": 6776832}
{"current_steps": 7060, "total_steps": 58920, "loss": 0.0327, "lr": 1.9976109350075667e-06, "epoch": 0.5991174473862865, "percentage": 11.98, "elapsed_time": "0:11:04", "remaining_time": "1:21:19", "throughput": 10208.81, "total_tokens": 6781120}
{"current_steps": 7065, "total_steps": 58920, "loss": 0.0341, "lr": 1.99759042754398e-06, "epoch": 0.5995417515274949, "percentage": 11.99, "elapsed_time": "0:11:04", "remaining_time": "1:21:18", "throughput": 10209.66, "total_tokens": 6785472}
{"current_steps": 7070, "total_steps": 58920, "loss": 0.1088, "lr": 1.9975698325454354e-06, "epoch": 0.5999660556687033, "percentage": 12.0, "elapsed_time": "0:11:05", "remaining_time": "1:21:17", "throughput": 10212.33, "total_tokens": 6791488}
{"current_steps": 7075, "total_steps": 58920, "loss": 0.0832, "lr": 1.9975491500137394e-06, "epoch": 0.6003903598099117, "percentage": 12.01, "elapsed_time": "0:11:05", "remaining_time": "1:21:16", "throughput": 10214.62, "total_tokens": 6797120}
{"current_steps": 7080, "total_steps": 58920, "loss": 0.0463, "lr": 1.9975283799507073e-06, "epoch": 0.6008146639511202, "percentage": 12.02, "elapsed_time": "0:11:05", "remaining_time": "1:21:15", "throughput": 10216.02, "total_tokens": 6801984}
{"current_steps": 7085, "total_steps": 58920, "loss": 0.081, "lr": 1.9975075223581614e-06, "epoch": 0.6012389680923286, "percentage": 12.02, "elapsed_time": "0:11:06", "remaining_time": "1:21:13", "throughput": 10217.09, "total_tokens": 6806528}
{"current_steps": 7090, "total_steps": 58920, "loss": 0.136, "lr": 1.9974865772379314e-06, "epoch": 0.601663272233537, "percentage": 12.03, "elapsed_time": "0:11:06", "remaining_time": "1:21:12", "throughput": 10218.63, "total_tokens": 6811456}
{"current_steps": 7095, "total_steps": 58920, "loss": 0.021, "lr": 1.9974655445918565e-06, "epoch": 0.6020875763747454, "percentage": 12.04, "elapsed_time": "0:11:06", "remaining_time": "1:21:11", "throughput": 10219.52, "total_tokens": 6815872}
{"current_steps": 7100, "total_steps": 58920, "loss": 0.0315, "lr": 1.997444424421781e-06, "epoch": 0.6025118805159538, "percentage": 12.05, "elapsed_time": "0:11:07", "remaining_time": "1:21:10", "throughput": 10221.69, "total_tokens": 6821376}
{"current_steps": 7105, "total_steps": 58920, "loss": 0.059, "lr": 1.997423216729558e-06, "epoch": 0.6029361846571623, "percentage": 12.06, "elapsed_time": "0:11:07", "remaining_time": "1:21:09", "throughput": 10223.58, "total_tokens": 6826688}
{"current_steps": 7110, "total_steps": 58920, "loss": 0.0386, "lr": 1.9974019215170495e-06, "epoch": 0.6033604887983707, "percentage": 12.07, "elapsed_time": "0:11:08", "remaining_time": "1:21:08", "throughput": 10225.11, "total_tokens": 6831680}
{"current_steps": 7115, "total_steps": 58920, "loss": 0.0454, "lr": 1.9973805387861237e-06, "epoch": 0.6037847929395791, "percentage": 12.08, "elapsed_time": "0:11:08", "remaining_time": "1:21:07", "throughput": 10225.89, "total_tokens": 6836032}
{"current_steps": 7120, "total_steps": 58920, "loss": 0.0835, "lr": 1.9973590685386565e-06, "epoch": 0.6042090970807875, "percentage": 12.08, "elapsed_time": "0:11:08", "remaining_time": "1:21:06", "throughput": 10226.93, "total_tokens": 6840576}
{"current_steps": 7125, "total_steps": 58920, "loss": 0.0835, "lr": 1.9973375107765317e-06, "epoch": 0.6046334012219959, "percentage": 12.09, "elapsed_time": "0:11:09", "remaining_time": "1:21:05", "throughput": 10228.61, "total_tokens": 6845696}
{"current_steps": 7130, "total_steps": 58920, "loss": 0.0637, "lr": 1.9973158655016415e-06, "epoch": 0.6050577053632044, "percentage": 12.1, "elapsed_time": "0:11:09", "remaining_time": "1:21:04", "throughput": 10229.31, "total_tokens": 6849984}
{"current_steps": 7135, "total_steps": 58920, "loss": 0.0368, "lr": 1.9972941327158845e-06, "epoch": 0.6054820095044128, "percentage": 12.11, "elapsed_time": "0:11:10", "remaining_time": "1:21:02", "throughput": 10230.43, "total_tokens": 6854592}
{"current_steps": 7140, "total_steps": 58920, "loss": 0.1713, "lr": 1.997272312421168e-06, "epoch": 0.6059063136456212, "percentage": 12.12, "elapsed_time": "0:11:10", "remaining_time": "1:21:01", "throughput": 10231.93, "total_tokens": 6859584}
{"current_steps": 7145, "total_steps": 58920, "loss": 0.1205, "lr": 1.9972504046194072e-06, "epoch": 0.6063306177868296, "percentage": 12.13, "elapsed_time": "0:11:10", "remaining_time": "1:21:00", "throughput": 10233.17, "total_tokens": 6864320}
{"current_steps": 7150, "total_steps": 58920, "loss": 0.0555, "lr": 1.997228409312524e-06, "epoch": 0.606754921928038, "percentage": 12.14, "elapsed_time": "0:11:11", "remaining_time": "1:20:59", "throughput": 10233.97, "total_tokens": 6868672}
{"current_steps": 7155, "total_steps": 58920, "loss": 0.0735, "lr": 1.997206326502448e-06, "epoch": 0.6071792260692465, "percentage": 12.14, "elapsed_time": "0:11:11", "remaining_time": "1:20:58", "throughput": 10234.86, "total_tokens": 6873088}
{"current_steps": 7160, "total_steps": 58920, "loss": 0.0349, "lr": 1.9971841561911176e-06, "epoch": 0.6076035302104549, "percentage": 12.15, "elapsed_time": "0:11:11", "remaining_time": "1:20:57", "throughput": 10235.83, "total_tokens": 6877568}
{"current_steps": 7165, "total_steps": 58920, "loss": 0.1663, "lr": 1.9971618983804772e-06, "epoch": 0.6080278343516633, "percentage": 12.16, "elapsed_time": "0:11:12", "remaining_time": "1:20:56", "throughput": 10236.85, "total_tokens": 6882112}
{"current_steps": 7170, "total_steps": 58920, "loss": 0.0892, "lr": 1.997139553072481e-06, "epoch": 0.6084521384928717, "percentage": 12.17, "elapsed_time": "0:11:12", "remaining_time": "1:20:55", "throughput": 10237.94, "total_tokens": 6886720}
{"current_steps": 7175, "total_steps": 58920, "loss": 0.0452, "lr": 1.997117120269089e-06, "epoch": 0.6088764426340801, "percentage": 12.18, "elapsed_time": "0:11:13", "remaining_time": "1:20:53", "throughput": 10239.34, "total_tokens": 6891584}
{"current_steps": 7180, "total_steps": 58920, "loss": 0.0353, "lr": 1.99709459997227e-06, "epoch": 0.6093007467752886, "percentage": 12.19, "elapsed_time": "0:11:13", "remaining_time": "1:20:52", "throughput": 10240.65, "total_tokens": 6896320}
{"current_steps": 7185, "total_steps": 58920, "loss": 0.1102, "lr": 1.9970719921839996e-06, "epoch": 0.609725050916497, "percentage": 12.19, "elapsed_time": "0:11:13", "remaining_time": "1:20:51", "throughput": 10241.87, "total_tokens": 6900992}
{"current_steps": 7190, "total_steps": 58920, "loss": 0.1083, "lr": 1.997049296906262e-06, "epoch": 0.6101493550577054, "percentage": 12.2, "elapsed_time": "0:11:14", "remaining_time": "1:20:50", "throughput": 10242.93, "total_tokens": 6905600}
{"current_steps": 7195, "total_steps": 58920, "loss": 0.0949, "lr": 1.997026514141048e-06, "epoch": 0.6105736591989138, "percentage": 12.21, "elapsed_time": "0:11:14", "remaining_time": "1:20:49", "throughput": 10243.99, "total_tokens": 6910208}
{"current_steps": 7200, "total_steps": 58920, "loss": 0.0728, "lr": 1.9970036438903573e-06, "epoch": 0.6109979633401222, "percentage": 12.22, "elapsed_time": "0:11:14", "remaining_time": "1:20:48", "throughput": 10245.56, "total_tokens": 6915264}
{"current_steps": 7205, "total_steps": 58920, "loss": 0.0458, "lr": 1.996980686156197e-06, "epoch": 0.6114222674813307, "percentage": 12.23, "elapsed_time": "0:11:15", "remaining_time": "1:20:47", "throughput": 10246.57, "total_tokens": 6919808}
{"current_steps": 7210, "total_steps": 58920, "loss": 0.0315, "lr": 1.9969576409405807e-06, "epoch": 0.6118465716225391, "percentage": 12.24, "elapsed_time": "0:11:15", "remaining_time": "1:20:46", "throughput": 10247.87, "total_tokens": 6924608}
{"current_steps": 7215, "total_steps": 58920, "loss": 0.0423, "lr": 1.996934508245531e-06, "epoch": 0.6122708757637475, "percentage": 12.25, "elapsed_time": "0:11:16", "remaining_time": "1:20:45", "throughput": 10249.16, "total_tokens": 6929344}
{"current_steps": 7220, "total_steps": 58920, "loss": 0.1435, "lr": 1.996911288073077e-06, "epoch": 0.6126951799049559, "percentage": 12.25, "elapsed_time": "0:11:16", "remaining_time": "1:20:44", "throughput": 10250.88, "total_tokens": 6934464}
{"current_steps": 7225, "total_steps": 58920, "loss": 0.1293, "lr": 1.9968879804252575e-06, "epoch": 0.6131194840461643, "percentage": 12.26, "elapsed_time": "0:11:16", "remaining_time": "1:20:42", "throughput": 10252.38, "total_tokens": 6939456}
{"current_steps": 7230, "total_steps": 58920, "loss": 0.0392, "lr": 1.996864585304117e-06, "epoch": 0.6135437881873728, "percentage": 12.27, "elapsed_time": "0:11:17", "remaining_time": "1:20:41", "throughput": 10253.14, "total_tokens": 6943808}
{"current_steps": 7235, "total_steps": 58920, "loss": 0.0302, "lr": 1.996841102711708e-06, "epoch": 0.6139680923285811, "percentage": 12.28, "elapsed_time": "0:11:17", "remaining_time": "1:20:40", "throughput": 10254.56, "total_tokens": 6948736}
{"current_steps": 7240, "total_steps": 58920, "loss": 0.0786, "lr": 1.9968175326500916e-06, "epoch": 0.6143923964697895, "percentage": 12.29, "elapsed_time": "0:11:18", "remaining_time": "1:20:39", "throughput": 10256.17, "total_tokens": 6953792}
{"current_steps": 7245, "total_steps": 58920, "loss": 0.0157, "lr": 1.9967938751213358e-06, "epoch": 0.6148167006109979, "percentage": 12.3, "elapsed_time": "0:11:18", "remaining_time": "1:20:38", "throughput": 10257.55, "total_tokens": 6958656}
{"current_steps": 7250, "total_steps": 58920, "loss": 0.0386, "lr": 1.9967701301275157e-06, "epoch": 0.6152410047522063, "percentage": 12.3, "elapsed_time": "0:11:18", "remaining_time": "1:20:37", "throughput": 10258.51, "total_tokens": 6963200}
{"current_steps": 7255, "total_steps": 58920, "loss": 0.0252, "lr": 1.996746297670716e-06, "epoch": 0.6156653088934148, "percentage": 12.31, "elapsed_time": "0:11:19", "remaining_time": "1:20:36", "throughput": 10260.34, "total_tokens": 6968448}
{"current_steps": 7260, "total_steps": 58920, "loss": 0.1112, "lr": 1.996722377753027e-06, "epoch": 0.6160896130346232, "percentage": 12.32, "elapsed_time": "0:11:19", "remaining_time": "1:20:35", "throughput": 10262.33, "total_tokens": 6973888}
{"current_steps": 7265, "total_steps": 58920, "loss": 0.0637, "lr": 1.9966983703765486e-06, "epoch": 0.6165139171758316, "percentage": 12.33, "elapsed_time": "0:11:19", "remaining_time": "1:20:34", "throughput": 10263.15, "total_tokens": 6978304}
{"current_steps": 7270, "total_steps": 58920, "loss": 0.1107, "lr": 1.9966742755433867e-06, "epoch": 0.61693822131704, "percentage": 12.34, "elapsed_time": "0:11:20", "remaining_time": "1:20:33", "throughput": 10264.5, "total_tokens": 6983168}
{"current_steps": 7275, "total_steps": 58920, "loss": 0.0547, "lr": 1.9966500932556553e-06, "epoch": 0.6173625254582484, "percentage": 12.35, "elapsed_time": "0:11:20", "remaining_time": "1:20:32", "throughput": 10266.06, "total_tokens": 6988224}
{"current_steps": 7280, "total_steps": 58920, "loss": 0.0829, "lr": 1.9966258235154766e-06, "epoch": 0.6177868295994569, "percentage": 12.36, "elapsed_time": "0:11:21", "remaining_time": "1:20:31", "throughput": 10266.62, "total_tokens": 6992448}
{"current_steps": 7285, "total_steps": 58920, "loss": 0.0563, "lr": 1.9966014663249804e-06, "epoch": 0.6182111337406653, "percentage": 12.36, "elapsed_time": "0:11:21", "remaining_time": "1:20:30", "throughput": 10267.39, "total_tokens": 6996864}
{"current_steps": 7290, "total_steps": 58920, "loss": 0.0386, "lr": 1.9965770216863034e-06, "epoch": 0.6186354378818737, "percentage": 12.37, "elapsed_time": "0:11:21", "remaining_time": "1:20:29", "throughput": 10269.03, "total_tokens": 7001984}
{"current_steps": 7295, "total_steps": 58920, "loss": 0.0612, "lr": 1.996552489601591e-06, "epoch": 0.6190597420230821, "percentage": 12.38, "elapsed_time": "0:11:22", "remaining_time": "1:20:28", "throughput": 10270.74, "total_tokens": 7007168}
{"current_steps": 7300, "total_steps": 58920, "loss": 0.0394, "lr": 1.996527870072996e-06, "epoch": 0.6194840461642905, "percentage": 12.39, "elapsed_time": "0:11:22", "remaining_time": "1:20:27", "throughput": 10272.49, "total_tokens": 7012416}
{"current_steps": 7305, "total_steps": 58920, "loss": 0.0648, "lr": 1.996503163102678e-06, "epoch": 0.619908350305499, "percentage": 12.4, "elapsed_time": "0:11:23", "remaining_time": "1:20:25", "throughput": 10273.05, "total_tokens": 7016576}
{"current_steps": 7310, "total_steps": 58920, "loss": 0.0449, "lr": 1.9964783686928058e-06, "epoch": 0.6203326544467074, "percentage": 12.41, "elapsed_time": "0:11:23", "remaining_time": "1:20:24", "throughput": 10273.93, "total_tokens": 7021056}
{"current_steps": 7315, "total_steps": 58920, "loss": 0.0647, "lr": 1.996453486845554e-06, "epoch": 0.6207569585879158, "percentage": 12.42, "elapsed_time": "0:11:23", "remaining_time": "1:20:23", "throughput": 10275.31, "total_tokens": 7025984}
{"current_steps": 7320, "total_steps": 58920, "loss": 0.0197, "lr": 1.9964285175631067e-06, "epoch": 0.6211812627291242, "percentage": 12.42, "elapsed_time": "0:11:24", "remaining_time": "1:20:22", "throughput": 10276.96, "total_tokens": 7031104}
{"current_steps": 7325, "total_steps": 58920, "loss": 0.0615, "lr": 1.996403460847654e-06, "epoch": 0.6216055668703326, "percentage": 12.43, "elapsed_time": "0:11:24", "remaining_time": "1:20:21", "throughput": 10278.27, "total_tokens": 7035904}
{"current_steps": 7330, "total_steps": 58920, "loss": 0.1503, "lr": 1.996378316701396e-06, "epoch": 0.6220298710115411, "percentage": 12.44, "elapsed_time": "0:11:24", "remaining_time": "1:20:20", "throughput": 10279.17, "total_tokens": 7040384}
{"current_steps": 7335, "total_steps": 58920, "loss": 0.0107, "lr": 1.9963530851265374e-06, "epoch": 0.6224541751527495, "percentage": 12.45, "elapsed_time": "0:11:25", "remaining_time": "1:20:19", "throughput": 10280.58, "total_tokens": 7045312}
{"current_steps": 7340, "total_steps": 58920, "loss": 0.0361, "lr": 1.996327766125293e-06, "epoch": 0.6228784792939579, "percentage": 12.46, "elapsed_time": "0:11:25", "remaining_time": "1:20:18", "throughput": 10281.78, "total_tokens": 7050048}
{"current_steps": 7345, "total_steps": 58920, "loss": 0.0324, "lr": 1.9963023596998847e-06, "epoch": 0.6233027834351663, "percentage": 12.47, "elapsed_time": "0:11:26", "remaining_time": "1:20:17", "throughput": 10282.74, "total_tokens": 7054592}
{"current_steps": 7350, "total_steps": 58920, "loss": 0.1007, "lr": 1.9962768658525417e-06, "epoch": 0.6237270875763747, "percentage": 12.47, "elapsed_time": "0:11:26", "remaining_time": "1:20:16", "throughput": 10284.0, "total_tokens": 7059392}
{"current_steps": 7355, "total_steps": 58920, "loss": 0.1307, "lr": 1.9962512845855e-06, "epoch": 0.6241513917175832, "percentage": 12.48, "elapsed_time": "0:11:26", "remaining_time": "1:20:15", "throughput": 10284.53, "total_tokens": 7063552}
{"current_steps": 7360, "total_steps": 58920, "loss": 0.0642, "lr": 1.9962256159010058e-06, "epoch": 0.6245756958587916, "percentage": 12.49, "elapsed_time": "0:11:27", "remaining_time": "1:20:14", "throughput": 10285.75, "total_tokens": 7068288}
{"current_steps": 7365, "total_steps": 58920, "loss": 0.0347, "lr": 1.9961998598013098e-06, "epoch": 0.625, "percentage": 12.5, "elapsed_time": "0:11:27", "remaining_time": "1:20:13", "throughput": 10287.19, "total_tokens": 7073216}
{"current_steps": 7370, "total_steps": 58920, "loss": 0.0872, "lr": 1.9961740162886733e-06, "epoch": 0.6254243041412084, "percentage": 12.51, "elapsed_time": "0:11:27", "remaining_time": "1:20:11", "throughput": 10288.17, "total_tokens": 7077824}
{"current_steps": 7375, "total_steps": 58920, "loss": 0.0382, "lr": 1.996148085365364e-06, "epoch": 0.6258486082824168, "percentage": 12.52, "elapsed_time": "0:11:28", "remaining_time": "1:20:10", "throughput": 10288.96, "total_tokens": 7082240}
{"current_steps": 7380, "total_steps": 58920, "loss": 0.0692, "lr": 1.996122067033656e-06, "epoch": 0.6262729124236253, "percentage": 12.53, "elapsed_time": "0:11:28", "remaining_time": "1:20:09", "throughput": 10290.57, "total_tokens": 7087360}
{"current_steps": 7385, "total_steps": 58920, "loss": 0.0356, "lr": 1.9960959612958334e-06, "epoch": 0.6266972165648337, "percentage": 12.53, "elapsed_time": "0:11:29", "remaining_time": "1:20:08", "throughput": 10292.05, "total_tokens": 7092288}
{"current_steps": 7390, "total_steps": 58920, "loss": 0.075, "lr": 1.9960697681541865e-06, "epoch": 0.6271215207060421, "percentage": 12.54, "elapsed_time": "0:11:29", "remaining_time": "1:20:07", "throughput": 10292.91, "total_tokens": 7096768}
{"current_steps": 7395, "total_steps": 58920, "loss": 0.0752, "lr": 1.9960434876110143e-06, "epoch": 0.6275458248472505, "percentage": 12.55, "elapsed_time": "0:11:29", "remaining_time": "1:20:06", "throughput": 10293.86, "total_tokens": 7101312}
{"current_steps": 7400, "total_steps": 58920, "loss": 0.0953, "lr": 1.9960171196686215e-06, "epoch": 0.6279701289884589, "percentage": 12.56, "elapsed_time": "0:11:30", "remaining_time": "1:20:05", "throughput": 10294.55, "total_tokens": 7105664}
{"current_steps": 7405, "total_steps": 58920, "loss": 0.0821, "lr": 1.995990664329323e-06, "epoch": 0.6283944331296674, "percentage": 12.57, "elapsed_time": "0:11:30", "remaining_time": "1:20:04", "throughput": 10295.5, "total_tokens": 7110208}
{"current_steps": 7410, "total_steps": 58920, "loss": 0.0069, "lr": 1.99596412159544e-06, "epoch": 0.6288187372708758, "percentage": 12.58, "elapsed_time": "0:11:31", "remaining_time": "1:20:03", "throughput": 10296.85, "total_tokens": 7115136}
{"current_steps": 7415, "total_steps": 58920, "loss": 0.037, "lr": 1.9959374914693003e-06, "epoch": 0.6292430414120842, "percentage": 12.58, "elapsed_time": "0:11:31", "remaining_time": "1:20:02", "throughput": 10297.68, "total_tokens": 7119552}
{"current_steps": 7420, "total_steps": 58920, "loss": 0.0488, "lr": 1.9959107739532422e-06, "epoch": 0.6296673455532926, "percentage": 12.59, "elapsed_time": "0:11:31", "remaining_time": "1:20:01", "throughput": 10298.92, "total_tokens": 7124352}
{"current_steps": 7425, "total_steps": 58920, "loss": 0.0268, "lr": 1.9958839690496094e-06, "epoch": 0.630091649694501, "percentage": 12.6, "elapsed_time": "0:11:32", "remaining_time": "1:20:00", "throughput": 10299.74, "total_tokens": 7128768}
{"current_steps": 7430, "total_steps": 58920, "loss": 0.0453, "lr": 1.9958570767607537e-06, "epoch": 0.6305159538357095, "percentage": 12.61, "elapsed_time": "0:11:32", "remaining_time": "1:19:59", "throughput": 10300.98, "total_tokens": 7133568}
{"current_steps": 7435, "total_steps": 58920, "loss": 0.0795, "lr": 1.9958300970890353e-06, "epoch": 0.6309402579769179, "percentage": 12.62, "elapsed_time": "0:11:32", "remaining_time": "1:19:58", "throughput": 10301.98, "total_tokens": 7138112}
{"current_steps": 7440, "total_steps": 58920, "loss": 0.0558, "lr": 1.9958030300368216e-06, "epoch": 0.6313645621181263, "percentage": 12.63, "elapsed_time": "0:11:33", "remaining_time": "1:19:56", "throughput": 10303.12, "total_tokens": 7142848}
{"current_steps": 7445, "total_steps": 58920, "loss": 0.0839, "lr": 1.9957758756064865e-06, "epoch": 0.6317888662593347, "percentage": 12.64, "elapsed_time": "0:11:33", "remaining_time": "1:19:55", "throughput": 10304.28, "total_tokens": 7147584}
{"current_steps": 7450, "total_steps": 58920, "loss": 0.0814, "lr": 1.9957486338004143e-06, "epoch": 0.6322131704005431, "percentage": 12.64, "elapsed_time": "0:11:34", "remaining_time": "1:19:54", "throughput": 10305.32, "total_tokens": 7152192}
{"current_steps": 7455, "total_steps": 58920, "loss": 0.1072, "lr": 1.995721304620994e-06, "epoch": 0.6326374745417516, "percentage": 12.65, "elapsed_time": "0:11:34", "remaining_time": "1:19:53", "throughput": 10306.22, "total_tokens": 7156672}
{"current_steps": 7460, "total_steps": 58920, "loss": 0.0638, "lr": 1.995693888070625e-06, "epoch": 0.63306177868296, "percentage": 12.66, "elapsed_time": "0:11:34", "remaining_time": "1:19:52", "throughput": 10307.68, "total_tokens": 7161664}
{"current_steps": 7465, "total_steps": 58920, "loss": 0.0532, "lr": 1.9956663841517115e-06, "epoch": 0.6334860828241684, "percentage": 12.67, "elapsed_time": "0:11:35", "remaining_time": "1:19:51", "throughput": 10308.41, "total_tokens": 7166016}
{"current_steps": 7470, "total_steps": 58920, "loss": 0.0545, "lr": 1.9956387928666677e-06, "epoch": 0.6339103869653768, "percentage": 12.68, "elapsed_time": "0:11:35", "remaining_time": "1:19:50", "throughput": 10309.53, "total_tokens": 7170752}
{"current_steps": 7475, "total_steps": 58920, "loss": 0.103, "lr": 1.995611114217915e-06, "epoch": 0.6343346911065852, "percentage": 12.69, "elapsed_time": "0:11:35", "remaining_time": "1:19:49", "throughput": 10311.26, "total_tokens": 7176064}
{"current_steps": 7480, "total_steps": 58920, "loss": 0.0725, "lr": 1.9955833482078815e-06, "epoch": 0.6347589952477937, "percentage": 12.7, "elapsed_time": "0:11:36", "remaining_time": "1:19:48", "throughput": 10312.89, "total_tokens": 7181312}
{"current_steps": 7485, "total_steps": 58920, "loss": 0.0964, "lr": 1.995555494839004e-06, "epoch": 0.6351832993890021, "percentage": 12.7, "elapsed_time": "0:11:36", "remaining_time": "1:19:47", "throughput": 10314.21, "total_tokens": 7186176}
{"current_steps": 7490, "total_steps": 58920, "loss": 0.0271, "lr": 1.9955275541137256e-06, "epoch": 0.6356076035302105, "percentage": 12.71, "elapsed_time": "0:11:37", "remaining_time": "1:19:46", "throughput": 10315.19, "total_tokens": 7190784}
{"current_steps": 7495, "total_steps": 58920, "loss": 0.0819, "lr": 1.995499526034499e-06, "epoch": 0.6360319076714189, "percentage": 12.72, "elapsed_time": "0:11:37", "remaining_time": "1:19:45", "throughput": 10316.68, "total_tokens": 7195840}
{"current_steps": 7500, "total_steps": 58920, "loss": 0.0706, "lr": 1.9954714106037833e-06, "epoch": 0.6364562118126272, "percentage": 12.73, "elapsed_time": "0:11:37", "remaining_time": "1:19:44", "throughput": 10318.31, "total_tokens": 7201024}
{"current_steps": 7505, "total_steps": 58920, "loss": 0.0692, "lr": 1.995443207824046e-06, "epoch": 0.6368805159538357, "percentage": 12.74, "elapsed_time": "0:11:38", "remaining_time": "1:19:43", "throughput": 10319.47, "total_tokens": 7205760}
{"current_steps": 7510, "total_steps": 58920, "loss": 0.056, "lr": 1.99541491769776e-06, "epoch": 0.6373048200950441, "percentage": 12.75, "elapsed_time": "0:11:38", "remaining_time": "1:19:42", "throughput": 10320.7, "total_tokens": 7210560}
{"current_steps": 7515, "total_steps": 58920, "loss": 0.0385, "lr": 1.99538654022741e-06, "epoch": 0.6377291242362525, "percentage": 12.75, "elapsed_time": "0:11:39", "remaining_time": "1:19:41", "throughput": 10322.07, "total_tokens": 7215488}
{"current_steps": 7520, "total_steps": 58920, "loss": 0.0891, "lr": 1.9953580754154845e-06, "epoch": 0.6381534283774609, "percentage": 12.76, "elapsed_time": "0:11:39", "remaining_time": "1:19:40", "throughput": 10323.62, "total_tokens": 7220608}
{"current_steps": 7525, "total_steps": 58920, "loss": 0.0538, "lr": 1.9953295232644816e-06, "epoch": 0.6385777325186693, "percentage": 12.77, "elapsed_time": "0:11:39", "remaining_time": "1:19:39", "throughput": 10324.71, "total_tokens": 7225280}
{"current_steps": 7530, "total_steps": 58920, "loss": 0.046, "lr": 1.9953008837769064e-06, "epoch": 0.6390020366598778, "percentage": 12.78, "elapsed_time": "0:11:40", "remaining_time": "1:19:38", "throughput": 10325.48, "total_tokens": 7229696}
{"current_steps": 7535, "total_steps": 58920, "loss": 0.1021, "lr": 1.9952721569552727e-06, "epoch": 0.6394263408010862, "percentage": 12.79, "elapsed_time": "0:11:40", "remaining_time": "1:19:37", "throughput": 10326.09, "total_tokens": 7233984}
{"current_steps": 7540, "total_steps": 58920, "loss": 0.0389, "lr": 1.9952433428021002e-06, "epoch": 0.6398506449422946, "percentage": 12.8, "elapsed_time": "0:11:40", "remaining_time": "1:19:36", "throughput": 10328.53, "total_tokens": 7239936}
{"current_steps": 7545, "total_steps": 58920, "loss": 0.0394, "lr": 1.995214441319918e-06, "epoch": 0.640274949083503, "percentage": 12.81, "elapsed_time": "0:11:41", "remaining_time": "1:19:35", "throughput": 10329.4, "total_tokens": 7244480}
{"current_steps": 7550, "total_steps": 58920, "loss": 0.0711, "lr": 1.9951854525112616e-06, "epoch": 0.6406992532247114, "percentage": 12.81, "elapsed_time": "0:11:41", "remaining_time": "1:19:34", "throughput": 10330.28, "total_tokens": 7248960}
{"current_steps": 7555, "total_steps": 58920, "loss": 0.0582, "lr": 1.995156376378675e-06, "epoch": 0.6411235573659199, "percentage": 12.82, "elapsed_time": "0:11:42", "remaining_time": "1:19:33", "throughput": 10331.65, "total_tokens": 7253888}
{"current_steps": 7560, "total_steps": 58920, "loss": 0.0257, "lr": 1.995127212924709e-06, "epoch": 0.6415478615071283, "percentage": 12.83, "elapsed_time": "0:11:42", "remaining_time": "1:19:32", "throughput": 10333.42, "total_tokens": 7259200}
{"current_steps": 7565, "total_steps": 58920, "loss": 0.041, "lr": 1.9950979621519236e-06, "epoch": 0.6419721656483367, "percentage": 12.84, "elapsed_time": "0:11:42", "remaining_time": "1:19:31", "throughput": 10334.41, "total_tokens": 7263808}
{"current_steps": 7570, "total_steps": 58920, "loss": 0.0855, "lr": 1.9950686240628844e-06, "epoch": 0.6423964697895451, "percentage": 12.85, "elapsed_time": "0:11:43", "remaining_time": "1:19:30", "throughput": 10336.3, "total_tokens": 7269248}
{"current_steps": 7575, "total_steps": 58920, "loss": 0.0831, "lr": 1.995039198660166e-06, "epoch": 0.6428207739307535, "percentage": 12.86, "elapsed_time": "0:11:43", "remaining_time": "1:19:29", "throughput": 10338.0, "total_tokens": 7274496}
{"current_steps": 7580, "total_steps": 58920, "loss": 0.198, "lr": 1.9950096859463508e-06, "epoch": 0.643245078071962, "percentage": 12.86, "elapsed_time": "0:11:44", "remaining_time": "1:19:28", "throughput": 10339.52, "total_tokens": 7279552}
{"current_steps": 7585, "total_steps": 58920, "loss": 0.1195, "lr": 1.994980085924028e-06, "epoch": 0.6436693822131704, "percentage": 12.87, "elapsed_time": "0:11:44", "remaining_time": "1:19:27", "throughput": 10340.47, "total_tokens": 7284096}
{"current_steps": 7590, "total_steps": 58920, "loss": 0.0513, "lr": 1.9949503985957947e-06, "epoch": 0.6440936863543788, "percentage": 12.88, "elapsed_time": "0:11:44", "remaining_time": "1:19:26", "throughput": 10341.92, "total_tokens": 7289088}
{"current_steps": 7595, "total_steps": 58920, "loss": 0.0781, "lr": 1.9949206239642565e-06, "epoch": 0.6445179904955872, "percentage": 12.89, "elapsed_time": "0:11:45", "remaining_time": "1:19:25", "throughput": 10342.9, "total_tokens": 7293696}
{"current_steps": 7600, "total_steps": 58920, "loss": 0.0412, "lr": 1.994890762032026e-06, "epoch": 0.6449422946367956, "percentage": 12.9, "elapsed_time": "0:11:45", "remaining_time": "1:19:24", "throughput": 10344.43, "total_tokens": 7298816}
{"current_steps": 7605, "total_steps": 58920, "loss": 0.0661, "lr": 1.9948608128017225e-06, "epoch": 0.6453665987780041, "percentage": 12.91, "elapsed_time": "0:11:45", "remaining_time": "1:19:23", "throughput": 10345.17, "total_tokens": 7303232}
{"current_steps": 7610, "total_steps": 58920, "loss": 0.0396, "lr": 1.994830776275975e-06, "epoch": 0.6457909029192125, "percentage": 12.92, "elapsed_time": "0:11:46", "remaining_time": "1:19:22", "throughput": 10346.8, "total_tokens": 7308416}
{"current_steps": 7615, "total_steps": 58920, "loss": 0.0288, "lr": 1.9948006524574187e-06, "epoch": 0.6462152070604209, "percentage": 12.92, "elapsed_time": "0:11:46", "remaining_time": "1:19:21", "throughput": 10347.77, "total_tokens": 7313024}
{"current_steps": 7620, "total_steps": 58920, "loss": 0.0575, "lr": 1.994770441348697e-06, "epoch": 0.6466395112016293, "percentage": 12.93, "elapsed_time": "0:11:47", "remaining_time": "1:19:20", "throughput": 10348.93, "total_tokens": 7317760}
{"current_steps": 7625, "total_steps": 58920, "loss": 0.049, "lr": 1.99474014295246e-06, "epoch": 0.6470638153428377, "percentage": 12.94, "elapsed_time": "0:11:47", "remaining_time": "1:19:19", "throughput": 10350.2, "total_tokens": 7322624}
{"current_steps": 7630, "total_steps": 58920, "loss": 0.0697, "lr": 1.9947097572713676e-06, "epoch": 0.6474881194840462, "percentage": 12.95, "elapsed_time": "0:11:47", "remaining_time": "1:19:18", "throughput": 10351.02, "total_tokens": 7327104}
{"current_steps": 7635, "total_steps": 58920, "loss": 0.0903, "lr": 1.9946792843080853e-06, "epoch": 0.6479124236252546, "percentage": 12.96, "elapsed_time": "0:11:48", "remaining_time": "1:19:17", "throughput": 10351.8, "total_tokens": 7331520}
{"current_steps": 7640, "total_steps": 58920, "loss": 0.088, "lr": 1.994648724065287e-06, "epoch": 0.648336727766463, "percentage": 12.97, "elapsed_time": "0:11:48", "remaining_time": "1:19:16", "throughput": 10353.15, "total_tokens": 7336448}
{"current_steps": 7645, "total_steps": 58920, "loss": 0.0964, "lr": 1.9946180765456542e-06, "epoch": 0.6487610319076714, "percentage": 12.98, "elapsed_time": "0:11:49", "remaining_time": "1:19:15", "throughput": 10354.29, "total_tokens": 7341248}
{"current_steps": 7650, "total_steps": 58920, "loss": 0.0529, "lr": 1.9945873417518765e-06, "epoch": 0.6491853360488798, "percentage": 12.98, "elapsed_time": "0:11:49", "remaining_time": "1:19:14", "throughput": 10355.3, "total_tokens": 7345920}
{"current_steps": 7655, "total_steps": 58920, "loss": 0.0592, "lr": 1.99455651968665e-06, "epoch": 0.6496096401900883, "percentage": 12.99, "elapsed_time": "0:11:49", "remaining_time": "1:19:13", "throughput": 10356.16, "total_tokens": 7350464}
{"current_steps": 7660, "total_steps": 58920, "loss": 0.097, "lr": 1.9945256103526804e-06, "epoch": 0.6500339443312967, "percentage": 13.0, "elapsed_time": "0:11:50", "remaining_time": "1:19:12", "throughput": 10357.07, "total_tokens": 7355008}
{"current_steps": 7665, "total_steps": 58920, "loss": 0.0471, "lr": 1.994494613752679e-06, "epoch": 0.6504582484725051, "percentage": 13.01, "elapsed_time": "0:11:50", "remaining_time": "1:19:11", "throughput": 10358.13, "total_tokens": 7359680}
{"current_steps": 7670, "total_steps": 58920, "loss": 0.0664, "lr": 1.994463529889366e-06, "epoch": 0.6508825526137135, "percentage": 13.02, "elapsed_time": "0:11:50", "remaining_time": "1:19:10", "throughput": 10358.71, "total_tokens": 7363968}
{"current_steps": 7675, "total_steps": 58920, "loss": 0.083, "lr": 1.994432358765468e-06, "epoch": 0.651306856754922, "percentage": 13.03, "elapsed_time": "0:11:51", "remaining_time": "1:19:09", "throughput": 10359.07, "total_tokens": 7368064}
{"current_steps": 7680, "total_steps": 58920, "loss": 0.0491, "lr": 1.9944011003837217e-06, "epoch": 0.6517311608961304, "percentage": 13.03, "elapsed_time": "0:11:51", "remaining_time": "1:19:08", "throughput": 10360.06, "total_tokens": 7372736}
{"current_steps": 7685, "total_steps": 58920, "loss": 0.0343, "lr": 1.994369754746869e-06, "epoch": 0.6521554650373388, "percentage": 13.04, "elapsed_time": "0:11:52", "remaining_time": "1:19:07", "throughput": 10361.36, "total_tokens": 7377600}
{"current_steps": 7690, "total_steps": 58920, "loss": 0.0318, "lr": 1.9943383218576604e-06, "epoch": 0.6525797691785472, "percentage": 13.05, "elapsed_time": "0:11:52", "remaining_time": "1:19:05", "throughput": 10362.03, "total_tokens": 7381952}
{"current_steps": 7695, "total_steps": 58920, "loss": 0.0572, "lr": 1.9943068017188537e-06, "epoch": 0.6530040733197556, "percentage": 13.06, "elapsed_time": "0:11:52", "remaining_time": "1:19:05", "throughput": 10363.81, "total_tokens": 7387264}
{"current_steps": 7700, "total_steps": 58920, "loss": 0.0959, "lr": 1.9942751943332153e-06, "epoch": 0.653428377460964, "percentage": 13.07, "elapsed_time": "0:11:53", "remaining_time": "1:19:03", "throughput": 10364.86, "total_tokens": 7391936}
{"current_steps": 7705, "total_steps": 58920, "loss": 0.0721, "lr": 1.9942434997035183e-06, "epoch": 0.6538526816021725, "percentage": 13.08, "elapsed_time": "0:11:53", "remaining_time": "1:19:03", "throughput": 10366.57, "total_tokens": 7397248}
{"current_steps": 7710, "total_steps": 58920, "loss": 0.1005, "lr": 1.9942117178325444e-06, "epoch": 0.6542769857433809, "percentage": 13.09, "elapsed_time": "0:11:53", "remaining_time": "1:19:02", "throughput": 10367.56, "total_tokens": 7401920}
{"current_steps": 7715, "total_steps": 58920, "loss": 0.0717, "lr": 1.9941798487230816e-06, "epoch": 0.6547012898845893, "percentage": 13.09, "elapsed_time": "0:11:54", "remaining_time": "1:19:01", "throughput": 10368.95, "total_tokens": 7406912}
{"current_steps": 7720, "total_steps": 58920, "loss": 0.0727, "lr": 1.9941478923779264e-06, "epoch": 0.6551255940257977, "percentage": 13.1, "elapsed_time": "0:11:54", "remaining_time": "1:19:00", "throughput": 10370.19, "total_tokens": 7411776}
{"current_steps": 7725, "total_steps": 58920, "loss": 0.0632, "lr": 1.994115848799883e-06, "epoch": 0.6555498981670062, "percentage": 13.11, "elapsed_time": "0:11:55", "remaining_time": "1:18:59", "throughput": 10370.93, "total_tokens": 7416128}
{"current_steps": 7730, "total_steps": 58920, "loss": 0.0411, "lr": 1.994083717991763e-06, "epoch": 0.6559742023082146, "percentage": 13.12, "elapsed_time": "0:11:55", "remaining_time": "1:18:58", "throughput": 10373.41, "total_tokens": 7422208}
{"current_steps": 7735, "total_steps": 58920, "loss": 0.0664, "lr": 1.9940514999563866e-06, "epoch": 0.656398506449423, "percentage": 13.13, "elapsed_time": "0:11:55", "remaining_time": "1:18:57", "throughput": 10374.56, "total_tokens": 7427008}
{"current_steps": 7740, "total_steps": 58920, "loss": 0.063, "lr": 1.9940191946965794e-06, "epoch": 0.6568228105906314, "percentage": 13.14, "elapsed_time": "0:11:56", "remaining_time": "1:18:56", "throughput": 10375.35, "total_tokens": 7431488}
{"current_steps": 7745, "total_steps": 58920, "loss": 0.0601, "lr": 1.993986802215177e-06, "epoch": 0.6572471147318398, "percentage": 13.14, "elapsed_time": "0:11:56", "remaining_time": "1:18:55", "throughput": 10376.78, "total_tokens": 7436544}
{"current_steps": 7750, "total_steps": 58920, "loss": 0.1003, "lr": 1.9939543225150214e-06, "epoch": 0.6576714188730483, "percentage": 13.15, "elapsed_time": "0:11:57", "remaining_time": "1:18:54", "throughput": 10377.46, "total_tokens": 7440896}
{"current_steps": 7755, "total_steps": 58920, "loss": 0.0975, "lr": 1.9939217555989623e-06, "epoch": 0.6580957230142567, "percentage": 13.16, "elapsed_time": "0:11:57", "remaining_time": "1:18:53", "throughput": 10378.81, "total_tokens": 7445824}
{"current_steps": 7760, "total_steps": 58920, "loss": 0.1038, "lr": 1.9938891014698583e-06, "epoch": 0.658520027155465, "percentage": 13.17, "elapsed_time": "0:11:57", "remaining_time": "1:18:52", "throughput": 10379.73, "total_tokens": 7450368}
{"current_steps": 7765, "total_steps": 58920, "loss": 0.0399, "lr": 1.9938563601305737e-06, "epoch": 0.6589443312966734, "percentage": 13.18, "elapsed_time": "0:11:58", "remaining_time": "1:18:51", "throughput": 10380.38, "total_tokens": 7454720}
{"current_steps": 7770, "total_steps": 58920, "loss": 0.0877, "lr": 1.993823531583982e-06, "epoch": 0.6593686354378818, "percentage": 13.19, "elapsed_time": "0:11:58", "remaining_time": "1:18:50", "throughput": 10381.24, "total_tokens": 7459264}
{"current_steps": 7775, "total_steps": 58920, "loss": 0.0382, "lr": 1.9937906158329635e-06, "epoch": 0.6597929395790902, "percentage": 13.2, "elapsed_time": "0:11:58", "remaining_time": "1:18:49", "throughput": 10382.07, "total_tokens": 7463744}
{"current_steps": 7780, "total_steps": 58920, "loss": 0.0299, "lr": 1.9937576128804067e-06, "epoch": 0.6602172437202987, "percentage": 13.2, "elapsed_time": "0:11:59", "remaining_time": "1:18:48", "throughput": 10383.5, "total_tokens": 7468800}
{"current_steps": 7785, "total_steps": 58920, "loss": 0.0872, "lr": 1.993724522729207e-06, "epoch": 0.6606415478615071, "percentage": 13.21, "elapsed_time": "0:11:59", "remaining_time": "1:18:47", "throughput": 10384.9, "total_tokens": 7473856}
{"current_steps": 7790, "total_steps": 58920, "loss": 0.0312, "lr": 1.9936913453822684e-06, "epoch": 0.6610658520027155, "percentage": 13.22, "elapsed_time": "0:12:00", "remaining_time": "1:18:46", "throughput": 10385.47, "total_tokens": 7478144}
{"current_steps": 7795, "total_steps": 58920, "loss": 0.09, "lr": 1.993658080842502e-06, "epoch": 0.6614901561439239, "percentage": 13.23, "elapsed_time": "0:12:00", "remaining_time": "1:18:45", "throughput": 10386.06, "total_tokens": 7482432}
{"current_steps": 7800, "total_steps": 58920, "loss": 0.0801, "lr": 1.9936247291128266e-06, "epoch": 0.6619144602851323, "percentage": 13.24, "elapsed_time": "0:12:00", "remaining_time": "1:18:44", "throughput": 10387.41, "total_tokens": 7487488}
{"current_steps": 7805, "total_steps": 58920, "loss": 0.0784, "lr": 1.993591290196169e-06, "epoch": 0.6623387644263408, "percentage": 13.25, "elapsed_time": "0:12:01", "remaining_time": "1:18:43", "throughput": 10388.26, "total_tokens": 7492032}
{"current_steps": 7810, "total_steps": 58920, "loss": 0.0484, "lr": 1.9935577640954623e-06, "epoch": 0.6627630685675492, "percentage": 13.26, "elapsed_time": "0:12:01", "remaining_time": "1:18:42", "throughput": 10389.09, "total_tokens": 7496576}
{"current_steps": 7815, "total_steps": 58920, "loss": 0.0308, "lr": 1.9935241508136495e-06, "epoch": 0.6631873727087576, "percentage": 13.26, "elapsed_time": "0:12:01", "remaining_time": "1:18:41", "throughput": 10389.87, "total_tokens": 7501056}
{"current_steps": 7820, "total_steps": 58920, "loss": 0.0743, "lr": 1.993490450353679e-06, "epoch": 0.663611676849966, "percentage": 13.27, "elapsed_time": "0:12:02", "remaining_time": "1:18:40", "throughput": 10390.93, "total_tokens": 7505792}
{"current_steps": 7825, "total_steps": 58920, "loss": 0.0611, "lr": 1.993456662718509e-06, "epoch": 0.6640359809911744, "percentage": 13.28, "elapsed_time": "0:12:02", "remaining_time": "1:18:39", "throughput": 10392.07, "total_tokens": 7510528}
{"current_steps": 7830, "total_steps": 58920, "loss": 0.0596, "lr": 1.993422787911104e-06, "epoch": 0.6644602851323829, "percentage": 13.29, "elapsed_time": "0:12:03", "remaining_time": "1:18:38", "throughput": 10393.03, "total_tokens": 7515200}
{"current_steps": 7835, "total_steps": 58920, "loss": 0.0176, "lr": 1.9933888259344356e-06, "epoch": 0.6648845892735913, "percentage": 13.3, "elapsed_time": "0:12:03", "remaining_time": "1:18:37", "throughput": 10394.34, "total_tokens": 7520128}
{"current_steps": 7840, "total_steps": 58920, "loss": 0.0508, "lr": 1.9933547767914846e-06, "epoch": 0.6653088934147997, "percentage": 13.31, "elapsed_time": "0:12:03", "remaining_time": "1:18:36", "throughput": 10395.0, "total_tokens": 7524544}
{"current_steps": 7845, "total_steps": 58920, "loss": 0.1211, "lr": 1.9933206404852384e-06, "epoch": 0.6657331975560081, "percentage": 13.31, "elapsed_time": "0:12:04", "remaining_time": "1:18:35", "throughput": 10396.48, "total_tokens": 7529664}
{"current_steps": 7850, "total_steps": 58920, "loss": 0.043, "lr": 1.993286417018692e-06, "epoch": 0.6661575016972165, "percentage": 13.32, "elapsed_time": "0:12:04", "remaining_time": "1:18:34", "throughput": 10396.83, "total_tokens": 7533760}
{"current_steps": 7855, "total_steps": 58920, "loss": 0.0526, "lr": 1.9932521063948492e-06, "epoch": 0.666581805838425, "percentage": 13.33, "elapsed_time": "0:12:04", "remaining_time": "1:18:33", "throughput": 10397.86, "total_tokens": 7538432}
{"current_steps": 7860, "total_steps": 58920, "loss": 0.0704, "lr": 1.9932177086167197e-06, "epoch": 0.6670061099796334, "percentage": 13.34, "elapsed_time": "0:12:05", "remaining_time": "1:18:32", "throughput": 10398.93, "total_tokens": 7543168}
{"current_steps": 7865, "total_steps": 58920, "loss": 0.0497, "lr": 1.993183223687323e-06, "epoch": 0.6674304141208418, "percentage": 13.35, "elapsed_time": "0:12:05", "remaining_time": "1:18:31", "throughput": 10399.98, "total_tokens": 7547840}
{"current_steps": 7870, "total_steps": 58920, "loss": 0.016, "lr": 1.9931486516096837e-06, "epoch": 0.6678547182620502, "percentage": 13.36, "elapsed_time": "0:12:06", "remaining_time": "1:18:30", "throughput": 10401.19, "total_tokens": 7552768}
{"current_steps": 7875, "total_steps": 58920, "loss": 0.1189, "lr": 1.993113992386836e-06, "epoch": 0.6682790224032586, "percentage": 13.37, "elapsed_time": "0:12:06", "remaining_time": "1:18:29", "throughput": 10402.09, "total_tokens": 7557312}
{"current_steps": 7880, "total_steps": 58920, "loss": 0.098, "lr": 1.993079246021821e-06, "epoch": 0.6687033265444671, "percentage": 13.37, "elapsed_time": "0:12:06", "remaining_time": "1:18:28", "throughput": 10403.01, "total_tokens": 7561920}
{"current_steps": 7885, "total_steps": 58920, "loss": 0.0696, "lr": 1.9930444125176883e-06, "epoch": 0.6691276306856755, "percentage": 13.38, "elapsed_time": "0:12:07", "remaining_time": "1:18:27", "throughput": 10404.52, "total_tokens": 7567104}
{"current_steps": 7890, "total_steps": 58920, "loss": 0.0128, "lr": 1.993009491877493e-06, "epoch": 0.6695519348268839, "percentage": 13.39, "elapsed_time": "0:12:07", "remaining_time": "1:18:26", "throughput": 10405.31, "total_tokens": 7571584}
{"current_steps": 7895, "total_steps": 58920, "loss": 0.046, "lr": 1.9929744841043007e-06, "epoch": 0.6699762389680923, "percentage": 13.4, "elapsed_time": "0:12:08", "remaining_time": "1:18:25", "throughput": 10406.35, "total_tokens": 7576256}
{"current_steps": 7900, "total_steps": 58920, "loss": 0.0624, "lr": 1.9929393892011822e-06, "epoch": 0.6704005431093008, "percentage": 13.41, "elapsed_time": "0:12:08", "remaining_time": "1:18:24", "throughput": 10407.53, "total_tokens": 7581248}
{"current_steps": 7905, "total_steps": 58920, "loss": 0.0279, "lr": 1.9929042071712173e-06, "epoch": 0.6708248472505092, "percentage": 13.42, "elapsed_time": "0:12:08", "remaining_time": "1:18:23", "throughput": 10408.56, "total_tokens": 7585984}
{"current_steps": 7910, "total_steps": 58920, "loss": 0.1071, "lr": 1.992868938017493e-06, "epoch": 0.6712491513917176, "percentage": 13.42, "elapsed_time": "0:12:09", "remaining_time": "1:18:22", "throughput": 10409.46, "total_tokens": 7590528}
{"current_steps": 7915, "total_steps": 58920, "loss": 0.0857, "lr": 1.9928335817431045e-06, "epoch": 0.671673455532926, "percentage": 13.43, "elapsed_time": "0:12:09", "remaining_time": "1:18:21", "throughput": 10410.53, "total_tokens": 7595328}
{"current_steps": 7920, "total_steps": 58920, "loss": 0.0919, "lr": 1.9927981383511536e-06, "epoch": 0.6720977596741344, "percentage": 13.44, "elapsed_time": "0:12:09", "remaining_time": "1:18:20", "throughput": 10411.62, "total_tokens": 7600128}
{"current_steps": 7925, "total_steps": 58920, "loss": 0.02, "lr": 1.9927626078447504e-06, "epoch": 0.6725220638153429, "percentage": 13.45, "elapsed_time": "0:12:10", "remaining_time": "1:18:19", "throughput": 10412.01, "total_tokens": 7604288}
{"current_steps": 7930, "total_steps": 58920, "loss": 0.0534, "lr": 1.992726990227013e-06, "epoch": 0.6729463679565513, "percentage": 13.46, "elapsed_time": "0:12:10", "remaining_time": "1:18:18", "throughput": 10413.37, "total_tokens": 7609280}
{"current_steps": 7935, "total_steps": 58920, "loss": 0.0816, "lr": 1.992691285501066e-06, "epoch": 0.6733706720977597, "percentage": 13.47, "elapsed_time": "0:12:11", "remaining_time": "1:18:17", "throughput": 10414.94, "total_tokens": 7614528}
{"current_steps": 7940, "total_steps": 58920, "loss": 0.0924, "lr": 1.992655493670043e-06, "epoch": 0.6737949762389681, "percentage": 13.48, "elapsed_time": "0:12:11", "remaining_time": "1:18:16", "throughput": 10416.01, "total_tokens": 7619264}
{"current_steps": 7945, "total_steps": 58920, "loss": 0.0053, "lr": 1.9926196147370847e-06, "epoch": 0.6742192803801765, "percentage": 13.48, "elapsed_time": "0:12:11", "remaining_time": "1:18:15", "throughput": 10417.28, "total_tokens": 7624192}
{"current_steps": 7950, "total_steps": 58920, "loss": 0.0197, "lr": 1.992583648705339e-06, "epoch": 0.674643584521385, "percentage": 13.49, "elapsed_time": "0:12:12", "remaining_time": "1:18:14", "throughput": 10418.49, "total_tokens": 7629120}
{"current_steps": 7955, "total_steps": 58920, "loss": 0.0734, "lr": 1.9925475955779614e-06, "epoch": 0.6750678886625934, "percentage": 13.5, "elapsed_time": "0:12:12", "remaining_time": "1:18:13", "throughput": 10419.6, "total_tokens": 7633984}
{"current_steps": 7960, "total_steps": 58920, "loss": 0.0893, "lr": 1.9925114553581163e-06, "epoch": 0.6754921928038018, "percentage": 13.51, "elapsed_time": "0:12:13", "remaining_time": "1:18:12", "throughput": 10420.88, "total_tokens": 7638976}
{"current_steps": 7965, "total_steps": 58920, "loss": 0.001, "lr": 1.992475228048974e-06, "epoch": 0.6759164969450102, "percentage": 13.52, "elapsed_time": "0:12:13", "remaining_time": "1:18:11", "throughput": 10421.71, "total_tokens": 7643520}
{"current_steps": 7970, "total_steps": 58920, "loss": 0.1131, "lr": 1.992438913653714e-06, "epoch": 0.6763408010862186, "percentage": 13.53, "elapsed_time": "0:12:13", "remaining_time": "1:18:11", "throughput": 10423.04, "total_tokens": 7648576}
{"current_steps": 7975, "total_steps": 58920, "loss": 0.036, "lr": 1.9924025121755226e-06, "epoch": 0.676765105227427, "percentage": 13.54, "elapsed_time": "0:12:14", "remaining_time": "1:18:10", "throughput": 10424.38, "total_tokens": 7653632}
{"current_steps": 7980, "total_steps": 58920, "loss": 0.0365, "lr": 1.9923660236175936e-06, "epoch": 0.6771894093686355, "percentage": 13.54, "elapsed_time": "0:12:14", "remaining_time": "1:18:09", "throughput": 10425.2, "total_tokens": 7658176}
{"current_steps": 7985, "total_steps": 58920, "loss": 0.1448, "lr": 1.9923294479831293e-06, "epoch": 0.6776137135098439, "percentage": 13.55, "elapsed_time": "0:12:14", "remaining_time": "1:18:08", "throughput": 10426.36, "total_tokens": 7663040}
{"current_steps": 7990, "total_steps": 58920, "loss": 0.0868, "lr": 1.9922927852753386e-06, "epoch": 0.6780380176510523, "percentage": 13.56, "elapsed_time": "0:12:15", "remaining_time": "1:18:07", "throughput": 10427.76, "total_tokens": 7668160}
{"current_steps": 7995, "total_steps": 58920, "loss": 0.0628, "lr": 1.9922560354974386e-06, "epoch": 0.6784623217922607, "percentage": 13.57, "elapsed_time": "0:12:15", "remaining_time": "1:18:06", "throughput": 10428.93, "total_tokens": 7673024}
{"current_steps": 8000, "total_steps": 58920, "loss": 0.0606, "lr": 1.992219198652654e-06, "epoch": 0.6788866259334692, "percentage": 13.58, "elapsed_time": "0:12:16", "remaining_time": "1:18:05", "throughput": 10429.9, "total_tokens": 7677696}
{"current_steps": 8005, "total_steps": 58920, "loss": 0.044, "lr": 1.9921822747442167e-06, "epoch": 0.6793109300746776, "percentage": 13.59, "elapsed_time": "0:12:16", "remaining_time": "1:18:04", "throughput": 10431.29, "total_tokens": 7682752}
{"current_steps": 8010, "total_steps": 58920, "loss": 0.0838, "lr": 1.9921452637753675e-06, "epoch": 0.679735234215886, "percentage": 13.59, "elapsed_time": "0:12:16", "remaining_time": "1:18:03", "throughput": 10432.51, "total_tokens": 7687872}
{"current_steps": 8015, "total_steps": 58920, "loss": 0.0986, "lr": 1.9921081657493538e-06, "epoch": 0.6801595383570944, "percentage": 13.6, "elapsed_time": "0:12:17", "remaining_time": "1:18:02", "throughput": 10433.73, "total_tokens": 7692800}
{"current_steps": 8020, "total_steps": 58920, "loss": 0.0075, "lr": 1.99207098066943e-06, "epoch": 0.6805838424983028, "percentage": 13.61, "elapsed_time": "0:12:17", "remaining_time": "1:18:01", "throughput": 10434.59, "total_tokens": 7697472}
{"current_steps": 8025, "total_steps": 58920, "loss": 0.0826, "lr": 1.9920337085388595e-06, "epoch": 0.6810081466395111, "percentage": 13.62, "elapsed_time": "0:12:18", "remaining_time": "1:18:00", "throughput": 10435.59, "total_tokens": 7702336}
{"current_steps": 8030, "total_steps": 58920, "loss": 0.1123, "lr": 1.9919963493609135e-06, "epoch": 0.6814324507807196, "percentage": 13.63, "elapsed_time": "0:12:18", "remaining_time": "1:18:00", "throughput": 10436.58, "total_tokens": 7707136}
{"current_steps": 8035, "total_steps": 58920, "loss": 0.0869, "lr": 1.9919589031388688e-06, "epoch": 0.681856754921928, "percentage": 13.64, "elapsed_time": "0:12:18", "remaining_time": "1:17:59", "throughput": 10437.55, "total_tokens": 7711808}
{"current_steps": 8040, "total_steps": 58920, "loss": 0.0676, "lr": 1.991921369876012e-06, "epoch": 0.6822810590631364, "percentage": 13.65, "elapsed_time": "0:12:19", "remaining_time": "1:17:58", "throughput": 10438.37, "total_tokens": 7716352}
{"current_steps": 8045, "total_steps": 58920, "loss": 0.0997, "lr": 1.991883749575636e-06, "epoch": 0.6827053632043448, "percentage": 13.65, "elapsed_time": "0:12:19", "remaining_time": "1:17:57", "throughput": 10439.35, "total_tokens": 7721024}
{"current_steps": 8050, "total_steps": 58920, "loss": 0.0688, "lr": 1.9918460422410424e-06, "epoch": 0.6831296673455532, "percentage": 13.66, "elapsed_time": "0:12:20", "remaining_time": "1:17:56", "throughput": 10440.8, "total_tokens": 7726208}
{"current_steps": 8055, "total_steps": 58920, "loss": 0.0897, "lr": 1.99180824787554e-06, "epoch": 0.6835539714867617, "percentage": 13.67, "elapsed_time": "0:12:20", "remaining_time": "1:17:55", "throughput": 10442.0, "total_tokens": 7731136}
{"current_steps": 8060, "total_steps": 58920, "loss": 0.1502, "lr": 1.991770366482444e-06, "epoch": 0.6839782756279701, "percentage": 13.68, "elapsed_time": "0:12:20", "remaining_time": "1:17:54", "throughput": 10442.68, "total_tokens": 7735552}
{"current_steps": 8065, "total_steps": 58920, "loss": 0.0943, "lr": 1.9917323980650796e-06, "epoch": 0.6844025797691785, "percentage": 13.69, "elapsed_time": "0:12:21", "remaining_time": "1:17:53", "throughput": 10443.42, "total_tokens": 7740032}
{"current_steps": 8070, "total_steps": 58920, "loss": 0.0662, "lr": 1.9916943426267776e-06, "epoch": 0.6848268839103869, "percentage": 13.7, "elapsed_time": "0:12:21", "remaining_time": "1:17:52", "throughput": 10444.61, "total_tokens": 7744960}
{"current_steps": 8075, "total_steps": 58920, "loss": 0.1514, "lr": 1.991656200170878e-06, "epoch": 0.6852511880515954, "percentage": 13.71, "elapsed_time": "0:12:21", "remaining_time": "1:17:51", "throughput": 10445.55, "total_tokens": 7749632}
{"current_steps": 8080, "total_steps": 58920, "loss": 0.0689, "lr": 1.991617970700727e-06, "epoch": 0.6856754921928038, "percentage": 13.71, "elapsed_time": "0:12:22", "remaining_time": "1:17:50", "throughput": 10446.35, "total_tokens": 7754176}
{"current_steps": 8085, "total_steps": 58920, "loss": 0.1005, "lr": 1.9915796542196795e-06, "epoch": 0.6860997963340122, "percentage": 13.72, "elapsed_time": "0:12:22", "remaining_time": "1:17:49", "throughput": 10447.82, "total_tokens": 7759360}
{"current_steps": 8090, "total_steps": 58920, "loss": 0.0983, "lr": 1.991541250731097e-06, "epoch": 0.6865241004752206, "percentage": 13.73, "elapsed_time": "0:12:23", "remaining_time": "1:17:48", "throughput": 10448.64, "total_tokens": 7763904}
{"current_steps": 8095, "total_steps": 58920, "loss": 0.0176, "lr": 1.9915027602383497e-06, "epoch": 0.686948404616429, "percentage": 13.74, "elapsed_time": "0:12:23", "remaining_time": "1:17:47", "throughput": 10449.33, "total_tokens": 7768320}
{"current_steps": 8100, "total_steps": 58920, "loss": 0.1019, "lr": 1.9914641827448153e-06, "epoch": 0.6873727087576375, "percentage": 13.75, "elapsed_time": "0:12:23", "remaining_time": "1:17:46", "throughput": 10450.26, "total_tokens": 7772928}
{"current_steps": 8105, "total_steps": 58920, "loss": 0.0457, "lr": 1.9914255182538784e-06, "epoch": 0.6877970128988459, "percentage": 13.76, "elapsed_time": "0:12:24", "remaining_time": "1:17:45", "throughput": 10450.89, "total_tokens": 7777280}
{"current_steps": 8110, "total_steps": 58920, "loss": 0.0766, "lr": 1.9913867667689316e-06, "epoch": 0.6882213170400543, "percentage": 13.76, "elapsed_time": "0:12:24", "remaining_time": "1:17:44", "throughput": 10451.95, "total_tokens": 7782080}
{"current_steps": 8115, "total_steps": 58920, "loss": 0.0925, "lr": 1.991347928293376e-06, "epoch": 0.6886456211812627, "percentage": 13.77, "elapsed_time": "0:12:24", "remaining_time": "1:17:43", "throughput": 10453.07, "total_tokens": 7786880}
{"current_steps": 8120, "total_steps": 58920, "loss": 0.0629, "lr": 1.9913090028306184e-06, "epoch": 0.6890699253224711, "percentage": 13.78, "elapsed_time": "0:12:25", "remaining_time": "1:17:42", "throughput": 10453.67, "total_tokens": 7791232}
{"current_steps": 8125, "total_steps": 58920, "loss": 0.0176, "lr": 1.991269990384075e-06, "epoch": 0.6894942294636796, "percentage": 13.79, "elapsed_time": "0:12:25", "remaining_time": "1:17:41", "throughput": 10454.72, "total_tokens": 7796160}
{"current_steps": 8130, "total_steps": 58920, "loss": 0.0302, "lr": 1.991230890957169e-06, "epoch": 0.689918533604888, "percentage": 13.8, "elapsed_time": "0:12:26", "remaining_time": "1:17:41", "throughput": 10455.84, "total_tokens": 7801024}
{"current_steps": 8135, "total_steps": 58920, "loss": 0.0829, "lr": 1.991191704553331e-06, "epoch": 0.6903428377460964, "percentage": 13.81, "elapsed_time": "0:12:26", "remaining_time": "1:17:40", "throughput": 10457.02, "total_tokens": 7805952}
{"current_steps": 8140, "total_steps": 58920, "loss": 0.055, "lr": 1.991152431176e-06, "epoch": 0.6907671418873048, "percentage": 13.82, "elapsed_time": "0:12:26", "remaining_time": "1:17:39", "throughput": 10458.34, "total_tokens": 7811008}
{"current_steps": 8145, "total_steps": 58920, "loss": 0.0241, "lr": 1.991113070828621e-06, "epoch": 0.6911914460285132, "percentage": 13.82, "elapsed_time": "0:12:27", "remaining_time": "1:17:38", "throughput": 10458.91, "total_tokens": 7815296}
{"current_steps": 8150, "total_steps": 58920, "loss": 0.0699, "lr": 1.991073623514649e-06, "epoch": 0.6916157501697217, "percentage": 13.83, "elapsed_time": "0:12:27", "remaining_time": "1:17:37", "throughput": 10460.77, "total_tokens": 7820864}
{"current_steps": 8155, "total_steps": 58920, "loss": 0.1106, "lr": 1.991034089237545e-06, "epoch": 0.6920400543109301, "percentage": 13.84, "elapsed_time": "0:12:28", "remaining_time": "1:17:36", "throughput": 10462.01, "total_tokens": 7825856}
{"current_steps": 8160, "total_steps": 58920, "loss": 0.0748, "lr": 1.9909944680007775e-06, "epoch": 0.6924643584521385, "percentage": 13.85, "elapsed_time": "0:12:28", "remaining_time": "1:17:35", "throughput": 10462.83, "total_tokens": 7830400}
{"current_steps": 8165, "total_steps": 58920, "loss": 0.0268, "lr": 1.990954759807823e-06, "epoch": 0.6928886625933469, "percentage": 13.86, "elapsed_time": "0:12:28", "remaining_time": "1:17:34", "throughput": 10464.46, "total_tokens": 7835776}
{"current_steps": 8170, "total_steps": 58920, "loss": 0.0891, "lr": 1.9909149646621667e-06, "epoch": 0.6933129667345553, "percentage": 13.87, "elapsed_time": "0:12:29", "remaining_time": "1:17:33", "throughput": 10465.53, "total_tokens": 7840640}
{"current_steps": 8175, "total_steps": 58920, "loss": 0.0835, "lr": 1.9908750825672994e-06, "epoch": 0.6937372708757638, "percentage": 13.87, "elapsed_time": "0:12:29", "remaining_time": "1:17:32", "throughput": 10466.29, "total_tokens": 7845120}
{"current_steps": 8180, "total_steps": 58920, "loss": 0.0425, "lr": 1.9908351135267218e-06, "epoch": 0.6941615750169722, "percentage": 13.88, "elapsed_time": "0:12:29", "remaining_time": "1:17:31", "throughput": 10467.12, "total_tokens": 7849664}
{"current_steps": 8185, "total_steps": 58920, "loss": 0.0216, "lr": 1.9907950575439402e-06, "epoch": 0.6945858791581806, "percentage": 13.89, "elapsed_time": "0:12:30", "remaining_time": "1:17:30", "throughput": 10467.79, "total_tokens": 7854080}
{"current_steps": 8190, "total_steps": 58920, "loss": 0.0394, "lr": 1.990754914622469e-06, "epoch": 0.695010183299389, "percentage": 13.9, "elapsed_time": "0:12:30", "remaining_time": "1:17:29", "throughput": 10468.08, "total_tokens": 7858176}
{"current_steps": 8195, "total_steps": 58920, "loss": 0.022, "lr": 1.9907146847658315e-06, "epoch": 0.6954344874405974, "percentage": 13.91, "elapsed_time": "0:12:31", "remaining_time": "1:17:28", "throughput": 10469.11, "total_tokens": 7862912}
{"current_steps": 8200, "total_steps": 58920, "loss": 0.0689, "lr": 1.9906743679775575e-06, "epoch": 0.6958587915818059, "percentage": 13.92, "elapsed_time": "0:12:31", "remaining_time": "1:17:27", "throughput": 10470.11, "total_tokens": 7867648}
{"current_steps": 8205, "total_steps": 58920, "loss": 0.0918, "lr": 1.9906339642611843e-06, "epoch": 0.6962830957230143, "percentage": 13.93, "elapsed_time": "0:12:31", "remaining_time": "1:17:27", "throughput": 10471.87, "total_tokens": 7873152}
{"current_steps": 8210, "total_steps": 58920, "loss": 0.0694, "lr": 1.990593473620258e-06, "epoch": 0.6967073998642227, "percentage": 13.93, "elapsed_time": "0:12:32", "remaining_time": "1:17:26", "throughput": 10472.82, "total_tokens": 7877824}
{"current_steps": 8215, "total_steps": 58920, "loss": 0.1042, "lr": 1.9905528960583304e-06, "epoch": 0.6971317040054311, "percentage": 13.94, "elapsed_time": "0:12:32", "remaining_time": "1:17:25", "throughput": 10473.99, "total_tokens": 7882688}
{"current_steps": 8220, "total_steps": 58920, "loss": 0.0431, "lr": 1.9905122315789625e-06, "epoch": 0.6975560081466395, "percentage": 13.95, "elapsed_time": "0:12:32", "remaining_time": "1:17:24", "throughput": 10475.02, "total_tokens": 7887424}
{"current_steps": 8225, "total_steps": 58920, "loss": 0.0217, "lr": 1.9904714801857227e-06, "epoch": 0.697980312287848, "percentage": 13.96, "elapsed_time": "0:12:33", "remaining_time": "1:17:23", "throughput": 10475.45, "total_tokens": 7891584}
{"current_steps": 8230, "total_steps": 58920, "loss": 0.1133, "lr": 1.9904306418821866e-06, "epoch": 0.6984046164290564, "percentage": 13.97, "elapsed_time": "0:12:33", "remaining_time": "1:17:22", "throughput": 10476.69, "total_tokens": 7896576}
{"current_steps": 8235, "total_steps": 58920, "loss": 0.0714, "lr": 1.9903897166719373e-06, "epoch": 0.6988289205702648, "percentage": 13.98, "elapsed_time": "0:12:34", "remaining_time": "1:17:21", "throughput": 10477.78, "total_tokens": 7901376}
{"current_steps": 8240, "total_steps": 58920, "loss": 0.0313, "lr": 1.9903487045585664e-06, "epoch": 0.6992532247114732, "percentage": 13.99, "elapsed_time": "0:12:34", "remaining_time": "1:17:20", "throughput": 10479.01, "total_tokens": 7906368}
{"current_steps": 8245, "total_steps": 58920, "loss": 0.0936, "lr": 1.9903076055456724e-06, "epoch": 0.6996775288526816, "percentage": 13.99, "elapsed_time": "0:12:34", "remaining_time": "1:17:19", "throughput": 10480.15, "total_tokens": 7911232}
{"current_steps": 8250, "total_steps": 58920, "loss": 0.0813, "lr": 1.9902664196368613e-06, "epoch": 0.7001018329938901, "percentage": 14.0, "elapsed_time": "0:12:35", "remaining_time": "1:17:18", "throughput": 10480.95, "total_tokens": 7915776}
{"current_steps": 8255, "total_steps": 58920, "loss": 0.0208, "lr": 1.9902251468357475e-06, "epoch": 0.7005261371350985, "percentage": 14.01, "elapsed_time": "0:12:35", "remaining_time": "1:17:17", "throughput": 10481.6, "total_tokens": 7920192}
{"current_steps": 8260, "total_steps": 58920, "loss": 0.1007, "lr": 1.990183787145952e-06, "epoch": 0.7009504412763069, "percentage": 14.02, "elapsed_time": "0:12:36", "remaining_time": "1:17:16", "throughput": 10482.47, "total_tokens": 7924800}
{"current_steps": 8265, "total_steps": 58920, "loss": 0.062, "lr": 1.9901423405711044e-06, "epoch": 0.7013747454175153, "percentage": 14.03, "elapsed_time": "0:12:36", "remaining_time": "1:17:15", "throughput": 10483.6, "total_tokens": 7929664}
{"current_steps": 8270, "total_steps": 58920, "loss": 0.0859, "lr": 1.9901008071148414e-06, "epoch": 0.7017990495587237, "percentage": 14.04, "elapsed_time": "0:12:36", "remaining_time": "1:17:14", "throughput": 10484.68, "total_tokens": 7934464}
{"current_steps": 8275, "total_steps": 58920, "loss": 0.0461, "lr": 1.990059186780807e-06, "epoch": 0.7022233536999322, "percentage": 14.04, "elapsed_time": "0:12:37", "remaining_time": "1:17:13", "throughput": 10485.77, "total_tokens": 7939264}
{"current_steps": 8280, "total_steps": 58920, "loss": 0.1047, "lr": 1.9900174795726536e-06, "epoch": 0.7026476578411406, "percentage": 14.05, "elapsed_time": "0:12:37", "remaining_time": "1:17:12", "throughput": 10486.29, "total_tokens": 7943552}
{"current_steps": 8285, "total_steps": 58920, "loss": 0.0434, "lr": 1.989975685494041e-06, "epoch": 0.703071961982349, "percentage": 14.06, "elapsed_time": "0:12:37", "remaining_time": "1:17:11", "throughput": 10487.04, "total_tokens": 7948032}
{"current_steps": 8290, "total_steps": 58920, "loss": 0.065, "lr": 1.9899338045486364e-06, "epoch": 0.7034962661235573, "percentage": 14.07, "elapsed_time": "0:12:38", "remaining_time": "1:17:11", "throughput": 10488.68, "total_tokens": 7953408}
{"current_steps": 8295, "total_steps": 58920, "loss": 0.0602, "lr": 1.989891836740114e-06, "epoch": 0.7039205702647657, "percentage": 14.08, "elapsed_time": "0:12:38", "remaining_time": "1:17:10", "throughput": 10489.26, "total_tokens": 7957760}
{"current_steps": 8300, "total_steps": 58920, "loss": 0.0159, "lr": 1.9898497820721574e-06, "epoch": 0.7043448744059742, "percentage": 14.09, "elapsed_time": "0:12:39", "remaining_time": "1:17:09", "throughput": 10491.43, "total_tokens": 7963712}
{"current_steps": 8305, "total_steps": 58920, "loss": 0.0826, "lr": 1.989807640548456e-06, "epoch": 0.7047691785471826, "percentage": 14.1, "elapsed_time": "0:12:39", "remaining_time": "1:17:08", "throughput": 10492.6, "total_tokens": 7968576}
{"current_steps": 8310, "total_steps": 58920, "loss": 0.107, "lr": 1.989765412172708e-06, "epoch": 0.705193482688391, "percentage": 14.1, "elapsed_time": "0:12:39", "remaining_time": "1:17:07", "throughput": 10493.46, "total_tokens": 7973184}
{"current_steps": 8315, "total_steps": 58920, "loss": 0.0428, "lr": 1.989723096948619e-06, "epoch": 0.7056177868295994, "percentage": 14.11, "elapsed_time": "0:12:40", "remaining_time": "1:17:06", "throughput": 10494.31, "total_tokens": 7977792}
{"current_steps": 8320, "total_steps": 58920, "loss": 0.0419, "lr": 1.989680694879901e-06, "epoch": 0.7060420909708078, "percentage": 14.12, "elapsed_time": "0:12:40", "remaining_time": "1:17:05", "throughput": 10494.53, "total_tokens": 7981824}
{"current_steps": 8325, "total_steps": 58920, "loss": 0.0816, "lr": 1.9896382059702758e-06, "epoch": 0.7064663951120163, "percentage": 14.13, "elapsed_time": "0:12:40", "remaining_time": "1:17:04", "throughput": 10495.04, "total_tokens": 7986112}
{"current_steps": 8330, "total_steps": 58920, "loss": 0.1464, "lr": 1.9895956302234706e-06, "epoch": 0.7068906992532247, "percentage": 14.14, "elapsed_time": "0:12:41", "remaining_time": "1:17:03", "throughput": 10495.79, "total_tokens": 7990592}
{"current_steps": 8335, "total_steps": 58920, "loss": 0.1503, "lr": 1.989552967643222e-06, "epoch": 0.7073150033944331, "percentage": 14.15, "elapsed_time": "0:12:41", "remaining_time": "1:17:02", "throughput": 10496.55, "total_tokens": 7995136}
{"current_steps": 8340, "total_steps": 58920, "loss": 0.0507, "lr": 1.989510218233273e-06, "epoch": 0.7077393075356415, "percentage": 14.15, "elapsed_time": "0:12:42", "remaining_time": "1:17:01", "throughput": 10497.57, "total_tokens": 7999872}
{"current_steps": 8345, "total_steps": 58920, "loss": 0.0644, "lr": 1.9894673819973753e-06, "epoch": 0.7081636116768499, "percentage": 14.16, "elapsed_time": "0:12:42", "remaining_time": "1:17:00", "throughput": 10498.53, "total_tokens": 8004608}
{"current_steps": 8350, "total_steps": 58920, "loss": 0.0264, "lr": 1.989424458939287e-06, "epoch": 0.7085879158180584, "percentage": 14.17, "elapsed_time": "0:12:42", "remaining_time": "1:16:59", "throughput": 10499.18, "total_tokens": 8009024}
{"current_steps": 8355, "total_steps": 58920, "loss": 0.0574, "lr": 1.989381449062775e-06, "epoch": 0.7090122199592668, "percentage": 14.18, "elapsed_time": "0:12:43", "remaining_time": "1:16:58", "throughput": 10499.89, "total_tokens": 8013504}
{"current_steps": 8360, "total_steps": 58920, "loss": 0.1165, "lr": 1.9893383523716128e-06, "epoch": 0.7094365241004752, "percentage": 14.19, "elapsed_time": "0:12:43", "remaining_time": "1:16:58", "throughput": 10501.09, "total_tokens": 8018432}
{"current_steps": 8365, "total_steps": 58920, "loss": 0.0066, "lr": 1.9892951688695827e-06, "epoch": 0.7098608282416836, "percentage": 14.2, "elapsed_time": "0:12:43", "remaining_time": "1:16:57", "throughput": 10501.74, "total_tokens": 8022848}
{"current_steps": 8370, "total_steps": 58920, "loss": 0.0462, "lr": 1.9892518985604728e-06, "epoch": 0.710285132382892, "percentage": 14.21, "elapsed_time": "0:12:44", "remaining_time": "1:16:56", "throughput": 10502.51, "total_tokens": 8027392}
{"current_steps": 8375, "total_steps": 58920, "loss": 0.1663, "lr": 1.9892085414480808e-06, "epoch": 0.7107094365241005, "percentage": 14.21, "elapsed_time": "0:12:44", "remaining_time": "1:16:55", "throughput": 10503.95, "total_tokens": 8032640}
{"current_steps": 8380, "total_steps": 58920, "loss": 0.0571, "lr": 1.9891650975362103e-06, "epoch": 0.7111337406653089, "percentage": 14.22, "elapsed_time": "0:12:45", "remaining_time": "1:16:54", "throughput": 10504.87, "total_tokens": 8037312}
{"current_steps": 8385, "total_steps": 58920, "loss": 0.1131, "lr": 1.989121566828674e-06, "epoch": 0.7115580448065173, "percentage": 14.23, "elapsed_time": "0:12:45", "remaining_time": "1:16:53", "throughput": 10506.05, "total_tokens": 8042240}
{"current_steps": 8390, "total_steps": 58920, "loss": 0.0413, "lr": 1.9890779493292918e-06, "epoch": 0.7119823489477257, "percentage": 14.24, "elapsed_time": "0:12:45", "remaining_time": "1:16:52", "throughput": 10507.38, "total_tokens": 8047360}
{"current_steps": 8395, "total_steps": 58920, "loss": 0.0632, "lr": 1.9890342450418904e-06, "epoch": 0.7124066530889341, "percentage": 14.25, "elapsed_time": "0:12:46", "remaining_time": "1:16:51", "throughput": 10508.33, "total_tokens": 8052096}
{"current_steps": 8400, "total_steps": 58920, "loss": 0.0374, "lr": 1.988990453970305e-06, "epoch": 0.7128309572301426, "percentage": 14.26, "elapsed_time": "0:12:46", "remaining_time": "1:16:50", "throughput": 10509.42, "total_tokens": 8056960}
{"current_steps": 8405, "total_steps": 58920, "loss": 0.0585, "lr": 1.9889465761183776e-06, "epoch": 0.713255261371351, "percentage": 14.27, "elapsed_time": "0:12:47", "remaining_time": "1:16:49", "throughput": 10510.26, "total_tokens": 8061568}
{"current_steps": 8410, "total_steps": 58920, "loss": 0.0562, "lr": 1.9889026114899594e-06, "epoch": 0.7136795655125594, "percentage": 14.27, "elapsed_time": "0:12:47", "remaining_time": "1:16:49", "throughput": 10511.53, "total_tokens": 8066624}
{"current_steps": 8415, "total_steps": 58920, "loss": 0.0579, "lr": 1.988858560088907e-06, "epoch": 0.7141038696537678, "percentage": 14.28, "elapsed_time": "0:12:47", "remaining_time": "1:16:48", "throughput": 10512.79, "total_tokens": 8071680}
{"current_steps": 8420, "total_steps": 58920, "loss": 0.0539, "lr": 1.9888144219190863e-06, "epoch": 0.7145281737949762, "percentage": 14.29, "elapsed_time": "0:12:48", "remaining_time": "1:16:47", "throughput": 10513.81, "total_tokens": 8076480}
{"current_steps": 8425, "total_steps": 58920, "loss": 0.0343, "lr": 1.98877019698437e-06, "epoch": 0.7149524779361847, "percentage": 14.3, "elapsed_time": "0:12:48", "remaining_time": "1:16:46", "throughput": 10514.32, "total_tokens": 8080768}
{"current_steps": 8430, "total_steps": 58920, "loss": 0.0761, "lr": 1.988725885288639e-06, "epoch": 0.7153767820773931, "percentage": 14.31, "elapsed_time": "0:12:48", "remaining_time": "1:16:45", "throughput": 10515.03, "total_tokens": 8085248}
{"current_steps": 8435, "total_steps": 58920, "loss": 0.0677, "lr": 1.9886814868357815e-06, "epoch": 0.7158010862186015, "percentage": 14.32, "elapsed_time": "0:12:49", "remaining_time": "1:16:44", "throughput": 10516.24, "total_tokens": 8090176}
{"current_steps": 8440, "total_steps": 58920, "loss": 0.0707, "lr": 1.988637001629693e-06, "epoch": 0.7162253903598099, "percentage": 14.32, "elapsed_time": "0:12:49", "remaining_time": "1:16:43", "throughput": 10516.72, "total_tokens": 8094464}
{"current_steps": 8445, "total_steps": 58920, "loss": 0.1023, "lr": 1.988592429674277e-06, "epoch": 0.7166496945010183, "percentage": 14.33, "elapsed_time": "0:12:50", "remaining_time": "1:16:42", "throughput": 10517.46, "total_tokens": 8099008}
{"current_steps": 8450, "total_steps": 58920, "loss": 0.0532, "lr": 1.9885477709734445e-06, "epoch": 0.7170739986422268, "percentage": 14.34, "elapsed_time": "0:12:50", "remaining_time": "1:16:41", "throughput": 10518.85, "total_tokens": 8104256}
{"current_steps": 8455, "total_steps": 58920, "loss": 0.0887, "lr": 1.9885030255311146e-06, "epoch": 0.7174983027834352, "percentage": 14.35, "elapsed_time": "0:12:50", "remaining_time": "1:16:40", "throughput": 10519.79, "total_tokens": 8109056}
{"current_steps": 8460, "total_steps": 58920, "loss": 0.1238, "lr": 1.988458193351213e-06, "epoch": 0.7179226069246436, "percentage": 14.36, "elapsed_time": "0:12:51", "remaining_time": "1:16:40", "throughput": 10521.11, "total_tokens": 8114176}
{"current_steps": 8465, "total_steps": 58920, "loss": 0.1177, "lr": 1.9884132744376737e-06, "epoch": 0.718346911065852, "percentage": 14.37, "elapsed_time": "0:12:51", "remaining_time": "1:16:39", "throughput": 10522.37, "total_tokens": 8119232}
{"current_steps": 8470, "total_steps": 58920, "loss": 0.0378, "lr": 1.988368268794438e-06, "epoch": 0.7187712152070604, "percentage": 14.38, "elapsed_time": "0:12:51", "remaining_time": "1:16:38", "throughput": 10523.15, "total_tokens": 8123840}
{"current_steps": 8475, "total_steps": 58920, "loss": 0.1088, "lr": 1.9883231764254556e-06, "epoch": 0.7191955193482689, "percentage": 14.38, "elapsed_time": "0:12:52", "remaining_time": "1:16:37", "throughput": 10523.78, "total_tokens": 8128256}
{"current_steps": 8480, "total_steps": 58920, "loss": 0.0664, "lr": 1.988277997334683e-06, "epoch": 0.7196198234894773, "percentage": 14.39, "elapsed_time": "0:12:52", "remaining_time": "1:16:36", "throughput": 10525.18, "total_tokens": 8133504}
{"current_steps": 8485, "total_steps": 58920, "loss": 0.016, "lr": 1.988232731526084e-06, "epoch": 0.7200441276306857, "percentage": 14.4, "elapsed_time": "0:12:53", "remaining_time": "1:16:35", "throughput": 10526.04, "total_tokens": 8138176}
{"current_steps": 8490, "total_steps": 58920, "loss": 0.0579, "lr": 1.9881873790036307e-06, "epoch": 0.7204684317718941, "percentage": 14.41, "elapsed_time": "0:12:53", "remaining_time": "1:16:34", "throughput": 10527.18, "total_tokens": 8143104}
{"current_steps": 8495, "total_steps": 58920, "loss": 0.046, "lr": 1.9881419397713025e-06, "epoch": 0.7208927359131025, "percentage": 14.42, "elapsed_time": "0:12:53", "remaining_time": "1:16:33", "throughput": 10527.87, "total_tokens": 8147584}
{"current_steps": 8500, "total_steps": 58920, "loss": 0.1619, "lr": 1.988096413833087e-06, "epoch": 0.721317040054311, "percentage": 14.43, "elapsed_time": "0:12:54", "remaining_time": "1:16:33", "throughput": 10529.21, "total_tokens": 8152896}
{"current_steps": 8505, "total_steps": 58920, "loss": 0.0257, "lr": 1.988050801192979e-06, "epoch": 0.7217413441955194, "percentage": 14.43, "elapsed_time": "0:12:54", "remaining_time": "1:16:32", "throughput": 10530.9, "total_tokens": 8158400}
{"current_steps": 8510, "total_steps": 58920, "loss": 0.0982, "lr": 1.9880051018549803e-06, "epoch": 0.7221656483367278, "percentage": 14.44, "elapsed_time": "0:12:55", "remaining_time": "1:16:31", "throughput": 10532.23, "total_tokens": 8163520}
{"current_steps": 8515, "total_steps": 58920, "loss": 0.0595, "lr": 1.987959315823101e-06, "epoch": 0.7225899524779362, "percentage": 14.45, "elapsed_time": "0:12:55", "remaining_time": "1:16:30", "throughput": 10533.15, "total_tokens": 8168256}
{"current_steps": 8520, "total_steps": 58920, "loss": 0.0331, "lr": 1.9879134431013587e-06, "epoch": 0.7230142566191446, "percentage": 14.46, "elapsed_time": "0:12:55", "remaining_time": "1:16:29", "throughput": 10534.04, "total_tokens": 8172928}
{"current_steps": 8525, "total_steps": 58920, "loss": 0.0532, "lr": 1.987867483693779e-06, "epoch": 0.7234385607603531, "percentage": 14.47, "elapsed_time": "0:12:56", "remaining_time": "1:16:28", "throughput": 10534.98, "total_tokens": 8177728}
{"current_steps": 8530, "total_steps": 58920, "loss": 0.0249, "lr": 1.987821437604394e-06, "epoch": 0.7238628649015615, "percentage": 14.48, "elapsed_time": "0:12:56", "remaining_time": "1:16:27", "throughput": 10535.75, "total_tokens": 8182272}
{"current_steps": 8535, "total_steps": 58920, "loss": 0.1651, "lr": 1.9877753048372443e-06, "epoch": 0.7242871690427699, "percentage": 14.49, "elapsed_time": "0:12:57", "remaining_time": "1:16:27", "throughput": 10537.38, "total_tokens": 8187776}
{"current_steps": 8540, "total_steps": 58920, "loss": 0.0709, "lr": 1.987729085396378e-06, "epoch": 0.7247114731839783, "percentage": 14.49, "elapsed_time": "0:12:57", "remaining_time": "1:16:26", "throughput": 10538.77, "total_tokens": 8192960}
{"current_steps": 8545, "total_steps": 58920, "loss": 0.1346, "lr": 1.9876827792858507e-06, "epoch": 0.7251357773251867, "percentage": 14.5, "elapsed_time": "0:12:57", "remaining_time": "1:16:25", "throughput": 10539.81, "total_tokens": 8197824}
{"current_steps": 8550, "total_steps": 58920, "loss": 0.0635, "lr": 1.9876363865097253e-06, "epoch": 0.7255600814663951, "percentage": 14.51, "elapsed_time": "0:12:58", "remaining_time": "1:16:24", "throughput": 10541.03, "total_tokens": 8202880}
{"current_steps": 8555, "total_steps": 58920, "loss": 0.1154, "lr": 1.9875899070720734e-06, "epoch": 0.7259843856076035, "percentage": 14.52, "elapsed_time": "0:12:58", "remaining_time": "1:16:23", "throughput": 10541.87, "total_tokens": 8207552}
{"current_steps": 8560, "total_steps": 58920, "loss": 0.1016, "lr": 1.9875433409769726e-06, "epoch": 0.7264086897488119, "percentage": 14.53, "elapsed_time": "0:12:58", "remaining_time": "1:16:22", "throughput": 10543.15, "total_tokens": 8212672}
{"current_steps": 8565, "total_steps": 58920, "loss": 0.0286, "lr": 1.9874966882285086e-06, "epoch": 0.7268329938900203, "percentage": 14.54, "elapsed_time": "0:12:59", "remaining_time": "1:16:22", "throughput": 10545.9, "total_tokens": 8219392}
{"current_steps": 8570, "total_steps": 58920, "loss": 0.0631, "lr": 1.987449948830776e-06, "epoch": 0.7272572980312287, "percentage": 14.55, "elapsed_time": "0:12:59", "remaining_time": "1:16:21", "throughput": 10546.74, "total_tokens": 8224064}
{"current_steps": 8575, "total_steps": 58920, "loss": 0.0774, "lr": 1.9874031227878757e-06, "epoch": 0.7276816021724372, "percentage": 14.55, "elapsed_time": "0:13:00", "remaining_time": "1:16:20", "throughput": 10548.2, "total_tokens": 8229376}
{"current_steps": 8580, "total_steps": 58920, "loss": 0.0355, "lr": 1.987356210103916e-06, "epoch": 0.7281059063136456, "percentage": 14.56, "elapsed_time": "0:13:00", "remaining_time": "1:16:19", "throughput": 10549.78, "total_tokens": 8234816}
{"current_steps": 8585, "total_steps": 58920, "loss": 0.0923, "lr": 1.987309210783014e-06, "epoch": 0.728530210454854, "percentage": 14.57, "elapsed_time": "0:13:00", "remaining_time": "1:16:18", "throughput": 10550.58, "total_tokens": 8239552}
{"current_steps": 8590, "total_steps": 58920, "loss": 0.0615, "lr": 1.9872621248292934e-06, "epoch": 0.7289545145960624, "percentage": 14.58, "elapsed_time": "0:13:01", "remaining_time": "1:16:17", "throughput": 10551.08, "total_tokens": 8243840}
{"current_steps": 8595, "total_steps": 58920, "loss": 0.1743, "lr": 1.9872149522468858e-06, "epoch": 0.7293788187372708, "percentage": 14.59, "elapsed_time": "0:13:01", "remaining_time": "1:16:17", "throughput": 10552.33, "total_tokens": 8248960}
{"current_steps": 8600, "total_steps": 58920, "loss": 0.053, "lr": 1.9871676930399302e-06, "epoch": 0.7298031228784793, "percentage": 14.6, "elapsed_time": "0:13:02", "remaining_time": "1:16:16", "throughput": 10553.47, "total_tokens": 8253888}
{"current_steps": 8605, "total_steps": 58920, "loss": 0.0928, "lr": 1.987120347212574e-06, "epoch": 0.7302274270196877, "percentage": 14.6, "elapsed_time": "0:13:02", "remaining_time": "1:16:15", "throughput": 10554.58, "total_tokens": 8258816}
{"current_steps": 8610, "total_steps": 58920, "loss": 0.1053, "lr": 1.9870729147689715e-06, "epoch": 0.7306517311608961, "percentage": 14.61, "elapsed_time": "0:13:02", "remaining_time": "1:16:14", "throughput": 10555.39, "total_tokens": 8263424}
{"current_steps": 8615, "total_steps": 58920, "loss": 0.0695, "lr": 1.987025395713284e-06, "epoch": 0.7310760353021045, "percentage": 14.62, "elapsed_time": "0:13:03", "remaining_time": "1:16:13", "throughput": 10556.4, "total_tokens": 8268288}
{"current_steps": 8620, "total_steps": 58920, "loss": 0.095, "lr": 1.986977790049682e-06, "epoch": 0.7315003394433129, "percentage": 14.63, "elapsed_time": "0:13:03", "remaining_time": "1:16:12", "throughput": 10557.5, "total_tokens": 8273152}
{"current_steps": 8625, "total_steps": 58920, "loss": 0.033, "lr": 1.9869300977823423e-06, "epoch": 0.7319246435845214, "percentage": 14.64, "elapsed_time": "0:13:04", "remaining_time": "1:16:11", "throughput": 10558.56, "total_tokens": 8278016}
{"current_steps": 8630, "total_steps": 58920, "loss": 0.08, "lr": 1.98688231891545e-06, "epoch": 0.7323489477257298, "percentage": 14.65, "elapsed_time": "0:13:04", "remaining_time": "1:16:11", "throughput": 10559.92, "total_tokens": 8283392}
{"current_steps": 8635, "total_steps": 58920, "loss": 0.0345, "lr": 1.986834453453197e-06, "epoch": 0.7327732518669382, "percentage": 14.66, "elapsed_time": "0:13:04", "remaining_time": "1:16:10", "throughput": 10560.79, "total_tokens": 8288064}
{"current_steps": 8640, "total_steps": 58920, "loss": 0.0747, "lr": 1.986786501399784e-06, "epoch": 0.7331975560081466, "percentage": 14.66, "elapsed_time": "0:13:05", "remaining_time": "1:16:09", "throughput": 10561.59, "total_tokens": 8292672}
{"current_steps": 8645, "total_steps": 58920, "loss": 0.0694, "lr": 1.9867384627594183e-06, "epoch": 0.733621860149355, "percentage": 14.67, "elapsed_time": "0:13:05", "remaining_time": "1:16:08", "throughput": 10562.41, "total_tokens": 8297344}
{"current_steps": 8650, "total_steps": 58920, "loss": 0.0571, "lr": 1.9866903375363145e-06, "epoch": 0.7340461642905635, "percentage": 14.68, "elapsed_time": "0:13:05", "remaining_time": "1:16:07", "throughput": 10563.29, "total_tokens": 8302080}
{"current_steps": 8655, "total_steps": 58920, "loss": 0.0593, "lr": 1.9866421257346965e-06, "epoch": 0.7344704684317719, "percentage": 14.69, "elapsed_time": "0:13:06", "remaining_time": "1:16:06", "throughput": 10564.36, "total_tokens": 8307008}
{"current_steps": 8660, "total_steps": 58920, "loss": 0.0994, "lr": 1.986593827358794e-06, "epoch": 0.7348947725729803, "percentage": 14.7, "elapsed_time": "0:13:06", "remaining_time": "1:16:05", "throughput": 10565.58, "total_tokens": 8312064}
{"current_steps": 8665, "total_steps": 58920, "loss": 0.036, "lr": 1.986545442412846e-06, "epoch": 0.7353190767141887, "percentage": 14.71, "elapsed_time": "0:13:07", "remaining_time": "1:16:04", "throughput": 10566.2, "total_tokens": 8316480}
{"current_steps": 8670, "total_steps": 58920, "loss": 0.0112, "lr": 1.9864969709010967e-06, "epoch": 0.7357433808553971, "percentage": 14.71, "elapsed_time": "0:13:07", "remaining_time": "1:16:04", "throughput": 10567.55, "total_tokens": 8321664}
{"current_steps": 8675, "total_steps": 58920, "loss": 0.0912, "lr": 1.9864484128278e-06, "epoch": 0.7361676849966056, "percentage": 14.72, "elapsed_time": "0:13:07", "remaining_time": "1:16:03", "throughput": 10568.07, "total_tokens": 8326016}
{"current_steps": 8680, "total_steps": 58920, "loss": 0.0081, "lr": 1.9863997681972165e-06, "epoch": 0.736591989137814, "percentage": 14.73, "elapsed_time": "0:13:08", "remaining_time": "1:16:02", "throughput": 10568.88, "total_tokens": 8330688}
{"current_steps": 8685, "total_steps": 58920, "loss": 0.0222, "lr": 1.9863510370136147e-06, "epoch": 0.7370162932790224, "percentage": 14.74, "elapsed_time": "0:13:08", "remaining_time": "1:16:01", "throughput": 10569.92, "total_tokens": 8335552}
{"current_steps": 8690, "total_steps": 58920, "loss": 0.0531, "lr": 1.986302219281271e-06, "epoch": 0.7374405974202308, "percentage": 14.75, "elapsed_time": "0:13:08", "remaining_time": "1:16:00", "throughput": 10570.73, "total_tokens": 8340224}
{"current_steps": 8695, "total_steps": 58920, "loss": 0.0604, "lr": 1.986253315004468e-06, "epoch": 0.7378649015614392, "percentage": 14.76, "elapsed_time": "0:13:09", "remaining_time": "1:15:59", "throughput": 10571.69, "total_tokens": 8345024}
{"current_steps": 8700, "total_steps": 58920, "loss": 0.0398, "lr": 1.986204324187498e-06, "epoch": 0.7382892057026477, "percentage": 14.77, "elapsed_time": "0:13:09", "remaining_time": "1:15:58", "throughput": 10572.49, "total_tokens": 8349632}
{"current_steps": 8705, "total_steps": 58920, "loss": 0.0996, "lr": 1.986155246834659e-06, "epoch": 0.7387135098438561, "percentage": 14.77, "elapsed_time": "0:13:10", "remaining_time": "1:15:57", "throughput": 10573.61, "total_tokens": 8354624}
{"current_steps": 8710, "total_steps": 58920, "loss": 0.1271, "lr": 1.9861060829502576e-06, "epoch": 0.7391378139850645, "percentage": 14.78, "elapsed_time": "0:13:10", "remaining_time": "1:15:57", "throughput": 10574.36, "total_tokens": 8359168}
{"current_steps": 8715, "total_steps": 58920, "loss": 0.0194, "lr": 1.986056832538608e-06, "epoch": 0.7395621181262729, "percentage": 14.79, "elapsed_time": "0:13:10", "remaining_time": "1:15:56", "throughput": 10575.25, "total_tokens": 8363968}
{"current_steps": 8720, "total_steps": 58920, "loss": 0.0576, "lr": 1.986007495604031e-06, "epoch": 0.7399864222674813, "percentage": 14.8, "elapsed_time": "0:13:11", "remaining_time": "1:15:55", "throughput": 10576.55, "total_tokens": 8369152}
{"current_steps": 8725, "total_steps": 58920, "loss": 0.0595, "lr": 1.9859580721508562e-06, "epoch": 0.7404107264086898, "percentage": 14.81, "elapsed_time": "0:13:11", "remaining_time": "1:15:54", "throughput": 10577.28, "total_tokens": 8373952}
{"current_steps": 8730, "total_steps": 58920, "loss": 0.058, "lr": 1.985908562183421e-06, "epoch": 0.7408350305498982, "percentage": 14.82, "elapsed_time": "0:13:12", "remaining_time": "1:15:53", "throughput": 10578.86, "total_tokens": 8379456}
{"current_steps": 8735, "total_steps": 58920, "loss": 0.032, "lr": 1.985858965706069e-06, "epoch": 0.7412593346911066, "percentage": 14.83, "elapsed_time": "0:13:12", "remaining_time": "1:15:52", "throughput": 10579.52, "total_tokens": 8383936}
{"current_steps": 8740, "total_steps": 58920, "loss": 0.0645, "lr": 1.9858092827231515e-06, "epoch": 0.741683638832315, "percentage": 14.83, "elapsed_time": "0:13:12", "remaining_time": "1:15:52", "throughput": 10580.59, "total_tokens": 8388864}
{"current_steps": 8745, "total_steps": 58920, "loss": 0.0531, "lr": 1.9857595132390294e-06, "epoch": 0.7421079429735234, "percentage": 14.84, "elapsed_time": "0:13:13", "remaining_time": "1:15:51", "throughput": 10581.78, "total_tokens": 8393920}
{"current_steps": 8750, "total_steps": 58920, "loss": 0.0866, "lr": 1.9857096572580686e-06, "epoch": 0.7425322471147319, "percentage": 14.85, "elapsed_time": "0:13:13", "remaining_time": "1:15:50", "throughput": 10582.82, "total_tokens": 8398848}
{"current_steps": 8755, "total_steps": 58920, "loss": 0.1325, "lr": 1.9856597147846444e-06, "epoch": 0.7429565512559403, "percentage": 14.86, "elapsed_time": "0:13:14", "remaining_time": "1:15:49", "throughput": 10584.2, "total_tokens": 8404160}
{"current_steps": 8760, "total_steps": 58920, "loss": 0.0558, "lr": 1.985609685823139e-06, "epoch": 0.7433808553971487, "percentage": 14.87, "elapsed_time": "0:13:14", "remaining_time": "1:15:48", "throughput": 10585.05, "total_tokens": 8408896}
{"current_steps": 8765, "total_steps": 58920, "loss": 0.1022, "lr": 1.985559570377942e-06, "epoch": 0.7438051595383571, "percentage": 14.88, "elapsed_time": "0:13:14", "remaining_time": "1:15:47", "throughput": 10585.61, "total_tokens": 8413312}
{"current_steps": 8770, "total_steps": 58920, "loss": 0.0349, "lr": 1.985509368453451e-06, "epoch": 0.7442294636795656, "percentage": 14.88, "elapsed_time": "0:13:15", "remaining_time": "1:15:47", "throughput": 10586.39, "total_tokens": 8417920}
{"current_steps": 8775, "total_steps": 58920, "loss": 0.0504, "lr": 1.9854590800540717e-06, "epoch": 0.744653767820774, "percentage": 14.89, "elapsed_time": "0:13:15", "remaining_time": "1:15:46", "throughput": 10587.12, "total_tokens": 8422720}
{"current_steps": 8780, "total_steps": 58920, "loss": 0.0414, "lr": 1.9854087051842155e-06, "epoch": 0.7450780719619824, "percentage": 14.9, "elapsed_time": "0:13:15", "remaining_time": "1:15:45", "throughput": 10587.52, "total_tokens": 8426944}
{"current_steps": 8785, "total_steps": 58920, "loss": 0.0349, "lr": 1.9853582438483034e-06, "epoch": 0.7455023761031908, "percentage": 14.91, "elapsed_time": "0:13:16", "remaining_time": "1:15:44", "throughput": 10587.81, "total_tokens": 8431104}
{"current_steps": 8790, "total_steps": 58920, "loss": 0.0963, "lr": 1.9853076960507634e-06, "epoch": 0.7459266802443992, "percentage": 14.92, "elapsed_time": "0:13:16", "remaining_time": "1:15:43", "throughput": 10588.39, "total_tokens": 8435520}
{"current_steps": 8795, "total_steps": 58920, "loss": 0.0542, "lr": 1.98525706179603e-06, "epoch": 0.7463509843856077, "percentage": 14.93, "elapsed_time": "0:13:17", "remaining_time": "1:15:42", "throughput": 10590.15, "total_tokens": 8441152}
{"current_steps": 8800, "total_steps": 58920, "loss": 0.0546, "lr": 1.985206341088547e-06, "epoch": 0.7467752885268161, "percentage": 14.94, "elapsed_time": "0:13:17", "remaining_time": "1:15:41", "throughput": 10590.98, "total_tokens": 8445824}
{"current_steps": 8805, "total_steps": 58920, "loss": 0.1133, "lr": 1.9851555339327646e-06, "epoch": 0.7471995926680245, "percentage": 14.94, "elapsed_time": "0:13:17", "remaining_time": "1:15:41", "throughput": 10592.02, "total_tokens": 8450752}
{"current_steps": 8810, "total_steps": 58920, "loss": 0.1282, "lr": 1.9851046403331408e-06, "epoch": 0.7476238968092329, "percentage": 14.95, "elapsed_time": "0:13:18", "remaining_time": "1:15:40", "throughput": 10592.69, "total_tokens": 8455296}
{"current_steps": 8815, "total_steps": 58920, "loss": 0.0591, "lr": 1.9850536602941414e-06, "epoch": 0.7480482009504412, "percentage": 14.96, "elapsed_time": "0:13:18", "remaining_time": "1:15:39", "throughput": 10593.95, "total_tokens": 8460480}
{"current_steps": 8820, "total_steps": 58920, "loss": 0.0784, "lr": 1.98500259382024e-06, "epoch": 0.7484725050916496, "percentage": 14.97, "elapsed_time": "0:13:18", "remaining_time": "1:15:38", "throughput": 10594.74, "total_tokens": 8465152}
{"current_steps": 8825, "total_steps": 58920, "loss": 0.0437, "lr": 1.9849514409159176e-06, "epoch": 0.7488968092328581, "percentage": 14.98, "elapsed_time": "0:13:19", "remaining_time": "1:15:37", "throughput": 10595.84, "total_tokens": 8470144}
{"current_steps": 8830, "total_steps": 58920, "loss": 0.0313, "lr": 1.984900201585662e-06, "epoch": 0.7493211133740665, "percentage": 14.99, "elapsed_time": "0:13:19", "remaining_time": "1:15:36", "throughput": 10597.65, "total_tokens": 8475840}
{"current_steps": 8835, "total_steps": 58920, "loss": 0.0473, "lr": 1.98484887583397e-06, "epoch": 0.7497454175152749, "percentage": 14.99, "elapsed_time": "0:13:20", "remaining_time": "1:15:36", "throughput": 10598.2, "total_tokens": 8480256}
{"current_steps": 8838, "total_steps": 58920, "eval_loss": 0.05446574091911316, "epoch": 0.75, "percentage": 15.0, "elapsed_time": "0:13:36", "remaining_time": "1:17:08", "throughput": 10384.99, "total_tokens": 8482944}
{"current_steps": 8840, "total_steps": 58920, "loss": 0.037, "lr": 1.9847974636653446e-06, "epoch": 0.7501697216564833, "percentage": 15.0, "elapsed_time": "0:14:13", "remaining_time": "1:20:36", "throughput": 9940.44, "total_tokens": 8485568}
{"current_steps": 8845, "total_steps": 58920, "loss": 0.0914, "lr": 1.9847459650842976e-06, "epoch": 0.7505940257976917, "percentage": 15.01, "elapsed_time": "0:14:14", "remaining_time": "1:20:34", "throughput": 9941.32, "total_tokens": 8490048}
{"current_steps": 8850, "total_steps": 58920, "loss": 0.0634, "lr": 1.9846943800953477e-06, "epoch": 0.7510183299389002, "percentage": 15.02, "elapsed_time": "0:14:14", "remaining_time": "1:20:33", "throughput": 9942.36, "total_tokens": 8494720}
{"current_steps": 8855, "total_steps": 58920, "loss": 0.0481, "lr": 1.9846427087030208e-06, "epoch": 0.7514426340801086, "percentage": 15.03, "elapsed_time": "0:14:14", "remaining_time": "1:20:32", "throughput": 9943.41, "total_tokens": 8499392}
{"current_steps": 8860, "total_steps": 58920, "loss": 0.0403, "lr": 1.9845909509118517e-06, "epoch": 0.751866938221317, "percentage": 15.04, "elapsed_time": "0:14:15", "remaining_time": "1:20:31", "throughput": 9944.61, "total_tokens": 8504256}
{"current_steps": 8865, "total_steps": 58920, "loss": 0.0585, "lr": 1.984539106726381e-06, "epoch": 0.7522912423625254, "percentage": 15.05, "elapsed_time": "0:14:15", "remaining_time": "1:20:30", "throughput": 9945.58, "total_tokens": 8508864}
{"current_steps": 8870, "total_steps": 58920, "loss": 0.1119, "lr": 1.9844871761511584e-06, "epoch": 0.7527155465037338, "percentage": 15.05, "elapsed_time": "0:14:15", "remaining_time": "1:20:29", "throughput": 9947.06, "total_tokens": 8514048}
{"current_steps": 8875, "total_steps": 58920, "loss": 0.0406, "lr": 1.984435159190741e-06, "epoch": 0.7531398506449423, "percentage": 15.06, "elapsed_time": "0:14:16", "remaining_time": "1:20:28", "throughput": 9948.02, "total_tokens": 8518656}
{"current_steps": 8880, "total_steps": 58920, "loss": 0.0403, "lr": 1.9843830558496927e-06, "epoch": 0.7535641547861507, "percentage": 15.07, "elapsed_time": "0:14:16", "remaining_time": "1:20:27", "throughput": 9949.23, "total_tokens": 8523520}
{"current_steps": 8885, "total_steps": 58920, "loss": 0.1591, "lr": 1.984330866132585e-06, "epoch": 0.7539884589273591, "percentage": 15.08, "elapsed_time": "0:14:17", "remaining_time": "1:20:26", "throughput": 9950.34, "total_tokens": 8528320}
{"current_steps": 8890, "total_steps": 58920, "loss": 0.0458, "lr": 1.9842785900439977e-06, "epoch": 0.7544127630685675, "percentage": 15.09, "elapsed_time": "0:14:17", "remaining_time": "1:20:25", "throughput": 9951.54, "total_tokens": 8533184}
{"current_steps": 8895, "total_steps": 58920, "loss": 0.0133, "lr": 1.984226227588518e-06, "epoch": 0.754837067209776, "percentage": 15.1, "elapsed_time": "0:14:17", "remaining_time": "1:20:24", "throughput": 9952.3, "total_tokens": 8537536}
{"current_steps": 8900, "total_steps": 58920, "loss": 0.0434, "lr": 1.9841737787707406e-06, "epoch": 0.7552613713509844, "percentage": 15.11, "elapsed_time": "0:14:18", "remaining_time": "1:20:23", "throughput": 9952.86, "total_tokens": 8541696}
{"current_steps": 8905, "total_steps": 58920, "loss": 0.0343, "lr": 1.984121243595267e-06, "epoch": 0.7556856754921928, "percentage": 15.11, "elapsed_time": "0:14:18", "remaining_time": "1:20:22", "throughput": 9953.73, "total_tokens": 8546176}
{"current_steps": 8910, "total_steps": 58920, "loss": 0.0451, "lr": 1.9840686220667077e-06, "epoch": 0.7561099796334012, "percentage": 15.12, "elapsed_time": "0:14:18", "remaining_time": "1:20:21", "throughput": 9954.5, "total_tokens": 8550592}
{"current_steps": 8915, "total_steps": 58920, "loss": 0.064, "lr": 1.9840159141896794e-06, "epoch": 0.7565342837746096, "percentage": 15.13, "elapsed_time": "0:14:19", "remaining_time": "1:20:20", "throughput": 9955.9, "total_tokens": 8555648}
{"current_steps": 8920, "total_steps": 58920, "loss": 0.1007, "lr": 1.983963119968808e-06, "epoch": 0.756958587915818, "percentage": 15.14, "elapsed_time": "0:14:19", "remaining_time": "1:20:19", "throughput": 9957.2, "total_tokens": 8560640}
{"current_steps": 8925, "total_steps": 58920, "loss": 0.076, "lr": 1.983910239408725e-06, "epoch": 0.7573828920570265, "percentage": 15.15, "elapsed_time": "0:14:20", "remaining_time": "1:20:18", "throughput": 9958.27, "total_tokens": 8565376}
{"current_steps": 8930, "total_steps": 58920, "loss": 0.0542, "lr": 1.983857272514071e-06, "epoch": 0.7578071961982349, "percentage": 15.16, "elapsed_time": "0:14:20", "remaining_time": "1:20:17", "throughput": 9958.99, "total_tokens": 8569728}
{"current_steps": 8935, "total_steps": 58920, "loss": 0.0808, "lr": 1.983804219289493e-06, "epoch": 0.7582315003394433, "percentage": 15.16, "elapsed_time": "0:14:20", "remaining_time": "1:20:16", "throughput": 9960.22, "total_tokens": 8574656}
{"current_steps": 8940, "total_steps": 58920, "loss": 0.0704, "lr": 1.9837510797396474e-06, "epoch": 0.7586558044806517, "percentage": 15.17, "elapsed_time": "0:14:21", "remaining_time": "1:20:14", "throughput": 9961.01, "total_tokens": 8579072}
{"current_steps": 8945, "total_steps": 58920, "loss": 0.0632, "lr": 1.9836978538691963e-06, "epoch": 0.7590801086218602, "percentage": 15.18, "elapsed_time": "0:14:21", "remaining_time": "1:20:13", "throughput": 9962.22, "total_tokens": 8584000}
{"current_steps": 8950, "total_steps": 58920, "loss": 0.1058, "lr": 1.9836445416828103e-06, "epoch": 0.7595044127630686, "percentage": 15.19, "elapsed_time": "0:14:22", "remaining_time": "1:20:13", "throughput": 9963.72, "total_tokens": 8589248}
{"current_steps": 8955, "total_steps": 58920, "loss": 0.058, "lr": 1.983591143185167e-06, "epoch": 0.759928716904277, "percentage": 15.2, "elapsed_time": "0:14:22", "remaining_time": "1:20:11", "throughput": 9964.35, "total_tokens": 8593472}
{"current_steps": 8960, "total_steps": 58920, "loss": 0.0259, "lr": 1.983537658380952e-06, "epoch": 0.7603530210454854, "percentage": 15.21, "elapsed_time": "0:14:22", "remaining_time": "1:20:10", "throughput": 9965.18, "total_tokens": 8597952}
{"current_steps": 8965, "total_steps": 58920, "loss": 0.0279, "lr": 1.983484087274859e-06, "epoch": 0.7607773251866938, "percentage": 15.22, "elapsed_time": "0:14:23", "remaining_time": "1:20:09", "throughput": 9966.36, "total_tokens": 8602816}
{"current_steps": 8970, "total_steps": 58920, "loss": 0.011, "lr": 1.9834304298715877e-06, "epoch": 0.7612016293279023, "percentage": 15.22, "elapsed_time": "0:14:23", "remaining_time": "1:20:08", "throughput": 9968.05, "total_tokens": 8608256}
{"current_steps": 8975, "total_steps": 58920, "loss": 0.0366, "lr": 1.983376686175847e-06, "epoch": 0.7616259334691107, "percentage": 15.23, "elapsed_time": "0:14:23", "remaining_time": "1:20:07", "throughput": 9969.07, "total_tokens": 8612928}
{"current_steps": 8980, "total_steps": 58920, "loss": 0.1059, "lr": 1.9833228561923523e-06, "epoch": 0.7620502376103191, "percentage": 15.24, "elapsed_time": "0:14:24", "remaining_time": "1:20:06", "throughput": 9969.83, "total_tokens": 8617280}
{"current_steps": 8985, "total_steps": 58920, "loss": 0.0017, "lr": 1.9832689399258276e-06, "epoch": 0.7624745417515275, "percentage": 15.25, "elapsed_time": "0:14:24", "remaining_time": "1:20:05", "throughput": 9970.83, "total_tokens": 8621952}
{"current_steps": 8990, "total_steps": 58920, "loss": 0.059, "lr": 1.9832149373810037e-06, "epoch": 0.7628988458927359, "percentage": 15.26, "elapsed_time": "0:14:25", "remaining_time": "1:20:04", "throughput": 9972.33, "total_tokens": 8627136}
{"current_steps": 8995, "total_steps": 58920, "loss": 0.0777, "lr": 1.9831608485626185e-06, "epoch": 0.7633231500339444, "percentage": 15.27, "elapsed_time": "0:14:25", "remaining_time": "1:20:03", "throughput": 9973.38, "total_tokens": 8631872}
{"current_steps": 9000, "total_steps": 58920, "loss": 0.116, "lr": 1.983106673475419e-06, "epoch": 0.7637474541751528, "percentage": 15.27, "elapsed_time": "0:14:25", "remaining_time": "1:20:02", "throughput": 9974.66, "total_tokens": 8636864}
{"current_steps": 9005, "total_steps": 58920, "loss": 0.03, "lr": 1.9830524121241575e-06, "epoch": 0.7641717583163612, "percentage": 15.28, "elapsed_time": "0:14:26", "remaining_time": "1:20:01", "throughput": 9975.86, "total_tokens": 8641792}
{"current_steps": 9010, "total_steps": 58920, "loss": 0.0547, "lr": 1.982998064513597e-06, "epoch": 0.7645960624575696, "percentage": 15.29, "elapsed_time": "0:14:26", "remaining_time": "1:20:00", "throughput": 9976.77, "total_tokens": 8646400}
{"current_steps": 9015, "total_steps": 58920, "loss": 0.0543, "lr": 1.982943630648505e-06, "epoch": 0.765020366598778, "percentage": 15.3, "elapsed_time": "0:14:27", "remaining_time": "1:19:59", "throughput": 9977.66, "total_tokens": 8650944}
{"current_steps": 9020, "total_steps": 58920, "loss": 0.0694, "lr": 1.982889110533658e-06, "epoch": 0.7654446707399865, "percentage": 15.31, "elapsed_time": "0:14:27", "remaining_time": "1:19:58", "throughput": 9979.65, "total_tokens": 8656704}
{"current_steps": 9025, "total_steps": 58920, "loss": 0.1153, "lr": 1.9828345041738413e-06, "epoch": 0.7658689748811949, "percentage": 15.32, "elapsed_time": "0:14:27", "remaining_time": "1:19:57", "throughput": 9980.43, "total_tokens": 8661120}
{"current_steps": 9030, "total_steps": 58920, "loss": 0.0642, "lr": 1.9827798115738445e-06, "epoch": 0.7662932790224033, "percentage": 15.33, "elapsed_time": "0:14:28", "remaining_time": "1:19:56", "throughput": 9981.3, "total_tokens": 8665664}
{"current_steps": 9035, "total_steps": 58920, "loss": 0.0824, "lr": 1.9827250327384677e-06, "epoch": 0.7667175831636117, "percentage": 15.33, "elapsed_time": "0:14:28", "remaining_time": "1:19:55", "throughput": 9982.56, "total_tokens": 8670592}
{"current_steps": 9040, "total_steps": 58920, "loss": 0.0902, "lr": 1.982670167672518e-06, "epoch": 0.7671418873048201, "percentage": 15.34, "elapsed_time": "0:14:29", "remaining_time": "1:19:54", "throughput": 9985.13, "total_tokens": 8677120}
{"current_steps": 9045, "total_steps": 58920, "loss": 0.1179, "lr": 1.9826152163808082e-06, "epoch": 0.7675661914460286, "percentage": 15.35, "elapsed_time": "0:14:29", "remaining_time": "1:19:53", "throughput": 9986.49, "total_tokens": 8682176}
{"current_steps": 9050, "total_steps": 58920, "loss": 0.0941, "lr": 1.9825601788681614e-06, "epoch": 0.767990495587237, "percentage": 15.36, "elapsed_time": "0:14:29", "remaining_time": "1:19:52", "throughput": 9987.64, "total_tokens": 8686976}
{"current_steps": 9055, "total_steps": 58920, "loss": 0.0394, "lr": 1.982505055139406e-06, "epoch": 0.7684147997284454, "percentage": 15.37, "elapsed_time": "0:14:30", "remaining_time": "1:19:51", "throughput": 9988.85, "total_tokens": 8691904}
{"current_steps": 9060, "total_steps": 58920, "loss": 0.0778, "lr": 1.98244984519938e-06, "epoch": 0.7688391038696538, "percentage": 15.38, "elapsed_time": "0:14:30", "remaining_time": "1:19:51", "throughput": 9993.47, "total_tokens": 8700928}
{"current_steps": 9065, "total_steps": 58920, "loss": 0.0256, "lr": 1.9823945490529263e-06, "epoch": 0.7692634080108622, "percentage": 15.39, "elapsed_time": "0:14:31", "remaining_time": "1:19:50", "throughput": 9994.23, "total_tokens": 8705344}
{"current_steps": 9070, "total_steps": 58920, "loss": 0.0678, "lr": 1.9823391667048983e-06, "epoch": 0.7696877121520707, "percentage": 15.39, "elapsed_time": "0:14:31", "remaining_time": "1:19:49", "throughput": 9995.9, "total_tokens": 8710784}
{"current_steps": 9075, "total_steps": 58920, "loss": 0.0413, "lr": 1.9822836981601553e-06, "epoch": 0.770112016293279, "percentage": 15.4, "elapsed_time": "0:14:31", "remaining_time": "1:19:48", "throughput": 9997.4, "total_tokens": 8716032}
{"current_steps": 9080, "total_steps": 58920, "loss": 0.0711, "lr": 1.982228143423564e-06, "epoch": 0.7705363204344874, "percentage": 15.41, "elapsed_time": "0:14:32", "remaining_time": "1:19:47", "throughput": 9998.7, "total_tokens": 8721088}
{"current_steps": 9085, "total_steps": 58920, "loss": 0.0261, "lr": 1.9821725024999996e-06, "epoch": 0.7709606245756958, "percentage": 15.42, "elapsed_time": "0:14:32", "remaining_time": "1:19:46", "throughput": 9999.53, "total_tokens": 8725632}
{"current_steps": 9090, "total_steps": 58920, "loss": 0.0345, "lr": 1.9821167753943443e-06, "epoch": 0.7713849287169042, "percentage": 15.43, "elapsed_time": "0:14:32", "remaining_time": "1:19:45", "throughput": 10000.76, "total_tokens": 8730560}
{"current_steps": 9095, "total_steps": 58920, "loss": 0.0618, "lr": 1.9820609621114874e-06, "epoch": 0.7718092328581126, "percentage": 15.44, "elapsed_time": "0:14:33", "remaining_time": "1:19:44", "throughput": 10002.89, "total_tokens": 8736640}
{"current_steps": 9100, "total_steps": 58920, "loss": 0.0771, "lr": 1.982005062656327e-06, "epoch": 0.7722335369993211, "percentage": 15.44, "elapsed_time": "0:14:33", "remaining_time": "1:19:43", "throughput": 10003.79, "total_tokens": 8741248}
{"current_steps": 9105, "total_steps": 58920, "loss": 0.0641, "lr": 1.9819490770337683e-06, "epoch": 0.7726578411405295, "percentage": 15.45, "elapsed_time": "0:14:34", "remaining_time": "1:19:42", "throughput": 10004.74, "total_tokens": 8745856}
{"current_steps": 9110, "total_steps": 58920, "loss": 0.1668, "lr": 1.981893005248723e-06, "epoch": 0.7730821452817379, "percentage": 15.46, "elapsed_time": "0:14:34", "remaining_time": "1:19:41", "throughput": 10005.28, "total_tokens": 8750016}
{"current_steps": 9115, "total_steps": 58920, "loss": 0.005, "lr": 1.981836847306112e-06, "epoch": 0.7735064494229463, "percentage": 15.47, "elapsed_time": "0:14:34", "remaining_time": "1:19:40", "throughput": 10006.46, "total_tokens": 8754944}
{"current_steps": 9120, "total_steps": 58920, "loss": 0.1309, "lr": 1.9817806032108624e-06, "epoch": 0.7739307535641547, "percentage": 15.48, "elapsed_time": "0:14:35", "remaining_time": "1:19:39", "throughput": 10007.31, "total_tokens": 8759488}
{"current_steps": 9125, "total_steps": 58920, "loss": 0.0915, "lr": 1.981724272967909e-06, "epoch": 0.7743550577053632, "percentage": 15.49, "elapsed_time": "0:14:35", "remaining_time": "1:19:38", "throughput": 10008.02, "total_tokens": 8763840}
{"current_steps": 9130, "total_steps": 58920, "loss": 0.0181, "lr": 1.981667856582196e-06, "epoch": 0.7747793618465716, "percentage": 15.5, "elapsed_time": "0:14:36", "remaining_time": "1:19:37", "throughput": 10008.83, "total_tokens": 8768320}
{"current_steps": 9135, "total_steps": 58920, "loss": 0.03, "lr": 1.9816113540586724e-06, "epoch": 0.77520366598778, "percentage": 15.5, "elapsed_time": "0:14:36", "remaining_time": "1:19:36", "throughput": 10010.33, "total_tokens": 8773568}
{"current_steps": 9140, "total_steps": 58920, "loss": 0.1231, "lr": 1.9815547654022965e-06, "epoch": 0.7756279701289884, "percentage": 15.51, "elapsed_time": "0:14:36", "remaining_time": "1:19:35", "throughput": 10011.26, "total_tokens": 8778176}
{"current_steps": 9145, "total_steps": 58920, "loss": 0.1171, "lr": 1.9814980906180343e-06, "epoch": 0.7760522742701969, "percentage": 15.52, "elapsed_time": "0:14:37", "remaining_time": "1:19:34", "throughput": 10012.15, "total_tokens": 8782784}
{"current_steps": 9150, "total_steps": 58920, "loss": 0.0323, "lr": 1.9814413297108577e-06, "epoch": 0.7764765784114053, "percentage": 15.53, "elapsed_time": "0:14:37", "remaining_time": "1:19:33", "throughput": 10013.17, "total_tokens": 8787456}
{"current_steps": 9155, "total_steps": 58920, "loss": 0.0788, "lr": 1.9813844826857486e-06, "epoch": 0.7769008825526137, "percentage": 15.54, "elapsed_time": "0:14:37", "remaining_time": "1:19:32", "throughput": 10014.22, "total_tokens": 8792256}
{"current_steps": 9160, "total_steps": 58920, "loss": 0.1297, "lr": 1.981327549547694e-06, "epoch": 0.7773251866938221, "percentage": 15.55, "elapsed_time": "0:14:38", "remaining_time": "1:19:31", "throughput": 10015.74, "total_tokens": 8797568}
{"current_steps": 9165, "total_steps": 58920, "loss": 0.0322, "lr": 1.98127053030169e-06, "epoch": 0.7777494908350305, "percentage": 15.55, "elapsed_time": "0:14:38", "remaining_time": "1:19:30", "throughput": 10016.54, "total_tokens": 8802112}
{"current_steps": 9170, "total_steps": 58920, "loss": 0.0209, "lr": 1.98121342495274e-06, "epoch": 0.778173794976239, "percentage": 15.56, "elapsed_time": "0:14:39", "remaining_time": "1:19:29", "throughput": 10017.51, "total_tokens": 8806784}
{"current_steps": 9175, "total_steps": 58920, "loss": 0.0294, "lr": 1.9811562335058546e-06, "epoch": 0.7785980991174474, "percentage": 15.57, "elapsed_time": "0:14:39", "remaining_time": "1:19:28", "throughput": 10019.05, "total_tokens": 8812096}
{"current_steps": 9180, "total_steps": 58920, "loss": 0.107, "lr": 1.9810989559660518e-06, "epoch": 0.7790224032586558, "percentage": 15.58, "elapsed_time": "0:14:39", "remaining_time": "1:19:27", "throughput": 10020.23, "total_tokens": 8817024}
{"current_steps": 9185, "total_steps": 58920, "loss": 0.2051, "lr": 1.981041592338358e-06, "epoch": 0.7794467073998642, "percentage": 15.59, "elapsed_time": "0:14:40", "remaining_time": "1:19:26", "throughput": 10021.15, "total_tokens": 8821696}
{"current_steps": 9190, "total_steps": 58920, "loss": 0.1661, "lr": 1.9809841426278065e-06, "epoch": 0.7798710115410726, "percentage": 15.6, "elapsed_time": "0:14:40", "remaining_time": "1:19:25", "throughput": 10022.28, "total_tokens": 8826560}
{"current_steps": 9195, "total_steps": 58920, "loss": 0.0315, "lr": 1.980926606839439e-06, "epoch": 0.780295315682281, "percentage": 15.61, "elapsed_time": "0:14:41", "remaining_time": "1:19:24", "throughput": 10023.53, "total_tokens": 8831552}
{"current_steps": 9200, "total_steps": 58920, "loss": 0.0636, "lr": 1.9808689849783024e-06, "epoch": 0.7807196198234895, "percentage": 15.61, "elapsed_time": "0:14:41", "remaining_time": "1:19:23", "throughput": 10024.73, "total_tokens": 8836480}
{"current_steps": 9205, "total_steps": 58920, "loss": 0.0683, "lr": 1.9808112770494543e-06, "epoch": 0.7811439239646979, "percentage": 15.62, "elapsed_time": "0:14:41", "remaining_time": "1:19:22", "throughput": 10025.39, "total_tokens": 8840832}
{"current_steps": 9210, "total_steps": 58920, "loss": 0.0681, "lr": 1.9807534830579575e-06, "epoch": 0.7815682281059063, "percentage": 15.63, "elapsed_time": "0:14:42", "remaining_time": "1:19:21", "throughput": 10026.21, "total_tokens": 8845376}
{"current_steps": 9215, "total_steps": 58920, "loss": 0.0283, "lr": 1.980695603008884e-06, "epoch": 0.7819925322471147, "percentage": 15.64, "elapsed_time": "0:14:42", "remaining_time": "1:19:20", "throughput": 10027.28, "total_tokens": 8850176}
{"current_steps": 9220, "total_steps": 58920, "loss": 0.061, "lr": 1.980637636907312e-06, "epoch": 0.7824168363883232, "percentage": 15.65, "elapsed_time": "0:14:42", "remaining_time": "1:19:19", "throughput": 10028.31, "total_tokens": 8854976}
{"current_steps": 9225, "total_steps": 58920, "loss": 0.0756, "lr": 1.9805795847583276e-06, "epoch": 0.7828411405295316, "percentage": 15.66, "elapsed_time": "0:14:43", "remaining_time": "1:19:18", "throughput": 10029.03, "total_tokens": 8859392}
{"current_steps": 9230, "total_steps": 58920, "loss": 0.0212, "lr": 1.9805214465670255e-06, "epoch": 0.78326544467074, "percentage": 15.67, "elapsed_time": "0:14:43", "remaining_time": "1:19:17", "throughput": 10029.87, "total_tokens": 8863936}
{"current_steps": 9235, "total_steps": 58920, "loss": 0.1083, "lr": 1.9804632223385063e-06, "epoch": 0.7836897488119484, "percentage": 15.67, "elapsed_time": "0:14:44", "remaining_time": "1:19:16", "throughput": 10030.75, "total_tokens": 8868480}
{"current_steps": 9240, "total_steps": 58920, "loss": 0.1264, "lr": 1.9804049120778793e-06, "epoch": 0.7841140529531568, "percentage": 15.68, "elapsed_time": "0:14:44", "remaining_time": "1:19:15", "throughput": 10031.85, "total_tokens": 8873344}
{"current_steps": 9245, "total_steps": 58920, "loss": 0.1158, "lr": 1.980346515790261e-06, "epoch": 0.7845383570943653, "percentage": 15.69, "elapsed_time": "0:14:44", "remaining_time": "1:19:14", "throughput": 10032.73, "total_tokens": 8878016}
{"current_steps": 9250, "total_steps": 58920, "loss": 0.1702, "lr": 1.9802880334807755e-06, "epoch": 0.7849626612355737, "percentage": 15.7, "elapsed_time": "0:14:45", "remaining_time": "1:19:13", "throughput": 10033.72, "total_tokens": 8882816}
{"current_steps": 9255, "total_steps": 58920, "loss": 0.0112, "lr": 1.9802294651545545e-06, "epoch": 0.7853869653767821, "percentage": 15.71, "elapsed_time": "0:14:45", "remaining_time": "1:19:12", "throughput": 10035.0, "total_tokens": 8887936}
{"current_steps": 9260, "total_steps": 58920, "loss": 0.03, "lr": 1.980170810816737e-06, "epoch": 0.7858112695179905, "percentage": 15.72, "elapsed_time": "0:14:46", "remaining_time": "1:19:11", "throughput": 10035.92, "total_tokens": 8892672}
{"current_steps": 9265, "total_steps": 58920, "loss": 0.0775, "lr": 1.9801120704724697e-06, "epoch": 0.7862355736591989, "percentage": 15.72, "elapsed_time": "0:14:46", "remaining_time": "1:19:10", "throughput": 10036.68, "total_tokens": 8897152}
{"current_steps": 9270, "total_steps": 58920, "loss": 0.0346, "lr": 1.980053244126907e-06, "epoch": 0.7866598778004074, "percentage": 15.73, "elapsed_time": "0:14:46", "remaining_time": "1:19:09", "throughput": 10037.32, "total_tokens": 8901504}
{"current_steps": 9275, "total_steps": 58920, "loss": 0.0506, "lr": 1.9799943317852105e-06, "epoch": 0.7870841819416158, "percentage": 15.74, "elapsed_time": "0:14:47", "remaining_time": "1:19:08", "throughput": 10038.27, "total_tokens": 8906176}
{"current_steps": 9280, "total_steps": 58920, "loss": 0.033, "lr": 1.9799353334525494e-06, "epoch": 0.7875084860828242, "percentage": 15.75, "elapsed_time": "0:14:47", "remaining_time": "1:19:07", "throughput": 10039.09, "total_tokens": 8910720}
{"current_steps": 9285, "total_steps": 58920, "loss": 0.0481, "lr": 1.9798762491341014e-06, "epoch": 0.7879327902240326, "percentage": 15.76, "elapsed_time": "0:14:47", "remaining_time": "1:19:06", "throughput": 10039.88, "total_tokens": 8915200}
{"current_steps": 9290, "total_steps": 58920, "loss": 0.0396, "lr": 1.9798170788350495e-06, "epoch": 0.788357094365241, "percentage": 15.77, "elapsed_time": "0:14:48", "remaining_time": "1:19:05", "throughput": 10041.15, "total_tokens": 8920256}
{"current_steps": 9295, "total_steps": 58920, "loss": 0.0936, "lr": 1.9797578225605873e-06, "epoch": 0.7887813985064495, "percentage": 15.78, "elapsed_time": "0:14:48", "remaining_time": "1:19:04", "throughput": 10042.0, "total_tokens": 8924864}
{"current_steps": 9300, "total_steps": 58920, "loss": 0.0746, "lr": 1.9796984803159135e-06, "epoch": 0.7892057026476579, "percentage": 15.78, "elapsed_time": "0:14:49", "remaining_time": "1:19:04", "throughput": 10043.22, "total_tokens": 8929856}
{"current_steps": 9305, "total_steps": 58920, "loss": 0.0385, "lr": 1.979639052106235e-06, "epoch": 0.7896300067888663, "percentage": 15.79, "elapsed_time": "0:14:49", "remaining_time": "1:19:03", "throughput": 10045.92, "total_tokens": 8936640}
{"current_steps": 9310, "total_steps": 58920, "loss": 0.0891, "lr": 1.9795795379367666e-06, "epoch": 0.7900543109300747, "percentage": 15.8, "elapsed_time": "0:14:49", "remaining_time": "1:19:02", "throughput": 10046.57, "total_tokens": 8940992}
{"current_steps": 9315, "total_steps": 58920, "loss": 0.1291, "lr": 1.9795199378127307e-06, "epoch": 0.7904786150712831, "percentage": 15.81, "elapsed_time": "0:14:50", "remaining_time": "1:19:01", "throughput": 10047.49, "total_tokens": 8945664}
{"current_steps": 9320, "total_steps": 58920, "loss": 0.1137, "lr": 1.9794602517393566e-06, "epoch": 0.7909029192124916, "percentage": 15.82, "elapsed_time": "0:14:50", "remaining_time": "1:19:00", "throughput": 10048.15, "total_tokens": 8950016}
{"current_steps": 9325, "total_steps": 58920, "loss": 0.0923, "lr": 1.9794004797218823e-06, "epoch": 0.7913272233537, "percentage": 15.83, "elapsed_time": "0:14:51", "remaining_time": "1:18:59", "throughput": 10049.25, "total_tokens": 8954880}
{"current_steps": 9330, "total_steps": 58920, "loss": 0.0746, "lr": 1.9793406217655515e-06, "epoch": 0.7917515274949084, "percentage": 15.84, "elapsed_time": "0:14:51", "remaining_time": "1:18:58", "throughput": 10050.71, "total_tokens": 8960128}
{"current_steps": 9335, "total_steps": 58920, "loss": 0.049, "lr": 1.979280677875617e-06, "epoch": 0.7921758316361168, "percentage": 15.84, "elapsed_time": "0:14:51", "remaining_time": "1:18:57", "throughput": 10051.67, "total_tokens": 8964864}
{"current_steps": 9340, "total_steps": 58920, "loss": 0.122, "lr": 1.979220648057339e-06, "epoch": 0.7926001357773251, "percentage": 15.85, "elapsed_time": "0:14:52", "remaining_time": "1:18:56", "throughput": 10053.08, "total_tokens": 8970112}
{"current_steps": 9345, "total_steps": 58920, "loss": 0.075, "lr": 1.9791605323159844e-06, "epoch": 0.7930244399185336, "percentage": 15.86, "elapsed_time": "0:14:52", "remaining_time": "1:18:55", "throughput": 10054.25, "total_tokens": 8975104}
{"current_steps": 9350, "total_steps": 58920, "loss": 0.0476, "lr": 1.9791003306568283e-06, "epoch": 0.793448744059742, "percentage": 15.87, "elapsed_time": "0:14:53", "remaining_time": "1:18:54", "throughput": 10055.49, "total_tokens": 8980160}
{"current_steps": 9355, "total_steps": 58920, "loss": 0.1153, "lr": 1.979040043085153e-06, "epoch": 0.7938730482009504, "percentage": 15.88, "elapsed_time": "0:14:53", "remaining_time": "1:18:53", "throughput": 10055.91, "total_tokens": 8984320}
{"current_steps": 9360, "total_steps": 58920, "loss": 0.0408, "lr": 1.9789796696062493e-06, "epoch": 0.7942973523421588, "percentage": 15.89, "elapsed_time": "0:14:53", "remaining_time": "1:18:52", "throughput": 10057.13, "total_tokens": 8989376}
{"current_steps": 9365, "total_steps": 58920, "loss": 0.0236, "lr": 1.978919210225414e-06, "epoch": 0.7947216564833672, "percentage": 15.89, "elapsed_time": "0:14:54", "remaining_time": "1:18:51", "throughput": 10057.9, "total_tokens": 8993920}
{"current_steps": 9370, "total_steps": 58920, "loss": 0.0656, "lr": 1.978858664947952e-06, "epoch": 0.7951459606245757, "percentage": 15.9, "elapsed_time": "0:14:54", "remaining_time": "1:18:50", "throughput": 10058.99, "total_tokens": 8998848}
{"current_steps": 9375, "total_steps": 58920, "loss": 0.0141, "lr": 1.9787980337791767e-06, "epoch": 0.7955702647657841, "percentage": 15.91, "elapsed_time": "0:14:54", "remaining_time": "1:18:49", "throughput": 10060.06, "total_tokens": 9003712}
{"current_steps": 9380, "total_steps": 58920, "loss": 0.0284, "lr": 1.9787373167244076e-06, "epoch": 0.7959945689069925, "percentage": 15.92, "elapsed_time": "0:14:55", "remaining_time": "1:18:49", "throughput": 10061.82, "total_tokens": 9009472}
{"current_steps": 9385, "total_steps": 58920, "loss": 0.0831, "lr": 1.9786765137889727e-06, "epoch": 0.7964188730482009, "percentage": 15.93, "elapsed_time": "0:14:55", "remaining_time": "1:18:48", "throughput": 10062.74, "total_tokens": 9014144}
{"current_steps": 9390, "total_steps": 58920, "loss": 0.0409, "lr": 1.9786156249782074e-06, "epoch": 0.7968431771894093, "percentage": 15.94, "elapsed_time": "0:14:56", "remaining_time": "1:18:47", "throughput": 10063.54, "total_tokens": 9018688}
{"current_steps": 9395, "total_steps": 58920, "loss": 0.0221, "lr": 1.9785546502974543e-06, "epoch": 0.7972674813306178, "percentage": 15.95, "elapsed_time": "0:14:56", "remaining_time": "1:18:46", "throughput": 10064.17, "total_tokens": 9023040}
{"current_steps": 9400, "total_steps": 58920, "loss": 0.0238, "lr": 1.9784935897520637e-06, "epoch": 0.7976917854718262, "percentage": 15.95, "elapsed_time": "0:14:56", "remaining_time": "1:18:45", "throughput": 10064.73, "total_tokens": 9027328}
{"current_steps": 9405, "total_steps": 58920, "loss": 0.0648, "lr": 1.9784324433473932e-06, "epoch": 0.7981160896130346, "percentage": 15.96, "elapsed_time": "0:14:57", "remaining_time": "1:18:44", "throughput": 10065.25, "total_tokens": 9031552}
{"current_steps": 9410, "total_steps": 58920, "loss": 0.0465, "lr": 1.9783712110888087e-06, "epoch": 0.798540393754243, "percentage": 15.97, "elapsed_time": "0:14:57", "remaining_time": "1:18:43", "throughput": 10066.52, "total_tokens": 9036672}
{"current_steps": 9415, "total_steps": 58920, "loss": 0.0827, "lr": 1.9783098929816825e-06, "epoch": 0.7989646978954514, "percentage": 15.98, "elapsed_time": "0:14:58", "remaining_time": "1:18:42", "throughput": 10067.52, "total_tokens": 9041472}
{"current_steps": 9420, "total_steps": 58920, "loss": 0.1205, "lr": 1.9782484890313957e-06, "epoch": 0.7993890020366599, "percentage": 15.99, "elapsed_time": "0:14:58", "remaining_time": "1:18:41", "throughput": 10069.09, "total_tokens": 9046912}
{"current_steps": 9425, "total_steps": 58920, "loss": 0.0691, "lr": 1.9781869992433355e-06, "epoch": 0.7998133061778683, "percentage": 16.0, "elapsed_time": "0:14:58", "remaining_time": "1:18:40", "throughput": 10070.11, "total_tokens": 9051712}
{"current_steps": 9430, "total_steps": 58920, "loss": 0.0956, "lr": 1.9781254236228985e-06, "epoch": 0.8002376103190767, "percentage": 16.0, "elapsed_time": "0:14:59", "remaining_time": "1:18:39", "throughput": 10070.98, "total_tokens": 9056256}
{"current_steps": 9435, "total_steps": 58920, "loss": 0.0368, "lr": 1.9780637621754864e-06, "epoch": 0.8006619144602851, "percentage": 16.01, "elapsed_time": "0:14:59", "remaining_time": "1:18:38", "throughput": 10072.31, "total_tokens": 9061376}
{"current_steps": 9440, "total_steps": 58920, "loss": 0.0907, "lr": 1.978002014906511e-06, "epoch": 0.8010862186014935, "percentage": 16.02, "elapsed_time": "0:15:00", "remaining_time": "1:18:37", "throughput": 10073.21, "total_tokens": 9066048}
{"current_steps": 9445, "total_steps": 58920, "loss": 0.0493, "lr": 1.9779401818213896e-06, "epoch": 0.801510522742702, "percentage": 16.03, "elapsed_time": "0:15:00", "remaining_time": "1:18:36", "throughput": 10074.59, "total_tokens": 9071232}
{"current_steps": 9450, "total_steps": 58920, "loss": 0.0543, "lr": 1.977878262925548e-06, "epoch": 0.8019348268839104, "percentage": 16.04, "elapsed_time": "0:15:00", "remaining_time": "1:18:35", "throughput": 10075.17, "total_tokens": 9075520}
{"current_steps": 9455, "total_steps": 58920, "loss": 0.0776, "lr": 1.9778162582244195e-06, "epoch": 0.8023591310251188, "percentage": 16.05, "elapsed_time": "0:15:01", "remaining_time": "1:18:34", "throughput": 10076.11, "total_tokens": 9080192}
{"current_steps": 9460, "total_steps": 58920, "loss": 0.0057, "lr": 1.9777541677234447e-06, "epoch": 0.8027834351663272, "percentage": 16.06, "elapsed_time": "0:15:01", "remaining_time": "1:18:33", "throughput": 10077.76, "total_tokens": 9085696}
{"current_steps": 9465, "total_steps": 58920, "loss": 0.0766, "lr": 1.9776919914280722e-06, "epoch": 0.8032077393075356, "percentage": 16.06, "elapsed_time": "0:15:01", "remaining_time": "1:18:32", "throughput": 10078.75, "total_tokens": 9090432}
{"current_steps": 9470, "total_steps": 58920, "loss": 0.0655, "lr": 1.977629729343757e-06, "epoch": 0.8036320434487441, "percentage": 16.07, "elapsed_time": "0:15:02", "remaining_time": "1:18:31", "throughput": 10079.57, "total_tokens": 9094976}
{"current_steps": 9475, "total_steps": 58920, "loss": 0.1036, "lr": 1.9775673814759627e-06, "epoch": 0.8040563475899525, "percentage": 16.08, "elapsed_time": "0:15:02", "remaining_time": "1:18:30", "throughput": 10080.92, "total_tokens": 9100096}
{"current_steps": 9480, "total_steps": 58920, "loss": 0.0708, "lr": 1.9775049478301604e-06, "epoch": 0.8044806517311609, "percentage": 16.09, "elapsed_time": "0:15:03", "remaining_time": "1:18:29", "throughput": 10082.38, "total_tokens": 9105408}
{"current_steps": 9485, "total_steps": 58920, "loss": 0.059, "lr": 1.9774424284118283e-06, "epoch": 0.8049049558723693, "percentage": 16.1, "elapsed_time": "0:15:03", "remaining_time": "1:18:28", "throughput": 10083.29, "total_tokens": 9110144}
{"current_steps": 9490, "total_steps": 58920, "loss": 0.0582, "lr": 1.9773798232264522e-06, "epoch": 0.8053292600135777, "percentage": 16.11, "elapsed_time": "0:15:03", "remaining_time": "1:18:28", "throughput": 10084.82, "total_tokens": 9115520}
{"current_steps": 9495, "total_steps": 58920, "loss": 0.0732, "lr": 1.977317132279525e-06, "epoch": 0.8057535641547862, "percentage": 16.12, "elapsed_time": "0:15:04", "remaining_time": "1:18:26", "throughput": 10085.41, "total_tokens": 9119808}
{"current_steps": 9500, "total_steps": 58920, "loss": 0.0628, "lr": 1.9772543555765485e-06, "epoch": 0.8061778682959946, "percentage": 16.12, "elapsed_time": "0:15:04", "remaining_time": "1:18:26", "throughput": 10086.51, "total_tokens": 9124672}
{"current_steps": 9505, "total_steps": 58920, "loss": 0.0403, "lr": 1.97719149312303e-06, "epoch": 0.806602172437203, "percentage": 16.13, "elapsed_time": "0:15:05", "remaining_time": "1:18:25", "throughput": 10087.32, "total_tokens": 9129216}
{"current_steps": 9510, "total_steps": 58920, "loss": 0.0615, "lr": 1.9771285449244868e-06, "epoch": 0.8070264765784114, "percentage": 16.14, "elapsed_time": "0:15:05", "remaining_time": "1:18:24", "throughput": 10088.32, "total_tokens": 9133952}
{"current_steps": 9515, "total_steps": 58920, "loss": 0.0578, "lr": 1.9770655109864416e-06, "epoch": 0.8074507807196198, "percentage": 16.15, "elapsed_time": "0:15:05", "remaining_time": "1:18:23", "throughput": 10088.89, "total_tokens": 9138240}
{"current_steps": 9520, "total_steps": 58920, "loss": 0.1231, "lr": 1.977002391314425e-06, "epoch": 0.8078750848608283, "percentage": 16.16, "elapsed_time": "0:15:06", "remaining_time": "1:18:22", "throughput": 10089.59, "total_tokens": 9142656}
{"current_steps": 9525, "total_steps": 58920, "loss": 0.033, "lr": 1.9769391859139763e-06, "epoch": 0.8082993890020367, "percentage": 16.17, "elapsed_time": "0:15:06", "remaining_time": "1:18:21", "throughput": 10090.61, "total_tokens": 9147456}
{"current_steps": 9530, "total_steps": 58920, "loss": 0.0298, "lr": 1.9768758947906414e-06, "epoch": 0.8087236931432451, "percentage": 16.17, "elapsed_time": "0:15:06", "remaining_time": "1:18:20", "throughput": 10091.49, "total_tokens": 9152064}
{"current_steps": 9535, "total_steps": 58920, "loss": 0.0937, "lr": 1.9768125179499736e-06, "epoch": 0.8091479972844535, "percentage": 16.18, "elapsed_time": "0:15:07", "remaining_time": "1:18:19", "throughput": 10092.23, "total_tokens": 9156544}
{"current_steps": 9540, "total_steps": 58920, "loss": 0.0358, "lr": 1.9767490553975344e-06, "epoch": 0.8095723014256619, "percentage": 16.19, "elapsed_time": "0:15:07", "remaining_time": "1:18:18", "throughput": 10093.06, "total_tokens": 9161088}
{"current_steps": 9545, "total_steps": 58920, "loss": 0.0876, "lr": 1.976685507138892e-06, "epoch": 0.8099966055668704, "percentage": 16.2, "elapsed_time": "0:15:08", "remaining_time": "1:18:17", "throughput": 10093.71, "total_tokens": 9165440}
{"current_steps": 9550, "total_steps": 58920, "loss": 0.042, "lr": 1.976621873179622e-06, "epoch": 0.8104209097080788, "percentage": 16.21, "elapsed_time": "0:15:08", "remaining_time": "1:18:16", "throughput": 10094.93, "total_tokens": 9170496}
{"current_steps": 9555, "total_steps": 58920, "loss": 0.0449, "lr": 1.9765581535253095e-06, "epoch": 0.8108452138492872, "percentage": 16.22, "elapsed_time": "0:15:08", "remaining_time": "1:18:15", "throughput": 10096.02, "total_tokens": 9175360}
{"current_steps": 9560, "total_steps": 58920, "loss": 0.0419, "lr": 1.9764943481815444e-06, "epoch": 0.8112695179904956, "percentage": 16.23, "elapsed_time": "0:15:09", "remaining_time": "1:18:14", "throughput": 10096.76, "total_tokens": 9179776}
{"current_steps": 9565, "total_steps": 58920, "loss": 0.0483, "lr": 1.9764304571539263e-06, "epoch": 0.811693822131704, "percentage": 16.23, "elapsed_time": "0:15:09", "remaining_time": "1:18:13", "throughput": 10098.59, "total_tokens": 9185536}
{"current_steps": 9570, "total_steps": 58920, "loss": 0.0296, "lr": 1.9763664804480607e-06, "epoch": 0.8121181262729125, "percentage": 16.24, "elapsed_time": "0:15:09", "remaining_time": "1:18:12", "throughput": 10099.78, "total_tokens": 9190528}
{"current_steps": 9575, "total_steps": 58920, "loss": 0.17, "lr": 1.9763024180695614e-06, "epoch": 0.8125424304141209, "percentage": 16.25, "elapsed_time": "0:15:10", "remaining_time": "1:18:11", "throughput": 10100.74, "total_tokens": 9195264}
{"current_steps": 9580, "total_steps": 58920, "loss": 0.0844, "lr": 1.9762382700240506e-06, "epoch": 0.8129667345553293, "percentage": 16.26, "elapsed_time": "0:15:10", "remaining_time": "1:18:10", "throughput": 10101.87, "total_tokens": 9200192}
{"current_steps": 9585, "total_steps": 58920, "loss": 0.0214, "lr": 1.9761740363171555e-06, "epoch": 0.8133910386965377, "percentage": 16.27, "elapsed_time": "0:15:11", "remaining_time": "1:18:09", "throughput": 10102.93, "total_tokens": 9205056}
{"current_steps": 9590, "total_steps": 58920, "loss": 0.0561, "lr": 1.9761097169545135e-06, "epoch": 0.8138153428377461, "percentage": 16.28, "elapsed_time": "0:15:11", "remaining_time": "1:18:08", "throughput": 10103.99, "total_tokens": 9209856}
{"current_steps": 9595, "total_steps": 58920, "loss": 0.0454, "lr": 1.976045311941768e-06, "epoch": 0.8142396469789546, "percentage": 16.28, "elapsed_time": "0:15:11", "remaining_time": "1:18:07", "throughput": 10104.86, "total_tokens": 9214464}
{"current_steps": 9600, "total_steps": 58920, "loss": 0.0726, "lr": 1.9759808212845705e-06, "epoch": 0.814663951120163, "percentage": 16.29, "elapsed_time": "0:15:12", "remaining_time": "1:18:06", "throughput": 10105.73, "total_tokens": 9219072}
{"current_steps": 9605, "total_steps": 58920, "loss": 0.0728, "lr": 1.9759162449885794e-06, "epoch": 0.8150882552613713, "percentage": 16.3, "elapsed_time": "0:15:12", "remaining_time": "1:18:05", "throughput": 10107.53, "total_tokens": 9224768}
{"current_steps": 9610, "total_steps": 58920, "loss": 0.059, "lr": 1.975851583059462e-06, "epoch": 0.8155125594025797, "percentage": 16.31, "elapsed_time": "0:15:13", "remaining_time": "1:18:04", "throughput": 10108.64, "total_tokens": 9229696}
{"current_steps": 9615, "total_steps": 58920, "loss": 0.114, "lr": 1.9757868355028907e-06, "epoch": 0.8159368635437881, "percentage": 16.32, "elapsed_time": "0:15:13", "remaining_time": "1:18:04", "throughput": 10110.13, "total_tokens": 9235072}
{"current_steps": 9620, "total_steps": 58920, "loss": 0.0836, "lr": 1.975722002324548e-06, "epoch": 0.8163611676849966, "percentage": 16.33, "elapsed_time": "0:15:13", "remaining_time": "1:18:03", "throughput": 10111.54, "total_tokens": 9240320}
{"current_steps": 9625, "total_steps": 58920, "loss": 0.0386, "lr": 1.975657083530122e-06, "epoch": 0.816785471826205, "percentage": 16.34, "elapsed_time": "0:15:14", "remaining_time": "1:18:02", "throughput": 10112.38, "total_tokens": 9244928}
{"current_steps": 9630, "total_steps": 58920, "loss": 0.1003, "lr": 1.9755920791253104e-06, "epoch": 0.8172097759674134, "percentage": 16.34, "elapsed_time": "0:15:14", "remaining_time": "1:18:01", "throughput": 10113.47, "total_tokens": 9249792}
{"current_steps": 9635, "total_steps": 58920, "loss": 0.0451, "lr": 1.9755269891158156e-06, "epoch": 0.8176340801086218, "percentage": 16.35, "elapsed_time": "0:15:14", "remaining_time": "1:18:00", "throughput": 10114.67, "total_tokens": 9254848}
{"current_steps": 9640, "total_steps": 58920, "loss": 0.0435, "lr": 1.97546181350735e-06, "epoch": 0.8180583842498302, "percentage": 16.36, "elapsed_time": "0:15:15", "remaining_time": "1:17:59", "throughput": 10115.46, "total_tokens": 9259392}
{"current_steps": 9645, "total_steps": 58920, "loss": 0.0838, "lr": 1.975396552305632e-06, "epoch": 0.8184826883910387, "percentage": 16.37, "elapsed_time": "0:15:15", "remaining_time": "1:17:58", "throughput": 10116.19, "total_tokens": 9263872}
{"current_steps": 9650, "total_steps": 58920, "loss": 0.0595, "lr": 1.975331205516388e-06, "epoch": 0.8189069925322471, "percentage": 16.38, "elapsed_time": "0:15:16", "remaining_time": "1:17:57", "throughput": 10117.29, "total_tokens": 9268800}
{"current_steps": 9655, "total_steps": 58920, "loss": 0.1511, "lr": 1.9752657731453523e-06, "epoch": 0.8193312966734555, "percentage": 16.39, "elapsed_time": "0:15:16", "remaining_time": "1:17:56", "throughput": 10118.11, "total_tokens": 9273408}
{"current_steps": 9660, "total_steps": 58920, "loss": 0.0507, "lr": 1.975200255198266e-06, "epoch": 0.8197556008146639, "percentage": 16.4, "elapsed_time": "0:15:16", "remaining_time": "1:17:55", "throughput": 10119.12, "total_tokens": 9278208}
{"current_steps": 9665, "total_steps": 58920, "loss": 0.0623, "lr": 1.975134651680878e-06, "epoch": 0.8201799049558723, "percentage": 16.4, "elapsed_time": "0:15:17", "remaining_time": "1:17:54", "throughput": 10120.06, "total_tokens": 9282944}
{"current_steps": 9670, "total_steps": 58920, "loss": 0.0077, "lr": 1.9750689625989457e-06, "epoch": 0.8206042090970808, "percentage": 16.41, "elapsed_time": "0:15:17", "remaining_time": "1:17:53", "throughput": 10121.34, "total_tokens": 9288064}
{"current_steps": 9675, "total_steps": 58920, "loss": 0.0363, "lr": 1.9750031879582322e-06, "epoch": 0.8210285132382892, "percentage": 16.42, "elapsed_time": "0:15:18", "remaining_time": "1:17:52", "throughput": 10122.56, "total_tokens": 9293120}
{"current_steps": 9680, "total_steps": 58920, "loss": 0.1105, "lr": 1.974937327764509e-06, "epoch": 0.8214528173794976, "percentage": 16.43, "elapsed_time": "0:15:18", "remaining_time": "1:17:51", "throughput": 10123.19, "total_tokens": 9297472}
{"current_steps": 9685, "total_steps": 58920, "loss": 0.0516, "lr": 1.9748713820235557e-06, "epoch": 0.821877121520706, "percentage": 16.44, "elapsed_time": "0:15:18", "remaining_time": "1:17:50", "throughput": 10124.12, "total_tokens": 9302144}
{"current_steps": 9690, "total_steps": 58920, "loss": 0.0766, "lr": 1.974805350741158e-06, "epoch": 0.8223014256619144, "percentage": 16.45, "elapsed_time": "0:15:19", "remaining_time": "1:17:50", "throughput": 10125.3, "total_tokens": 9307200}
{"current_steps": 9695, "total_steps": 58920, "loss": 0.0669, "lr": 1.9747392339231103e-06, "epoch": 0.8227257298031229, "percentage": 16.45, "elapsed_time": "0:15:19", "remaining_time": "1:17:49", "throughput": 10126.63, "total_tokens": 9312384}
{"current_steps": 9700, "total_steps": 58920, "loss": 0.0031, "lr": 1.974673031575214e-06, "epoch": 0.8231500339443313, "percentage": 16.46, "elapsed_time": "0:15:19", "remaining_time": "1:17:48", "throughput": 10127.6, "total_tokens": 9317120}
{"current_steps": 9705, "total_steps": 58920, "loss": 0.0553, "lr": 1.9746067437032784e-06, "epoch": 0.8235743380855397, "percentage": 16.47, "elapsed_time": "0:15:20", "remaining_time": "1:17:47", "throughput": 10128.39, "total_tokens": 9321664}
{"current_steps": 9710, "total_steps": 58920, "loss": 0.0935, "lr": 1.9745403703131197e-06, "epoch": 0.8239986422267481, "percentage": 16.48, "elapsed_time": "0:15:20", "remaining_time": "1:17:46", "throughput": 10129.19, "total_tokens": 9326208}
{"current_steps": 9715, "total_steps": 58920, "loss": 0.0958, "lr": 1.9744739114105626e-06, "epoch": 0.8244229463679565, "percentage": 16.49, "elapsed_time": "0:15:21", "remaining_time": "1:17:45", "throughput": 10130.4, "total_tokens": 9331264}
{"current_steps": 9720, "total_steps": 58920, "loss": 0.0948, "lr": 1.9744073670014377e-06, "epoch": 0.824847250509165, "percentage": 16.5, "elapsed_time": "0:15:21", "remaining_time": "1:17:44", "throughput": 10131.94, "total_tokens": 9336704}
{"current_steps": 9725, "total_steps": 58920, "loss": 0.0965, "lr": 1.9743407370915843e-06, "epoch": 0.8252715546503734, "percentage": 16.51, "elapsed_time": "0:15:21", "remaining_time": "1:17:43", "throughput": 10133.37, "total_tokens": 9342016}
{"current_steps": 9730, "total_steps": 58920, "loss": 0.0565, "lr": 1.9742740216868493e-06, "epoch": 0.8256958587915818, "percentage": 16.51, "elapsed_time": "0:15:22", "remaining_time": "1:17:42", "throughput": 10134.35, "total_tokens": 9346752}
{"current_steps": 9735, "total_steps": 58920, "loss": 0.043, "lr": 1.9742072207930863e-06, "epoch": 0.8261201629327902, "percentage": 16.52, "elapsed_time": "0:15:22", "remaining_time": "1:17:41", "throughput": 10135.14, "total_tokens": 9351296}
{"current_steps": 9740, "total_steps": 58920, "loss": 0.0868, "lr": 1.9741403344161573e-06, "epoch": 0.8265444670739986, "percentage": 16.53, "elapsed_time": "0:15:23", "remaining_time": "1:17:40", "throughput": 10135.8, "total_tokens": 9355712}
{"current_steps": 9745, "total_steps": 58920, "loss": 0.0922, "lr": 1.974073362561931e-06, "epoch": 0.8269687712152071, "percentage": 16.54, "elapsed_time": "0:15:23", "remaining_time": "1:17:39", "throughput": 10136.67, "total_tokens": 9360384}
{"current_steps": 9750, "total_steps": 58920, "loss": 0.0386, "lr": 1.974006305236284e-06, "epoch": 0.8273930753564155, "percentage": 16.55, "elapsed_time": "0:15:23", "remaining_time": "1:17:38", "throughput": 10137.17, "total_tokens": 9364608}
{"current_steps": 9755, "total_steps": 58920, "loss": 0.0192, "lr": 1.9739391624451e-06, "epoch": 0.8278173794976239, "percentage": 16.56, "elapsed_time": "0:15:24", "remaining_time": "1:17:37", "throughput": 10138.41, "total_tokens": 9369728}
{"current_steps": 9760, "total_steps": 58920, "loss": 0.0575, "lr": 1.973871934194271e-06, "epoch": 0.8282416836388323, "percentage": 16.56, "elapsed_time": "0:15:24", "remaining_time": "1:17:36", "throughput": 10139.48, "total_tokens": 9374592}
{"current_steps": 9765, "total_steps": 58920, "loss": 0.0373, "lr": 1.9738046204896963e-06, "epoch": 0.8286659877800407, "percentage": 16.57, "elapsed_time": "0:15:24", "remaining_time": "1:17:36", "throughput": 10141.12, "total_tokens": 9380160}
{"current_steps": 9770, "total_steps": 58920, "loss": 0.0614, "lr": 1.973737221337282e-06, "epoch": 0.8290902919212492, "percentage": 16.58, "elapsed_time": "0:15:25", "remaining_time": "1:17:35", "throughput": 10142.33, "total_tokens": 9385216}
{"current_steps": 9775, "total_steps": 58920, "loss": 0.0686, "lr": 1.9736697367429417e-06, "epoch": 0.8295145960624576, "percentage": 16.59, "elapsed_time": "0:15:25", "remaining_time": "1:17:34", "throughput": 10143.39, "total_tokens": 9390080}
{"current_steps": 9780, "total_steps": 58920, "loss": 0.0055, "lr": 1.973602166712598e-06, "epoch": 0.829938900203666, "percentage": 16.6, "elapsed_time": "0:15:26", "remaining_time": "1:17:33", "throughput": 10143.91, "total_tokens": 9394304}
{"current_steps": 9785, "total_steps": 58920, "loss": 0.1177, "lr": 1.9735345112521793e-06, "epoch": 0.8303632043448744, "percentage": 16.61, "elapsed_time": "0:15:26", "remaining_time": "1:17:32", "throughput": 10145.11, "total_tokens": 9399360}
{"current_steps": 9790, "total_steps": 58920, "loss": 0.0469, "lr": 1.973466770367622e-06, "epoch": 0.8307875084860828, "percentage": 16.62, "elapsed_time": "0:15:26", "remaining_time": "1:17:31", "throughput": 10146.27, "total_tokens": 9404352}
{"current_steps": 9795, "total_steps": 58920, "loss": 0.0273, "lr": 1.97339894406487e-06, "epoch": 0.8312118126272913, "percentage": 16.62, "elapsed_time": "0:15:27", "remaining_time": "1:17:30", "throughput": 10147.23, "total_tokens": 9409152}
{"current_steps": 9800, "total_steps": 58920, "loss": 0.0693, "lr": 1.9733310323498756e-06, "epoch": 0.8316361167684997, "percentage": 16.63, "elapsed_time": "0:15:27", "remaining_time": "1:17:29", "throughput": 10148.46, "total_tokens": 9414208}
{"current_steps": 9805, "total_steps": 58920, "loss": 0.0848, "lr": 1.973263035228597e-06, "epoch": 0.8320604209097081, "percentage": 16.64, "elapsed_time": "0:15:28", "remaining_time": "1:17:28", "throughput": 10149.42, "total_tokens": 9419008}
{"current_steps": 9810, "total_steps": 58920, "loss": 0.0259, "lr": 1.973194952707001e-06, "epoch": 0.8324847250509165, "percentage": 16.65, "elapsed_time": "0:15:28", "remaining_time": "1:17:27", "throughput": 10150.7, "total_tokens": 9424192}
{"current_steps": 9815, "total_steps": 58920, "loss": 0.0316, "lr": 1.973126784791062e-06, "epoch": 0.832909029192125, "percentage": 16.66, "elapsed_time": "0:15:28", "remaining_time": "1:17:26", "throughput": 10151.69, "total_tokens": 9429056}
{"current_steps": 9820, "total_steps": 58920, "loss": 0.0672, "lr": 1.9730585314867604e-06, "epoch": 0.8333333333333334, "percentage": 16.67, "elapsed_time": "0:15:29", "remaining_time": "1:17:25", "throughput": 10151.97, "total_tokens": 9433024}
{"current_steps": 9825, "total_steps": 58920, "loss": 0.0718, "lr": 1.972990192800086e-06, "epoch": 0.8337576374745418, "percentage": 16.68, "elapsed_time": "0:15:29", "remaining_time": "1:17:24", "throughput": 10152.8, "total_tokens": 9437696}
{"current_steps": 9830, "total_steps": 58920, "loss": 0.0704, "lr": 1.972921768737036e-06, "epoch": 0.8341819416157502, "percentage": 16.68, "elapsed_time": "0:15:29", "remaining_time": "1:17:24", "throughput": 10154.12, "total_tokens": 9442944}
{"current_steps": 9835, "total_steps": 58920, "loss": 0.0594, "lr": 1.9728532593036128e-06, "epoch": 0.8346062457569586, "percentage": 16.69, "elapsed_time": "0:15:30", "remaining_time": "1:17:23", "throughput": 10155.08, "total_tokens": 9447680}
{"current_steps": 9840, "total_steps": 58920, "loss": 0.1126, "lr": 1.972784664505829e-06, "epoch": 0.835030549898167, "percentage": 16.7, "elapsed_time": "0:15:30", "remaining_time": "1:17:22", "throughput": 10155.91, "total_tokens": 9452288}
{"current_steps": 9845, "total_steps": 58920, "loss": 0.0507, "lr": 1.9727159843497024e-06, "epoch": 0.8354548540393755, "percentage": 16.71, "elapsed_time": "0:15:31", "remaining_time": "1:17:21", "throughput": 10156.71, "total_tokens": 9456896}
{"current_steps": 9850, "total_steps": 58920, "loss": 0.1127, "lr": 1.9726472188412608e-06, "epoch": 0.8358791581805839, "percentage": 16.72, "elapsed_time": "0:15:31", "remaining_time": "1:17:20", "throughput": 10157.67, "total_tokens": 9461632}
{"current_steps": 9855, "total_steps": 58920, "loss": 0.0692, "lr": 1.972578367986537e-06, "epoch": 0.8363034623217923, "percentage": 16.73, "elapsed_time": "0:15:31", "remaining_time": "1:17:19", "throughput": 10158.69, "total_tokens": 9466560}
{"current_steps": 9860, "total_steps": 58920, "loss": 0.0389, "lr": 1.9725094317915732e-06, "epoch": 0.8367277664630007, "percentage": 16.73, "elapsed_time": "0:15:32", "remaining_time": "1:17:18", "throughput": 10159.53, "total_tokens": 9471168}
{"current_steps": 9865, "total_steps": 58920, "loss": 0.0332, "lr": 1.972440410262418e-06, "epoch": 0.837152070604209, "percentage": 16.74, "elapsed_time": "0:15:32", "remaining_time": "1:17:17", "throughput": 10160.52, "total_tokens": 9475968}
{"current_steps": 9870, "total_steps": 58920, "loss": 0.0903, "lr": 1.9723713034051275e-06, "epoch": 0.8375763747454175, "percentage": 16.75, "elapsed_time": "0:15:33", "remaining_time": "1:17:16", "throughput": 10161.9, "total_tokens": 9481280}
{"current_steps": 9875, "total_steps": 58920, "loss": 0.0386, "lr": 1.9723021112257663e-06, "epoch": 0.8380006788866259, "percentage": 16.76, "elapsed_time": "0:15:33", "remaining_time": "1:17:15", "throughput": 10162.76, "total_tokens": 9485952}
{"current_steps": 9880, "total_steps": 58920, "loss": 0.0512, "lr": 1.972232833730405e-06, "epoch": 0.8384249830278343, "percentage": 16.77, "elapsed_time": "0:15:33", "remaining_time": "1:17:14", "throughput": 10163.13, "total_tokens": 9490048}
{"current_steps": 9885, "total_steps": 58920, "loss": 0.1028, "lr": 1.972163470925123e-06, "epoch": 0.8388492871690427, "percentage": 16.78, "elapsed_time": "0:15:34", "remaining_time": "1:17:13", "throughput": 10164.49, "total_tokens": 9495360}
{"current_steps": 9890, "total_steps": 58920, "loss": 0.0987, "lr": 1.972094022816006e-06, "epoch": 0.8392735913102511, "percentage": 16.79, "elapsed_time": "0:15:34", "remaining_time": "1:17:13", "throughput": 10165.32, "total_tokens": 9499968}
{"current_steps": 9895, "total_steps": 58920, "loss": 0.1142, "lr": 1.972024489409149e-06, "epoch": 0.8396978954514596, "percentage": 16.79, "elapsed_time": "0:15:34", "remaining_time": "1:17:12", "throughput": 10166.25, "total_tokens": 9504704}
{"current_steps": 9900, "total_steps": 58920, "loss": 0.0286, "lr": 1.9719548707106517e-06, "epoch": 0.840122199592668, "percentage": 16.8, "elapsed_time": "0:15:35", "remaining_time": "1:17:11", "throughput": 10166.94, "total_tokens": 9509184}
{"current_steps": 9905, "total_steps": 58920, "loss": 0.0418, "lr": 1.971885166726624e-06, "epoch": 0.8405465037338764, "percentage": 16.81, "elapsed_time": "0:15:35", "remaining_time": "1:17:10", "throughput": 10167.92, "total_tokens": 9514048}
{"current_steps": 9910, "total_steps": 58920, "loss": 0.0358, "lr": 1.971815377463182e-06, "epoch": 0.8409708078750848, "percentage": 16.82, "elapsed_time": "0:15:36", "remaining_time": "1:17:09", "throughput": 10169.11, "total_tokens": 9519104}
{"current_steps": 9915, "total_steps": 58920, "loss": 0.0736, "lr": 1.9717455029264493e-06, "epoch": 0.8413951120162932, "percentage": 16.83, "elapsed_time": "0:15:36", "remaining_time": "1:17:08", "throughput": 10169.97, "total_tokens": 9523840}
{"current_steps": 9920, "total_steps": 58920, "loss": 0.0677, "lr": 1.9716755431225572e-06, "epoch": 0.8418194161575017, "percentage": 16.84, "elapsed_time": "0:15:36", "remaining_time": "1:17:07", "throughput": 10170.75, "total_tokens": 9528384}
{"current_steps": 9925, "total_steps": 58920, "loss": 0.0551, "lr": 1.9716054980576445e-06, "epoch": 0.8422437202987101, "percentage": 16.84, "elapsed_time": "0:15:37", "remaining_time": "1:17:06", "throughput": 10171.74, "total_tokens": 9533184}
{"current_steps": 9930, "total_steps": 58920, "loss": 0.0763, "lr": 1.9715353677378573e-06, "epoch": 0.8426680244399185, "percentage": 16.85, "elapsed_time": "0:15:37", "remaining_time": "1:17:05", "throughput": 10173.46, "total_tokens": 9538944}
{"current_steps": 9935, "total_steps": 58920, "loss": 0.03, "lr": 1.971465152169349e-06, "epoch": 0.8430923285811269, "percentage": 16.86, "elapsed_time": "0:15:38", "remaining_time": "1:17:04", "throughput": 10174.06, "total_tokens": 9543296}
{"current_steps": 9940, "total_steps": 58920, "loss": 0.0773, "lr": 1.9713948513582813e-06, "epoch": 0.8435166327223353, "percentage": 16.87, "elapsed_time": "0:15:38", "remaining_time": "1:17:03", "throughput": 10174.8, "total_tokens": 9547840}
{"current_steps": 9945, "total_steps": 58920, "loss": 0.1195, "lr": 1.9713244653108228e-06, "epoch": 0.8439409368635438, "percentage": 16.88, "elapsed_time": "0:15:38", "remaining_time": "1:17:03", "throughput": 10175.82, "total_tokens": 9552704}
{"current_steps": 9950, "total_steps": 58920, "loss": 0.0957, "lr": 1.971253994033149e-06, "epoch": 0.8443652410047522, "percentage": 16.89, "elapsed_time": "0:15:39", "remaining_time": "1:17:02", "throughput": 10177.39, "total_tokens": 9558272}
{"current_steps": 9955, "total_steps": 58920, "loss": 0.0611, "lr": 1.9711834375314444e-06, "epoch": 0.8447895451459606, "percentage": 16.9, "elapsed_time": "0:15:39", "remaining_time": "1:17:01", "throughput": 10178.53, "total_tokens": 9563264}
{"current_steps": 9960, "total_steps": 58920, "loss": 0.0313, "lr": 1.9711127958118993e-06, "epoch": 0.845213849287169, "percentage": 16.9, "elapsed_time": "0:15:39", "remaining_time": "1:17:00", "throughput": 10179.14, "total_tokens": 9567680}
{"current_steps": 9965, "total_steps": 58920, "loss": 0.0854, "lr": 1.9710420688807122e-06, "epoch": 0.8456381534283774, "percentage": 16.91, "elapsed_time": "0:15:40", "remaining_time": "1:16:59", "throughput": 10180.21, "total_tokens": 9572608}
{"current_steps": 9970, "total_steps": 58920, "loss": 0.0769, "lr": 1.97097125674409e-06, "epoch": 0.8460624575695859, "percentage": 16.92, "elapsed_time": "0:15:40", "remaining_time": "1:16:58", "throughput": 10180.92, "total_tokens": 9577088}
{"current_steps": 9975, "total_steps": 58920, "loss": 0.0472, "lr": 1.9709003594082455e-06, "epoch": 0.8464867617107943, "percentage": 16.93, "elapsed_time": "0:15:41", "remaining_time": "1:16:57", "throughput": 10181.95, "total_tokens": 9581952}
{"current_steps": 9980, "total_steps": 58920, "loss": 0.1066, "lr": 1.9708293768794003e-06, "epoch": 0.8469110658520027, "percentage": 16.94, "elapsed_time": "0:15:41", "remaining_time": "1:16:56", "throughput": 10182.68, "total_tokens": 9586496}
{"current_steps": 9985, "total_steps": 58920, "loss": 0.0648, "lr": 1.970758309163782e-06, "epoch": 0.8473353699932111, "percentage": 16.95, "elapsed_time": "0:15:41", "remaining_time": "1:16:55", "throughput": 10183.68, "total_tokens": 9591296}
{"current_steps": 9990, "total_steps": 58920, "loss": 0.0669, "lr": 1.970687156267627e-06, "epoch": 0.8477596741344195, "percentage": 16.96, "elapsed_time": "0:15:42", "remaining_time": "1:16:54", "throughput": 10184.51, "total_tokens": 9595904}
{"current_steps": 9995, "total_steps": 58920, "loss": 0.1861, "lr": 1.970615918197179e-06, "epoch": 0.848183978275628, "percentage": 16.96, "elapsed_time": "0:15:42", "remaining_time": "1:16:53", "throughput": 10185.43, "total_tokens": 9600640}
{"current_steps": 10000, "total_steps": 58920, "loss": 0.0482, "lr": 1.970544594958688e-06, "epoch": 0.8486082824168364, "percentage": 16.97, "elapsed_time": "0:15:42", "remaining_time": "1:16:52", "throughput": 10186.08, "total_tokens": 9605056}
{"current_steps": 10005, "total_steps": 58920, "loss": 0.0476, "lr": 1.970473186558413e-06, "epoch": 0.8490325865580448, "percentage": 16.98, "elapsed_time": "0:15:43", "remaining_time": "1:16:52", "throughput": 10187.23, "total_tokens": 9610112}
{"current_steps": 10010, "total_steps": 58920, "loss": 0.0309, "lr": 1.97040169300262e-06, "epoch": 0.8494568906992532, "percentage": 16.99, "elapsed_time": "0:15:43", "remaining_time": "1:16:51", "throughput": 10188.81, "total_tokens": 9615744}
{"current_steps": 10015, "total_steps": 58920, "loss": 0.0319, "lr": 1.9703301142975823e-06, "epoch": 0.8498811948404617, "percentage": 17.0, "elapsed_time": "0:15:44", "remaining_time": "1:16:50", "throughput": 10189.55, "total_tokens": 9620288}
{"current_steps": 10020, "total_steps": 58920, "loss": 0.0723, "lr": 1.9702584504495804e-06, "epoch": 0.8503054989816701, "percentage": 17.01, "elapsed_time": "0:15:44", "remaining_time": "1:16:49", "throughput": 10190.43, "total_tokens": 9625024}
{"current_steps": 10025, "total_steps": 58920, "loss": 0.0797, "lr": 1.9701867014649026e-06, "epoch": 0.8507298031228785, "percentage": 17.01, "elapsed_time": "0:15:44", "remaining_time": "1:16:48", "throughput": 10191.61, "total_tokens": 9630144}
{"current_steps": 10030, "total_steps": 58920, "loss": 0.1103, "lr": 1.970114867349844e-06, "epoch": 0.8511541072640869, "percentage": 17.02, "elapsed_time": "0:15:45", "remaining_time": "1:16:47", "throughput": 10192.32, "total_tokens": 9634624}
{"current_steps": 10035, "total_steps": 58920, "loss": 0.0015, "lr": 1.9700429481107086e-06, "epoch": 0.8515784114052953, "percentage": 17.03, "elapsed_time": "0:15:45", "remaining_time": "1:16:46", "throughput": 10193.57, "total_tokens": 9639744}
{"current_steps": 10040, "total_steps": 58920, "loss": 0.0186, "lr": 1.9699709437538076e-06, "epoch": 0.8520027155465038, "percentage": 17.04, "elapsed_time": "0:15:46", "remaining_time": "1:16:45", "throughput": 10194.46, "total_tokens": 9644480}
{"current_steps": 10045, "total_steps": 58920, "loss": 0.0416, "lr": 1.9698988542854576e-06, "epoch": 0.8524270196877122, "percentage": 17.05, "elapsed_time": "0:15:46", "remaining_time": "1:16:45", "throughput": 10195.47, "total_tokens": 9649408}
{"current_steps": 10050, "total_steps": 58920, "loss": 0.0911, "lr": 1.969826679711985e-06, "epoch": 0.8528513238289206, "percentage": 17.06, "elapsed_time": "0:15:46", "remaining_time": "1:16:44", "throughput": 10195.74, "total_tokens": 9653440}
{"current_steps": 10055, "total_steps": 58920, "loss": 0.0673, "lr": 1.969754420039723e-06, "epoch": 0.853275627970129, "percentage": 17.07, "elapsed_time": "0:15:47", "remaining_time": "1:16:43", "throughput": 10196.62, "total_tokens": 9658176}
{"current_steps": 10060, "total_steps": 58920, "loss": 0.0917, "lr": 1.9696820752750115e-06, "epoch": 0.8536999321113374, "percentage": 17.07, "elapsed_time": "0:15:47", "remaining_time": "1:16:42", "throughput": 10197.45, "total_tokens": 9662848}
{"current_steps": 10065, "total_steps": 58920, "loss": 0.0966, "lr": 1.9696096454241995e-06, "epoch": 0.8541242362525459, "percentage": 17.08, "elapsed_time": "0:15:47", "remaining_time": "1:16:41", "throughput": 10198.22, "total_tokens": 9667392}
{"current_steps": 10070, "total_steps": 58920, "loss": 0.1369, "lr": 1.9695371304936417e-06, "epoch": 0.8545485403937543, "percentage": 17.09, "elapsed_time": "0:15:48", "remaining_time": "1:16:40", "throughput": 10199.3, "total_tokens": 9672384}
{"current_steps": 10075, "total_steps": 58920, "loss": 0.0705, "lr": 1.969464530489701e-06, "epoch": 0.8549728445349627, "percentage": 17.1, "elapsed_time": "0:15:48", "remaining_time": "1:16:39", "throughput": 10200.29, "total_tokens": 9677248}
{"current_steps": 10080, "total_steps": 58920, "loss": 0.0303, "lr": 1.969391845418748e-06, "epoch": 0.8553971486761711, "percentage": 17.11, "elapsed_time": "0:15:49", "remaining_time": "1:16:38", "throughput": 10200.79, "total_tokens": 9681536}
{"current_steps": 10085, "total_steps": 58920, "loss": 0.0702, "lr": 1.969319075287161e-06, "epoch": 0.8558214528173795, "percentage": 17.12, "elapsed_time": "0:15:49", "remaining_time": "1:16:37", "throughput": 10201.94, "total_tokens": 9686592}
{"current_steps": 10090, "total_steps": 58920, "loss": 0.0578, "lr": 1.9692462201013243e-06, "epoch": 0.856245756958588, "percentage": 17.12, "elapsed_time": "0:15:49", "remaining_time": "1:16:36", "throughput": 10203.09, "total_tokens": 9691648}
{"current_steps": 10095, "total_steps": 58920, "loss": 0.0611, "lr": 1.9691732798676314e-06, "epoch": 0.8566700610997964, "percentage": 17.13, "elapsed_time": "0:15:50", "remaining_time": "1:16:36", "throughput": 10204.29, "total_tokens": 9696768}
{"current_steps": 10100, "total_steps": 58920, "loss": 0.086, "lr": 1.9691002545924824e-06, "epoch": 0.8570943652410048, "percentage": 17.14, "elapsed_time": "0:15:50", "remaining_time": "1:16:35", "throughput": 10205.09, "total_tokens": 9701376}
{"current_steps": 10105, "total_steps": 58920, "loss": 0.0623, "lr": 1.9690271442822846e-06, "epoch": 0.8575186693822132, "percentage": 17.15, "elapsed_time": "0:15:51", "remaining_time": "1:16:34", "throughput": 10205.41, "total_tokens": 9705408}
{"current_steps": 10110, "total_steps": 58920, "loss": 0.1035, "lr": 1.9689539489434545e-06, "epoch": 0.8579429735234216, "percentage": 17.16, "elapsed_time": "0:15:51", "remaining_time": "1:16:33", "throughput": 10206.02, "total_tokens": 9709824}
{"current_steps": 10115, "total_steps": 58920, "loss": 0.093, "lr": 1.9688806685824127e-06, "epoch": 0.8583672776646301, "percentage": 17.17, "elapsed_time": "0:15:51", "remaining_time": "1:16:32", "throughput": 10207.31, "total_tokens": 9715072}
{"current_steps": 10120, "total_steps": 58920, "loss": 0.0576, "lr": 1.968807303205591e-06, "epoch": 0.8587915818058385, "percentage": 17.18, "elapsed_time": "0:15:52", "remaining_time": "1:16:31", "throughput": 10208.38, "total_tokens": 9720000}
{"current_steps": 10125, "total_steps": 58920, "loss": 0.0088, "lr": 1.9687338528194263e-06, "epoch": 0.8592158859470469, "percentage": 17.18, "elapsed_time": "0:15:52", "remaining_time": "1:16:30", "throughput": 10208.93, "total_tokens": 9724288}
{"current_steps": 10130, "total_steps": 58920, "loss": 0.0503, "lr": 1.9686603174303637e-06, "epoch": 0.8596401900882552, "percentage": 17.19, "elapsed_time": "0:15:52", "remaining_time": "1:16:29", "throughput": 10209.97, "total_tokens": 9729280}
{"current_steps": 10135, "total_steps": 58920, "loss": 0.107, "lr": 1.968586697044855e-06, "epoch": 0.8600644942294636, "percentage": 17.2, "elapsed_time": "0:15:53", "remaining_time": "1:16:28", "throughput": 10210.56, "total_tokens": 9733696}
{"current_steps": 10140, "total_steps": 58920, "loss": 0.0267, "lr": 1.968512991669361e-06, "epoch": 0.860488798370672, "percentage": 17.21, "elapsed_time": "0:15:53", "remaining_time": "1:16:27", "throughput": 10211.52, "total_tokens": 9738624}
{"current_steps": 10145, "total_steps": 58920, "loss": 0.0731, "lr": 1.9684392013103494e-06, "epoch": 0.8609131025118805, "percentage": 17.22, "elapsed_time": "0:15:54", "remaining_time": "1:16:27", "throughput": 10212.46, "total_tokens": 9743488}
{"current_steps": 10150, "total_steps": 58920, "loss": 0.0333, "lr": 1.9683653259742937e-06, "epoch": 0.8613374066530889, "percentage": 17.23, "elapsed_time": "0:15:54", "remaining_time": "1:16:26", "throughput": 10214.39, "total_tokens": 9749632}
{"current_steps": 10155, "total_steps": 58920, "loss": 0.039, "lr": 1.968291365667677e-06, "epoch": 0.8617617107942973, "percentage": 17.24, "elapsed_time": "0:15:54", "remaining_time": "1:16:25", "throughput": 10215.34, "total_tokens": 9754432}
{"current_steps": 10160, "total_steps": 58920, "loss": 0.0517, "lr": 1.968217320396989e-06, "epoch": 0.8621860149355057, "percentage": 17.24, "elapsed_time": "0:15:55", "remaining_time": "1:16:24", "throughput": 10216.22, "total_tokens": 9759168}
{"current_steps": 10165, "total_steps": 58920, "loss": 0.0175, "lr": 1.968143190168727e-06, "epoch": 0.8626103190767141, "percentage": 17.25, "elapsed_time": "0:15:55", "remaining_time": "1:16:23", "throughput": 10217.27, "total_tokens": 9764096}
{"current_steps": 10170, "total_steps": 58920, "loss": 0.0438, "lr": 1.9680689749893956e-06, "epoch": 0.8630346232179226, "percentage": 17.26, "elapsed_time": "0:15:56", "remaining_time": "1:16:22", "throughput": 10218.08, "total_tokens": 9768768}
{"current_steps": 10175, "total_steps": 58920, "loss": 0.0483, "lr": 1.9679946748655067e-06, "epoch": 0.863458927359131, "percentage": 17.27, "elapsed_time": "0:15:56", "remaining_time": "1:16:21", "throughput": 10218.68, "total_tokens": 9773184}
{"current_steps": 10180, "total_steps": 58920, "loss": 0.0935, "lr": 1.9679202898035798e-06, "epoch": 0.8638832315003394, "percentage": 17.28, "elapsed_time": "0:15:56", "remaining_time": "1:16:20", "throughput": 10220.17, "total_tokens": 9778688}
{"current_steps": 10185, "total_steps": 58920, "loss": 0.0772, "lr": 1.9678458198101424e-06, "epoch": 0.8643075356415478, "percentage": 17.29, "elapsed_time": "0:15:57", "remaining_time": "1:16:20", "throughput": 10220.81, "total_tokens": 9783168}
{"current_steps": 10190, "total_steps": 58920, "loss": 0.096, "lr": 1.9677712648917287e-06, "epoch": 0.8647318397827563, "percentage": 17.29, "elapsed_time": "0:15:57", "remaining_time": "1:16:19", "throughput": 10221.55, "total_tokens": 9787712}
{"current_steps": 10195, "total_steps": 58920, "loss": 0.0543, "lr": 1.9676966250548807e-06, "epoch": 0.8651561439239647, "percentage": 17.3, "elapsed_time": "0:15:57", "remaining_time": "1:16:18", "throughput": 10222.39, "total_tokens": 9792384}
{"current_steps": 10200, "total_steps": 58920, "loss": 0.0795, "lr": 1.967621900306147e-06, "epoch": 0.8655804480651731, "percentage": 17.31, "elapsed_time": "0:15:58", "remaining_time": "1:16:17", "throughput": 10223.82, "total_tokens": 9797824}
{"current_steps": 10205, "total_steps": 58920, "loss": 0.1521, "lr": 1.967547090652086e-06, "epoch": 0.8660047522063815, "percentage": 17.32, "elapsed_time": "0:15:58", "remaining_time": "1:16:16", "throughput": 10224.94, "total_tokens": 9802880}
{"current_steps": 10210, "total_steps": 58920, "loss": 0.1005, "lr": 1.967472196099261e-06, "epoch": 0.8664290563475899, "percentage": 17.33, "elapsed_time": "0:15:59", "remaining_time": "1:16:15", "throughput": 10225.67, "total_tokens": 9807424}
{"current_steps": 10215, "total_steps": 58920, "loss": 0.0491, "lr": 1.9673972166542437e-06, "epoch": 0.8668533604887984, "percentage": 17.34, "elapsed_time": "0:15:59", "remaining_time": "1:16:14", "throughput": 10226.82, "total_tokens": 9812480}
{"current_steps": 10220, "total_steps": 58920, "loss": 0.0648, "lr": 1.9673221523236133e-06, "epoch": 0.8672776646300068, "percentage": 17.35, "elapsed_time": "0:15:59", "remaining_time": "1:16:13", "throughput": 10227.5, "total_tokens": 9816960}
{"current_steps": 10225, "total_steps": 58920, "loss": 0.0288, "lr": 1.9672470031139563e-06, "epoch": 0.8677019687712152, "percentage": 17.35, "elapsed_time": "0:16:00", "remaining_time": "1:16:12", "throughput": 10228.24, "total_tokens": 9821568}
{"current_steps": 10230, "total_steps": 58920, "loss": 0.1128, "lr": 1.9671717690318675e-06, "epoch": 0.8681262729124236, "percentage": 17.36, "elapsed_time": "0:16:00", "remaining_time": "1:16:12", "throughput": 10228.87, "total_tokens": 9826048}
{"current_steps": 10235, "total_steps": 58920, "loss": 0.0448, "lr": 1.967096450083948e-06, "epoch": 0.868550577053632, "percentage": 17.37, "elapsed_time": "0:16:00", "remaining_time": "1:16:11", "throughput": 10229.73, "total_tokens": 9830720}
{"current_steps": 10240, "total_steps": 58920, "loss": 0.0263, "lr": 1.9670210462768064e-06, "epoch": 0.8689748811948405, "percentage": 17.38, "elapsed_time": "0:16:01", "remaining_time": "1:16:10", "throughput": 10230.74, "total_tokens": 9835648}
{"current_steps": 10245, "total_steps": 58920, "loss": 0.1168, "lr": 1.9669455576170594e-06, "epoch": 0.8693991853360489, "percentage": 17.39, "elapsed_time": "0:16:01", "remaining_time": "1:16:09", "throughput": 10231.22, "total_tokens": 9839936}
{"current_steps": 10250, "total_steps": 58920, "loss": 0.0637, "lr": 1.966869984111331e-06, "epoch": 0.8698234894772573, "percentage": 17.4, "elapsed_time": "0:16:02", "remaining_time": "1:16:08", "throughput": 10232.03, "total_tokens": 9844608}
{"current_steps": 10255, "total_steps": 58920, "loss": 0.0723, "lr": 1.9667943257662523e-06, "epoch": 0.8702477936184657, "percentage": 17.4, "elapsed_time": "0:16:02", "remaining_time": "1:16:07", "throughput": 10232.5, "total_tokens": 9848896}
{"current_steps": 10260, "total_steps": 58920, "loss": 0.162, "lr": 1.966718582588462e-06, "epoch": 0.8706720977596741, "percentage": 17.41, "elapsed_time": "0:16:02", "remaining_time": "1:16:06", "throughput": 10233.0, "total_tokens": 9853184}
{"current_steps": 10265, "total_steps": 58920, "loss": 0.097, "lr": 1.9666427545846063e-06, "epoch": 0.8710964019008826, "percentage": 17.42, "elapsed_time": "0:16:03", "remaining_time": "1:16:05", "throughput": 10233.8, "total_tokens": 9857856}
{"current_steps": 10270, "total_steps": 58920, "loss": 0.0419, "lr": 1.9665668417613393e-06, "epoch": 0.871520706042091, "percentage": 17.43, "elapsed_time": "0:16:03", "remaining_time": "1:16:04", "throughput": 10234.69, "total_tokens": 9862592}
{"current_steps": 10275, "total_steps": 58920, "loss": 0.0587, "lr": 1.9664908441253215e-06, "epoch": 0.8719450101832994, "percentage": 17.44, "elapsed_time": "0:16:04", "remaining_time": "1:16:04", "throughput": 10235.71, "total_tokens": 9867584}
{"current_steps": 10280, "total_steps": 58920, "loss": 0.0214, "lr": 1.9664147616832214e-06, "epoch": 0.8723693143245078, "percentage": 17.45, "elapsed_time": "0:16:04", "remaining_time": "1:16:03", "throughput": 10236.62, "total_tokens": 9872384}
{"current_steps": 10285, "total_steps": 58920, "loss": 0.1089, "lr": 1.9663385944417156e-06, "epoch": 0.8727936184657162, "percentage": 17.46, "elapsed_time": "0:16:04", "remaining_time": "1:16:02", "throughput": 10237.14, "total_tokens": 9876672}
{"current_steps": 10290, "total_steps": 58920, "loss": 0.0447, "lr": 1.966262342407487e-06, "epoch": 0.8732179226069247, "percentage": 17.46, "elapsed_time": "0:16:05", "remaining_time": "1:16:01", "throughput": 10238.31, "total_tokens": 9881792}
{"current_steps": 10295, "total_steps": 58920, "loss": 0.1297, "lr": 1.9661860055872266e-06, "epoch": 0.8736422267481331, "percentage": 17.47, "elapsed_time": "0:16:05", "remaining_time": "1:16:00", "throughput": 10239.09, "total_tokens": 9886464}
{"current_steps": 10300, "total_steps": 58920, "loss": 0.0376, "lr": 1.9661095839876326e-06, "epoch": 0.8740665308893415, "percentage": 17.48, "elapsed_time": "0:16:05", "remaining_time": "1:15:59", "throughput": 10239.98, "total_tokens": 9891264}
{"current_steps": 10305, "total_steps": 58920, "loss": 0.0389, "lr": 1.9660330776154104e-06, "epoch": 0.8744908350305499, "percentage": 17.49, "elapsed_time": "0:16:06", "remaining_time": "1:15:58", "throughput": 10241.07, "total_tokens": 9896320}
{"current_steps": 10310, "total_steps": 58920, "loss": 0.067, "lr": 1.9659564864772737e-06, "epoch": 0.8749151391717583, "percentage": 17.5, "elapsed_time": "0:16:06", "remaining_time": "1:15:57", "throughput": 10242.31, "total_tokens": 9901504}
{"current_steps": 10315, "total_steps": 58920, "loss": 0.0438, "lr": 1.965879810579943e-06, "epoch": 0.8753394433129668, "percentage": 17.51, "elapsed_time": "0:16:07", "remaining_time": "1:15:57", "throughput": 10243.77, "total_tokens": 9907008}
{"current_steps": 10320, "total_steps": 58920, "loss": 0.0973, "lr": 1.965803049930146e-06, "epoch": 0.8757637474541752, "percentage": 17.52, "elapsed_time": "0:16:07", "remaining_time": "1:15:56", "throughput": 10244.62, "total_tokens": 9911744}
{"current_steps": 10325, "total_steps": 58920, "loss": 0.1167, "lr": 1.9657262045346187e-06, "epoch": 0.8761880515953836, "percentage": 17.52, "elapsed_time": "0:16:07", "remaining_time": "1:15:55", "throughput": 10245.16, "total_tokens": 9916096}
{"current_steps": 10330, "total_steps": 58920, "loss": 0.0366, "lr": 1.9656492744001033e-06, "epoch": 0.876612355736592, "percentage": 17.53, "elapsed_time": "0:16:08", "remaining_time": "1:15:54", "throughput": 10245.68, "total_tokens": 9920448}
{"current_steps": 10335, "total_steps": 58920, "loss": 0.0657, "lr": 1.965572259533351e-06, "epoch": 0.8770366598778004, "percentage": 17.54, "elapsed_time": "0:16:08", "remaining_time": "1:15:53", "throughput": 10246.61, "total_tokens": 9925312}
{"current_steps": 10340, "total_steps": 58920, "loss": 0.102, "lr": 1.965495159941119e-06, "epoch": 0.8774609640190089, "percentage": 17.55, "elapsed_time": "0:16:09", "remaining_time": "1:15:52", "throughput": 10247.34, "total_tokens": 9929920}
{"current_steps": 10345, "total_steps": 58920, "loss": 0.0059, "lr": 1.965417975630172e-06, "epoch": 0.8778852681602173, "percentage": 17.56, "elapsed_time": "0:16:09", "remaining_time": "1:15:51", "throughput": 10248.39, "total_tokens": 9934912}
{"current_steps": 10350, "total_steps": 58920, "loss": 0.0843, "lr": 1.9653407066072838e-06, "epoch": 0.8783095723014257, "percentage": 17.57, "elapsed_time": "0:16:09", "remaining_time": "1:15:50", "throughput": 10249.17, "total_tokens": 9939520}
{"current_steps": 10355, "total_steps": 58920, "loss": 0.0868, "lr": 1.965263352879234e-06, "epoch": 0.8787338764426341, "percentage": 17.57, "elapsed_time": "0:16:10", "remaining_time": "1:15:50", "throughput": 10250.12, "total_tokens": 9944384}
{"current_steps": 10360, "total_steps": 58920, "loss": 0.0244, "lr": 1.9651859144528096e-06, "epoch": 0.8791581805838425, "percentage": 17.58, "elapsed_time": "0:16:10", "remaining_time": "1:15:49", "throughput": 10250.95, "total_tokens": 9949056}
{"current_steps": 10365, "total_steps": 58920, "loss": 0.0399, "lr": 1.9651083913348064e-06, "epoch": 0.879582484725051, "percentage": 17.59, "elapsed_time": "0:16:10", "remaining_time": "1:15:48", "throughput": 10252.14, "total_tokens": 9954176}
{"current_steps": 10370, "total_steps": 58920, "loss": 0.0861, "lr": 1.9650307835320263e-06, "epoch": 0.8800067888662594, "percentage": 17.6, "elapsed_time": "0:16:11", "remaining_time": "1:15:47", "throughput": 10253.01, "total_tokens": 9958912}
{"current_steps": 10375, "total_steps": 58920, "loss": 0.1055, "lr": 1.9649530910512794e-06, "epoch": 0.8804310930074678, "percentage": 17.61, "elapsed_time": "0:16:11", "remaining_time": "1:15:46", "throughput": 10253.85, "total_tokens": 9963648}
{"current_steps": 10380, "total_steps": 58920, "loss": 0.0085, "lr": 1.9648753138993823e-06, "epoch": 0.8808553971486762, "percentage": 17.62, "elapsed_time": "0:16:12", "remaining_time": "1:15:45", "throughput": 10254.62, "total_tokens": 9968256}
{"current_steps": 10385, "total_steps": 58920, "loss": 0.0502, "lr": 1.9647974520831603e-06, "epoch": 0.8812797012898846, "percentage": 17.63, "elapsed_time": "0:16:12", "remaining_time": "1:15:44", "throughput": 10255.78, "total_tokens": 9973376}
{"current_steps": 10390, "total_steps": 58920, "loss": 0.0714, "lr": 1.964719505609445e-06, "epoch": 0.881704005431093, "percentage": 17.63, "elapsed_time": "0:16:12", "remaining_time": "1:15:43", "throughput": 10256.77, "total_tokens": 9978240}
{"current_steps": 10395, "total_steps": 58920, "loss": 0.023, "lr": 1.9646414744850764e-06, "epoch": 0.8821283095723014, "percentage": 17.64, "elapsed_time": "0:16:13", "remaining_time": "1:15:43", "throughput": 10257.49, "total_tokens": 9982784}
{"current_steps": 10400, "total_steps": 58920, "loss": 0.0757, "lr": 1.9645633587169016e-06, "epoch": 0.8825526137135098, "percentage": 17.65, "elapsed_time": "0:16:13", "remaining_time": "1:15:42", "throughput": 10257.91, "total_tokens": 9987008}
{"current_steps": 10405, "total_steps": 58920, "loss": 0.0912, "lr": 1.964485158311774e-06, "epoch": 0.8829769178547182, "percentage": 17.66, "elapsed_time": "0:16:13", "remaining_time": "1:15:41", "throughput": 10259.44, "total_tokens": 9992640}
{"current_steps": 10410, "total_steps": 58920, "loss": 0.0765, "lr": 1.9644068732765563e-06, "epoch": 0.8834012219959266, "percentage": 17.67, "elapsed_time": "0:16:14", "remaining_time": "1:15:40", "throughput": 10259.71, "total_tokens": 9996672}
{"current_steps": 10415, "total_steps": 58920, "loss": 0.058, "lr": 1.9643285036181174e-06, "epoch": 0.883825526137135, "percentage": 17.68, "elapsed_time": "0:16:14", "remaining_time": "1:15:39", "throughput": 10260.41, "total_tokens": 10001216}
{"current_steps": 10420, "total_steps": 58920, "loss": 0.0411, "lr": 1.964250049343334e-06, "epoch": 0.8842498302783435, "percentage": 17.68, "elapsed_time": "0:16:15", "remaining_time": "1:15:38", "throughput": 10261.43, "total_tokens": 10006144}
{"current_steps": 10425, "total_steps": 58920, "loss": 0.0514, "lr": 1.9641715104590906e-06, "epoch": 0.8846741344195519, "percentage": 17.69, "elapsed_time": "0:16:15", "remaining_time": "1:15:37", "throughput": 10262.72, "total_tokens": 10011520}
{"current_steps": 10430, "total_steps": 58920, "loss": 0.0153, "lr": 1.9640928869722776e-06, "epoch": 0.8850984385607603, "percentage": 17.7, "elapsed_time": "0:16:15", "remaining_time": "1:15:37", "throughput": 10263.78, "total_tokens": 10016512}
{"current_steps": 10435, "total_steps": 58920, "loss": 0.0926, "lr": 1.9640141788897947e-06, "epoch": 0.8855227427019687, "percentage": 17.71, "elapsed_time": "0:16:16", "remaining_time": "1:15:36", "throughput": 10264.38, "total_tokens": 10020928}
{"current_steps": 10440, "total_steps": 58920, "loss": 0.013, "lr": 1.9639353862185483e-06, "epoch": 0.8859470468431772, "percentage": 17.72, "elapsed_time": "0:16:16", "remaining_time": "1:15:35", "throughput": 10265.42, "total_tokens": 10025920}
{"current_steps": 10445, "total_steps": 58920, "loss": 0.0703, "lr": 1.963856508965452e-06, "epoch": 0.8863713509843856, "percentage": 17.73, "elapsed_time": "0:16:17", "remaining_time": "1:15:34", "throughput": 10266.1, "total_tokens": 10030464}
{"current_steps": 10450, "total_steps": 58920, "loss": 0.0561, "lr": 1.9637775471374274e-06, "epoch": 0.886795655125594, "percentage": 17.74, "elapsed_time": "0:16:17", "remaining_time": "1:15:33", "throughput": 10267.01, "total_tokens": 10035328}
{"current_steps": 10455, "total_steps": 58920, "loss": 0.1057, "lr": 1.9636985007414024e-06, "epoch": 0.8872199592668024, "percentage": 17.74, "elapsed_time": "0:16:17", "remaining_time": "1:15:32", "throughput": 10268.11, "total_tokens": 10040384}
{"current_steps": 10460, "total_steps": 58920, "loss": 0.0252, "lr": 1.9636193697843135e-06, "epoch": 0.8876442634080108, "percentage": 17.75, "elapsed_time": "0:16:18", "remaining_time": "1:15:31", "throughput": 10269.23, "total_tokens": 10045440}
{"current_steps": 10465, "total_steps": 58920, "loss": 0.0112, "lr": 1.963540154273104e-06, "epoch": 0.8880685675492193, "percentage": 17.76, "elapsed_time": "0:16:18", "remaining_time": "1:15:31", "throughput": 10270.26, "total_tokens": 10050432}
{"current_steps": 10470, "total_steps": 58920, "loss": 0.0713, "lr": 1.9634608542147246e-06, "epoch": 0.8884928716904277, "percentage": 17.77, "elapsed_time": "0:16:18", "remaining_time": "1:15:30", "throughput": 10271.18, "total_tokens": 10055296}
{"current_steps": 10475, "total_steps": 58920, "loss": 0.077, "lr": 1.963381469616134e-06, "epoch": 0.8889171758316361, "percentage": 17.78, "elapsed_time": "0:16:19", "remaining_time": "1:15:29", "throughput": 10272.31, "total_tokens": 10060416}
{"current_steps": 10480, "total_steps": 58920, "loss": 0.0424, "lr": 1.963302000484298e-06, "epoch": 0.8893414799728445, "percentage": 17.79, "elapsed_time": "0:16:19", "remaining_time": "1:15:28", "throughput": 10273.4, "total_tokens": 10065472}
{"current_steps": 10485, "total_steps": 58920, "loss": 0.0273, "lr": 1.9632224468261887e-06, "epoch": 0.8897657841140529, "percentage": 17.8, "elapsed_time": "0:16:20", "remaining_time": "1:15:27", "throughput": 10274.65, "total_tokens": 10070784}
{"current_steps": 10490, "total_steps": 58920, "loss": 0.0298, "lr": 1.963142808648788e-06, "epoch": 0.8901900882552614, "percentage": 17.8, "elapsed_time": "0:16:20", "remaining_time": "1:15:26", "throughput": 10275.82, "total_tokens": 10075904}
{"current_steps": 10495, "total_steps": 58920, "loss": 0.0781, "lr": 1.9630630859590833e-06, "epoch": 0.8906143923964698, "percentage": 17.81, "elapsed_time": "0:16:20", "remaining_time": "1:15:26", "throughput": 10276.74, "total_tokens": 10080768}
{"current_steps": 10500, "total_steps": 58920, "loss": 0.0729, "lr": 1.9629832787640697e-06, "epoch": 0.8910386965376782, "percentage": 17.82, "elapsed_time": "0:16:21", "remaining_time": "1:15:25", "throughput": 10277.4, "total_tokens": 10085312}
{"current_steps": 10505, "total_steps": 58920, "loss": 0.1118, "lr": 1.96290338707075e-06, "epoch": 0.8914630006788866, "percentage": 17.83, "elapsed_time": "0:16:21", "remaining_time": "1:15:24", "throughput": 10278.04, "total_tokens": 10089792}
{"current_steps": 10510, "total_steps": 58920, "loss": 0.0982, "lr": 1.962823410886135e-06, "epoch": 0.891887304820095, "percentage": 17.84, "elapsed_time": "0:16:22", "remaining_time": "1:15:23", "throughput": 10279.23, "total_tokens": 10094976}
{"current_steps": 10515, "total_steps": 58920, "loss": 0.018, "lr": 1.9627433502172417e-06, "epoch": 0.8923116089613035, "percentage": 17.85, "elapsed_time": "0:16:22", "remaining_time": "1:15:22", "throughput": 10279.64, "total_tokens": 10099200}
{"current_steps": 10520, "total_steps": 58920, "loss": 0.0843, "lr": 1.962663205071096e-06, "epoch": 0.8927359131025119, "percentage": 17.85, "elapsed_time": "0:16:22", "remaining_time": "1:15:21", "throughput": 10280.74, "total_tokens": 10104320}
{"current_steps": 10525, "total_steps": 58920, "loss": 0.0825, "lr": 1.962582975454729e-06, "epoch": 0.8931602172437203, "percentage": 17.86, "elapsed_time": "0:16:23", "remaining_time": "1:15:20", "throughput": 10281.79, "total_tokens": 10109312}
{"current_steps": 10530, "total_steps": 58920, "loss": 0.0301, "lr": 1.9625026613751815e-06, "epoch": 0.8935845213849287, "percentage": 17.87, "elapsed_time": "0:16:23", "remaining_time": "1:15:20", "throughput": 10282.26, "total_tokens": 10113600}
{"current_steps": 10535, "total_steps": 58920, "loss": 0.0037, "lr": 1.962422262839501e-06, "epoch": 0.8940088255261371, "percentage": 17.88, "elapsed_time": "0:16:23", "remaining_time": "1:15:19", "throughput": 10283.01, "total_tokens": 10118272}
{"current_steps": 10540, "total_steps": 58920, "loss": 0.0587, "lr": 1.9623417798547412e-06, "epoch": 0.8944331296673456, "percentage": 17.89, "elapsed_time": "0:16:24", "remaining_time": "1:15:18", "throughput": 10283.58, "total_tokens": 10122688}
{"current_steps": 10545, "total_steps": 58920, "loss": 0.1108, "lr": 1.962261212427965e-06, "epoch": 0.894857433808554, "percentage": 17.9, "elapsed_time": "0:16:24", "remaining_time": "1:15:17", "throughput": 10284.84, "total_tokens": 10128000}
{"current_steps": 10550, "total_steps": 58920, "loss": 0.0849, "lr": 1.9621805605662413e-06, "epoch": 0.8952817379497624, "percentage": 17.91, "elapsed_time": "0:16:25", "remaining_time": "1:15:16", "throughput": 10285.52, "total_tokens": 10132544}
{"current_steps": 10555, "total_steps": 58920, "loss": 0.0793, "lr": 1.9620998242766478e-06, "epoch": 0.8957060420909708, "percentage": 17.91, "elapsed_time": "0:16:25", "remaining_time": "1:15:15", "throughput": 10287.29, "total_tokens": 10138496}
{"current_steps": 10560, "total_steps": 58920, "loss": 0.0628, "lr": 1.9620190035662682e-06, "epoch": 0.8961303462321792, "percentage": 17.92, "elapsed_time": "0:16:25", "remaining_time": "1:15:15", "throughput": 10288.29, "total_tokens": 10143424}
{"current_steps": 10565, "total_steps": 58920, "loss": 0.1019, "lr": 1.961938098442194e-06, "epoch": 0.8965546503733877, "percentage": 17.93, "elapsed_time": "0:16:26", "remaining_time": "1:15:14", "throughput": 10289.49, "total_tokens": 10148672}
{"current_steps": 10570, "total_steps": 58920, "loss": 0.0376, "lr": 1.9618571089115253e-06, "epoch": 0.8969789545145961, "percentage": 17.94, "elapsed_time": "0:16:26", "remaining_time": "1:15:13", "throughput": 10290.3, "total_tokens": 10153408}
{"current_steps": 10575, "total_steps": 58920, "loss": 0.0625, "lr": 1.961776034981368e-06, "epoch": 0.8974032586558045, "percentage": 17.95, "elapsed_time": "0:16:27", "remaining_time": "1:15:12", "throughput": 10290.95, "total_tokens": 10157952}
{"current_steps": 10580, "total_steps": 58920, "loss": 0.036, "lr": 1.961694876658836e-06, "epoch": 0.8978275627970129, "percentage": 17.96, "elapsed_time": "0:16:27", "remaining_time": "1:15:11", "throughput": 10292.55, "total_tokens": 10163712}
{"current_steps": 10585, "total_steps": 58920, "loss": 0.0565, "lr": 1.9616136339510505e-06, "epoch": 0.8982518669382213, "percentage": 17.97, "elapsed_time": "0:16:27", "remaining_time": "1:15:10", "throughput": 10293.42, "total_tokens": 10168512}
{"current_steps": 10590, "total_steps": 58920, "loss": 0.064, "lr": 1.9615323068651407e-06, "epoch": 0.8986761710794298, "percentage": 17.97, "elapsed_time": "0:16:28", "remaining_time": "1:15:10", "throughput": 10294.16, "total_tokens": 10173120}
{"current_steps": 10595, "total_steps": 58920, "loss": 0.1117, "lr": 1.961450895408243e-06, "epoch": 0.8991004752206382, "percentage": 17.98, "elapsed_time": "0:16:28", "remaining_time": "1:15:09", "throughput": 10294.97, "total_tokens": 10177856}
{"current_steps": 10600, "total_steps": 58920, "loss": 0.059, "lr": 1.9613693995875e-06, "epoch": 0.8995247793618466, "percentage": 17.99, "elapsed_time": "0:16:28", "remaining_time": "1:15:08", "throughput": 10295.37, "total_tokens": 10182080}
{"current_steps": 10605, "total_steps": 58920, "loss": 0.0561, "lr": 1.961287819410063e-06, "epoch": 0.899949083503055, "percentage": 18.0, "elapsed_time": "0:16:29", "remaining_time": "1:15:07", "throughput": 10295.95, "total_tokens": 10186496}
{"current_steps": 10610, "total_steps": 58920, "loss": 0.0344, "lr": 1.961206154883091e-06, "epoch": 0.9003733876442634, "percentage": 18.01, "elapsed_time": "0:16:29", "remaining_time": "1:15:06", "throughput": 10296.53, "total_tokens": 10190912}
{"current_steps": 10615, "total_steps": 58920, "loss": 0.037, "lr": 1.9611244060137494e-06, "epoch": 0.9007976917854719, "percentage": 18.02, "elapsed_time": "0:16:30", "remaining_time": "1:15:05", "throughput": 10296.81, "total_tokens": 10195008}
{"current_steps": 10620, "total_steps": 58920, "loss": 0.0918, "lr": 1.961042572809211e-06, "epoch": 0.9012219959266803, "percentage": 18.02, "elapsed_time": "0:16:30", "remaining_time": "1:15:04", "throughput": 10297.38, "total_tokens": 10199424}
{"current_steps": 10625, "total_steps": 58920, "loss": 0.1267, "lr": 1.9609606552766567e-06, "epoch": 0.9016463000678887, "percentage": 18.03, "elapsed_time": "0:16:30", "remaining_time": "1:15:03", "throughput": 10298.04, "total_tokens": 10203968}
{"current_steps": 10630, "total_steps": 58920, "loss": 0.0837, "lr": 1.9608786534232748e-06, "epoch": 0.9020706042090971, "percentage": 18.04, "elapsed_time": "0:16:31", "remaining_time": "1:15:03", "throughput": 10298.79, "total_tokens": 10208640}
{"current_steps": 10635, "total_steps": 58920, "loss": 0.0088, "lr": 1.96079656725626e-06, "epoch": 0.9024949083503055, "percentage": 18.05, "elapsed_time": "0:16:31", "remaining_time": "1:15:02", "throughput": 10299.71, "total_tokens": 10213504}
{"current_steps": 10640, "total_steps": 58920, "loss": 0.0627, "lr": 1.9607143967828154e-06, "epoch": 0.902919212491514, "percentage": 18.06, "elapsed_time": "0:16:32", "remaining_time": "1:15:01", "throughput": 10300.69, "total_tokens": 10218432}
{"current_steps": 10645, "total_steps": 58920, "loss": 0.0802, "lr": 1.960632142010151e-06, "epoch": 0.9033435166327224, "percentage": 18.07, "elapsed_time": "0:16:32", "remaining_time": "1:15:00", "throughput": 10301.58, "total_tokens": 10223296}
{"current_steps": 10650, "total_steps": 58920, "loss": 0.1004, "lr": 1.9605498029454846e-06, "epoch": 0.9037678207739308, "percentage": 18.08, "elapsed_time": "0:16:32", "remaining_time": "1:14:59", "throughput": 10302.33, "total_tokens": 10227904}
{"current_steps": 10655, "total_steps": 58920, "loss": 0.0733, "lr": 1.960467379596041e-06, "epoch": 0.9041921249151391, "percentage": 18.08, "elapsed_time": "0:16:33", "remaining_time": "1:14:58", "throughput": 10303.15, "total_tokens": 10232640}
{"current_steps": 10660, "total_steps": 58920, "loss": 0.0995, "lr": 1.960384871969053e-06, "epoch": 0.9046164290563475, "percentage": 18.09, "elapsed_time": "0:16:33", "remaining_time": "1:14:57", "throughput": 10303.56, "total_tokens": 10236864}
{"current_steps": 10665, "total_steps": 58920, "loss": 0.0467, "lr": 1.9603022800717593e-06, "epoch": 0.905040733197556, "percentage": 18.1, "elapsed_time": "0:16:33", "remaining_time": "1:14:57", "throughput": 10304.07, "total_tokens": 10241216}
{"current_steps": 10670, "total_steps": 58920, "loss": 0.054, "lr": 1.9602196039114082e-06, "epoch": 0.9054650373387644, "percentage": 18.11, "elapsed_time": "0:16:34", "remaining_time": "1:14:56", "throughput": 10304.9, "total_tokens": 10245952}
{"current_steps": 10675, "total_steps": 58920, "loss": 0.0325, "lr": 1.9601368434952534e-06, "epoch": 0.9058893414799728, "percentage": 18.12, "elapsed_time": "0:16:34", "remaining_time": "1:14:55", "throughput": 10306.26, "total_tokens": 10251392}
{"current_steps": 10680, "total_steps": 58920, "loss": 0.0864, "lr": 1.960053998830557e-06, "epoch": 0.9063136456211812, "percentage": 18.13, "elapsed_time": "0:16:35", "remaining_time": "1:14:54", "throughput": 10307.06, "total_tokens": 10256128}
{"current_steps": 10685, "total_steps": 58920, "loss": 0.0607, "lr": 1.9599710699245892e-06, "epoch": 0.9067379497623896, "percentage": 18.13, "elapsed_time": "0:16:35", "remaining_time": "1:14:53", "throughput": 10307.46, "total_tokens": 10260352}
{"current_steps": 10690, "total_steps": 58920, "loss": 0.0252, "lr": 1.959888056784625e-06, "epoch": 0.9071622539035981, "percentage": 18.14, "elapsed_time": "0:16:35", "remaining_time": "1:14:52", "throughput": 10308.48, "total_tokens": 10265344}
{"current_steps": 10695, "total_steps": 58920, "loss": 0.0526, "lr": 1.9598049594179504e-06, "epoch": 0.9075865580448065, "percentage": 18.15, "elapsed_time": "0:16:36", "remaining_time": "1:14:51", "throughput": 10308.88, "total_tokens": 10269632}
{"current_steps": 10700, "total_steps": 58920, "loss": 0.0486, "lr": 1.959721777831855e-06, "epoch": 0.9080108621860149, "percentage": 18.16, "elapsed_time": "0:16:36", "remaining_time": "1:14:51", "throughput": 10309.82, "total_tokens": 10274560}
{"current_steps": 10705, "total_steps": 58920, "loss": 0.0535, "lr": 1.9596385120336393e-06, "epoch": 0.9084351663272233, "percentage": 18.17, "elapsed_time": "0:16:36", "remaining_time": "1:14:50", "throughput": 10310.78, "total_tokens": 10279552}
{"current_steps": 10710, "total_steps": 58920, "loss": 0.0503, "lr": 1.959555162030609e-06, "epoch": 0.9088594704684317, "percentage": 18.18, "elapsed_time": "0:16:37", "remaining_time": "1:14:49", "throughput": 10311.56, "total_tokens": 10284288}
{"current_steps": 10715, "total_steps": 58920, "loss": 0.0712, "lr": 1.9594717278300775e-06, "epoch": 0.9092837746096402, "percentage": 18.19, "elapsed_time": "0:16:37", "remaining_time": "1:14:48", "throughput": 10312.81, "total_tokens": 10289600}
{"current_steps": 10720, "total_steps": 58920, "loss": 0.022, "lr": 1.959388209439366e-06, "epoch": 0.9097080787508486, "percentage": 18.19, "elapsed_time": "0:16:38", "remaining_time": "1:14:47", "throughput": 10313.43, "total_tokens": 10294144}
{"current_steps": 10725, "total_steps": 58920, "loss": 0.0395, "lr": 1.959304606865803e-06, "epoch": 0.910132382892057, "percentage": 18.2, "elapsed_time": "0:16:38", "remaining_time": "1:14:46", "throughput": 10314.15, "total_tokens": 10298752}
{"current_steps": 10730, "total_steps": 58920, "loss": 0.0677, "lr": 1.9592209201167244e-06, "epoch": 0.9105566870332654, "percentage": 18.21, "elapsed_time": "0:16:38", "remaining_time": "1:14:46", "throughput": 10314.92, "total_tokens": 10303424}
{"current_steps": 10735, "total_steps": 58920, "loss": 0.054, "lr": 1.9591371491994733e-06, "epoch": 0.9109809911744738, "percentage": 18.22, "elapsed_time": "0:16:39", "remaining_time": "1:14:45", "throughput": 10315.68, "total_tokens": 10308096}
{"current_steps": 10740, "total_steps": 58920, "loss": 0.0516, "lr": 1.9590532941214004e-06, "epoch": 0.9114052953156823, "percentage": 18.23, "elapsed_time": "0:16:39", "remaining_time": "1:14:44", "throughput": 10316.76, "total_tokens": 10313152}
{"current_steps": 10745, "total_steps": 58920, "loss": 0.0386, "lr": 1.9589693548898634e-06, "epoch": 0.9118295994568907, "percentage": 18.24, "elapsed_time": "0:16:40", "remaining_time": "1:14:43", "throughput": 10317.66, "total_tokens": 10318016}
{"current_steps": 10750, "total_steps": 58920, "loss": 0.0221, "lr": 1.9588853315122278e-06, "epoch": 0.9122539035980991, "percentage": 18.25, "elapsed_time": "0:16:40", "remaining_time": "1:14:42", "throughput": 10318.22, "total_tokens": 10322432}
{"current_steps": 10755, "total_steps": 58920, "loss": 0.0448, "lr": 1.9588012239958665e-06, "epoch": 0.9126782077393075, "percentage": 18.25, "elapsed_time": "0:16:40", "remaining_time": "1:14:41", "throughput": 10319.01, "total_tokens": 10327168}
{"current_steps": 10760, "total_steps": 58920, "loss": 0.0897, "lr": 1.9587170323481593e-06, "epoch": 0.9131025118805159, "percentage": 18.26, "elapsed_time": "0:16:41", "remaining_time": "1:14:41", "throughput": 10319.58, "total_tokens": 10331584}
{"current_steps": 10765, "total_steps": 58920, "loss": 0.0419, "lr": 1.9586327565764944e-06, "epoch": 0.9135268160217244, "percentage": 18.27, "elapsed_time": "0:16:41", "remaining_time": "1:14:40", "throughput": 10320.66, "total_tokens": 10336640}
{"current_steps": 10770, "total_steps": 58920, "loss": 0.0926, "lr": 1.9585483966882657e-06, "epoch": 0.9139511201629328, "percentage": 18.28, "elapsed_time": "0:16:41", "remaining_time": "1:14:39", "throughput": 10321.54, "total_tokens": 10341440}
{"current_steps": 10775, "total_steps": 58920, "loss": 0.0166, "lr": 1.9584639526908766e-06, "epoch": 0.9143754243041412, "percentage": 18.29, "elapsed_time": "0:16:42", "remaining_time": "1:14:38", "throughput": 10322.67, "total_tokens": 10346624}
{"current_steps": 10780, "total_steps": 58920, "loss": 0.0127, "lr": 1.9583794245917356e-06, "epoch": 0.9147997284453496, "percentage": 18.3, "elapsed_time": "0:16:42", "remaining_time": "1:14:37", "throughput": 10323.63, "total_tokens": 10351552}
{"current_steps": 10785, "total_steps": 58920, "loss": 0.0615, "lr": 1.958294812398261e-06, "epoch": 0.915224032586558, "percentage": 18.3, "elapsed_time": "0:16:43", "remaining_time": "1:14:36", "throughput": 10324.46, "total_tokens": 10356352}
{"current_steps": 10790, "total_steps": 58920, "loss": 0.0915, "lr": 1.958210116117876e-06, "epoch": 0.9156483367277665, "percentage": 18.31, "elapsed_time": "0:16:43", "remaining_time": "1:14:36", "throughput": 10325.87, "total_tokens": 10361920}
{"current_steps": 10795, "total_steps": 58920, "loss": 0.0829, "lr": 1.958125335758013e-06, "epoch": 0.9160726408689749, "percentage": 18.32, "elapsed_time": "0:16:43", "remaining_time": "1:14:35", "throughput": 10326.35, "total_tokens": 10366272}
{"current_steps": 10800, "total_steps": 58920, "loss": 0.0381, "lr": 1.958040471326111e-06, "epoch": 0.9164969450101833, "percentage": 18.33, "elapsed_time": "0:16:44", "remaining_time": "1:14:34", "throughput": 10327.41, "total_tokens": 10371328}
{"current_steps": 10805, "total_steps": 58920, "loss": 0.0901, "lr": 1.957955522829617e-06, "epoch": 0.9169212491513917, "percentage": 18.34, "elapsed_time": "0:16:44", "remaining_time": "1:14:33", "throughput": 10328.43, "total_tokens": 10376384}
{"current_steps": 10810, "total_steps": 58920, "loss": 0.0894, "lr": 1.9578704902759843e-06, "epoch": 0.9173455532926001, "percentage": 18.35, "elapsed_time": "0:16:45", "remaining_time": "1:14:32", "throughput": 10329.23, "total_tokens": 10381120}
{"current_steps": 10815, "total_steps": 58920, "loss": 0.0283, "lr": 1.9577853736726745e-06, "epoch": 0.9177698574338086, "percentage": 18.36, "elapsed_time": "0:16:45", "remaining_time": "1:14:32", "throughput": 10329.75, "total_tokens": 10385536}
{"current_steps": 10820, "total_steps": 58920, "loss": 0.0311, "lr": 1.957700173027156e-06, "epoch": 0.918194161575017, "percentage": 18.36, "elapsed_time": "0:16:45", "remaining_time": "1:14:31", "throughput": 10330.51, "total_tokens": 10390208}
{"current_steps": 10825, "total_steps": 58920, "loss": 0.0614, "lr": 1.9576148883469052e-06, "epoch": 0.9186184657162254, "percentage": 18.37, "elapsed_time": "0:16:46", "remaining_time": "1:14:30", "throughput": 10331.0, "total_tokens": 10394560}
{"current_steps": 10830, "total_steps": 58920, "loss": 0.1099, "lr": 1.9575295196394056e-06, "epoch": 0.9190427698574338, "percentage": 18.38, "elapsed_time": "0:16:46", "remaining_time": "1:14:29", "throughput": 10331.43, "total_tokens": 10398848}
{"current_steps": 10835, "total_steps": 58920, "loss": 0.0467, "lr": 1.957444066912148e-06, "epoch": 0.9194670739986422, "percentage": 18.39, "elapsed_time": "0:16:46", "remaining_time": "1:14:28", "throughput": 10332.66, "total_tokens": 10404160}
{"current_steps": 10840, "total_steps": 58920, "loss": 0.0541, "lr": 1.9573585301726298e-06, "epoch": 0.9198913781398507, "percentage": 18.4, "elapsed_time": "0:16:47", "remaining_time": "1:14:27", "throughput": 10333.29, "total_tokens": 10408704}
{"current_steps": 10845, "total_steps": 58920, "loss": 0.0596, "lr": 1.9572729094283574e-06, "epoch": 0.9203156822810591, "percentage": 18.41, "elapsed_time": "0:16:47", "remaining_time": "1:14:26", "throughput": 10333.95, "total_tokens": 10413312}
{"current_steps": 10850, "total_steps": 58920, "loss": 0.067, "lr": 1.957187204686843e-06, "epoch": 0.9207399864222675, "percentage": 18.41, "elapsed_time": "0:16:48", "remaining_time": "1:14:26", "throughput": 10334.73, "total_tokens": 10418048}
{"current_steps": 10855, "total_steps": 58920, "loss": 0.0406, "lr": 1.9571014159556078e-06, "epoch": 0.9211642905634759, "percentage": 18.42, "elapsed_time": "0:16:48", "remaining_time": "1:14:25", "throughput": 10335.28, "total_tokens": 10422464}
{"current_steps": 10860, "total_steps": 58920, "loss": 0.093, "lr": 1.957015543242179e-06, "epoch": 0.9215885947046843, "percentage": 18.43, "elapsed_time": "0:16:48", "remaining_time": "1:14:24", "throughput": 10335.84, "total_tokens": 10426880}
{"current_steps": 10865, "total_steps": 58920, "loss": 0.0803, "lr": 1.9569295865540915e-06, "epoch": 0.9220128988458928, "percentage": 18.44, "elapsed_time": "0:16:49", "remaining_time": "1:14:23", "throughput": 10336.31, "total_tokens": 10431232}
{"current_steps": 10870, "total_steps": 58920, "loss": 0.102, "lr": 1.9568435458988874e-06, "epoch": 0.9224372029871012, "percentage": 18.45, "elapsed_time": "0:16:49", "remaining_time": "1:14:22", "throughput": 10337.95, "total_tokens": 10437120}
{"current_steps": 10875, "total_steps": 58920, "loss": 0.1426, "lr": 1.9567574212841174e-06, "epoch": 0.9228615071283096, "percentage": 18.46, "elapsed_time": "0:16:50", "remaining_time": "1:14:22", "throughput": 10339.93, "total_tokens": 10443456}
{"current_steps": 10880, "total_steps": 58920, "loss": 0.055, "lr": 1.9566712127173374e-06, "epoch": 0.923285811269518, "percentage": 18.47, "elapsed_time": "0:16:50", "remaining_time": "1:14:21", "throughput": 10340.98, "total_tokens": 10448576}
{"current_steps": 10885, "total_steps": 58920, "loss": 0.0533, "lr": 1.9565849202061127e-06, "epoch": 0.9237101154107265, "percentage": 18.47, "elapsed_time": "0:16:50", "remaining_time": "1:14:20", "throughput": 10341.9, "total_tokens": 10453440}
{"current_steps": 10890, "total_steps": 58920, "loss": 0.0307, "lr": 1.9564985437580154e-06, "epoch": 0.9241344195519349, "percentage": 18.48, "elapsed_time": "0:16:51", "remaining_time": "1:14:19", "throughput": 10342.65, "total_tokens": 10458176}
{"current_steps": 10895, "total_steps": 58920, "loss": 0.0533, "lr": 1.9564120833806243e-06, "epoch": 0.9245587236931433, "percentage": 18.49, "elapsed_time": "0:16:51", "remaining_time": "1:14:18", "throughput": 10343.66, "total_tokens": 10463232}
{"current_steps": 10900, "total_steps": 58920, "loss": 0.0936, "lr": 1.9563255390815255e-06, "epoch": 0.9249830278343517, "percentage": 18.5, "elapsed_time": "0:16:51", "remaining_time": "1:14:18", "throughput": 10344.47, "total_tokens": 10468032}
{"current_steps": 10905, "total_steps": 58920, "loss": 0.0178, "lr": 1.9562389108683137e-06, "epoch": 0.9254073319755601, "percentage": 18.51, "elapsed_time": "0:16:52", "remaining_time": "1:14:17", "throughput": 10345.29, "total_tokens": 10472832}
{"current_steps": 10910, "total_steps": 58920, "loss": 0.0175, "lr": 1.95615219874859e-06, "epoch": 0.9258316361167686, "percentage": 18.52, "elapsed_time": "0:16:52", "remaining_time": "1:14:16", "throughput": 10345.82, "total_tokens": 10477248}
{"current_steps": 10915, "total_steps": 58920, "loss": 0.0823, "lr": 1.9560654027299627e-06, "epoch": 0.926255940257977, "percentage": 18.53, "elapsed_time": "0:16:53", "remaining_time": "1:14:15", "throughput": 10346.54, "total_tokens": 10481920}
{"current_steps": 10920, "total_steps": 58920, "loss": 0.0869, "lr": 1.955978522820049e-06, "epoch": 0.9266802443991853, "percentage": 18.53, "elapsed_time": "0:16:53", "remaining_time": "1:14:14", "throughput": 10347.5, "total_tokens": 10486976}
{"current_steps": 10925, "total_steps": 58920, "loss": 0.0525, "lr": 1.955891559026471e-06, "epoch": 0.9271045485403937, "percentage": 18.54, "elapsed_time": "0:16:53", "remaining_time": "1:14:14", "throughput": 10348.26, "total_tokens": 10491712}
{"current_steps": 10930, "total_steps": 58920, "loss": 0.0876, "lr": 1.9558045113568596e-06, "epoch": 0.9275288526816021, "percentage": 18.55, "elapsed_time": "0:16:54", "remaining_time": "1:14:13", "throughput": 10349.42, "total_tokens": 10496960}
{"current_steps": 10935, "total_steps": 58920, "loss": 0.0441, "lr": 1.9557173798188532e-06, "epoch": 0.9279531568228105, "percentage": 18.56, "elapsed_time": "0:16:54", "remaining_time": "1:14:12", "throughput": 10349.76, "total_tokens": 10501120}
{"current_steps": 10940, "total_steps": 58920, "loss": 0.0505, "lr": 1.9556301644200975e-06, "epoch": 0.928377460964019, "percentage": 18.57, "elapsed_time": "0:16:55", "remaining_time": "1:14:11", "throughput": 10351.4, "total_tokens": 10507008}
{"current_steps": 10945, "total_steps": 58920, "loss": 0.0654, "lr": 1.9555428651682454e-06, "epoch": 0.9288017651052274, "percentage": 18.58, "elapsed_time": "0:16:55", "remaining_time": "1:14:10", "throughput": 10351.9, "total_tokens": 10511424}
{"current_steps": 10950, "total_steps": 58920, "loss": 0.0384, "lr": 1.955455482070957e-06, "epoch": 0.9292260692464358, "percentage": 18.58, "elapsed_time": "0:16:55", "remaining_time": "1:14:09", "throughput": 10352.5, "total_tokens": 10515968}
{"current_steps": 10955, "total_steps": 58920, "loss": 0.0926, "lr": 1.9553680151358993e-06, "epoch": 0.9296503733876442, "percentage": 18.59, "elapsed_time": "0:16:56", "remaining_time": "1:14:09", "throughput": 10353.2, "total_tokens": 10520576}
{"current_steps": 10960, "total_steps": 58920, "loss": 0.0469, "lr": 1.9552804643707476e-06, "epoch": 0.9300746775288526, "percentage": 18.6, "elapsed_time": "0:16:56", "remaining_time": "1:14:08", "throughput": 10354.12, "total_tokens": 10525504}
{"current_steps": 10965, "total_steps": 58920, "loss": 0.1026, "lr": 1.9551928297831845e-06, "epoch": 0.9304989816700611, "percentage": 18.61, "elapsed_time": "0:16:56", "remaining_time": "1:14:07", "throughput": 10354.76, "total_tokens": 10530112}
{"current_steps": 10970, "total_steps": 58920, "loss": 0.0839, "lr": 1.955105111380899e-06, "epoch": 0.9309232858112695, "percentage": 18.62, "elapsed_time": "0:16:57", "remaining_time": "1:14:06", "throughput": 10355.83, "total_tokens": 10535232}
{"current_steps": 10975, "total_steps": 58920, "loss": 0.0329, "lr": 1.9550173091715885e-06, "epoch": 0.9313475899524779, "percentage": 18.63, "elapsed_time": "0:16:57", "remaining_time": "1:14:05", "throughput": 10356.42, "total_tokens": 10539712}
{"current_steps": 10980, "total_steps": 58920, "loss": 0.0603, "lr": 1.9549294231629575e-06, "epoch": 0.9317718940936863, "percentage": 18.64, "elapsed_time": "0:16:58", "remaining_time": "1:14:05", "throughput": 10356.92, "total_tokens": 10544128}
{"current_steps": 10985, "total_steps": 58920, "loss": 0.0323, "lr": 1.9548414533627167e-06, "epoch": 0.9321961982348947, "percentage": 18.64, "elapsed_time": "0:16:58", "remaining_time": "1:14:04", "throughput": 10357.23, "total_tokens": 10548288}
{"current_steps": 10990, "total_steps": 58920, "loss": 0.0474, "lr": 1.9547533997785863e-06, "epoch": 0.9326205023761032, "percentage": 18.65, "elapsed_time": "0:16:58", "remaining_time": "1:14:03", "throughput": 10357.6, "total_tokens": 10552512}
{"current_steps": 10995, "total_steps": 58920, "loss": 0.051, "lr": 1.954665262418292e-06, "epoch": 0.9330448065173116, "percentage": 18.66, "elapsed_time": "0:16:59", "remaining_time": "1:14:02", "throughput": 10358.88, "total_tokens": 10557952}
{"current_steps": 11000, "total_steps": 58920, "loss": 0.0512, "lr": 1.954577041289568e-06, "epoch": 0.93346911065852, "percentage": 18.67, "elapsed_time": "0:16:59", "remaining_time": "1:14:01", "throughput": 10359.27, "total_tokens": 10562240}
{"current_steps": 11005, "total_steps": 58920, "loss": 0.074, "lr": 1.954488736400155e-06, "epoch": 0.9338934147997284, "percentage": 18.68, "elapsed_time": "0:16:59", "remaining_time": "1:14:00", "throughput": 10359.99, "total_tokens": 10566976}
{"current_steps": 11010, "total_steps": 58920, "loss": 0.0509, "lr": 1.9544003477578014e-06, "epoch": 0.9343177189409368, "percentage": 18.69, "elapsed_time": "0:17:00", "remaining_time": "1:14:00", "throughput": 10360.63, "total_tokens": 10571584}
{"current_steps": 11015, "total_steps": 58920, "loss": 0.062, "lr": 1.954311875370263e-06, "epoch": 0.9347420230821453, "percentage": 18.69, "elapsed_time": "0:17:00", "remaining_time": "1:13:59", "throughput": 10361.74, "total_tokens": 10576832}
{"current_steps": 11020, "total_steps": 58920, "loss": 0.0469, "lr": 1.954223319245303e-06, "epoch": 0.9351663272233537, "percentage": 18.7, "elapsed_time": "0:17:01", "remaining_time": "1:13:58", "throughput": 10362.17, "total_tokens": 10581184}
{"current_steps": 11025, "total_steps": 58920, "loss": 0.0592, "lr": 1.9541346793906924e-06, "epoch": 0.9355906313645621, "percentage": 18.71, "elapsed_time": "0:17:01", "remaining_time": "1:13:57", "throughput": 10362.81, "total_tokens": 10585792}
{"current_steps": 11030, "total_steps": 58920, "loss": 0.0178, "lr": 1.9540459558142085e-06, "epoch": 0.9360149355057705, "percentage": 18.72, "elapsed_time": "0:17:01", "remaining_time": "1:13:56", "throughput": 10363.15, "total_tokens": 10590016}
{"current_steps": 11035, "total_steps": 58920, "loss": 0.0016, "lr": 1.9539571485236364e-06, "epoch": 0.936439239646979, "percentage": 18.73, "elapsed_time": "0:17:02", "remaining_time": "1:13:56", "throughput": 10363.78, "total_tokens": 10594624}
{"current_steps": 11040, "total_steps": 58920, "loss": 0.148, "lr": 1.953868257526769e-06, "epoch": 0.9368635437881874, "percentage": 18.74, "elapsed_time": "0:17:02", "remaining_time": "1:13:55", "throughput": 10364.16, "total_tokens": 10598912}
{"current_steps": 11045, "total_steps": 58920, "loss": 0.0407, "lr": 1.953779282831406e-06, "epoch": 0.9372878479293958, "percentage": 18.75, "elapsed_time": "0:17:03", "remaining_time": "1:13:54", "throughput": 10364.94, "total_tokens": 10603648}
{"current_steps": 11050, "total_steps": 58920, "loss": 0.0646, "lr": 1.9536902244453536e-06, "epoch": 0.9377121520706042, "percentage": 18.75, "elapsed_time": "0:17:03", "remaining_time": "1:13:53", "throughput": 10365.89, "total_tokens": 10608640}
{"current_steps": 11055, "total_steps": 58920, "loss": 0.1466, "lr": 1.9536010823764284e-06, "epoch": 0.9381364562118126, "percentage": 18.76, "elapsed_time": "0:17:03", "remaining_time": "1:13:52", "throughput": 10366.6, "total_tokens": 10613312}
{"current_steps": 11060, "total_steps": 58920, "loss": 0.0341, "lr": 1.9535118566324505e-06, "epoch": 0.938560760353021, "percentage": 18.77, "elapsed_time": "0:17:04", "remaining_time": "1:13:51", "throughput": 10367.03, "total_tokens": 10617600}
{"current_steps": 11065, "total_steps": 58920, "loss": 0.0979, "lr": 1.95342254722125e-06, "epoch": 0.9389850644942295, "percentage": 18.78, "elapsed_time": "0:17:04", "remaining_time": "1:13:51", "throughput": 10367.63, "total_tokens": 10622144}
{"current_steps": 11070, "total_steps": 58920, "loss": 0.0076, "lr": 1.9533331541506636e-06, "epoch": 0.9394093686354379, "percentage": 18.79, "elapsed_time": "0:17:04", "remaining_time": "1:13:50", "throughput": 10368.37, "total_tokens": 10626880}
{"current_steps": 11075, "total_steps": 58920, "loss": 0.1108, "lr": 1.9532436774285344e-06, "epoch": 0.9398336727766463, "percentage": 18.8, "elapsed_time": "0:17:05", "remaining_time": "1:13:49", "throughput": 10369.52, "total_tokens": 10632128}
{"current_steps": 11080, "total_steps": 58920, "loss": 0.069, "lr": 1.9531541170627144e-06, "epoch": 0.9402579769178547, "percentage": 18.81, "elapsed_time": "0:17:05", "remaining_time": "1:13:48", "throughput": 10370.27, "total_tokens": 10636800}
{"current_steps": 11085, "total_steps": 58920, "loss": 0.0285, "lr": 1.953064473061062e-06, "epoch": 0.9406822810590632, "percentage": 18.81, "elapsed_time": "0:17:06", "remaining_time": "1:13:47", "throughput": 10370.92, "total_tokens": 10641408}
{"current_steps": 11090, "total_steps": 58920, "loss": 0.038, "lr": 1.9529747454314434e-06, "epoch": 0.9411065852002716, "percentage": 18.82, "elapsed_time": "0:17:06", "remaining_time": "1:13:47", "throughput": 10371.87, "total_tokens": 10646400}
{"current_steps": 11095, "total_steps": 58920, "loss": 0.1388, "lr": 1.952884934181731e-06, "epoch": 0.94153088934148, "percentage": 18.83, "elapsed_time": "0:17:06", "remaining_time": "1:13:46", "throughput": 10372.39, "total_tokens": 10650816}
{"current_steps": 11100, "total_steps": 58920, "loss": 0.0415, "lr": 1.9527950393198067e-06, "epoch": 0.9419551934826884, "percentage": 18.84, "elapsed_time": "0:17:07", "remaining_time": "1:13:45", "throughput": 10373.03, "total_tokens": 10655424}
{"current_steps": 11105, "total_steps": 58920, "loss": 0.0941, "lr": 1.9527050608535573e-06, "epoch": 0.9423794976238968, "percentage": 18.85, "elapsed_time": "0:17:07", "remaining_time": "1:13:44", "throughput": 10373.99, "total_tokens": 10660416}
{"current_steps": 11110, "total_steps": 58920, "loss": 0.0752, "lr": 1.9526149987908786e-06, "epoch": 0.9428038017651053, "percentage": 18.86, "elapsed_time": "0:17:07", "remaining_time": "1:13:43", "throughput": 10374.72, "total_tokens": 10665088}
{"current_steps": 11115, "total_steps": 58920, "loss": 0.0429, "lr": 1.9525248531396734e-06, "epoch": 0.9432281059063137, "percentage": 18.86, "elapsed_time": "0:17:08", "remaining_time": "1:13:42", "throughput": 10375.3, "total_tokens": 10669632}
{"current_steps": 11120, "total_steps": 58920, "loss": 0.0486, "lr": 1.9524346239078512e-06, "epoch": 0.9436524100475221, "percentage": 18.87, "elapsed_time": "0:17:08", "remaining_time": "1:13:42", "throughput": 10376.37, "total_tokens": 10674752}
{"current_steps": 11125, "total_steps": 58920, "loss": 0.0328, "lr": 1.9523443111033294e-06, "epoch": 0.9440767141887305, "percentage": 18.88, "elapsed_time": "0:17:09", "remaining_time": "1:13:41", "throughput": 10376.95, "total_tokens": 10679296}
{"current_steps": 11130, "total_steps": 58920, "loss": 0.1319, "lr": 1.9522539147340326e-06, "epoch": 0.9445010183299389, "percentage": 18.89, "elapsed_time": "0:17:09", "remaining_time": "1:13:40", "throughput": 10377.67, "total_tokens": 10683968}
{"current_steps": 11135, "total_steps": 58920, "loss": 0.0941, "lr": 1.952163434807893e-06, "epoch": 0.9449253224711474, "percentage": 18.9, "elapsed_time": "0:17:09", "remaining_time": "1:13:39", "throughput": 10378.28, "total_tokens": 10688512}
{"current_steps": 11140, "total_steps": 58920, "loss": 0.0927, "lr": 1.95207287133285e-06, "epoch": 0.9453496266123558, "percentage": 18.91, "elapsed_time": "0:17:10", "remaining_time": "1:13:38", "throughput": 10379.09, "total_tokens": 10693312}
{"current_steps": 11145, "total_steps": 58920, "loss": 0.1105, "lr": 1.95198222431685e-06, "epoch": 0.9457739307535642, "percentage": 18.92, "elapsed_time": "0:17:10", "remaining_time": "1:13:38", "throughput": 10380.31, "total_tokens": 10698688}
{"current_steps": 11150, "total_steps": 58920, "loss": 0.1329, "lr": 1.9518914937678466e-06, "epoch": 0.9461982348947726, "percentage": 18.92, "elapsed_time": "0:17:11", "remaining_time": "1:13:37", "throughput": 10381.83, "total_tokens": 10704448}
{"current_steps": 11155, "total_steps": 58920, "loss": 0.0572, "lr": 1.951800679693802e-06, "epoch": 0.946622539035981, "percentage": 18.93, "elapsed_time": "0:17:11", "remaining_time": "1:13:36", "throughput": 10382.68, "total_tokens": 10709312}
{"current_steps": 11160, "total_steps": 58920, "loss": 0.0555, "lr": 1.9517097821026837e-06, "epoch": 0.9470468431771895, "percentage": 18.94, "elapsed_time": "0:17:11", "remaining_time": "1:13:35", "throughput": 10383.7, "total_tokens": 10714368}
{"current_steps": 11165, "total_steps": 58920, "loss": 0.0707, "lr": 1.9516188010024682e-06, "epoch": 0.9474711473183979, "percentage": 18.95, "elapsed_time": "0:17:12", "remaining_time": "1:13:35", "throughput": 10384.25, "total_tokens": 10718848}
{"current_steps": 11170, "total_steps": 58920, "loss": 0.0277, "lr": 1.951527736401139e-06, "epoch": 0.9478954514596063, "percentage": 18.96, "elapsed_time": "0:17:12", "remaining_time": "1:13:34", "throughput": 10385.09, "total_tokens": 10723712}
{"current_steps": 11175, "total_steps": 58920, "loss": 0.0509, "lr": 1.9514365883066863e-06, "epoch": 0.9483197556008147, "percentage": 18.97, "elapsed_time": "0:17:12", "remaining_time": "1:13:33", "throughput": 10385.78, "total_tokens": 10728384}
{"current_steps": 11180, "total_steps": 58920, "loss": 0.0159, "lr": 1.951345356727108e-06, "epoch": 0.948744059742023, "percentage": 18.97, "elapsed_time": "0:17:13", "remaining_time": "1:13:32", "throughput": 10386.88, "total_tokens": 10733632}
{"current_steps": 11185, "total_steps": 58920, "loss": 0.0762, "lr": 1.951254041670409e-06, "epoch": 0.9491683638832314, "percentage": 18.98, "elapsed_time": "0:17:13", "remaining_time": "1:13:31", "throughput": 10387.99, "total_tokens": 10738880}
{"current_steps": 11190, "total_steps": 58920, "loss": 0.0761, "lr": 1.9511626431446035e-06, "epoch": 0.9495926680244399, "percentage": 18.99, "elapsed_time": "0:17:14", "remaining_time": "1:13:31", "throughput": 10389.3, "total_tokens": 10744384}
{"current_steps": 11195, "total_steps": 58920, "loss": 0.0221, "lr": 1.9510711611577092e-06, "epoch": 0.9500169721656483, "percentage": 19.0, "elapsed_time": "0:17:14", "remaining_time": "1:13:30", "throughput": 10390.46, "total_tokens": 10749632}
{"current_steps": 11200, "total_steps": 58920, "loss": 0.0282, "lr": 1.9509795957177548e-06, "epoch": 0.9504412763068567, "percentage": 19.01, "elapsed_time": "0:17:14", "remaining_time": "1:13:29", "throughput": 10391.42, "total_tokens": 10754624}
{"current_steps": 11205, "total_steps": 58920, "loss": 0.082, "lr": 1.950887946832774e-06, "epoch": 0.9508655804480651, "percentage": 19.02, "elapsed_time": "0:17:15", "remaining_time": "1:13:28", "throughput": 10392.27, "total_tokens": 10759488}
{"current_steps": 11210, "total_steps": 58920, "loss": 0.0113, "lr": 1.9507962145108096e-06, "epoch": 0.9512898845892735, "percentage": 19.03, "elapsed_time": "0:17:15", "remaining_time": "1:13:28", "throughput": 10392.91, "total_tokens": 10764096}
{"current_steps": 11215, "total_steps": 58920, "loss": 0.0538, "lr": 1.95070439875991e-06, "epoch": 0.951714188730482, "percentage": 19.03, "elapsed_time": "0:17:16", "remaining_time": "1:13:27", "throughput": 10393.54, "total_tokens": 10768640}
{"current_steps": 11220, "total_steps": 58920, "loss": 0.0557, "lr": 1.9506124995881315e-06, "epoch": 0.9521384928716904, "percentage": 19.04, "elapsed_time": "0:17:16", "remaining_time": "1:13:26", "throughput": 10394.76, "total_tokens": 10774016}
{"current_steps": 11225, "total_steps": 58920, "loss": 0.0582, "lr": 1.950520517003539e-06, "epoch": 0.9525627970128988, "percentage": 19.05, "elapsed_time": "0:17:16", "remaining_time": "1:13:25", "throughput": 10395.73, "total_tokens": 10779072}
{"current_steps": 11230, "total_steps": 58920, "loss": 0.101, "lr": 1.9504284510142026e-06, "epoch": 0.9529871011541072, "percentage": 19.06, "elapsed_time": "0:17:17", "remaining_time": "1:13:24", "throughput": 10396.65, "total_tokens": 10784000}
{"current_steps": 11235, "total_steps": 58920, "loss": 0.0547, "lr": 1.950336301628201e-06, "epoch": 0.9534114052953157, "percentage": 19.07, "elapsed_time": "0:17:17", "remaining_time": "1:13:24", "throughput": 10397.52, "total_tokens": 10788928}
{"current_steps": 11240, "total_steps": 58920, "loss": 0.0475, "lr": 1.95024406885362e-06, "epoch": 0.9538357094365241, "percentage": 19.08, "elapsed_time": "0:17:18", "remaining_time": "1:13:23", "throughput": 10398.73, "total_tokens": 10794304}
{"current_steps": 11245, "total_steps": 58920, "loss": 0.0096, "lr": 1.9501517526985535e-06, "epoch": 0.9542600135777325, "percentage": 19.09, "elapsed_time": "0:17:18", "remaining_time": "1:13:22", "throughput": 10399.08, "total_tokens": 10798528}
{"current_steps": 11250, "total_steps": 58920, "loss": 0.0918, "lr": 1.9500593531711007e-06, "epoch": 0.9546843177189409, "percentage": 19.09, "elapsed_time": "0:17:18", "remaining_time": "1:13:21", "throughput": 10399.82, "total_tokens": 10803200}
{"current_steps": 11255, "total_steps": 58920, "loss": 0.0358, "lr": 1.94996687027937e-06, "epoch": 0.9551086218601493, "percentage": 19.1, "elapsed_time": "0:17:19", "remaining_time": "1:13:20", "throughput": 10400.37, "total_tokens": 10807680}
{"current_steps": 11260, "total_steps": 58920, "loss": 0.0523, "lr": 1.949874304031476e-06, "epoch": 0.9555329260013578, "percentage": 19.11, "elapsed_time": "0:17:19", "remaining_time": "1:13:20", "throughput": 10401.0, "total_tokens": 10812224}
{"current_steps": 11265, "total_steps": 58920, "loss": 0.0556, "lr": 1.9497816544355415e-06, "epoch": 0.9559572301425662, "percentage": 19.12, "elapsed_time": "0:17:19", "remaining_time": "1:13:19", "throughput": 10401.53, "total_tokens": 10816640}
{"current_steps": 11270, "total_steps": 58920, "loss": 0.0236, "lr": 1.949688921499696e-06, "epoch": 0.9563815342837746, "percentage": 19.13, "elapsed_time": "0:17:20", "remaining_time": "1:13:18", "throughput": 10402.32, "total_tokens": 10821440}
{"current_steps": 11275, "total_steps": 58920, "loss": 0.0904, "lr": 1.9495961052320765e-06, "epoch": 0.956805838424983, "percentage": 19.14, "elapsed_time": "0:17:20", "remaining_time": "1:13:17", "throughput": 10403.35, "total_tokens": 10826560}
{"current_steps": 11280, "total_steps": 58920, "loss": 0.0732, "lr": 1.9495032056408272e-06, "epoch": 0.9572301425661914, "percentage": 19.14, "elapsed_time": "0:17:21", "remaining_time": "1:13:16", "throughput": 10404.3, "total_tokens": 10831552}
{"current_steps": 11285, "total_steps": 58920, "loss": 0.0279, "lr": 1.9494102227341e-06, "epoch": 0.9576544467073999, "percentage": 19.15, "elapsed_time": "0:17:21", "remaining_time": "1:13:16", "throughput": 10404.81, "total_tokens": 10835968}
{"current_steps": 11290, "total_steps": 58920, "loss": 0.0713, "lr": 1.9493171565200533e-06, "epoch": 0.9580787508486083, "percentage": 19.16, "elapsed_time": "0:17:21", "remaining_time": "1:13:15", "throughput": 10405.04, "total_tokens": 10840064}
{"current_steps": 11295, "total_steps": 58920, "loss": 0.0901, "lr": 1.9492240070068536e-06, "epoch": 0.9585030549898167, "percentage": 19.17, "elapsed_time": "0:17:22", "remaining_time": "1:13:14", "throughput": 10405.67, "total_tokens": 10844672}
{"current_steps": 11300, "total_steps": 58920, "loss": 0.0666, "lr": 1.9491307742026752e-06, "epoch": 0.9589273591310251, "percentage": 19.18, "elapsed_time": "0:17:22", "remaining_time": "1:13:13", "throughput": 10407.11, "total_tokens": 10850304}
{"current_steps": 11305, "total_steps": 58920, "loss": 0.0409, "lr": 1.9490374581156975e-06, "epoch": 0.9593516632722335, "percentage": 19.19, "elapsed_time": "0:17:22", "remaining_time": "1:13:12", "throughput": 10407.77, "total_tokens": 10854912}
{"current_steps": 11310, "total_steps": 58920, "loss": 0.0386, "lr": 1.9489440587541092e-06, "epoch": 0.959775967413442, "percentage": 19.2, "elapsed_time": "0:17:23", "remaining_time": "1:13:12", "throughput": 10408.67, "total_tokens": 10859904}
{"current_steps": 11315, "total_steps": 58920, "loss": 0.0675, "lr": 1.9488505761261062e-06, "epoch": 0.9602002715546504, "percentage": 19.2, "elapsed_time": "0:17:23", "remaining_time": "1:13:11", "throughput": 10409.47, "total_tokens": 10864704}
{"current_steps": 11320, "total_steps": 58920, "loss": 0.0162, "lr": 1.9487570102398907e-06, "epoch": 0.9606245756958588, "percentage": 19.21, "elapsed_time": "0:17:24", "remaining_time": "1:13:10", "throughput": 10410.09, "total_tokens": 10869248}
{"current_steps": 11325, "total_steps": 58920, "loss": 0.0403, "lr": 1.9486633611036735e-06, "epoch": 0.9610488798370672, "percentage": 19.22, "elapsed_time": "0:17:24", "remaining_time": "1:13:09", "throughput": 10410.83, "total_tokens": 10873984}
{"current_steps": 11330, "total_steps": 58920, "loss": 0.0983, "lr": 1.948569628725671e-06, "epoch": 0.9614731839782756, "percentage": 19.23, "elapsed_time": "0:17:24", "remaining_time": "1:13:08", "throughput": 10411.49, "total_tokens": 10878592}
{"current_steps": 11335, "total_steps": 58920, "loss": 0.0909, "lr": 1.9484758131141088e-06, "epoch": 0.9618974881194841, "percentage": 19.24, "elapsed_time": "0:17:25", "remaining_time": "1:13:08", "throughput": 10412.17, "total_tokens": 10883264}
{"current_steps": 11340, "total_steps": 58920, "loss": 0.0269, "lr": 1.948381914277218e-06, "epoch": 0.9623217922606925, "percentage": 19.25, "elapsed_time": "0:17:25", "remaining_time": "1:13:07", "throughput": 10412.56, "total_tokens": 10887552}
{"current_steps": 11345, "total_steps": 58920, "loss": 0.0955, "lr": 1.9482879322232384e-06, "epoch": 0.9627460964019009, "percentage": 19.25, "elapsed_time": "0:17:26", "remaining_time": "1:13:06", "throughput": 10413.69, "total_tokens": 10892800}
{"current_steps": 11350, "total_steps": 58920, "loss": 0.1207, "lr": 1.9481938669604166e-06, "epoch": 0.9631704005431093, "percentage": 19.26, "elapsed_time": "0:17:26", "remaining_time": "1:13:05", "throughput": 10414.25, "total_tokens": 10897280}
{"current_steps": 11355, "total_steps": 58920, "loss": 0.0548, "lr": 1.948099718497007e-06, "epoch": 0.9635947046843177, "percentage": 19.27, "elapsed_time": "0:17:26", "remaining_time": "1:13:04", "throughput": 10415.09, "total_tokens": 10902144}
{"current_steps": 11360, "total_steps": 58920, "loss": 0.0687, "lr": 1.9480054868412693e-06, "epoch": 0.9640190088255262, "percentage": 19.28, "elapsed_time": "0:17:27", "remaining_time": "1:13:04", "throughput": 10416.1, "total_tokens": 10907264}
{"current_steps": 11365, "total_steps": 58920, "loss": 0.0105, "lr": 1.9479111720014733e-06, "epoch": 0.9644433129667346, "percentage": 19.29, "elapsed_time": "0:17:27", "remaining_time": "1:13:03", "throughput": 10416.71, "total_tokens": 10911808}
{"current_steps": 11370, "total_steps": 58920, "loss": 0.0455, "lr": 1.9478167739858942e-06, "epoch": 0.964867617107943, "percentage": 19.3, "elapsed_time": "0:17:27", "remaining_time": "1:13:02", "throughput": 10417.47, "total_tokens": 10916544}
{"current_steps": 11375, "total_steps": 58920, "loss": 0.0315, "lr": 1.9477222928028153e-06, "epoch": 0.9652919212491514, "percentage": 19.31, "elapsed_time": "0:17:28", "remaining_time": "1:13:01", "throughput": 10418.0, "total_tokens": 10921024}
{"current_steps": 11380, "total_steps": 58920, "loss": 0.0536, "lr": 1.9476277284605276e-06, "epoch": 0.9657162253903598, "percentage": 19.31, "elapsed_time": "0:17:28", "remaining_time": "1:13:00", "throughput": 10418.87, "total_tokens": 10926016}
{"current_steps": 11385, "total_steps": 58920, "loss": 0.1187, "lr": 1.9475330809673274e-06, "epoch": 0.9661405295315683, "percentage": 19.32, "elapsed_time": "0:17:29", "remaining_time": "1:13:00", "throughput": 10419.94, "total_tokens": 10931200}
{"current_steps": 11390, "total_steps": 58920, "loss": 0.0915, "lr": 1.9474383503315204e-06, "epoch": 0.9665648336727767, "percentage": 19.33, "elapsed_time": "0:17:29", "remaining_time": "1:12:59", "throughput": 10420.96, "total_tokens": 10936384}
{"current_steps": 11395, "total_steps": 58920, "loss": 0.0691, "lr": 1.9473435365614193e-06, "epoch": 0.9669891378139851, "percentage": 19.34, "elapsed_time": "0:17:29", "remaining_time": "1:12:58", "throughput": 10421.75, "total_tokens": 10941184}
{"current_steps": 11400, "total_steps": 58920, "loss": 0.0733, "lr": 1.947248639665343e-06, "epoch": 0.9674134419551935, "percentage": 19.35, "elapsed_time": "0:17:30", "remaining_time": "1:12:57", "throughput": 10422.1, "total_tokens": 10945408}
{"current_steps": 11405, "total_steps": 58920, "loss": 0.1023, "lr": 1.9471536596516185e-06, "epoch": 0.9678377460964019, "percentage": 19.36, "elapsed_time": "0:17:30", "remaining_time": "1:12:56", "throughput": 10422.84, "total_tokens": 10950144}
{"current_steps": 11410, "total_steps": 58920, "loss": 0.0923, "lr": 1.94705859652858e-06, "epoch": 0.9682620502376104, "percentage": 19.37, "elapsed_time": "0:17:30", "remaining_time": "1:12:56", "throughput": 10423.85, "total_tokens": 10955264}
{"current_steps": 11415, "total_steps": 58920, "loss": 0.0214, "lr": 1.9469634503045693e-06, "epoch": 0.9686863543788188, "percentage": 19.37, "elapsed_time": "0:17:31", "remaining_time": "1:12:55", "throughput": 10424.75, "total_tokens": 10960256}
{"current_steps": 11420, "total_steps": 58920, "loss": 0.0809, "lr": 1.9468682209879346e-06, "epoch": 0.9691106585200272, "percentage": 19.38, "elapsed_time": "0:17:31", "remaining_time": "1:12:54", "throughput": 10425.26, "total_tokens": 10964672}
{"current_steps": 11425, "total_steps": 58920, "loss": 0.0625, "lr": 1.9467729085870325e-06, "epoch": 0.9695349626612356, "percentage": 19.39, "elapsed_time": "0:17:32", "remaining_time": "1:12:53", "throughput": 10426.2, "total_tokens": 10969728}
{"current_steps": 11430, "total_steps": 58920, "loss": 0.0553, "lr": 1.9466775131102257e-06, "epoch": 0.969959266802444, "percentage": 19.4, "elapsed_time": "0:17:32", "remaining_time": "1:12:53", "throughput": 10427.14, "total_tokens": 10974720}
{"current_steps": 11435, "total_steps": 58920, "loss": 0.0735, "lr": 1.946582034565885e-06, "epoch": 0.9703835709436525, "percentage": 19.41, "elapsed_time": "0:17:32", "remaining_time": "1:12:52", "throughput": 10427.5, "total_tokens": 10979008}
{"current_steps": 11440, "total_steps": 58920, "loss": 0.0484, "lr": 1.9464864729623886e-06, "epoch": 0.9708078750848609, "percentage": 19.42, "elapsed_time": "0:17:33", "remaining_time": "1:12:51", "throughput": 10428.51, "total_tokens": 10984128}
{"current_steps": 11445, "total_steps": 58920, "loss": 0.0812, "lr": 1.9463908283081212e-06, "epoch": 0.9712321792260692, "percentage": 19.42, "elapsed_time": "0:17:33", "remaining_time": "1:12:50", "throughput": 10428.92, "total_tokens": 10988480}
{"current_steps": 11450, "total_steps": 58920, "loss": 0.0718, "lr": 1.946295100611476e-06, "epoch": 0.9716564833672776, "percentage": 19.43, "elapsed_time": "0:17:34", "remaining_time": "1:12:49", "throughput": 10429.38, "total_tokens": 10992896}
{"current_steps": 11455, "total_steps": 58920, "loss": 0.0745, "lr": 1.9461992898808515e-06, "epoch": 0.972080787508486, "percentage": 19.44, "elapsed_time": "0:17:34", "remaining_time": "1:12:49", "throughput": 10430.18, "total_tokens": 10997696}
{"current_steps": 11460, "total_steps": 58920, "loss": 0.0889, "lr": 1.9461033961246565e-06, "epoch": 0.9725050916496945, "percentage": 19.45, "elapsed_time": "0:17:34", "remaining_time": "1:12:48", "throughput": 10431.25, "total_tokens": 11002944}
{"current_steps": 11465, "total_steps": 58920, "loss": 0.1058, "lr": 1.946007419351304e-06, "epoch": 0.9729293957909029, "percentage": 19.46, "elapsed_time": "0:17:35", "remaining_time": "1:12:47", "throughput": 10432.47, "total_tokens": 11008384}
{"current_steps": 11470, "total_steps": 58920, "loss": 0.0897, "lr": 1.945911359569216e-06, "epoch": 0.9733536999321113, "percentage": 19.47, "elapsed_time": "0:17:35", "remaining_time": "1:12:46", "throughput": 10432.98, "total_tokens": 11012800}
{"current_steps": 11475, "total_steps": 58920, "loss": 0.1333, "lr": 1.945815216786821e-06, "epoch": 0.9737780040733197, "percentage": 19.48, "elapsed_time": "0:17:35", "remaining_time": "1:12:45", "throughput": 10433.47, "total_tokens": 11017216}
{"current_steps": 11480, "total_steps": 58920, "loss": 0.0765, "lr": 1.9457189910125562e-06, "epoch": 0.9742023082145281, "percentage": 19.48, "elapsed_time": "0:17:36", "remaining_time": "1:12:45", "throughput": 10433.84, "total_tokens": 11021504}
{"current_steps": 11485, "total_steps": 58920, "loss": 0.082, "lr": 1.945622682254864e-06, "epoch": 0.9746266123557366, "percentage": 19.49, "elapsed_time": "0:17:36", "remaining_time": "1:12:44", "throughput": 10434.97, "total_tokens": 11026816}
{"current_steps": 11490, "total_steps": 58920, "loss": 0.0536, "lr": 1.945526290522196e-06, "epoch": 0.975050916496945, "percentage": 19.5, "elapsed_time": "0:17:37", "remaining_time": "1:12:43", "throughput": 10436.3, "total_tokens": 11032448}
{"current_steps": 11495, "total_steps": 58920, "loss": 0.0907, "lr": 1.9454298158230093e-06, "epoch": 0.9754752206381534, "percentage": 19.51, "elapsed_time": "0:17:37", "remaining_time": "1:12:42", "throughput": 10436.89, "total_tokens": 11037056}
{"current_steps": 11500, "total_steps": 58920, "loss": 0.0883, "lr": 1.9453332581657703e-06, "epoch": 0.9758995247793618, "percentage": 19.52, "elapsed_time": "0:17:37", "remaining_time": "1:12:42", "throughput": 10437.12, "total_tokens": 11041152}
{"current_steps": 11505, "total_steps": 58920, "loss": 0.0464, "lr": 1.9452366175589505e-06, "epoch": 0.9763238289205702, "percentage": 19.53, "elapsed_time": "0:17:38", "remaining_time": "1:12:41", "throughput": 10437.53, "total_tokens": 11045504}
{"current_steps": 11510, "total_steps": 58920, "loss": 0.0852, "lr": 1.945139894011031e-06, "epoch": 0.9767481330617787, "percentage": 19.53, "elapsed_time": "0:17:38", "remaining_time": "1:12:40", "throughput": 10437.93, "total_tokens": 11049792}
{"current_steps": 11515, "total_steps": 58920, "loss": 0.0397, "lr": 1.9450430875304973e-06, "epoch": 0.9771724372029871, "percentage": 19.54, "elapsed_time": "0:17:38", "remaining_time": "1:12:39", "throughput": 10438.22, "total_tokens": 11053952}
{"current_steps": 11520, "total_steps": 58920, "loss": 0.0689, "lr": 1.9449461981258453e-06, "epoch": 0.9775967413441955, "percentage": 19.55, "elapsed_time": "0:17:39", "remaining_time": "1:12:38", "throughput": 10438.6, "total_tokens": 11058240}
{"current_steps": 11525, "total_steps": 58920, "loss": 0.0692, "lr": 1.944849225805576e-06, "epoch": 0.9780210454854039, "percentage": 19.56, "elapsed_time": "0:17:39", "remaining_time": "1:12:38", "throughput": 10439.7, "total_tokens": 11063488}
{"current_steps": 11530, "total_steps": 58920, "loss": 0.0473, "lr": 1.9447521705781986e-06, "epoch": 0.9784453496266123, "percentage": 19.57, "elapsed_time": "0:17:40", "remaining_time": "1:12:37", "throughput": 10440.32, "total_tokens": 11068096}
{"current_steps": 11535, "total_steps": 58920, "loss": 0.0787, "lr": 1.944655032452229e-06, "epoch": 0.9788696537678208, "percentage": 19.58, "elapsed_time": "0:17:40", "remaining_time": "1:12:36", "throughput": 10441.68, "total_tokens": 11073728}
{"current_steps": 11540, "total_steps": 58920, "loss": 0.101, "lr": 1.9445578114361906e-06, "epoch": 0.9792939579090292, "percentage": 19.59, "elapsed_time": "0:17:40", "remaining_time": "1:12:35", "throughput": 10442.11, "total_tokens": 11078144}
{"current_steps": 11545, "total_steps": 58920, "loss": 0.0241, "lr": 1.9444605075386153e-06, "epoch": 0.9797182620502376, "percentage": 19.59, "elapsed_time": "0:17:41", "remaining_time": "1:12:35", "throughput": 10443.16, "total_tokens": 11083328}
{"current_steps": 11550, "total_steps": 58920, "loss": 0.0891, "lr": 1.94436312076804e-06, "epoch": 0.980142566191446, "percentage": 19.6, "elapsed_time": "0:17:41", "remaining_time": "1:12:34", "throughput": 10443.9, "total_tokens": 11088064}
{"current_steps": 11555, "total_steps": 58920, "loss": 0.0286, "lr": 1.9442656511330106e-06, "epoch": 0.9805668703326544, "percentage": 19.61, "elapsed_time": "0:17:42", "remaining_time": "1:12:33", "throughput": 10444.56, "total_tokens": 11092736}
{"current_steps": 11560, "total_steps": 58920, "loss": 0.0769, "lr": 1.94416809864208e-06, "epoch": 0.9809911744738629, "percentage": 19.62, "elapsed_time": "0:17:42", "remaining_time": "1:12:32", "throughput": 10445.81, "total_tokens": 11098176}
{"current_steps": 11565, "total_steps": 58920, "loss": 0.0775, "lr": 1.944070463303807e-06, "epoch": 0.9814154786150713, "percentage": 19.63, "elapsed_time": "0:17:42", "remaining_time": "1:12:31", "throughput": 10446.5, "total_tokens": 11102912}
{"current_steps": 11570, "total_steps": 58920, "loss": 0.1006, "lr": 1.94397274512676e-06, "epoch": 0.9818397827562797, "percentage": 19.64, "elapsed_time": "0:17:43", "remaining_time": "1:12:31", "throughput": 10447.03, "total_tokens": 11107392}
{"current_steps": 11575, "total_steps": 58920, "loss": 0.0542, "lr": 1.943874944119512e-06, "epoch": 0.9822640868974881, "percentage": 19.65, "elapsed_time": "0:17:43", "remaining_time": "1:12:30", "throughput": 10447.87, "total_tokens": 11112256}
{"current_steps": 11580, "total_steps": 58920, "loss": 0.0505, "lr": 1.943777060290646e-06, "epoch": 0.9826883910386965, "percentage": 19.65, "elapsed_time": "0:17:43", "remaining_time": "1:12:29", "throughput": 10448.85, "total_tokens": 11117376}
{"current_steps": 11585, "total_steps": 58920, "loss": 0.0786, "lr": 1.9436790936487506e-06, "epoch": 0.983112695179905, "percentage": 19.66, "elapsed_time": "0:17:44", "remaining_time": "1:12:28", "throughput": 10449.91, "total_tokens": 11122624}
{"current_steps": 11590, "total_steps": 58920, "loss": 0.038, "lr": 1.9435810442024216e-06, "epoch": 0.9835369993211134, "percentage": 19.67, "elapsed_time": "0:17:44", "remaining_time": "1:12:28", "throughput": 10450.87, "total_tokens": 11127680}
{"current_steps": 11595, "total_steps": 58920, "loss": 0.087, "lr": 1.9434829119602627e-06, "epoch": 0.9839613034623218, "percentage": 19.68, "elapsed_time": "0:17:45", "remaining_time": "1:12:27", "throughput": 10451.74, "total_tokens": 11132672}
{"current_steps": 11600, "total_steps": 58920, "loss": 0.0532, "lr": 1.943384696930885e-06, "epoch": 0.9843856076035302, "percentage": 19.69, "elapsed_time": "0:17:45", "remaining_time": "1:12:26", "throughput": 10452.45, "total_tokens": 11137408}
{"current_steps": 11605, "total_steps": 58920, "loss": 0.0492, "lr": 1.943286399122906e-06, "epoch": 0.9848099117447386, "percentage": 19.7, "elapsed_time": "0:17:45", "remaining_time": "1:12:25", "throughput": 10453.06, "total_tokens": 11142016}
{"current_steps": 11610, "total_steps": 58920, "loss": 0.0396, "lr": 1.9431880185449516e-06, "epoch": 0.9852342158859471, "percentage": 19.7, "elapsed_time": "0:17:46", "remaining_time": "1:12:25", "throughput": 10453.69, "total_tokens": 11146624}
{"current_steps": 11615, "total_steps": 58920, "loss": 0.0797, "lr": 1.9430895552056532e-06, "epoch": 0.9856585200271555, "percentage": 19.71, "elapsed_time": "0:17:46", "remaining_time": "1:12:24", "throughput": 10454.6, "total_tokens": 11151680}
{"current_steps": 11620, "total_steps": 58920, "loss": 0.053, "lr": 1.9429910091136517e-06, "epoch": 0.9860828241683639, "percentage": 19.72, "elapsed_time": "0:17:47", "remaining_time": "1:12:23", "throughput": 10455.09, "total_tokens": 11156096}
{"current_steps": 11625, "total_steps": 58920, "loss": 0.0402, "lr": 1.9428923802775942e-06, "epoch": 0.9865071283095723, "percentage": 19.73, "elapsed_time": "0:17:47", "remaining_time": "1:12:22", "throughput": 10455.37, "total_tokens": 11160256}
{"current_steps": 11630, "total_steps": 58920, "loss": 0.0529, "lr": 1.9427936687061343e-06, "epoch": 0.9869314324507807, "percentage": 19.74, "elapsed_time": "0:17:47", "remaining_time": "1:12:21", "throughput": 10456.51, "total_tokens": 11165568}
{"current_steps": 11635, "total_steps": 58920, "loss": 0.048, "lr": 1.9426948744079335e-06, "epoch": 0.9873557365919892, "percentage": 19.75, "elapsed_time": "0:17:48", "remaining_time": "1:12:21", "throughput": 10457.31, "total_tokens": 11170432}
{"current_steps": 11640, "total_steps": 58920, "loss": 0.0911, "lr": 1.9425959973916617e-06, "epoch": 0.9877800407331976, "percentage": 19.76, "elapsed_time": "0:17:48", "remaining_time": "1:12:20", "throughput": 10457.94, "total_tokens": 11175104}
{"current_steps": 11645, "total_steps": 58920, "loss": 0.0066, "lr": 1.9424970376659942e-06, "epoch": 0.988204344874406, "percentage": 19.76, "elapsed_time": "0:17:48", "remaining_time": "1:12:19", "throughput": 10458.49, "total_tokens": 11179584}
{"current_steps": 11650, "total_steps": 58920, "loss": 0.105, "lr": 1.9423979952396145e-06, "epoch": 0.9886286490156144, "percentage": 19.77, "elapsed_time": "0:17:49", "remaining_time": "1:12:18", "throughput": 10459.65, "total_tokens": 11184960}
{"current_steps": 11655, "total_steps": 58920, "loss": 0.0854, "lr": 1.942298870121213e-06, "epoch": 0.9890529531568228, "percentage": 19.78, "elapsed_time": "0:17:49", "remaining_time": "1:12:18", "throughput": 10460.89, "total_tokens": 11190464}
{"current_steps": 11660, "total_steps": 58920, "loss": 0.0776, "lr": 1.942199662319488e-06, "epoch": 0.9894772572980313, "percentage": 19.79, "elapsed_time": "0:17:50", "remaining_time": "1:12:17", "throughput": 10461.71, "total_tokens": 11195392}
{"current_steps": 11665, "total_steps": 58920, "loss": 0.0351, "lr": 1.9421003718431444e-06, "epoch": 0.9899015614392397, "percentage": 19.8, "elapsed_time": "0:17:50", "remaining_time": "1:12:16", "throughput": 10462.39, "total_tokens": 11200128}
{"current_steps": 11670, "total_steps": 58920, "loss": 0.0684, "lr": 1.9420009987008946e-06, "epoch": 0.9903258655804481, "percentage": 19.81, "elapsed_time": "0:17:50", "remaining_time": "1:12:15", "throughput": 10463.07, "total_tokens": 11204800}
{"current_steps": 11675, "total_steps": 58920, "loss": 0.0896, "lr": 1.941901542901458e-06, "epoch": 0.9907501697216565, "percentage": 19.82, "elapsed_time": "0:17:51", "remaining_time": "1:12:15", "throughput": 10463.74, "total_tokens": 11209472}
{"current_steps": 11680, "total_steps": 58920, "loss": 0.0944, "lr": 1.9418020044535623e-06, "epoch": 0.991174473862865, "percentage": 19.82, "elapsed_time": "0:17:51", "remaining_time": "1:12:14", "throughput": 10464.32, "total_tokens": 11214016}
{"current_steps": 11685, "total_steps": 58920, "loss": 0.0715, "lr": 1.9417023833659405e-06, "epoch": 0.9915987780040734, "percentage": 19.83, "elapsed_time": "0:17:52", "remaining_time": "1:12:13", "throughput": 10465.01, "total_tokens": 11218752}
{"current_steps": 11690, "total_steps": 58920, "loss": 0.1443, "lr": 1.941602679647335e-06, "epoch": 0.9920230821452818, "percentage": 19.84, "elapsed_time": "0:17:52", "remaining_time": "1:12:12", "throughput": 10465.77, "total_tokens": 11223552}
{"current_steps": 11695, "total_steps": 58920, "loss": 0.0417, "lr": 1.941502893306494e-06, "epoch": 0.9924473862864902, "percentage": 19.85, "elapsed_time": "0:17:52", "remaining_time": "1:12:11", "throughput": 10466.28, "total_tokens": 11228032}
{"current_steps": 11700, "total_steps": 58920, "loss": 0.0261, "lr": 1.9414030243521727e-06, "epoch": 0.9928716904276986, "percentage": 19.86, "elapsed_time": "0:17:53", "remaining_time": "1:12:11", "throughput": 10466.72, "total_tokens": 11232448}
{"current_steps": 11705, "total_steps": 58920, "loss": 0.0495, "lr": 1.941303072793136e-06, "epoch": 0.993295994568907, "percentage": 19.87, "elapsed_time": "0:17:53", "remaining_time": "1:12:10", "throughput": 10467.58, "total_tokens": 11237440}
{"current_steps": 11710, "total_steps": 58920, "loss": 0.087, "lr": 1.9412030386381525e-06, "epoch": 0.9937202987101154, "percentage": 19.87, "elapsed_time": "0:17:53", "remaining_time": "1:12:09", "throughput": 10468.18, "total_tokens": 11242048}
{"current_steps": 11715, "total_steps": 58920, "loss": 0.1086, "lr": 1.9411029218960006e-06, "epoch": 0.9941446028513238, "percentage": 19.88, "elapsed_time": "0:17:54", "remaining_time": "1:12:08", "throughput": 10468.62, "total_tokens": 11246400}
{"current_steps": 11720, "total_steps": 58920, "loss": 0.0556, "lr": 1.9410027225754653e-06, "epoch": 0.9945689069925322, "percentage": 19.89, "elapsed_time": "0:17:54", "remaining_time": "1:12:08", "throughput": 10469.51, "total_tokens": 11251456}
{"current_steps": 11725, "total_steps": 58920, "loss": 0.0265, "lr": 1.940902440685339e-06, "epoch": 0.9949932111337406, "percentage": 19.9, "elapsed_time": "0:17:55", "remaining_time": "1:12:07", "throughput": 10470.13, "total_tokens": 11256128}
{"current_steps": 11730, "total_steps": 58920, "loss": 0.0622, "lr": 1.9408020762344198e-06, "epoch": 0.995417515274949, "percentage": 19.91, "elapsed_time": "0:17:55", "remaining_time": "1:12:06", "throughput": 10470.73, "total_tokens": 11260736}
{"current_steps": 11735, "total_steps": 58920, "loss": 0.0497, "lr": 1.9407016292315155e-06, "epoch": 0.9958418194161575, "percentage": 19.92, "elapsed_time": "0:17:55", "remaining_time": "1:12:05", "throughput": 10470.99, "total_tokens": 11264896}
{"current_steps": 11740, "total_steps": 58920, "loss": 0.0056, "lr": 1.9406010996854398e-06, "epoch": 0.9962661235573659, "percentage": 19.93, "elapsed_time": "0:17:56", "remaining_time": "1:12:05", "throughput": 10472.19, "total_tokens": 11270400}
{"current_steps": 11745, "total_steps": 58920, "loss": 0.0276, "lr": 1.9405004876050133e-06, "epoch": 0.9966904276985743, "percentage": 19.93, "elapsed_time": "0:17:56", "remaining_time": "1:12:04", "throughput": 10472.77, "total_tokens": 11275008}
{"current_steps": 11750, "total_steps": 58920, "loss": 0.0774, "lr": 1.9403997929990654e-06, "epoch": 0.9971147318397827, "percentage": 19.94, "elapsed_time": "0:17:56", "remaining_time": "1:12:03", "throughput": 10473.51, "total_tokens": 11279808}
{"current_steps": 11755, "total_steps": 58920, "loss": 0.0847, "lr": 1.9402990158764303e-06, "epoch": 0.9975390359809911, "percentage": 19.95, "elapsed_time": "0:17:57", "remaining_time": "1:12:02", "throughput": 10473.73, "total_tokens": 11283904}
{"current_steps": 11760, "total_steps": 58920, "loss": 0.0912, "lr": 1.9401981562459514e-06, "epoch": 0.9979633401221996, "percentage": 19.96, "elapsed_time": "0:17:57", "remaining_time": "1:12:01", "throughput": 10474.31, "total_tokens": 11288512}
{"current_steps": 11765, "total_steps": 58920, "loss": 0.0917, "lr": 1.9400972141164794e-06, "epoch": 0.998387644263408, "percentage": 19.97, "elapsed_time": "0:17:58", "remaining_time": "1:12:01", "throughput": 10475.22, "total_tokens": 11293568}
{"current_steps": 11770, "total_steps": 58920, "loss": 0.108, "lr": 1.9399961894968705e-06, "epoch": 0.9988119484046164, "percentage": 19.98, "elapsed_time": "0:17:58", "remaining_time": "1:12:00", "throughput": 10476.23, "total_tokens": 11298752}
{"current_steps": 11775, "total_steps": 58920, "loss": 0.0568, "lr": 1.93989508239599e-06, "epoch": 0.9992362525458248, "percentage": 19.98, "elapsed_time": "0:17:58", "remaining_time": "1:11:59", "throughput": 10477.04, "total_tokens": 11303680}
{"current_steps": 11780, "total_steps": 58920, "loss": 0.0346, "lr": 1.93979389282271e-06, "epoch": 0.9996605566870332, "percentage": 19.99, "elapsed_time": "0:17:59", "remaining_time": "1:11:58", "throughput": 10477.69, "total_tokens": 11308288}
{"current_steps": 11784, "total_steps": 58920, "eval_loss": 0.053497761487960815, "epoch": 1.0, "percentage": 20.0, "elapsed_time": "0:18:15", "remaining_time": "1:13:03", "throughput": 10321.66, "total_tokens": 11312256}
{"current_steps": 11785, "total_steps": 58920, "loss": 0.064, "lr": 1.9396926207859082e-06, "epoch": 1.0000848608282418, "percentage": 20.0, "elapsed_time": "0:18:56", "remaining_time": "1:15:47", "throughput": 9950.73, "total_tokens": 11313024}
{"current_steps": 11790, "total_steps": 58920, "loss": 0.008, "lr": 1.939591266294472e-06, "epoch": 1.0005091649694502, "percentage": 20.01, "elapsed_time": "0:18:57", "remaining_time": "1:15:46", "throughput": 9951.67, "total_tokens": 11317952}
{"current_steps": 11795, "total_steps": 58920, "loss": 0.0456, "lr": 1.9394898293572947e-06, "epoch": 1.0009334691106586, "percentage": 20.02, "elapsed_time": "0:18:57", "remaining_time": "1:15:45", "throughput": 9952.4, "total_tokens": 11322560}
{"current_steps": 11800, "total_steps": 58920, "loss": 0.0513, "lr": 1.9393883099832768e-06, "epoch": 1.001357773251867, "percentage": 20.03, "elapsed_time": "0:18:58", "remaining_time": "1:15:44", "throughput": 9953.47, "total_tokens": 11327680}
{"current_steps": 11805, "total_steps": 58920, "loss": 0.0381, "lr": 1.9392867081813263e-06, "epoch": 1.0017820773930755, "percentage": 20.04, "elapsed_time": "0:18:58", "remaining_time": "1:15:43", "throughput": 9954.62, "total_tokens": 11332928}
{"current_steps": 11810, "total_steps": 58920, "loss": 0.0364, "lr": 1.9391850239603587e-06, "epoch": 1.0022063815342839, "percentage": 20.04, "elapsed_time": "0:18:58", "remaining_time": "1:15:42", "throughput": 9955.73, "total_tokens": 11338112}
{"current_steps": 11815, "total_steps": 58920, "loss": 0.0037, "lr": 1.9390832573292963e-06, "epoch": 1.0026306856754923, "percentage": 20.05, "elapsed_time": "0:18:59", "remaining_time": "1:15:41", "throughput": 9956.43, "total_tokens": 11342656}
{"current_steps": 11820, "total_steps": 58920, "loss": 0.0031, "lr": 1.9389814082970683e-06, "epoch": 1.0030549898167007, "percentage": 20.06, "elapsed_time": "0:18:59", "remaining_time": "1:15:41", "throughput": 9957.21, "total_tokens": 11347328}
{"current_steps": 11825, "total_steps": 58920, "loss": 0.0121, "lr": 1.9388794768726115e-06, "epoch": 1.0034792939579091, "percentage": 20.07, "elapsed_time": "0:18:59", "remaining_time": "1:15:40", "throughput": 9957.89, "total_tokens": 11351872}
{"current_steps": 11830, "total_steps": 58920, "loss": 0.0107, "lr": 1.938777463064871e-06, "epoch": 1.0039035980991176, "percentage": 20.08, "elapsed_time": "0:19:00", "remaining_time": "1:15:39", "throughput": 9958.37, "total_tokens": 11356160}
{"current_steps": 11835, "total_steps": 58920, "loss": 0.0426, "lr": 1.938675366882797e-06, "epoch": 1.004327902240326, "percentage": 20.09, "elapsed_time": "0:19:00", "remaining_time": "1:15:38", "throughput": 9959.55, "total_tokens": 11361472}
{"current_steps": 11840, "total_steps": 58920, "loss": 0.0402, "lr": 1.9385731883353493e-06, "epoch": 1.0047522063815342, "percentage": 20.1, "elapsed_time": "0:19:01", "remaining_time": "1:15:37", "throughput": 9960.22, "total_tokens": 11366016}
{"current_steps": 11845, "total_steps": 58920, "loss": 0.1372, "lr": 1.9384709274314924e-06, "epoch": 1.0051765105227426, "percentage": 20.1, "elapsed_time": "0:19:01", "remaining_time": "1:15:36", "throughput": 9960.86, "total_tokens": 11370496}
{"current_steps": 11850, "total_steps": 58920, "loss": 0.0448, "lr": 1.9383685841802007e-06, "epoch": 1.005600814663951, "percentage": 20.11, "elapsed_time": "0:19:01", "remaining_time": "1:15:35", "throughput": 9961.59, "total_tokens": 11375168}
{"current_steps": 11855, "total_steps": 58920, "loss": 0.1067, "lr": 1.938266158590453e-06, "epoch": 1.0060251188051594, "percentage": 20.12, "elapsed_time": "0:19:02", "remaining_time": "1:15:34", "throughput": 9961.95, "total_tokens": 11379264}
{"current_steps": 11860, "total_steps": 58920, "loss": 0.0039, "lr": 1.938163650671238e-06, "epoch": 1.0064494229463679, "percentage": 20.13, "elapsed_time": "0:19:02", "remaining_time": "1:15:34", "throughput": 9962.86, "total_tokens": 11384128}
{"current_steps": 11865, "total_steps": 58920, "loss": 0.0393, "lr": 1.9380610604315496e-06, "epoch": 1.0068737270875763, "percentage": 20.14, "elapsed_time": "0:19:03", "remaining_time": "1:15:33", "throughput": 9963.55, "total_tokens": 11388736}
{"current_steps": 11870, "total_steps": 58920, "loss": 0.0428, "lr": 1.9379583878803902e-06, "epoch": 1.0072980312287847, "percentage": 20.15, "elapsed_time": "0:19:03", "remaining_time": "1:15:32", "throughput": 9964.97, "total_tokens": 11394432}
{"current_steps": 11875, "total_steps": 58920, "loss": 0.0561, "lr": 1.9378556330267688e-06, "epoch": 1.0077223353699931, "percentage": 20.15, "elapsed_time": "0:19:03", "remaining_time": "1:15:31", "throughput": 9966.08, "total_tokens": 11399616}
{"current_steps": 11880, "total_steps": 58920, "loss": 0.0321, "lr": 1.937752795879701e-06, "epoch": 1.0081466395112015, "percentage": 20.16, "elapsed_time": "0:19:04", "remaining_time": "1:15:30", "throughput": 9966.79, "total_tokens": 11404224}
{"current_steps": 11885, "total_steps": 58920, "loss": 0.0894, "lr": 1.9376498764482117e-06, "epoch": 1.00857094365241, "percentage": 20.17, "elapsed_time": "0:19:04", "remaining_time": "1:15:29", "throughput": 9967.75, "total_tokens": 11409216}
{"current_steps": 11890, "total_steps": 58920, "loss": 0.0197, "lr": 1.937546874741331e-06, "epoch": 1.0089952477936184, "percentage": 20.18, "elapsed_time": "0:19:04", "remaining_time": "1:15:28", "throughput": 9968.18, "total_tokens": 11413376}
{"current_steps": 11895, "total_steps": 58920, "loss": 0.0533, "lr": 1.937443790768097e-06, "epoch": 1.0094195519348268, "percentage": 20.19, "elapsed_time": "0:19:05", "remaining_time": "1:15:28", "throughput": 9969.21, "total_tokens": 11418432}
{"current_steps": 11900, "total_steps": 58920, "loss": 0.0139, "lr": 1.937340624537555e-06, "epoch": 1.0098438560760352, "percentage": 20.2, "elapsed_time": "0:19:05", "remaining_time": "1:15:27", "throughput": 9969.97, "total_tokens": 11423104}
{"current_steps": 11905, "total_steps": 58920, "loss": 0.0377, "lr": 1.9372373760587577e-06, "epoch": 1.0102681602172436, "percentage": 20.21, "elapsed_time": "0:19:06", "remaining_time": "1:15:26", "throughput": 9970.85, "total_tokens": 11427904}
{"current_steps": 11910, "total_steps": 58920, "loss": 0.0546, "lr": 1.937134045340764e-06, "epoch": 1.010692464358452, "percentage": 20.21, "elapsed_time": "0:19:06", "remaining_time": "1:15:25", "throughput": 9971.6, "total_tokens": 11432576}
{"current_steps": 11915, "total_steps": 58920, "loss": 0.0169, "lr": 1.937030632392642e-06, "epoch": 1.0111167684996605, "percentage": 20.22, "elapsed_time": "0:19:06", "remaining_time": "1:15:24", "throughput": 9972.54, "total_tokens": 11437504}
{"current_steps": 11920, "total_steps": 58920, "loss": 0.0028, "lr": 1.9369271372234648e-06, "epoch": 1.011541072640869, "percentage": 20.23, "elapsed_time": "0:19:07", "remaining_time": "1:15:23", "throughput": 9973.49, "total_tokens": 11442432}
{"current_steps": 11925, "total_steps": 58920, "loss": 0.0223, "lr": 1.936823559842314e-06, "epoch": 1.0119653767820773, "percentage": 20.24, "elapsed_time": "0:19:07", "remaining_time": "1:15:22", "throughput": 9974.53, "total_tokens": 11447488}
{"current_steps": 11930, "total_steps": 58920, "loss": 0.0442, "lr": 1.9367199002582788e-06, "epoch": 1.0123896809232857, "percentage": 20.25, "elapsed_time": "0:19:08", "remaining_time": "1:15:21", "throughput": 9975.37, "total_tokens": 11452224}
{"current_steps": 11935, "total_steps": 58920, "loss": 0.0014, "lr": 1.9366161584804534e-06, "epoch": 1.0128139850644942, "percentage": 20.26, "elapsed_time": "0:19:08", "remaining_time": "1:15:21", "throughput": 9976.46, "total_tokens": 11457408}
{"current_steps": 11940, "total_steps": 58920, "loss": 0.0471, "lr": 1.936512334517942e-06, "epoch": 1.0132382892057026, "percentage": 20.26, "elapsed_time": "0:19:08", "remaining_time": "1:15:20", "throughput": 9977.39, "total_tokens": 11462336}
{"current_steps": 11945, "total_steps": 58920, "loss": 0.0443, "lr": 1.9364084283798548e-06, "epoch": 1.013662593346911, "percentage": 20.27, "elapsed_time": "0:19:09", "remaining_time": "1:15:19", "throughput": 9978.03, "total_tokens": 11466816}
{"current_steps": 11950, "total_steps": 58920, "loss": 0.0579, "lr": 1.936304440075309e-06, "epoch": 1.0140868974881194, "percentage": 20.28, "elapsed_time": "0:19:09", "remaining_time": "1:15:18", "throughput": 9979.02, "total_tokens": 11471808}
{"current_steps": 11955, "total_steps": 58920, "loss": 0.0014, "lr": 1.936200369613429e-06, "epoch": 1.0145112016293278, "percentage": 20.29, "elapsed_time": "0:19:09", "remaining_time": "1:15:17", "throughput": 9979.66, "total_tokens": 11476352}
{"current_steps": 11960, "total_steps": 58920, "loss": 0.0008, "lr": 1.9360962170033468e-06, "epoch": 1.0149355057705363, "percentage": 20.3, "elapsed_time": "0:19:10", "remaining_time": "1:15:16", "throughput": 9980.32, "total_tokens": 11480960}
{"current_steps": 11965, "total_steps": 58920, "loss": 0.0247, "lr": 1.935991982254201e-06, "epoch": 1.0153598099117447, "percentage": 20.31, "elapsed_time": "0:19:10", "remaining_time": "1:15:15", "throughput": 9980.83, "total_tokens": 11485312}
{"current_steps": 11970, "total_steps": 58920, "loss": 0.0529, "lr": 1.935887665375138e-06, "epoch": 1.015784114052953, "percentage": 20.32, "elapsed_time": "0:19:11", "remaining_time": "1:15:15", "throughput": 9984.19, "total_tokens": 11494144}
{"current_steps": 11975, "total_steps": 58920, "loss": 0.0095, "lr": 1.9357832663753116e-06, "epoch": 1.0162084181941615, "percentage": 20.32, "elapsed_time": "0:19:11", "remaining_time": "1:15:14", "throughput": 9985.35, "total_tokens": 11499456}
{"current_steps": 11980, "total_steps": 58920, "loss": 0.0479, "lr": 1.9356787852638825e-06, "epoch": 1.01663272233537, "percentage": 20.33, "elapsed_time": "0:19:12", "remaining_time": "1:15:13", "throughput": 9986.05, "total_tokens": 11504000}
{"current_steps": 11985, "total_steps": 58920, "loss": 0.0721, "lr": 1.935574222050018e-06, "epoch": 1.0170570264765784, "percentage": 20.34, "elapsed_time": "0:19:12", "remaining_time": "1:15:12", "throughput": 9986.93, "total_tokens": 11508864}
{"current_steps": 11990, "total_steps": 58920, "loss": 0.0159, "lr": 1.9354695767428933e-06, "epoch": 1.0174813306177868, "percentage": 20.35, "elapsed_time": "0:19:12", "remaining_time": "1:15:12", "throughput": 9987.49, "total_tokens": 11513216}
{"current_steps": 11995, "total_steps": 58920, "loss": 0.0299, "lr": 1.935364849351691e-06, "epoch": 1.0179056347589952, "percentage": 20.36, "elapsed_time": "0:19:13", "remaining_time": "1:15:11", "throughput": 9988.45, "total_tokens": 11518208}
{"current_steps": 12000, "total_steps": 58920, "loss": 0.0424, "lr": 1.9352600398856e-06, "epoch": 1.0183299389002036, "percentage": 20.37, "elapsed_time": "0:19:13", "remaining_time": "1:15:10", "throughput": 9990.09, "total_tokens": 11524288}
{"current_steps": 12005, "total_steps": 58920, "loss": 0.0523, "lr": 1.935155148353817e-06, "epoch": 1.018754243041412, "percentage": 20.38, "elapsed_time": "0:19:13", "remaining_time": "1:15:09", "throughput": 9990.67, "total_tokens": 11528704}
{"current_steps": 12010, "total_steps": 58920, "loss": 0.0209, "lr": 1.935050174765547e-06, "epoch": 1.0191785471826205, "percentage": 20.38, "elapsed_time": "0:19:14", "remaining_time": "1:15:08", "throughput": 9991.18, "total_tokens": 11533056}
{"current_steps": 12015, "total_steps": 58920, "loss": 0.0381, "lr": 1.9349451191299994e-06, "epoch": 1.0196028513238289, "percentage": 20.39, "elapsed_time": "0:19:14", "remaining_time": "1:15:07", "throughput": 9991.75, "total_tokens": 11537472}
{"current_steps": 12020, "total_steps": 58920, "loss": 0.0248, "lr": 1.9348399814563934e-06, "epoch": 1.0200271554650373, "percentage": 20.4, "elapsed_time": "0:19:15", "remaining_time": "1:15:06", "throughput": 9992.59, "total_tokens": 11542272}
{"current_steps": 12025, "total_steps": 58920, "loss": 0.0621, "lr": 1.9347347617539543e-06, "epoch": 1.0204514596062457, "percentage": 20.41, "elapsed_time": "0:19:15", "remaining_time": "1:15:06", "throughput": 9993.09, "total_tokens": 11546560}
{"current_steps": 12030, "total_steps": 58920, "loss": 0.0839, "lr": 1.9346294600319147e-06, "epoch": 1.0208757637474541, "percentage": 20.42, "elapsed_time": "0:19:15", "remaining_time": "1:15:05", "throughput": 9994.07, "total_tokens": 11551680}
{"current_steps": 12035, "total_steps": 58920, "loss": 0.0377, "lr": 1.934524076299514e-06, "epoch": 1.0213000678886626, "percentage": 20.43, "elapsed_time": "0:19:16", "remaining_time": "1:15:04", "throughput": 9994.84, "total_tokens": 11556416}
{"current_steps": 12040, "total_steps": 58920, "loss": 0.0103, "lr": 1.9344186105660006e-06, "epoch": 1.021724372029871, "percentage": 20.43, "elapsed_time": "0:19:16", "remaining_time": "1:15:03", "throughput": 9995.71, "total_tokens": 11561280}
{"current_steps": 12045, "total_steps": 58920, "loss": 0.0705, "lr": 1.9343130628406273e-06, "epoch": 1.0221486761710794, "percentage": 20.44, "elapsed_time": "0:19:17", "remaining_time": "1:15:02", "throughput": 9996.32, "total_tokens": 11565760}
{"current_steps": 12050, "total_steps": 58920, "loss": 0.0029, "lr": 1.934207433132656e-06, "epoch": 1.0225729803122878, "percentage": 20.45, "elapsed_time": "0:19:17", "remaining_time": "1:15:01", "throughput": 9996.95, "total_tokens": 11570304}
{"current_steps": 12055, "total_steps": 58920, "loss": 0.0729, "lr": 1.9341017214513555e-06, "epoch": 1.0229972844534962, "percentage": 20.46, "elapsed_time": "0:19:17", "remaining_time": "1:15:00", "throughput": 9997.63, "total_tokens": 11574912}
{"current_steps": 12060, "total_steps": 58920, "loss": 0.021, "lr": 1.9339959278060016e-06, "epoch": 1.0234215885947047, "percentage": 20.47, "elapsed_time": "0:19:18", "remaining_time": "1:15:00", "throughput": 9998.44, "total_tokens": 11579712}
{"current_steps": 12065, "total_steps": 58920, "loss": 0.0296, "lr": 1.933890052205877e-06, "epoch": 1.023845892735913, "percentage": 20.48, "elapsed_time": "0:19:18", "remaining_time": "1:14:59", "throughput": 9999.8, "total_tokens": 11585408}
{"current_steps": 12070, "total_steps": 58920, "loss": 0.0386, "lr": 1.933784094660272e-06, "epoch": 1.0242701968771215, "percentage": 20.49, "elapsed_time": "0:19:18", "remaining_time": "1:14:58", "throughput": 10000.85, "total_tokens": 11590592}
{"current_steps": 12075, "total_steps": 58920, "loss": 0.0034, "lr": 1.933678055178484e-06, "epoch": 1.02469450101833, "percentage": 20.49, "elapsed_time": "0:19:19", "remaining_time": "1:14:57", "throughput": 10001.84, "total_tokens": 11595648}
{"current_steps": 12080, "total_steps": 58920, "loss": 0.0347, "lr": 1.9335719337698184e-06, "epoch": 1.0251188051595383, "percentage": 20.5, "elapsed_time": "0:19:19", "remaining_time": "1:14:56", "throughput": 10002.69, "total_tokens": 11600576}
{"current_steps": 12085, "total_steps": 58920, "loss": 0.0953, "lr": 1.933465730443586e-06, "epoch": 1.0255431093007468, "percentage": 20.51, "elapsed_time": "0:19:20", "remaining_time": "1:14:56", "throughput": 10003.13, "total_tokens": 11604864}
{"current_steps": 12090, "total_steps": 58920, "loss": 0.024, "lr": 1.933359445209106e-06, "epoch": 1.0259674134419552, "percentage": 20.52, "elapsed_time": "0:19:20", "remaining_time": "1:14:55", "throughput": 10003.8, "total_tokens": 11609472}
{"current_steps": 12095, "total_steps": 58920, "loss": 0.0216, "lr": 1.9332530780757044e-06, "epoch": 1.0263917175831636, "percentage": 20.53, "elapsed_time": "0:19:20", "remaining_time": "1:14:54", "throughput": 10004.66, "total_tokens": 11614400}
{"current_steps": 12100, "total_steps": 58920, "loss": 0.0777, "lr": 1.933146629052715e-06, "epoch": 1.026816021724372, "percentage": 20.54, "elapsed_time": "0:19:21", "remaining_time": "1:14:53", "throughput": 10005.45, "total_tokens": 11619200}
{"current_steps": 12105, "total_steps": 58920, "loss": 0.0146, "lr": 1.9330400981494775e-06, "epoch": 1.0272403258655805, "percentage": 20.54, "elapsed_time": "0:19:21", "remaining_time": "1:14:52", "throughput": 10006.11, "total_tokens": 11623872}
{"current_steps": 12110, "total_steps": 58920, "loss": 0.0507, "lr": 1.93293348537534e-06, "epoch": 1.0276646300067889, "percentage": 20.55, "elapsed_time": "0:19:22", "remaining_time": "1:14:51", "throughput": 10006.94, "total_tokens": 11628736}
{"current_steps": 12115, "total_steps": 58920, "loss": 0.0458, "lr": 1.932826790739658e-06, "epoch": 1.0280889341479973, "percentage": 20.56, "elapsed_time": "0:19:22", "remaining_time": "1:14:50", "throughput": 10007.46, "total_tokens": 11633152}
{"current_steps": 12120, "total_steps": 58920, "loss": 0.0256, "lr": 1.9327200142517934e-06, "epoch": 1.0285132382892057, "percentage": 20.57, "elapsed_time": "0:19:22", "remaining_time": "1:14:50", "throughput": 10008.21, "total_tokens": 11637888}
{"current_steps": 12125, "total_steps": 58920, "loss": 0.0462, "lr": 1.9326131559211143e-06, "epoch": 1.0289375424304141, "percentage": 20.58, "elapsed_time": "0:19:23", "remaining_time": "1:14:49", "throughput": 10009.09, "total_tokens": 11642816}
{"current_steps": 12130, "total_steps": 58920, "loss": 0.0908, "lr": 1.9325062157569983e-06, "epoch": 1.0293618465716226, "percentage": 20.59, "elapsed_time": "0:19:23", "remaining_time": "1:14:48", "throughput": 10009.55, "total_tokens": 11647168}
{"current_steps": 12135, "total_steps": 58920, "loss": 0.0573, "lr": 1.9323991937688288e-06, "epoch": 1.029786150712831, "percentage": 20.6, "elapsed_time": "0:19:24", "remaining_time": "1:14:47", "throughput": 10010.78, "total_tokens": 11652672}
{"current_steps": 12140, "total_steps": 58920, "loss": 0.0359, "lr": 1.9322920899659963e-06, "epoch": 1.0302104548540394, "percentage": 20.6, "elapsed_time": "0:19:24", "remaining_time": "1:14:46", "throughput": 10012.04, "total_tokens": 11658176}
{"current_steps": 12145, "total_steps": 58920, "loss": 0.0279, "lr": 1.932184904357899e-06, "epoch": 1.0306347589952478, "percentage": 20.61, "elapsed_time": "0:19:24", "remaining_time": "1:14:46", "throughput": 10012.8, "total_tokens": 11662976}
{"current_steps": 12150, "total_steps": 58920, "loss": 0.054, "lr": 1.932077636953942e-06, "epoch": 1.0310590631364562, "percentage": 20.62, "elapsed_time": "0:19:25", "remaining_time": "1:14:45", "throughput": 10013.72, "total_tokens": 11668032}
{"current_steps": 12155, "total_steps": 58920, "loss": 0.1026, "lr": 1.9319702877635377e-06, "epoch": 1.0314833672776647, "percentage": 20.63, "elapsed_time": "0:19:25", "remaining_time": "1:14:44", "throughput": 10014.49, "total_tokens": 11672896}
{"current_steps": 12160, "total_steps": 58920, "loss": 0.0416, "lr": 1.931862856796105e-06, "epoch": 1.031907671418873, "percentage": 20.64, "elapsed_time": "0:19:26", "remaining_time": "1:14:43", "throughput": 10015.79, "total_tokens": 11678464}
{"current_steps": 12165, "total_steps": 58920, "loss": 0.023, "lr": 1.931755344061072e-06, "epoch": 1.0323319755600815, "percentage": 20.65, "elapsed_time": "0:19:26", "remaining_time": "1:14:42", "throughput": 10016.74, "total_tokens": 11683520}
{"current_steps": 12170, "total_steps": 58920, "loss": 0.0062, "lr": 1.931647749567871e-06, "epoch": 1.03275627970129, "percentage": 20.66, "elapsed_time": "0:19:26", "remaining_time": "1:14:42", "throughput": 10017.41, "total_tokens": 11688128}
{"current_steps": 12175, "total_steps": 58920, "loss": 0.0065, "lr": 1.931540073325944e-06, "epoch": 1.0331805838424983, "percentage": 20.66, "elapsed_time": "0:19:27", "remaining_time": "1:14:41", "throughput": 10017.89, "total_tokens": 11692480}
{"current_steps": 12180, "total_steps": 58920, "loss": 0.0025, "lr": 1.9314323153447385e-06, "epoch": 1.0336048879837068, "percentage": 20.67, "elapsed_time": "0:19:27", "remaining_time": "1:14:40", "throughput": 10018.77, "total_tokens": 11697472}
{"current_steps": 12185, "total_steps": 58920, "loss": 0.0428, "lr": 1.9313244756337102e-06, "epoch": 1.0340291921249152, "percentage": 20.68, "elapsed_time": "0:19:27", "remaining_time": "1:14:39", "throughput": 10019.34, "total_tokens": 11702144}
{"current_steps": 12190, "total_steps": 58920, "loss": 0.0047, "lr": 1.9312165542023222e-06, "epoch": 1.0344534962661236, "percentage": 20.69, "elapsed_time": "0:19:28", "remaining_time": "1:14:38", "throughput": 10020.41, "total_tokens": 11707392}
{"current_steps": 12195, "total_steps": 58920, "loss": 0.0138, "lr": 1.9311085510600434e-06, "epoch": 1.034877800407332, "percentage": 20.7, "elapsed_time": "0:19:28", "remaining_time": "1:14:38", "throughput": 10021.13, "total_tokens": 11712128}
{"current_steps": 12200, "total_steps": 58920, "loss": 0.013, "lr": 1.931000466216351e-06, "epoch": 1.0353021045485404, "percentage": 20.71, "elapsed_time": "0:19:29", "remaining_time": "1:14:37", "throughput": 10021.92, "total_tokens": 11716992}
{"current_steps": 12205, "total_steps": 58920, "loss": 0.1042, "lr": 1.930892299680729e-06, "epoch": 1.0357264086897489, "percentage": 20.71, "elapsed_time": "0:19:29", "remaining_time": "1:14:36", "throughput": 10022.71, "total_tokens": 11721856}
{"current_steps": 12210, "total_steps": 58920, "loss": 0.0365, "lr": 1.930784051462669e-06, "epoch": 1.0361507128309573, "percentage": 20.72, "elapsed_time": "0:19:29", "remaining_time": "1:14:35", "throughput": 10023.41, "total_tokens": 11726528}
{"current_steps": 12215, "total_steps": 58920, "loss": 0.0882, "lr": 1.930675721571669e-06, "epoch": 1.0365750169721657, "percentage": 20.73, "elapsed_time": "0:19:30", "remaining_time": "1:14:34", "throughput": 10024.11, "total_tokens": 11731200}
{"current_steps": 12220, "total_steps": 58920, "loss": 0.0686, "lr": 1.9305673100172346e-06, "epoch": 1.0369993211133741, "percentage": 20.74, "elapsed_time": "0:19:30", "remaining_time": "1:14:33", "throughput": 10025.04, "total_tokens": 11736192}
{"current_steps": 12225, "total_steps": 58920, "loss": 0.0147, "lr": 1.930458816808878e-06, "epoch": 1.0374236252545825, "percentage": 20.75, "elapsed_time": "0:19:31", "remaining_time": "1:14:33", "throughput": 10026.19, "total_tokens": 11741632}
{"current_steps": 12230, "total_steps": 58920, "loss": 0.0374, "lr": 1.93035024195612e-06, "epoch": 1.037847929395791, "percentage": 20.76, "elapsed_time": "0:19:31", "remaining_time": "1:14:32", "throughput": 10027.24, "total_tokens": 11746944}
{"current_steps": 12235, "total_steps": 58920, "loss": 0.0219, "lr": 1.9302415854684873e-06, "epoch": 1.0382722335369994, "percentage": 20.77, "elapsed_time": "0:19:31", "remaining_time": "1:14:31", "throughput": 10027.99, "total_tokens": 11751808}
{"current_steps": 12240, "total_steps": 58920, "loss": 0.039, "lr": 1.9301328473555143e-06, "epoch": 1.0386965376782078, "percentage": 20.77, "elapsed_time": "0:19:32", "remaining_time": "1:14:30", "throughput": 10028.5, "total_tokens": 11756288}
{"current_steps": 12245, "total_steps": 58920, "loss": 0.0016, "lr": 1.9300240276267423e-06, "epoch": 1.0391208418194162, "percentage": 20.78, "elapsed_time": "0:19:32", "remaining_time": "1:14:29", "throughput": 10029.4, "total_tokens": 11761344}
{"current_steps": 12250, "total_steps": 58920, "loss": 0.0414, "lr": 1.929915126291719e-06, "epoch": 1.0395451459606246, "percentage": 20.79, "elapsed_time": "0:19:33", "remaining_time": "1:14:29", "throughput": 10029.85, "total_tokens": 11765696}
{"current_steps": 12255, "total_steps": 58920, "loss": 0.0463, "lr": 1.9298061433600014e-06, "epoch": 1.039969450101833, "percentage": 20.8, "elapsed_time": "0:19:33", "remaining_time": "1:14:28", "throughput": 10030.66, "total_tokens": 11770560}
{"current_steps": 12260, "total_steps": 58920, "loss": 0.0544, "lr": 1.9296970788411517e-06, "epoch": 1.0403937542430415, "percentage": 20.81, "elapsed_time": "0:19:33", "remaining_time": "1:14:27", "throughput": 10031.23, "total_tokens": 11775104}
{"current_steps": 12265, "total_steps": 58920, "loss": 0.0655, "lr": 1.9295879327447397e-06, "epoch": 1.04081805838425, "percentage": 20.82, "elapsed_time": "0:19:34", "remaining_time": "1:14:26", "throughput": 10031.8, "total_tokens": 11779648}
{"current_steps": 12270, "total_steps": 58920, "loss": 0.0391, "lr": 1.929478705080343e-06, "epoch": 1.0412423625254583, "percentage": 20.82, "elapsed_time": "0:19:34", "remaining_time": "1:14:25", "throughput": 10032.39, "total_tokens": 11784192}
{"current_steps": 12275, "total_steps": 58920, "loss": 0.0008, "lr": 1.929369395857546e-06, "epoch": 1.0416666666666667, "percentage": 20.83, "elapsed_time": "0:19:35", "remaining_time": "1:14:25", "throughput": 10033.35, "total_tokens": 11789248}
{"current_steps": 12280, "total_steps": 58920, "loss": 0.0502, "lr": 1.92926000508594e-06, "epoch": 1.0420909708078752, "percentage": 20.84, "elapsed_time": "0:19:35", "remaining_time": "1:14:24", "throughput": 10034.24, "total_tokens": 11794304}
{"current_steps": 12285, "total_steps": 58920, "loss": 0.0008, "lr": 1.9291505327751235e-06, "epoch": 1.0425152749490836, "percentage": 20.85, "elapsed_time": "0:19:35", "remaining_time": "1:14:23", "throughput": 10035.32, "total_tokens": 11799552}
{"current_steps": 12290, "total_steps": 58920, "loss": 0.0842, "lr": 1.929040978934702e-06, "epoch": 1.042939579090292, "percentage": 20.86, "elapsed_time": "0:19:36", "remaining_time": "1:14:22", "throughput": 10036.01, "total_tokens": 11804224}
{"current_steps": 12295, "total_steps": 58920, "loss": 0.0427, "lr": 1.9289313435742893e-06, "epoch": 1.0433638832315004, "percentage": 20.87, "elapsed_time": "0:19:36", "remaining_time": "1:14:21", "throughput": 10036.48, "total_tokens": 11808576}
{"current_steps": 12300, "total_steps": 58920, "loss": 0.052, "lr": 1.9288216267035053e-06, "epoch": 1.0437881873727088, "percentage": 20.88, "elapsed_time": "0:19:36", "remaining_time": "1:14:20", "throughput": 10037.11, "total_tokens": 11813120}
{"current_steps": 12305, "total_steps": 58920, "loss": 0.0577, "lr": 1.928711828331977e-06, "epoch": 1.0442124915139173, "percentage": 20.88, "elapsed_time": "0:19:37", "remaining_time": "1:14:20", "throughput": 10037.85, "total_tokens": 11817856}
{"current_steps": 12310, "total_steps": 58920, "loss": 0.091, "lr": 1.9286019484693388e-06, "epoch": 1.0446367956551257, "percentage": 20.89, "elapsed_time": "0:19:37", "remaining_time": "1:14:19", "throughput": 10038.89, "total_tokens": 11823104}
{"current_steps": 12315, "total_steps": 58920, "loss": 0.043, "lr": 1.928491987125232e-06, "epoch": 1.045061099796334, "percentage": 20.9, "elapsed_time": "0:19:38", "remaining_time": "1:14:18", "throughput": 10039.66, "total_tokens": 11827968}
{"current_steps": 12320, "total_steps": 58920, "loss": 0.0294, "lr": 1.9283819443093057e-06, "epoch": 1.0454854039375425, "percentage": 20.91, "elapsed_time": "0:19:38", "remaining_time": "1:14:17", "throughput": 10040.27, "total_tokens": 11832512}
{"current_steps": 12325, "total_steps": 58920, "loss": 0.0444, "lr": 1.9282718200312162e-06, "epoch": 1.045909708078751, "percentage": 20.92, "elapsed_time": "0:19:38", "remaining_time": "1:14:16", "throughput": 10040.7, "total_tokens": 11836800}
{"current_steps": 12330, "total_steps": 58920, "loss": 0.0009, "lr": 1.9281616143006254e-06, "epoch": 1.0463340122199594, "percentage": 20.93, "elapsed_time": "0:19:39", "remaining_time": "1:14:15", "throughput": 10041.35, "total_tokens": 11841408}
{"current_steps": 12335, "total_steps": 58920, "loss": 0.0524, "lr": 1.9280513271272044e-06, "epoch": 1.0467583163611678, "percentage": 20.94, "elapsed_time": "0:19:39", "remaining_time": "1:14:15", "throughput": 10041.88, "total_tokens": 11845888}
{"current_steps": 12340, "total_steps": 58920, "loss": 0.0365, "lr": 1.9279409585206304e-06, "epoch": 1.0471826205023762, "percentage": 20.94, "elapsed_time": "0:19:40", "remaining_time": "1:14:14", "throughput": 10042.63, "total_tokens": 11850624}
{"current_steps": 12345, "total_steps": 58920, "loss": 0.0532, "lr": 1.927830508490587e-06, "epoch": 1.0476069246435846, "percentage": 20.95, "elapsed_time": "0:19:40", "remaining_time": "1:14:13", "throughput": 10042.86, "total_tokens": 11854592}
{"current_steps": 12350, "total_steps": 58920, "loss": 0.0577, "lr": 1.9277199770467665e-06, "epoch": 1.048031228784793, "percentage": 20.96, "elapsed_time": "0:19:40", "remaining_time": "1:14:12", "throughput": 10043.76, "total_tokens": 11859520}
{"current_steps": 12355, "total_steps": 58920, "loss": 0.0653, "lr": 1.927609364198868e-06, "epoch": 1.0484555329260012, "percentage": 20.97, "elapsed_time": "0:19:41", "remaining_time": "1:14:11", "throughput": 10044.4, "total_tokens": 11864128}
{"current_steps": 12360, "total_steps": 58920, "loss": 0.004, "lr": 1.9274986699565966e-06, "epoch": 1.0488798370672097, "percentage": 20.98, "elapsed_time": "0:19:41", "remaining_time": "1:14:10", "throughput": 10045.21, "total_tokens": 11868928}
{"current_steps": 12365, "total_steps": 58920, "loss": 0.0021, "lr": 1.927387894329666e-06, "epoch": 1.049304141208418, "percentage": 20.99, "elapsed_time": "0:19:41", "remaining_time": "1:14:10", "throughput": 10045.89, "total_tokens": 11873536}
{"current_steps": 12370, "total_steps": 58920, "loss": 0.024, "lr": 1.9272770373277956e-06, "epoch": 1.0497284453496265, "percentage": 20.99, "elapsed_time": "0:19:42", "remaining_time": "1:14:09", "throughput": 10046.85, "total_tokens": 11878592}
{"current_steps": 12375, "total_steps": 58920, "loss": 0.0281, "lr": 1.9271660989607132e-06, "epoch": 1.050152749490835, "percentage": 21.0, "elapsed_time": "0:19:42", "remaining_time": "1:14:08", "throughput": 10048.05, "total_tokens": 11884224}
{"current_steps": 12380, "total_steps": 58920, "loss": 0.0254, "lr": 1.927055079238153e-06, "epoch": 1.0505770536320433, "percentage": 21.01, "elapsed_time": "0:19:43", "remaining_time": "1:14:07", "throughput": 10048.84, "total_tokens": 11889024}
{"current_steps": 12385, "total_steps": 58920, "loss": 0.0195, "lr": 1.9269439781698566e-06, "epoch": 1.0510013577732518, "percentage": 21.02, "elapsed_time": "0:19:43", "remaining_time": "1:14:06", "throughput": 10049.87, "total_tokens": 11894208}
{"current_steps": 12390, "total_steps": 58920, "loss": 0.0005, "lr": 1.9268327957655733e-06, "epoch": 1.0514256619144602, "percentage": 21.03, "elapsed_time": "0:19:43", "remaining_time": "1:14:06", "throughput": 10050.77, "total_tokens": 11899136}
{"current_steps": 12395, "total_steps": 58920, "loss": 0.1016, "lr": 1.926721532035058e-06, "epoch": 1.0518499660556686, "percentage": 21.04, "elapsed_time": "0:19:44", "remaining_time": "1:14:05", "throughput": 10051.25, "total_tokens": 11903424}
{"current_steps": 12400, "total_steps": 58920, "loss": 0.0121, "lr": 1.9266101869880743e-06, "epoch": 1.052274270196877, "percentage": 21.05, "elapsed_time": "0:19:44", "remaining_time": "1:14:04", "throughput": 10052.13, "total_tokens": 11908288}
{"current_steps": 12405, "total_steps": 58920, "loss": 0.0118, "lr": 1.9264987606343924e-06, "epoch": 1.0526985743380854, "percentage": 21.05, "elapsed_time": "0:19:45", "remaining_time": "1:14:03", "throughput": 10052.83, "total_tokens": 11912960}
{"current_steps": 12410, "total_steps": 58920, "loss": 0.138, "lr": 1.9263872529837896e-06, "epoch": 1.0531228784792939, "percentage": 21.06, "elapsed_time": "0:19:45", "remaining_time": "1:14:02", "throughput": 10053.52, "total_tokens": 11917632}
{"current_steps": 12415, "total_steps": 58920, "loss": 0.0189, "lr": 1.9262756640460497e-06, "epoch": 1.0535471826205023, "percentage": 21.07, "elapsed_time": "0:19:45", "remaining_time": "1:14:01", "throughput": 10054.09, "total_tokens": 11922048}
{"current_steps": 12420, "total_steps": 58920, "loss": 0.0594, "lr": 1.9261639938309647e-06, "epoch": 1.0539714867617107, "percentage": 21.08, "elapsed_time": "0:19:46", "remaining_time": "1:14:01", "throughput": 10055.08, "total_tokens": 11927168}
{"current_steps": 12425, "total_steps": 58920, "loss": 0.024, "lr": 1.926052242348333e-06, "epoch": 1.0543957909029191, "percentage": 21.09, "elapsed_time": "0:19:46", "remaining_time": "1:14:00", "throughput": 10056.15, "total_tokens": 11932544}
{"current_steps": 12430, "total_steps": 58920, "loss": 0.0458, "lr": 1.9259404096079604e-06, "epoch": 1.0548200950441275, "percentage": 21.1, "elapsed_time": "0:19:46", "remaining_time": "1:13:59", "throughput": 10056.71, "total_tokens": 11937024}
{"current_steps": 12435, "total_steps": 58920, "loss": 0.0684, "lr": 1.9258284956196605e-06, "epoch": 1.055244399185336, "percentage": 21.1, "elapsed_time": "0:19:47", "remaining_time": "1:13:58", "throughput": 10057.64, "total_tokens": 11942016}
{"current_steps": 12440, "total_steps": 58920, "loss": 0.0362, "lr": 1.925716500393252e-06, "epoch": 1.0556687033265444, "percentage": 21.11, "elapsed_time": "0:19:47", "remaining_time": "1:13:57", "throughput": 10058.79, "total_tokens": 11947328}
{"current_steps": 12445, "total_steps": 58920, "loss": 0.0246, "lr": 1.9256044239385636e-06, "epoch": 1.0560930074677528, "percentage": 21.12, "elapsed_time": "0:19:48", "remaining_time": "1:13:56", "throughput": 10059.42, "total_tokens": 11951872}
{"current_steps": 12450, "total_steps": 58920, "loss": 0.0989, "lr": 1.9254922662654285e-06, "epoch": 1.0565173116089612, "percentage": 21.13, "elapsed_time": "0:19:48", "remaining_time": "1:13:56", "throughput": 10060.61, "total_tokens": 11957312}
{"current_steps": 12455, "total_steps": 58920, "loss": 0.0059, "lr": 1.9253800273836884e-06, "epoch": 1.0569416157501696, "percentage": 21.14, "elapsed_time": "0:19:48", "remaining_time": "1:13:55", "throughput": 10061.46, "total_tokens": 11962176}
{"current_steps": 12460, "total_steps": 58920, "loss": 0.0856, "lr": 1.9252677073031928e-06, "epoch": 1.057365919891378, "percentage": 21.15, "elapsed_time": "0:19:49", "remaining_time": "1:13:54", "throughput": 10061.96, "total_tokens": 11966592}
{"current_steps": 12465, "total_steps": 58920, "loss": 0.0444, "lr": 1.925155306033796e-06, "epoch": 1.0577902240325865, "percentage": 21.16, "elapsed_time": "0:19:49", "remaining_time": "1:13:53", "throughput": 10062.65, "total_tokens": 11971200}
{"current_steps": 12470, "total_steps": 58920, "loss": 0.098, "lr": 1.925042823585361e-06, "epoch": 1.058214528173795, "percentage": 21.16, "elapsed_time": "0:19:50", "remaining_time": "1:13:52", "throughput": 10063.86, "total_tokens": 11976640}
{"current_steps": 12475, "total_steps": 58920, "loss": 0.0425, "lr": 1.9249302599677586e-06, "epoch": 1.0586388323150033, "percentage": 21.17, "elapsed_time": "0:19:50", "remaining_time": "1:13:52", "throughput": 10064.7, "total_tokens": 11981504}
{"current_steps": 12480, "total_steps": 58920, "loss": 0.0261, "lr": 1.9248176151908647e-06, "epoch": 1.0590631364562118, "percentage": 21.18, "elapsed_time": "0:19:50", "remaining_time": "1:13:51", "throughput": 10065.42, "total_tokens": 11986240}
{"current_steps": 12485, "total_steps": 58920, "loss": 0.0026, "lr": 1.9247048892645646e-06, "epoch": 1.0594874405974202, "percentage": 21.19, "elapsed_time": "0:19:51", "remaining_time": "1:13:50", "throughput": 10066.6, "total_tokens": 11991680}
{"current_steps": 12490, "total_steps": 58920, "loss": 0.0767, "lr": 1.924592082198749e-06, "epoch": 1.0599117447386286, "percentage": 21.2, "elapsed_time": "0:19:51", "remaining_time": "1:13:49", "throughput": 10067.32, "total_tokens": 11996416}
{"current_steps": 12495, "total_steps": 58920, "loss": 0.0331, "lr": 1.9244791940033166e-06, "epoch": 1.060336048879837, "percentage": 21.21, "elapsed_time": "0:19:52", "remaining_time": "1:13:48", "throughput": 10068.32, "total_tokens": 12001536}
{"current_steps": 12500, "total_steps": 58920, "loss": 0.0422, "lr": 1.924366224688173e-06, "epoch": 1.0607603530210454, "percentage": 21.22, "elapsed_time": "0:19:52", "remaining_time": "1:13:48", "throughput": 10069.25, "total_tokens": 12006528}
{"current_steps": 12505, "total_steps": 58920, "loss": 0.0019, "lr": 1.9242531742632296e-06, "epoch": 1.0611846571622539, "percentage": 21.22, "elapsed_time": "0:19:52", "remaining_time": "1:13:47", "throughput": 10070.08, "total_tokens": 12011392}
{"current_steps": 12510, "total_steps": 58920, "loss": 0.0008, "lr": 1.924140042738408e-06, "epoch": 1.0616089613034623, "percentage": 21.23, "elapsed_time": "0:19:53", "remaining_time": "1:13:46", "throughput": 10070.91, "total_tokens": 12016192}
{"current_steps": 12515, "total_steps": 58920, "loss": 0.0496, "lr": 1.924026830123634e-06, "epoch": 1.0620332654446707, "percentage": 21.24, "elapsed_time": "0:19:53", "remaining_time": "1:13:45", "throughput": 10071.67, "total_tokens": 12020992}
{"current_steps": 12520, "total_steps": 58920, "loss": 0.0363, "lr": 1.923913536428842e-06, "epoch": 1.0624575695858791, "percentage": 21.25, "elapsed_time": "0:19:53", "remaining_time": "1:13:44", "throughput": 10072.04, "total_tokens": 12025152}
{"current_steps": 12525, "total_steps": 58920, "loss": 0.0228, "lr": 1.9238001616639728e-06, "epoch": 1.0628818737270875, "percentage": 21.26, "elapsed_time": "0:19:54", "remaining_time": "1:13:43", "throughput": 10072.58, "total_tokens": 12029760}
{"current_steps": 12530, "total_steps": 58920, "loss": 0.0012, "lr": 1.9236867058389745e-06, "epoch": 1.063306177868296, "percentage": 21.27, "elapsed_time": "0:19:54", "remaining_time": "1:13:43", "throughput": 10073.45, "total_tokens": 12034688}
{"current_steps": 12535, "total_steps": 58920, "loss": 0.025, "lr": 1.923573168963803e-06, "epoch": 1.0637304820095044, "percentage": 21.27, "elapsed_time": "0:19:55", "remaining_time": "1:13:42", "throughput": 10074.34, "total_tokens": 12039616}
{"current_steps": 12540, "total_steps": 58920, "loss": 0.0769, "lr": 1.9234595510484204e-06, "epoch": 1.0641547861507128, "percentage": 21.28, "elapsed_time": "0:19:55", "remaining_time": "1:13:41", "throughput": 10075.41, "total_tokens": 12044864}
{"current_steps": 12545, "total_steps": 58920, "loss": 0.0939, "lr": 1.9233458521027965e-06, "epoch": 1.0645790902919212, "percentage": 21.29, "elapsed_time": "0:19:55", "remaining_time": "1:13:40", "throughput": 10076.53, "total_tokens": 12050176}
{"current_steps": 12550, "total_steps": 58920, "loss": 0.0605, "lr": 1.9232320721369076e-06, "epoch": 1.0650033944331296, "percentage": 21.3, "elapsed_time": "0:19:56", "remaining_time": "1:13:39", "throughput": 10077.44, "total_tokens": 12055168}
{"current_steps": 12555, "total_steps": 58920, "loss": 0.0335, "lr": 1.923118211160738e-06, "epoch": 1.065427698574338, "percentage": 21.31, "elapsed_time": "0:19:56", "remaining_time": "1:13:39", "throughput": 10078.39, "total_tokens": 12060224}
{"current_steps": 12560, "total_steps": 58920, "loss": 0.0045, "lr": 1.923004269184278e-06, "epoch": 1.0658520027155465, "percentage": 21.32, "elapsed_time": "0:19:57", "remaining_time": "1:13:38", "throughput": 10079.54, "total_tokens": 12065600}
{"current_steps": 12565, "total_steps": 58920, "loss": 0.0319, "lr": 1.922890246217526e-06, "epoch": 1.066276306856755, "percentage": 21.33, "elapsed_time": "0:19:57", "remaining_time": "1:13:37", "throughput": 10080.09, "total_tokens": 12070016}
{"current_steps": 12570, "total_steps": 58920, "loss": 0.058, "lr": 1.922776142270487e-06, "epoch": 1.0667006109979633, "percentage": 21.33, "elapsed_time": "0:19:57", "remaining_time": "1:13:36", "throughput": 10081.05, "total_tokens": 12075008}
{"current_steps": 12575, "total_steps": 58920, "loss": 0.0309, "lr": 1.9226619573531727e-06, "epoch": 1.0671249151391717, "percentage": 21.34, "elapsed_time": "0:19:58", "remaining_time": "1:13:35", "throughput": 10082.05, "total_tokens": 12080128}
{"current_steps": 12580, "total_steps": 58920, "loss": 0.0292, "lr": 1.9225476914756036e-06, "epoch": 1.0675492192803802, "percentage": 21.35, "elapsed_time": "0:19:58", "remaining_time": "1:13:35", "throughput": 10082.92, "total_tokens": 12085056}
{"current_steps": 12585, "total_steps": 58920, "loss": 0.0026, "lr": 1.922433344647805e-06, "epoch": 1.0679735234215886, "percentage": 21.36, "elapsed_time": "0:19:58", "remaining_time": "1:13:34", "throughput": 10083.94, "total_tokens": 12090240}
{"current_steps": 12590, "total_steps": 58920, "loss": 0.0955, "lr": 1.9223189168798112e-06, "epoch": 1.068397827562797, "percentage": 21.37, "elapsed_time": "0:19:59", "remaining_time": "1:13:33", "throughput": 10084.71, "total_tokens": 12095040}
{"current_steps": 12595, "total_steps": 58920, "loss": 0.0011, "lr": 1.9222044081816618e-06, "epoch": 1.0688221317040054, "percentage": 21.38, "elapsed_time": "0:19:59", "remaining_time": "1:13:32", "throughput": 10085.56, "total_tokens": 12099904}
{"current_steps": 12600, "total_steps": 58920, "loss": 0.006, "lr": 1.922089818563406e-06, "epoch": 1.0692464358452138, "percentage": 21.38, "elapsed_time": "0:20:00", "remaining_time": "1:13:31", "throughput": 10086.29, "total_tokens": 12104576}
{"current_steps": 12605, "total_steps": 58920, "loss": 0.0793, "lr": 1.9219751480350973e-06, "epoch": 1.0696707399864223, "percentage": 21.39, "elapsed_time": "0:20:00", "remaining_time": "1:13:30", "throughput": 10086.82, "total_tokens": 12108992}
{"current_steps": 12610, "total_steps": 58920, "loss": 0.0535, "lr": 1.921860396606798e-06, "epoch": 1.0700950441276307, "percentage": 21.4, "elapsed_time": "0:20:00", "remaining_time": "1:13:30", "throughput": 10087.49, "total_tokens": 12113600}
{"current_steps": 12615, "total_steps": 58920, "loss": 0.0339, "lr": 1.9217455642885776e-06, "epoch": 1.070519348268839, "percentage": 21.41, "elapsed_time": "0:20:01", "remaining_time": "1:13:29", "throughput": 10088.08, "total_tokens": 12118080}
{"current_steps": 12620, "total_steps": 58920, "loss": 0.0876, "lr": 1.921630651090512e-06, "epoch": 1.0709436524100475, "percentage": 21.42, "elapsed_time": "0:20:01", "remaining_time": "1:13:28", "throughput": 10089.23, "total_tokens": 12123392}
{"current_steps": 12625, "total_steps": 58920, "loss": 0.0036, "lr": 1.921515657022684e-06, "epoch": 1.071367956551256, "percentage": 21.43, "elapsed_time": "0:20:01", "remaining_time": "1:13:27", "throughput": 10089.71, "total_tokens": 12127744}
{"current_steps": 12630, "total_steps": 58920, "loss": 0.0117, "lr": 1.9214005820951846e-06, "epoch": 1.0717922606924644, "percentage": 21.44, "elapsed_time": "0:20:02", "remaining_time": "1:13:26", "throughput": 10090.28, "total_tokens": 12132224}
{"current_steps": 12635, "total_steps": 58920, "loss": 0.0006, "lr": 1.92128542631811e-06, "epoch": 1.0722165648336728, "percentage": 21.44, "elapsed_time": "0:20:02", "remaining_time": "1:13:25", "throughput": 10090.75, "total_tokens": 12136512}
{"current_steps": 12640, "total_steps": 58920, "loss": 0.0598, "lr": 1.9211701897015666e-06, "epoch": 1.0726408689748812, "percentage": 21.45, "elapsed_time": "0:20:03", "remaining_time": "1:13:25", "throughput": 10091.45, "total_tokens": 12141184}
{"current_steps": 12645, "total_steps": 58920, "loss": 0.0297, "lr": 1.9210548722556645e-06, "epoch": 1.0730651731160896, "percentage": 21.46, "elapsed_time": "0:20:03", "remaining_time": "1:13:24", "throughput": 10092.2, "total_tokens": 12145984}
{"current_steps": 12650, "total_steps": 58920, "loss": 0.0415, "lr": 1.9209394739905225e-06, "epoch": 1.073489477257298, "percentage": 21.47, "elapsed_time": "0:20:03", "remaining_time": "1:13:23", "throughput": 10093.06, "total_tokens": 12150912}
{"current_steps": 12655, "total_steps": 58920, "loss": 0.094, "lr": 1.9208239949162668e-06, "epoch": 1.0739137813985065, "percentage": 21.48, "elapsed_time": "0:20:04", "remaining_time": "1:13:22", "throughput": 10093.96, "total_tokens": 12155968}
{"current_steps": 12660, "total_steps": 58920, "loss": 0.0762, "lr": 1.9207084350430304e-06, "epoch": 1.0743380855397149, "percentage": 21.49, "elapsed_time": "0:20:04", "remaining_time": "1:13:21", "throughput": 10094.7, "total_tokens": 12160768}
{"current_steps": 12665, "total_steps": 58920, "loss": 0.0029, "lr": 1.920592794380953e-06, "epoch": 1.0747623896809233, "percentage": 21.5, "elapsed_time": "0:20:05", "remaining_time": "1:13:21", "throughput": 10095.44, "total_tokens": 12165504}
{"current_steps": 12670, "total_steps": 58920, "loss": 0.051, "lr": 1.9204770729401815e-06, "epoch": 1.0751866938221317, "percentage": 21.5, "elapsed_time": "0:20:05", "remaining_time": "1:13:20", "throughput": 10095.99, "total_tokens": 12169984}
{"current_steps": 12675, "total_steps": 58920, "loss": 0.0746, "lr": 1.92036127073087e-06, "epoch": 1.0756109979633401, "percentage": 21.51, "elapsed_time": "0:20:05", "remaining_time": "1:13:19", "throughput": 10097.42, "total_tokens": 12175808}
{"current_steps": 12680, "total_steps": 58920, "loss": 0.001, "lr": 1.9202453877631808e-06, "epoch": 1.0760353021045486, "percentage": 21.52, "elapsed_time": "0:20:06", "remaining_time": "1:13:18", "throughput": 10098.03, "total_tokens": 12180352}
{"current_steps": 12685, "total_steps": 58920, "loss": 0.0388, "lr": 1.9201294240472806e-06, "epoch": 1.076459606245757, "percentage": 21.53, "elapsed_time": "0:20:06", "remaining_time": "1:13:17", "throughput": 10098.72, "total_tokens": 12185024}
{"current_steps": 12690, "total_steps": 58920, "loss": 0.0297, "lr": 1.9200133795933455e-06, "epoch": 1.0768839103869654, "percentage": 21.54, "elapsed_time": "0:20:06", "remaining_time": "1:13:17", "throughput": 10099.32, "total_tokens": 12189568}
{"current_steps": 12695, "total_steps": 58920, "loss": 0.0343, "lr": 1.9198972544115585e-06, "epoch": 1.0773082145281738, "percentage": 21.55, "elapsed_time": "0:20:07", "remaining_time": "1:13:16", "throughput": 10100.82, "total_tokens": 12195584}
{"current_steps": 12700, "total_steps": 58920, "loss": 0.0759, "lr": 1.9197810485121086e-06, "epoch": 1.0777325186693822, "percentage": 21.55, "elapsed_time": "0:20:07", "remaining_time": "1:13:15", "throughput": 10101.75, "total_tokens": 12200640}
{"current_steps": 12705, "total_steps": 58920, "loss": 0.0077, "lr": 1.9196647619051923e-06, "epoch": 1.0781568228105907, "percentage": 21.56, "elapsed_time": "0:20:08", "remaining_time": "1:13:14", "throughput": 10102.31, "total_tokens": 12205120}
{"current_steps": 12710, "total_steps": 58920, "loss": 0.0413, "lr": 1.919548394601014e-06, "epoch": 1.078581126951799, "percentage": 21.57, "elapsed_time": "0:20:08", "remaining_time": "1:13:13", "throughput": 10102.85, "total_tokens": 12209536}
{"current_steps": 12715, "total_steps": 58920, "loss": 0.0402, "lr": 1.9194319466097835e-06, "epoch": 1.0790054310930075, "percentage": 21.58, "elapsed_time": "0:20:08", "remaining_time": "1:13:13", "throughput": 10103.45, "total_tokens": 12214080}
{"current_steps": 12720, "total_steps": 58920, "loss": 0.0381, "lr": 1.9193154179417193e-06, "epoch": 1.079429735234216, "percentage": 21.59, "elapsed_time": "0:20:09", "remaining_time": "1:13:12", "throughput": 10104.3, "total_tokens": 12218944}
{"current_steps": 12725, "total_steps": 58920, "loss": 0.0813, "lr": 1.919198808607047e-06, "epoch": 1.0798540393754243, "percentage": 21.6, "elapsed_time": "0:20:09", "remaining_time": "1:13:11", "throughput": 10105.06, "total_tokens": 12223744}
{"current_steps": 12730, "total_steps": 58920, "loss": 0.03, "lr": 1.9190821186159976e-06, "epoch": 1.0802783435166328, "percentage": 21.61, "elapsed_time": "0:20:10", "remaining_time": "1:13:10", "throughput": 10105.76, "total_tokens": 12228416}
{"current_steps": 12735, "total_steps": 58920, "loss": 0.0365, "lr": 1.9189653479788105e-06, "epoch": 1.0807026476578412, "percentage": 21.61, "elapsed_time": "0:20:10", "remaining_time": "1:13:09", "throughput": 10106.23, "total_tokens": 12232768}
{"current_steps": 12740, "total_steps": 58920, "loss": 0.0197, "lr": 1.9188484967057325e-06, "epoch": 1.0811269517990496, "percentage": 21.62, "elapsed_time": "0:20:10", "remaining_time": "1:13:08", "throughput": 10106.97, "total_tokens": 12237504}
{"current_steps": 12745, "total_steps": 58920, "loss": 0.0612, "lr": 1.918731564807016e-06, "epoch": 1.081551255940258, "percentage": 21.63, "elapsed_time": "0:20:11", "remaining_time": "1:13:08", "throughput": 10107.85, "total_tokens": 12242432}
{"current_steps": 12750, "total_steps": 58920, "loss": 0.0725, "lr": 1.9186145522929218e-06, "epoch": 1.0819755600814664, "percentage": 21.64, "elapsed_time": "0:20:11", "remaining_time": "1:13:07", "throughput": 10108.55, "total_tokens": 12247104}
{"current_steps": 12755, "total_steps": 58920, "loss": 0.0588, "lr": 1.9184974591737173e-06, "epoch": 1.0823998642226749, "percentage": 21.65, "elapsed_time": "0:20:11", "remaining_time": "1:13:06", "throughput": 10109.53, "total_tokens": 12252224}
{"current_steps": 12760, "total_steps": 58920, "loss": 0.0184, "lr": 1.9183802854596772e-06, "epoch": 1.0828241683638833, "percentage": 21.66, "elapsed_time": "0:20:12", "remaining_time": "1:13:05", "throughput": 10110.59, "total_tokens": 12257472}
{"current_steps": 12765, "total_steps": 58920, "loss": 0.0323, "lr": 1.9182630311610825e-06, "epoch": 1.0832484725050917, "percentage": 21.66, "elapsed_time": "0:20:12", "remaining_time": "1:13:04", "throughput": 10111.35, "total_tokens": 12262208}
{"current_steps": 12770, "total_steps": 58920, "loss": 0.0553, "lr": 1.9181456962882225e-06, "epoch": 1.0836727766463001, "percentage": 21.67, "elapsed_time": "0:20:13", "remaining_time": "1:13:04", "throughput": 10112.03, "total_tokens": 12266880}
{"current_steps": 12775, "total_steps": 58920, "loss": 0.0775, "lr": 1.9180282808513924e-06, "epoch": 1.0840970807875085, "percentage": 21.68, "elapsed_time": "0:20:13", "remaining_time": "1:13:03", "throughput": 10112.8, "total_tokens": 12271680}
{"current_steps": 12780, "total_steps": 58920, "loss": 0.0689, "lr": 1.917910784860895e-06, "epoch": 1.084521384928717, "percentage": 21.69, "elapsed_time": "0:20:13", "remaining_time": "1:13:02", "throughput": 10113.41, "total_tokens": 12276224}
{"current_steps": 12785, "total_steps": 58920, "loss": 0.0837, "lr": 1.9177932083270407e-06, "epoch": 1.0849456890699254, "percentage": 21.7, "elapsed_time": "0:20:14", "remaining_time": "1:13:01", "throughput": 10114.09, "total_tokens": 12280896}
{"current_steps": 12790, "total_steps": 58920, "loss": 0.076, "lr": 1.917675551260146e-06, "epoch": 1.0853699932111338, "percentage": 21.71, "elapsed_time": "0:20:14", "remaining_time": "1:13:00", "throughput": 10114.76, "total_tokens": 12285568}
{"current_steps": 12795, "total_steps": 58920, "loss": 0.0193, "lr": 1.917557813670535e-06, "epoch": 1.0857942973523422, "percentage": 21.72, "elapsed_time": "0:20:14", "remaining_time": "1:12:59", "throughput": 10115.22, "total_tokens": 12289856}
{"current_steps": 12800, "total_steps": 58920, "loss": 0.0179, "lr": 1.9174399955685382e-06, "epoch": 1.0862186014935507, "percentage": 21.72, "elapsed_time": "0:20:15", "remaining_time": "1:12:59", "throughput": 10116.1, "total_tokens": 12294784}
{"current_steps": 12805, "total_steps": 58920, "loss": 0.0192, "lr": 1.9173220969644943e-06, "epoch": 1.086642905634759, "percentage": 21.73, "elapsed_time": "0:20:15", "remaining_time": "1:12:58", "throughput": 10117.06, "total_tokens": 12299904}
{"current_steps": 12810, "total_steps": 58920, "loss": 0.0259, "lr": 1.9172041178687492e-06, "epoch": 1.0870672097759675, "percentage": 21.74, "elapsed_time": "0:20:16", "remaining_time": "1:12:57", "throughput": 10117.73, "total_tokens": 12304512}
{"current_steps": 12815, "total_steps": 58920, "loss": 0.0004, "lr": 1.9170860582916536e-06, "epoch": 1.087491513917176, "percentage": 21.75, "elapsed_time": "0:20:16", "remaining_time": "1:12:56", "throughput": 10118.52, "total_tokens": 12309376}
{"current_steps": 12820, "total_steps": 58920, "loss": 0.0713, "lr": 1.9169679182435676e-06, "epoch": 1.0879158180583843, "percentage": 21.76, "elapsed_time": "0:20:16", "remaining_time": "1:12:55", "throughput": 10119.32, "total_tokens": 12314240}
{"current_steps": 12825, "total_steps": 58920, "loss": 0.0201, "lr": 1.9168496977348576e-06, "epoch": 1.0883401221995928, "percentage": 21.77, "elapsed_time": "0:20:17", "remaining_time": "1:12:55", "throughput": 10120.29, "total_tokens": 12319360}
{"current_steps": 12830, "total_steps": 58920, "loss": 0.0417, "lr": 1.9167313967758963e-06, "epoch": 1.0887644263408012, "percentage": 21.78, "elapsed_time": "0:20:17", "remaining_time": "1:12:54", "throughput": 10120.79, "total_tokens": 12323776}
{"current_steps": 12835, "total_steps": 58920, "loss": 0.0297, "lr": 1.9166130153770655e-06, "epoch": 1.0891887304820096, "percentage": 21.78, "elapsed_time": "0:20:18", "remaining_time": "1:12:53", "throughput": 10121.84, "total_tokens": 12329024}
{"current_steps": 12840, "total_steps": 58920, "loss": 0.0004, "lr": 1.916494553548752e-06, "epoch": 1.089613034623218, "percentage": 21.79, "elapsed_time": "0:20:18", "remaining_time": "1:12:52", "throughput": 10122.22, "total_tokens": 12333248}
{"current_steps": 12845, "total_steps": 58920, "loss": 0.0022, "lr": 1.91637601130135e-06, "epoch": 1.0900373387644264, "percentage": 21.8, "elapsed_time": "0:20:18", "remaining_time": "1:12:51", "throughput": 10122.97, "total_tokens": 12338048}
{"current_steps": 12850, "total_steps": 58920, "loss": 0.0323, "lr": 1.916257388645262e-06, "epoch": 1.0904616429056349, "percentage": 21.81, "elapsed_time": "0:20:19", "remaining_time": "1:12:51", "throughput": 10123.8, "total_tokens": 12342976}
{"current_steps": 12855, "total_steps": 58920, "loss": 0.0827, "lr": 1.916138685590896e-06, "epoch": 1.0908859470468433, "percentage": 21.82, "elapsed_time": "0:20:19", "remaining_time": "1:12:50", "throughput": 10124.18, "total_tokens": 12347200}
{"current_steps": 12860, "total_steps": 58920, "loss": 0.0198, "lr": 1.916019902148668e-06, "epoch": 1.0913102511880517, "percentage": 21.83, "elapsed_time": "0:20:19", "remaining_time": "1:12:49", "throughput": 10124.62, "total_tokens": 12351552}
{"current_steps": 12865, "total_steps": 58920, "loss": 0.0481, "lr": 1.915901038329001e-06, "epoch": 1.0917345553292601, "percentage": 21.83, "elapsed_time": "0:20:20", "remaining_time": "1:12:48", "throughput": 10125.25, "total_tokens": 12356160}
{"current_steps": 12870, "total_steps": 58920, "loss": 0.0361, "lr": 1.915782094142325e-06, "epoch": 1.0921588594704685, "percentage": 21.84, "elapsed_time": "0:20:20", "remaining_time": "1:12:47", "throughput": 10125.99, "total_tokens": 12360960}
{"current_steps": 12875, "total_steps": 58920, "loss": 0.0007, "lr": 1.9156630695990762e-06, "epoch": 1.092583163611677, "percentage": 21.85, "elapsed_time": "0:20:21", "remaining_time": "1:12:47", "throughput": 10126.61, "total_tokens": 12365568}
{"current_steps": 12880, "total_steps": 58920, "loss": 0.1075, "lr": 1.9155439647096988e-06, "epoch": 1.0930074677528854, "percentage": 21.86, "elapsed_time": "0:20:21", "remaining_time": "1:12:46", "throughput": 10127.37, "total_tokens": 12370368}
{"current_steps": 12885, "total_steps": 58920, "loss": 0.0672, "lr": 1.9154247794846444e-06, "epoch": 1.0934317718940938, "percentage": 21.87, "elapsed_time": "0:20:21", "remaining_time": "1:12:45", "throughput": 10127.8, "total_tokens": 12374848}
{"current_steps": 12890, "total_steps": 58920, "loss": 0.0329, "lr": 1.915305513934371e-06, "epoch": 1.0938560760353022, "percentage": 21.88, "elapsed_time": "0:20:22", "remaining_time": "1:12:44", "throughput": 10128.43, "total_tokens": 12379456}
{"current_steps": 12895, "total_steps": 58920, "loss": 0.0397, "lr": 1.915186168069343e-06, "epoch": 1.0942803801765106, "percentage": 21.89, "elapsed_time": "0:20:22", "remaining_time": "1:12:44", "throughput": 10130.43, "total_tokens": 12386304}
{"current_steps": 12900, "total_steps": 58920, "loss": 0.0674, "lr": 1.915066741900033e-06, "epoch": 1.094704684317719, "percentage": 21.89, "elapsed_time": "0:20:23", "remaining_time": "1:12:43", "throughput": 10131.01, "total_tokens": 12390848}
{"current_steps": 12905, "total_steps": 58920, "loss": 0.038, "lr": 1.9149472354369208e-06, "epoch": 1.0951289884589275, "percentage": 21.9, "elapsed_time": "0:20:23", "remaining_time": "1:12:42", "throughput": 10131.66, "total_tokens": 12395456}
{"current_steps": 12910, "total_steps": 58920, "loss": 0.0539, "lr": 1.9148276486904917e-06, "epoch": 1.0955532926001357, "percentage": 21.91, "elapsed_time": "0:20:23", "remaining_time": "1:12:41", "throughput": 10132.44, "total_tokens": 12400320}
{"current_steps": 12915, "total_steps": 58920, "loss": 0.0639, "lr": 1.91470798167124e-06, "epoch": 1.095977596741344, "percentage": 21.92, "elapsed_time": "0:20:24", "remaining_time": "1:12:40", "throughput": 10132.98, "total_tokens": 12404800}
{"current_steps": 12920, "total_steps": 58920, "loss": 0.0024, "lr": 1.9145882343896645e-06, "epoch": 1.0964019008825525, "percentage": 21.93, "elapsed_time": "0:20:24", "remaining_time": "1:12:40", "throughput": 10131.83, "total_tokens": 12409984}
{"current_steps": 12925, "total_steps": 58920, "loss": 0.0572, "lr": 1.914468406856274e-06, "epoch": 1.096826205023761, "percentage": 21.94, "elapsed_time": "0:20:25", "remaining_time": "1:12:40", "throughput": 10132.28, "total_tokens": 12414336}
{"current_steps": 12930, "total_steps": 58920, "loss": 0.0871, "lr": 1.9143484990815823e-06, "epoch": 1.0972505091649694, "percentage": 21.95, "elapsed_time": "0:20:25", "remaining_time": "1:12:39", "throughput": 10132.57, "total_tokens": 12418432}
{"current_steps": 12935, "total_steps": 58920, "loss": 0.0015, "lr": 1.914228511076111e-06, "epoch": 1.0976748133061778, "percentage": 21.95, "elapsed_time": "0:20:25", "remaining_time": "1:12:38", "throughput": 10133.23, "total_tokens": 12423104}
{"current_steps": 12940, "total_steps": 58920, "loss": 0.0101, "lr": 1.9141084428503893e-06, "epoch": 1.0980991174473862, "percentage": 21.96, "elapsed_time": "0:20:26", "remaining_time": "1:12:37", "throughput": 10133.79, "total_tokens": 12427584}
{"current_steps": 12945, "total_steps": 58920, "loss": 0.0286, "lr": 1.9139882944149516e-06, "epoch": 1.0985234215885946, "percentage": 21.97, "elapsed_time": "0:20:26", "remaining_time": "1:12:36", "throughput": 10134.97, "total_tokens": 12433024}
{"current_steps": 12950, "total_steps": 58920, "loss": 0.0176, "lr": 1.913868065780341e-06, "epoch": 1.098947725729803, "percentage": 21.98, "elapsed_time": "0:20:27", "remaining_time": "1:12:36", "throughput": 10135.63, "total_tokens": 12437696}
{"current_steps": 12955, "total_steps": 58920, "loss": 0.033, "lr": 1.913747756957107e-06, "epoch": 1.0993720298710115, "percentage": 21.99, "elapsed_time": "0:20:27", "remaining_time": "1:12:35", "throughput": 10136.46, "total_tokens": 12442624}
{"current_steps": 12960, "total_steps": 58920, "loss": 0.0182, "lr": 1.9136273679558064e-06, "epoch": 1.0997963340122199, "percentage": 22.0, "elapsed_time": "0:20:27", "remaining_time": "1:12:34", "throughput": 10137.04, "total_tokens": 12447168}
{"current_steps": 12965, "total_steps": 58920, "loss": 0.0243, "lr": 1.9135068987870035e-06, "epoch": 1.1002206381534283, "percentage": 22.0, "elapsed_time": "0:20:28", "remaining_time": "1:12:33", "throughput": 10137.91, "total_tokens": 12452160}
{"current_steps": 12970, "total_steps": 58920, "loss": 0.0348, "lr": 1.913386349461268e-06, "epoch": 1.1006449422946367, "percentage": 22.01, "elapsed_time": "0:20:28", "remaining_time": "1:12:32", "throughput": 10138.57, "total_tokens": 12456832}
{"current_steps": 12975, "total_steps": 58920, "loss": 0.1219, "lr": 1.913265719989178e-06, "epoch": 1.1010692464358451, "percentage": 22.02, "elapsed_time": "0:20:29", "remaining_time": "1:12:32", "throughput": 10139.14, "total_tokens": 12461376}
{"current_steps": 12980, "total_steps": 58920, "loss": 0.0252, "lr": 1.9131450103813185e-06, "epoch": 1.1014935505770536, "percentage": 22.03, "elapsed_time": "0:20:29", "remaining_time": "1:12:31", "throughput": 10140.21, "total_tokens": 12466688}
{"current_steps": 12985, "total_steps": 58920, "loss": 0.0657, "lr": 1.9130242206482812e-06, "epoch": 1.101917854718262, "percentage": 22.04, "elapsed_time": "0:20:29", "remaining_time": "1:12:30", "throughput": 10140.69, "total_tokens": 12471040}
{"current_steps": 12990, "total_steps": 58920, "loss": 0.0346, "lr": 1.912903350800665e-06, "epoch": 1.1023421588594704, "percentage": 22.05, "elapsed_time": "0:20:30", "remaining_time": "1:12:29", "throughput": 10141.51, "total_tokens": 12475968}
{"current_steps": 12995, "total_steps": 58920, "loss": 0.0016, "lr": 1.9127824008490762e-06, "epoch": 1.1027664630006788, "percentage": 22.06, "elapsed_time": "0:20:30", "remaining_time": "1:12:28", "throughput": 10142.27, "total_tokens": 12480960}
{"current_steps": 13000, "total_steps": 58920, "loss": 0.0277, "lr": 1.9126613708041267e-06, "epoch": 1.1031907671418872, "percentage": 22.06, "elapsed_time": "0:20:30", "remaining_time": "1:12:28", "throughput": 10143.56, "total_tokens": 12486656}
{"current_steps": 13005, "total_steps": 58920, "loss": 0.0435, "lr": 1.912540260676438e-06, "epoch": 1.1036150712830957, "percentage": 22.07, "elapsed_time": "0:20:31", "remaining_time": "1:12:27", "throughput": 10144.53, "total_tokens": 12491776}
{"current_steps": 13010, "total_steps": 58920, "loss": 0.0337, "lr": 1.912419070476635e-06, "epoch": 1.104039375424304, "percentage": 22.08, "elapsed_time": "0:20:31", "remaining_time": "1:12:26", "throughput": 10145.21, "total_tokens": 12496448}
{"current_steps": 13015, "total_steps": 58920, "loss": 0.027, "lr": 1.912297800215353e-06, "epoch": 1.1044636795655125, "percentage": 22.09, "elapsed_time": "0:20:32", "remaining_time": "1:12:25", "throughput": 10145.75, "total_tokens": 12500928}
{"current_steps": 13020, "total_steps": 58920, "loss": 0.0004, "lr": 1.9121764499032333e-06, "epoch": 1.104887983706721, "percentage": 22.1, "elapsed_time": "0:20:32", "remaining_time": "1:12:25", "throughput": 10147.06, "total_tokens": 12506688}
{"current_steps": 13025, "total_steps": 58920, "loss": 0.0097, "lr": 1.9120550195509236e-06, "epoch": 1.1053122878479293, "percentage": 22.11, "elapsed_time": "0:20:32", "remaining_time": "1:12:24", "throughput": 10147.63, "total_tokens": 12511232}
{"current_steps": 13030, "total_steps": 58920, "loss": 0.1022, "lr": 1.9119335091690785e-06, "epoch": 1.1057365919891378, "percentage": 22.11, "elapsed_time": "0:20:33", "remaining_time": "1:12:23", "throughput": 10148.25, "total_tokens": 12515840}
{"current_steps": 13035, "total_steps": 58920, "loss": 0.0321, "lr": 1.911811918768361e-06, "epoch": 1.1061608961303462, "percentage": 22.12, "elapsed_time": "0:20:33", "remaining_time": "1:12:22", "throughput": 10148.94, "total_tokens": 12520512}
{"current_steps": 13040, "total_steps": 58920, "loss": 0.0153, "lr": 1.9116902483594393e-06, "epoch": 1.1065852002715546, "percentage": 22.13, "elapsed_time": "0:20:34", "remaining_time": "1:12:21", "throughput": 10149.68, "total_tokens": 12525312}
{"current_steps": 13045, "total_steps": 58920, "loss": 0.0501, "lr": 1.91156849795299e-06, "epoch": 1.107009504412763, "percentage": 22.14, "elapsed_time": "0:20:34", "remaining_time": "1:12:21", "throughput": 10150.32, "total_tokens": 12529920}
{"current_steps": 13050, "total_steps": 58920, "loss": 0.0284, "lr": 1.911446667559696e-06, "epoch": 1.1074338085539714, "percentage": 22.15, "elapsed_time": "0:20:34", "remaining_time": "1:12:20", "throughput": 10150.99, "total_tokens": 12534592}
{"current_steps": 13055, "total_steps": 58920, "loss": 0.0083, "lr": 1.9113247571902484e-06, "epoch": 1.1078581126951799, "percentage": 22.16, "elapsed_time": "0:20:35", "remaining_time": "1:12:19", "throughput": 10151.76, "total_tokens": 12539392}
{"current_steps": 13060, "total_steps": 58920, "loss": 0.0198, "lr": 1.911202766855343e-06, "epoch": 1.1082824168363883, "percentage": 22.17, "elapsed_time": "0:20:35", "remaining_time": "1:12:18", "throughput": 10152.41, "total_tokens": 12544064}
{"current_steps": 13065, "total_steps": 58920, "loss": 0.0021, "lr": 1.911080696565685e-06, "epoch": 1.1087067209775967, "percentage": 22.17, "elapsed_time": "0:20:35", "remaining_time": "1:12:17", "throughput": 10153.2, "total_tokens": 12548928}
{"current_steps": 13070, "total_steps": 58920, "loss": 0.0467, "lr": 1.9109585463319854e-06, "epoch": 1.1091310251188051, "percentage": 22.18, "elapsed_time": "0:20:36", "remaining_time": "1:12:17", "throughput": 10153.48, "total_tokens": 12553024}
{"current_steps": 13075, "total_steps": 58920, "loss": 0.0215, "lr": 1.910836316164962e-06, "epoch": 1.1095553292600135, "percentage": 22.19, "elapsed_time": "0:20:36", "remaining_time": "1:12:16", "throughput": 10154.18, "total_tokens": 12557760}
{"current_steps": 13080, "total_steps": 58920, "loss": 0.0006, "lr": 1.9107140060753406e-06, "epoch": 1.109979633401222, "percentage": 22.2, "elapsed_time": "0:20:37", "remaining_time": "1:12:15", "throughput": 10155.08, "total_tokens": 12562816}
{"current_steps": 13085, "total_steps": 58920, "loss": 0.0023, "lr": 1.9105916160738533e-06, "epoch": 1.1104039375424304, "percentage": 22.21, "elapsed_time": "0:20:37", "remaining_time": "1:12:14", "throughput": 10155.63, "total_tokens": 12567360}
{"current_steps": 13090, "total_steps": 58920, "loss": 0.0777, "lr": 1.9104691461712394e-06, "epoch": 1.1108282416836388, "percentage": 22.22, "elapsed_time": "0:20:37", "remaining_time": "1:12:13", "throughput": 10156.42, "total_tokens": 12572224}
{"current_steps": 13095, "total_steps": 58920, "loss": 0.0003, "lr": 1.9103465963782453e-06, "epoch": 1.1112525458248472, "percentage": 22.23, "elapsed_time": "0:20:38", "remaining_time": "1:12:13", "throughput": 10157.48, "total_tokens": 12577536}
{"current_steps": 13100, "total_steps": 58920, "loss": 0.0857, "lr": 1.910223966705624e-06, "epoch": 1.1116768499660556, "percentage": 22.23, "elapsed_time": "0:20:38", "remaining_time": "1:12:12", "throughput": 10157.85, "total_tokens": 12581952}
{"current_steps": 13105, "total_steps": 58920, "loss": 0.069, "lr": 1.910101257164136e-06, "epoch": 1.112101154107264, "percentage": 22.24, "elapsed_time": "0:20:39", "remaining_time": "1:12:11", "throughput": 10158.54, "total_tokens": 12586624}
{"current_steps": 13110, "total_steps": 58920, "loss": 0.0008, "lr": 1.9099784677645487e-06, "epoch": 1.1125254582484725, "percentage": 22.25, "elapsed_time": "0:20:39", "remaining_time": "1:12:10", "throughput": 10159.08, "total_tokens": 12591104}
{"current_steps": 13115, "total_steps": 58920, "loss": 0.0804, "lr": 1.909855598517636e-06, "epoch": 1.112949762389681, "percentage": 22.26, "elapsed_time": "0:20:39", "remaining_time": "1:12:09", "throughput": 10159.55, "total_tokens": 12595520}
{"current_steps": 13120, "total_steps": 58920, "loss": 0.0193, "lr": 1.9097326494341796e-06, "epoch": 1.1133740665308893, "percentage": 22.27, "elapsed_time": "0:20:40", "remaining_time": "1:12:09", "throughput": 10160.36, "total_tokens": 12600448}
{"current_steps": 13125, "total_steps": 58920, "loss": 0.0829, "lr": 1.909609620524968e-06, "epoch": 1.1137983706720977, "percentage": 22.28, "elapsed_time": "0:20:40", "remaining_time": "1:12:08", "throughput": 10160.97, "total_tokens": 12605056}
{"current_steps": 13130, "total_steps": 58920, "loss": 0.0206, "lr": 1.909486511800796e-06, "epoch": 1.1142226748133062, "percentage": 22.28, "elapsed_time": "0:20:40", "remaining_time": "1:12:07", "throughput": 10161.9, "total_tokens": 12610112}
{"current_steps": 13135, "total_steps": 58920, "loss": 0.0696, "lr": 1.9093633232724667e-06, "epoch": 1.1146469789545146, "percentage": 22.29, "elapsed_time": "0:20:41", "remaining_time": "1:12:06", "throughput": 10162.54, "total_tokens": 12614784}
{"current_steps": 13140, "total_steps": 58920, "loss": 0.0213, "lr": 1.909240054950789e-06, "epoch": 1.115071283095723, "percentage": 22.3, "elapsed_time": "0:20:41", "remaining_time": "1:12:06", "throughput": 10162.93, "total_tokens": 12619072}
{"current_steps": 13145, "total_steps": 58920, "loss": 0.0015, "lr": 1.909116706846579e-06, "epoch": 1.1154955872369314, "percentage": 22.31, "elapsed_time": "0:20:42", "remaining_time": "1:12:05", "throughput": 10164.18, "total_tokens": 12624704}
{"current_steps": 13150, "total_steps": 58920, "loss": 0.025, "lr": 1.9089932789706606e-06, "epoch": 1.1159198913781398, "percentage": 22.32, "elapsed_time": "0:20:42", "remaining_time": "1:12:04", "throughput": 10167.13, "total_tokens": 12633344}
{"current_steps": 13155, "total_steps": 58920, "loss": 0.1477, "lr": 1.9088697713338637e-06, "epoch": 1.1163441955193483, "percentage": 22.33, "elapsed_time": "0:20:42", "remaining_time": "1:12:04", "throughput": 10168.07, "total_tokens": 12638464}
{"current_steps": 13160, "total_steps": 58920, "loss": 0.0627, "lr": 1.908746183947026e-06, "epoch": 1.1167684996605567, "percentage": 22.34, "elapsed_time": "0:20:43", "remaining_time": "1:12:03", "throughput": 10169.13, "total_tokens": 12643776}
{"current_steps": 13165, "total_steps": 58920, "loss": 0.0642, "lr": 1.9086225168209915e-06, "epoch": 1.117192803801765, "percentage": 22.34, "elapsed_time": "0:20:43", "remaining_time": "1:12:02", "throughput": 10169.57, "total_tokens": 12648128}
{"current_steps": 13170, "total_steps": 58920, "loss": 0.014, "lr": 1.9084987699666117e-06, "epoch": 1.1176171079429735, "percentage": 22.35, "elapsed_time": "0:20:44", "remaining_time": "1:12:01", "throughput": 10170.5, "total_tokens": 12653248}
{"current_steps": 13175, "total_steps": 58920, "loss": 0.0886, "lr": 1.908374943394745e-06, "epoch": 1.118041412084182, "percentage": 22.36, "elapsed_time": "0:20:44", "remaining_time": "1:12:00", "throughput": 10170.89, "total_tokens": 12657536}
{"current_steps": 13180, "total_steps": 58920, "loss": 0.0008, "lr": 1.9082510371162567e-06, "epoch": 1.1184657162253904, "percentage": 22.37, "elapsed_time": "0:20:44", "remaining_time": "1:12:00", "throughput": 10171.61, "total_tokens": 12662336}
{"current_steps": 13185, "total_steps": 58920, "loss": 0.0351, "lr": 1.908127051142019e-06, "epoch": 1.1188900203665988, "percentage": 22.38, "elapsed_time": "0:20:45", "remaining_time": "1:11:59", "throughput": 10172.35, "total_tokens": 12667136}
{"current_steps": 13190, "total_steps": 58920, "loss": 0.0414, "lr": 1.9080029854829116e-06, "epoch": 1.1193143245078072, "percentage": 22.39, "elapsed_time": "0:20:45", "remaining_time": "1:11:58", "throughput": 10173.01, "total_tokens": 12671808}
{"current_steps": 13195, "total_steps": 58920, "loss": 0.0011, "lr": 1.9078788401498205e-06, "epoch": 1.1197386286490156, "percentage": 22.39, "elapsed_time": "0:20:46", "remaining_time": "1:11:57", "throughput": 10173.64, "total_tokens": 12676416}
{"current_steps": 13200, "total_steps": 58920, "loss": 0.0308, "lr": 1.9077546151536386e-06, "epoch": 1.120162932790224, "percentage": 22.4, "elapsed_time": "0:20:46", "remaining_time": "1:11:57", "throughput": 10174.86, "total_tokens": 12682048}
{"current_steps": 13205, "total_steps": 58920, "loss": 0.0045, "lr": 1.9076303105052672e-06, "epoch": 1.1205872369314325, "percentage": 22.41, "elapsed_time": "0:20:46", "remaining_time": "1:11:56", "throughput": 10175.83, "total_tokens": 12687232}
{"current_steps": 13210, "total_steps": 58920, "loss": 0.036, "lr": 1.907505926215613e-06, "epoch": 1.121011541072641, "percentage": 22.42, "elapsed_time": "0:20:47", "remaining_time": "1:11:55", "throughput": 10176.72, "total_tokens": 12692288}
{"current_steps": 13215, "total_steps": 58920, "loss": 0.0114, "lr": 1.90738146229559e-06, "epoch": 1.1214358452138493, "percentage": 22.43, "elapsed_time": "0:20:47", "remaining_time": "1:11:54", "throughput": 10177.25, "total_tokens": 12696768}
{"current_steps": 13220, "total_steps": 58920, "loss": 0.0816, "lr": 1.9072569187561202e-06, "epoch": 1.1218601493550577, "percentage": 22.44, "elapsed_time": "0:20:47", "remaining_time": "1:11:54", "throughput": 10178.19, "total_tokens": 12701952}
{"current_steps": 13225, "total_steps": 58920, "loss": 0.0772, "lr": 1.907132295608131e-06, "epoch": 1.1222844534962662, "percentage": 22.45, "elapsed_time": "0:20:48", "remaining_time": "1:11:53", "throughput": 10178.84, "total_tokens": 12706688}
{"current_steps": 13230, "total_steps": 58920, "loss": 0.0059, "lr": 1.9070075928625583e-06, "epoch": 1.1227087576374746, "percentage": 22.45, "elapsed_time": "0:20:48", "remaining_time": "1:11:52", "throughput": 10179.78, "total_tokens": 12711872}
{"current_steps": 13235, "total_steps": 58920, "loss": 0.0011, "lr": 1.906882810530344e-06, "epoch": 1.123133061778683, "percentage": 22.46, "elapsed_time": "0:20:49", "remaining_time": "1:11:51", "throughput": 10180.54, "total_tokens": 12716736}
{"current_steps": 13240, "total_steps": 58920, "loss": 0.0253, "lr": 1.9067579486224375e-06, "epoch": 1.1235573659198914, "percentage": 22.47, "elapsed_time": "0:20:49", "remaining_time": "1:11:50", "throughput": 10180.98, "total_tokens": 12721088}
{"current_steps": 13245, "total_steps": 58920, "loss": 0.0968, "lr": 1.9066330071497947e-06, "epoch": 1.1239816700610998, "percentage": 22.48, "elapsed_time": "0:20:49", "remaining_time": "1:11:50", "throughput": 10181.64, "total_tokens": 12725824}
{"current_steps": 13250, "total_steps": 58920, "loss": 0.001, "lr": 1.9065079861233789e-06, "epoch": 1.1244059742023083, "percentage": 22.49, "elapsed_time": "0:20:50", "remaining_time": "1:11:49", "throughput": 10182.23, "total_tokens": 12730368}
{"current_steps": 13255, "total_steps": 58920, "loss": 0.0362, "lr": 1.9063828855541604e-06, "epoch": 1.1248302783435167, "percentage": 22.5, "elapsed_time": "0:20:50", "remaining_time": "1:11:48", "throughput": 10183.37, "total_tokens": 12735872}
{"current_steps": 13260, "total_steps": 58920, "loss": 0.0333, "lr": 1.9062577054531159e-06, "epoch": 1.125254582484725, "percentage": 22.51, "elapsed_time": "0:20:51", "remaining_time": "1:11:47", "throughput": 10183.96, "total_tokens": 12740480}
{"current_steps": 13265, "total_steps": 58920, "loss": 0.032, "lr": 1.90613244583123e-06, "epoch": 1.1256788866259335, "percentage": 22.51, "elapsed_time": "0:20:51", "remaining_time": "1:11:47", "throughput": 10184.66, "total_tokens": 12745216}
{"current_steps": 13270, "total_steps": 58920, "loss": 0.0312, "lr": 1.9060071066994933e-06, "epoch": 1.126103190767142, "percentage": 22.52, "elapsed_time": "0:20:51", "remaining_time": "1:11:46", "throughput": 10185.12, "total_tokens": 12749632}
{"current_steps": 13275, "total_steps": 58920, "loss": 0.0584, "lr": 1.9058816880689043e-06, "epoch": 1.1265274949083504, "percentage": 22.53, "elapsed_time": "0:20:52", "remaining_time": "1:11:45", "throughput": 10185.77, "total_tokens": 12754304}
{"current_steps": 13280, "total_steps": 58920, "loss": 0.0454, "lr": 1.905756189950468e-06, "epoch": 1.1269517990495588, "percentage": 22.54, "elapsed_time": "0:20:52", "remaining_time": "1:11:44", "throughput": 10186.34, "total_tokens": 12758848}
{"current_steps": 13285, "total_steps": 58920, "loss": 0.0739, "lr": 1.905630612355196e-06, "epoch": 1.1273761031907672, "percentage": 22.55, "elapsed_time": "0:20:52", "remaining_time": "1:11:43", "throughput": 10186.7, "total_tokens": 12763072}
{"current_steps": 13290, "total_steps": 58920, "loss": 0.1023, "lr": 1.9055049552941075e-06, "epoch": 1.1278004073319756, "percentage": 22.56, "elapsed_time": "0:20:53", "remaining_time": "1:11:43", "throughput": 10187.0, "total_tokens": 12767232}
{"current_steps": 13295, "total_steps": 58920, "loss": 0.055, "lr": 1.9053792187782287e-06, "epoch": 1.128224711473184, "percentage": 22.56, "elapsed_time": "0:20:53", "remaining_time": "1:11:42", "throughput": 10187.57, "total_tokens": 12771776}
{"current_steps": 13300, "total_steps": 58920, "loss": 0.143, "lr": 1.9052534028185923e-06, "epoch": 1.1286490156143925, "percentage": 22.57, "elapsed_time": "0:20:54", "remaining_time": "1:11:41", "throughput": 10188.28, "total_tokens": 12776576}
{"current_steps": 13305, "total_steps": 58920, "loss": 0.0375, "lr": 1.9051275074262381e-06, "epoch": 1.1290733197556009, "percentage": 22.58, "elapsed_time": "0:20:54", "remaining_time": "1:11:40", "throughput": 10189.03, "total_tokens": 12781440}
{"current_steps": 13310, "total_steps": 58920, "loss": 0.0923, "lr": 1.9050015326122128e-06, "epoch": 1.1294976238968093, "percentage": 22.59, "elapsed_time": "0:20:54", "remaining_time": "1:11:39", "throughput": 10189.63, "total_tokens": 12785984}
{"current_steps": 13315, "total_steps": 58920, "loss": 0.0545, "lr": 1.9048754783875709e-06, "epoch": 1.1299219280380177, "percentage": 22.6, "elapsed_time": "0:20:55", "remaining_time": "1:11:39", "throughput": 10190.26, "total_tokens": 12790592}
{"current_steps": 13320, "total_steps": 58920, "loss": 0.0117, "lr": 1.9047493447633728e-06, "epoch": 1.1303462321792261, "percentage": 22.61, "elapsed_time": "0:20:55", "remaining_time": "1:11:38", "throughput": 10190.74, "total_tokens": 12795008}
{"current_steps": 13325, "total_steps": 58920, "loss": 0.0181, "lr": 1.9046231317506862e-06, "epoch": 1.1307705363204346, "percentage": 22.62, "elapsed_time": "0:20:55", "remaining_time": "1:11:37", "throughput": 10191.14, "total_tokens": 12799296}
{"current_steps": 13330, "total_steps": 58920, "loss": 0.0519, "lr": 1.9044968393605857e-06, "epoch": 1.131194840461643, "percentage": 22.62, "elapsed_time": "0:20:56", "remaining_time": "1:11:36", "throughput": 10192.1, "total_tokens": 12804480}
{"current_steps": 13335, "total_steps": 58920, "loss": 0.0282, "lr": 1.9043704676041537e-06, "epoch": 1.1316191446028514, "percentage": 22.63, "elapsed_time": "0:20:56", "remaining_time": "1:11:35", "throughput": 10192.61, "total_tokens": 12808960}
{"current_steps": 13340, "total_steps": 58920, "loss": 0.0935, "lr": 1.904244016492478e-06, "epoch": 1.1320434487440598, "percentage": 22.64, "elapsed_time": "0:20:57", "remaining_time": "1:11:35", "throughput": 10193.15, "total_tokens": 12813440}
{"current_steps": 13345, "total_steps": 58920, "loss": 0.021, "lr": 1.9041174860366547e-06, "epoch": 1.1324677528852682, "percentage": 22.65, "elapsed_time": "0:20:57", "remaining_time": "1:11:34", "throughput": 10193.9, "total_tokens": 12818304}
{"current_steps": 13350, "total_steps": 58920, "loss": 0.005, "lr": 1.9039908762477866e-06, "epoch": 1.1328920570264767, "percentage": 22.66, "elapsed_time": "0:20:57", "remaining_time": "1:11:33", "throughput": 10194.36, "total_tokens": 12822720}
{"current_steps": 13355, "total_steps": 58920, "loss": 0.0303, "lr": 1.9038641871369825e-06, "epoch": 1.133316361167685, "percentage": 22.67, "elapsed_time": "0:20:58", "remaining_time": "1:11:32", "throughput": 10194.95, "total_tokens": 12827328}
{"current_steps": 13360, "total_steps": 58920, "loss": 0.0031, "lr": 1.9037374187153596e-06, "epoch": 1.1337406653088935, "percentage": 22.67, "elapsed_time": "0:20:58", "remaining_time": "1:11:32", "throughput": 10196.33, "total_tokens": 12833280}
{"current_steps": 13365, "total_steps": 58920, "loss": 0.0348, "lr": 1.903610570994041e-06, "epoch": 1.134164969450102, "percentage": 22.68, "elapsed_time": "0:20:58", "remaining_time": "1:11:31", "throughput": 10196.85, "total_tokens": 12837824}
{"current_steps": 13370, "total_steps": 58920, "loss": 0.0507, "lr": 1.9034836439841576e-06, "epoch": 1.1345892735913103, "percentage": 22.69, "elapsed_time": "0:20:59", "remaining_time": "1:11:30", "throughput": 10197.72, "total_tokens": 12842880}
{"current_steps": 13375, "total_steps": 58920, "loss": 0.0009, "lr": 1.903356637696846e-06, "epoch": 1.1350135777325188, "percentage": 22.7, "elapsed_time": "0:20:59", "remaining_time": "1:11:29", "throughput": 10198.64, "total_tokens": 12848064}
{"current_steps": 13380, "total_steps": 58920, "loss": 0.032, "lr": 1.9032295521432512e-06, "epoch": 1.1354378818737272, "percentage": 22.71, "elapsed_time": "0:21:00", "remaining_time": "1:11:29", "throughput": 10199.49, "total_tokens": 12853120}
{"current_steps": 13385, "total_steps": 58920, "loss": 0.0921, "lr": 1.9031023873345244e-06, "epoch": 1.1358621860149354, "percentage": 22.72, "elapsed_time": "0:21:00", "remaining_time": "1:11:28", "throughput": 10200.11, "total_tokens": 12857792}
{"current_steps": 13390, "total_steps": 58920, "loss": 0.0383, "lr": 1.9029751432818237e-06, "epoch": 1.1362864901561438, "percentage": 22.73, "elapsed_time": "0:21:00", "remaining_time": "1:11:27", "throughput": 10200.86, "total_tokens": 12862656}
{"current_steps": 13395, "total_steps": 58920, "loss": 0.1034, "lr": 1.9028478199963142e-06, "epoch": 1.1367107942973522, "percentage": 22.73, "elapsed_time": "0:21:01", "remaining_time": "1:11:26", "throughput": 10201.55, "total_tokens": 12867456}
{"current_steps": 13400, "total_steps": 58920, "loss": 0.0983, "lr": 1.9027204174891684e-06, "epoch": 1.1371350984385606, "percentage": 22.74, "elapsed_time": "0:21:01", "remaining_time": "1:11:26", "throughput": 10202.4, "total_tokens": 12872448}
{"current_steps": 13405, "total_steps": 58920, "loss": 0.0692, "lr": 1.902592935771565e-06, "epoch": 1.137559402579769, "percentage": 22.75, "elapsed_time": "0:21:02", "remaining_time": "1:11:25", "throughput": 10202.87, "total_tokens": 12876864}
{"current_steps": 13410, "total_steps": 58920, "loss": 0.0555, "lr": 1.9024653748546905e-06, "epoch": 1.1379837067209775, "percentage": 22.76, "elapsed_time": "0:21:02", "remaining_time": "1:11:24", "throughput": 10203.52, "total_tokens": 12881536}
{"current_steps": 13415, "total_steps": 58920, "loss": 0.0422, "lr": 1.9023377347497375e-06, "epoch": 1.138408010862186, "percentage": 22.77, "elapsed_time": "0:21:02", "remaining_time": "1:11:23", "throughput": 10204.11, "total_tokens": 12886144}
{"current_steps": 13420, "total_steps": 58920, "loss": 0.0297, "lr": 1.9022100154679063e-06, "epoch": 1.1388323150033943, "percentage": 22.78, "elapsed_time": "0:21:03", "remaining_time": "1:11:22", "throughput": 10204.71, "total_tokens": 12890752}
{"current_steps": 13425, "total_steps": 58920, "loss": 0.0195, "lr": 1.902082217020404e-06, "epoch": 1.1392566191446027, "percentage": 22.79, "elapsed_time": "0:21:03", "remaining_time": "1:11:22", "throughput": 10205.32, "total_tokens": 12895360}
{"current_steps": 13430, "total_steps": 58920, "loss": 0.0248, "lr": 1.9019543394184434e-06, "epoch": 1.1396809232858112, "percentage": 22.79, "elapsed_time": "0:21:03", "remaining_time": "1:11:21", "throughput": 10206.23, "total_tokens": 12900480}
{"current_steps": 13435, "total_steps": 58920, "loss": 0.0385, "lr": 1.9018263826732465e-06, "epoch": 1.1401052274270196, "percentage": 22.8, "elapsed_time": "0:21:04", "remaining_time": "1:11:20", "throughput": 10206.78, "total_tokens": 12905024}
{"current_steps": 13440, "total_steps": 58920, "loss": 0.0172, "lr": 1.9016983467960404e-06, "epoch": 1.140529531568228, "percentage": 22.81, "elapsed_time": "0:21:04", "remaining_time": "1:11:19", "throughput": 10207.58, "total_tokens": 12909952}
{"current_steps": 13445, "total_steps": 58920, "loss": 0.052, "lr": 1.9015702317980599e-06, "epoch": 1.1409538357094364, "percentage": 22.82, "elapsed_time": "0:21:05", "remaining_time": "1:11:18", "throughput": 10208.1, "total_tokens": 12914432}
{"current_steps": 13450, "total_steps": 58920, "loss": 0.0243, "lr": 1.9014420376905468e-06, "epoch": 1.1413781398506448, "percentage": 22.83, "elapsed_time": "0:21:05", "remaining_time": "1:11:18", "throughput": 10208.86, "total_tokens": 12919296}
{"current_steps": 13455, "total_steps": 58920, "loss": 0.1348, "lr": 1.9013137644847494e-06, "epoch": 1.1418024439918533, "percentage": 22.84, "elapsed_time": "0:21:05", "remaining_time": "1:11:17", "throughput": 10209.33, "total_tokens": 12923712}
{"current_steps": 13460, "total_steps": 58920, "loss": 0.001, "lr": 1.9011854121919236e-06, "epoch": 1.1422267481330617, "percentage": 22.84, "elapsed_time": "0:21:06", "remaining_time": "1:11:16", "throughput": 10209.87, "total_tokens": 12928256}
{"current_steps": 13465, "total_steps": 58920, "loss": 0.0067, "lr": 1.9010569808233312e-06, "epoch": 1.14265105227427, "percentage": 22.85, "elapsed_time": "0:21:06", "remaining_time": "1:11:15", "throughput": 10210.33, "total_tokens": 12932672}
{"current_steps": 13470, "total_steps": 58920, "loss": 0.051, "lr": 1.900928470390242e-06, "epoch": 1.1430753564154785, "percentage": 22.86, "elapsed_time": "0:21:07", "remaining_time": "1:11:15", "throughput": 10210.95, "total_tokens": 12937344}
{"current_steps": 13475, "total_steps": 58920, "loss": 0.08, "lr": 1.9007998809039327e-06, "epoch": 1.143499660556687, "percentage": 22.87, "elapsed_time": "0:21:07", "remaining_time": "1:11:14", "throughput": 10211.32, "total_tokens": 12941568}
{"current_steps": 13480, "total_steps": 58920, "loss": 0.1116, "lr": 1.9006712123756858e-06, "epoch": 1.1439239646978954, "percentage": 22.88, "elapsed_time": "0:21:07", "remaining_time": "1:11:13", "throughput": 10212.28, "total_tokens": 12946816}
{"current_steps": 13485, "total_steps": 58920, "loss": 0.0213, "lr": 1.9005424648167923e-06, "epoch": 1.1443482688391038, "percentage": 22.89, "elapsed_time": "0:21:08", "remaining_time": "1:11:13", "throughput": 10215.09, "total_tokens": 12955392}
{"current_steps": 13490, "total_steps": 58920, "loss": 0.0779, "lr": 1.9004136382385486e-06, "epoch": 1.1447725729803122, "percentage": 22.9, "elapsed_time": "0:21:08", "remaining_time": "1:11:12", "throughput": 10215.75, "total_tokens": 12960128}
{"current_steps": 13495, "total_steps": 58920, "loss": 0.093, "lr": 1.9002847326522591e-06, "epoch": 1.1451968771215206, "percentage": 22.9, "elapsed_time": "0:21:09", "remaining_time": "1:11:11", "throughput": 10216.47, "total_tokens": 12964928}
{"current_steps": 13500, "total_steps": 58920, "loss": 0.0027, "lr": 1.9001557480692348e-06, "epoch": 1.145621181262729, "percentage": 22.91, "elapsed_time": "0:21:09", "remaining_time": "1:11:10", "throughput": 10216.78, "total_tokens": 12969088}
{"current_steps": 13505, "total_steps": 58920, "loss": 0.059, "lr": 1.9000266845007937e-06, "epoch": 1.1460454854039375, "percentage": 22.92, "elapsed_time": "0:21:09", "remaining_time": "1:11:10", "throughput": 10217.39, "total_tokens": 12973696}
{"current_steps": 13510, "total_steps": 58920, "loss": 0.0519, "lr": 1.8998975419582603e-06, "epoch": 1.146469789545146, "percentage": 22.93, "elapsed_time": "0:21:10", "remaining_time": "1:11:09", "throughput": 10218.11, "total_tokens": 12978496}
{"current_steps": 13515, "total_steps": 58920, "loss": 0.0131, "lr": 1.899768320452967e-06, "epoch": 1.1468940936863543, "percentage": 22.94, "elapsed_time": "0:21:10", "remaining_time": "1:11:08", "throughput": 10218.77, "total_tokens": 12983232}
{"current_steps": 13520, "total_steps": 58920, "loss": 0.024, "lr": 1.899639019996252e-06, "epoch": 1.1473183978275627, "percentage": 22.95, "elapsed_time": "0:21:10", "remaining_time": "1:11:07", "throughput": 10219.51, "total_tokens": 12988096}
{"current_steps": 13525, "total_steps": 58920, "loss": 0.0492, "lr": 1.8995096405994611e-06, "epoch": 1.1477427019687712, "percentage": 22.95, "elapsed_time": "0:21:11", "remaining_time": "1:11:06", "throughput": 10220.32, "total_tokens": 12993088}
{"current_steps": 13530, "total_steps": 58920, "loss": 0.0758, "lr": 1.899380182273947e-06, "epoch": 1.1481670061099796, "percentage": 22.96, "elapsed_time": "0:21:11", "remaining_time": "1:11:06", "throughput": 10220.81, "total_tokens": 12997568}
{"current_steps": 13535, "total_steps": 58920, "loss": 0.0007, "lr": 1.899250645031069e-06, "epoch": 1.148591310251188, "percentage": 22.97, "elapsed_time": "0:21:12", "remaining_time": "1:11:05", "throughput": 10221.31, "total_tokens": 13002048}
{"current_steps": 13540, "total_steps": 58920, "loss": 0.0244, "lr": 1.8991210288821937e-06, "epoch": 1.1490156143923964, "percentage": 22.98, "elapsed_time": "0:21:12", "remaining_time": "1:11:04", "throughput": 10221.58, "total_tokens": 13006144}
{"current_steps": 13545, "total_steps": 58920, "loss": 0.0396, "lr": 1.8989913338386945e-06, "epoch": 1.1494399185336048, "percentage": 22.99, "elapsed_time": "0:21:12", "remaining_time": "1:11:03", "throughput": 10221.96, "total_tokens": 13010432}
{"current_steps": 13550, "total_steps": 58920, "loss": 0.018, "lr": 1.8988615599119514e-06, "epoch": 1.1498642226748133, "percentage": 23.0, "elapsed_time": "0:21:13", "remaining_time": "1:11:02", "throughput": 10222.45, "total_tokens": 13014848}
{"current_steps": 13555, "total_steps": 58920, "loss": 0.0013, "lr": 1.8987317071133515e-06, "epoch": 1.1502885268160217, "percentage": 23.01, "elapsed_time": "0:21:13", "remaining_time": "1:11:02", "throughput": 10223.11, "total_tokens": 13019584}
{"current_steps": 13560, "total_steps": 58920, "loss": 0.0402, "lr": 1.8986017754542897e-06, "epoch": 1.15071283095723, "percentage": 23.01, "elapsed_time": "0:21:13", "remaining_time": "1:11:01", "throughput": 10224.18, "total_tokens": 13024960}
{"current_steps": 13565, "total_steps": 58920, "loss": 0.0778, "lr": 1.898471764946166e-06, "epoch": 1.1511371350984385, "percentage": 23.02, "elapsed_time": "0:21:14", "remaining_time": "1:11:00", "throughput": 10224.7, "total_tokens": 13029440}
{"current_steps": 13570, "total_steps": 58920, "loss": 0.049, "lr": 1.8983416756003892e-06, "epoch": 1.151561439239647, "percentage": 23.03, "elapsed_time": "0:21:14", "remaining_time": "1:10:59", "throughput": 10225.73, "total_tokens": 13034752}
{"current_steps": 13575, "total_steps": 58920, "loss": 0.0067, "lr": 1.8982115074283738e-06, "epoch": 1.1519857433808554, "percentage": 23.04, "elapsed_time": "0:21:15", "remaining_time": "1:10:59", "throughput": 10226.83, "total_tokens": 13040192}
{"current_steps": 13580, "total_steps": 58920, "loss": 0.0411, "lr": 1.8980812604415414e-06, "epoch": 1.1524100475220638, "percentage": 23.05, "elapsed_time": "0:21:15", "remaining_time": "1:10:58", "throughput": 10227.27, "total_tokens": 13044544}
{"current_steps": 13585, "total_steps": 58920, "loss": 0.0229, "lr": 1.8979509346513209e-06, "epoch": 1.1528343516632722, "percentage": 23.06, "elapsed_time": "0:21:15", "remaining_time": "1:10:57", "throughput": 10228.13, "total_tokens": 13049664}
{"current_steps": 13590, "total_steps": 58920, "loss": 0.0468, "lr": 1.8978205300691482e-06, "epoch": 1.1532586558044806, "percentage": 23.07, "elapsed_time": "0:21:16", "remaining_time": "1:10:56", "throughput": 10229.05, "total_tokens": 13054848}
{"current_steps": 13595, "total_steps": 58920, "loss": 0.1175, "lr": 1.8976900467064652e-06, "epoch": 1.153682959945689, "percentage": 23.07, "elapsed_time": "0:21:16", "remaining_time": "1:10:56", "throughput": 10229.88, "total_tokens": 13059904}
{"current_steps": 13600, "total_steps": 58920, "loss": 0.0167, "lr": 1.8975594845747218e-06, "epoch": 1.1541072640868975, "percentage": 23.08, "elapsed_time": "0:21:17", "remaining_time": "1:10:55", "throughput": 10230.35, "total_tokens": 13064320}
{"current_steps": 13605, "total_steps": 58920, "loss": 0.0413, "lr": 1.8974288436853745e-06, "epoch": 1.1545315682281059, "percentage": 23.09, "elapsed_time": "0:21:17", "remaining_time": "1:10:54", "throughput": 10231.45, "total_tokens": 13069824}
{"current_steps": 13610, "total_steps": 58920, "loss": 0.038, "lr": 1.897298124049886e-06, "epoch": 1.1549558723693143, "percentage": 23.1, "elapsed_time": "0:21:17", "remaining_time": "1:10:53", "throughput": 10232.0, "total_tokens": 13074368}
{"current_steps": 13615, "total_steps": 58920, "loss": 0.073, "lr": 1.8971673256797272e-06, "epoch": 1.1553801765105227, "percentage": 23.11, "elapsed_time": "0:21:18", "remaining_time": "1:10:53", "throughput": 10232.88, "total_tokens": 13079488}
{"current_steps": 13620, "total_steps": 58920, "loss": 0.0269, "lr": 1.8970364485863743e-06, "epoch": 1.1558044806517311, "percentage": 23.12, "elapsed_time": "0:21:18", "remaining_time": "1:10:52", "throughput": 10233.69, "total_tokens": 13084480}
{"current_steps": 13625, "total_steps": 58920, "loss": 0.0363, "lr": 1.8969054927813119e-06, "epoch": 1.1562287847929396, "percentage": 23.12, "elapsed_time": "0:21:18", "remaining_time": "1:10:51", "throughput": 10234.27, "total_tokens": 13089088}
{"current_steps": 13630, "total_steps": 58920, "loss": 0.0014, "lr": 1.896774458276031e-06, "epoch": 1.156653088934148, "percentage": 23.13, "elapsed_time": "0:21:19", "remaining_time": "1:10:50", "throughput": 10235.08, "total_tokens": 13094080}
{"current_steps": 13635, "total_steps": 58920, "loss": 0.0562, "lr": 1.896643345082029e-06, "epoch": 1.1570773930753564, "percentage": 23.14, "elapsed_time": "0:21:19", "remaining_time": "1:10:50", "throughput": 10235.78, "total_tokens": 13098880}
{"current_steps": 13640, "total_steps": 58920, "loss": 0.0006, "lr": 1.8965121532108107e-06, "epoch": 1.1575016972165648, "percentage": 23.15, "elapsed_time": "0:21:20", "remaining_time": "1:10:49", "throughput": 10236.52, "total_tokens": 13103744}
{"current_steps": 13645, "total_steps": 58920, "loss": 0.0046, "lr": 1.896380882673888e-06, "epoch": 1.1579260013577732, "percentage": 23.16, "elapsed_time": "0:21:20", "remaining_time": "1:10:48", "throughput": 10237.22, "total_tokens": 13108544}
{"current_steps": 13650, "total_steps": 58920, "loss": 0.0005, "lr": 1.8962495334827793e-06, "epoch": 1.1583503054989817, "percentage": 23.17, "elapsed_time": "0:21:20", "remaining_time": "1:10:47", "throughput": 10237.59, "total_tokens": 13112832}
{"current_steps": 13655, "total_steps": 58920, "loss": 0.0005, "lr": 1.8961181056490096e-06, "epoch": 1.15877460964019, "percentage": 23.18, "elapsed_time": "0:21:21", "remaining_time": "1:10:47", "throughput": 10237.97, "total_tokens": 13117120}
{"current_steps": 13660, "total_steps": 58920, "loss": 0.0184, "lr": 1.8959865991841118e-06, "epoch": 1.1591989137813985, "percentage": 23.18, "elapsed_time": "0:21:21", "remaining_time": "1:10:46", "throughput": 10238.65, "total_tokens": 13121856}
{"current_steps": 13665, "total_steps": 58920, "loss": 0.0538, "lr": 1.8958550140996248e-06, "epoch": 1.159623217922607, "percentage": 23.19, "elapsed_time": "0:21:21", "remaining_time": "1:10:45", "throughput": 10239.58, "total_tokens": 13127104}
{"current_steps": 13670, "total_steps": 58920, "loss": 0.0001, "lr": 1.8957233504070945e-06, "epoch": 1.1600475220638153, "percentage": 23.2, "elapsed_time": "0:21:22", "remaining_time": "1:10:44", "throughput": 10240.48, "total_tokens": 13132288}
{"current_steps": 13675, "total_steps": 58920, "loss": 0.0678, "lr": 1.8955916081180747e-06, "epoch": 1.1604718262050238, "percentage": 23.21, "elapsed_time": "0:21:22", "remaining_time": "1:10:44", "throughput": 10241.39, "total_tokens": 13137472}
{"current_steps": 13680, "total_steps": 58920, "loss": 0.0753, "lr": 1.8954597872441247e-06, "epoch": 1.1608961303462322, "percentage": 23.22, "elapsed_time": "0:21:23", "remaining_time": "1:10:43", "throughput": 10241.91, "total_tokens": 13141952}
{"current_steps": 13685, "total_steps": 58920, "loss": 0.0051, "lr": 1.8953278877968112e-06, "epoch": 1.1613204344874406, "percentage": 23.23, "elapsed_time": "0:21:23", "remaining_time": "1:10:42", "throughput": 10242.45, "total_tokens": 13146496}
{"current_steps": 13690, "total_steps": 58920, "loss": 0.1145, "lr": 1.8951959097877084e-06, "epoch": 1.161744738628649, "percentage": 23.23, "elapsed_time": "0:21:23", "remaining_time": "1:10:41", "throughput": 10242.92, "total_tokens": 13150976}
{"current_steps": 13695, "total_steps": 58920, "loss": 0.0154, "lr": 1.8950638532283962e-06, "epoch": 1.1621690427698574, "percentage": 23.24, "elapsed_time": "0:21:24", "remaining_time": "1:10:41", "throughput": 10243.12, "total_tokens": 13155008}
{"current_steps": 13700, "total_steps": 58920, "loss": 0.0126, "lr": 1.8949317181304627e-06, "epoch": 1.1625933469110659, "percentage": 23.25, "elapsed_time": "0:21:24", "remaining_time": "1:10:40", "throughput": 10244.39, "total_tokens": 13160768}
{"current_steps": 13705, "total_steps": 58920, "loss": 0.0153, "lr": 1.894799504505502e-06, "epoch": 1.1630176510522743, "percentage": 23.26, "elapsed_time": "0:21:25", "remaining_time": "1:10:39", "throughput": 10244.77, "total_tokens": 13165056}
{"current_steps": 13710, "total_steps": 58920, "loss": 0.022, "lr": 1.8946672123651158e-06, "epoch": 1.1634419551934827, "percentage": 23.27, "elapsed_time": "0:21:25", "remaining_time": "1:10:38", "throughput": 10245.4, "total_tokens": 13169728}
{"current_steps": 13715, "total_steps": 58920, "loss": 0.0435, "lr": 1.8945348417209115e-06, "epoch": 1.1638662593346911, "percentage": 23.28, "elapsed_time": "0:21:25", "remaining_time": "1:10:38", "throughput": 10246.15, "total_tokens": 13174656}
{"current_steps": 13720, "total_steps": 58920, "loss": 0.0815, "lr": 1.8944023925845048e-06, "epoch": 1.1642905634758995, "percentage": 23.29, "elapsed_time": "0:21:26", "remaining_time": "1:10:37", "throughput": 10246.83, "total_tokens": 13179392}
{"current_steps": 13725, "total_steps": 58920, "loss": 0.0004, "lr": 1.894269864967517e-06, "epoch": 1.164714867617108, "percentage": 23.29, "elapsed_time": "0:21:26", "remaining_time": "1:10:36", "throughput": 10247.42, "total_tokens": 13184000}
{"current_steps": 13730, "total_steps": 58920, "loss": 0.0152, "lr": 1.8941372588815775e-06, "epoch": 1.1651391717583164, "percentage": 23.3, "elapsed_time": "0:21:26", "remaining_time": "1:10:35", "throughput": 10248.31, "total_tokens": 13189120}
{"current_steps": 13735, "total_steps": 58920, "loss": 0.0836, "lr": 1.894004574338322e-06, "epoch": 1.1655634758995248, "percentage": 23.31, "elapsed_time": "0:21:27", "remaining_time": "1:10:35", "throughput": 10248.93, "total_tokens": 13193856}
{"current_steps": 13740, "total_steps": 58920, "loss": 0.001, "lr": 1.8938718113493927e-06, "epoch": 1.1659877800407332, "percentage": 23.32, "elapsed_time": "0:21:27", "remaining_time": "1:10:34", "throughput": 10249.4, "total_tokens": 13198336}
{"current_steps": 13745, "total_steps": 58920, "loss": 0.0369, "lr": 1.8937389699264395e-06, "epoch": 1.1664120841819416, "percentage": 23.33, "elapsed_time": "0:21:28", "remaining_time": "1:10:33", "throughput": 10250.34, "total_tokens": 13203584}
{"current_steps": 13750, "total_steps": 58920, "loss": 0.0539, "lr": 1.8936060500811183e-06, "epoch": 1.16683638832315, "percentage": 23.34, "elapsed_time": "0:21:28", "remaining_time": "1:10:32", "throughput": 10251.35, "total_tokens": 13208896}
{"current_steps": 13755, "total_steps": 58920, "loss": 0.0007, "lr": 1.8934730518250926e-06, "epoch": 1.1672606924643585, "percentage": 23.35, "elapsed_time": "0:21:28", "remaining_time": "1:10:32", "throughput": 10252.15, "total_tokens": 13213888}
{"current_steps": 13760, "total_steps": 58920, "loss": 0.0008, "lr": 1.8933399751700323e-06, "epoch": 1.167684996605567, "percentage": 23.35, "elapsed_time": "0:21:29", "remaining_time": "1:10:31", "throughput": 10252.96, "total_tokens": 13218880}
{"current_steps": 13765, "total_steps": 58920, "loss": 0.0266, "lr": 1.8932068201276147e-06, "epoch": 1.1681093007467753, "percentage": 23.36, "elapsed_time": "0:21:29", "remaining_time": "1:10:30", "throughput": 10254.02, "total_tokens": 13224320}
{"current_steps": 13770, "total_steps": 58920, "loss": 0.0434, "lr": 1.8930735867095237e-06, "epoch": 1.1685336048879837, "percentage": 23.37, "elapsed_time": "0:21:30", "remaining_time": "1:10:29", "throughput": 10254.48, "total_tokens": 13228736}
{"current_steps": 13775, "total_steps": 58920, "loss": 0.0452, "lr": 1.89294027492745e-06, "epoch": 1.1689579090291922, "percentage": 23.38, "elapsed_time": "0:21:30", "remaining_time": "1:10:29", "throughput": 10255.25, "total_tokens": 13233664}
{"current_steps": 13780, "total_steps": 58920, "loss": 0.0708, "lr": 1.8928068847930906e-06, "epoch": 1.1693822131704006, "percentage": 23.39, "elapsed_time": "0:21:30", "remaining_time": "1:10:28", "throughput": 10255.79, "total_tokens": 13238208}
{"current_steps": 13785, "total_steps": 58920, "loss": 0.0257, "lr": 1.8926734163181509e-06, "epoch": 1.169806517311609, "percentage": 23.4, "elapsed_time": "0:21:31", "remaining_time": "1:10:27", "throughput": 10256.8, "total_tokens": 13243584}
{"current_steps": 13790, "total_steps": 58920, "loss": 0.0581, "lr": 1.8925398695143419e-06, "epoch": 1.1702308214528174, "percentage": 23.4, "elapsed_time": "0:21:31", "remaining_time": "1:10:26", "throughput": 10257.42, "total_tokens": 13248256}
{"current_steps": 13795, "total_steps": 58920, "loss": 0.0194, "lr": 1.8924062443933817e-06, "epoch": 1.1706551255940258, "percentage": 23.41, "elapsed_time": "0:21:31", "remaining_time": "1:10:26", "throughput": 10257.95, "total_tokens": 13252800}
{"current_steps": 13800, "total_steps": 58920, "loss": 0.0612, "lr": 1.8922725409669957e-06, "epoch": 1.1710794297352343, "percentage": 23.42, "elapsed_time": "0:21:32", "remaining_time": "1:10:25", "throughput": 10258.36, "total_tokens": 13257088}
{"current_steps": 13805, "total_steps": 58920, "loss": 0.0534, "lr": 1.8921387592469156e-06, "epoch": 1.1715037338764427, "percentage": 23.43, "elapsed_time": "0:21:32", "remaining_time": "1:10:24", "throughput": 10258.76, "total_tokens": 13261440}
{"current_steps": 13810, "total_steps": 58920, "loss": 0.0586, "lr": 1.8920048992448808e-06, "epoch": 1.171928038017651, "percentage": 23.44, "elapsed_time": "0:21:33", "remaining_time": "1:10:23", "throughput": 10259.36, "total_tokens": 13266112}
{"current_steps": 13815, "total_steps": 58920, "loss": 0.0578, "lr": 1.8918709609726362e-06, "epoch": 1.1723523421588595, "percentage": 23.45, "elapsed_time": "0:21:33", "remaining_time": "1:10:23", "throughput": 10259.9, "total_tokens": 13270656}
{"current_steps": 13820, "total_steps": 58920, "loss": 0.0081, "lr": 1.891736944441935e-06, "epoch": 1.172776646300068, "percentage": 23.46, "elapsed_time": "0:21:33", "remaining_time": "1:10:22", "throughput": 10260.5, "total_tokens": 13275328}
{"current_steps": 13825, "total_steps": 58920, "loss": 0.0009, "lr": 1.8916028496645366e-06, "epoch": 1.1732009504412764, "percentage": 23.46, "elapsed_time": "0:21:34", "remaining_time": "1:10:21", "throughput": 10261.07, "total_tokens": 13279936}
{"current_steps": 13830, "total_steps": 58920, "loss": 0.0072, "lr": 1.8914686766522072e-06, "epoch": 1.1736252545824848, "percentage": 23.47, "elapsed_time": "0:21:34", "remaining_time": "1:10:20", "throughput": 10261.82, "total_tokens": 13284800}
{"current_steps": 13835, "total_steps": 58920, "loss": 0.0002, "lr": 1.8913344254167204e-06, "epoch": 1.1740495587236932, "percentage": 23.48, "elapsed_time": "0:21:34", "remaining_time": "1:10:19", "throughput": 10262.26, "total_tokens": 13289216}
{"current_steps": 13840, "total_steps": 58920, "loss": 0.0546, "lr": 1.8912000959698555e-06, "epoch": 1.1744738628649016, "percentage": 23.49, "elapsed_time": "0:21:35", "remaining_time": "1:10:19", "throughput": 10263.0, "total_tokens": 13294144}
{"current_steps": 13845, "total_steps": 58920, "loss": 0.0995, "lr": 1.8910656883234e-06, "epoch": 1.17489816700611, "percentage": 23.5, "elapsed_time": "0:21:35", "remaining_time": "1:10:18", "throughput": 10263.61, "total_tokens": 13298816}
{"current_steps": 13850, "total_steps": 58920, "loss": 0.0532, "lr": 1.8909312024891474e-06, "epoch": 1.1753224711473185, "percentage": 23.51, "elapsed_time": "0:21:36", "remaining_time": "1:10:17", "throughput": 10264.07, "total_tokens": 13303232}
{"current_steps": 13855, "total_steps": 58920, "loss": 0.0187, "lr": 1.8907966384788987e-06, "epoch": 1.175746775288527, "percentage": 23.51, "elapsed_time": "0:21:36", "remaining_time": "1:10:16", "throughput": 10264.54, "total_tokens": 13307648}
{"current_steps": 13860, "total_steps": 58920, "loss": 0.0546, "lr": 1.890661996304461e-06, "epoch": 1.1761710794297353, "percentage": 23.52, "elapsed_time": "0:21:36", "remaining_time": "1:10:16", "throughput": 10265.46, "total_tokens": 13312896}
{"current_steps": 13865, "total_steps": 58920, "loss": 0.034, "lr": 1.890527275977649e-06, "epoch": 1.1765953835709437, "percentage": 23.53, "elapsed_time": "0:21:37", "remaining_time": "1:10:15", "throughput": 10266.22, "total_tokens": 13317824}
{"current_steps": 13870, "total_steps": 58920, "loss": 0.0979, "lr": 1.8903924775102834e-06, "epoch": 1.1770196877121522, "percentage": 23.54, "elapsed_time": "0:21:37", "remaining_time": "1:10:14", "throughput": 10266.67, "total_tokens": 13322240}
{"current_steps": 13875, "total_steps": 58920, "loss": 0.0233, "lr": 1.890257600914193e-06, "epoch": 1.1774439918533606, "percentage": 23.55, "elapsed_time": "0:21:37", "remaining_time": "1:10:13", "throughput": 10267.19, "total_tokens": 13326784}
{"current_steps": 13880, "total_steps": 58920, "loss": 0.1265, "lr": 1.8901226462012126e-06, "epoch": 1.177868295994569, "percentage": 23.56, "elapsed_time": "0:21:38", "remaining_time": "1:10:13", "throughput": 10267.59, "total_tokens": 13331136}
{"current_steps": 13885, "total_steps": 58920, "loss": 0.0177, "lr": 1.8899876133831833e-06, "epoch": 1.1782926001357774, "percentage": 23.57, "elapsed_time": "0:21:38", "remaining_time": "1:10:12", "throughput": 10268.31, "total_tokens": 13336000}
{"current_steps": 13890, "total_steps": 58920, "loss": 0.0682, "lr": 1.8898525024719544e-06, "epoch": 1.1787169042769858, "percentage": 23.57, "elapsed_time": "0:21:39", "remaining_time": "1:10:11", "throughput": 10268.59, "total_tokens": 13340160}
{"current_steps": 13895, "total_steps": 58920, "loss": 0.0605, "lr": 1.8897173134793814e-06, "epoch": 1.1791412084181943, "percentage": 23.58, "elapsed_time": "0:21:39", "remaining_time": "1:10:10", "throughput": 10269.03, "total_tokens": 13344576}
{"current_steps": 13900, "total_steps": 58920, "loss": 0.0648, "lr": 1.8895820464173261e-06, "epoch": 1.1795655125594027, "percentage": 23.59, "elapsed_time": "0:21:39", "remaining_time": "1:10:10", "throughput": 10269.57, "total_tokens": 13349184}
{"current_steps": 13905, "total_steps": 58920, "loss": 0.051, "lr": 1.8894467012976584e-06, "epoch": 1.179989816700611, "percentage": 23.6, "elapsed_time": "0:21:40", "remaining_time": "1:10:09", "throughput": 10270.71, "total_tokens": 13354816}
{"current_steps": 13910, "total_steps": 58920, "loss": 0.0007, "lr": 1.8893112781322537e-06, "epoch": 1.1804141208418195, "percentage": 23.61, "elapsed_time": "0:21:40", "remaining_time": "1:10:08", "throughput": 10271.03, "total_tokens": 13359040}
{"current_steps": 13915, "total_steps": 58920, "loss": 0.0841, "lr": 1.8891757769329952e-06, "epoch": 1.180838424983028, "percentage": 23.62, "elapsed_time": "0:21:41", "remaining_time": "1:10:07", "throughput": 10271.46, "total_tokens": 13363456}
{"current_steps": 13920, "total_steps": 58920, "loss": 0.0113, "lr": 1.8890401977117726e-06, "epoch": 1.1812627291242364, "percentage": 23.63, "elapsed_time": "0:21:41", "remaining_time": "1:10:07", "throughput": 10272.59, "total_tokens": 13369088}
{"current_steps": 13925, "total_steps": 58920, "loss": 0.0701, "lr": 1.8889045404804828e-06, "epoch": 1.1816870332654448, "percentage": 23.63, "elapsed_time": "0:21:41", "remaining_time": "1:10:06", "throughput": 10273.81, "total_tokens": 13374912}
{"current_steps": 13930, "total_steps": 58920, "loss": 0.045, "lr": 1.8887688052510289e-06, "epoch": 1.1821113374066532, "percentage": 23.64, "elapsed_time": "0:21:42", "remaining_time": "1:10:05", "throughput": 10274.19, "total_tokens": 13379200}
{"current_steps": 13935, "total_steps": 58920, "loss": 0.0916, "lr": 1.8886329920353213e-06, "epoch": 1.1825356415478616, "percentage": 23.65, "elapsed_time": "0:21:42", "remaining_time": "1:10:05", "throughput": 10274.8, "total_tokens": 13383936}
{"current_steps": 13940, "total_steps": 58920, "loss": 0.1202, "lr": 1.8884971008452765e-06, "epoch": 1.18295994568907, "percentage": 23.66, "elapsed_time": "0:21:42", "remaining_time": "1:10:04", "throughput": 10275.57, "total_tokens": 13388928}
{"current_steps": 13945, "total_steps": 58920, "loss": 0.0867, "lr": 1.8883611316928195e-06, "epoch": 1.1833842498302785, "percentage": 23.67, "elapsed_time": "0:21:43", "remaining_time": "1:10:03", "throughput": 10276.45, "total_tokens": 13394048}
{"current_steps": 13950, "total_steps": 58920, "loss": 0.0014, "lr": 1.8882250845898806e-06, "epoch": 1.1838085539714869, "percentage": 23.68, "elapsed_time": "0:21:43", "remaining_time": "1:10:02", "throughput": 10276.99, "total_tokens": 13398656}
{"current_steps": 13955, "total_steps": 58920, "loss": 0.0501, "lr": 1.8880889595483973e-06, "epoch": 1.1842328581126953, "percentage": 23.68, "elapsed_time": "0:21:44", "remaining_time": "1:10:02", "throughput": 10277.49, "total_tokens": 13403200}
{"current_steps": 13960, "total_steps": 58920, "loss": 0.0041, "lr": 1.8879527565803142e-06, "epoch": 1.1846571622539037, "percentage": 23.69, "elapsed_time": "0:21:44", "remaining_time": "1:10:01", "throughput": 10277.85, "total_tokens": 13407488}
{"current_steps": 13965, "total_steps": 58920, "loss": 0.0236, "lr": 1.8878164756975828e-06, "epoch": 1.1850814663951121, "percentage": 23.7, "elapsed_time": "0:21:44", "remaining_time": "1:10:00", "throughput": 10278.69, "total_tokens": 13412544}
{"current_steps": 13970, "total_steps": 58920, "loss": 0.0433, "lr": 1.8876801169121607e-06, "epoch": 1.1855057705363206, "percentage": 23.71, "elapsed_time": "0:21:45", "remaining_time": "1:09:59", "throughput": 10279.21, "total_tokens": 13417088}
{"current_steps": 13975, "total_steps": 58920, "loss": 0.0519, "lr": 1.8875436802360139e-06, "epoch": 1.1859300746775288, "percentage": 23.72, "elapsed_time": "0:21:45", "remaining_time": "1:09:59", "throughput": 10279.71, "total_tokens": 13421632}
{"current_steps": 13980, "total_steps": 58920, "loss": 0.0128, "lr": 1.8874071656811131e-06, "epoch": 1.1863543788187372, "percentage": 23.73, "elapsed_time": "0:21:46", "remaining_time": "1:09:58", "throughput": 10280.4, "total_tokens": 13426496}
{"current_steps": 13985, "total_steps": 58920, "loss": 0.0815, "lr": 1.8872705732594381e-06, "epoch": 1.1867786829599456, "percentage": 23.74, "elapsed_time": "0:21:46", "remaining_time": "1:09:57", "throughput": 10280.88, "total_tokens": 13430976}
{"current_steps": 13990, "total_steps": 58920, "loss": 0.0757, "lr": 1.8871339029829731e-06, "epoch": 1.187202987101154, "percentage": 23.74, "elapsed_time": "0:21:46", "remaining_time": "1:09:56", "throughput": 10281.57, "total_tokens": 13435840}
{"current_steps": 13995, "total_steps": 58920, "loss": 0.0345, "lr": 1.8869971548637116e-06, "epoch": 1.1876272912423624, "percentage": 23.75, "elapsed_time": "0:21:47", "remaining_time": "1:09:56", "throughput": 10282.42, "total_tokens": 13440960}
{"current_steps": 14000, "total_steps": 58920, "loss": 0.0231, "lr": 1.886860328913652e-06, "epoch": 1.1880515953835709, "percentage": 23.76, "elapsed_time": "0:21:47", "remaining_time": "1:09:55", "throughput": 10282.93, "total_tokens": 13445504}
{"current_steps": 14005, "total_steps": 58920, "loss": 0.0322, "lr": 1.8867234251448005e-06, "epoch": 1.1884758995247793, "percentage": 23.77, "elapsed_time": "0:21:47", "remaining_time": "1:09:54", "throughput": 10283.46, "total_tokens": 13450112}
{"current_steps": 14010, "total_steps": 58920, "loss": 0.018, "lr": 1.88658644356917e-06, "epoch": 1.1889002036659877, "percentage": 23.78, "elapsed_time": "0:21:48", "remaining_time": "1:09:53", "throughput": 10284.08, "total_tokens": 13454848}
{"current_steps": 14015, "total_steps": 58920, "loss": 0.1094, "lr": 1.88644938419878e-06, "epoch": 1.1893245078071961, "percentage": 23.79, "elapsed_time": "0:21:48", "remaining_time": "1:09:53", "throughput": 10284.5, "total_tokens": 13459264}
{"current_steps": 14020, "total_steps": 58920, "loss": 0.052, "lr": 1.8863122470456573e-06, "epoch": 1.1897488119484045, "percentage": 23.79, "elapsed_time": "0:21:49", "remaining_time": "1:09:52", "throughput": 10285.1, "total_tokens": 13463936}
{"current_steps": 14025, "total_steps": 58920, "loss": 0.061, "lr": 1.8861750321218348e-06, "epoch": 1.190173116089613, "percentage": 23.8, "elapsed_time": "0:21:49", "remaining_time": "1:09:51", "throughput": 10285.91, "total_tokens": 13468992}
{"current_steps": 14030, "total_steps": 58920, "loss": 0.0407, "lr": 1.8860377394393528e-06, "epoch": 1.1905974202308214, "percentage": 23.81, "elapsed_time": "0:21:49", "remaining_time": "1:09:51", "throughput": 10287.39, "total_tokens": 13475200}
{"current_steps": 14035, "total_steps": 58920, "loss": 0.039, "lr": 1.8859003690102582e-06, "epoch": 1.1910217243720298, "percentage": 23.82, "elapsed_time": "0:21:50", "remaining_time": "1:09:50", "throughput": 10288.18, "total_tokens": 13480256}
{"current_steps": 14040, "total_steps": 58920, "loss": 0.032, "lr": 1.8857629208466047e-06, "epoch": 1.1914460285132382, "percentage": 23.83, "elapsed_time": "0:21:50", "remaining_time": "1:09:49", "throughput": 10288.6, "total_tokens": 13484672}
{"current_steps": 14045, "total_steps": 58920, "loss": 0.0656, "lr": 1.8856253949604528e-06, "epoch": 1.1918703326544466, "percentage": 23.84, "elapsed_time": "0:21:51", "remaining_time": "1:09:48", "throughput": 10289.11, "total_tokens": 13489216}
{"current_steps": 14050, "total_steps": 58920, "loss": 0.004, "lr": 1.8854877913638702e-06, "epoch": 1.192294636795655, "percentage": 23.85, "elapsed_time": "0:21:51", "remaining_time": "1:09:48", "throughput": 10289.91, "total_tokens": 13494272}
{"current_steps": 14055, "total_steps": 58920, "loss": 0.001, "lr": 1.8853501100689312e-06, "epoch": 1.1927189409368635, "percentage": 23.85, "elapsed_time": "0:21:51", "remaining_time": "1:09:47", "throughput": 10290.33, "total_tokens": 13498688}
{"current_steps": 14060, "total_steps": 58920, "loss": 0.0978, "lr": 1.885212351087716e-06, "epoch": 1.193143245078072, "percentage": 23.86, "elapsed_time": "0:21:52", "remaining_time": "1:09:46", "throughput": 10290.77, "total_tokens": 13503104}
{"current_steps": 14065, "total_steps": 58920, "loss": 0.0286, "lr": 1.8850745144323134e-06, "epoch": 1.1935675492192803, "percentage": 23.87, "elapsed_time": "0:21:52", "remaining_time": "1:09:45", "throughput": 10291.28, "total_tokens": 13507648}
{"current_steps": 14070, "total_steps": 58920, "loss": 0.1366, "lr": 1.8849366001148174e-06, "epoch": 1.1939918533604887, "percentage": 23.88, "elapsed_time": "0:21:52", "remaining_time": "1:09:45", "throughput": 10291.85, "total_tokens": 13512256}
{"current_steps": 14075, "total_steps": 58920, "loss": 0.0239, "lr": 1.8847986081473301e-06, "epoch": 1.1944161575016972, "percentage": 23.89, "elapsed_time": "0:21:53", "remaining_time": "1:09:44", "throughput": 10292.52, "total_tokens": 13517120}
{"current_steps": 14080, "total_steps": 58920, "loss": 0.0467, "lr": 1.8846605385419596e-06, "epoch": 1.1948404616429056, "percentage": 23.9, "elapsed_time": "0:21:53", "remaining_time": "1:09:43", "throughput": 10293.15, "total_tokens": 13521920}
{"current_steps": 14085, "total_steps": 58920, "loss": 0.0774, "lr": 1.8845223913108206e-06, "epoch": 1.195264765784114, "percentage": 23.91, "elapsed_time": "0:21:54", "remaining_time": "1:09:42", "throughput": 10293.81, "total_tokens": 13526784}
{"current_steps": 14090, "total_steps": 58920, "loss": 0.0186, "lr": 1.8843841664660355e-06, "epoch": 1.1956890699253224, "percentage": 23.91, "elapsed_time": "0:21:54", "remaining_time": "1:09:42", "throughput": 10294.2, "total_tokens": 13531136}
{"current_steps": 14095, "total_steps": 58920, "loss": 0.0227, "lr": 1.8842458640197327e-06, "epoch": 1.1961133740665308, "percentage": 23.92, "elapsed_time": "0:21:54", "remaining_time": "1:09:41", "throughput": 10294.87, "total_tokens": 13535936}
{"current_steps": 14100, "total_steps": 58920, "loss": 0.0263, "lr": 1.884107483984048e-06, "epoch": 1.1965376782077393, "percentage": 23.93, "elapsed_time": "0:21:55", "remaining_time": "1:09:40", "throughput": 10295.58, "total_tokens": 13540800}
{"current_steps": 14105, "total_steps": 58920, "loss": 0.0701, "lr": 1.8839690263711236e-06, "epoch": 1.1969619823489477, "percentage": 23.94, "elapsed_time": "0:21:55", "remaining_time": "1:09:39", "throughput": 10296.56, "total_tokens": 13546176}
{"current_steps": 14110, "total_steps": 58920, "loss": 0.0018, "lr": 1.883830491193109e-06, "epoch": 1.197386286490156, "percentage": 23.95, "elapsed_time": "0:21:55", "remaining_time": "1:09:39", "throughput": 10297.15, "total_tokens": 13550912}
{"current_steps": 14115, "total_steps": 58920, "loss": 0.0062, "lr": 1.8836918784621592e-06, "epoch": 1.1978105906313645, "percentage": 23.96, "elapsed_time": "0:21:56", "remaining_time": "1:09:38", "throughput": 10297.62, "total_tokens": 13555392}
{"current_steps": 14120, "total_steps": 58920, "loss": 0.0322, "lr": 1.883553188190438e-06, "epoch": 1.198234894772573, "percentage": 23.96, "elapsed_time": "0:21:56", "remaining_time": "1:09:37", "throughput": 10298.1, "total_tokens": 13559936}
{"current_steps": 14125, "total_steps": 58920, "loss": 0.0472, "lr": 1.8834144203901148e-06, "epoch": 1.1986591989137814, "percentage": 23.97, "elapsed_time": "0:21:57", "remaining_time": "1:09:36", "throughput": 10298.4, "total_tokens": 13564160}
{"current_steps": 14130, "total_steps": 58920, "loss": 0.1145, "lr": 1.8832755750733654e-06, "epoch": 1.1990835030549898, "percentage": 23.98, "elapsed_time": "0:21:57", "remaining_time": "1:09:36", "throughput": 10298.88, "total_tokens": 13568704}
{"current_steps": 14135, "total_steps": 58920, "loss": 0.0889, "lr": 1.8831366522523732e-06, "epoch": 1.1995078071961982, "percentage": 23.99, "elapsed_time": "0:21:57", "remaining_time": "1:09:35", "throughput": 10300.13, "total_tokens": 13574592}
{"current_steps": 14140, "total_steps": 58920, "loss": 0.0602, "lr": 1.8829976519393287e-06, "epoch": 1.1999321113374066, "percentage": 24.0, "elapsed_time": "0:21:58", "remaining_time": "1:09:34", "throughput": 10301.06, "total_tokens": 13579840}
{"current_steps": 14145, "total_steps": 58920, "loss": 0.0222, "lr": 1.8828585741464281e-06, "epoch": 1.200356415478615, "percentage": 24.01, "elapsed_time": "0:21:58", "remaining_time": "1:09:34", "throughput": 10301.67, "total_tokens": 13584576}
{"current_steps": 14150, "total_steps": 58920, "loss": 0.0809, "lr": 1.8827194188858755e-06, "epoch": 1.2007807196198235, "percentage": 24.02, "elapsed_time": "0:21:59", "remaining_time": "1:09:33", "throughput": 10302.27, "total_tokens": 13589312}
{"current_steps": 14155, "total_steps": 58920, "loss": 0.0008, "lr": 1.8825801861698806e-06, "epoch": 1.2012050237610319, "percentage": 24.02, "elapsed_time": "0:21:59", "remaining_time": "1:09:32", "throughput": 10302.6, "total_tokens": 13593600}
{"current_steps": 14160, "total_steps": 58920, "loss": 0.0802, "lr": 1.8824408760106612e-06, "epoch": 1.2016293279022403, "percentage": 24.03, "elapsed_time": "0:21:59", "remaining_time": "1:09:32", "throughput": 10303.54, "total_tokens": 13598912}
{"current_steps": 14165, "total_steps": 58920, "loss": 0.0289, "lr": 1.8823014884204407e-06, "epoch": 1.2020536320434487, "percentage": 24.04, "elapsed_time": "0:22:00", "remaining_time": "1:09:31", "throughput": 10304.04, "total_tokens": 13603456}
{"current_steps": 14170, "total_steps": 58920, "loss": 0.0641, "lr": 1.8821620234114502e-06, "epoch": 1.2024779361846571, "percentage": 24.05, "elapsed_time": "0:22:00", "remaining_time": "1:09:30", "throughput": 10304.87, "total_tokens": 13608512}
{"current_steps": 14175, "total_steps": 58920, "loss": 0.0135, "lr": 1.8820224809959271e-06, "epoch": 1.2029022403258656, "percentage": 24.06, "elapsed_time": "0:22:00", "remaining_time": "1:09:29", "throughput": 10305.72, "total_tokens": 13613696}
{"current_steps": 14180, "total_steps": 58920, "loss": 0.0126, "lr": 1.8818828611861157e-06, "epoch": 1.203326544467074, "percentage": 24.07, "elapsed_time": "0:22:01", "remaining_time": "1:09:29", "throughput": 10306.27, "total_tokens": 13618304}
{"current_steps": 14185, "total_steps": 58920, "loss": 0.0253, "lr": 1.8817431639942675e-06, "epoch": 1.2037508486082824, "percentage": 24.08, "elapsed_time": "0:22:01", "remaining_time": "1:09:28", "throughput": 10306.97, "total_tokens": 13623168}
{"current_steps": 14190, "total_steps": 58920, "loss": 0.0468, "lr": 1.8816033894326403e-06, "epoch": 1.2041751527494908, "percentage": 24.08, "elapsed_time": "0:22:02", "remaining_time": "1:09:27", "throughput": 10307.65, "total_tokens": 13628032}
{"current_steps": 14195, "total_steps": 58920, "loss": 0.0253, "lr": 1.8814635375134986e-06, "epoch": 1.2045994568906992, "percentage": 24.09, "elapsed_time": "0:22:02", "remaining_time": "1:09:26", "throughput": 10308.21, "total_tokens": 13632704}
{"current_steps": 14200, "total_steps": 58920, "loss": 0.0573, "lr": 1.8813236082491136e-06, "epoch": 1.2050237610319077, "percentage": 24.1, "elapsed_time": "0:22:02", "remaining_time": "1:09:26", "throughput": 10308.63, "total_tokens": 13637120}
{"current_steps": 14205, "total_steps": 58920, "loss": 0.0314, "lr": 1.8811836016517643e-06, "epoch": 1.205448065173116, "percentage": 24.11, "elapsed_time": "0:22:03", "remaining_time": "1:09:25", "throughput": 10309.01, "total_tokens": 13641472}
{"current_steps": 14210, "total_steps": 58920, "loss": 0.0012, "lr": 1.8810435177337358e-06, "epoch": 1.2058723693143245, "percentage": 24.12, "elapsed_time": "0:22:03", "remaining_time": "1:09:24", "throughput": 10310.59, "total_tokens": 13647936}
{"current_steps": 14215, "total_steps": 58920, "loss": 0.0013, "lr": 1.8809033565073191e-06, "epoch": 1.206296673455533, "percentage": 24.13, "elapsed_time": "0:22:04", "remaining_time": "1:09:24", "throughput": 10311.28, "total_tokens": 13652800}
{"current_steps": 14220, "total_steps": 58920, "loss": 0.0311, "lr": 1.8807631179848136e-06, "epoch": 1.2067209775967414, "percentage": 24.13, "elapsed_time": "0:22:04", "remaining_time": "1:09:23", "throughput": 10311.8, "total_tokens": 13657344}
{"current_steps": 14225, "total_steps": 58920, "loss": 0.0109, "lr": 1.8806228021785244e-06, "epoch": 1.2071452817379498, "percentage": 24.14, "elapsed_time": "0:22:04", "remaining_time": "1:09:22", "throughput": 10312.61, "total_tokens": 13662400}
{"current_steps": 14230, "total_steps": 58920, "loss": 0.0796, "lr": 1.8804824091007637e-06, "epoch": 1.2075695858791582, "percentage": 24.15, "elapsed_time": "0:22:05", "remaining_time": "1:09:21", "throughput": 10313.17, "total_tokens": 13667072}
{"current_steps": 14235, "total_steps": 58920, "loss": 0.0006, "lr": 1.8803419387638506e-06, "epoch": 1.2079938900203666, "percentage": 24.16, "elapsed_time": "0:22:05", "remaining_time": "1:09:21", "throughput": 10313.58, "total_tokens": 13671488}
{"current_steps": 14240, "total_steps": 58920, "loss": 0.075, "lr": 1.8802013911801108e-06, "epoch": 1.208418194161575, "percentage": 24.17, "elapsed_time": "0:22:05", "remaining_time": "1:09:20", "throughput": 10314.23, "total_tokens": 13676288}
{"current_steps": 14245, "total_steps": 58920, "loss": 0.0003, "lr": 1.8800607663618772e-06, "epoch": 1.2088424983027835, "percentage": 24.18, "elapsed_time": "0:22:06", "remaining_time": "1:09:19", "throughput": 10314.94, "total_tokens": 13681216}
{"current_steps": 14250, "total_steps": 58920, "loss": 0.1243, "lr": 1.8799200643214887e-06, "epoch": 1.2092668024439919, "percentage": 24.19, "elapsed_time": "0:22:06", "remaining_time": "1:09:18", "throughput": 10315.5, "total_tokens": 13685888}
{"current_steps": 14255, "total_steps": 58920, "loss": 0.0157, "lr": 1.8797792850712913e-06, "epoch": 1.2096911065852003, "percentage": 24.19, "elapsed_time": "0:22:07", "remaining_time": "1:09:18", "throughput": 10316.43, "total_tokens": 13691200}
{"current_steps": 14260, "total_steps": 58920, "loss": 0.0509, "lr": 1.8796384286236382e-06, "epoch": 1.2101154107264087, "percentage": 24.2, "elapsed_time": "0:22:07", "remaining_time": "1:09:17", "throughput": 10316.89, "total_tokens": 13695680}
{"current_steps": 14265, "total_steps": 58920, "loss": 0.0491, "lr": 1.8794974949908888e-06, "epoch": 1.2105397148676171, "percentage": 24.21, "elapsed_time": "0:22:07", "remaining_time": "1:09:16", "throughput": 10317.3, "total_tokens": 13700096}
{"current_steps": 14270, "total_steps": 58920, "loss": 0.0207, "lr": 1.8793564841854097e-06, "epoch": 1.2109640190088256, "percentage": 24.22, "elapsed_time": "0:22:08", "remaining_time": "1:09:16", "throughput": 10317.63, "total_tokens": 13704384}
{"current_steps": 14275, "total_steps": 58920, "loss": 0.1513, "lr": 1.879215396219574e-06, "epoch": 1.211388323150034, "percentage": 24.23, "elapsed_time": "0:22:08", "remaining_time": "1:09:15", "throughput": 10318.36, "total_tokens": 13709312}
{"current_steps": 14280, "total_steps": 58920, "loss": 0.0596, "lr": 1.8790742311057618e-06, "epoch": 1.2118126272912424, "percentage": 24.24, "elapsed_time": "0:22:09", "remaining_time": "1:09:14", "throughput": 10318.81, "total_tokens": 13713792}
{"current_steps": 14285, "total_steps": 58920, "loss": 0.0014, "lr": 1.8789329888563591e-06, "epoch": 1.2122369314324508, "percentage": 24.24, "elapsed_time": "0:22:09", "remaining_time": "1:09:13", "throughput": 10319.29, "total_tokens": 13718336}
{"current_steps": 14290, "total_steps": 58920, "loss": 0.0436, "lr": 1.878791669483761e-06, "epoch": 1.2126612355736592, "percentage": 24.25, "elapsed_time": "0:22:09", "remaining_time": "1:09:13", "throughput": 10319.96, "total_tokens": 13723136}
{"current_steps": 14295, "total_steps": 58920, "loss": 0.0174, "lr": 1.8786502730003662e-06, "epoch": 1.2130855397148677, "percentage": 24.26, "elapsed_time": "0:22:10", "remaining_time": "1:09:12", "throughput": 10320.63, "total_tokens": 13728000}
{"current_steps": 14300, "total_steps": 58920, "loss": 0.0554, "lr": 1.878508799418582e-06, "epoch": 1.213509843856076, "percentage": 24.27, "elapsed_time": "0:22:10", "remaining_time": "1:09:11", "throughput": 10321.09, "total_tokens": 13732480}
{"current_steps": 14305, "total_steps": 58920, "loss": 0.1227, "lr": 1.8783672487508228e-06, "epoch": 1.2139341479972845, "percentage": 24.28, "elapsed_time": "0:22:10", "remaining_time": "1:09:10", "throughput": 10321.77, "total_tokens": 13737344}
{"current_steps": 14310, "total_steps": 58920, "loss": 0.0626, "lr": 1.8782256210095092e-06, "epoch": 1.214358452138493, "percentage": 24.29, "elapsed_time": "0:22:11", "remaining_time": "1:09:10", "throughput": 10322.25, "total_tokens": 13741888}
{"current_steps": 14315, "total_steps": 58920, "loss": 0.0377, "lr": 1.8780839162070675e-06, "epoch": 1.2147827562797013, "percentage": 24.3, "elapsed_time": "0:22:11", "remaining_time": "1:09:09", "throughput": 10322.79, "total_tokens": 13746496}
{"current_steps": 14320, "total_steps": 58920, "loss": 0.0158, "lr": 1.877942134355933e-06, "epoch": 1.2152070604209098, "percentage": 24.3, "elapsed_time": "0:22:12", "remaining_time": "1:09:08", "throughput": 10323.45, "total_tokens": 13751296}
{"current_steps": 14325, "total_steps": 58920, "loss": 0.0339, "lr": 1.877800275468546e-06, "epoch": 1.2156313645621182, "percentage": 24.31, "elapsed_time": "0:22:12", "remaining_time": "1:09:07", "throughput": 10323.87, "total_tokens": 13755712}
{"current_steps": 14330, "total_steps": 58920, "loss": 0.0241, "lr": 1.877658339557354e-06, "epoch": 1.2160556687033266, "percentage": 24.32, "elapsed_time": "0:22:12", "remaining_time": "1:09:07", "throughput": 10324.6, "total_tokens": 13760704}
{"current_steps": 14335, "total_steps": 58920, "loss": 0.0224, "lr": 1.8775163266348113e-06, "epoch": 1.216479972844535, "percentage": 24.33, "elapsed_time": "0:22:13", "remaining_time": "1:09:06", "throughput": 10325.47, "total_tokens": 13765888}
{"current_steps": 14340, "total_steps": 58920, "loss": 0.0218, "lr": 1.8773742367133793e-06, "epoch": 1.2169042769857434, "percentage": 24.34, "elapsed_time": "0:22:13", "remaining_time": "1:09:05", "throughput": 10326.14, "total_tokens": 13770752}
{"current_steps": 14345, "total_steps": 58920, "loss": 0.0304, "lr": 1.877232069805526e-06, "epoch": 1.2173285811269519, "percentage": 24.35, "elapsed_time": "0:22:13", "remaining_time": "1:09:05", "throughput": 10326.88, "total_tokens": 13775744}
{"current_steps": 14350, "total_steps": 58920, "loss": 0.0564, "lr": 1.8770898259237253e-06, "epoch": 1.2177528852681603, "percentage": 24.36, "elapsed_time": "0:22:14", "remaining_time": "1:09:04", "throughput": 10327.39, "total_tokens": 13780352}
{"current_steps": 14355, "total_steps": 58920, "loss": 0.0452, "lr": 1.8769475050804595e-06, "epoch": 1.2181771894093687, "percentage": 24.36, "elapsed_time": "0:22:14", "remaining_time": "1:09:03", "throughput": 10328.02, "total_tokens": 13785088}
{"current_steps": 14360, "total_steps": 58920, "loss": 0.0573, "lr": 1.8768051072882163e-06, "epoch": 1.2186014935505771, "percentage": 24.37, "elapsed_time": "0:22:15", "remaining_time": "1:09:02", "throughput": 10328.97, "total_tokens": 13790400}
{"current_steps": 14365, "total_steps": 58920, "loss": 0.0611, "lr": 1.8766626325594906e-06, "epoch": 1.2190257976917855, "percentage": 24.38, "elapsed_time": "0:22:15", "remaining_time": "1:09:02", "throughput": 10329.56, "total_tokens": 13795136}
{"current_steps": 14370, "total_steps": 58920, "loss": 0.0503, "lr": 1.876520080906784e-06, "epoch": 1.219450101832994, "percentage": 24.39, "elapsed_time": "0:22:15", "remaining_time": "1:09:01", "throughput": 10330.09, "total_tokens": 13799744}
{"current_steps": 14375, "total_steps": 58920, "loss": 0.0195, "lr": 1.876377452342605e-06, "epoch": 1.2198744059742024, "percentage": 24.4, "elapsed_time": "0:22:16", "remaining_time": "1:09:00", "throughput": 10330.82, "total_tokens": 13804736}
{"current_steps": 14380, "total_steps": 58920, "loss": 0.0243, "lr": 1.8762347468794686e-06, "epoch": 1.2202987101154108, "percentage": 24.41, "elapsed_time": "0:22:16", "remaining_time": "1:09:00", "throughput": 10331.36, "total_tokens": 13809344}
{"current_steps": 14385, "total_steps": 58920, "loss": 0.0381, "lr": 1.876091964529897e-06, "epoch": 1.2207230142566192, "percentage": 24.41, "elapsed_time": "0:22:17", "remaining_time": "1:08:59", "throughput": 10332.13, "total_tokens": 13814400}
{"current_steps": 14390, "total_steps": 58920, "loss": 0.0351, "lr": 1.8759491053064185e-06, "epoch": 1.2211473183978276, "percentage": 24.42, "elapsed_time": "0:22:17", "remaining_time": "1:08:58", "throughput": 10332.66, "total_tokens": 13819008}
{"current_steps": 14395, "total_steps": 58920, "loss": 0.1396, "lr": 1.8758061692215685e-06, "epoch": 1.221571622539036, "percentage": 24.43, "elapsed_time": "0:22:17", "remaining_time": "1:08:57", "throughput": 10333.27, "total_tokens": 13823744}
{"current_steps": 14400, "total_steps": 58920, "loss": 0.0012, "lr": 1.8756631562878894e-06, "epoch": 1.2219959266802445, "percentage": 24.44, "elapsed_time": "0:22:18", "remaining_time": "1:08:57", "throughput": 10334.38, "total_tokens": 13829376}
{"current_steps": 14405, "total_steps": 58920, "loss": 0.0345, "lr": 1.87552006651793e-06, "epoch": 1.222420230821453, "percentage": 24.45, "elapsed_time": "0:22:18", "remaining_time": "1:08:56", "throughput": 10335.1, "total_tokens": 13834368}
{"current_steps": 14410, "total_steps": 58920, "loss": 0.0348, "lr": 1.8753768999242455e-06, "epoch": 1.2228445349626613, "percentage": 24.46, "elapsed_time": "0:22:18", "remaining_time": "1:08:55", "throughput": 10335.65, "total_tokens": 13839040}
{"current_steps": 14415, "total_steps": 58920, "loss": 0.0238, "lr": 1.8752336565193989e-06, "epoch": 1.2232688391038697, "percentage": 24.47, "elapsed_time": "0:22:19", "remaining_time": "1:08:55", "throughput": 10335.99, "total_tokens": 13843392}
{"current_steps": 14420, "total_steps": 58920, "loss": 0.0407, "lr": 1.875090336315959e-06, "epoch": 1.2236931432450782, "percentage": 24.47, "elapsed_time": "0:22:19", "remaining_time": "1:08:54", "throughput": 10336.45, "total_tokens": 13847872}
{"current_steps": 14425, "total_steps": 58920, "loss": 0.0706, "lr": 1.8749469393265013e-06, "epoch": 1.2241174473862866, "percentage": 24.48, "elapsed_time": "0:22:20", "remaining_time": "1:08:53", "throughput": 10337.13, "total_tokens": 13852736}
{"current_steps": 14430, "total_steps": 58920, "loss": 0.0437, "lr": 1.874803465563609e-06, "epoch": 1.224541751527495, "percentage": 24.49, "elapsed_time": "0:22:20", "remaining_time": "1:08:52", "throughput": 10337.76, "total_tokens": 13857536}
{"current_steps": 14435, "total_steps": 58920, "loss": 0.0008, "lr": 1.8746599150398707e-06, "epoch": 1.2249660556687032, "percentage": 24.5, "elapsed_time": "0:22:20", "remaining_time": "1:08:52", "throughput": 10338.42, "total_tokens": 13862400}
{"current_steps": 14440, "total_steps": 58920, "loss": 0.0752, "lr": 1.874516287767883e-06, "epoch": 1.2253903598099116, "percentage": 24.51, "elapsed_time": "0:22:21", "remaining_time": "1:08:51", "throughput": 10339.08, "total_tokens": 13867264}
{"current_steps": 14445, "total_steps": 58920, "loss": 0.0014, "lr": 1.8743725837602482e-06, "epoch": 1.22581466395112, "percentage": 24.52, "elapsed_time": "0:22:21", "remaining_time": "1:08:50", "throughput": 10339.59, "total_tokens": 13871808}
{"current_steps": 14450, "total_steps": 58920, "loss": 0.0507, "lr": 1.8742288030295765e-06, "epoch": 1.2262389680923285, "percentage": 24.52, "elapsed_time": "0:22:21", "remaining_time": "1:08:50", "throughput": 10339.94, "total_tokens": 13876160}
{"current_steps": 14455, "total_steps": 58920, "loss": 0.0668, "lr": 1.8740849455884832e-06, "epoch": 1.2266632722335369, "percentage": 24.53, "elapsed_time": "0:22:22", "remaining_time": "1:08:49", "throughput": 10340.79, "total_tokens": 13881280}
{"current_steps": 14460, "total_steps": 58920, "loss": 0.0466, "lr": 1.8739410114495924e-06, "epoch": 1.2270875763747453, "percentage": 24.54, "elapsed_time": "0:22:22", "remaining_time": "1:08:48", "throughput": 10341.08, "total_tokens": 13885504}
{"current_steps": 14465, "total_steps": 58920, "loss": 0.0357, "lr": 1.8737970006255329e-06, "epoch": 1.2275118805159537, "percentage": 24.55, "elapsed_time": "0:22:23", "remaining_time": "1:08:47", "throughput": 10341.36, "total_tokens": 13889728}
{"current_steps": 14470, "total_steps": 58920, "loss": 0.0233, "lr": 1.8736529131289414e-06, "epoch": 1.2279361846571621, "percentage": 24.56, "elapsed_time": "0:22:23", "remaining_time": "1:08:47", "throughput": 10341.74, "total_tokens": 13894080}
{"current_steps": 14475, "total_steps": 58920, "loss": 0.0469, "lr": 1.873508748972461e-06, "epoch": 1.2283604887983706, "percentage": 24.57, "elapsed_time": "0:22:23", "remaining_time": "1:08:46", "throughput": 10342.1, "total_tokens": 13898432}
{"current_steps": 14480, "total_steps": 58920, "loss": 0.0013, "lr": 1.873364508168742e-06, "epoch": 1.228784792939579, "percentage": 24.58, "elapsed_time": "0:22:24", "remaining_time": "1:08:45", "throughput": 10342.72, "total_tokens": 13903168}
{"current_steps": 14485, "total_steps": 58920, "loss": 0.0244, "lr": 1.8732201907304404e-06, "epoch": 1.2292090970807874, "percentage": 24.58, "elapsed_time": "0:22:24", "remaining_time": "1:08:44", "throughput": 10343.59, "total_tokens": 13908416}
{"current_steps": 14490, "total_steps": 58920, "loss": 0.0946, "lr": 1.8730757966702199e-06, "epoch": 1.2296334012219958, "percentage": 24.59, "elapsed_time": "0:22:25", "remaining_time": "1:08:44", "throughput": 10343.97, "total_tokens": 13912768}
{"current_steps": 14495, "total_steps": 58920, "loss": 0.035, "lr": 1.8729313260007505e-06, "epoch": 1.2300577053632042, "percentage": 24.6, "elapsed_time": "0:22:25", "remaining_time": "1:08:43", "throughput": 10344.4, "total_tokens": 13917248}
{"current_steps": 14500, "total_steps": 58920, "loss": 0.0251, "lr": 1.8727867787347087e-06, "epoch": 1.2304820095044127, "percentage": 24.61, "elapsed_time": "0:22:25", "remaining_time": "1:08:42", "throughput": 10345.17, "total_tokens": 13922304}
{"current_steps": 14505, "total_steps": 58920, "loss": 0.032, "lr": 1.8726421548847785e-06, "epoch": 1.230906313645621, "percentage": 24.62, "elapsed_time": "0:22:26", "remaining_time": "1:08:42", "throughput": 10345.92, "total_tokens": 13927296}
{"current_steps": 14510, "total_steps": 58920, "loss": 0.0313, "lr": 1.87249745446365e-06, "epoch": 1.2313306177868295, "percentage": 24.63, "elapsed_time": "0:22:26", "remaining_time": "1:08:41", "throughput": 10346.53, "total_tokens": 13932032}
{"current_steps": 14515, "total_steps": 58920, "loss": 0.0202, "lr": 1.8723526774840196e-06, "epoch": 1.231754921928038, "percentage": 24.64, "elapsed_time": "0:22:26", "remaining_time": "1:08:40", "throughput": 10347.11, "total_tokens": 13936768}
{"current_steps": 14520, "total_steps": 58920, "loss": 0.0242, "lr": 1.8722078239585918e-06, "epoch": 1.2321792260692463, "percentage": 24.64, "elapsed_time": "0:22:27", "remaining_time": "1:08:39", "throughput": 10347.64, "total_tokens": 13941376}
{"current_steps": 14525, "total_steps": 58920, "loss": 0.0195, "lr": 1.8720628939000763e-06, "epoch": 1.2326035302104548, "percentage": 24.65, "elapsed_time": "0:22:27", "remaining_time": "1:08:39", "throughput": 10348.61, "total_tokens": 13946816}
{"current_steps": 14530, "total_steps": 58920, "loss": 0.032, "lr": 1.8719178873211905e-06, "epoch": 1.2330278343516632, "percentage": 24.66, "elapsed_time": "0:22:28", "remaining_time": "1:08:38", "throughput": 10349.36, "total_tokens": 13951808}
{"current_steps": 14535, "total_steps": 58920, "loss": 0.064, "lr": 1.871772804234658e-06, "epoch": 1.2334521384928716, "percentage": 24.67, "elapsed_time": "0:22:28", "remaining_time": "1:08:37", "throughput": 10349.59, "total_tokens": 13955904}
{"current_steps": 14540, "total_steps": 58920, "loss": 0.0652, "lr": 1.8716276446532095e-06, "epoch": 1.23387644263408, "percentage": 24.68, "elapsed_time": "0:22:28", "remaining_time": "1:08:37", "throughput": 10350.25, "total_tokens": 13960768}
{"current_steps": 14545, "total_steps": 58920, "loss": 0.0245, "lr": 1.8714824085895825e-06, "epoch": 1.2343007467752884, "percentage": 24.69, "elapsed_time": "0:22:29", "remaining_time": "1:08:36", "throughput": 10350.58, "total_tokens": 13965120}
{"current_steps": 14550, "total_steps": 58920, "loss": 0.0105, "lr": 1.8713370960565203e-06, "epoch": 1.2347250509164969, "percentage": 24.69, "elapsed_time": "0:22:29", "remaining_time": "1:08:35", "throughput": 10351.03, "total_tokens": 13969664}
{"current_steps": 14555, "total_steps": 58920, "loss": 0.025, "lr": 1.871191707066774e-06, "epoch": 1.2351493550577053, "percentage": 24.7, "elapsed_time": "0:22:29", "remaining_time": "1:08:34", "throughput": 10351.76, "total_tokens": 13974656}
{"current_steps": 14560, "total_steps": 58920, "loss": 0.0341, "lr": 1.8710462416331007e-06, "epoch": 1.2355736591989137, "percentage": 24.71, "elapsed_time": "0:22:30", "remaining_time": "1:08:34", "throughput": 10352.16, "total_tokens": 13979072}
{"current_steps": 14565, "total_steps": 58920, "loss": 0.0006, "lr": 1.8709006997682649e-06, "epoch": 1.2359979633401221, "percentage": 24.72, "elapsed_time": "0:22:30", "remaining_time": "1:08:33", "throughput": 10352.67, "total_tokens": 13983616}
{"current_steps": 14570, "total_steps": 58920, "loss": 0.0423, "lr": 1.8707550814850366e-06, "epoch": 1.2364222674813306, "percentage": 24.73, "elapsed_time": "0:22:31", "remaining_time": "1:08:32", "throughput": 10353.05, "total_tokens": 13988032}
{"current_steps": 14575, "total_steps": 58920, "loss": 0.0006, "lr": 1.8706093867961941e-06, "epoch": 1.236846571622539, "percentage": 24.74, "elapsed_time": "0:22:31", "remaining_time": "1:08:31", "throughput": 10353.7, "total_tokens": 13992896}
{"current_steps": 14580, "total_steps": 58920, "loss": 0.0475, "lr": 1.870463615714521e-06, "epoch": 1.2372708757637474, "percentage": 24.75, "elapsed_time": "0:22:31", "remaining_time": "1:08:31", "throughput": 10354.53, "total_tokens": 13998080}
{"current_steps": 14585, "total_steps": 58920, "loss": 0.034, "lr": 1.8703177682528084e-06, "epoch": 1.2376951799049558, "percentage": 24.75, "elapsed_time": "0:22:32", "remaining_time": "1:08:30", "throughput": 10354.91, "total_tokens": 14002496}
{"current_steps": 14590, "total_steps": 58920, "loss": 0.0072, "lr": 1.870171844423854e-06, "epoch": 1.2381194840461642, "percentage": 24.76, "elapsed_time": "0:22:32", "remaining_time": "1:08:29", "throughput": 10355.58, "total_tokens": 14007424}
{"current_steps": 14595, "total_steps": 58920, "loss": 0.0006, "lr": 1.870025844240462e-06, "epoch": 1.2385437881873727, "percentage": 24.77, "elapsed_time": "0:22:33", "remaining_time": "1:08:29", "throughput": 10356.26, "total_tokens": 14012352}
{"current_steps": 14600, "total_steps": 58920, "loss": 0.0308, "lr": 1.8698797677154437e-06, "epoch": 1.238968092328581, "percentage": 24.78, "elapsed_time": "0:22:33", "remaining_time": "1:08:28", "throughput": 10356.72, "total_tokens": 14016896}
{"current_steps": 14605, "total_steps": 58920, "loss": 0.0024, "lr": 1.8697336148616161e-06, "epoch": 1.2393923964697895, "percentage": 24.79, "elapsed_time": "0:22:33", "remaining_time": "1:08:27", "throughput": 10357.38, "total_tokens": 14021760}
{"current_steps": 14610, "total_steps": 58920, "loss": 0.0174, "lr": 1.869587385691804e-06, "epoch": 1.239816700610998, "percentage": 24.8, "elapsed_time": "0:22:34", "remaining_time": "1:08:27", "throughput": 10358.16, "total_tokens": 14026880}
{"current_steps": 14615, "total_steps": 58920, "loss": 0.0606, "lr": 1.8694410802188386e-06, "epoch": 1.2402410047522063, "percentage": 24.8, "elapsed_time": "0:22:34", "remaining_time": "1:08:26", "throughput": 10358.97, "total_tokens": 14032000}
{"current_steps": 14620, "total_steps": 58920, "loss": 0.1314, "lr": 1.8692946984555573e-06, "epoch": 1.2406653088934148, "percentage": 24.81, "elapsed_time": "0:22:34", "remaining_time": "1:08:25", "throughput": 10359.8, "total_tokens": 14037184}
{"current_steps": 14625, "total_steps": 58920, "loss": 0.0734, "lr": 1.8691482404148048e-06, "epoch": 1.2410896130346232, "percentage": 24.82, "elapsed_time": "0:22:35", "remaining_time": "1:08:24", "throughput": 10360.28, "total_tokens": 14041728}
{"current_steps": 14630, "total_steps": 58920, "loss": 0.0013, "lr": 1.8690017061094325e-06, "epoch": 1.2415139171758316, "percentage": 24.83, "elapsed_time": "0:22:35", "remaining_time": "1:08:24", "throughput": 10362.05, "total_tokens": 14048704}
{"current_steps": 14635, "total_steps": 58920, "loss": 0.0283, "lr": 1.868855095552298e-06, "epoch": 1.24193822131704, "percentage": 24.84, "elapsed_time": "0:22:36", "remaining_time": "1:08:23", "throughput": 10363.01, "total_tokens": 14054144}
{"current_steps": 14640, "total_steps": 58920, "loss": 0.0352, "lr": 1.8687084087562655e-06, "epoch": 1.2423625254582484, "percentage": 24.85, "elapsed_time": "0:22:36", "remaining_time": "1:08:23", "throughput": 10363.35, "total_tokens": 14058496}
{"current_steps": 14645, "total_steps": 58920, "loss": 0.0527, "lr": 1.8685616457342066e-06, "epoch": 1.2427868295994569, "percentage": 24.86, "elapsed_time": "0:22:36", "remaining_time": "1:08:22", "throughput": 10364.24, "total_tokens": 14063808}
{"current_steps": 14650, "total_steps": 58920, "loss": 0.0398, "lr": 1.8684148064989995e-06, "epoch": 1.2432111337406653, "percentage": 24.86, "elapsed_time": "0:22:37", "remaining_time": "1:08:21", "throughput": 10364.62, "total_tokens": 14068224}
{"current_steps": 14655, "total_steps": 58920, "loss": 0.0899, "lr": 1.8682678910635286e-06, "epoch": 1.2436354378818737, "percentage": 24.87, "elapsed_time": "0:22:37", "remaining_time": "1:08:20", "throughput": 10364.98, "total_tokens": 14072576}
{"current_steps": 14660, "total_steps": 58920, "loss": 0.0868, "lr": 1.8681208994406848e-06, "epoch": 1.2440597420230821, "percentage": 24.88, "elapsed_time": "0:22:38", "remaining_time": "1:08:20", "throughput": 10365.66, "total_tokens": 14077504}
{"current_steps": 14665, "total_steps": 58920, "loss": 0.0208, "lr": 1.8679738316433666e-06, "epoch": 1.2444840461642905, "percentage": 24.89, "elapsed_time": "0:22:38", "remaining_time": "1:08:19", "throughput": 10366.48, "total_tokens": 14082688}
{"current_steps": 14670, "total_steps": 58920, "loss": 0.0229, "lr": 1.8678266876844785e-06, "epoch": 1.244908350305499, "percentage": 24.9, "elapsed_time": "0:22:38", "remaining_time": "1:08:18", "throughput": 10366.89, "total_tokens": 14087168}
{"current_steps": 14675, "total_steps": 58920, "loss": 0.025, "lr": 1.8676794675769316e-06, "epoch": 1.2453326544467074, "percentage": 24.91, "elapsed_time": "0:22:39", "remaining_time": "1:08:18", "throughput": 10367.47, "total_tokens": 14091968}
{"current_steps": 14680, "total_steps": 58920, "loss": 0.0961, "lr": 1.8675321713336444e-06, "epoch": 1.2457569585879158, "percentage": 24.92, "elapsed_time": "0:22:39", "remaining_time": "1:08:17", "throughput": 10367.99, "total_tokens": 14096640}
{"current_steps": 14685, "total_steps": 58920, "loss": 0.0485, "lr": 1.8673847989675414e-06, "epoch": 1.2461812627291242, "percentage": 24.92, "elapsed_time": "0:22:40", "remaining_time": "1:08:16", "throughput": 10368.47, "total_tokens": 14101184}
{"current_steps": 14690, "total_steps": 58920, "loss": 0.0278, "lr": 1.867237350491554e-06, "epoch": 1.2466055668703326, "percentage": 24.93, "elapsed_time": "0:22:40", "remaining_time": "1:08:15", "throughput": 10368.85, "total_tokens": 14105600}
{"current_steps": 14695, "total_steps": 58920, "loss": 0.0674, "lr": 1.86708982591862e-06, "epoch": 1.247029871011541, "percentage": 24.94, "elapsed_time": "0:22:40", "remaining_time": "1:08:15", "throughput": 10369.2, "total_tokens": 14109952}
{"current_steps": 14700, "total_steps": 58920, "loss": 0.0541, "lr": 1.8669422252616847e-06, "epoch": 1.2474541751527495, "percentage": 24.95, "elapsed_time": "0:22:41", "remaining_time": "1:08:14", "throughput": 10369.6, "total_tokens": 14114432}
{"current_steps": 14705, "total_steps": 58920, "loss": 0.0818, "lr": 1.866794548533699e-06, "epoch": 1.247878479293958, "percentage": 24.96, "elapsed_time": "0:22:41", "remaining_time": "1:08:13", "throughput": 10370.11, "total_tokens": 14119040}
{"current_steps": 14710, "total_steps": 58920, "loss": 0.0497, "lr": 1.8666467957476212e-06, "epoch": 1.2483027834351663, "percentage": 24.97, "elapsed_time": "0:22:41", "remaining_time": "1:08:13", "throughput": 10370.56, "total_tokens": 14123584}
{"current_steps": 14715, "total_steps": 58920, "loss": 0.002, "lr": 1.8664989669164163e-06, "epoch": 1.2487270875763747, "percentage": 24.97, "elapsed_time": "0:22:42", "remaining_time": "1:08:12", "throughput": 10370.96, "total_tokens": 14128064}
{"current_steps": 14720, "total_steps": 58920, "loss": 0.039, "lr": 1.8663510620530551e-06, "epoch": 1.2491513917175832, "percentage": 24.98, "elapsed_time": "0:22:42", "remaining_time": "1:08:11", "throughput": 10371.64, "total_tokens": 14132992}
{"current_steps": 14725, "total_steps": 58920, "loss": 0.1179, "lr": 1.8662030811705165e-06, "epoch": 1.2495756958587916, "percentage": 24.99, "elapsed_time": "0:22:43", "remaining_time": "1:08:10", "throughput": 10372.25, "total_tokens": 14137792}
{"current_steps": 14730, "total_steps": 58920, "loss": 0.0299, "lr": 1.866055024281785e-06, "epoch": 1.25, "percentage": 25.0, "elapsed_time": "0:22:43", "remaining_time": "1:08:10", "throughput": 10372.96, "total_tokens": 14142784}
{"current_steps": 14730, "total_steps": 58920, "eval_loss": 0.07637283951044083, "epoch": 1.25, "percentage": 25.0, "elapsed_time": "0:22:59", "remaining_time": "1:08:59", "throughput": 10248.91, "total_tokens": 14142784}
{"current_steps": 14735, "total_steps": 58920, "loss": 0.0007, "lr": 1.865906891399852e-06, "epoch": 1.2504243041412084, "percentage": 25.01, "elapsed_time": "0:23:34", "remaining_time": "1:10:41", "throughput": 10002.37, "total_tokens": 14147904}
{"current_steps": 14740, "total_steps": 58920, "loss": 0.088, "lr": 1.8657586825377152e-06, "epoch": 1.2508486082824168, "percentage": 25.02, "elapsed_time": "0:23:34", "remaining_time": "1:10:40", "throughput": 10003.18, "total_tokens": 14152960}
{"current_steps": 14745, "total_steps": 58920, "loss": 0.0022, "lr": 1.8656103977083801e-06, "epoch": 1.2512729124236253, "percentage": 25.03, "elapsed_time": "0:23:35", "remaining_time": "1:10:39", "throughput": 10003.68, "total_tokens": 14157440}
{"current_steps": 14750, "total_steps": 58920, "loss": 0.0046, "lr": 1.8654620369248582e-06, "epoch": 1.2516972165648337, "percentage": 25.03, "elapsed_time": "0:23:35", "remaining_time": "1:10:39", "throughput": 10004.47, "total_tokens": 14162432}
{"current_steps": 14755, "total_steps": 58920, "loss": 0.034, "lr": 1.8653136002001668e-06, "epoch": 1.252121520706042, "percentage": 25.04, "elapsed_time": "0:23:35", "remaining_time": "1:10:38", "throughput": 10005.05, "total_tokens": 14167040}
{"current_steps": 14760, "total_steps": 58920, "loss": 0.0014, "lr": 1.8651650875473313e-06, "epoch": 1.2525458248472505, "percentage": 25.05, "elapsed_time": "0:23:36", "remaining_time": "1:10:37", "throughput": 10005.84, "total_tokens": 14172032}
{"current_steps": 14765, "total_steps": 58920, "loss": 0.0241, "lr": 1.8650164989793834e-06, "epoch": 1.252970128988459, "percentage": 25.06, "elapsed_time": "0:23:36", "remaining_time": "1:10:36", "throughput": 10006.38, "total_tokens": 14176576}
{"current_steps": 14770, "total_steps": 58920, "loss": 0.0527, "lr": 1.8648678345093604e-06, "epoch": 1.2533944331296674, "percentage": 25.07, "elapsed_time": "0:23:37", "remaining_time": "1:10:36", "throughput": 10006.84, "total_tokens": 14180992}
{"current_steps": 14775, "total_steps": 58920, "loss": 0.0035, "lr": 1.8647190941503074e-06, "epoch": 1.2538187372708758, "percentage": 25.08, "elapsed_time": "0:23:37", "remaining_time": "1:10:35", "throughput": 10007.39, "total_tokens": 14185536}
{"current_steps": 14780, "total_steps": 58920, "loss": 0.0348, "lr": 1.8645702779152765e-06, "epoch": 1.2542430414120842, "percentage": 25.08, "elapsed_time": "0:23:37", "remaining_time": "1:10:34", "throughput": 10007.97, "total_tokens": 14190208}
{"current_steps": 14785, "total_steps": 58920, "loss": 0.0421, "lr": 1.8644213858173248e-06, "epoch": 1.2546673455532926, "percentage": 25.09, "elapsed_time": "0:23:38", "remaining_time": "1:10:33", "throughput": 10008.46, "total_tokens": 14194688}
{"current_steps": 14790, "total_steps": 58920, "loss": 0.0341, "lr": 1.8642724178695177e-06, "epoch": 1.255091649694501, "percentage": 25.1, "elapsed_time": "0:23:38", "remaining_time": "1:10:32", "throughput": 10008.91, "total_tokens": 14199104}
{"current_steps": 14795, "total_steps": 58920, "loss": 0.0256, "lr": 1.8641233740849262e-06, "epoch": 1.2555159538357095, "percentage": 25.11, "elapsed_time": "0:23:39", "remaining_time": "1:10:32", "throughput": 10009.27, "total_tokens": 14203328}
{"current_steps": 14800, "total_steps": 58920, "loss": 0.0312, "lr": 1.8639742544766289e-06, "epoch": 1.2559402579769179, "percentage": 25.12, "elapsed_time": "0:23:39", "remaining_time": "1:10:31", "throughput": 10009.85, "total_tokens": 14207936}
{"current_steps": 14805, "total_steps": 58920, "loss": 0.0479, "lr": 1.8638250590577096e-06, "epoch": 1.2563645621181263, "percentage": 25.13, "elapsed_time": "0:23:39", "remaining_time": "1:10:30", "throughput": 10010.56, "total_tokens": 14212800}
{"current_steps": 14810, "total_steps": 58920, "loss": 0.0614, "lr": 1.8636757878412604e-06, "epoch": 1.2567888662593347, "percentage": 25.14, "elapsed_time": "0:23:40", "remaining_time": "1:10:29", "throughput": 10011.29, "total_tokens": 14217728}
{"current_steps": 14815, "total_steps": 58920, "loss": 0.0013, "lr": 1.8635264408403795e-06, "epoch": 1.2572131704005431, "percentage": 25.14, "elapsed_time": "0:23:40", "remaining_time": "1:10:29", "throughput": 10012.19, "total_tokens": 14222976}
{"current_steps": 14820, "total_steps": 58920, "loss": 0.0003, "lr": 1.8633770180681708e-06, "epoch": 1.2576374745417516, "percentage": 25.15, "elapsed_time": "0:23:40", "remaining_time": "1:10:28", "throughput": 10013.0, "total_tokens": 14228032}
{"current_steps": 14825, "total_steps": 58920, "loss": 0.0004, "lr": 1.8632275195377458e-06, "epoch": 1.25806177868296, "percentage": 25.16, "elapsed_time": "0:23:41", "remaining_time": "1:10:27", "throughput": 10013.31, "total_tokens": 14232192}
{"current_steps": 14830, "total_steps": 58920, "loss": 0.0616, "lr": 1.8630779452622227e-06, "epoch": 1.2584860828241684, "percentage": 25.17, "elapsed_time": "0:23:41", "remaining_time": "1:10:26", "throughput": 10014.11, "total_tokens": 14237248}
{"current_steps": 14835, "total_steps": 58920, "loss": 0.0371, "lr": 1.8629282952547266e-06, "epoch": 1.2589103869653768, "percentage": 25.18, "elapsed_time": "0:23:42", "remaining_time": "1:10:26", "throughput": 10015.2, "total_tokens": 14242816}
{"current_steps": 14840, "total_steps": 58920, "loss": 0.0468, "lr": 1.8627785695283875e-06, "epoch": 1.2593346911065852, "percentage": 25.19, "elapsed_time": "0:23:42", "remaining_time": "1:10:25", "throughput": 10015.76, "total_tokens": 14247424}
{"current_steps": 14845, "total_steps": 58920, "loss": 0.0094, "lr": 1.8626287680963442e-06, "epoch": 1.2597589952477937, "percentage": 25.2, "elapsed_time": "0:23:42", "remaining_time": "1:10:24", "throughput": 10016.4, "total_tokens": 14252160}
{"current_steps": 14850, "total_steps": 58920, "loss": 0.0411, "lr": 1.862478890971741e-06, "epoch": 1.260183299389002, "percentage": 25.2, "elapsed_time": "0:23:43", "remaining_time": "1:10:23", "throughput": 10017.13, "total_tokens": 14257088}
{"current_steps": 14855, "total_steps": 58920, "loss": 0.0227, "lr": 1.8623289381677291e-06, "epoch": 1.2606076035302105, "percentage": 25.21, "elapsed_time": "0:23:43", "remaining_time": "1:10:23", "throughput": 10017.52, "total_tokens": 14261376}
{"current_steps": 14860, "total_steps": 58920, "loss": 0.0415, "lr": 1.8621789096974662e-06, "epoch": 1.261031907671419, "percentage": 25.22, "elapsed_time": "0:23:44", "remaining_time": "1:10:22", "throughput": 10018.19, "total_tokens": 14266176}
{"current_steps": 14865, "total_steps": 58920, "loss": 0.0303, "lr": 1.8620288055741171e-06, "epoch": 1.2614562118126273, "percentage": 25.23, "elapsed_time": "0:23:44", "remaining_time": "1:10:21", "throughput": 10018.8, "total_tokens": 14270848}
{"current_steps": 14870, "total_steps": 58920, "loss": 0.0284, "lr": 1.8618786258108526e-06, "epoch": 1.2618805159538358, "percentage": 25.24, "elapsed_time": "0:23:44", "remaining_time": "1:10:20", "throughput": 10019.4, "total_tokens": 14275520}
{"current_steps": 14875, "total_steps": 58920, "loss": 0.0181, "lr": 1.8617283704208503e-06, "epoch": 1.2623048200950442, "percentage": 25.25, "elapsed_time": "0:23:45", "remaining_time": "1:10:19", "throughput": 10019.96, "total_tokens": 14280128}
{"current_steps": 14880, "total_steps": 58920, "loss": 0.0005, "lr": 1.8615780394172948e-06, "epoch": 1.2627291242362526, "percentage": 25.25, "elapsed_time": "0:23:45", "remaining_time": "1:10:19", "throughput": 10020.68, "total_tokens": 14285056}
{"current_steps": 14885, "total_steps": 58920, "loss": 0.0693, "lr": 1.861427632813377e-06, "epoch": 1.263153428377461, "percentage": 25.26, "elapsed_time": "0:23:45", "remaining_time": "1:10:18", "throughput": 10021.45, "total_tokens": 14290112}
{"current_steps": 14890, "total_steps": 58920, "loss": 0.055, "lr": 1.8612771506222948e-06, "epoch": 1.2635777325186694, "percentage": 25.27, "elapsed_time": "0:23:46", "remaining_time": "1:10:17", "throughput": 10022.24, "total_tokens": 14295104}
{"current_steps": 14895, "total_steps": 58920, "loss": 0.0273, "lr": 1.8611265928572526e-06, "epoch": 1.2640020366598779, "percentage": 25.28, "elapsed_time": "0:23:46", "remaining_time": "1:10:16", "throughput": 10022.92, "total_tokens": 14299968}
{"current_steps": 14900, "total_steps": 58920, "loss": 0.047, "lr": 1.8609759595314602e-06, "epoch": 1.2644263408010863, "percentage": 25.29, "elapsed_time": "0:23:47", "remaining_time": "1:10:16", "throughput": 10023.75, "total_tokens": 14305088}
{"current_steps": 14905, "total_steps": 58920, "loss": 0.1141, "lr": 1.8608252506581363e-06, "epoch": 1.2648506449422947, "percentage": 25.3, "elapsed_time": "0:23:47", "remaining_time": "1:10:15", "throughput": 10024.41, "total_tokens": 14309824}
{"current_steps": 14910, "total_steps": 58920, "loss": 0.0022, "lr": 1.8606744662505046e-06, "epoch": 1.2652749490835031, "percentage": 25.31, "elapsed_time": "0:23:47", "remaining_time": "1:10:14", "throughput": 10025.2, "total_tokens": 14314880}
{"current_steps": 14915, "total_steps": 58920, "loss": 0.0071, "lr": 1.860523606321796e-06, "epoch": 1.2656992532247116, "percentage": 25.31, "elapsed_time": "0:23:48", "remaining_time": "1:10:14", "throughput": 10026.49, "total_tokens": 14320896}
{"current_steps": 14920, "total_steps": 58920, "loss": 0.071, "lr": 1.8603726708852477e-06, "epoch": 1.26612355736592, "percentage": 25.32, "elapsed_time": "0:23:48", "remaining_time": "1:10:13", "throughput": 10027.17, "total_tokens": 14325760}
{"current_steps": 14925, "total_steps": 58920, "loss": 0.0637, "lr": 1.8602216599541042e-06, "epoch": 1.2665478615071284, "percentage": 25.33, "elapsed_time": "0:23:49", "remaining_time": "1:10:12", "throughput": 10027.7, "total_tokens": 14330304}
{"current_steps": 14930, "total_steps": 58920, "loss": 0.0395, "lr": 1.8600705735416154e-06, "epoch": 1.2669721656483368, "percentage": 25.34, "elapsed_time": "0:23:49", "remaining_time": "1:10:11", "throughput": 10028.34, "total_tokens": 14335040}
{"current_steps": 14935, "total_steps": 58920, "loss": 0.0163, "lr": 1.8599194116610393e-06, "epoch": 1.2673964697895452, "percentage": 25.35, "elapsed_time": "0:23:49", "remaining_time": "1:10:10", "throughput": 10028.81, "total_tokens": 14339456}
{"current_steps": 14940, "total_steps": 58920, "loss": 0.0424, "lr": 1.8597681743256394e-06, "epoch": 1.2678207739307537, "percentage": 25.36, "elapsed_time": "0:23:50", "remaining_time": "1:10:10", "throughput": 10029.3, "total_tokens": 14343936}
{"current_steps": 14945, "total_steps": 58920, "loss": 0.1043, "lr": 1.8596168615486868e-06, "epoch": 1.268245078071962, "percentage": 25.36, "elapsed_time": "0:23:50", "remaining_time": "1:10:09", "throughput": 10029.94, "total_tokens": 14348672}
{"current_steps": 14950, "total_steps": 58920, "loss": 0.0206, "lr": 1.8594654733434578e-06, "epoch": 1.2686693822131705, "percentage": 25.37, "elapsed_time": "0:23:50", "remaining_time": "1:10:08", "throughput": 10030.46, "total_tokens": 14353216}
{"current_steps": 14955, "total_steps": 58920, "loss": 0.0024, "lr": 1.8593140097232368e-06, "epoch": 1.269093686354379, "percentage": 25.38, "elapsed_time": "0:23:51", "remaining_time": "1:10:07", "throughput": 10031.21, "total_tokens": 14358144}
{"current_steps": 14960, "total_steps": 58920, "loss": 0.1274, "lr": 1.8591624707013138e-06, "epoch": 1.2695179904955873, "percentage": 25.39, "elapsed_time": "0:23:51", "remaining_time": "1:10:07", "throughput": 10031.71, "total_tokens": 14362688}
{"current_steps": 14965, "total_steps": 58920, "loss": 0.0055, "lr": 1.859010856290986e-06, "epoch": 1.2699422946367958, "percentage": 25.4, "elapsed_time": "0:23:52", "remaining_time": "1:10:06", "throughput": 10032.3, "total_tokens": 14367360}
{"current_steps": 14970, "total_steps": 58920, "loss": 0.0584, "lr": 1.8588591665055575e-06, "epoch": 1.2703665987780042, "percentage": 25.41, "elapsed_time": "0:23:52", "remaining_time": "1:10:05", "throughput": 10032.82, "total_tokens": 14371904}
{"current_steps": 14975, "total_steps": 58920, "loss": 0.0488, "lr": 1.8587074013583374e-06, "epoch": 1.2707909029192126, "percentage": 25.42, "elapsed_time": "0:23:52", "remaining_time": "1:10:04", "throughput": 10033.41, "total_tokens": 14376576}
{"current_steps": 14980, "total_steps": 58920, "loss": 0.0461, "lr": 1.8585555608626438e-06, "epoch": 1.271215207060421, "percentage": 25.42, "elapsed_time": "0:23:53", "remaining_time": "1:10:04", "throughput": 10034.11, "total_tokens": 14381440}
{"current_steps": 14985, "total_steps": 58920, "loss": 0.0342, "lr": 1.858403645031799e-06, "epoch": 1.2716395112016294, "percentage": 25.43, "elapsed_time": "0:23:53", "remaining_time": "1:10:03", "throughput": 10034.89, "total_tokens": 14386432}
{"current_steps": 14990, "total_steps": 58920, "loss": 0.0006, "lr": 1.8582516538791337e-06, "epoch": 1.2720638153428379, "percentage": 25.44, "elapsed_time": "0:23:54", "remaining_time": "1:10:02", "throughput": 10035.55, "total_tokens": 14391232}
{"current_steps": 14995, "total_steps": 58920, "loss": 0.0492, "lr": 1.8580995874179846e-06, "epoch": 1.2724881194840463, "percentage": 25.45, "elapsed_time": "0:23:54", "remaining_time": "1:10:01", "throughput": 10036.24, "total_tokens": 14396032}
{"current_steps": 15000, "total_steps": 58920, "loss": 0.0346, "lr": 1.8579474456616948e-06, "epoch": 1.2729124236252547, "percentage": 25.46, "elapsed_time": "0:23:54", "remaining_time": "1:10:01", "throughput": 10036.77, "total_tokens": 14400576}
{"current_steps": 15005, "total_steps": 58920, "loss": 0.0078, "lr": 1.8577952286236143e-06, "epoch": 1.2733367277664631, "percentage": 25.47, "elapsed_time": "0:23:55", "remaining_time": "1:10:00", "throughput": 10037.15, "total_tokens": 14404864}
{"current_steps": 15010, "total_steps": 58920, "loss": 0.0215, "lr": 1.8576429363170996e-06, "epoch": 1.2737610319076715, "percentage": 25.48, "elapsed_time": "0:23:55", "remaining_time": "1:09:59", "throughput": 10037.98, "total_tokens": 14409984}
{"current_steps": 15015, "total_steps": 58920, "loss": 0.0786, "lr": 1.8574905687555137e-06, "epoch": 1.27418533604888, "percentage": 25.48, "elapsed_time": "0:23:55", "remaining_time": "1:09:58", "throughput": 10038.51, "total_tokens": 14414528}
{"current_steps": 15020, "total_steps": 58920, "loss": 0.0397, "lr": 1.8573381259522263e-06, "epoch": 1.2746096401900884, "percentage": 25.49, "elapsed_time": "0:23:56", "remaining_time": "1:09:57", "throughput": 10039.17, "total_tokens": 14419328}
{"current_steps": 15025, "total_steps": 58920, "loss": 0.037, "lr": 1.8571856079206136e-06, "epoch": 1.2750339443312968, "percentage": 25.5, "elapsed_time": "0:23:56", "remaining_time": "1:09:57", "throughput": 10039.89, "total_tokens": 14424256}
{"current_steps": 15030, "total_steps": 58920, "loss": 0.091, "lr": 1.857033014674059e-06, "epoch": 1.2754582484725052, "percentage": 25.51, "elapsed_time": "0:23:57", "remaining_time": "1:09:56", "throughput": 10040.32, "total_tokens": 14428672}
{"current_steps": 15035, "total_steps": 58920, "loss": 0.0671, "lr": 1.8568803462259516e-06, "epoch": 1.2758825526137136, "percentage": 25.52, "elapsed_time": "0:23:57", "remaining_time": "1:09:55", "throughput": 10041.07, "total_tokens": 14433600}
{"current_steps": 15040, "total_steps": 58920, "loss": 0.0328, "lr": 1.856727602589687e-06, "epoch": 1.276306856754922, "percentage": 25.53, "elapsed_time": "0:23:57", "remaining_time": "1:09:54", "throughput": 10041.55, "total_tokens": 14438144}
{"current_steps": 15045, "total_steps": 58920, "loss": 0.0503, "lr": 1.8565747837786692e-06, "epoch": 1.2767311608961305, "percentage": 25.53, "elapsed_time": "0:23:58", "remaining_time": "1:09:54", "throughput": 10042.17, "total_tokens": 14442944}
{"current_steps": 15050, "total_steps": 58920, "loss": 0.0676, "lr": 1.8564218898063066e-06, "epoch": 1.277155465037339, "percentage": 25.54, "elapsed_time": "0:23:58", "remaining_time": "1:09:53", "throughput": 10042.78, "total_tokens": 14447744}
{"current_steps": 15055, "total_steps": 58920, "loss": 0.0637, "lr": 1.8562689206860152e-06, "epoch": 1.2775797691785473, "percentage": 25.55, "elapsed_time": "0:23:59", "remaining_time": "1:09:52", "throughput": 10043.59, "total_tokens": 14452928}
{"current_steps": 15060, "total_steps": 58920, "loss": 0.0147, "lr": 1.8561158764312174e-06, "epoch": 1.2780040733197555, "percentage": 25.56, "elapsed_time": "0:23:59", "remaining_time": "1:09:52", "throughput": 10044.15, "total_tokens": 14457536}
{"current_steps": 15065, "total_steps": 58920, "loss": 0.0334, "lr": 1.8559627570553426e-06, "epoch": 1.278428377460964, "percentage": 25.57, "elapsed_time": "0:23:59", "remaining_time": "1:09:51", "throughput": 10044.73, "total_tokens": 14462208}
{"current_steps": 15070, "total_steps": 58920, "loss": 0.0364, "lr": 1.8558095625718265e-06, "epoch": 1.2788526816021724, "percentage": 25.58, "elapsed_time": "0:24:00", "remaining_time": "1:09:50", "throughput": 10045.1, "total_tokens": 14466560}
{"current_steps": 15075, "total_steps": 58920, "loss": 0.014, "lr": 1.8556562929941108e-06, "epoch": 1.2792769857433808, "percentage": 25.59, "elapsed_time": "0:24:00", "remaining_time": "1:09:49", "throughput": 10045.64, "total_tokens": 14471168}
{"current_steps": 15080, "total_steps": 58920, "loss": 0.0411, "lr": 1.855502948335645e-06, "epoch": 1.2797012898845892, "percentage": 25.59, "elapsed_time": "0:24:00", "remaining_time": "1:09:49", "throughput": 10046.38, "total_tokens": 14476224}
{"current_steps": 15085, "total_steps": 58920, "loss": 0.0529, "lr": 1.8553495286098842e-06, "epoch": 1.2801255940257976, "percentage": 25.6, "elapsed_time": "0:24:01", "remaining_time": "1:09:48", "throughput": 10046.87, "total_tokens": 14480768}
{"current_steps": 15090, "total_steps": 58920, "loss": 0.0075, "lr": 1.8551960338302902e-06, "epoch": 1.280549898167006, "percentage": 25.61, "elapsed_time": "0:24:01", "remaining_time": "1:09:47", "throughput": 10047.29, "total_tokens": 14485248}
{"current_steps": 15095, "total_steps": 58920, "loss": 0.0214, "lr": 1.8550424640103324e-06, "epoch": 1.2809742023082145, "percentage": 25.62, "elapsed_time": "0:24:02", "remaining_time": "1:09:46", "throughput": 10048.32, "total_tokens": 14490816}
{"current_steps": 15100, "total_steps": 58920, "loss": 0.202, "lr": 1.8548888191634852e-06, "epoch": 1.2813985064494229, "percentage": 25.63, "elapsed_time": "0:24:02", "remaining_time": "1:09:46", "throughput": 10049.14, "total_tokens": 14496000}
{"current_steps": 15105, "total_steps": 58920, "loss": 0.063, "lr": 1.8547350993032308e-06, "epoch": 1.2818228105906313, "percentage": 25.64, "elapsed_time": "0:24:02", "remaining_time": "1:09:45", "throughput": 10049.41, "total_tokens": 14500160}
{"current_steps": 15110, "total_steps": 58920, "loss": 0.0154, "lr": 1.8545813044430575e-06, "epoch": 1.2822471147318397, "percentage": 25.64, "elapsed_time": "0:24:03", "remaining_time": "1:09:44", "throughput": 10049.96, "total_tokens": 14504832}
{"current_steps": 15115, "total_steps": 58920, "loss": 0.0034, "lr": 1.8544274345964598e-06, "epoch": 1.2826714188730481, "percentage": 25.65, "elapsed_time": "0:24:03", "remaining_time": "1:09:43", "throughput": 10050.46, "total_tokens": 14509440}
{"current_steps": 15120, "total_steps": 58920, "loss": 0.1027, "lr": 1.85427348977694e-06, "epoch": 1.2830957230142566, "percentage": 25.66, "elapsed_time": "0:24:04", "remaining_time": "1:09:43", "throughput": 10051.11, "total_tokens": 14514304}
{"current_steps": 15125, "total_steps": 58920, "loss": 0.0308, "lr": 1.8541194699980055e-06, "epoch": 1.283520027155465, "percentage": 25.67, "elapsed_time": "0:24:04", "remaining_time": "1:09:42", "throughput": 10051.57, "total_tokens": 14518848}
{"current_steps": 15130, "total_steps": 58920, "loss": 0.0303, "lr": 1.8539653752731718e-06, "epoch": 1.2839443312966734, "percentage": 25.68, "elapsed_time": "0:24:04", "remaining_time": "1:09:41", "throughput": 10052.2, "total_tokens": 14523712}
{"current_steps": 15135, "total_steps": 58920, "loss": 0.0348, "lr": 1.8538112056159592e-06, "epoch": 1.2843686354378818, "percentage": 25.69, "elapsed_time": "0:24:05", "remaining_time": "1:09:40", "throughput": 10052.6, "total_tokens": 14528256}
{"current_steps": 15140, "total_steps": 58920, "loss": 0.0285, "lr": 1.853656961039896e-06, "epoch": 1.2847929395790902, "percentage": 25.7, "elapsed_time": "0:24:05", "remaining_time": "1:09:40", "throughput": 10053.18, "total_tokens": 14532992}
{"current_steps": 15145, "total_steps": 58920, "loss": 0.0019, "lr": 1.8535026415585167e-06, "epoch": 1.2852172437202987, "percentage": 25.7, "elapsed_time": "0:24:06", "remaining_time": "1:09:39", "throughput": 10054.27, "total_tokens": 14538752}
{"current_steps": 15150, "total_steps": 58920, "loss": 0.0022, "lr": 1.8533482471853623e-06, "epoch": 1.285641547861507, "percentage": 25.71, "elapsed_time": "0:24:06", "remaining_time": "1:09:38", "throughput": 10054.7, "total_tokens": 14543232}
{"current_steps": 15155, "total_steps": 58920, "loss": 0.0602, "lr": 1.8531937779339801e-06, "epoch": 1.2860658520027155, "percentage": 25.72, "elapsed_time": "0:24:06", "remaining_time": "1:09:38", "throughput": 10055.18, "total_tokens": 14547776}
{"current_steps": 15160, "total_steps": 58920, "loss": 0.0612, "lr": 1.8530392338179244e-06, "epoch": 1.286490156143924, "percentage": 25.73, "elapsed_time": "0:24:07", "remaining_time": "1:09:37", "throughput": 10055.56, "total_tokens": 14552128}
{"current_steps": 15165, "total_steps": 58920, "loss": 0.0469, "lr": 1.8528846148507556e-06, "epoch": 1.2869144602851323, "percentage": 25.74, "elapsed_time": "0:24:07", "remaining_time": "1:09:36", "throughput": 10056.26, "total_tokens": 14557120}
{"current_steps": 15170, "total_steps": 58920, "loss": 0.0236, "lr": 1.8527299210460412e-06, "epoch": 1.2873387644263408, "percentage": 25.75, "elapsed_time": "0:24:07", "remaining_time": "1:09:35", "throughput": 10056.93, "total_tokens": 14562048}
{"current_steps": 15175, "total_steps": 58920, "loss": 0.0657, "lr": 1.852575152417355e-06, "epoch": 1.2877630685675492, "percentage": 25.76, "elapsed_time": "0:24:08", "remaining_time": "1:09:35", "throughput": 10057.71, "total_tokens": 14567104}
{"current_steps": 15180, "total_steps": 58920, "loss": 0.0703, "lr": 1.8524203089782778e-06, "epoch": 1.2881873727087576, "percentage": 25.76, "elapsed_time": "0:24:08", "remaining_time": "1:09:34", "throughput": 10058.16, "total_tokens": 14571584}
{"current_steps": 15185, "total_steps": 58920, "loss": 0.0007, "lr": 1.8522653907423956e-06, "epoch": 1.288611676849966, "percentage": 25.77, "elapsed_time": "0:24:09", "remaining_time": "1:09:33", "throughput": 10058.64, "total_tokens": 14576128}
{"current_steps": 15190, "total_steps": 58920, "loss": 0.0245, "lr": 1.8521103977233028e-06, "epoch": 1.2890359809911744, "percentage": 25.78, "elapsed_time": "0:24:09", "remaining_time": "1:09:32", "throughput": 10059.3, "total_tokens": 14580992}
{"current_steps": 15195, "total_steps": 58920, "loss": 0.1137, "lr": 1.8519553299345989e-06, "epoch": 1.2894602851323829, "percentage": 25.79, "elapsed_time": "0:24:09", "remaining_time": "1:09:32", "throughput": 10060.02, "total_tokens": 14585984}
{"current_steps": 15200, "total_steps": 58920, "loss": 0.1153, "lr": 1.851800187389891e-06, "epoch": 1.2898845892735913, "percentage": 25.8, "elapsed_time": "0:24:10", "remaining_time": "1:09:31", "throughput": 10060.64, "total_tokens": 14590784}
{"current_steps": 15205, "total_steps": 58920, "loss": 0.0296, "lr": 1.8516449701027922e-06, "epoch": 1.2903088934147997, "percentage": 25.81, "elapsed_time": "0:24:10", "remaining_time": "1:09:30", "throughput": 10061.8, "total_tokens": 14596608}
{"current_steps": 15210, "total_steps": 58920, "loss": 0.0131, "lr": 1.8514896780869215e-06, "epoch": 1.2907331975560081, "percentage": 25.81, "elapsed_time": "0:24:11", "remaining_time": "1:09:30", "throughput": 10062.88, "total_tokens": 14602304}
{"current_steps": 15215, "total_steps": 58920, "loss": 0.0085, "lr": 1.8513343113559063e-06, "epoch": 1.2911575016972165, "percentage": 25.82, "elapsed_time": "0:24:11", "remaining_time": "1:09:29", "throughput": 10063.66, "total_tokens": 14607424}
{"current_steps": 15220, "total_steps": 58920, "loss": 0.0475, "lr": 1.851178869923379e-06, "epoch": 1.291581805838425, "percentage": 25.83, "elapsed_time": "0:24:11", "remaining_time": "1:09:28", "throughput": 10064.52, "total_tokens": 14612672}
{"current_steps": 15225, "total_steps": 58920, "loss": 0.0189, "lr": 1.8510233538029788e-06, "epoch": 1.2920061099796334, "percentage": 25.84, "elapsed_time": "0:24:12", "remaining_time": "1:09:27", "throughput": 10064.84, "total_tokens": 14616960}
{"current_steps": 15230, "total_steps": 58920, "loss": 0.0289, "lr": 1.8508677630083522e-06, "epoch": 1.2924304141208418, "percentage": 25.85, "elapsed_time": "0:24:12", "remaining_time": "1:09:27", "throughput": 10065.71, "total_tokens": 14622272}
{"current_steps": 15235, "total_steps": 58920, "loss": 0.0545, "lr": 1.8507120975531513e-06, "epoch": 1.2928547182620502, "percentage": 25.86, "elapsed_time": "0:24:13", "remaining_time": "1:09:26", "throughput": 10066.48, "total_tokens": 14627392}
{"current_steps": 15240, "total_steps": 58920, "loss": 0.0837, "lr": 1.8505563574510354e-06, "epoch": 1.2932790224032586, "percentage": 25.87, "elapsed_time": "0:24:13", "remaining_time": "1:09:25", "throughput": 10067.07, "total_tokens": 14632320}
{"current_steps": 15245, "total_steps": 58920, "loss": 0.0976, "lr": 1.85040054271567e-06, "epoch": 1.293703326544467, "percentage": 25.87, "elapsed_time": "0:24:13", "remaining_time": "1:09:25", "throughput": 10067.55, "total_tokens": 14636928}
{"current_steps": 15250, "total_steps": 58920, "loss": 0.0599, "lr": 1.8502446533607272e-06, "epoch": 1.2941276306856755, "percentage": 25.88, "elapsed_time": "0:24:14", "remaining_time": "1:09:24", "throughput": 10068.23, "total_tokens": 14641856}
{"current_steps": 15255, "total_steps": 58920, "loss": 0.0375, "lr": 1.850088689399886e-06, "epoch": 1.294551934826884, "percentage": 25.89, "elapsed_time": "0:24:14", "remaining_time": "1:09:23", "throughput": 10068.65, "total_tokens": 14646272}
{"current_steps": 15260, "total_steps": 58920, "loss": 0.0554, "lr": 1.8499326508468315e-06, "epoch": 1.2949762389680923, "percentage": 25.9, "elapsed_time": "0:24:15", "remaining_time": "1:09:22", "throughput": 10069.62, "total_tokens": 14651712}
{"current_steps": 15265, "total_steps": 58920, "loss": 0.0845, "lr": 1.8497765377152556e-06, "epoch": 1.2954005431093008, "percentage": 25.91, "elapsed_time": "0:24:15", "remaining_time": "1:09:22", "throughput": 10069.89, "total_tokens": 14655808}
{"current_steps": 15270, "total_steps": 58920, "loss": 0.0221, "lr": 1.8496203500188568e-06, "epoch": 1.2958248472505092, "percentage": 25.92, "elapsed_time": "0:24:15", "remaining_time": "1:09:21", "throughput": 10070.55, "total_tokens": 14660608}
{"current_steps": 15275, "total_steps": 58920, "loss": 0.0814, "lr": 1.8494640877713396e-06, "epoch": 1.2962491513917176, "percentage": 25.92, "elapsed_time": "0:24:16", "remaining_time": "1:09:20", "throughput": 10071.6, "total_tokens": 14666176}
{"current_steps": 15280, "total_steps": 58920, "loss": 0.0367, "lr": 1.8493077509864156e-06, "epoch": 1.296673455532926, "percentage": 25.93, "elapsed_time": "0:24:16", "remaining_time": "1:09:19", "throughput": 10072.12, "total_tokens": 14670720}
{"current_steps": 15285, "total_steps": 58920, "loss": 0.051, "lr": 1.8491513396778032e-06, "epoch": 1.2970977596741344, "percentage": 25.94, "elapsed_time": "0:24:16", "remaining_time": "1:09:19", "throughput": 10072.93, "total_tokens": 14675840}
{"current_steps": 15290, "total_steps": 58920, "loss": 0.0112, "lr": 1.848994853859226e-06, "epoch": 1.2975220638153429, "percentage": 25.95, "elapsed_time": "0:24:17", "remaining_time": "1:09:18", "throughput": 10073.36, "total_tokens": 14680320}
{"current_steps": 15295, "total_steps": 58920, "loss": 0.0711, "lr": 1.8488382935444163e-06, "epoch": 1.2979463679565513, "percentage": 25.96, "elapsed_time": "0:24:17", "remaining_time": "1:09:17", "throughput": 10073.93, "total_tokens": 14685056}
{"current_steps": 15300, "total_steps": 58920, "loss": 0.079, "lr": 1.8486816587471105e-06, "epoch": 1.2983706720977597, "percentage": 25.97, "elapsed_time": "0:24:18", "remaining_time": "1:09:17", "throughput": 10074.49, "total_tokens": 14689728}
{"current_steps": 15305, "total_steps": 58920, "loss": 0.0111, "lr": 1.8485249494810537e-06, "epoch": 1.2987949762389681, "percentage": 25.98, "elapsed_time": "0:24:18", "remaining_time": "1:09:16", "throughput": 10075.24, "total_tokens": 14694656}
{"current_steps": 15310, "total_steps": 58920, "loss": 0.052, "lr": 1.848368165759996e-06, "epoch": 1.2992192803801765, "percentage": 25.98, "elapsed_time": "0:24:18", "remaining_time": "1:09:15", "throughput": 10076.1, "total_tokens": 14699904}
{"current_steps": 15315, "total_steps": 58920, "loss": 0.0299, "lr": 1.8482113075976948e-06, "epoch": 1.299643584521385, "percentage": 25.99, "elapsed_time": "0:24:19", "remaining_time": "1:09:14", "throughput": 10076.41, "total_tokens": 14704128}
{"current_steps": 15320, "total_steps": 58920, "loss": 0.0726, "lr": 1.8480543750079137e-06, "epoch": 1.3000678886625934, "percentage": 26.0, "elapsed_time": "0:24:19", "remaining_time": "1:09:14", "throughput": 10077.08, "total_tokens": 14708992}
{"current_steps": 15325, "total_steps": 58920, "loss": 0.0367, "lr": 1.8478973680044233e-06, "epoch": 1.3004921928038018, "percentage": 26.01, "elapsed_time": "0:24:20", "remaining_time": "1:09:13", "throughput": 10077.61, "total_tokens": 14713600}
{"current_steps": 15330, "total_steps": 58920, "loss": 0.0411, "lr": 1.847740286601e-06, "epoch": 1.3009164969450102, "percentage": 26.02, "elapsed_time": "0:24:20", "remaining_time": "1:09:12", "throughput": 10078.31, "total_tokens": 14718528}
{"current_steps": 15335, "total_steps": 58920, "loss": 0.0472, "lr": 1.8475831308114276e-06, "epoch": 1.3013408010862186, "percentage": 26.03, "elapsed_time": "0:24:20", "remaining_time": "1:09:11", "throughput": 10078.96, "total_tokens": 14723328}
{"current_steps": 15340, "total_steps": 58920, "loss": 0.0236, "lr": 1.8474259006494956e-06, "epoch": 1.301765105227427, "percentage": 26.04, "elapsed_time": "0:24:21", "remaining_time": "1:09:11", "throughput": 10079.51, "total_tokens": 14728000}
{"current_steps": 15345, "total_steps": 58920, "loss": 0.0262, "lr": 1.8472685961290002e-06, "epoch": 1.3021894093686355, "percentage": 26.04, "elapsed_time": "0:24:21", "remaining_time": "1:09:10", "throughput": 10080.18, "total_tokens": 14732864}
{"current_steps": 15350, "total_steps": 58920, "loss": 0.0518, "lr": 1.8471112172637447e-06, "epoch": 1.302613713509844, "percentage": 26.05, "elapsed_time": "0:24:21", "remaining_time": "1:09:09", "throughput": 10080.5, "total_tokens": 14737216}
{"current_steps": 15355, "total_steps": 58920, "loss": 0.0493, "lr": 1.8469537640675384e-06, "epoch": 1.3030380176510523, "percentage": 26.06, "elapsed_time": "0:24:22", "remaining_time": "1:09:08", "throughput": 10081.31, "total_tokens": 14742336}
{"current_steps": 15360, "total_steps": 58920, "loss": 0.0011, "lr": 1.8467962365541969e-06, "epoch": 1.3034623217922607, "percentage": 26.07, "elapsed_time": "0:24:22", "remaining_time": "1:09:08", "throughput": 10082.04, "total_tokens": 14747328}
{"current_steps": 15365, "total_steps": 58920, "loss": 0.0556, "lr": 1.8466386347375433e-06, "epoch": 1.3038866259334692, "percentage": 26.08, "elapsed_time": "0:24:23", "remaining_time": "1:09:07", "throughput": 10082.54, "total_tokens": 14751808}
{"current_steps": 15370, "total_steps": 58920, "loss": 0.0177, "lr": 1.8464809586314063e-06, "epoch": 1.3043109300746776, "percentage": 26.09, "elapsed_time": "0:24:23", "remaining_time": "1:09:06", "throughput": 10083.09, "total_tokens": 14756416}
{"current_steps": 15375, "total_steps": 58920, "loss": 0.1044, "lr": 1.8463232082496212e-06, "epoch": 1.304735234215886, "percentage": 26.09, "elapsed_time": "0:24:23", "remaining_time": "1:09:05", "throughput": 10083.58, "total_tokens": 14760960}
{"current_steps": 15380, "total_steps": 58920, "loss": 0.02, "lr": 1.8461653836060304e-06, "epoch": 1.3051595383570944, "percentage": 26.1, "elapsed_time": "0:24:24", "remaining_time": "1:09:05", "throughput": 10083.91, "total_tokens": 14765184}
{"current_steps": 15385, "total_steps": 58920, "loss": 0.0006, "lr": 1.846007484714482e-06, "epoch": 1.3055838424983028, "percentage": 26.11, "elapsed_time": "0:24:24", "remaining_time": "1:09:04", "throughput": 10084.75, "total_tokens": 14770304}
{"current_steps": 15390, "total_steps": 58920, "loss": 0.0021, "lr": 1.8458495115888316e-06, "epoch": 1.3060081466395113, "percentage": 26.12, "elapsed_time": "0:24:24", "remaining_time": "1:09:03", "throughput": 10085.1, "total_tokens": 14774592}
{"current_steps": 15395, "total_steps": 58920, "loss": 0.0389, "lr": 1.8456914642429404e-06, "epoch": 1.3064324507807197, "percentage": 26.13, "elapsed_time": "0:24:25", "remaining_time": "1:09:02", "throughput": 10085.69, "total_tokens": 14779328}
{"current_steps": 15400, "total_steps": 58920, "loss": 0.091, "lr": 1.8455333426906766e-06, "epoch": 1.306856754921928, "percentage": 26.14, "elapsed_time": "0:24:25", "remaining_time": "1:09:02", "throughput": 10086.35, "total_tokens": 14784128}
{"current_steps": 15405, "total_steps": 58920, "loss": 0.0687, "lr": 1.8453751469459145e-06, "epoch": 1.3072810590631365, "percentage": 26.15, "elapsed_time": "0:24:26", "remaining_time": "1:09:01", "throughput": 10086.7, "total_tokens": 14788416}
{"current_steps": 15410, "total_steps": 58920, "loss": 0.056, "lr": 1.8452168770225356e-06, "epoch": 1.307705363204345, "percentage": 26.15, "elapsed_time": "0:24:26", "remaining_time": "1:09:00", "throughput": 10087.42, "total_tokens": 14793344}
{"current_steps": 15415, "total_steps": 58920, "loss": 0.0323, "lr": 1.8450585329344275e-06, "epoch": 1.3081296673455534, "percentage": 26.16, "elapsed_time": "0:24:26", "remaining_time": "1:08:59", "throughput": 10087.95, "total_tokens": 14797952}
{"current_steps": 15420, "total_steps": 58920, "loss": 0.0423, "lr": 1.844900114695484e-06, "epoch": 1.3085539714867618, "percentage": 26.17, "elapsed_time": "0:24:27", "remaining_time": "1:08:59", "throughput": 10088.5, "total_tokens": 14802560}
{"current_steps": 15425, "total_steps": 58920, "loss": 0.026, "lr": 1.8447416223196064e-06, "epoch": 1.3089782756279702, "percentage": 26.18, "elapsed_time": "0:24:27", "remaining_time": "1:08:58", "throughput": 10089.12, "total_tokens": 14807296}
{"current_steps": 15430, "total_steps": 58920, "loss": 0.0407, "lr": 1.844583055820701e-06, "epoch": 1.3094025797691786, "percentage": 26.19, "elapsed_time": "0:24:28", "remaining_time": "1:08:57", "throughput": 10089.77, "total_tokens": 14812096}
{"current_steps": 15435, "total_steps": 58920, "loss": 0.0322, "lr": 1.8444244152126817e-06, "epoch": 1.309826883910387, "percentage": 26.2, "elapsed_time": "0:24:28", "remaining_time": "1:08:56", "throughput": 10090.2, "total_tokens": 14816512}
{"current_steps": 15440, "total_steps": 58920, "loss": 0.0514, "lr": 1.844265700509469e-06, "epoch": 1.3102511880515955, "percentage": 26.21, "elapsed_time": "0:24:28", "remaining_time": "1:08:56", "throughput": 10090.88, "total_tokens": 14821376}
{"current_steps": 15445, "total_steps": 58920, "loss": 0.0017, "lr": 1.8441069117249893e-06, "epoch": 1.3106754921928039, "percentage": 26.21, "elapsed_time": "0:24:29", "remaining_time": "1:08:55", "throughput": 10091.69, "total_tokens": 14826496}
{"current_steps": 15450, "total_steps": 58920, "loss": 0.0497, "lr": 1.8439480488731754e-06, "epoch": 1.3110997963340123, "percentage": 26.22, "elapsed_time": "0:24:29", "remaining_time": "1:08:54", "throughput": 10092.26, "total_tokens": 14831168}
{"current_steps": 15455, "total_steps": 58920, "loss": 0.0172, "lr": 1.8437891119679677e-06, "epoch": 1.3115241004752205, "percentage": 26.23, "elapsed_time": "0:24:29", "remaining_time": "1:08:54", "throughput": 10093.03, "total_tokens": 14836224}
{"current_steps": 15460, "total_steps": 58920, "loss": 0.0646, "lr": 1.8436301010233115e-06, "epoch": 1.311948404616429, "percentage": 26.24, "elapsed_time": "0:24:30", "remaining_time": "1:08:53", "throughput": 10093.59, "total_tokens": 14840832}
{"current_steps": 15465, "total_steps": 58920, "loss": 0.0374, "lr": 1.8434710160531601e-06, "epoch": 1.3123727087576373, "percentage": 26.25, "elapsed_time": "0:24:30", "remaining_time": "1:08:52", "throughput": 10094.1, "total_tokens": 14845376}
{"current_steps": 15470, "total_steps": 58920, "loss": 0.0379, "lr": 1.8433118570714723e-06, "epoch": 1.3127970128988458, "percentage": 26.26, "elapsed_time": "0:24:31", "remaining_time": "1:08:51", "throughput": 10094.77, "total_tokens": 14850240}
{"current_steps": 15475, "total_steps": 58920, "loss": 0.1075, "lr": 1.843152624092214e-06, "epoch": 1.3132213170400542, "percentage": 26.26, "elapsed_time": "0:24:31", "remaining_time": "1:08:51", "throughput": 10095.29, "total_tokens": 14854784}
{"current_steps": 15480, "total_steps": 58920, "loss": 0.0224, "lr": 1.8429933171293567e-06, "epoch": 1.3136456211812626, "percentage": 26.27, "elapsed_time": "0:24:31", "remaining_time": "1:08:50", "throughput": 10095.76, "total_tokens": 14859264}
{"current_steps": 15485, "total_steps": 58920, "loss": 0.0441, "lr": 1.8428339361968801e-06, "epoch": 1.314069925322471, "percentage": 26.28, "elapsed_time": "0:24:32", "remaining_time": "1:08:49", "throughput": 10096.39, "total_tokens": 14864000}
{"current_steps": 15490, "total_steps": 58920, "loss": 0.0383, "lr": 1.842674481308768e-06, "epoch": 1.3144942294636794, "percentage": 26.29, "elapsed_time": "0:24:32", "remaining_time": "1:08:48", "throughput": 10097.2, "total_tokens": 14869120}
{"current_steps": 15495, "total_steps": 58920, "loss": 0.0385, "lr": 1.842514952479013e-06, "epoch": 1.3149185336048879, "percentage": 26.3, "elapsed_time": "0:24:32", "remaining_time": "1:08:48", "throughput": 10097.96, "total_tokens": 14874176}
{"current_steps": 15500, "total_steps": 58920, "loss": 0.0457, "lr": 1.8423553497216126e-06, "epoch": 1.3153428377460963, "percentage": 26.31, "elapsed_time": "0:24:33", "remaining_time": "1:08:47", "throughput": 10098.44, "total_tokens": 14878720}
{"current_steps": 15505, "total_steps": 58920, "loss": 0.0702, "lr": 1.8421956730505719e-06, "epoch": 1.3157671418873047, "percentage": 26.32, "elapsed_time": "0:24:33", "remaining_time": "1:08:46", "throughput": 10099.42, "total_tokens": 14884160}
{"current_steps": 15510, "total_steps": 58920, "loss": 0.0191, "lr": 1.8420359224799013e-06, "epoch": 1.3161914460285131, "percentage": 26.32, "elapsed_time": "0:24:34", "remaining_time": "1:08:45", "throughput": 10100.35, "total_tokens": 14889536}
{"current_steps": 15515, "total_steps": 58920, "loss": 0.0417, "lr": 1.8418760980236185e-06, "epoch": 1.3166157501697215, "percentage": 26.33, "elapsed_time": "0:24:34", "remaining_time": "1:08:45", "throughput": 10100.79, "total_tokens": 14893952}
{"current_steps": 15520, "total_steps": 58920, "loss": 0.0773, "lr": 1.8417161996957483e-06, "epoch": 1.31704005431093, "percentage": 26.34, "elapsed_time": "0:24:34", "remaining_time": "1:08:44", "throughput": 10101.38, "total_tokens": 14898688}
{"current_steps": 15525, "total_steps": 58920, "loss": 0.0368, "lr": 1.84155622751032e-06, "epoch": 1.3174643584521384, "percentage": 26.35, "elapsed_time": "0:24:35", "remaining_time": "1:08:43", "throughput": 10102.18, "total_tokens": 14903808}
{"current_steps": 15530, "total_steps": 58920, "loss": 0.0449, "lr": 1.8413961814813714e-06, "epoch": 1.3178886625933468, "percentage": 26.36, "elapsed_time": "0:24:35", "remaining_time": "1:08:42", "throughput": 10102.86, "total_tokens": 14908672}
{"current_steps": 15535, "total_steps": 58920, "loss": 0.0498, "lr": 1.8412360616229456e-06, "epoch": 1.3183129667345552, "percentage": 26.37, "elapsed_time": "0:24:36", "remaining_time": "1:08:42", "throughput": 10103.96, "total_tokens": 14914432}
{"current_steps": 15540, "total_steps": 58920, "loss": 0.0253, "lr": 1.841075867949093e-06, "epoch": 1.3187372708757636, "percentage": 26.37, "elapsed_time": "0:24:36", "remaining_time": "1:08:41", "throughput": 10104.52, "total_tokens": 14919104}
{"current_steps": 15545, "total_steps": 58920, "loss": 0.0245, "lr": 1.8409156004738693e-06, "epoch": 1.319161575016972, "percentage": 26.38, "elapsed_time": "0:24:36", "remaining_time": "1:08:40", "throughput": 10105.24, "total_tokens": 14924096}
{"current_steps": 15550, "total_steps": 58920, "loss": 0.0408, "lr": 1.840755259211338e-06, "epoch": 1.3195858791581805, "percentage": 26.39, "elapsed_time": "0:24:37", "remaining_time": "1:08:40", "throughput": 10105.52, "total_tokens": 14928256}
{"current_steps": 15555, "total_steps": 58920, "loss": 0.0308, "lr": 1.840594844175568e-06, "epoch": 1.320010183299389, "percentage": 26.4, "elapsed_time": "0:24:37", "remaining_time": "1:08:39", "throughput": 10106.01, "total_tokens": 14932800}
{"current_steps": 15560, "total_steps": 58920, "loss": 0.0199, "lr": 1.8404343553806356e-06, "epoch": 1.3204344874405973, "percentage": 26.41, "elapsed_time": "0:24:37", "remaining_time": "1:08:38", "throughput": 10106.61, "total_tokens": 14937536}
{"current_steps": 15565, "total_steps": 58920, "loss": 0.0521, "lr": 1.8402737928406228e-06, "epoch": 1.3208587915818057, "percentage": 26.42, "elapsed_time": "0:24:38", "remaining_time": "1:08:37", "throughput": 10107.46, "total_tokens": 14942784}
{"current_steps": 15570, "total_steps": 58920, "loss": 0.0005, "lr": 1.8401131565696187e-06, "epoch": 1.3212830957230142, "percentage": 26.43, "elapsed_time": "0:24:38", "remaining_time": "1:08:37", "throughput": 10108.04, "total_tokens": 14947520}
{"current_steps": 15575, "total_steps": 58920, "loss": 0.0243, "lr": 1.839952446581718e-06, "epoch": 1.3217073998642226, "percentage": 26.43, "elapsed_time": "0:24:39", "remaining_time": "1:08:36", "throughput": 10108.51, "total_tokens": 14952064}
{"current_steps": 15580, "total_steps": 58920, "loss": 0.0888, "lr": 1.8397916628910227e-06, "epoch": 1.322131704005431, "percentage": 26.44, "elapsed_time": "0:24:39", "remaining_time": "1:08:35", "throughput": 10108.93, "total_tokens": 14956480}
{"current_steps": 15585, "total_steps": 58920, "loss": 0.0943, "lr": 1.8396308055116413e-06, "epoch": 1.3225560081466394, "percentage": 26.45, "elapsed_time": "0:24:39", "remaining_time": "1:08:34", "throughput": 10109.29, "total_tokens": 14960768}
{"current_steps": 15590, "total_steps": 58920, "loss": 0.0009, "lr": 1.8394698744576882e-06, "epoch": 1.3229803122878478, "percentage": 26.46, "elapsed_time": "0:24:40", "remaining_time": "1:08:34", "throughput": 10109.66, "total_tokens": 14965120}
{"current_steps": 15595, "total_steps": 58920, "loss": 0.1299, "lr": 1.8393088697432843e-06, "epoch": 1.3234046164290563, "percentage": 26.47, "elapsed_time": "0:24:40", "remaining_time": "1:08:33", "throughput": 10110.44, "total_tokens": 14970240}
{"current_steps": 15600, "total_steps": 58920, "loss": 0.0173, "lr": 1.8391477913825577e-06, "epoch": 1.3238289205702647, "percentage": 26.48, "elapsed_time": "0:24:41", "remaining_time": "1:08:32", "throughput": 10110.86, "total_tokens": 14974656}
{"current_steps": 15605, "total_steps": 58920, "loss": 0.0463, "lr": 1.8389866393896417e-06, "epoch": 1.324253224711473, "percentage": 26.49, "elapsed_time": "0:24:41", "remaining_time": "1:08:32", "throughput": 10111.35, "total_tokens": 14979200}
{"current_steps": 15610, "total_steps": 58920, "loss": 0.02, "lr": 1.8388254137786776e-06, "epoch": 1.3246775288526815, "percentage": 26.49, "elapsed_time": "0:24:41", "remaining_time": "1:08:31", "throughput": 10111.8, "total_tokens": 14983680}
{"current_steps": 15615, "total_steps": 58920, "loss": 0.0706, "lr": 1.838664114563812e-06, "epoch": 1.32510183299389, "percentage": 26.5, "elapsed_time": "0:24:42", "remaining_time": "1:08:30", "throughput": 10112.32, "total_tokens": 14988288}
{"current_steps": 15620, "total_steps": 58920, "loss": 0.0006, "lr": 1.8385027417591981e-06, "epoch": 1.3255261371350984, "percentage": 26.51, "elapsed_time": "0:24:42", "remaining_time": "1:08:29", "throughput": 10112.7, "total_tokens": 14992640}
{"current_steps": 15625, "total_steps": 58920, "loss": 0.0215, "lr": 1.838341295378996e-06, "epoch": 1.3259504412763068, "percentage": 26.52, "elapsed_time": "0:24:42", "remaining_time": "1:08:29", "throughput": 10113.55, "total_tokens": 14997888}
{"current_steps": 15630, "total_steps": 58920, "loss": 0.026, "lr": 1.8381797754373725e-06, "epoch": 1.3263747454175152, "percentage": 26.53, "elapsed_time": "0:24:43", "remaining_time": "1:08:28", "throughput": 10114.07, "total_tokens": 15002496}
{"current_steps": 15635, "total_steps": 58920, "loss": 0.0072, "lr": 1.8380181819484997e-06, "epoch": 1.3267990495587236, "percentage": 26.54, "elapsed_time": "0:24:43", "remaining_time": "1:08:27", "throughput": 10114.56, "total_tokens": 15007104}
{"current_steps": 15640, "total_steps": 58920, "loss": 0.0003, "lr": 1.8378565149265569e-06, "epoch": 1.327223353699932, "percentage": 26.54, "elapsed_time": "0:24:44", "remaining_time": "1:08:26", "throughput": 10114.91, "total_tokens": 15011392}
{"current_steps": 15645, "total_steps": 58920, "loss": 0.0472, "lr": 1.83769477438573e-06, "epoch": 1.3276476578411405, "percentage": 26.55, "elapsed_time": "0:24:44", "remaining_time": "1:08:26", "throughput": 10115.46, "total_tokens": 15016064}
{"current_steps": 15650, "total_steps": 58920, "loss": 0.0078, "lr": 1.8375329603402111e-06, "epoch": 1.328071961982349, "percentage": 26.56, "elapsed_time": "0:24:44", "remaining_time": "1:08:25", "throughput": 10116.13, "total_tokens": 15020928}
{"current_steps": 15655, "total_steps": 58920, "loss": 0.0618, "lr": 1.8373710728041992e-06, "epoch": 1.3284962661235573, "percentage": 26.57, "elapsed_time": "0:24:45", "remaining_time": "1:08:24", "throughput": 10116.46, "total_tokens": 15025216}
{"current_steps": 15660, "total_steps": 58920, "loss": 0.0005, "lr": 1.8372091117918988e-06, "epoch": 1.3289205702647657, "percentage": 26.58, "elapsed_time": "0:24:45", "remaining_time": "1:08:23", "throughput": 10116.83, "total_tokens": 15029568}
{"current_steps": 15665, "total_steps": 58920, "loss": 0.0481, "lr": 1.8370470773175212e-06, "epoch": 1.3293448744059742, "percentage": 26.59, "elapsed_time": "0:24:45", "remaining_time": "1:08:23", "throughput": 10117.23, "total_tokens": 15033984}
{"current_steps": 15670, "total_steps": 58920, "loss": 0.03, "lr": 1.8368849693952852e-06, "epoch": 1.3297691785471826, "percentage": 26.6, "elapsed_time": "0:24:46", "remaining_time": "1:08:22", "throughput": 10117.86, "total_tokens": 15038784}
{"current_steps": 15675, "total_steps": 58920, "loss": 0.0357, "lr": 1.8367227880394146e-06, "epoch": 1.330193482688391, "percentage": 26.6, "elapsed_time": "0:24:46", "remaining_time": "1:08:21", "throughput": 10118.49, "total_tokens": 15043584}
{"current_steps": 15680, "total_steps": 58920, "loss": 0.0274, "lr": 1.8365605332641402e-06, "epoch": 1.3306177868295994, "percentage": 26.61, "elapsed_time": "0:24:47", "remaining_time": "1:08:20", "throughput": 10118.96, "total_tokens": 15048128}
{"current_steps": 15685, "total_steps": 58920, "loss": 0.012, "lr": 1.8363982050836994e-06, "epoch": 1.3310420909708078, "percentage": 26.62, "elapsed_time": "0:24:47", "remaining_time": "1:08:20", "throughput": 10119.47, "total_tokens": 15052672}
{"current_steps": 15690, "total_steps": 58920, "loss": 0.0052, "lr": 1.836235803512336e-06, "epoch": 1.3314663951120163, "percentage": 26.63, "elapsed_time": "0:24:47", "remaining_time": "1:08:19", "throughput": 10120.14, "total_tokens": 15057536}
{"current_steps": 15695, "total_steps": 58920, "loss": 0.0901, "lr": 1.8360733285643e-06, "epoch": 1.3318906992532247, "percentage": 26.64, "elapsed_time": "0:24:48", "remaining_time": "1:08:18", "throughput": 10120.68, "total_tokens": 15062144}
{"current_steps": 15700, "total_steps": 58920, "loss": 0.118, "lr": 1.835910780253848e-06, "epoch": 1.332315003394433, "percentage": 26.65, "elapsed_time": "0:24:48", "remaining_time": "1:08:18", "throughput": 10121.31, "total_tokens": 15066944}
{"current_steps": 15705, "total_steps": 58920, "loss": 0.0662, "lr": 1.8357481585952431e-06, "epoch": 1.3327393075356415, "percentage": 26.65, "elapsed_time": "0:24:49", "remaining_time": "1:08:17", "throughput": 10122.14, "total_tokens": 15072128}
{"current_steps": 15710, "total_steps": 58920, "loss": 0.0203, "lr": 1.8355854636027547e-06, "epoch": 1.33316361167685, "percentage": 26.66, "elapsed_time": "0:24:49", "remaining_time": "1:08:16", "throughput": 10122.55, "total_tokens": 15076544}
{"current_steps": 15715, "total_steps": 58920, "loss": 0.0227, "lr": 1.835422695290659e-06, "epoch": 1.3335879158180584, "percentage": 26.67, "elapsed_time": "0:24:49", "remaining_time": "1:08:15", "throughput": 10123.08, "total_tokens": 15081152}
{"current_steps": 15720, "total_steps": 58920, "loss": 0.05, "lr": 1.835259853673238e-06, "epoch": 1.3340122199592668, "percentage": 26.68, "elapsed_time": "0:24:50", "remaining_time": "1:08:15", "throughput": 10123.71, "total_tokens": 15085952}
{"current_steps": 15725, "total_steps": 58920, "loss": 0.001, "lr": 1.8350969387647802e-06, "epoch": 1.3344365241004752, "percentage": 26.69, "elapsed_time": "0:24:50", "remaining_time": "1:08:14", "throughput": 10124.22, "total_tokens": 15090560}
{"current_steps": 15730, "total_steps": 58920, "loss": 0.0281, "lr": 1.8349339505795816e-06, "epoch": 1.3348608282416836, "percentage": 26.7, "elapsed_time": "0:24:50", "remaining_time": "1:08:13", "throughput": 10124.8, "total_tokens": 15095296}
{"current_steps": 15735, "total_steps": 58920, "loss": 0.0006, "lr": 1.834770889131943e-06, "epoch": 1.335285132382892, "percentage": 26.71, "elapsed_time": "0:24:51", "remaining_time": "1:08:12", "throughput": 10125.9, "total_tokens": 15101056}
{"current_steps": 15740, "total_steps": 58920, "loss": 0.0468, "lr": 1.8346077544361728e-06, "epoch": 1.3357094365241005, "percentage": 26.71, "elapsed_time": "0:24:51", "remaining_time": "1:08:12", "throughput": 10126.2, "total_tokens": 15105216}
{"current_steps": 15745, "total_steps": 58920, "loss": 0.045, "lr": 1.8344445465065856e-06, "epoch": 1.3361337406653089, "percentage": 26.72, "elapsed_time": "0:24:52", "remaining_time": "1:08:11", "throughput": 10127.07, "total_tokens": 15110464}
{"current_steps": 15750, "total_steps": 58920, "loss": 0.0402, "lr": 1.8342812653575024e-06, "epoch": 1.3365580448065173, "percentage": 26.73, "elapsed_time": "0:24:52", "remaining_time": "1:08:10", "throughput": 10127.58, "total_tokens": 15115072}
{"current_steps": 15755, "total_steps": 58920, "loss": 0.0292, "lr": 1.83411791100325e-06, "epoch": 1.3369823489477257, "percentage": 26.74, "elapsed_time": "0:24:52", "remaining_time": "1:08:10", "throughput": 10128.23, "total_tokens": 15119936}
{"current_steps": 15760, "total_steps": 58920, "loss": 0.0676, "lr": 1.8339544834581625e-06, "epoch": 1.3374066530889341, "percentage": 26.75, "elapsed_time": "0:24:53", "remaining_time": "1:08:09", "throughput": 10128.95, "total_tokens": 15124928}
{"current_steps": 15765, "total_steps": 58920, "loss": 0.0265, "lr": 1.8337909827365803e-06, "epoch": 1.3378309572301426, "percentage": 26.76, "elapsed_time": "0:24:53", "remaining_time": "1:08:08", "throughput": 10129.46, "total_tokens": 15129536}
{"current_steps": 15770, "total_steps": 58920, "loss": 0.017, "lr": 1.8336274088528495e-06, "epoch": 1.338255261371351, "percentage": 26.77, "elapsed_time": "0:24:54", "remaining_time": "1:08:07", "throughput": 10130.37, "total_tokens": 15134912}
{"current_steps": 15775, "total_steps": 58920, "loss": 0.0042, "lr": 1.8334637618213236e-06, "epoch": 1.3386795655125594, "percentage": 26.77, "elapsed_time": "0:24:54", "remaining_time": "1:08:07", "throughput": 10130.89, "total_tokens": 15139520}
{"current_steps": 15780, "total_steps": 58920, "loss": 0.0222, "lr": 1.8333000416563617e-06, "epoch": 1.3391038696537678, "percentage": 26.78, "elapsed_time": "0:24:54", "remaining_time": "1:08:06", "throughput": 10132.65, "total_tokens": 15146624}
{"current_steps": 15785, "total_steps": 58920, "loss": 0.0006, "lr": 1.83313624837233e-06, "epoch": 1.3395281737949762, "percentage": 26.79, "elapsed_time": "0:24:55", "remaining_time": "1:08:05", "throughput": 10133.29, "total_tokens": 15151488}
{"current_steps": 15790, "total_steps": 58920, "loss": 0.0298, "lr": 1.8329723819836e-06, "epoch": 1.3399524779361847, "percentage": 26.8, "elapsed_time": "0:24:55", "remaining_time": "1:08:05", "throughput": 10133.98, "total_tokens": 15156416}
{"current_steps": 15795, "total_steps": 58920, "loss": 0.0769, "lr": 1.832808442504551e-06, "epoch": 1.340376782077393, "percentage": 26.81, "elapsed_time": "0:24:55", "remaining_time": "1:08:04", "throughput": 10134.53, "total_tokens": 15161088}
{"current_steps": 15800, "total_steps": 58920, "loss": 0.0519, "lr": 1.8326444299495686e-06, "epoch": 1.3408010862186015, "percentage": 26.82, "elapsed_time": "0:24:56", "remaining_time": "1:08:03", "throughput": 10134.88, "total_tokens": 15165376}
{"current_steps": 15805, "total_steps": 58920, "loss": 0.0573, "lr": 1.8324803443330433e-06, "epoch": 1.34122539035981, "percentage": 26.82, "elapsed_time": "0:24:56", "remaining_time": "1:08:02", "throughput": 10135.48, "total_tokens": 15170112}
{"current_steps": 15810, "total_steps": 58920, "loss": 0.0304, "lr": 1.8323161856693733e-06, "epoch": 1.3416496945010183, "percentage": 26.83, "elapsed_time": "0:24:57", "remaining_time": "1:08:02", "throughput": 10136.13, "total_tokens": 15174976}
{"current_steps": 15815, "total_steps": 58920, "loss": 0.0018, "lr": 1.8321519539729633e-06, "epoch": 1.3420739986422268, "percentage": 26.84, "elapsed_time": "0:24:57", "remaining_time": "1:08:01", "throughput": 10136.53, "total_tokens": 15179328}
{"current_steps": 15820, "total_steps": 58920, "loss": 0.0729, "lr": 1.831987649258224e-06, "epoch": 1.3424983027834352, "percentage": 26.85, "elapsed_time": "0:24:57", "remaining_time": "1:08:00", "throughput": 10137.09, "total_tokens": 15184000}
{"current_steps": 15825, "total_steps": 58920, "loss": 0.067, "lr": 1.8318232715395719e-06, "epoch": 1.3429226069246436, "percentage": 26.86, "elapsed_time": "0:24:58", "remaining_time": "1:08:00", "throughput": 10138.11, "total_tokens": 15189568}
{"current_steps": 15830, "total_steps": 58920, "loss": 0.0162, "lr": 1.8316588208314311e-06, "epoch": 1.343346911065852, "percentage": 26.87, "elapsed_time": "0:24:58", "remaining_time": "1:07:59", "throughput": 10138.43, "total_tokens": 15193792}
{"current_steps": 15835, "total_steps": 58920, "loss": 0.0566, "lr": 1.8314942971482315e-06, "epoch": 1.3437712152070604, "percentage": 26.88, "elapsed_time": "0:24:59", "remaining_time": "1:07:58", "throughput": 10138.78, "total_tokens": 15198080}
{"current_steps": 15840, "total_steps": 58920, "loss": 0.0505, "lr": 1.8313297005044097e-06, "epoch": 1.3441955193482689, "percentage": 26.88, "elapsed_time": "0:24:59", "remaining_time": "1:07:57", "throughput": 10139.35, "total_tokens": 15202816}
{"current_steps": 15845, "total_steps": 58920, "loss": 0.0808, "lr": 1.831165030914408e-06, "epoch": 1.3446198234894773, "percentage": 26.89, "elapsed_time": "0:24:59", "remaining_time": "1:07:57", "throughput": 10140.61, "total_tokens": 15208896}
{"current_steps": 15850, "total_steps": 58920, "loss": 0.0014, "lr": 1.831000288392676e-06, "epoch": 1.3450441276306857, "percentage": 26.9, "elapsed_time": "0:25:00", "remaining_time": "1:07:56", "throughput": 10140.93, "total_tokens": 15213120}
{"current_steps": 15855, "total_steps": 58920, "loss": 0.029, "lr": 1.8308354729536685e-06, "epoch": 1.3454684317718941, "percentage": 26.91, "elapsed_time": "0:25:00", "remaining_time": "1:07:55", "throughput": 10141.58, "total_tokens": 15217984}
{"current_steps": 15860, "total_steps": 58920, "loss": 0.0211, "lr": 1.8306705846118482e-06, "epoch": 1.3458927359131025, "percentage": 26.92, "elapsed_time": "0:25:00", "remaining_time": "1:07:55", "throughput": 10142.04, "total_tokens": 15222464}
{"current_steps": 15865, "total_steps": 58920, "loss": 0.047, "lr": 1.830505623381683e-06, "epoch": 1.346317040054311, "percentage": 26.93, "elapsed_time": "0:25:01", "remaining_time": "1:07:54", "throughput": 10142.8, "total_tokens": 15227520}
{"current_steps": 15870, "total_steps": 58920, "loss": 0.0172, "lr": 1.8303405892776485e-06, "epoch": 1.3467413441955194, "percentage": 26.93, "elapsed_time": "0:25:01", "remaining_time": "1:07:53", "throughput": 10143.36, "total_tokens": 15232192}
{"current_steps": 15875, "total_steps": 58920, "loss": 0.014, "lr": 1.8301754823142245e-06, "epoch": 1.3471656483367278, "percentage": 26.94, "elapsed_time": "0:25:02", "remaining_time": "1:07:52", "throughput": 10143.96, "total_tokens": 15236928}
{"current_steps": 15880, "total_steps": 58920, "loss": 0.0479, "lr": 1.8300103025059e-06, "epoch": 1.3475899524779362, "percentage": 26.95, "elapsed_time": "0:25:02", "remaining_time": "1:07:52", "throughput": 10144.46, "total_tokens": 15241472}
{"current_steps": 15885, "total_steps": 58920, "loss": 0.0455, "lr": 1.8298450498671679e-06, "epoch": 1.3480142566191446, "percentage": 26.96, "elapsed_time": "0:25:02", "remaining_time": "1:07:51", "throughput": 10145.1, "total_tokens": 15246336}
{"current_steps": 15890, "total_steps": 58920, "loss": 0.0457, "lr": 1.8296797244125285e-06, "epoch": 1.348438560760353, "percentage": 26.97, "elapsed_time": "0:25:03", "remaining_time": "1:07:50", "throughput": 10145.9, "total_tokens": 15251456}
{"current_steps": 15895, "total_steps": 58920, "loss": 0.0261, "lr": 1.829514326156489e-06, "epoch": 1.3488628649015615, "percentage": 26.98, "elapsed_time": "0:25:03", "remaining_time": "1:07:49", "throughput": 10146.38, "total_tokens": 15256000}
{"current_steps": 15900, "total_steps": 58920, "loss": 0.0622, "lr": 1.8293488551135624e-06, "epoch": 1.34928716904277, "percentage": 26.99, "elapsed_time": "0:25:03", "remaining_time": "1:07:49", "throughput": 10147.46, "total_tokens": 15261696}
{"current_steps": 15905, "total_steps": 58920, "loss": 0.0664, "lr": 1.8291833112982682e-06, "epoch": 1.3497114731839783, "percentage": 26.99, "elapsed_time": "0:25:04", "remaining_time": "1:07:48", "throughput": 10148.21, "total_tokens": 15266752}
{"current_steps": 15910, "total_steps": 58920, "loss": 0.02, "lr": 1.829017694725132e-06, "epoch": 1.3501357773251867, "percentage": 27.0, "elapsed_time": "0:25:04", "remaining_time": "1:07:47", "throughput": 10148.75, "total_tokens": 15271424}
{"current_steps": 15915, "total_steps": 58920, "loss": 0.0219, "lr": 1.8288520054086862e-06, "epoch": 1.3505600814663952, "percentage": 27.01, "elapsed_time": "0:25:05", "remaining_time": "1:07:47", "throughput": 10149.21, "total_tokens": 15275968}
{"current_steps": 15920, "total_steps": 58920, "loss": 0.0992, "lr": 1.8286862433634698e-06, "epoch": 1.3509843856076036, "percentage": 27.02, "elapsed_time": "0:25:05", "remaining_time": "1:07:46", "throughput": 10150.08, "total_tokens": 15281280}
{"current_steps": 15925, "total_steps": 58920, "loss": 0.0118, "lr": 1.8285204086040273e-06, "epoch": 1.351408689748812, "percentage": 27.03, "elapsed_time": "0:25:05", "remaining_time": "1:07:45", "throughput": 10150.68, "total_tokens": 15286016}
{"current_steps": 15930, "total_steps": 58920, "loss": 0.0266, "lr": 1.8283545011449103e-06, "epoch": 1.3518329938900204, "percentage": 27.04, "elapsed_time": "0:25:06", "remaining_time": "1:07:45", "throughput": 10151.96, "total_tokens": 15292160}
{"current_steps": 15935, "total_steps": 58920, "loss": 0.0014, "lr": 1.8281885210006767e-06, "epoch": 1.3522572980312288, "percentage": 27.05, "elapsed_time": "0:25:06", "remaining_time": "1:07:44", "throughput": 10152.46, "total_tokens": 15296768}
{"current_steps": 15940, "total_steps": 58920, "loss": 0.032, "lr": 1.8280224681858904e-06, "epoch": 1.3526816021724373, "percentage": 27.05, "elapsed_time": "0:25:07", "remaining_time": "1:07:43", "throughput": 10153.02, "total_tokens": 15301440}
{"current_steps": 15945, "total_steps": 58920, "loss": 0.0144, "lr": 1.827856342715122e-06, "epoch": 1.3531059063136457, "percentage": 27.06, "elapsed_time": "0:25:07", "remaining_time": "1:07:42", "throughput": 10153.76, "total_tokens": 15306496}
{"current_steps": 15950, "total_steps": 58920, "loss": 0.0226, "lr": 1.8276901446029487e-06, "epoch": 1.353530210454854, "percentage": 27.07, "elapsed_time": "0:25:07", "remaining_time": "1:07:42", "throughput": 10154.52, "total_tokens": 15311552}
{"current_steps": 15955, "total_steps": 58920, "loss": 0.0268, "lr": 1.8275238738639537e-06, "epoch": 1.3539545145960625, "percentage": 27.08, "elapsed_time": "0:25:08", "remaining_time": "1:07:41", "throughput": 10154.97, "total_tokens": 15316032}
{"current_steps": 15960, "total_steps": 58920, "loss": 0.0018, "lr": 1.8273575305127262e-06, "epoch": 1.354378818737271, "percentage": 27.09, "elapsed_time": "0:25:08", "remaining_time": "1:07:40", "throughput": 10155.41, "total_tokens": 15320512}
{"current_steps": 15965, "total_steps": 58920, "loss": 0.0013, "lr": 1.8271911145638629e-06, "epoch": 1.3548031228784794, "percentage": 27.1, "elapsed_time": "0:25:08", "remaining_time": "1:07:40", "throughput": 10155.84, "total_tokens": 15324992}
{"current_steps": 15970, "total_steps": 58920, "loss": 0.1047, "lr": 1.8270246260319656e-06, "epoch": 1.3552274270196878, "percentage": 27.1, "elapsed_time": "0:25:09", "remaining_time": "1:07:39", "throughput": 10156.47, "total_tokens": 15329792}
{"current_steps": 15975, "total_steps": 58920, "loss": 0.0006, "lr": 1.8268580649316432e-06, "epoch": 1.3556517311608962, "percentage": 27.11, "elapsed_time": "0:25:09", "remaining_time": "1:07:38", "throughput": 10156.89, "total_tokens": 15334208}
{"current_steps": 15980, "total_steps": 58920, "loss": 0.0797, "lr": 1.8266914312775112e-06, "epoch": 1.3560760353021046, "percentage": 27.12, "elapsed_time": "0:25:10", "remaining_time": "1:07:37", "throughput": 10157.31, "total_tokens": 15338688}
{"current_steps": 15985, "total_steps": 58920, "loss": 0.0253, "lr": 1.8265247250841909e-06, "epoch": 1.356500339443313, "percentage": 27.13, "elapsed_time": "0:25:10", "remaining_time": "1:07:37", "throughput": 10157.65, "total_tokens": 15342976}
{"current_steps": 15990, "total_steps": 58920, "loss": 0.1372, "lr": 1.82635794636631e-06, "epoch": 1.3569246435845215, "percentage": 27.14, "elapsed_time": "0:25:10", "remaining_time": "1:07:36", "throughput": 10158.25, "total_tokens": 15347776}
{"current_steps": 15995, "total_steps": 58920, "loss": 0.0347, "lr": 1.826191095138503e-06, "epoch": 1.35734894772573, "percentage": 27.15, "elapsed_time": "0:25:11", "remaining_time": "1:07:35", "throughput": 10158.61, "total_tokens": 15352128}
{"current_steps": 16000, "total_steps": 58920, "loss": 0.0018, "lr": 1.82602417141541e-06, "epoch": 1.3577732518669383, "percentage": 27.16, "elapsed_time": "0:25:11", "remaining_time": "1:07:34", "throughput": 10159.45, "total_tokens": 15357376}
{"current_steps": 16005, "total_steps": 58920, "loss": 0.0191, "lr": 1.8258571752116788e-06, "epoch": 1.3581975560081467, "percentage": 27.16, "elapsed_time": "0:25:12", "remaining_time": "1:07:34", "throughput": 10159.91, "total_tokens": 15361856}
{"current_steps": 16010, "total_steps": 58920, "loss": 0.0441, "lr": 1.8256901065419618e-06, "epoch": 1.3586218601493552, "percentage": 27.17, "elapsed_time": "0:25:12", "remaining_time": "1:07:33", "throughput": 10160.38, "total_tokens": 15366400}
{"current_steps": 16015, "total_steps": 58920, "loss": 0.0262, "lr": 1.8255229654209194e-06, "epoch": 1.3590461642905636, "percentage": 27.18, "elapsed_time": "0:25:12", "remaining_time": "1:07:32", "throughput": 10161.04, "total_tokens": 15371328}
{"current_steps": 16020, "total_steps": 58920, "loss": 0.0745, "lr": 1.825355751863217e-06, "epoch": 1.359470468431772, "percentage": 27.19, "elapsed_time": "0:25:13", "remaining_time": "1:07:32", "throughput": 10161.5, "total_tokens": 15375872}
{"current_steps": 16025, "total_steps": 58920, "loss": 0.0487, "lr": 1.8251884658835275e-06, "epoch": 1.3598947725729804, "percentage": 27.2, "elapsed_time": "0:25:13", "remaining_time": "1:07:31", "throughput": 10162.33, "total_tokens": 15381120}
{"current_steps": 16030, "total_steps": 58920, "loss": 0.0122, "lr": 1.8250211074965296e-06, "epoch": 1.3603190767141888, "percentage": 27.21, "elapsed_time": "0:25:13", "remaining_time": "1:07:30", "throughput": 10162.67, "total_tokens": 15385408}
{"current_steps": 16035, "total_steps": 58920, "loss": 0.0394, "lr": 1.8248536767169081e-06, "epoch": 1.3607433808553973, "percentage": 27.21, "elapsed_time": "0:25:14", "remaining_time": "1:07:29", "throughput": 10163.32, "total_tokens": 15390272}
{"current_steps": 16040, "total_steps": 58920, "loss": 0.0765, "lr": 1.8246861735593545e-06, "epoch": 1.3611676849966057, "percentage": 27.22, "elapsed_time": "0:25:14", "remaining_time": "1:07:29", "throughput": 10164.37, "total_tokens": 15395968}
{"current_steps": 16045, "total_steps": 58920, "loss": 0.0473, "lr": 1.8245185980385669e-06, "epoch": 1.361591989137814, "percentage": 27.23, "elapsed_time": "0:25:15", "remaining_time": "1:07:28", "throughput": 10164.74, "total_tokens": 15400320}
{"current_steps": 16050, "total_steps": 58920, "loss": 0.0287, "lr": 1.8243509501692488e-06, "epoch": 1.3620162932790225, "percentage": 27.24, "elapsed_time": "0:25:15", "remaining_time": "1:07:27", "throughput": 10165.07, "total_tokens": 15404608}
{"current_steps": 16055, "total_steps": 58920, "loss": 0.0006, "lr": 1.8241832299661115e-06, "epoch": 1.362440597420231, "percentage": 27.25, "elapsed_time": "0:25:15", "remaining_time": "1:07:27", "throughput": 10165.66, "total_tokens": 15409344}
{"current_steps": 16060, "total_steps": 58920, "loss": 0.0645, "lr": 1.8240154374438713e-06, "epoch": 1.3628649015614394, "percentage": 27.26, "elapsed_time": "0:25:16", "remaining_time": "1:07:26", "throughput": 10166.18, "total_tokens": 15413952}
{"current_steps": 16065, "total_steps": 58920, "loss": 0.0419, "lr": 1.823847572617252e-06, "epoch": 1.3632892057026478, "percentage": 27.27, "elapsed_time": "0:25:16", "remaining_time": "1:07:25", "throughput": 10166.94, "total_tokens": 15419072}
{"current_steps": 16070, "total_steps": 58920, "loss": 0.0254, "lr": 1.8236796355009822e-06, "epoch": 1.3637135098438562, "percentage": 27.27, "elapsed_time": "0:25:16", "remaining_time": "1:07:24", "throughput": 10167.45, "total_tokens": 15423680}
{"current_steps": 16075, "total_steps": 58920, "loss": 0.0214, "lr": 1.8235116261097986e-06, "epoch": 1.3641378139850646, "percentage": 27.28, "elapsed_time": "0:25:17", "remaining_time": "1:07:24", "throughput": 10168.03, "total_tokens": 15428480}
{"current_steps": 16080, "total_steps": 58920, "loss": 0.0239, "lr": 1.8233435444584426e-06, "epoch": 1.364562118126273, "percentage": 27.29, "elapsed_time": "0:25:17", "remaining_time": "1:07:23", "throughput": 10168.84, "total_tokens": 15433728}
{"current_steps": 16085, "total_steps": 58920, "loss": 0.0864, "lr": 1.8231753905616638e-06, "epoch": 1.3649864222674815, "percentage": 27.3, "elapsed_time": "0:25:18", "remaining_time": "1:07:22", "throughput": 10169.74, "total_tokens": 15439104}
{"current_steps": 16090, "total_steps": 58920, "loss": 0.0395, "lr": 1.8230071644342165e-06, "epoch": 1.3654107264086899, "percentage": 27.31, "elapsed_time": "0:25:18", "remaining_time": "1:07:22", "throughput": 10170.31, "total_tokens": 15443840}
{"current_steps": 16095, "total_steps": 58920, "loss": 0.0406, "lr": 1.8228388660908615e-06, "epoch": 1.3658350305498983, "percentage": 27.32, "elapsed_time": "0:25:18", "remaining_time": "1:07:21", "throughput": 10170.9, "total_tokens": 15448640}
{"current_steps": 16100, "total_steps": 58920, "loss": 0.0538, "lr": 1.8226704955463671e-06, "epoch": 1.3662593346911067, "percentage": 27.33, "elapsed_time": "0:25:19", "remaining_time": "1:07:20", "throughput": 10171.35, "total_tokens": 15453120}
{"current_steps": 16105, "total_steps": 58920, "loss": 0.1242, "lr": 1.822502052815507e-06, "epoch": 1.3666836388323151, "percentage": 27.33, "elapsed_time": "0:25:19", "remaining_time": "1:07:19", "throughput": 10171.68, "total_tokens": 15457408}
{"current_steps": 16110, "total_steps": 58920, "loss": 0.0358, "lr": 1.8223335379130616e-06, "epoch": 1.3671079429735236, "percentage": 27.34, "elapsed_time": "0:25:20", "remaining_time": "1:07:19", "throughput": 10172.24, "total_tokens": 15462080}
{"current_steps": 16115, "total_steps": 58920, "loss": 0.0764, "lr": 1.8221649508538168e-06, "epoch": 1.3675322471147318, "percentage": 27.35, "elapsed_time": "0:25:20", "remaining_time": "1:07:18", "throughput": 10172.81, "total_tokens": 15466816}
{"current_steps": 16120, "total_steps": 58920, "loss": 0.0244, "lr": 1.8219962916525663e-06, "epoch": 1.3679565512559402, "percentage": 27.36, "elapsed_time": "0:25:20", "remaining_time": "1:07:17", "throughput": 10173.59, "total_tokens": 15471936}
{"current_steps": 16125, "total_steps": 58920, "loss": 0.0129, "lr": 1.821827560324109e-06, "epoch": 1.3683808553971486, "percentage": 27.37, "elapsed_time": "0:25:21", "remaining_time": "1:07:17", "throughput": 10173.96, "total_tokens": 15476288}
{"current_steps": 16130, "total_steps": 58920, "loss": 0.0182, "lr": 1.8216587568832503e-06, "epoch": 1.368805159538357, "percentage": 27.38, "elapsed_time": "0:25:21", "remaining_time": "1:07:16", "throughput": 10174.66, "total_tokens": 15481280}
{"current_steps": 16135, "total_steps": 58920, "loss": 0.0632, "lr": 1.8214898813448024e-06, "epoch": 1.3692294636795654, "percentage": 27.38, "elapsed_time": "0:25:21", "remaining_time": "1:07:15", "throughput": 10175.41, "total_tokens": 15486336}
{"current_steps": 16140, "total_steps": 58920, "loss": 0.0188, "lr": 1.8213209337235832e-06, "epoch": 1.3696537678207739, "percentage": 27.39, "elapsed_time": "0:25:22", "remaining_time": "1:07:14", "throughput": 10176.0, "total_tokens": 15491136}
{"current_steps": 16145, "total_steps": 58920, "loss": 0.088, "lr": 1.8211519140344178e-06, "epoch": 1.3700780719619823, "percentage": 27.4, "elapsed_time": "0:25:22", "remaining_time": "1:07:14", "throughput": 10177.02, "total_tokens": 15496768}
{"current_steps": 16150, "total_steps": 58920, "loss": 0.054, "lr": 1.8209828222921365e-06, "epoch": 1.3705023761031907, "percentage": 27.41, "elapsed_time": "0:25:23", "remaining_time": "1:07:13", "throughput": 10177.5, "total_tokens": 15501376}
{"current_steps": 16155, "total_steps": 58920, "loss": 0.0011, "lr": 1.8208136585115768e-06, "epoch": 1.3709266802443991, "percentage": 27.42, "elapsed_time": "0:25:23", "remaining_time": "1:07:12", "throughput": 10177.86, "total_tokens": 15505728}
{"current_steps": 16160, "total_steps": 58920, "loss": 0.0301, "lr": 1.8206444227075819e-06, "epoch": 1.3713509843856075, "percentage": 27.43, "elapsed_time": "0:25:23", "remaining_time": "1:07:12", "throughput": 10178.19, "total_tokens": 15510016}
{"current_steps": 16165, "total_steps": 58920, "loss": 0.0269, "lr": 1.820475114895002e-06, "epoch": 1.371775288526816, "percentage": 27.44, "elapsed_time": "0:25:24", "remaining_time": "1:07:11", "throughput": 10178.96, "total_tokens": 15515200}
{"current_steps": 16170, "total_steps": 58920, "loss": 0.0009, "lr": 1.8203057350886932e-06, "epoch": 1.3721995926680244, "percentage": 27.44, "elapsed_time": "0:25:24", "remaining_time": "1:07:10", "throughput": 10179.56, "total_tokens": 15520000}
{"current_steps": 16175, "total_steps": 58920, "loss": 0.0115, "lr": 1.8201362833035177e-06, "epoch": 1.3726238968092328, "percentage": 27.45, "elapsed_time": "0:25:24", "remaining_time": "1:07:10", "throughput": 10179.93, "total_tokens": 15524352}
{"current_steps": 16180, "total_steps": 58920, "loss": 0.0632, "lr": 1.8199667595543443e-06, "epoch": 1.3730482009504412, "percentage": 27.46, "elapsed_time": "0:25:25", "remaining_time": "1:07:09", "throughput": 10180.36, "total_tokens": 15528832}
{"current_steps": 16185, "total_steps": 58920, "loss": 0.0693, "lr": 1.8197971638560482e-06, "epoch": 1.3734725050916496, "percentage": 27.47, "elapsed_time": "0:25:25", "remaining_time": "1:07:08", "throughput": 10180.69, "total_tokens": 15533120}
{"current_steps": 16190, "total_steps": 58920, "loss": 0.0601, "lr": 1.819627496223511e-06, "epoch": 1.373896809232858, "percentage": 27.48, "elapsed_time": "0:25:26", "remaining_time": "1:07:07", "throughput": 10181.17, "total_tokens": 15537664}
{"current_steps": 16195, "total_steps": 58920, "loss": 0.0006, "lr": 1.8194577566716202e-06, "epoch": 1.3743211133740665, "percentage": 27.49, "elapsed_time": "0:25:26", "remaining_time": "1:07:07", "throughput": 10181.68, "total_tokens": 15542272}
{"current_steps": 16200, "total_steps": 58920, "loss": 0.0007, "lr": 1.8192879452152701e-06, "epoch": 1.374745417515275, "percentage": 27.49, "elapsed_time": "0:25:26", "remaining_time": "1:07:06", "throughput": 10182.18, "total_tokens": 15546880}
{"current_steps": 16205, "total_steps": 58920, "loss": 0.0506, "lr": 1.8191180618693604e-06, "epoch": 1.3751697216564833, "percentage": 27.5, "elapsed_time": "0:25:27", "remaining_time": "1:07:05", "throughput": 10183.12, "total_tokens": 15552384}
{"current_steps": 16210, "total_steps": 58920, "loss": 0.0663, "lr": 1.8189481066487983e-06, "epoch": 1.3755940257976917, "percentage": 27.51, "elapsed_time": "0:25:27", "remaining_time": "1:07:05", "throughput": 10183.51, "total_tokens": 15556800}
{"current_steps": 16215, "total_steps": 58920, "loss": 0.06, "lr": 1.818778079568497e-06, "epoch": 1.3760183299389002, "percentage": 27.52, "elapsed_time": "0:25:28", "remaining_time": "1:07:04", "throughput": 10183.78, "total_tokens": 15560960}
{"current_steps": 16220, "total_steps": 58920, "loss": 0.0553, "lr": 1.818607980643375e-06, "epoch": 1.3764426340801086, "percentage": 27.53, "elapsed_time": "0:25:28", "remaining_time": "1:07:03", "throughput": 10184.42, "total_tokens": 15565888}
{"current_steps": 16225, "total_steps": 58920, "loss": 0.0634, "lr": 1.818437809888359e-06, "epoch": 1.376866938221317, "percentage": 27.54, "elapsed_time": "0:25:28", "remaining_time": "1:07:02", "throughput": 10184.98, "total_tokens": 15570624}
{"current_steps": 16230, "total_steps": 58920, "loss": 0.125, "lr": 1.8182675673183794e-06, "epoch": 1.3772912423625254, "percentage": 27.55, "elapsed_time": "0:25:29", "remaining_time": "1:07:02", "throughput": 10185.43, "total_tokens": 15575168}
{"current_steps": 16235, "total_steps": 58920, "loss": 0.0141, "lr": 1.8180972529483753e-06, "epoch": 1.3777155465037338, "percentage": 27.55, "elapsed_time": "0:25:29", "remaining_time": "1:07:01", "throughput": 10185.9, "total_tokens": 15579712}
{"current_steps": 16240, "total_steps": 58920, "loss": 0.0191, "lr": 1.8179268667932909e-06, "epoch": 1.3781398506449423, "percentage": 27.56, "elapsed_time": "0:25:29", "remaining_time": "1:07:00", "throughput": 10186.41, "total_tokens": 15584384}
{"current_steps": 16245, "total_steps": 58920, "loss": 0.0222, "lr": 1.8177564088680773e-06, "epoch": 1.3785641547861507, "percentage": 27.57, "elapsed_time": "0:25:30", "remaining_time": "1:07:00", "throughput": 10187.22, "total_tokens": 15589632}
{"current_steps": 16250, "total_steps": 58920, "loss": 0.0867, "lr": 1.8175858791876907e-06, "epoch": 1.378988458927359, "percentage": 27.58, "elapsed_time": "0:25:30", "remaining_time": "1:06:59", "throughput": 10187.62, "total_tokens": 15594048}
{"current_steps": 16255, "total_steps": 58920, "loss": 0.0037, "lr": 1.817415277767096e-06, "epoch": 1.3794127630685675, "percentage": 27.59, "elapsed_time": "0:25:31", "remaining_time": "1:06:58", "throughput": 10188.28, "total_tokens": 15598976}
{"current_steps": 16260, "total_steps": 58920, "loss": 0.0242, "lr": 1.8172446046212614e-06, "epoch": 1.379837067209776, "percentage": 27.6, "elapsed_time": "0:25:31", "remaining_time": "1:06:57", "throughput": 10188.95, "total_tokens": 15603904}
{"current_steps": 16265, "total_steps": 58920, "loss": 0.0139, "lr": 1.8170738597651633e-06, "epoch": 1.3802613713509844, "percentage": 27.61, "elapsed_time": "0:25:31", "remaining_time": "1:06:57", "throughput": 10189.35, "total_tokens": 15608320}
{"current_steps": 16270, "total_steps": 58920, "loss": 0.0576, "lr": 1.8169030432137844e-06, "epoch": 1.3806856754921928, "percentage": 27.61, "elapsed_time": "0:25:32", "remaining_time": "1:06:56", "throughput": 10190.17, "total_tokens": 15613568}
{"current_steps": 16275, "total_steps": 58920, "loss": 0.0493, "lr": 1.8167321549821125e-06, "epoch": 1.3811099796334012, "percentage": 27.62, "elapsed_time": "0:25:32", "remaining_time": "1:06:55", "throughput": 10190.86, "total_tokens": 15618560}
{"current_steps": 16280, "total_steps": 58920, "loss": 0.0255, "lr": 1.8165611950851432e-06, "epoch": 1.3815342837746096, "percentage": 27.63, "elapsed_time": "0:25:32", "remaining_time": "1:06:55", "throughput": 10191.54, "total_tokens": 15623552}
{"current_steps": 16285, "total_steps": 58920, "loss": 0.0058, "lr": 1.8163901635378768e-06, "epoch": 1.381958587915818, "percentage": 27.64, "elapsed_time": "0:25:33", "remaining_time": "1:06:54", "throughput": 10192.01, "total_tokens": 15628096}
{"current_steps": 16290, "total_steps": 58920, "loss": 0.0419, "lr": 1.8162190603553214e-06, "epoch": 1.3823828920570265, "percentage": 27.65, "elapsed_time": "0:25:33", "remaining_time": "1:06:53", "throughput": 10192.26, "total_tokens": 15632256}
{"current_steps": 16295, "total_steps": 58920, "loss": 0.0409, "lr": 1.8160478855524902e-06, "epoch": 1.382807196198235, "percentage": 27.66, "elapsed_time": "0:25:34", "remaining_time": "1:06:53", "throughput": 10193.2, "total_tokens": 15637760}
{"current_steps": 16300, "total_steps": 58920, "loss": 0.0241, "lr": 1.8158766391444036e-06, "epoch": 1.3832315003394433, "percentage": 27.66, "elapsed_time": "0:25:34", "remaining_time": "1:06:52", "throughput": 10193.88, "total_tokens": 15642752}
{"current_steps": 16305, "total_steps": 58920, "loss": 0.0728, "lr": 1.8157053211460875e-06, "epoch": 1.3836558044806517, "percentage": 27.67, "elapsed_time": "0:25:34", "remaining_time": "1:06:51", "throughput": 10194.44, "total_tokens": 15647488}
{"current_steps": 16310, "total_steps": 58920, "loss": 0.0212, "lr": 1.8155339315725746e-06, "epoch": 1.3840801086218602, "percentage": 27.68, "elapsed_time": "0:25:35", "remaining_time": "1:06:50", "throughput": 10195.32, "total_tokens": 15652864}
{"current_steps": 16315, "total_steps": 58920, "loss": 0.0423, "lr": 1.8153624704389037e-06, "epoch": 1.3845044127630686, "percentage": 27.69, "elapsed_time": "0:25:35", "remaining_time": "1:06:50", "throughput": 10196.12, "total_tokens": 15658112}
{"current_steps": 16320, "total_steps": 58920, "loss": 0.0336, "lr": 1.81519093776012e-06, "epoch": 1.384928716904277, "percentage": 27.7, "elapsed_time": "0:25:36", "remaining_time": "1:06:49", "throughput": 10196.96, "total_tokens": 15663424}
{"current_steps": 16325, "total_steps": 58920, "loss": 0.0111, "lr": 1.8150193335512744e-06, "epoch": 1.3853530210454854, "percentage": 27.71, "elapsed_time": "0:25:36", "remaining_time": "1:06:48", "throughput": 10197.48, "total_tokens": 15668096}
{"current_steps": 16330, "total_steps": 58920, "loss": 0.039, "lr": 1.814847657827425e-06, "epoch": 1.3857773251866938, "percentage": 27.72, "elapsed_time": "0:25:36", "remaining_time": "1:06:48", "throughput": 10198.09, "total_tokens": 15672896}
{"current_steps": 16335, "total_steps": 58920, "loss": 0.0547, "lr": 1.8146759106036357e-06, "epoch": 1.3862016293279023, "percentage": 27.72, "elapsed_time": "0:25:37", "remaining_time": "1:06:47", "throughput": 10199.1, "total_tokens": 15678528}
{"current_steps": 16340, "total_steps": 58920, "loss": 0.0673, "lr": 1.8145040918949768e-06, "epoch": 1.3866259334691107, "percentage": 27.73, "elapsed_time": "0:25:37", "remaining_time": "1:06:46", "throughput": 10199.59, "total_tokens": 15683136}
{"current_steps": 16345, "total_steps": 58920, "loss": 0.0027, "lr": 1.8143322017165242e-06, "epoch": 1.387050237610319, "percentage": 27.74, "elapsed_time": "0:25:37", "remaining_time": "1:06:46", "throughput": 10199.94, "total_tokens": 15687488}
{"current_steps": 16350, "total_steps": 58920, "loss": 0.0155, "lr": 1.8141602400833613e-06, "epoch": 1.3874745417515275, "percentage": 27.75, "elapsed_time": "0:25:38", "remaining_time": "1:06:45", "throughput": 10200.33, "total_tokens": 15691904}
{"current_steps": 16355, "total_steps": 58920, "loss": 0.0974, "lr": 1.8139882070105767e-06, "epoch": 1.387898845892736, "percentage": 27.76, "elapsed_time": "0:25:38", "remaining_time": "1:06:44", "throughput": 10200.81, "total_tokens": 15696512}
{"current_steps": 16360, "total_steps": 58920, "loss": 0.0255, "lr": 1.813816102513266e-06, "epoch": 1.3883231500339444, "percentage": 27.77, "elapsed_time": "0:25:39", "remaining_time": "1:06:43", "throughput": 10201.19, "total_tokens": 15700928}
{"current_steps": 16365, "total_steps": 58920, "loss": 0.0189, "lr": 1.8136439266065304e-06, "epoch": 1.3887474541751528, "percentage": 27.77, "elapsed_time": "0:25:39", "remaining_time": "1:06:43", "throughput": 10202.01, "total_tokens": 15706176}
{"current_steps": 16370, "total_steps": 58920, "loss": 0.0011, "lr": 1.8134716793054781e-06, "epoch": 1.3891717583163612, "percentage": 27.78, "elapsed_time": "0:25:39", "remaining_time": "1:06:42", "throughput": 10202.63, "total_tokens": 15711040}
{"current_steps": 16375, "total_steps": 58920, "loss": 0.0995, "lr": 1.8132993606252226e-06, "epoch": 1.3895960624575696, "percentage": 27.79, "elapsed_time": "0:25:40", "remaining_time": "1:06:41", "throughput": 10203.31, "total_tokens": 15716032}
{"current_steps": 16380, "total_steps": 58920, "loss": 0.0231, "lr": 1.813126970580885e-06, "epoch": 1.390020366598778, "percentage": 27.8, "elapsed_time": "0:25:40", "remaining_time": "1:06:41", "throughput": 10203.85, "total_tokens": 15720768}
{"current_steps": 16385, "total_steps": 58920, "loss": 0.0468, "lr": 1.8129545091875914e-06, "epoch": 1.3904446707399865, "percentage": 27.81, "elapsed_time": "0:25:41", "remaining_time": "1:06:40", "throughput": 10204.41, "total_tokens": 15725504}
{"current_steps": 16390, "total_steps": 58920, "loss": 0.0778, "lr": 1.8127819764604747e-06, "epoch": 1.3908689748811949, "percentage": 27.82, "elapsed_time": "0:25:41", "remaining_time": "1:06:39", "throughput": 10204.83, "total_tokens": 15729984}
{"current_steps": 16395, "total_steps": 58920, "loss": 0.1377, "lr": 1.8126093724146742e-06, "epoch": 1.3912932790224033, "percentage": 27.83, "elapsed_time": "0:25:41", "remaining_time": "1:06:39", "throughput": 10205.36, "total_tokens": 15734656}
{"current_steps": 16400, "total_steps": 58920, "loss": 0.0017, "lr": 1.8124366970653353e-06, "epoch": 1.3917175831636117, "percentage": 27.83, "elapsed_time": "0:25:42", "remaining_time": "1:06:38", "throughput": 10206.01, "total_tokens": 15739584}
{"current_steps": 16405, "total_steps": 58920, "loss": 0.0171, "lr": 1.8122639504276094e-06, "epoch": 1.3921418873048201, "percentage": 27.84, "elapsed_time": "0:25:42", "remaining_time": "1:06:37", "throughput": 10206.65, "total_tokens": 15744576}
{"current_steps": 16410, "total_steps": 58920, "loss": 0.025, "lr": 1.8120911325166545e-06, "epoch": 1.3925661914460286, "percentage": 27.85, "elapsed_time": "0:25:42", "remaining_time": "1:06:37", "throughput": 10207.38, "total_tokens": 15749632}
{"current_steps": 16415, "total_steps": 58920, "loss": 0.0236, "lr": 1.8119182433476348e-06, "epoch": 1.392990495587237, "percentage": 27.86, "elapsed_time": "0:25:43", "remaining_time": "1:06:36", "throughput": 10207.96, "total_tokens": 15754432}
{"current_steps": 16420, "total_steps": 58920, "loss": 0.0238, "lr": 1.8117452829357206e-06, "epoch": 1.3934147997284454, "percentage": 27.87, "elapsed_time": "0:25:43", "remaining_time": "1:06:35", "throughput": 10208.41, "total_tokens": 15758976}
{"current_steps": 16425, "total_steps": 58920, "loss": 0.0215, "lr": 1.8115722512960886e-06, "epoch": 1.3938391038696538, "percentage": 27.88, "elapsed_time": "0:25:44", "remaining_time": "1:06:34", "throughput": 10209.0, "total_tokens": 15763776}
{"current_steps": 16430, "total_steps": 58920, "loss": 0.0322, "lr": 1.8113991484439217e-06, "epoch": 1.3942634080108622, "percentage": 27.89, "elapsed_time": "0:25:44", "remaining_time": "1:06:34", "throughput": 10209.64, "total_tokens": 15768704}
{"current_steps": 16435, "total_steps": 58920, "loss": 0.0631, "lr": 1.811225974394409e-06, "epoch": 1.3946877121520707, "percentage": 27.89, "elapsed_time": "0:25:44", "remaining_time": "1:06:33", "throughput": 10210.32, "total_tokens": 15773696}
{"current_steps": 16440, "total_steps": 58920, "loss": 0.0394, "lr": 1.8110527291627462e-06, "epoch": 1.395112016293279, "percentage": 27.9, "elapsed_time": "0:25:45", "remaining_time": "1:06:32", "throughput": 10210.62, "total_tokens": 15777920}
{"current_steps": 16445, "total_steps": 58920, "loss": 0.075, "lr": 1.8108794127641346e-06, "epoch": 1.3955363204344875, "percentage": 27.91, "elapsed_time": "0:25:45", "remaining_time": "1:06:32", "throughput": 10211.16, "total_tokens": 15782656}
{"current_steps": 16450, "total_steps": 58920, "loss": 0.0024, "lr": 1.8107060252137822e-06, "epoch": 1.395960624575696, "percentage": 27.92, "elapsed_time": "0:25:46", "remaining_time": "1:06:31", "throughput": 10212.1, "total_tokens": 15788160}
{"current_steps": 16455, "total_steps": 58920, "loss": 0.05, "lr": 1.810532566526903e-06, "epoch": 1.3963849287169043, "percentage": 27.93, "elapsed_time": "0:25:46", "remaining_time": "1:06:30", "throughput": 10212.71, "total_tokens": 15793024}
{"current_steps": 16460, "total_steps": 58920, "loss": 0.0339, "lr": 1.8103590367187177e-06, "epoch": 1.3968092328581128, "percentage": 27.94, "elapsed_time": "0:25:46", "remaining_time": "1:06:30", "throughput": 10213.37, "total_tokens": 15798016}
{"current_steps": 16465, "total_steps": 58920, "loss": 0.0362, "lr": 1.8101854358044526e-06, "epoch": 1.3972335369993212, "percentage": 27.94, "elapsed_time": "0:25:47", "remaining_time": "1:06:29", "throughput": 10213.76, "total_tokens": 15802432}
{"current_steps": 16470, "total_steps": 58920, "loss": 0.128, "lr": 1.8100117637993408e-06, "epoch": 1.3976578411405296, "percentage": 27.95, "elapsed_time": "0:25:47", "remaining_time": "1:06:28", "throughput": 10214.51, "total_tokens": 15807616}
{"current_steps": 16475, "total_steps": 58920, "loss": 0.0108, "lr": 1.8098380207186211e-06, "epoch": 1.398082145281738, "percentage": 27.96, "elapsed_time": "0:25:47", "remaining_time": "1:06:28", "throughput": 10215.05, "total_tokens": 15812352}
{"current_steps": 16480, "total_steps": 58920, "loss": 0.0698, "lr": 1.8096642065775392e-06, "epoch": 1.3985064494229464, "percentage": 27.97, "elapsed_time": "0:25:48", "remaining_time": "1:06:27", "throughput": 10215.62, "total_tokens": 15817152}
{"current_steps": 16485, "total_steps": 58920, "loss": 0.0302, "lr": 1.8094903213913463e-06, "epoch": 1.3989307535641549, "percentage": 27.98, "elapsed_time": "0:25:48", "remaining_time": "1:06:26", "throughput": 10216.29, "total_tokens": 15822080}
{"current_steps": 16490, "total_steps": 58920, "loss": 0.0266, "lr": 1.8093163651753004e-06, "epoch": 1.3993550577053633, "percentage": 27.99, "elapsed_time": "0:25:49", "remaining_time": "1:06:25", "throughput": 10216.53, "total_tokens": 15826240}
{"current_steps": 16495, "total_steps": 58920, "loss": 0.0388, "lr": 1.8091423379446655e-06, "epoch": 1.3997793618465717, "percentage": 28.0, "elapsed_time": "0:25:49", "remaining_time": "1:06:25", "throughput": 10217.44, "total_tokens": 15831744}
{"current_steps": 16500, "total_steps": 58920, "loss": 0.0162, "lr": 1.8089682397147116e-06, "epoch": 1.4002036659877801, "percentage": 28.0, "elapsed_time": "0:25:49", "remaining_time": "1:06:24", "throughput": 10217.87, "total_tokens": 15836224}
{"current_steps": 16505, "total_steps": 58920, "loss": 0.083, "lr": 1.808794070500716e-06, "epoch": 1.4006279701289885, "percentage": 28.01, "elapsed_time": "0:25:50", "remaining_time": "1:06:23", "throughput": 10218.37, "total_tokens": 15840896}
{"current_steps": 16510, "total_steps": 58920, "loss": 0.0019, "lr": 1.8086198303179604e-06, "epoch": 1.4010522742701967, "percentage": 28.02, "elapsed_time": "0:25:50", "remaining_time": "1:06:23", "throughput": 10218.66, "total_tokens": 15845120}
{"current_steps": 16515, "total_steps": 58920, "loss": 0.0559, "lr": 1.8084455191817343e-06, "epoch": 1.4014765784114052, "percentage": 28.03, "elapsed_time": "0:25:50", "remaining_time": "1:06:22", "throughput": 10219.35, "total_tokens": 15850176}
{"current_steps": 16520, "total_steps": 58920, "loss": 0.0554, "lr": 1.8082711371073325e-06, "epoch": 1.4019008825526136, "percentage": 28.04, "elapsed_time": "0:25:51", "remaining_time": "1:06:21", "throughput": 10219.96, "total_tokens": 15855040}
{"current_steps": 16525, "total_steps": 58920, "loss": 0.0259, "lr": 1.8080966841100568e-06, "epoch": 1.402325186693822, "percentage": 28.05, "elapsed_time": "0:25:51", "remaining_time": "1:06:21", "throughput": 10220.46, "total_tokens": 15859712}
{"current_steps": 16530, "total_steps": 58920, "loss": 0.0018, "lr": 1.8079221602052151e-06, "epoch": 1.4027494908350304, "percentage": 28.05, "elapsed_time": "0:25:52", "remaining_time": "1:06:20", "throughput": 10220.94, "total_tokens": 15864320}
{"current_steps": 16535, "total_steps": 58920, "loss": 0.0012, "lr": 1.8077475654081207e-06, "epoch": 1.4031737949762388, "percentage": 28.06, "elapsed_time": "0:25:52", "remaining_time": "1:06:19", "throughput": 10221.29, "total_tokens": 15868672}
{"current_steps": 16540, "total_steps": 58920, "loss": 0.068, "lr": 1.8075728997340933e-06, "epoch": 1.4035980991174473, "percentage": 28.07, "elapsed_time": "0:25:52", "remaining_time": "1:06:18", "throughput": 10222.04, "total_tokens": 15873856}
{"current_steps": 16545, "total_steps": 58920, "loss": 0.1044, "lr": 1.80739816319846e-06, "epoch": 1.4040224032586557, "percentage": 28.08, "elapsed_time": "0:25:53", "remaining_time": "1:06:18", "throughput": 10222.69, "total_tokens": 15878848}
{"current_steps": 16550, "total_steps": 58920, "loss": 0.0368, "lr": 1.8072233558165533e-06, "epoch": 1.404446707399864, "percentage": 28.09, "elapsed_time": "0:25:53", "remaining_time": "1:06:17", "throughput": 10223.08, "total_tokens": 15883264}
{"current_steps": 16555, "total_steps": 58920, "loss": 0.0149, "lr": 1.807048477603711e-06, "epoch": 1.4048710115410725, "percentage": 28.1, "elapsed_time": "0:25:54", "remaining_time": "1:06:16", "throughput": 10223.73, "total_tokens": 15888192}
{"current_steps": 16560, "total_steps": 58920, "loss": 0.0006, "lr": 1.806873528575279e-06, "epoch": 1.405295315682281, "percentage": 28.11, "elapsed_time": "0:25:54", "remaining_time": "1:06:16", "throughput": 10224.56, "total_tokens": 15893504}
{"current_steps": 16565, "total_steps": 58920, "loss": 0.0384, "lr": 1.8066985087466082e-06, "epoch": 1.4057196198234894, "percentage": 28.11, "elapsed_time": "0:25:54", "remaining_time": "1:06:15", "throughput": 10225.01, "total_tokens": 15898048}
{"current_steps": 16570, "total_steps": 58920, "loss": 0.0538, "lr": 1.8065234181330556e-06, "epoch": 1.4061439239646978, "percentage": 28.12, "elapsed_time": "0:25:55", "remaining_time": "1:06:14", "throughput": 10225.49, "total_tokens": 15902656}
{"current_steps": 16575, "total_steps": 58920, "loss": 0.0471, "lr": 1.806348256749985e-06, "epoch": 1.4065682281059062, "percentage": 28.13, "elapsed_time": "0:25:55", "remaining_time": "1:06:14", "throughput": 10226.02, "total_tokens": 15907392}
{"current_steps": 16580, "total_steps": 58920, "loss": 0.025, "lr": 1.8061730246127662e-06, "epoch": 1.4069925322471146, "percentage": 28.14, "elapsed_time": "0:25:55", "remaining_time": "1:06:13", "throughput": 10226.62, "total_tokens": 15912256}
{"current_steps": 16585, "total_steps": 58920, "loss": 0.0348, "lr": 1.8059977217367751e-06, "epoch": 1.407416836388323, "percentage": 28.15, "elapsed_time": "0:25:56", "remaining_time": "1:06:12", "throughput": 10227.14, "total_tokens": 15916928}
{"current_steps": 16590, "total_steps": 58920, "loss": 0.0277, "lr": 1.8058223481373941e-06, "epoch": 1.4078411405295315, "percentage": 28.16, "elapsed_time": "0:25:56", "remaining_time": "1:06:12", "throughput": 10227.33, "total_tokens": 15921024}
{"current_steps": 16595, "total_steps": 58920, "loss": 0.0149, "lr": 1.8056469038300115e-06, "epoch": 1.4082654446707399, "percentage": 28.17, "elapsed_time": "0:25:57", "remaining_time": "1:06:11", "throughput": 10228.21, "total_tokens": 15926464}
{"current_steps": 16600, "total_steps": 58920, "loss": 0.0253, "lr": 1.8054713888300217e-06, "epoch": 1.4086897488119483, "percentage": 28.17, "elapsed_time": "0:25:57", "remaining_time": "1:06:10", "throughput": 10228.75, "total_tokens": 15931200}
{"current_steps": 16605, "total_steps": 58920, "loss": 0.0436, "lr": 1.8052958031528255e-06, "epoch": 1.4091140529531567, "percentage": 28.18, "elapsed_time": "0:25:57", "remaining_time": "1:06:09", "throughput": 10229.19, "total_tokens": 15935744}
{"current_steps": 16610, "total_steps": 58920, "loss": 0.04, "lr": 1.8051201468138306e-06, "epoch": 1.4095383570943651, "percentage": 28.19, "elapsed_time": "0:25:58", "remaining_time": "1:06:09", "throughput": 10229.74, "total_tokens": 15940480}
{"current_steps": 16615, "total_steps": 58920, "loss": 0.0143, "lr": 1.8049444198284494e-06, "epoch": 1.4099626612355736, "percentage": 28.2, "elapsed_time": "0:25:58", "remaining_time": "1:06:08", "throughput": 10230.07, "total_tokens": 15944832}
{"current_steps": 16620, "total_steps": 58920, "loss": 0.1047, "lr": 1.8047686222121015e-06, "epoch": 1.410386965376782, "percentage": 28.21, "elapsed_time": "0:25:58", "remaining_time": "1:06:07", "throughput": 10230.49, "total_tokens": 15949312}
{"current_steps": 16625, "total_steps": 58920, "loss": 0.0448, "lr": 1.804592753980213e-06, "epoch": 1.4108112695179904, "percentage": 28.22, "elapsed_time": "0:25:59", "remaining_time": "1:06:07", "throughput": 10230.91, "total_tokens": 15953792}
{"current_steps": 16630, "total_steps": 58920, "loss": 0.0531, "lr": 1.8044168151482148e-06, "epoch": 1.4112355736591988, "percentage": 28.22, "elapsed_time": "0:25:59", "remaining_time": "1:06:06", "throughput": 10231.5, "total_tokens": 15958656}
{"current_steps": 16635, "total_steps": 58920, "loss": 0.0287, "lr": 1.8042408057315456e-06, "epoch": 1.4116598778004072, "percentage": 28.23, "elapsed_time": "0:26:00", "remaining_time": "1:06:05", "throughput": 10231.97, "total_tokens": 15963264}
{"current_steps": 16640, "total_steps": 58920, "loss": 0.0344, "lr": 1.8040647257456495e-06, "epoch": 1.4120841819416157, "percentage": 28.24, "elapsed_time": "0:26:00", "remaining_time": "1:06:05", "throughput": 10232.92, "total_tokens": 15968896}
{"current_steps": 16645, "total_steps": 58920, "loss": 0.0268, "lr": 1.8038885752059768e-06, "epoch": 1.412508486082824, "percentage": 28.25, "elapsed_time": "0:26:00", "remaining_time": "1:06:04", "throughput": 10233.84, "total_tokens": 15974400}
{"current_steps": 16650, "total_steps": 58920, "loss": 0.0362, "lr": 1.8037123541279838e-06, "epoch": 1.4129327902240325, "percentage": 28.26, "elapsed_time": "0:26:01", "remaining_time": "1:06:03", "throughput": 10234.36, "total_tokens": 15979136}
{"current_steps": 16655, "total_steps": 58920, "loss": 0.0282, "lr": 1.803536062527134e-06, "epoch": 1.413357094365241, "percentage": 28.27, "elapsed_time": "0:26:01", "remaining_time": "1:06:03", "throughput": 10234.67, "total_tokens": 15983424}
{"current_steps": 16660, "total_steps": 58920, "loss": 0.0251, "lr": 1.8033597004188952e-06, "epoch": 1.4137813985064493, "percentage": 28.28, "elapsed_time": "0:26:02", "remaining_time": "1:06:02", "throughput": 10235.21, "total_tokens": 15988160}
{"current_steps": 16665, "total_steps": 58920, "loss": 0.0369, "lr": 1.8031832678187437e-06, "epoch": 1.4142057026476578, "percentage": 28.28, "elapsed_time": "0:26:02", "remaining_time": "1:06:01", "throughput": 10235.48, "total_tokens": 15992384}
{"current_steps": 16670, "total_steps": 58920, "loss": 0.0013, "lr": 1.80300676474216e-06, "epoch": 1.4146300067888662, "percentage": 28.29, "elapsed_time": "0:26:02", "remaining_time": "1:06:00", "throughput": 10236.0, "total_tokens": 15997120}
{"current_steps": 16675, "total_steps": 58920, "loss": 0.1515, "lr": 1.8028301912046322e-06, "epoch": 1.4150543109300746, "percentage": 28.3, "elapsed_time": "0:26:03", "remaining_time": "1:06:00", "throughput": 10236.42, "total_tokens": 16001664}
{"current_steps": 16680, "total_steps": 58920, "loss": 0.0869, "lr": 1.8026535472216538e-06, "epoch": 1.415478615071283, "percentage": 28.31, "elapsed_time": "0:26:03", "remaining_time": "1:05:59", "throughput": 10236.89, "total_tokens": 16006272}
{"current_steps": 16685, "total_steps": 58920, "loss": 0.0696, "lr": 1.8024768328087245e-06, "epoch": 1.4159029192124915, "percentage": 28.32, "elapsed_time": "0:26:03", "remaining_time": "1:05:58", "throughput": 10237.3, "total_tokens": 16010752}
{"current_steps": 16690, "total_steps": 58920, "loss": 0.0413, "lr": 1.8023000479813503e-06, "epoch": 1.4163272233536999, "percentage": 28.33, "elapsed_time": "0:26:04", "remaining_time": "1:05:58", "throughput": 10238.01, "total_tokens": 16015872}
{"current_steps": 16695, "total_steps": 58920, "loss": 0.031, "lr": 1.8021231927550438e-06, "epoch": 1.4167515274949083, "percentage": 28.34, "elapsed_time": "0:26:04", "remaining_time": "1:05:57", "throughput": 10238.45, "total_tokens": 16020416}
{"current_steps": 16700, "total_steps": 58920, "loss": 0.0462, "lr": 1.8019462671453232e-06, "epoch": 1.4171758316361167, "percentage": 28.34, "elapsed_time": "0:26:05", "remaining_time": "1:05:56", "throughput": 10238.93, "total_tokens": 16025024}
{"current_steps": 16705, "total_steps": 58920, "loss": 0.004, "lr": 1.8017692711677128e-06, "epoch": 1.4176001357773251, "percentage": 28.35, "elapsed_time": "0:26:05", "remaining_time": "1:05:56", "throughput": 10239.46, "total_tokens": 16029760}
{"current_steps": 16710, "total_steps": 58920, "loss": 0.0014, "lr": 1.8015922048377437e-06, "epoch": 1.4180244399185336, "percentage": 28.36, "elapsed_time": "0:26:05", "remaining_time": "1:05:55", "throughput": 10239.99, "total_tokens": 16034496}
{"current_steps": 16715, "total_steps": 58920, "loss": 0.0305, "lr": 1.8014150681709527e-06, "epoch": 1.418448744059742, "percentage": 28.37, "elapsed_time": "0:26:06", "remaining_time": "1:05:54", "throughput": 10240.53, "total_tokens": 16039232}
{"current_steps": 16720, "total_steps": 58920, "loss": 0.0418, "lr": 1.8012378611828833e-06, "epoch": 1.4188730482009504, "percentage": 28.38, "elapsed_time": "0:26:06", "remaining_time": "1:05:54", "throughput": 10241.03, "total_tokens": 16043904}
{"current_steps": 16725, "total_steps": 58920, "loss": 0.106, "lr": 1.8010605838890842e-06, "epoch": 1.4192973523421588, "percentage": 28.39, "elapsed_time": "0:26:07", "remaining_time": "1:05:53", "throughput": 10241.5, "total_tokens": 16048512}
{"current_steps": 16730, "total_steps": 58920, "loss": 0.0411, "lr": 1.8008832363051112e-06, "epoch": 1.4197216564833672, "percentage": 28.39, "elapsed_time": "0:26:07", "remaining_time": "1:05:52", "throughput": 10242.23, "total_tokens": 16053568}
{"current_steps": 16735, "total_steps": 58920, "loss": 0.0529, "lr": 1.8007058184465258e-06, "epoch": 1.4201459606245757, "percentage": 28.4, "elapsed_time": "0:26:07", "remaining_time": "1:05:51", "throughput": 10242.59, "total_tokens": 16057984}
{"current_steps": 16740, "total_steps": 58920, "loss": 0.036, "lr": 1.8005283303288957e-06, "epoch": 1.420570264765784, "percentage": 28.41, "elapsed_time": "0:26:08", "remaining_time": "1:05:51", "throughput": 10242.92, "total_tokens": 16062336}
{"current_steps": 16745, "total_steps": 58920, "loss": 0.0457, "lr": 1.8003507719677948e-06, "epoch": 1.4209945689069925, "percentage": 28.42, "elapsed_time": "0:26:08", "remaining_time": "1:05:50", "throughput": 10243.36, "total_tokens": 16066944}
{"current_steps": 16750, "total_steps": 58920, "loss": 0.0611, "lr": 1.8001731433788035e-06, "epoch": 1.421418873048201, "percentage": 28.43, "elapsed_time": "0:26:08", "remaining_time": "1:05:49", "throughput": 10243.92, "total_tokens": 16071744}
{"current_steps": 16755, "total_steps": 58920, "loss": 0.0328, "lr": 1.7999954445775076e-06, "epoch": 1.4218431771894093, "percentage": 28.44, "elapsed_time": "0:26:09", "remaining_time": "1:05:49", "throughput": 10244.64, "total_tokens": 16076864}
{"current_steps": 16760, "total_steps": 58920, "loss": 0.0566, "lr": 1.7998176755795003e-06, "epoch": 1.4222674813306178, "percentage": 28.45, "elapsed_time": "0:26:09", "remaining_time": "1:05:48", "throughput": 10245.45, "total_tokens": 16082176}
{"current_steps": 16765, "total_steps": 58920, "loss": 0.0129, "lr": 1.7996398364003793e-06, "epoch": 1.4226917854718262, "percentage": 28.45, "elapsed_time": "0:26:10", "remaining_time": "1:05:47", "throughput": 10246.13, "total_tokens": 16087168}
{"current_steps": 16770, "total_steps": 58920, "loss": 0.0016, "lr": 1.7994619270557497e-06, "epoch": 1.4231160896130346, "percentage": 28.46, "elapsed_time": "0:26:10", "remaining_time": "1:05:47", "throughput": 10246.88, "total_tokens": 16092352}
{"current_steps": 16775, "total_steps": 58920, "loss": 0.0016, "lr": 1.7992839475612226e-06, "epoch": 1.423540393754243, "percentage": 28.47, "elapsed_time": "0:26:10", "remaining_time": "1:05:46", "throughput": 10247.23, "total_tokens": 16096704}
{"current_steps": 16780, "total_steps": 58920, "loss": 0.0558, "lr": 1.7991058979324149e-06, "epoch": 1.4239646978954514, "percentage": 28.48, "elapsed_time": "0:26:11", "remaining_time": "1:05:45", "throughput": 10248.02, "total_tokens": 16101952}
{"current_steps": 16785, "total_steps": 58920, "loss": 0.075, "lr": 1.7989277781849499e-06, "epoch": 1.4243890020366599, "percentage": 28.49, "elapsed_time": "0:26:11", "remaining_time": "1:05:45", "throughput": 10248.56, "total_tokens": 16106688}
{"current_steps": 16790, "total_steps": 58920, "loss": 0.0152, "lr": 1.798749588334457e-06, "epoch": 1.4248133061778683, "percentage": 28.5, "elapsed_time": "0:26:11", "remaining_time": "1:05:44", "throughput": 10249.21, "total_tokens": 16111680}
{"current_steps": 16795, "total_steps": 58920, "loss": 0.0313, "lr": 1.798571328396571e-06, "epoch": 1.4252376103190767, "percentage": 28.5, "elapsed_time": "0:26:12", "remaining_time": "1:05:43", "throughput": 10249.62, "total_tokens": 16116224}
{"current_steps": 16800, "total_steps": 58920, "loss": 0.0385, "lr": 1.7983929983869348e-06, "epoch": 1.4256619144602851, "percentage": 28.51, "elapsed_time": "0:26:12", "remaining_time": "1:05:43", "throughput": 10250.01, "total_tokens": 16120704}
{"current_steps": 16805, "total_steps": 58920, "loss": 0.0393, "lr": 1.7982145983211953e-06, "epoch": 1.4260862186014935, "percentage": 28.52, "elapsed_time": "0:26:13", "remaining_time": "1:05:42", "throughput": 10250.52, "total_tokens": 16125440}
{"current_steps": 16810, "total_steps": 58920, "loss": 0.0856, "lr": 1.7980361282150068e-06, "epoch": 1.426510522742702, "percentage": 28.53, "elapsed_time": "0:26:13", "remaining_time": "1:05:41", "throughput": 10251.07, "total_tokens": 16130240}
{"current_steps": 16815, "total_steps": 58920, "loss": 0.0007, "lr": 1.7978575880840293e-06, "epoch": 1.4269348268839104, "percentage": 28.54, "elapsed_time": "0:26:13", "remaining_time": "1:05:41", "throughput": 10251.48, "total_tokens": 16134720}
{"current_steps": 16820, "total_steps": 58920, "loss": 0.0541, "lr": 1.797678977943929e-06, "epoch": 1.4273591310251188, "percentage": 28.55, "elapsed_time": "0:26:14", "remaining_time": "1:05:40", "throughput": 10252.23, "total_tokens": 16139904}
{"current_steps": 16825, "total_steps": 58920, "loss": 0.1128, "lr": 1.7975002978103787e-06, "epoch": 1.4277834351663272, "percentage": 28.56, "elapsed_time": "0:26:14", "remaining_time": "1:05:39", "throughput": 10252.93, "total_tokens": 16144960}
{"current_steps": 16830, "total_steps": 58920, "loss": 0.0557, "lr": 1.7973215476990563e-06, "epoch": 1.4282077393075356, "percentage": 28.56, "elapsed_time": "0:26:15", "remaining_time": "1:05:39", "throughput": 10253.4, "total_tokens": 16149632}
{"current_steps": 16835, "total_steps": 58920, "loss": 0.0289, "lr": 1.7971427276256471e-06, "epoch": 1.428632043448744, "percentage": 28.57, "elapsed_time": "0:26:15", "remaining_time": "1:05:38", "throughput": 10253.74, "total_tokens": 16153984}
{"current_steps": 16840, "total_steps": 58920, "loss": 0.0474, "lr": 1.7969638376058415e-06, "epoch": 1.4290563475899525, "percentage": 28.58, "elapsed_time": "0:26:15", "remaining_time": "1:05:37", "throughput": 10254.37, "total_tokens": 16158912}
{"current_steps": 16845, "total_steps": 58920, "loss": 0.065, "lr": 1.7967848776553365e-06, "epoch": 1.429480651731161, "percentage": 28.59, "elapsed_time": "0:26:16", "remaining_time": "1:05:36", "throughput": 10254.8, "total_tokens": 16163456}
{"current_steps": 16850, "total_steps": 58920, "loss": 0.05, "lr": 1.7966058477898354e-06, "epoch": 1.4299049558723693, "percentage": 28.6, "elapsed_time": "0:26:16", "remaining_time": "1:05:36", "throughput": 10255.28, "total_tokens": 16168064}
{"current_steps": 16855, "total_steps": 58920, "loss": 0.0014, "lr": 1.7964267480250473e-06, "epoch": 1.4303292600135777, "percentage": 28.61, "elapsed_time": "0:26:16", "remaining_time": "1:05:35", "throughput": 10255.71, "total_tokens": 16172608}
{"current_steps": 16860, "total_steps": 58920, "loss": 0.0573, "lr": 1.7962475783766875e-06, "epoch": 1.4307535641547862, "percentage": 28.62, "elapsed_time": "0:26:17", "remaining_time": "1:05:35", "throughput": 10258.28, "total_tokens": 16181824}
{"current_steps": 16865, "total_steps": 58920, "loss": 0.0011, "lr": 1.7960683388604774e-06, "epoch": 1.4311778682959946, "percentage": 28.62, "elapsed_time": "0:26:17", "remaining_time": "1:05:34", "throughput": 10258.91, "total_tokens": 16186752}
{"current_steps": 16870, "total_steps": 58920, "loss": 0.0212, "lr": 1.795889029492145e-06, "epoch": 1.431602172437203, "percentage": 28.63, "elapsed_time": "0:26:18", "remaining_time": "1:05:33", "throughput": 10259.45, "total_tokens": 16191552}
{"current_steps": 16875, "total_steps": 58920, "loss": 0.0402, "lr": 1.7957096502874236e-06, "epoch": 1.4320264765784114, "percentage": 28.64, "elapsed_time": "0:26:18", "remaining_time": "1:05:33", "throughput": 10260.47, "total_tokens": 16197312}
{"current_steps": 16880, "total_steps": 58920, "loss": 0.0189, "lr": 1.7955302012620533e-06, "epoch": 1.4324507807196198, "percentage": 28.65, "elapsed_time": "0:26:18", "remaining_time": "1:05:32", "throughput": 10260.98, "total_tokens": 16202048}
{"current_steps": 16885, "total_steps": 58920, "loss": 0.052, "lr": 1.7953506824317804e-06, "epoch": 1.4328750848608283, "percentage": 28.66, "elapsed_time": "0:26:19", "remaining_time": "1:05:31", "throughput": 10261.88, "total_tokens": 16207552}
{"current_steps": 16890, "total_steps": 58920, "loss": 0.0029, "lr": 1.7951710938123563e-06, "epoch": 1.4332993890020367, "percentage": 28.67, "elapsed_time": "0:26:19", "remaining_time": "1:05:31", "throughput": 10262.61, "total_tokens": 16212736}
{"current_steps": 16895, "total_steps": 58920, "loss": 0.016, "lr": 1.7949914354195396e-06, "epoch": 1.433723693143245, "percentage": 28.67, "elapsed_time": "0:26:20", "remaining_time": "1:05:30", "throughput": 10263.01, "total_tokens": 16217216}
{"current_steps": 16900, "total_steps": 58920, "loss": 0.0404, "lr": 1.7948117072690951e-06, "epoch": 1.4341479972844535, "percentage": 28.68, "elapsed_time": "0:26:20", "remaining_time": "1:05:29", "throughput": 10263.76, "total_tokens": 16222400}
{"current_steps": 16905, "total_steps": 58920, "loss": 0.0257, "lr": 1.7946319093767928e-06, "epoch": 1.434572301425662, "percentage": 28.69, "elapsed_time": "0:26:20", "remaining_time": "1:05:29", "throughput": 10264.27, "total_tokens": 16227072}
{"current_steps": 16910, "total_steps": 58920, "loss": 0.0508, "lr": 1.7944520417584097e-06, "epoch": 1.4349966055668704, "percentage": 28.7, "elapsed_time": "0:26:21", "remaining_time": "1:05:28", "throughput": 10264.82, "total_tokens": 16231808}
{"current_steps": 16915, "total_steps": 58920, "loss": 0.0837, "lr": 1.794272104429728e-06, "epoch": 1.4354209097080788, "percentage": 28.71, "elapsed_time": "0:26:21", "remaining_time": "1:05:27", "throughput": 10265.42, "total_tokens": 16236736}
{"current_steps": 16920, "total_steps": 58920, "loss": 0.0206, "lr": 1.794092097406537e-06, "epoch": 1.4358452138492872, "percentage": 28.72, "elapsed_time": "0:26:22", "remaining_time": "1:05:27", "throughput": 10266.12, "total_tokens": 16241856}
{"current_steps": 16925, "total_steps": 58920, "loss": 0.0526, "lr": 1.7939120207046315e-06, "epoch": 1.4362695179904956, "percentage": 28.73, "elapsed_time": "0:26:22", "remaining_time": "1:05:26", "throughput": 10266.93, "total_tokens": 16247168}
{"current_steps": 16930, "total_steps": 58920, "loss": 0.0013, "lr": 1.7937318743398121e-06, "epoch": 1.436693822131704, "percentage": 28.73, "elapsed_time": "0:26:22", "remaining_time": "1:05:25", "throughput": 10267.29, "total_tokens": 16251584}
{"current_steps": 16935, "total_steps": 58920, "loss": 0.046, "lr": 1.7935516583278871e-06, "epoch": 1.4371181262729125, "percentage": 28.74, "elapsed_time": "0:26:23", "remaining_time": "1:05:25", "throughput": 10267.81, "total_tokens": 16256320}
{"current_steps": 16940, "total_steps": 58920, "loss": 0.0541, "lr": 1.7933713726846688e-06, "epoch": 1.4375424304141209, "percentage": 28.75, "elapsed_time": "0:26:23", "remaining_time": "1:05:24", "throughput": 10268.19, "total_tokens": 16260736}
{"current_steps": 16945, "total_steps": 58920, "loss": 0.0309, "lr": 1.7931910174259775e-06, "epoch": 1.4379667345553293, "percentage": 28.76, "elapsed_time": "0:26:23", "remaining_time": "1:05:23", "throughput": 10268.61, "total_tokens": 16265280}
{"current_steps": 16950, "total_steps": 58920, "loss": 0.0573, "lr": 1.7930105925676378e-06, "epoch": 1.4383910386965377, "percentage": 28.77, "elapsed_time": "0:26:24", "remaining_time": "1:05:23", "throughput": 10269.49, "total_tokens": 16270784}
{"current_steps": 16955, "total_steps": 58920, "loss": 0.0015, "lr": 1.7928300981254817e-06, "epoch": 1.4388153428377461, "percentage": 28.78, "elapsed_time": "0:26:24", "remaining_time": "1:05:22", "throughput": 10270.06, "total_tokens": 16275648}
{"current_steps": 16960, "total_steps": 58920, "loss": 0.0316, "lr": 1.7926495341153474e-06, "epoch": 1.4392396469789546, "percentage": 28.78, "elapsed_time": "0:26:25", "remaining_time": "1:05:21", "throughput": 10270.38, "total_tokens": 16280000}
{"current_steps": 16965, "total_steps": 58920, "loss": 0.0227, "lr": 1.7924689005530783e-06, "epoch": 1.439663951120163, "percentage": 28.79, "elapsed_time": "0:26:25", "remaining_time": "1:05:21", "throughput": 10270.75, "total_tokens": 16284480}
{"current_steps": 16970, "total_steps": 58920, "loss": 0.0272, "lr": 1.7922881974545238e-06, "epoch": 1.4400882552613714, "percentage": 28.8, "elapsed_time": "0:26:25", "remaining_time": "1:05:20", "throughput": 10271.34, "total_tokens": 16289344}
{"current_steps": 16975, "total_steps": 58920, "loss": 0.0604, "lr": 1.792107424835541e-06, "epoch": 1.4405125594025798, "percentage": 28.81, "elapsed_time": "0:26:26", "remaining_time": "1:05:19", "throughput": 10272.01, "total_tokens": 16294400}
{"current_steps": 16980, "total_steps": 58920, "loss": 0.0613, "lr": 1.7919265827119916e-06, "epoch": 1.4409368635437882, "percentage": 28.82, "elapsed_time": "0:26:26", "remaining_time": "1:05:18", "throughput": 10272.23, "total_tokens": 16298560}
{"current_steps": 16985, "total_steps": 58920, "loss": 0.0005, "lr": 1.7917456710997435e-06, "epoch": 1.4413611676849967, "percentage": 28.83, "elapsed_time": "0:26:27", "remaining_time": "1:05:18", "throughput": 10272.89, "total_tokens": 16303616}
{"current_steps": 16990, "total_steps": 58920, "loss": 0.0226, "lr": 1.7915646900146716e-06, "epoch": 1.441785471826205, "percentage": 28.84, "elapsed_time": "0:26:27", "remaining_time": "1:05:17", "throughput": 10273.42, "total_tokens": 16308352}
{"current_steps": 16995, "total_steps": 58920, "loss": 0.0008, "lr": 1.791383639472656e-06, "epoch": 1.4422097759674135, "percentage": 28.84, "elapsed_time": "0:26:27", "remaining_time": "1:05:17", "throughput": 10274.11, "total_tokens": 16313472}
{"current_steps": 17000, "total_steps": 58920, "loss": 0.0008, "lr": 1.7912025194895834e-06, "epoch": 1.442634080108622, "percentage": 28.85, "elapsed_time": "0:26:28", "remaining_time": "1:05:16", "throughput": 10274.69, "total_tokens": 16318336}
{"current_steps": 17005, "total_steps": 58920, "loss": 0.0532, "lr": 1.7910213300813463e-06, "epoch": 1.4430583842498304, "percentage": 28.86, "elapsed_time": "0:26:28", "remaining_time": "1:05:15", "throughput": 10275.25, "total_tokens": 16323136}
{"current_steps": 17010, "total_steps": 58920, "loss": 0.0485, "lr": 1.7908400712638434e-06, "epoch": 1.4434826883910388, "percentage": 28.87, "elapsed_time": "0:26:28", "remaining_time": "1:05:14", "throughput": 10275.58, "total_tokens": 16327488}
{"current_steps": 17015, "total_steps": 58920, "loss": 0.0004, "lr": 1.7906587430529796e-06, "epoch": 1.4439069925322472, "percentage": 28.88, "elapsed_time": "0:26:29", "remaining_time": "1:05:14", "throughput": 10276.06, "total_tokens": 16332160}
{"current_steps": 17020, "total_steps": 58920, "loss": 0.0005, "lr": 1.7904773454646655e-06, "epoch": 1.4443312966734556, "percentage": 28.89, "elapsed_time": "0:26:29", "remaining_time": "1:05:13", "throughput": 10276.96, "total_tokens": 16337728}
{"current_steps": 17025, "total_steps": 58920, "loss": 0.0004, "lr": 1.7902958785148185e-06, "epoch": 1.444755600814664, "percentage": 28.9, "elapsed_time": "0:26:30", "remaining_time": "1:05:12", "throughput": 10277.43, "total_tokens": 16342336}
{"current_steps": 17030, "total_steps": 58920, "loss": 0.0502, "lr": 1.7901143422193616e-06, "epoch": 1.4451799049558725, "percentage": 28.9, "elapsed_time": "0:26:30", "remaining_time": "1:05:12", "throughput": 10278.2, "total_tokens": 16347648}
{"current_steps": 17035, "total_steps": 58920, "loss": 0.0003, "lr": 1.789932736594224e-06, "epoch": 1.4456042090970809, "percentage": 28.91, "elapsed_time": "0:26:30", "remaining_time": "1:05:11", "throughput": 10278.69, "total_tokens": 16352320}
{"current_steps": 17040, "total_steps": 58920, "loss": 0.0003, "lr": 1.7897510616553405e-06, "epoch": 1.4460285132382893, "percentage": 28.92, "elapsed_time": "0:26:31", "remaining_time": "1:05:10", "throughput": 10279.33, "total_tokens": 16357248}
{"current_steps": 17045, "total_steps": 58920, "loss": 0.0952, "lr": 1.789569317418653e-06, "epoch": 1.4464528173794977, "percentage": 28.93, "elapsed_time": "0:26:31", "remaining_time": "1:05:10", "throughput": 10280.2, "total_tokens": 16362752}
{"current_steps": 17050, "total_steps": 58920, "loss": 0.1072, "lr": 1.7893875039001087e-06, "epoch": 1.4468771215207061, "percentage": 28.94, "elapsed_time": "0:26:32", "remaining_time": "1:05:09", "throughput": 10281.08, "total_tokens": 16368256}
{"current_steps": 17055, "total_steps": 58920, "loss": 0.0711, "lr": 1.7892056211156608e-06, "epoch": 1.4473014256619146, "percentage": 28.95, "elapsed_time": "0:26:32", "remaining_time": "1:05:08", "throughput": 10281.48, "total_tokens": 16372736}
{"current_steps": 17060, "total_steps": 58920, "loss": 0.0397, "lr": 1.789023669081269e-06, "epoch": 1.447725729803123, "percentage": 28.95, "elapsed_time": "0:26:32", "remaining_time": "1:05:08", "throughput": 10281.87, "total_tokens": 16377216}
{"current_steps": 17065, "total_steps": 58920, "loss": 0.0009, "lr": 1.788841647812899e-06, "epoch": 1.4481500339443314, "percentage": 28.96, "elapsed_time": "0:26:33", "remaining_time": "1:05:07", "throughput": 10282.44, "total_tokens": 16382016}
{"current_steps": 17070, "total_steps": 58920, "loss": 0.0627, "lr": 1.7886595573265226e-06, "epoch": 1.4485743380855398, "percentage": 28.97, "elapsed_time": "0:26:33", "remaining_time": "1:05:06", "throughput": 10282.89, "total_tokens": 16386624}
{"current_steps": 17075, "total_steps": 58920, "loss": 0.0907, "lr": 1.7884773976381173e-06, "epoch": 1.4489986422267482, "percentage": 28.98, "elapsed_time": "0:26:33", "remaining_time": "1:05:06", "throughput": 10283.51, "total_tokens": 16391616}
{"current_steps": 17080, "total_steps": 58920, "loss": 0.0718, "lr": 1.7882951687636677e-06, "epoch": 1.4494229463679567, "percentage": 28.99, "elapsed_time": "0:26:34", "remaining_time": "1:05:05", "throughput": 10284.08, "total_tokens": 16396480}
{"current_steps": 17085, "total_steps": 58920, "loss": 0.1054, "lr": 1.7881128707191627e-06, "epoch": 1.449847250509165, "percentage": 29.0, "elapsed_time": "0:26:34", "remaining_time": "1:05:04", "throughput": 10284.75, "total_tokens": 16401600}
{"current_steps": 17090, "total_steps": 58920, "loss": 0.0553, "lr": 1.7879305035205988e-06, "epoch": 1.4502715546503735, "percentage": 29.01, "elapsed_time": "0:26:35", "remaining_time": "1:05:04", "throughput": 10285.54, "total_tokens": 16406976}
{"current_steps": 17095, "total_steps": 58920, "loss": 0.1013, "lr": 1.787748067183978e-06, "epoch": 1.450695858791582, "percentage": 29.01, "elapsed_time": "0:26:35", "remaining_time": "1:05:03", "throughput": 10286.06, "total_tokens": 16411776}
{"current_steps": 17100, "total_steps": 58920, "loss": 0.0484, "lr": 1.7875655617253088e-06, "epoch": 1.4511201629327903, "percentage": 29.02, "elapsed_time": "0:26:35", "remaining_time": "1:05:02", "throughput": 10286.65, "total_tokens": 16416640}
{"current_steps": 17105, "total_steps": 58920, "loss": 0.0123, "lr": 1.7873829871606045e-06, "epoch": 1.4515444670739988, "percentage": 29.03, "elapsed_time": "0:26:36", "remaining_time": "1:05:02", "throughput": 10287.07, "total_tokens": 16421184}
{"current_steps": 17110, "total_steps": 58920, "loss": 0.0733, "lr": 1.7872003435058863e-06, "epoch": 1.4519687712152072, "percentage": 29.04, "elapsed_time": "0:26:36", "remaining_time": "1:05:01", "throughput": 10287.64, "total_tokens": 16426048}
{"current_steps": 17115, "total_steps": 58920, "loss": 0.0432, "lr": 1.78701763077718e-06, "epoch": 1.4523930753564156, "percentage": 29.05, "elapsed_time": "0:26:37", "remaining_time": "1:05:00", "throughput": 10288.24, "total_tokens": 16430976}
{"current_steps": 17120, "total_steps": 58920, "loss": 0.0459, "lr": 1.786834848990518e-06, "epoch": 1.452817379497624, "percentage": 29.06, "elapsed_time": "0:26:37", "remaining_time": "1:05:00", "throughput": 10288.96, "total_tokens": 16436160}
{"current_steps": 17125, "total_steps": 58920, "loss": 0.0216, "lr": 1.7866519981619393e-06, "epoch": 1.4532416836388324, "percentage": 29.06, "elapsed_time": "0:26:37", "remaining_time": "1:04:59", "throughput": 10289.7, "total_tokens": 16441408}
{"current_steps": 17130, "total_steps": 58920, "loss": 0.0219, "lr": 1.7864690783074874e-06, "epoch": 1.4536659877800409, "percentage": 29.07, "elapsed_time": "0:26:38", "remaining_time": "1:04:59", "throughput": 10290.32, "total_tokens": 16446400}
{"current_steps": 17135, "total_steps": 58920, "loss": 0.0193, "lr": 1.7862860894432136e-06, "epoch": 1.4540902919212493, "percentage": 29.08, "elapsed_time": "0:26:38", "remaining_time": "1:04:58", "throughput": 10290.74, "total_tokens": 16450944}
{"current_steps": 17140, "total_steps": 58920, "loss": 0.0455, "lr": 1.7861030315851746e-06, "epoch": 1.4545145960624577, "percentage": 29.09, "elapsed_time": "0:26:38", "remaining_time": "1:04:57", "throughput": 10291.27, "total_tokens": 16455680}
{"current_steps": 17145, "total_steps": 58920, "loss": 0.0585, "lr": 1.7859199047494324e-06, "epoch": 1.4549389002036661, "percentage": 29.1, "elapsed_time": "0:26:39", "remaining_time": "1:04:56", "throughput": 10291.5, "total_tokens": 16459840}
{"current_steps": 17150, "total_steps": 58920, "loss": 0.0745, "lr": 1.7857367089520564e-06, "epoch": 1.4553632043448745, "percentage": 29.11, "elapsed_time": "0:26:39", "remaining_time": "1:04:56", "throughput": 10291.82, "total_tokens": 16464192}
{"current_steps": 17155, "total_steps": 58920, "loss": 0.0395, "lr": 1.7855534442091212e-06, "epoch": 1.455787508486083, "percentage": 29.12, "elapsed_time": "0:26:40", "remaining_time": "1:04:55", "throughput": 10292.03, "total_tokens": 16468288}
{"current_steps": 17160, "total_steps": 58920, "loss": 0.0004, "lr": 1.7853701105367073e-06, "epoch": 1.4562118126272914, "percentage": 29.12, "elapsed_time": "0:26:40", "remaining_time": "1:04:54", "throughput": 10292.41, "total_tokens": 16472768}
{"current_steps": 17165, "total_steps": 58920, "loss": 0.0586, "lr": 1.7851867079509015e-06, "epoch": 1.4566361167684996, "percentage": 29.13, "elapsed_time": "0:26:40", "remaining_time": "1:04:54", "throughput": 10292.87, "total_tokens": 16477376}
{"current_steps": 17170, "total_steps": 58920, "loss": 0.001, "lr": 1.7850032364677974e-06, "epoch": 1.457060420909708, "percentage": 29.14, "elapsed_time": "0:26:41", "remaining_time": "1:04:53", "throughput": 10293.15, "total_tokens": 16481664}
{"current_steps": 17175, "total_steps": 58920, "loss": 0.0276, "lr": 1.7848196961034932e-06, "epoch": 1.4574847250509164, "percentage": 29.15, "elapsed_time": "0:26:41", "remaining_time": "1:04:52", "throughput": 10293.33, "total_tokens": 16485760}
{"current_steps": 17180, "total_steps": 58920, "loss": 0.1105, "lr": 1.7846360868740944e-06, "epoch": 1.4579090291921248, "percentage": 29.16, "elapsed_time": "0:26:41", "remaining_time": "1:04:52", "throughput": 10294.02, "total_tokens": 16490880}
{"current_steps": 17185, "total_steps": 58920, "loss": 0.0816, "lr": 1.784452408795712e-06, "epoch": 1.4583333333333333, "percentage": 29.17, "elapsed_time": "0:26:42", "remaining_time": "1:04:51", "throughput": 10294.83, "total_tokens": 16496256}
{"current_steps": 17190, "total_steps": 58920, "loss": 0.0141, "lr": 1.7842686618844628e-06, "epoch": 1.4587576374745417, "percentage": 29.18, "elapsed_time": "0:26:42", "remaining_time": "1:04:50", "throughput": 10295.33, "total_tokens": 16500992}
{"current_steps": 17195, "total_steps": 58920, "loss": 0.0355, "lr": 1.7840848461564701e-06, "epoch": 1.45918194161575, "percentage": 29.18, "elapsed_time": "0:26:43", "remaining_time": "1:04:50", "throughput": 10296.01, "total_tokens": 16506112}
{"current_steps": 17200, "total_steps": 58920, "loss": 0.0394, "lr": 1.7839009616278636e-06, "epoch": 1.4596062457569585, "percentage": 29.19, "elapsed_time": "0:26:43", "remaining_time": "1:04:49", "throughput": 10296.55, "total_tokens": 16510912}
{"current_steps": 17205, "total_steps": 58920, "loss": 0.0638, "lr": 1.7837170083147774e-06, "epoch": 1.460030549898167, "percentage": 29.2, "elapsed_time": "0:26:43", "remaining_time": "1:04:48", "throughput": 10296.94, "total_tokens": 16515392}
{"current_steps": 17210, "total_steps": 58920, "loss": 0.0432, "lr": 1.7835329862333535e-06, "epoch": 1.4604548540393754, "percentage": 29.21, "elapsed_time": "0:26:44", "remaining_time": "1:04:48", "throughput": 10297.68, "total_tokens": 16520640}
{"current_steps": 17215, "total_steps": 58920, "loss": 0.0305, "lr": 1.783348895399739e-06, "epoch": 1.4608791581805838, "percentage": 29.22, "elapsed_time": "0:26:44", "remaining_time": "1:04:47", "throughput": 10298.21, "total_tokens": 16525376}
{"current_steps": 17220, "total_steps": 58920, "loss": 0.0095, "lr": 1.7831647358300872e-06, "epoch": 1.4613034623217922, "percentage": 29.23, "elapsed_time": "0:26:45", "remaining_time": "1:04:46", "throughput": 10298.75, "total_tokens": 16530176}
{"current_steps": 17225, "total_steps": 58920, "loss": 0.0363, "lr": 1.7829805075405572e-06, "epoch": 1.4617277664630006, "percentage": 29.23, "elapsed_time": "0:26:45", "remaining_time": "1:04:46", "throughput": 10299.08, "total_tokens": 16534528}
{"current_steps": 17230, "total_steps": 58920, "loss": 0.0008, "lr": 1.782796210547315e-06, "epoch": 1.462152070604209, "percentage": 29.24, "elapsed_time": "0:26:45", "remaining_time": "1:04:45", "throughput": 10299.8, "total_tokens": 16539712}
{"current_steps": 17235, "total_steps": 58920, "loss": 0.0641, "lr": 1.7826118448665313e-06, "epoch": 1.4625763747454175, "percentage": 29.25, "elapsed_time": "0:26:46", "remaining_time": "1:04:44", "throughput": 10300.19, "total_tokens": 16544256}
{"current_steps": 17240, "total_steps": 58920, "loss": 0.0812, "lr": 1.782427410514384e-06, "epoch": 1.4630006788866259, "percentage": 29.26, "elapsed_time": "0:26:46", "remaining_time": "1:04:44", "throughput": 10300.65, "total_tokens": 16548928}
{"current_steps": 17245, "total_steps": 58920, "loss": 0.0274, "lr": 1.7822429075070561e-06, "epoch": 1.4634249830278343, "percentage": 29.27, "elapsed_time": "0:26:46", "remaining_time": "1:04:43", "throughput": 10301.07, "total_tokens": 16553472}
{"current_steps": 17250, "total_steps": 58920, "loss": 0.0711, "lr": 1.7820583358607377e-06, "epoch": 1.4638492871690427, "percentage": 29.28, "elapsed_time": "0:26:47", "remaining_time": "1:04:42", "throughput": 10301.41, "total_tokens": 16557888}
{"current_steps": 17255, "total_steps": 58920, "loss": 0.036, "lr": 1.7818736955916237e-06, "epoch": 1.4642735913102511, "percentage": 29.29, "elapsed_time": "0:26:47", "remaining_time": "1:04:42", "throughput": 10301.91, "total_tokens": 16562560}
{"current_steps": 17260, "total_steps": 58920, "loss": 0.0911, "lr": 1.781688986715916e-06, "epoch": 1.4646978954514596, "percentage": 29.29, "elapsed_time": "0:26:48", "remaining_time": "1:04:41", "throughput": 10302.61, "total_tokens": 16567680}
{"current_steps": 17265, "total_steps": 58920, "loss": 0.0491, "lr": 1.7815042092498221e-06, "epoch": 1.465122199592668, "percentage": 29.3, "elapsed_time": "0:26:48", "remaining_time": "1:04:40", "throughput": 10303.37, "total_tokens": 16572928}
{"current_steps": 17270, "total_steps": 58920, "loss": 0.0291, "lr": 1.7813193632095551e-06, "epoch": 1.4655465037338764, "percentage": 29.31, "elapsed_time": "0:26:48", "remaining_time": "1:04:40", "throughput": 10304.04, "total_tokens": 16578048}
{"current_steps": 17275, "total_steps": 58920, "loss": 0.0493, "lr": 1.781134448611335e-06, "epoch": 1.4659708078750848, "percentage": 29.32, "elapsed_time": "0:26:49", "remaining_time": "1:04:39", "throughput": 10304.31, "total_tokens": 16582336}
{"current_steps": 17280, "total_steps": 58920, "loss": 0.0697, "lr": 1.7809494654713877e-06, "epoch": 1.4663951120162932, "percentage": 29.33, "elapsed_time": "0:26:49", "remaining_time": "1:04:38", "throughput": 10304.7, "total_tokens": 16586816}
{"current_steps": 17285, "total_steps": 58920, "loss": 0.0057, "lr": 1.7807644138059442e-06, "epoch": 1.4668194161575017, "percentage": 29.34, "elapsed_time": "0:26:50", "remaining_time": "1:04:38", "throughput": 10305.27, "total_tokens": 16591680}
{"current_steps": 17290, "total_steps": 58920, "loss": 0.0456, "lr": 1.780579293631242e-06, "epoch": 1.46724372029871, "percentage": 29.34, "elapsed_time": "0:26:50", "remaining_time": "1:04:37", "throughput": 10305.78, "total_tokens": 16596416}
{"current_steps": 17295, "total_steps": 58920, "loss": 0.013, "lr": 1.7803941049635253e-06, "epoch": 1.4676680244399185, "percentage": 29.35, "elapsed_time": "0:26:50", "remaining_time": "1:04:36", "throughput": 10306.17, "total_tokens": 16600896}
{"current_steps": 17300, "total_steps": 58920, "loss": 0.0322, "lr": 1.7802088478190437e-06, "epoch": 1.468092328581127, "percentage": 29.36, "elapsed_time": "0:26:51", "remaining_time": "1:04:36", "throughput": 10306.85, "total_tokens": 16605952}
{"current_steps": 17305, "total_steps": 58920, "loss": 0.0266, "lr": 1.7800235222140523e-06, "epoch": 1.4685166327223353, "percentage": 29.37, "elapsed_time": "0:26:51", "remaining_time": "1:04:35", "throughput": 10307.49, "total_tokens": 16610944}
{"current_steps": 17310, "total_steps": 58920, "loss": 0.0813, "lr": 1.7798381281648133e-06, "epoch": 1.4689409368635438, "percentage": 29.38, "elapsed_time": "0:26:51", "remaining_time": "1:04:34", "throughput": 10307.94, "total_tokens": 16615552}
{"current_steps": 17315, "total_steps": 58920, "loss": 0.0362, "lr": 1.779652665687594e-06, "epoch": 1.4693652410047522, "percentage": 29.39, "elapsed_time": "0:26:52", "remaining_time": "1:04:34", "throughput": 10308.46, "total_tokens": 16620288}
{"current_steps": 17320, "total_steps": 58920, "loss": 0.0101, "lr": 1.7794671347986685e-06, "epoch": 1.4697895451459606, "percentage": 29.4, "elapsed_time": "0:26:52", "remaining_time": "1:04:33", "throughput": 10309.08, "total_tokens": 16625216}
{"current_steps": 17325, "total_steps": 58920, "loss": 0.0723, "lr": 1.7792815355143157e-06, "epoch": 1.470213849287169, "percentage": 29.4, "elapsed_time": "0:26:53", "remaining_time": "1:04:32", "throughput": 10309.64, "total_tokens": 16630080}
{"current_steps": 17330, "total_steps": 58920, "loss": 0.0561, "lr": 1.7790958678508221e-06, "epoch": 1.4706381534283774, "percentage": 29.41, "elapsed_time": "0:26:53", "remaining_time": "1:04:32", "throughput": 10310.12, "total_tokens": 16634752}
{"current_steps": 17335, "total_steps": 58920, "loss": 0.0009, "lr": 1.778910131824479e-06, "epoch": 1.4710624575695859, "percentage": 29.42, "elapsed_time": "0:26:53", "remaining_time": "1:04:31", "throughput": 10310.45, "total_tokens": 16639168}
{"current_steps": 17340, "total_steps": 58920, "loss": 0.0008, "lr": 1.778724327451584e-06, "epoch": 1.4714867617107943, "percentage": 29.43, "elapsed_time": "0:26:54", "remaining_time": "1:04:30", "throughput": 10310.98, "total_tokens": 16643968}
{"current_steps": 17345, "total_steps": 58920, "loss": 0.082, "lr": 1.7785384547484408e-06, "epoch": 1.4719110658520027, "percentage": 29.44, "elapsed_time": "0:26:54", "remaining_time": "1:04:30", "throughput": 10311.53, "total_tokens": 16648768}
{"current_steps": 17350, "total_steps": 58920, "loss": 0.0778, "lr": 1.7783525137313592e-06, "epoch": 1.4723353699932111, "percentage": 29.45, "elapsed_time": "0:26:54", "remaining_time": "1:04:29", "throughput": 10311.94, "total_tokens": 16653312}
{"current_steps": 17355, "total_steps": 58920, "loss": 0.056, "lr": 1.7781665044166545e-06, "epoch": 1.4727596741344195, "percentage": 29.46, "elapsed_time": "0:26:55", "remaining_time": "1:04:28", "throughput": 10312.3, "total_tokens": 16657792}
{"current_steps": 17360, "total_steps": 58920, "loss": 0.0455, "lr": 1.7779804268206488e-06, "epoch": 1.473183978275628, "percentage": 29.46, "elapsed_time": "0:26:55", "remaining_time": "1:04:28", "throughput": 10312.76, "total_tokens": 16662464}
{"current_steps": 17365, "total_steps": 58920, "loss": 0.0278, "lr": 1.7777942809596696e-06, "epoch": 1.4736082824168364, "percentage": 29.47, "elapsed_time": "0:26:56", "remaining_time": "1:04:27", "throughput": 10313.32, "total_tokens": 16667328}
{"current_steps": 17370, "total_steps": 58920, "loss": 0.0405, "lr": 1.7776080668500503e-06, "epoch": 1.4740325865580448, "percentage": 29.48, "elapsed_time": "0:26:56", "remaining_time": "1:04:26", "throughput": 10313.77, "total_tokens": 16671936}
{"current_steps": 17375, "total_steps": 58920, "loss": 0.0297, "lr": 1.7774217845081308e-06, "epoch": 1.4744568906992532, "percentage": 29.49, "elapsed_time": "0:26:56", "remaining_time": "1:04:26", "throughput": 10314.15, "total_tokens": 16676416}
{"current_steps": 17380, "total_steps": 58920, "loss": 0.0632, "lr": 1.7772354339502564e-06, "epoch": 1.4748811948404617, "percentage": 29.5, "elapsed_time": "0:26:57", "remaining_time": "1:04:25", "throughput": 10314.72, "total_tokens": 16681280}
{"current_steps": 17385, "total_steps": 58920, "loss": 0.0802, "lr": 1.7770490151927791e-06, "epoch": 1.47530549898167, "percentage": 29.51, "elapsed_time": "0:26:57", "remaining_time": "1:04:24", "throughput": 10315.17, "total_tokens": 16685888}
{"current_steps": 17390, "total_steps": 58920, "loss": 0.0568, "lr": 1.7768625282520561e-06, "epoch": 1.4757298031228785, "percentage": 29.51, "elapsed_time": "0:26:57", "remaining_time": "1:04:23", "throughput": 10315.56, "total_tokens": 16690432}
{"current_steps": 17395, "total_steps": 58920, "loss": 0.0716, "lr": 1.7766759731444511e-06, "epoch": 1.476154107264087, "percentage": 29.52, "elapsed_time": "0:26:58", "remaining_time": "1:04:23", "throughput": 10315.81, "total_tokens": 16694656}
{"current_steps": 17400, "total_steps": 58920, "loss": 0.0849, "lr": 1.7764893498863339e-06, "epoch": 1.4765784114052953, "percentage": 29.53, "elapsed_time": "0:26:58", "remaining_time": "1:04:22", "throughput": 10317.09, "total_tokens": 16701120}
{"current_steps": 17405, "total_steps": 58920, "loss": 0.034, "lr": 1.7763026584940796e-06, "epoch": 1.4770027155465038, "percentage": 29.54, "elapsed_time": "0:26:59", "remaining_time": "1:04:22", "throughput": 10317.69, "total_tokens": 16706112}
{"current_steps": 17410, "total_steps": 58920, "loss": 0.0013, "lr": 1.7761158989840696e-06, "epoch": 1.4774270196877122, "percentage": 29.55, "elapsed_time": "0:26:59", "remaining_time": "1:04:21", "throughput": 10318.19, "total_tokens": 16710848}
{"current_steps": 17415, "total_steps": 58920, "loss": 0.0176, "lr": 1.7759290713726919e-06, "epoch": 1.4778513238289206, "percentage": 29.56, "elapsed_time": "0:26:59", "remaining_time": "1:04:20", "throughput": 10318.86, "total_tokens": 16715904}
{"current_steps": 17420, "total_steps": 58920, "loss": 0.057, "lr": 1.7757421756763393e-06, "epoch": 1.478275627970129, "percentage": 29.57, "elapsed_time": "0:27:00", "remaining_time": "1:04:20", "throughput": 10319.53, "total_tokens": 16721024}
{"current_steps": 17425, "total_steps": 58920, "loss": 0.0234, "lr": 1.775555211911412e-06, "epoch": 1.4786999321113374, "percentage": 29.57, "elapsed_time": "0:27:00", "remaining_time": "1:04:19", "throughput": 10320.0, "total_tokens": 16725696}
{"current_steps": 17430, "total_steps": 58920, "loss": 0.0401, "lr": 1.7753681800943147e-06, "epoch": 1.4791242362525459, "percentage": 29.58, "elapsed_time": "0:27:01", "remaining_time": "1:04:18", "throughput": 10320.5, "total_tokens": 16730432}
{"current_steps": 17435, "total_steps": 58920, "loss": 0.0125, "lr": 1.7751810802414592e-06, "epoch": 1.4795485403937543, "percentage": 29.59, "elapsed_time": "0:27:01", "remaining_time": "1:04:18", "throughput": 10321.76, "total_tokens": 16736832}
{"current_steps": 17440, "total_steps": 58920, "loss": 0.0444, "lr": 1.7749939123692626e-06, "epoch": 1.4799728445349627, "percentage": 29.6, "elapsed_time": "0:27:01", "remaining_time": "1:04:17", "throughput": 10322.32, "total_tokens": 16741696}
{"current_steps": 17445, "total_steps": 58920, "loss": 0.0828, "lr": 1.7748066764941484e-06, "epoch": 1.4803971486761711, "percentage": 29.61, "elapsed_time": "0:27:02", "remaining_time": "1:04:16", "throughput": 10322.89, "total_tokens": 16746560}
{"current_steps": 17450, "total_steps": 58920, "loss": 0.0865, "lr": 1.7746193726325459e-06, "epoch": 1.4808214528173795, "percentage": 29.62, "elapsed_time": "0:27:02", "remaining_time": "1:04:16", "throughput": 10323.31, "total_tokens": 16751104}
{"current_steps": 17455, "total_steps": 58920, "loss": 0.09, "lr": 1.77443200080089e-06, "epoch": 1.481245756958588, "percentage": 29.62, "elapsed_time": "0:27:03", "remaining_time": "1:04:15", "throughput": 10323.67, "total_tokens": 16755584}
{"current_steps": 17460, "total_steps": 58920, "loss": 0.0182, "lr": 1.7742445610156219e-06, "epoch": 1.4816700610997964, "percentage": 29.63, "elapsed_time": "0:27:03", "remaining_time": "1:04:14", "throughput": 10324.21, "total_tokens": 16760384}
{"current_steps": 17465, "total_steps": 58920, "loss": 0.0028, "lr": 1.7740570532931893e-06, "epoch": 1.4820943652410048, "percentage": 29.64, "elapsed_time": "0:27:03", "remaining_time": "1:04:14", "throughput": 10324.61, "total_tokens": 16764928}
{"current_steps": 17470, "total_steps": 58920, "loss": 0.0091, "lr": 1.7738694776500448e-06, "epoch": 1.4825186693822132, "percentage": 29.65, "elapsed_time": "0:27:04", "remaining_time": "1:04:13", "throughput": 10325.51, "total_tokens": 16770560}
{"current_steps": 17475, "total_steps": 58920, "loss": 0.0431, "lr": 1.773681834102648e-06, "epoch": 1.4829429735234216, "percentage": 29.66, "elapsed_time": "0:27:04", "remaining_time": "1:04:12", "throughput": 10326.14, "total_tokens": 16775616}
{"current_steps": 17480, "total_steps": 58920, "loss": 0.0368, "lr": 1.7734941226674631e-06, "epoch": 1.48336727766463, "percentage": 29.67, "elapsed_time": "0:27:04", "remaining_time": "1:04:12", "throughput": 10326.67, "total_tokens": 16780416}
{"current_steps": 17485, "total_steps": 58920, "loss": 0.0639, "lr": 1.773306343360962e-06, "epoch": 1.4837915818058385, "percentage": 29.68, "elapsed_time": "0:27:05", "remaining_time": "1:04:11", "throughput": 10327.48, "total_tokens": 16785856}
{"current_steps": 17490, "total_steps": 58920, "loss": 0.0502, "lr": 1.7731184961996215e-06, "epoch": 1.484215885947047, "percentage": 29.68, "elapsed_time": "0:27:05", "remaining_time": "1:04:11", "throughput": 10327.92, "total_tokens": 16790464}
{"current_steps": 17495, "total_steps": 58920, "loss": 0.0622, "lr": 1.7729305811999238e-06, "epoch": 1.4846401900882553, "percentage": 29.69, "elapsed_time": "0:27:06", "remaining_time": "1:04:10", "throughput": 10328.44, "total_tokens": 16795264}
{"current_steps": 17500, "total_steps": 58920, "loss": 0.046, "lr": 1.7727425983783583e-06, "epoch": 1.4850644942294637, "percentage": 29.7, "elapsed_time": "0:27:06", "remaining_time": "1:04:09", "throughput": 10328.88, "total_tokens": 16799872}
{"current_steps": 17505, "total_steps": 58920, "loss": 0.0765, "lr": 1.77255454775142e-06, "epoch": 1.4854887983706722, "percentage": 29.71, "elapsed_time": "0:27:06", "remaining_time": "1:04:09", "throughput": 10329.37, "total_tokens": 16804672}
{"current_steps": 17510, "total_steps": 58920, "loss": 0.0193, "lr": 1.7723664293356095e-06, "epoch": 1.4859131025118806, "percentage": 29.72, "elapsed_time": "0:27:07", "remaining_time": "1:04:08", "throughput": 10330.06, "total_tokens": 16809856}
{"current_steps": 17515, "total_steps": 58920, "loss": 0.0374, "lr": 1.7721782431474334e-06, "epoch": 1.486337406653089, "percentage": 29.73, "elapsed_time": "0:27:07", "remaining_time": "1:04:07", "throughput": 10330.73, "total_tokens": 16814976}
{"current_steps": 17520, "total_steps": 58920, "loss": 0.0249, "lr": 1.771989989203404e-06, "epoch": 1.4867617107942974, "percentage": 29.74, "elapsed_time": "0:27:08", "remaining_time": "1:04:07", "throughput": 10331.16, "total_tokens": 16819584}
{"current_steps": 17525, "total_steps": 58920, "loss": 0.0259, "lr": 1.7718016675200409e-06, "epoch": 1.4871860149355058, "percentage": 29.74, "elapsed_time": "0:27:08", "remaining_time": "1:04:06", "throughput": 10331.59, "total_tokens": 16824192}
{"current_steps": 17530, "total_steps": 58920, "loss": 0.0439, "lr": 1.7716132781138677e-06, "epoch": 1.4876103190767143, "percentage": 29.75, "elapsed_time": "0:27:08", "remaining_time": "1:04:05", "throughput": 10332.13, "total_tokens": 16828992}
{"current_steps": 17535, "total_steps": 58920, "loss": 0.0476, "lr": 1.7714248210014154e-06, "epoch": 1.4880346232179227, "percentage": 29.76, "elapsed_time": "0:27:09", "remaining_time": "1:04:05", "throughput": 10332.74, "total_tokens": 16833984}
{"current_steps": 17540, "total_steps": 58920, "loss": 0.0229, "lr": 1.7712362961992203e-06, "epoch": 1.488458927359131, "percentage": 29.77, "elapsed_time": "0:27:09", "remaining_time": "1:04:04", "throughput": 10333.17, "total_tokens": 16838592}
{"current_steps": 17545, "total_steps": 58920, "loss": 0.0253, "lr": 1.7710477037238244e-06, "epoch": 1.4888832315003395, "percentage": 29.78, "elapsed_time": "0:27:09", "remaining_time": "1:04:03", "throughput": 10333.58, "total_tokens": 16843136}
{"current_steps": 17550, "total_steps": 58920, "loss": 0.0239, "lr": 1.7708590435917764e-06, "epoch": 1.489307535641548, "percentage": 29.79, "elapsed_time": "0:27:10", "remaining_time": "1:04:03", "throughput": 10333.9, "total_tokens": 16847488}
{"current_steps": 17555, "total_steps": 58920, "loss": 0.0196, "lr": 1.7706703158196308e-06, "epoch": 1.4897318397827564, "percentage": 29.79, "elapsed_time": "0:27:10", "remaining_time": "1:04:02", "throughput": 10334.32, "total_tokens": 16852096}
{"current_steps": 17560, "total_steps": 58920, "loss": 0.0479, "lr": 1.7704815204239475e-06, "epoch": 1.4901561439239646, "percentage": 29.8, "elapsed_time": "0:27:11", "remaining_time": "1:04:01", "throughput": 10334.87, "total_tokens": 16856960}
{"current_steps": 17565, "total_steps": 58920, "loss": 0.0593, "lr": 1.7702926574212923e-06, "epoch": 1.490580448065173, "percentage": 29.81, "elapsed_time": "0:27:11", "remaining_time": "1:04:01", "throughput": 10335.38, "total_tokens": 16861696}
{"current_steps": 17570, "total_steps": 58920, "loss": 0.0212, "lr": 1.7701037268282377e-06, "epoch": 1.4910047522063814, "percentage": 29.82, "elapsed_time": "0:27:11", "remaining_time": "1:04:00", "throughput": 10336.05, "total_tokens": 16866816}
{"current_steps": 17575, "total_steps": 58920, "loss": 0.0291, "lr": 1.7699147286613619e-06, "epoch": 1.4914290563475898, "percentage": 29.83, "elapsed_time": "0:27:12", "remaining_time": "1:03:59", "throughput": 10336.63, "total_tokens": 16871744}
{"current_steps": 17580, "total_steps": 58920, "loss": 0.0013, "lr": 1.769725662937248e-06, "epoch": 1.4918533604887982, "percentage": 29.84, "elapsed_time": "0:27:12", "remaining_time": "1:03:59", "throughput": 10337.16, "total_tokens": 16876608}
{"current_steps": 17585, "total_steps": 58920, "loss": 0.0351, "lr": 1.7695365296724861e-06, "epoch": 1.4922776646300067, "percentage": 29.85, "elapsed_time": "0:27:12", "remaining_time": "1:03:58", "throughput": 10337.59, "total_tokens": 16881216}
{"current_steps": 17590, "total_steps": 58920, "loss": 0.04, "lr": 1.7693473288836725e-06, "epoch": 1.492701968771215, "percentage": 29.85, "elapsed_time": "0:27:13", "remaining_time": "1:03:57", "throughput": 10338.59, "total_tokens": 16887104}
{"current_steps": 17595, "total_steps": 58920, "loss": 0.0402, "lr": 1.7691580605874083e-06, "epoch": 1.4931262729124235, "percentage": 29.86, "elapsed_time": "0:27:13", "remaining_time": "1:03:57", "throughput": 10339.03, "total_tokens": 16891712}
{"current_steps": 17600, "total_steps": 58920, "loss": 0.0779, "lr": 1.768968724800301e-06, "epoch": 1.493550577053632, "percentage": 29.87, "elapsed_time": "0:27:14", "remaining_time": "1:03:56", "throughput": 10339.78, "total_tokens": 16897024}
{"current_steps": 17605, "total_steps": 58920, "loss": 0.0319, "lr": 1.7687793215389651e-06, "epoch": 1.4939748811948403, "percentage": 29.88, "elapsed_time": "0:27:14", "remaining_time": "1:03:55", "throughput": 10340.17, "total_tokens": 16901568}
{"current_steps": 17610, "total_steps": 58920, "loss": 0.0321, "lr": 1.7685898508200193e-06, "epoch": 1.4943991853360488, "percentage": 29.89, "elapsed_time": "0:27:14", "remaining_time": "1:03:55", "throughput": 10340.8, "total_tokens": 16906560}
{"current_steps": 17615, "total_steps": 58920, "loss": 0.0817, "lr": 1.7684003126600887e-06, "epoch": 1.4948234894772572, "percentage": 29.9, "elapsed_time": "0:27:15", "remaining_time": "1:03:54", "throughput": 10341.09, "total_tokens": 16910912}
{"current_steps": 17620, "total_steps": 58920, "loss": 0.0485, "lr": 1.7682107070758053e-06, "epoch": 1.4952477936184656, "percentage": 29.9, "elapsed_time": "0:27:15", "remaining_time": "1:03:53", "throughput": 10341.66, "total_tokens": 16915840}
{"current_steps": 17625, "total_steps": 58920, "loss": 0.0149, "lr": 1.7680210340838056e-06, "epoch": 1.495672097759674, "percentage": 29.91, "elapsed_time": "0:27:16", "remaining_time": "1:03:53", "throughput": 10342.12, "total_tokens": 16920512}
{"current_steps": 17630, "total_steps": 58920, "loss": 0.0741, "lr": 1.7678312937007334e-06, "epoch": 1.4960964019008824, "percentage": 29.92, "elapsed_time": "0:27:16", "remaining_time": "1:03:52", "throughput": 10342.45, "total_tokens": 16924928}
{"current_steps": 17635, "total_steps": 58920, "loss": 0.0029, "lr": 1.7676414859432373e-06, "epoch": 1.4965207060420909, "percentage": 29.93, "elapsed_time": "0:27:16", "remaining_time": "1:03:52", "throughput": 10343.22, "total_tokens": 16930304}
{"current_steps": 17640, "total_steps": 58920, "loss": 0.0136, "lr": 1.7674516108279724e-06, "epoch": 1.4969450101832993, "percentage": 29.94, "elapsed_time": "0:27:17", "remaining_time": "1:03:51", "throughput": 10343.62, "total_tokens": 16934848}
{"current_steps": 17645, "total_steps": 58920, "loss": 0.0226, "lr": 1.7672616683715996e-06, "epoch": 1.4973693143245077, "percentage": 29.95, "elapsed_time": "0:27:17", "remaining_time": "1:03:50", "throughput": 10344.37, "total_tokens": 16940160}
{"current_steps": 17650, "total_steps": 58920, "loss": 0.0616, "lr": 1.7670716585907855e-06, "epoch": 1.4977936184657161, "percentage": 29.96, "elapsed_time": "0:27:17", "remaining_time": "1:03:50", "throughput": 10344.58, "total_tokens": 16944320}
{"current_steps": 17655, "total_steps": 58920, "loss": 0.001, "lr": 1.7668815815022028e-06, "epoch": 1.4982179226069245, "percentage": 29.96, "elapsed_time": "0:27:18", "remaining_time": "1:03:49", "throughput": 10345.12, "total_tokens": 16949184}
{"current_steps": 17660, "total_steps": 58920, "loss": 0.0241, "lr": 1.7666914371225302e-06, "epoch": 1.498642226748133, "percentage": 29.97, "elapsed_time": "0:27:18", "remaining_time": "1:03:48", "throughput": 10345.66, "total_tokens": 16954112}
{"current_steps": 17665, "total_steps": 58920, "loss": 0.0574, "lr": 1.7665012254684523e-06, "epoch": 1.4990665308893414, "percentage": 29.98, "elapsed_time": "0:27:19", "remaining_time": "1:03:48", "throughput": 10346.14, "total_tokens": 16958848}
{"current_steps": 17670, "total_steps": 58920, "loss": 0.0006, "lr": 1.766310946556659e-06, "epoch": 1.4994908350305498, "percentage": 29.99, "elapsed_time": "0:27:19", "remaining_time": "1:03:47", "throughput": 10346.75, "total_tokens": 16963840}
{"current_steps": 17675, "total_steps": 58920, "loss": 0.0363, "lr": 1.766120600403847e-06, "epoch": 1.4999151391717582, "percentage": 30.0, "elapsed_time": "0:27:19", "remaining_time": "1:03:46", "throughput": 10347.2, "total_tokens": 16968512}
{"current_steps": 17676, "total_steps": 58920, "eval_loss": 0.08333459496498108, "epoch": 1.5, "percentage": 30.0, "elapsed_time": "0:27:36", "remaining_time": "1:04:24", "throughput": 10244.9, "total_tokens": 16969472}
{"current_steps": 17680, "total_steps": 58920, "loss": 0.0365, "lr": 1.7659301870267184e-06, "epoch": 1.5003394433129666, "percentage": 30.01, "elapsed_time": "0:28:10", "remaining_time": "1:05:42", "throughput": 10041.15, "total_tokens": 16972992}
{"current_steps": 17685, "total_steps": 58920, "loss": 0.002, "lr": 1.7657397064419813e-06, "epoch": 1.500763747454175, "percentage": 30.02, "elapsed_time": "0:28:10", "remaining_time": "1:05:42", "throughput": 10041.75, "total_tokens": 16977856}
{"current_steps": 17690, "total_steps": 58920, "loss": 0.0599, "lr": 1.7655491586663493e-06, "epoch": 1.5011880515953835, "percentage": 30.02, "elapsed_time": "0:28:11", "remaining_time": "1:05:41", "throughput": 10041.99, "total_tokens": 16981952}
{"current_steps": 17695, "total_steps": 58920, "loss": 0.1041, "lr": 1.7653585437165432e-06, "epoch": 1.501612355736592, "percentage": 30.03, "elapsed_time": "0:28:11", "remaining_time": "1:05:40", "throughput": 10042.76, "total_tokens": 16987200}
{"current_steps": 17700, "total_steps": 58920, "loss": 0.1122, "lr": 1.765167861609288e-06, "epoch": 1.5020366598778003, "percentage": 30.04, "elapsed_time": "0:28:11", "remaining_time": "1:05:40", "throughput": 10043.38, "total_tokens": 16992128}
{"current_steps": 17705, "total_steps": 58920, "loss": 0.0485, "lr": 1.7649771123613155e-06, "epoch": 1.5024609640190087, "percentage": 30.05, "elapsed_time": "0:28:12", "remaining_time": "1:05:39", "throughput": 10043.89, "total_tokens": 16996800}
{"current_steps": 17710, "total_steps": 58920, "loss": 0.027, "lr": 1.7647862959893633e-06, "epoch": 1.5028852681602172, "percentage": 30.06, "elapsed_time": "0:28:12", "remaining_time": "1:05:38", "throughput": 10044.58, "total_tokens": 17001856}
{"current_steps": 17715, "total_steps": 58920, "loss": 0.0013, "lr": 1.764595412510175e-06, "epoch": 1.5033095723014256, "percentage": 30.07, "elapsed_time": "0:28:13", "remaining_time": "1:05:37", "throughput": 10045.06, "total_tokens": 17006464}
{"current_steps": 17720, "total_steps": 58920, "loss": 0.0882, "lr": 1.7644044619404998e-06, "epoch": 1.503733876442634, "percentage": 30.07, "elapsed_time": "0:28:13", "remaining_time": "1:05:37", "throughput": 10045.48, "total_tokens": 17010944}
{"current_steps": 17725, "total_steps": 58920, "loss": 0.0707, "lr": 1.7642134442970928e-06, "epoch": 1.5041581805838424, "percentage": 30.08, "elapsed_time": "0:28:13", "remaining_time": "1:05:36", "throughput": 10046.04, "total_tokens": 17015744}
{"current_steps": 17730, "total_steps": 58920, "loss": 0.1242, "lr": 1.7640223595967155e-06, "epoch": 1.5045824847250509, "percentage": 30.09, "elapsed_time": "0:28:14", "remaining_time": "1:05:35", "throughput": 10046.51, "total_tokens": 17020416}
{"current_steps": 17735, "total_steps": 58920, "loss": 0.033, "lr": 1.763831207856134e-06, "epoch": 1.5050067888662593, "percentage": 30.1, "elapsed_time": "0:28:14", "remaining_time": "1:05:35", "throughput": 10046.88, "total_tokens": 17024832}
{"current_steps": 17740, "total_steps": 58920, "loss": 0.016, "lr": 1.7636399890921227e-06, "epoch": 1.5054310930074677, "percentage": 30.11, "elapsed_time": "0:28:14", "remaining_time": "1:05:34", "throughput": 10047.37, "total_tokens": 17029504}
{"current_steps": 17745, "total_steps": 58920, "loss": 0.0567, "lr": 1.763448703321459e-06, "epoch": 1.5058553971486761, "percentage": 30.12, "elapsed_time": "0:28:15", "remaining_time": "1:05:33", "throughput": 10047.94, "total_tokens": 17034304}
{"current_steps": 17750, "total_steps": 58920, "loss": 0.0796, "lr": 1.763257350560928e-06, "epoch": 1.5062797012898845, "percentage": 30.13, "elapsed_time": "0:28:15", "remaining_time": "1:05:33", "throughput": 10048.59, "total_tokens": 17039360}
{"current_steps": 17755, "total_steps": 58920, "loss": 0.0607, "lr": 1.7630659308273201e-06, "epoch": 1.506704005431093, "percentage": 30.13, "elapsed_time": "0:28:16", "remaining_time": "1:05:32", "throughput": 10049.26, "total_tokens": 17044416}
{"current_steps": 17760, "total_steps": 58920, "loss": 0.0023, "lr": 1.762874444137432e-06, "epoch": 1.5071283095723014, "percentage": 30.14, "elapsed_time": "0:28:16", "remaining_time": "1:05:31", "throughput": 10049.63, "total_tokens": 17048832}
{"current_steps": 17765, "total_steps": 58920, "loss": 0.0044, "lr": 1.7626828905080659e-06, "epoch": 1.5075526137135098, "percentage": 30.15, "elapsed_time": "0:28:16", "remaining_time": "1:05:30", "throughput": 10050.05, "total_tokens": 17053312}
{"current_steps": 17770, "total_steps": 58920, "loss": 0.0329, "lr": 1.7624912699560296e-06, "epoch": 1.5079769178547182, "percentage": 30.16, "elapsed_time": "0:28:17", "remaining_time": "1:05:30", "throughput": 10050.66, "total_tokens": 17058240}
{"current_steps": 17775, "total_steps": 58920, "loss": 0.0468, "lr": 1.7622995824981376e-06, "epoch": 1.5084012219959266, "percentage": 30.17, "elapsed_time": "0:28:17", "remaining_time": "1:05:29", "throughput": 10051.04, "total_tokens": 17062656}
{"current_steps": 17780, "total_steps": 58920, "loss": 0.0181, "lr": 1.7621078281512092e-06, "epoch": 1.508825526137135, "percentage": 30.18, "elapsed_time": "0:28:17", "remaining_time": "1:05:28", "throughput": 10051.58, "total_tokens": 17067392}
{"current_steps": 17785, "total_steps": 58920, "loss": 0.0543, "lr": 1.7619160069320707e-06, "epoch": 1.5092498302783435, "percentage": 30.18, "elapsed_time": "0:28:18", "remaining_time": "1:05:28", "throughput": 10052.23, "total_tokens": 17072384}
{"current_steps": 17790, "total_steps": 58920, "loss": 0.0308, "lr": 1.7617241188575531e-06, "epoch": 1.509674134419552, "percentage": 30.19, "elapsed_time": "0:28:18", "remaining_time": "1:05:27", "throughput": 10052.88, "total_tokens": 17077376}
{"current_steps": 17795, "total_steps": 58920, "loss": 0.0257, "lr": 1.7615321639444948e-06, "epoch": 1.5100984385607603, "percentage": 30.2, "elapsed_time": "0:28:19", "remaining_time": "1:05:26", "throughput": 10053.48, "total_tokens": 17082368}
{"current_steps": 17800, "total_steps": 58920, "loss": 0.0008, "lr": 1.761340142209738e-06, "epoch": 1.5105227427019687, "percentage": 30.21, "elapsed_time": "0:28:19", "remaining_time": "1:05:26", "throughput": 10054.11, "total_tokens": 17087296}
{"current_steps": 17805, "total_steps": 58920, "loss": 0.0223, "lr": 1.7611480536701332e-06, "epoch": 1.5109470468431772, "percentage": 30.22, "elapsed_time": "0:28:19", "remaining_time": "1:05:25", "throughput": 10054.76, "total_tokens": 17092288}
{"current_steps": 17810, "total_steps": 58920, "loss": 0.0607, "lr": 1.760955898342534e-06, "epoch": 1.5113713509843856, "percentage": 30.23, "elapsed_time": "0:28:20", "remaining_time": "1:05:24", "throughput": 10055.43, "total_tokens": 17097344}
{"current_steps": 17815, "total_steps": 58920, "loss": 0.0557, "lr": 1.7607636762438027e-06, "epoch": 1.511795655125594, "percentage": 30.24, "elapsed_time": "0:28:20", "remaining_time": "1:05:24", "throughput": 10055.87, "total_tokens": 17101888}
{"current_steps": 17820, "total_steps": 58920, "loss": 0.0555, "lr": 1.7605713873908055e-06, "epoch": 1.5122199592668024, "percentage": 30.24, "elapsed_time": "0:28:21", "remaining_time": "1:05:23", "throughput": 10056.36, "total_tokens": 17106496}
{"current_steps": 17825, "total_steps": 58920, "loss": 0.1079, "lr": 1.760379031800415e-06, "epoch": 1.5126442634080108, "percentage": 30.25, "elapsed_time": "0:28:21", "remaining_time": "1:05:22", "throughput": 10057.18, "total_tokens": 17112064}
{"current_steps": 17830, "total_steps": 58920, "loss": 0.0229, "lr": 1.76018660948951e-06, "epoch": 1.5130685675492193, "percentage": 30.26, "elapsed_time": "0:28:21", "remaining_time": "1:05:21", "throughput": 10057.66, "total_tokens": 17116672}
{"current_steps": 17835, "total_steps": 58920, "loss": 0.0282, "lr": 1.7599941204749743e-06, "epoch": 1.5134928716904277, "percentage": 30.27, "elapsed_time": "0:28:22", "remaining_time": "1:05:21", "throughput": 10058.45, "total_tokens": 17121984}
{"current_steps": 17840, "total_steps": 58920, "loss": 0.0007, "lr": 1.7598015647736988e-06, "epoch": 1.513917175831636, "percentage": 30.28, "elapsed_time": "0:28:22", "remaining_time": "1:05:20", "throughput": 10059.19, "total_tokens": 17127232}
{"current_steps": 17845, "total_steps": 58920, "loss": 0.0696, "lr": 1.759608942402579e-06, "epoch": 1.5143414799728445, "percentage": 30.29, "elapsed_time": "0:28:23", "remaining_time": "1:05:19", "throughput": 10059.84, "total_tokens": 17132224}
{"current_steps": 17850, "total_steps": 58920, "loss": 0.0067, "lr": 1.759416253378517e-06, "epoch": 1.514765784114053, "percentage": 30.3, "elapsed_time": "0:28:23", "remaining_time": "1:05:19", "throughput": 10060.68, "total_tokens": 17137664}
{"current_steps": 17855, "total_steps": 58920, "loss": 0.0281, "lr": 1.759223497718421e-06, "epoch": 1.5151900882552614, "percentage": 30.3, "elapsed_time": "0:28:23", "remaining_time": "1:05:18", "throughput": 10061.08, "total_tokens": 17142144}
{"current_steps": 17860, "total_steps": 58920, "loss": 0.0422, "lr": 1.759030675439204e-06, "epoch": 1.5156143923964698, "percentage": 30.31, "elapsed_time": "0:28:24", "remaining_time": "1:05:17", "throughput": 10061.65, "total_tokens": 17147008}
{"current_steps": 17865, "total_steps": 58920, "loss": 0.112, "lr": 1.7588377865577857e-06, "epoch": 1.5160386965376782, "percentage": 30.32, "elapsed_time": "0:28:24", "remaining_time": "1:05:17", "throughput": 10062.11, "total_tokens": 17151616}
{"current_steps": 17870, "total_steps": 58920, "loss": 0.0289, "lr": 1.7586448310910913e-06, "epoch": 1.5164630006788866, "percentage": 30.33, "elapsed_time": "0:28:24", "remaining_time": "1:05:16", "throughput": 10063.0, "total_tokens": 17157376}
{"current_steps": 17875, "total_steps": 58920, "loss": 0.047, "lr": 1.7584518090560524e-06, "epoch": 1.516887304820095, "percentage": 30.34, "elapsed_time": "0:28:25", "remaining_time": "1:05:15", "throughput": 10063.51, "total_tokens": 17162112}
{"current_steps": 17880, "total_steps": 58920, "loss": 0.0539, "lr": 1.7582587204696054e-06, "epoch": 1.5173116089613035, "percentage": 30.35, "elapsed_time": "0:28:25", "remaining_time": "1:05:15", "throughput": 10063.96, "total_tokens": 17166656}
{"current_steps": 17885, "total_steps": 58920, "loss": 0.0331, "lr": 1.7580655653486933e-06, "epoch": 1.5177359131025119, "percentage": 30.35, "elapsed_time": "0:28:26", "remaining_time": "1:05:14", "throughput": 10064.4, "total_tokens": 17171200}
{"current_steps": 17890, "total_steps": 58920, "loss": 0.0673, "lr": 1.757872343710265e-06, "epoch": 1.5181602172437203, "percentage": 30.36, "elapsed_time": "0:28:26", "remaining_time": "1:05:13", "throughput": 10065.08, "total_tokens": 17176320}
{"current_steps": 17895, "total_steps": 58920, "loss": 0.0474, "lr": 1.7576790555712747e-06, "epoch": 1.5185845213849287, "percentage": 30.37, "elapsed_time": "0:28:26", "remaining_time": "1:05:13", "throughput": 10065.41, "total_tokens": 17180672}
{"current_steps": 17900, "total_steps": 58920, "loss": 0.0528, "lr": 1.7574857009486827e-06, "epoch": 1.5190088255261371, "percentage": 30.38, "elapsed_time": "0:28:27", "remaining_time": "1:05:12", "throughput": 10065.55, "total_tokens": 17184576}
{"current_steps": 17905, "total_steps": 58920, "loss": 0.0226, "lr": 1.7572922798594557e-06, "epoch": 1.5194331296673456, "percentage": 30.39, "elapsed_time": "0:28:27", "remaining_time": "1:05:11", "throughput": 10065.88, "total_tokens": 17188928}
{"current_steps": 17910, "total_steps": 58920, "loss": 0.0369, "lr": 1.757098792320565e-06, "epoch": 1.519857433808554, "percentage": 30.4, "elapsed_time": "0:28:28", "remaining_time": "1:05:11", "throughput": 10066.37, "total_tokens": 17193600}
{"current_steps": 17915, "total_steps": 58920, "loss": 0.0408, "lr": 1.756905238348989e-06, "epoch": 1.5202817379497624, "percentage": 30.41, "elapsed_time": "0:28:28", "remaining_time": "1:05:10", "throughput": 10066.65, "total_tokens": 17197824}
{"current_steps": 17920, "total_steps": 58920, "loss": 0.0843, "lr": 1.756711617961711e-06, "epoch": 1.5207060420909708, "percentage": 30.41, "elapsed_time": "0:28:28", "remaining_time": "1:05:09", "throughput": 10067.07, "total_tokens": 17202368}
{"current_steps": 17925, "total_steps": 58920, "loss": 0.0033, "lr": 1.7565179311757206e-06, "epoch": 1.5211303462321792, "percentage": 30.42, "elapsed_time": "0:28:29", "remaining_time": "1:05:08", "throughput": 10067.48, "total_tokens": 17206912}
{"current_steps": 17930, "total_steps": 58920, "loss": 0.0319, "lr": 1.7563241780080134e-06, "epoch": 1.5215546503733877, "percentage": 30.43, "elapsed_time": "0:28:29", "remaining_time": "1:05:08", "throughput": 10068.11, "total_tokens": 17211904}
{"current_steps": 17935, "total_steps": 58920, "loss": 0.0029, "lr": 1.75613035847559e-06, "epoch": 1.521978954514596, "percentage": 30.44, "elapsed_time": "0:28:29", "remaining_time": "1:05:07", "throughput": 10068.81, "total_tokens": 17217088}
{"current_steps": 17940, "total_steps": 58920, "loss": 0.09, "lr": 1.7559364725954575e-06, "epoch": 1.5224032586558045, "percentage": 30.45, "elapsed_time": "0:28:30", "remaining_time": "1:05:06", "throughput": 10069.31, "total_tokens": 17221760}
{"current_steps": 17945, "total_steps": 58920, "loss": 0.0259, "lr": 1.7557425203846293e-06, "epoch": 1.522827562797013, "percentage": 30.46, "elapsed_time": "0:28:30", "remaining_time": "1:05:06", "throughput": 10070.22, "total_tokens": 17227456}
{"current_steps": 17950, "total_steps": 58920, "loss": 0.132, "lr": 1.7555485018601232e-06, "epoch": 1.5232518669382213, "percentage": 30.47, "elapsed_time": "0:28:31", "remaining_time": "1:05:05", "throughput": 10070.63, "total_tokens": 17232000}
{"current_steps": 17955, "total_steps": 58920, "loss": 0.0013, "lr": 1.755354417038964e-06, "epoch": 1.5236761710794298, "percentage": 30.47, "elapsed_time": "0:28:31", "remaining_time": "1:05:04", "throughput": 10071.19, "total_tokens": 17236928}
{"current_steps": 17960, "total_steps": 58920, "loss": 0.0012, "lr": 1.755160265938182e-06, "epoch": 1.5241004752206382, "percentage": 30.48, "elapsed_time": "0:28:31", "remaining_time": "1:05:04", "throughput": 10071.74, "total_tokens": 17241984}
{"current_steps": 17965, "total_steps": 58920, "loss": 0.044, "lr": 1.754966048574813e-06, "epoch": 1.5245247793618466, "percentage": 30.49, "elapsed_time": "0:28:32", "remaining_time": "1:05:03", "throughput": 10072.16, "total_tokens": 17246528}
{"current_steps": 17970, "total_steps": 58920, "loss": 0.0009, "lr": 1.7547717649658994e-06, "epoch": 1.524949083503055, "percentage": 30.5, "elapsed_time": "0:28:32", "remaining_time": "1:05:02", "throughput": 10072.6, "total_tokens": 17251136}
{"current_steps": 17975, "total_steps": 58920, "loss": 0.025, "lr": 1.7545774151284881e-06, "epoch": 1.5253733876442634, "percentage": 30.51, "elapsed_time": "0:28:33", "remaining_time": "1:05:02", "throughput": 10073.08, "total_tokens": 17255872}
{"current_steps": 17980, "total_steps": 58920, "loss": 0.0351, "lr": 1.7543829990796333e-06, "epoch": 1.5257976917854719, "percentage": 30.52, "elapsed_time": "0:28:33", "remaining_time": "1:05:01", "throughput": 10073.49, "total_tokens": 17260416}
{"current_steps": 17985, "total_steps": 58920, "loss": 0.0284, "lr": 1.7541885168363937e-06, "epoch": 1.5262219959266803, "percentage": 30.52, "elapsed_time": "0:28:33", "remaining_time": "1:05:00", "throughput": 10073.88, "total_tokens": 17264896}
{"current_steps": 17990, "total_steps": 58920, "loss": 0.035, "lr": 1.753993968415835e-06, "epoch": 1.5266463000678887, "percentage": 30.53, "elapsed_time": "0:28:34", "remaining_time": "1:05:00", "throughput": 10074.82, "total_tokens": 17270656}
{"current_steps": 17995, "total_steps": 58920, "loss": 0.038, "lr": 1.7537993538350277e-06, "epoch": 1.5270706042090971, "percentage": 30.54, "elapsed_time": "0:28:34", "remaining_time": "1:04:59", "throughput": 10075.35, "total_tokens": 17275520}
{"current_steps": 18000, "total_steps": 58920, "loss": 0.0621, "lr": 1.7536046731110487e-06, "epoch": 1.5274949083503055, "percentage": 30.55, "elapsed_time": "0:28:35", "remaining_time": "1:04:58", "throughput": 10075.65, "total_tokens": 17279872}
{"current_steps": 18005, "total_steps": 58920, "loss": 0.0512, "lr": 1.7534099262609806e-06, "epoch": 1.527919212491514, "percentage": 30.56, "elapsed_time": "0:28:35", "remaining_time": "1:04:58", "throughput": 10076.12, "total_tokens": 17284544}
{"current_steps": 18010, "total_steps": 58920, "loss": 0.0254, "lr": 1.7532151133019116e-06, "epoch": 1.5283435166327224, "percentage": 30.57, "elapsed_time": "0:28:35", "remaining_time": "1:04:57", "throughput": 10076.58, "total_tokens": 17289216}
{"current_steps": 18015, "total_steps": 58920, "loss": 0.0382, "lr": 1.7530202342509362e-06, "epoch": 1.5287678207739308, "percentage": 30.58, "elapsed_time": "0:28:36", "remaining_time": "1:04:56", "throughput": 10077.07, "total_tokens": 17294144}
{"current_steps": 18020, "total_steps": 58920, "loss": 0.0237, "lr": 1.7528252891251537e-06, "epoch": 1.5291921249151392, "percentage": 30.58, "elapsed_time": "0:28:36", "remaining_time": "1:04:56", "throughput": 10077.75, "total_tokens": 17299328}
{"current_steps": 18025, "total_steps": 58920, "loss": 0.0324, "lr": 1.75263027794167e-06, "epoch": 1.5296164290563476, "percentage": 30.59, "elapsed_time": "0:28:36", "remaining_time": "1:04:55", "throughput": 10078.3, "total_tokens": 17304256}
{"current_steps": 18030, "total_steps": 58920, "loss": 0.0303, "lr": 1.752435200717597e-06, "epoch": 1.530040733197556, "percentage": 30.6, "elapsed_time": "0:28:37", "remaining_time": "1:04:54", "throughput": 10078.63, "total_tokens": 17308672}
{"current_steps": 18035, "total_steps": 58920, "loss": 0.0328, "lr": 1.7522400574700517e-06, "epoch": 1.5304650373387645, "percentage": 30.61, "elapsed_time": "0:28:37", "remaining_time": "1:04:54", "throughput": 10079.1, "total_tokens": 17313344}
{"current_steps": 18040, "total_steps": 58920, "loss": 0.0594, "lr": 1.7520448482161575e-06, "epoch": 1.530889341479973, "percentage": 30.62, "elapsed_time": "0:28:38", "remaining_time": "1:04:53", "throughput": 10079.73, "total_tokens": 17318336}
{"current_steps": 18045, "total_steps": 58920, "loss": 0.0294, "lr": 1.7518495729730428e-06, "epoch": 1.5313136456211813, "percentage": 30.63, "elapsed_time": "0:28:38", "remaining_time": "1:04:52", "throughput": 10080.19, "total_tokens": 17323008}
{"current_steps": 18050, "total_steps": 58920, "loss": 0.0356, "lr": 1.7516542317578427e-06, "epoch": 1.5317379497623897, "percentage": 30.63, "elapsed_time": "0:28:38", "remaining_time": "1:04:52", "throughput": 10080.53, "total_tokens": 17327424}
{"current_steps": 18055, "total_steps": 58920, "loss": 0.0437, "lr": 1.7514588245876975e-06, "epoch": 1.5321622539035982, "percentage": 30.64, "elapsed_time": "0:28:39", "remaining_time": "1:04:51", "throughput": 10081.05, "total_tokens": 17332224}
{"current_steps": 18060, "total_steps": 58920, "loss": 0.0011, "lr": 1.751263351479754e-06, "epoch": 1.5325865580448066, "percentage": 30.65, "elapsed_time": "0:28:39", "remaining_time": "1:04:50", "throughput": 10081.31, "total_tokens": 17336512}
{"current_steps": 18065, "total_steps": 58920, "loss": 0.0188, "lr": 1.7510678124511636e-06, "epoch": 1.533010862186015, "percentage": 30.66, "elapsed_time": "0:28:40", "remaining_time": "1:04:49", "throughput": 10081.58, "total_tokens": 17340800}
{"current_steps": 18070, "total_steps": 58920, "loss": 0.0868, "lr": 1.7508722075190844e-06, "epoch": 1.5334351663272234, "percentage": 30.67, "elapsed_time": "0:28:40", "remaining_time": "1:04:49", "throughput": 10081.95, "total_tokens": 17345280}
{"current_steps": 18075, "total_steps": 58920, "loss": 0.023, "lr": 1.7506765367006797e-06, "epoch": 1.5338594704684319, "percentage": 30.68, "elapsed_time": "0:28:40", "remaining_time": "1:04:48", "throughput": 10082.56, "total_tokens": 17350336}
{"current_steps": 18080, "total_steps": 58920, "loss": 0.0226, "lr": 1.7504808000131197e-06, "epoch": 1.5342837746096403, "percentage": 30.69, "elapsed_time": "0:28:41", "remaining_time": "1:04:47", "throughput": 10083.28, "total_tokens": 17355584}
{"current_steps": 18085, "total_steps": 58920, "loss": 0.0619, "lr": 1.7502849974735788e-06, "epoch": 1.5347080787508487, "percentage": 30.69, "elapsed_time": "0:28:41", "remaining_time": "1:04:47", "throughput": 10083.86, "total_tokens": 17360512}
{"current_steps": 18090, "total_steps": 58920, "loss": 0.0983, "lr": 1.7500891290992384e-06, "epoch": 1.5351323828920571, "percentage": 30.7, "elapsed_time": "0:28:42", "remaining_time": "1:04:46", "throughput": 10084.41, "total_tokens": 17365440}
{"current_steps": 18095, "total_steps": 58920, "loss": 0.0328, "lr": 1.749893194907285e-06, "epoch": 1.5355566870332655, "percentage": 30.71, "elapsed_time": "0:28:42", "remaining_time": "1:04:45", "throughput": 10084.89, "total_tokens": 17370240}
{"current_steps": 18100, "total_steps": 58920, "loss": 0.0016, "lr": 1.7496971949149111e-06, "epoch": 1.535980991174474, "percentage": 30.72, "elapsed_time": "0:28:42", "remaining_time": "1:04:45", "throughput": 10085.45, "total_tokens": 17375168}
{"current_steps": 18105, "total_steps": 58920, "loss": 0.0007, "lr": 1.7495011291393154e-06, "epoch": 1.5364052953156824, "percentage": 30.73, "elapsed_time": "0:28:43", "remaining_time": "1:04:44", "throughput": 10086.23, "total_tokens": 17380608}
{"current_steps": 18110, "total_steps": 58920, "loss": 0.0452, "lr": 1.7493049975977015e-06, "epoch": 1.5368295994568908, "percentage": 30.74, "elapsed_time": "0:28:43", "remaining_time": "1:04:44", "throughput": 10086.71, "total_tokens": 17385280}
{"current_steps": 18115, "total_steps": 58920, "loss": 0.0688, "lr": 1.7491088003072797e-06, "epoch": 1.5372539035980992, "percentage": 30.75, "elapsed_time": "0:28:43", "remaining_time": "1:04:43", "throughput": 10087.07, "total_tokens": 17389760}
{"current_steps": 18120, "total_steps": 58920, "loss": 0.0071, "lr": 1.748912537285265e-06, "epoch": 1.5376782077393076, "percentage": 30.75, "elapsed_time": "0:28:44", "remaining_time": "1:04:42", "throughput": 10087.74, "total_tokens": 17394880}
{"current_steps": 18125, "total_steps": 58920, "loss": 0.0055, "lr": 1.7487162085488788e-06, "epoch": 1.538102511880516, "percentage": 30.76, "elapsed_time": "0:28:44", "remaining_time": "1:04:41", "throughput": 10088.1, "total_tokens": 17399296}
{"current_steps": 18130, "total_steps": 58920, "loss": 0.0934, "lr": 1.7485198141153491e-06, "epoch": 1.5385268160217245, "percentage": 30.77, "elapsed_time": "0:28:45", "remaining_time": "1:04:41", "throughput": 10088.61, "total_tokens": 17404032}
{"current_steps": 18135, "total_steps": 58920, "loss": 0.0326, "lr": 1.748323354001908e-06, "epoch": 1.538951120162933, "percentage": 30.78, "elapsed_time": "0:28:45", "remaining_time": "1:04:40", "throughput": 10089.22, "total_tokens": 17408960}
{"current_steps": 18140, "total_steps": 58920, "loss": 0.0046, "lr": 1.7481268282257946e-06, "epoch": 1.5393754243041413, "percentage": 30.79, "elapsed_time": "0:28:45", "remaining_time": "1:04:39", "throughput": 10089.63, "total_tokens": 17413504}
{"current_steps": 18145, "total_steps": 58920, "loss": 0.0176, "lr": 1.7479302368042527e-06, "epoch": 1.5397997284453497, "percentage": 30.8, "elapsed_time": "0:28:46", "remaining_time": "1:04:39", "throughput": 10090.13, "total_tokens": 17418240}
{"current_steps": 18150, "total_steps": 58920, "loss": 0.0193, "lr": 1.7477335797545333e-06, "epoch": 1.5402240325865582, "percentage": 30.8, "elapsed_time": "0:28:46", "remaining_time": "1:04:38", "throughput": 10090.63, "total_tokens": 17423040}
{"current_steps": 18155, "total_steps": 58920, "loss": 0.0769, "lr": 1.7475368570938919e-06, "epoch": 1.5406483367277666, "percentage": 30.81, "elapsed_time": "0:28:47", "remaining_time": "1:04:37", "throughput": 10091.08, "total_tokens": 17427712}
{"current_steps": 18160, "total_steps": 58920, "loss": 0.0018, "lr": 1.7473400688395903e-06, "epoch": 1.541072640868975, "percentage": 30.82, "elapsed_time": "0:28:47", "remaining_time": "1:04:37", "throughput": 10091.51, "total_tokens": 17432512}
{"current_steps": 18165, "total_steps": 58920, "loss": 0.0337, "lr": 1.7471432150088959e-06, "epoch": 1.5414969450101834, "percentage": 30.83, "elapsed_time": "0:28:47", "remaining_time": "1:04:36", "throughput": 10092.09, "total_tokens": 17437440}
{"current_steps": 18170, "total_steps": 58920, "loss": 0.0004, "lr": 1.7469462956190816e-06, "epoch": 1.5419212491513918, "percentage": 30.84, "elapsed_time": "0:28:48", "remaining_time": "1:04:35", "throughput": 10092.57, "total_tokens": 17442176}
{"current_steps": 18175, "total_steps": 58920, "loss": 0.056, "lr": 1.7467493106874272e-06, "epoch": 1.5423455532926003, "percentage": 30.85, "elapsed_time": "0:28:48", "remaining_time": "1:04:35", "throughput": 10093.17, "total_tokens": 17447168}
{"current_steps": 18180, "total_steps": 58920, "loss": 0.0526, "lr": 1.7465522602312165e-06, "epoch": 1.5427698574338087, "percentage": 30.86, "elapsed_time": "0:28:49", "remaining_time": "1:04:34", "throughput": 10093.62, "total_tokens": 17451904}
{"current_steps": 18185, "total_steps": 58920, "loss": 0.0392, "lr": 1.7463551442677406e-06, "epoch": 1.543194161575017, "percentage": 30.86, "elapsed_time": "0:28:49", "remaining_time": "1:04:33", "throughput": 10094.18, "total_tokens": 17456832}
{"current_steps": 18190, "total_steps": 58920, "loss": 0.0363, "lr": 1.7461579628142954e-06, "epoch": 1.5436184657162255, "percentage": 30.87, "elapsed_time": "0:28:49", "remaining_time": "1:04:33", "throughput": 10094.67, "total_tokens": 17461568}
{"current_steps": 18195, "total_steps": 58920, "loss": 0.0008, "lr": 1.745960715888183e-06, "epoch": 1.544042769857434, "percentage": 30.88, "elapsed_time": "0:28:50", "remaining_time": "1:04:32", "throughput": 10094.96, "total_tokens": 17465920}
{"current_steps": 18200, "total_steps": 58920, "loss": 0.0785, "lr": 1.745763403506711e-06, "epoch": 1.5444670739986424, "percentage": 30.89, "elapsed_time": "0:28:50", "remaining_time": "1:04:31", "throughput": 10095.26, "total_tokens": 17470208}
{"current_steps": 18205, "total_steps": 58920, "loss": 0.0009, "lr": 1.745566025687193e-06, "epoch": 1.5448913781398508, "percentage": 30.9, "elapsed_time": "0:28:50", "remaining_time": "1:04:31", "throughput": 10095.73, "total_tokens": 17475008}
{"current_steps": 18210, "total_steps": 58920, "loss": 0.0465, "lr": 1.745368582446948e-06, "epoch": 1.5453156822810592, "percentage": 30.91, "elapsed_time": "0:28:51", "remaining_time": "1:04:30", "throughput": 10096.3, "total_tokens": 17480000}
{"current_steps": 18215, "total_steps": 58920, "loss": 0.001, "lr": 1.7451710738033013e-06, "epoch": 1.5457399864222676, "percentage": 30.91, "elapsed_time": "0:28:51", "remaining_time": "1:04:29", "throughput": 10096.85, "total_tokens": 17484864}
{"current_steps": 18220, "total_steps": 58920, "loss": 0.0227, "lr": 1.744973499773583e-06, "epoch": 1.546164290563476, "percentage": 30.92, "elapsed_time": "0:28:52", "remaining_time": "1:04:29", "throughput": 10097.45, "total_tokens": 17489856}
{"current_steps": 18225, "total_steps": 58920, "loss": 0.0321, "lr": 1.7447758603751298e-06, "epoch": 1.5465885947046845, "percentage": 30.93, "elapsed_time": "0:28:52", "remaining_time": "1:04:28", "throughput": 10097.82, "total_tokens": 17494336}
{"current_steps": 18230, "total_steps": 58920, "loss": 0.0444, "lr": 1.7445781556252838e-06, "epoch": 1.5470128988458929, "percentage": 30.94, "elapsed_time": "0:28:52", "remaining_time": "1:04:27", "throughput": 10098.43, "total_tokens": 17499328}
{"current_steps": 18235, "total_steps": 58920, "loss": 0.0006, "lr": 1.7443803855413935e-06, "epoch": 1.5474372029871013, "percentage": 30.95, "elapsed_time": "0:28:53", "remaining_time": "1:04:27", "throughput": 10098.8, "total_tokens": 17503744}
{"current_steps": 18240, "total_steps": 58920, "loss": 0.0826, "lr": 1.7441825501408114e-06, "epoch": 1.5478615071283097, "percentage": 30.96, "elapsed_time": "0:28:53", "remaining_time": "1:04:26", "throughput": 10099.3, "total_tokens": 17508544}
{"current_steps": 18245, "total_steps": 58920, "loss": 0.063, "lr": 1.7439846494408976e-06, "epoch": 1.5482858112695181, "percentage": 30.97, "elapsed_time": "0:28:54", "remaining_time": "1:04:25", "throughput": 10099.61, "total_tokens": 17512832}
{"current_steps": 18250, "total_steps": 58920, "loss": 0.1013, "lr": 1.743786683459017e-06, "epoch": 1.5487101154107266, "percentage": 30.97, "elapsed_time": "0:28:54", "remaining_time": "1:04:25", "throughput": 10100.18, "total_tokens": 17517696}
{"current_steps": 18255, "total_steps": 58920, "loss": 0.1363, "lr": 1.74358865221254e-06, "epoch": 1.549134419551935, "percentage": 30.98, "elapsed_time": "0:28:54", "remaining_time": "1:04:24", "throughput": 10100.73, "total_tokens": 17522560}
{"current_steps": 18260, "total_steps": 58920, "loss": 0.0132, "lr": 1.7433905557188437e-06, "epoch": 1.5495587236931434, "percentage": 30.99, "elapsed_time": "0:28:55", "remaining_time": "1:04:23", "throughput": 10101.07, "total_tokens": 17526976}
{"current_steps": 18265, "total_steps": 58920, "loss": 0.006, "lr": 1.7431923939953102e-06, "epoch": 1.5499830278343518, "percentage": 31.0, "elapsed_time": "0:28:55", "remaining_time": "1:04:23", "throughput": 10101.59, "total_tokens": 17531776}
{"current_steps": 18270, "total_steps": 58920, "loss": 0.0789, "lr": 1.7429941670593277e-06, "epoch": 1.5504073319755602, "percentage": 31.01, "elapsed_time": "0:28:55", "remaining_time": "1:04:22", "throughput": 10101.97, "total_tokens": 17536256}
{"current_steps": 18275, "total_steps": 58920, "loss": 0.0014, "lr": 1.742795874928289e-06, "epoch": 1.5508316361167687, "percentage": 31.02, "elapsed_time": "0:28:56", "remaining_time": "1:04:21", "throughput": 10102.46, "total_tokens": 17540928}
{"current_steps": 18280, "total_steps": 58920, "loss": 0.0695, "lr": 1.7425975176195945e-06, "epoch": 1.551255940257977, "percentage": 31.03, "elapsed_time": "0:28:56", "remaining_time": "1:04:20", "throughput": 10102.85, "total_tokens": 17545472}
{"current_steps": 18285, "total_steps": 58920, "loss": 0.0016, "lr": 1.7423990951506489e-06, "epoch": 1.5516802443991853, "percentage": 31.03, "elapsed_time": "0:28:57", "remaining_time": "1:04:20", "throughput": 10103.16, "total_tokens": 17549760}
{"current_steps": 18290, "total_steps": 58920, "loss": 0.0012, "lr": 1.742200607538863e-06, "epoch": 1.5521045485403937, "percentage": 31.04, "elapsed_time": "0:28:57", "remaining_time": "1:04:19", "throughput": 10103.9, "total_tokens": 17555008}
{"current_steps": 18295, "total_steps": 58920, "loss": 0.0259, "lr": 1.7420020548016536e-06, "epoch": 1.5525288526816021, "percentage": 31.05, "elapsed_time": "0:28:57", "remaining_time": "1:04:18", "throughput": 10104.52, "total_tokens": 17560000}
{"current_steps": 18300, "total_steps": 58920, "loss": 0.0336, "lr": 1.7418034369564429e-06, "epoch": 1.5529531568228105, "percentage": 31.06, "elapsed_time": "0:28:58", "remaining_time": "1:04:18", "throughput": 10104.88, "total_tokens": 17564416}
{"current_steps": 18305, "total_steps": 58920, "loss": 0.0748, "lr": 1.7416047540206588e-06, "epoch": 1.553377460964019, "percentage": 31.07, "elapsed_time": "0:28:58", "remaining_time": "1:04:17", "throughput": 10105.67, "total_tokens": 17569856}
{"current_steps": 18310, "total_steps": 58920, "loss": 0.0249, "lr": 1.7414060060117354e-06, "epoch": 1.5538017651052274, "percentage": 31.08, "elapsed_time": "0:28:58", "remaining_time": "1:04:16", "throughput": 10106.13, "total_tokens": 17574464}
{"current_steps": 18315, "total_steps": 58920, "loss": 0.0566, "lr": 1.7412071929471114e-06, "epoch": 1.5542260692464358, "percentage": 31.08, "elapsed_time": "0:28:59", "remaining_time": "1:04:16", "throughput": 10106.6, "total_tokens": 17579136}
{"current_steps": 18320, "total_steps": 58920, "loss": 0.0092, "lr": 1.7410083148442323e-06, "epoch": 1.5546503733876442, "percentage": 31.09, "elapsed_time": "0:28:59", "remaining_time": "1:04:15", "throughput": 10106.86, "total_tokens": 17583360}
{"current_steps": 18325, "total_steps": 58920, "loss": 0.0424, "lr": 1.7408093717205495e-06, "epoch": 1.5550746775288526, "percentage": 31.1, "elapsed_time": "0:29:00", "remaining_time": "1:04:14", "throughput": 10107.57, "total_tokens": 17588544}
{"current_steps": 18330, "total_steps": 58920, "loss": 0.1061, "lr": 1.7406103635935184e-06, "epoch": 1.555498981670061, "percentage": 31.11, "elapsed_time": "0:29:00", "remaining_time": "1:04:14", "throughput": 10107.82, "total_tokens": 17592768}
{"current_steps": 18335, "total_steps": 58920, "loss": 0.0465, "lr": 1.740411290480602e-06, "epoch": 1.5559232858112695, "percentage": 31.12, "elapsed_time": "0:29:00", "remaining_time": "1:04:13", "throughput": 10108.27, "total_tokens": 17597376}
{"current_steps": 18340, "total_steps": 58920, "loss": 0.0425, "lr": 1.7402121523992684e-06, "epoch": 1.556347589952478, "percentage": 31.13, "elapsed_time": "0:29:01", "remaining_time": "1:04:12", "throughput": 10108.44, "total_tokens": 17601408}
{"current_steps": 18345, "total_steps": 58920, "loss": 0.0019, "lr": 1.740012949366991e-06, "epoch": 1.5567718940936863, "percentage": 31.14, "elapsed_time": "0:29:01", "remaining_time": "1:04:12", "throughput": 10109.11, "total_tokens": 17606528}
{"current_steps": 18350, "total_steps": 58920, "loss": 0.0058, "lr": 1.7398136814012486e-06, "epoch": 1.5571961982348947, "percentage": 31.14, "elapsed_time": "0:29:02", "remaining_time": "1:04:11", "throughput": 10109.5, "total_tokens": 17611008}
{"current_steps": 18355, "total_steps": 58920, "loss": 0.0004, "lr": 1.7396143485195272e-06, "epoch": 1.5576205023761032, "percentage": 31.15, "elapsed_time": "0:29:02", "remaining_time": "1:04:10", "throughput": 10109.89, "total_tokens": 17615488}
{"current_steps": 18360, "total_steps": 58920, "loss": 0.0183, "lr": 1.739414950739317e-06, "epoch": 1.5580448065173116, "percentage": 31.16, "elapsed_time": "0:29:02", "remaining_time": "1:04:10", "throughput": 10110.44, "total_tokens": 17620352}
{"current_steps": 18365, "total_steps": 58920, "loss": 0.0653, "lr": 1.7392154880781143e-06, "epoch": 1.55846911065852, "percentage": 31.17, "elapsed_time": "0:29:03", "remaining_time": "1:04:09", "throughput": 10110.95, "total_tokens": 17625088}
{"current_steps": 18370, "total_steps": 58920, "loss": 0.1321, "lr": 1.7390159605534218e-06, "epoch": 1.5588934147997284, "percentage": 31.18, "elapsed_time": "0:29:03", "remaining_time": "1:04:08", "throughput": 10111.3, "total_tokens": 17629504}
{"current_steps": 18375, "total_steps": 58920, "loss": 0.0063, "lr": 1.7388163681827466e-06, "epoch": 1.5593177189409368, "percentage": 31.19, "elapsed_time": "0:29:03", "remaining_time": "1:04:08", "throughput": 10111.69, "total_tokens": 17634176}
{"current_steps": 18380, "total_steps": 58920, "loss": 0.0767, "lr": 1.7386167109836024e-06, "epoch": 1.5597420230821453, "percentage": 31.19, "elapsed_time": "0:29:04", "remaining_time": "1:04:07", "throughput": 10111.91, "total_tokens": 17638336}
{"current_steps": 18385, "total_steps": 58920, "loss": 0.0848, "lr": 1.738416988973509e-06, "epoch": 1.5601663272233537, "percentage": 31.2, "elapsed_time": "0:29:04", "remaining_time": "1:04:06", "throughput": 10112.45, "total_tokens": 17643200}
{"current_steps": 18390, "total_steps": 58920, "loss": 0.0535, "lr": 1.7382172021699911e-06, "epoch": 1.560590631364562, "percentage": 31.21, "elapsed_time": "0:29:05", "remaining_time": "1:04:06", "throughput": 10113.04, "total_tokens": 17648128}
{"current_steps": 18395, "total_steps": 58920, "loss": 0.0093, "lr": 1.7380173505905787e-06, "epoch": 1.5610149355057705, "percentage": 31.22, "elapsed_time": "0:29:05", "remaining_time": "1:04:05", "throughput": 10113.63, "total_tokens": 17653056}
{"current_steps": 18400, "total_steps": 58920, "loss": 0.0703, "lr": 1.7378174342528082e-06, "epoch": 1.561439239646979, "percentage": 31.23, "elapsed_time": "0:29:05", "remaining_time": "1:04:04", "throughput": 10114.21, "total_tokens": 17657984}
{"current_steps": 18405, "total_steps": 58920, "loss": 0.0141, "lr": 1.737617453174222e-06, "epoch": 1.5618635437881874, "percentage": 31.24, "elapsed_time": "0:29:06", "remaining_time": "1:04:04", "throughput": 10115.1, "total_tokens": 17663616}
{"current_steps": 18410, "total_steps": 58920, "loss": 0.0209, "lr": 1.7374174073723674e-06, "epoch": 1.5622878479293958, "percentage": 31.25, "elapsed_time": "0:29:06", "remaining_time": "1:04:03", "throughput": 10115.68, "total_tokens": 17668544}
{"current_steps": 18415, "total_steps": 58920, "loss": 0.0506, "lr": 1.7372172968647977e-06, "epoch": 1.5627121520706042, "percentage": 31.25, "elapsed_time": "0:29:07", "remaining_time": "1:04:02", "throughput": 10116.02, "total_tokens": 17672896}
{"current_steps": 18420, "total_steps": 58920, "loss": 0.0696, "lr": 1.737017121669072e-06, "epoch": 1.5631364562118126, "percentage": 31.26, "elapsed_time": "0:29:07", "remaining_time": "1:04:01", "throughput": 10116.38, "total_tokens": 17677312}
{"current_steps": 18425, "total_steps": 58920, "loss": 0.0419, "lr": 1.7368168818027545e-06, "epoch": 1.563560760353021, "percentage": 31.27, "elapsed_time": "0:29:07", "remaining_time": "1:04:01", "throughput": 10116.83, "total_tokens": 17681920}
{"current_steps": 18430, "total_steps": 58920, "loss": 0.1629, "lr": 1.7366165772834163e-06, "epoch": 1.5639850644942295, "percentage": 31.28, "elapsed_time": "0:29:08", "remaining_time": "1:04:00", "throughput": 10117.32, "total_tokens": 17686656}
{"current_steps": 18435, "total_steps": 58920, "loss": 0.002, "lr": 1.736416208128633e-06, "epoch": 1.564409368635438, "percentage": 31.29, "elapsed_time": "0:29:08", "remaining_time": "1:03:59", "throughput": 10117.79, "total_tokens": 17691328}
{"current_steps": 18440, "total_steps": 58920, "loss": 0.04, "lr": 1.736215774355986e-06, "epoch": 1.5648336727766463, "percentage": 31.3, "elapsed_time": "0:29:08", "remaining_time": "1:03:59", "throughput": 10118.17, "total_tokens": 17695744}
{"current_steps": 18445, "total_steps": 58920, "loss": 0.0403, "lr": 1.7360152759830629e-06, "epoch": 1.5652579769178547, "percentage": 31.31, "elapsed_time": "0:29:09", "remaining_time": "1:03:58", "throughput": 10118.6, "total_tokens": 17700352}
{"current_steps": 18450, "total_steps": 58920, "loss": 0.0232, "lr": 1.7358147130274569e-06, "epoch": 1.5656822810590632, "percentage": 31.31, "elapsed_time": "0:29:09", "remaining_time": "1:03:57", "throughput": 10118.99, "total_tokens": 17704832}
{"current_steps": 18455, "total_steps": 58920, "loss": 0.0186, "lr": 1.7356140855067662e-06, "epoch": 1.5661065852002716, "percentage": 31.32, "elapsed_time": "0:29:10", "remaining_time": "1:03:57", "throughput": 10119.67, "total_tokens": 17710016}
{"current_steps": 18460, "total_steps": 58920, "loss": 0.0635, "lr": 1.7354133934385957e-06, "epoch": 1.56653088934148, "percentage": 31.33, "elapsed_time": "0:29:10", "remaining_time": "1:03:56", "throughput": 10120.04, "total_tokens": 17714496}
{"current_steps": 18465, "total_steps": 58920, "loss": 0.0206, "lr": 1.735212636840555e-06, "epoch": 1.5669551934826884, "percentage": 31.34, "elapsed_time": "0:29:10", "remaining_time": "1:03:55", "throughput": 10120.35, "total_tokens": 17718848}
{"current_steps": 18470, "total_steps": 58920, "loss": 0.0526, "lr": 1.7350118157302598e-06, "epoch": 1.5673794976238968, "percentage": 31.35, "elapsed_time": "0:29:11", "remaining_time": "1:03:55", "throughput": 10120.71, "total_tokens": 17723264}
{"current_steps": 18475, "total_steps": 58920, "loss": 0.0017, "lr": 1.7348109301253318e-06, "epoch": 1.5678038017651053, "percentage": 31.36, "elapsed_time": "0:29:11", "remaining_time": "1:03:54", "throughput": 10121.27, "total_tokens": 17728192}
{"current_steps": 18480, "total_steps": 58920, "loss": 0.0543, "lr": 1.7346099800433976e-06, "epoch": 1.5682281059063137, "percentage": 31.36, "elapsed_time": "0:29:11", "remaining_time": "1:03:53", "throughput": 10121.58, "total_tokens": 17732544}
{"current_steps": 18485, "total_steps": 58920, "loss": 0.039, "lr": 1.7344089655020899e-06, "epoch": 1.568652410047522, "percentage": 31.37, "elapsed_time": "0:29:12", "remaining_time": "1:03:53", "throughput": 10121.9, "total_tokens": 17737024}
{"current_steps": 18490, "total_steps": 58920, "loss": 0.0487, "lr": 1.734207886519047e-06, "epoch": 1.5690767141887305, "percentage": 31.38, "elapsed_time": "0:29:12", "remaining_time": "1:03:52", "throughput": 10122.19, "total_tokens": 17741312}
{"current_steps": 18495, "total_steps": 58920, "loss": 0.0645, "lr": 1.734006743111913e-06, "epoch": 1.569501018329939, "percentage": 31.39, "elapsed_time": "0:29:13", "remaining_time": "1:03:51", "throughput": 10122.75, "total_tokens": 17746176}
{"current_steps": 18500, "total_steps": 58920, "loss": 0.002, "lr": 1.7338055352983374e-06, "epoch": 1.5699253224711474, "percentage": 31.4, "elapsed_time": "0:29:13", "remaining_time": "1:03:51", "throughput": 10123.12, "total_tokens": 17750656}
{"current_steps": 18505, "total_steps": 58920, "loss": 0.001, "lr": 1.7336042630959753e-06, "epoch": 1.5703496266123558, "percentage": 31.41, "elapsed_time": "0:29:13", "remaining_time": "1:03:50", "throughput": 10123.38, "total_tokens": 17754880}
{"current_steps": 18510, "total_steps": 58920, "loss": 0.0441, "lr": 1.7334029265224878e-06, "epoch": 1.5707739307535642, "percentage": 31.42, "elapsed_time": "0:29:14", "remaining_time": "1:03:49", "throughput": 10123.96, "total_tokens": 17759808}
{"current_steps": 18515, "total_steps": 58920, "loss": 0.001, "lr": 1.7332015255955416e-06, "epoch": 1.5711982348947726, "percentage": 31.42, "elapsed_time": "0:29:14", "remaining_time": "1:03:49", "throughput": 10124.2, "total_tokens": 17764096}
{"current_steps": 18520, "total_steps": 58920, "loss": 0.0269, "lr": 1.7330000603328087e-06, "epoch": 1.571622539035981, "percentage": 31.43, "elapsed_time": "0:29:14", "remaining_time": "1:03:48", "throughput": 10124.54, "total_tokens": 17768512}
{"current_steps": 18525, "total_steps": 58920, "loss": 0.0332, "lr": 1.732798530751967e-06, "epoch": 1.5720468431771895, "percentage": 31.44, "elapsed_time": "0:29:15", "remaining_time": "1:03:47", "throughput": 10124.9, "total_tokens": 17772992}
{"current_steps": 18530, "total_steps": 58920, "loss": 0.0653, "lr": 1.7325969368707002e-06, "epoch": 1.5724711473183979, "percentage": 31.45, "elapsed_time": "0:29:15", "remaining_time": "1:03:47", "throughput": 10125.17, "total_tokens": 17777280}
{"current_steps": 18535, "total_steps": 58920, "loss": 0.0314, "lr": 1.732395278706697e-06, "epoch": 1.5728954514596063, "percentage": 31.46, "elapsed_time": "0:29:16", "remaining_time": "1:03:46", "throughput": 10125.61, "total_tokens": 17781888}
{"current_steps": 18540, "total_steps": 58920, "loss": 0.001, "lr": 1.7321935562776524e-06, "epoch": 1.5733197556008147, "percentage": 31.47, "elapsed_time": "0:29:16", "remaining_time": "1:03:45", "throughput": 10126.15, "total_tokens": 17786752}
{"current_steps": 18545, "total_steps": 58920, "loss": 0.0346, "lr": 1.7319917696012665e-06, "epoch": 1.573744059742023, "percentage": 31.47, "elapsed_time": "0:29:16", "remaining_time": "1:03:45", "throughput": 10126.63, "total_tokens": 17791488}
{"current_steps": 18550, "total_steps": 58920, "loss": 0.061, "lr": 1.731789918695246e-06, "epoch": 1.5741683638832313, "percentage": 31.48, "elapsed_time": "0:29:17", "remaining_time": "1:03:44", "throughput": 10127.25, "total_tokens": 17796544}
{"current_steps": 18555, "total_steps": 58920, "loss": 0.0347, "lr": 1.7315880035773024e-06, "epoch": 1.5745926680244398, "percentage": 31.49, "elapsed_time": "0:29:17", "remaining_time": "1:03:43", "throughput": 10127.77, "total_tokens": 17801344}
{"current_steps": 18560, "total_steps": 58920, "loss": 0.0121, "lr": 1.7313860242651526e-06, "epoch": 1.5750169721656482, "percentage": 31.5, "elapsed_time": "0:29:18", "remaining_time": "1:03:43", "throughput": 10128.13, "total_tokens": 17805760}
{"current_steps": 18565, "total_steps": 58920, "loss": 0.0163, "lr": 1.7311839807765202e-06, "epoch": 1.5754412763068566, "percentage": 31.51, "elapsed_time": "0:29:18", "remaining_time": "1:03:42", "throughput": 10128.46, "total_tokens": 17810112}
{"current_steps": 18570, "total_steps": 58920, "loss": 0.0395, "lr": 1.7309818731291327e-06, "epoch": 1.575865580448065, "percentage": 31.52, "elapsed_time": "0:29:18", "remaining_time": "1:03:41", "throughput": 10128.82, "total_tokens": 17814656}
{"current_steps": 18575, "total_steps": 58920, "loss": 0.0435, "lr": 1.7307797013407255e-06, "epoch": 1.5762898845892734, "percentage": 31.53, "elapsed_time": "0:29:19", "remaining_time": "1:03:41", "throughput": 10129.69, "total_tokens": 17820288}
{"current_steps": 18580, "total_steps": 58920, "loss": 0.0011, "lr": 1.7305774654290382e-06, "epoch": 1.5767141887304819, "percentage": 31.53, "elapsed_time": "0:29:19", "remaining_time": "1:03:40", "throughput": 10130.08, "total_tokens": 17824768}
{"current_steps": 18585, "total_steps": 58920, "loss": 0.0239, "lr": 1.7303751654118158e-06, "epoch": 1.5771384928716903, "percentage": 31.54, "elapsed_time": "0:29:19", "remaining_time": "1:03:39", "throughput": 10130.45, "total_tokens": 17829248}
{"current_steps": 18590, "total_steps": 58920, "loss": 0.0249, "lr": 1.7301728013068096e-06, "epoch": 1.5775627970128987, "percentage": 31.55, "elapsed_time": "0:29:20", "remaining_time": "1:03:38", "throughput": 10130.76, "total_tokens": 17833600}
{"current_steps": 18595, "total_steps": 58920, "loss": 0.0199, "lr": 1.7299703731317763e-06, "epoch": 1.5779871011541071, "percentage": 31.56, "elapsed_time": "0:29:20", "remaining_time": "1:03:38", "throughput": 10131.26, "total_tokens": 17838336}
{"current_steps": 18600, "total_steps": 58920, "loss": 0.0948, "lr": 1.7297678809044784e-06, "epoch": 1.5784114052953155, "percentage": 31.57, "elapsed_time": "0:29:21", "remaining_time": "1:03:37", "throughput": 10131.62, "total_tokens": 17842816}
{"current_steps": 18605, "total_steps": 58920, "loss": 0.0549, "lr": 1.7295653246426838e-06, "epoch": 1.578835709436524, "percentage": 31.58, "elapsed_time": "0:29:21", "remaining_time": "1:03:36", "throughput": 10131.93, "total_tokens": 17847168}
{"current_steps": 18610, "total_steps": 58920, "loss": 0.0297, "lr": 1.729362704364166e-06, "epoch": 1.5792600135777324, "percentage": 31.59, "elapsed_time": "0:29:21", "remaining_time": "1:03:36", "throughput": 10132.44, "total_tokens": 17851904}
{"current_steps": 18615, "total_steps": 58920, "loss": 0.0092, "lr": 1.7291600200867043e-06, "epoch": 1.5796843177189408, "percentage": 31.59, "elapsed_time": "0:29:22", "remaining_time": "1:03:35", "throughput": 10133.04, "total_tokens": 17856896}
{"current_steps": 18620, "total_steps": 58920, "loss": 0.1149, "lr": 1.7289572718280833e-06, "epoch": 1.5801086218601492, "percentage": 31.6, "elapsed_time": "0:29:22", "remaining_time": "1:03:34", "throughput": 10133.2, "total_tokens": 17861056}
{"current_steps": 18625, "total_steps": 58920, "loss": 0.0844, "lr": 1.728754459606094e-06, "epoch": 1.5805329260013576, "percentage": 31.61, "elapsed_time": "0:29:23", "remaining_time": "1:03:34", "throughput": 10133.69, "total_tokens": 17865728}
{"current_steps": 18630, "total_steps": 58920, "loss": 0.0226, "lr": 1.7285515834385315e-06, "epoch": 1.580957230142566, "percentage": 31.62, "elapsed_time": "0:29:23", "remaining_time": "1:03:33", "throughput": 10134.22, "total_tokens": 17870528}
{"current_steps": 18635, "total_steps": 58920, "loss": 0.0009, "lr": 1.7283486433431983e-06, "epoch": 1.5813815342837745, "percentage": 31.63, "elapsed_time": "0:29:23", "remaining_time": "1:03:32", "throughput": 10134.5, "total_tokens": 17874816}
{"current_steps": 18640, "total_steps": 58920, "loss": 0.0349, "lr": 1.7281456393379012e-06, "epoch": 1.581805838424983, "percentage": 31.64, "elapsed_time": "0:29:24", "remaining_time": "1:03:32", "throughput": 10134.9, "total_tokens": 17879360}
{"current_steps": 18645, "total_steps": 58920, "loss": 0.0334, "lr": 1.7279425714404533e-06, "epoch": 1.5822301425661913, "percentage": 31.64, "elapsed_time": "0:29:24", "remaining_time": "1:03:31", "throughput": 10135.85, "total_tokens": 17885120}
{"current_steps": 18650, "total_steps": 58920, "loss": 0.0215, "lr": 1.727739439668673e-06, "epoch": 1.5826544467073997, "percentage": 31.65, "elapsed_time": "0:29:24", "remaining_time": "1:03:30", "throughput": 10136.4, "total_tokens": 17889984}
{"current_steps": 18655, "total_steps": 58920, "loss": 0.0006, "lr": 1.7275362440403842e-06, "epoch": 1.5830787508486082, "percentage": 31.66, "elapsed_time": "0:29:25", "remaining_time": "1:03:30", "throughput": 10136.77, "total_tokens": 17894400}
{"current_steps": 18660, "total_steps": 58920, "loss": 0.0436, "lr": 1.7273329845734171e-06, "epoch": 1.5835030549898166, "percentage": 31.67, "elapsed_time": "0:29:25", "remaining_time": "1:03:29", "throughput": 10137.18, "total_tokens": 17899008}
{"current_steps": 18665, "total_steps": 58920, "loss": 0.0011, "lr": 1.7271296612856062e-06, "epoch": 1.583927359131025, "percentage": 31.68, "elapsed_time": "0:29:26", "remaining_time": "1:03:28", "throughput": 10137.7, "total_tokens": 17903808}
{"current_steps": 18670, "total_steps": 58920, "loss": 0.0261, "lr": 1.726926274194793e-06, "epoch": 1.5843516632722334, "percentage": 31.69, "elapsed_time": "0:29:26", "remaining_time": "1:03:28", "throughput": 10138.28, "total_tokens": 17908800}
{"current_steps": 18675, "total_steps": 58920, "loss": 0.0005, "lr": 1.7267228233188239e-06, "epoch": 1.5847759674134418, "percentage": 31.7, "elapsed_time": "0:29:26", "remaining_time": "1:03:27", "throughput": 10138.58, "total_tokens": 17913088}
{"current_steps": 18680, "total_steps": 58920, "loss": 0.0246, "lr": 1.7265193086755508e-06, "epoch": 1.5852002715546503, "percentage": 31.7, "elapsed_time": "0:29:27", "remaining_time": "1:03:26", "throughput": 10139.03, "total_tokens": 17917760}
{"current_steps": 18685, "total_steps": 58920, "loss": 0.0406, "lr": 1.7263157302828313e-06, "epoch": 1.5856245756958587, "percentage": 31.71, "elapsed_time": "0:29:27", "remaining_time": "1:03:26", "throughput": 10139.56, "total_tokens": 17922624}
{"current_steps": 18690, "total_steps": 58920, "loss": 0.0329, "lr": 1.7261120881585289e-06, "epoch": 1.586048879837067, "percentage": 31.72, "elapsed_time": "0:29:27", "remaining_time": "1:03:25", "throughput": 10140.06, "total_tokens": 17927360}
{"current_steps": 18695, "total_steps": 58920, "loss": 0.0882, "lr": 1.7259083823205126e-06, "epoch": 1.5864731839782755, "percentage": 31.73, "elapsed_time": "0:29:28", "remaining_time": "1:03:24", "throughput": 10140.59, "total_tokens": 17932160}
{"current_steps": 18700, "total_steps": 58920, "loss": 0.1062, "lr": 1.7257046127866563e-06, "epoch": 1.586897488119484, "percentage": 31.74, "elapsed_time": "0:29:28", "remaining_time": "1:03:24", "throughput": 10141.53, "total_tokens": 17937984}
{"current_steps": 18705, "total_steps": 58920, "loss": 0.0554, "lr": 1.7255007795748404e-06, "epoch": 1.5873217922606924, "percentage": 31.75, "elapsed_time": "0:29:29", "remaining_time": "1:03:23", "throughput": 10142.07, "total_tokens": 17942848}
{"current_steps": 18710, "total_steps": 58920, "loss": 0.0216, "lr": 1.7252968827029509e-06, "epoch": 1.5877460964019008, "percentage": 31.75, "elapsed_time": "0:29:29", "remaining_time": "1:03:22", "throughput": 10142.44, "total_tokens": 17947328}
{"current_steps": 18715, "total_steps": 58920, "loss": 0.0243, "lr": 1.7250929221888781e-06, "epoch": 1.5881704005431092, "percentage": 31.76, "elapsed_time": "0:29:29", "remaining_time": "1:03:22", "throughput": 10142.87, "total_tokens": 17951936}
{"current_steps": 18720, "total_steps": 58920, "loss": 0.0405, "lr": 1.7248888980505195e-06, "epoch": 1.5885947046843176, "percentage": 31.77, "elapsed_time": "0:29:30", "remaining_time": "1:03:21", "throughput": 10143.78, "total_tokens": 17957632}
{"current_steps": 18725, "total_steps": 58920, "loss": 0.023, "lr": 1.7246848103057773e-06, "epoch": 1.589019008825526, "percentage": 31.78, "elapsed_time": "0:29:30", "remaining_time": "1:03:20", "throughput": 10144.23, "total_tokens": 17962304}
{"current_steps": 18730, "total_steps": 58920, "loss": 0.0277, "lr": 1.7244806589725597e-06, "epoch": 1.5894433129667345, "percentage": 31.79, "elapsed_time": "0:29:31", "remaining_time": "1:03:20", "throughput": 10145.2, "total_tokens": 17968128}
{"current_steps": 18735, "total_steps": 58920, "loss": 0.0585, "lr": 1.7242764440687798e-06, "epoch": 1.5898676171079429, "percentage": 31.8, "elapsed_time": "0:29:31", "remaining_time": "1:03:19", "throughput": 10145.69, "total_tokens": 17972864}
{"current_steps": 18740, "total_steps": 58920, "loss": 0.015, "lr": 1.724072165612357e-06, "epoch": 1.5902919212491513, "percentage": 31.81, "elapsed_time": "0:29:31", "remaining_time": "1:03:19", "throughput": 10146.29, "total_tokens": 17977792}
{"current_steps": 18745, "total_steps": 58920, "loss": 0.0761, "lr": 1.7238678236212159e-06, "epoch": 1.5907162253903597, "percentage": 31.81, "elapsed_time": "0:29:32", "remaining_time": "1:03:18", "throughput": 10146.64, "total_tokens": 17982208}
{"current_steps": 18750, "total_steps": 58920, "loss": 0.0516, "lr": 1.7236634181132868e-06, "epoch": 1.5911405295315681, "percentage": 31.82, "elapsed_time": "0:29:32", "remaining_time": "1:03:17", "throughput": 10147.21, "total_tokens": 17987136}
{"current_steps": 18755, "total_steps": 58920, "loss": 0.0444, "lr": 1.7234589491065052e-06, "epoch": 1.5915648336727766, "percentage": 31.83, "elapsed_time": "0:29:32", "remaining_time": "1:03:16", "throughput": 10147.58, "total_tokens": 17991616}
{"current_steps": 18760, "total_steps": 58920, "loss": 0.0449, "lr": 1.7232544166188134e-06, "epoch": 1.591989137813985, "percentage": 31.84, "elapsed_time": "0:29:33", "remaining_time": "1:03:16", "throughput": 10147.98, "total_tokens": 17996160}
{"current_steps": 18765, "total_steps": 58920, "loss": 0.0411, "lr": 1.7230498206681573e-06, "epoch": 1.5924134419551934, "percentage": 31.85, "elapsed_time": "0:29:33", "remaining_time": "1:03:15", "throughput": 10148.48, "total_tokens": 18000960}
{"current_steps": 18770, "total_steps": 58920, "loss": 0.0661, "lr": 1.7228451612724906e-06, "epoch": 1.5928377460964018, "percentage": 31.86, "elapsed_time": "0:29:34", "remaining_time": "1:03:15", "throughput": 10149.26, "total_tokens": 18006400}
{"current_steps": 18775, "total_steps": 58920, "loss": 0.0308, "lr": 1.7226404384497704e-06, "epoch": 1.5932620502376103, "percentage": 31.87, "elapsed_time": "0:29:34", "remaining_time": "1:03:14", "throughput": 10149.52, "total_tokens": 18010624}
{"current_steps": 18780, "total_steps": 58920, "loss": 0.0216, "lr": 1.7224356522179608e-06, "epoch": 1.5936863543788187, "percentage": 31.87, "elapsed_time": "0:29:34", "remaining_time": "1:03:13", "throughput": 10150.12, "total_tokens": 18015616}
{"current_steps": 18785, "total_steps": 58920, "loss": 0.0318, "lr": 1.7222308025950315e-06, "epoch": 1.594110658520027, "percentage": 31.88, "elapsed_time": "0:29:35", "remaining_time": "1:03:13", "throughput": 10150.79, "total_tokens": 18020800}
{"current_steps": 18790, "total_steps": 58920, "loss": 0.0929, "lr": 1.7220258895989563e-06, "epoch": 1.5945349626612355, "percentage": 31.89, "elapsed_time": "0:29:35", "remaining_time": "1:03:12", "throughput": 10151.26, "total_tokens": 18025472}
{"current_steps": 18795, "total_steps": 58920, "loss": 0.0159, "lr": 1.7218209132477166e-06, "epoch": 1.594959266802444, "percentage": 31.9, "elapsed_time": "0:29:36", "remaining_time": "1:03:11", "throughput": 10151.68, "total_tokens": 18030080}
{"current_steps": 18800, "total_steps": 58920, "loss": 0.0824, "lr": 1.7216158735592976e-06, "epoch": 1.5953835709436524, "percentage": 31.91, "elapsed_time": "0:29:36", "remaining_time": "1:03:11", "throughput": 10152.04, "total_tokens": 18034560}
{"current_steps": 18805, "total_steps": 58920, "loss": 0.0647, "lr": 1.7214107705516912e-06, "epoch": 1.5958078750848608, "percentage": 31.92, "elapsed_time": "0:29:36", "remaining_time": "1:03:10", "throughput": 10152.66, "total_tokens": 18039616}
{"current_steps": 18810, "total_steps": 58920, "loss": 0.0071, "lr": 1.7212056042428942e-06, "epoch": 1.5962321792260692, "percentage": 31.92, "elapsed_time": "0:29:37", "remaining_time": "1:03:09", "throughput": 10152.95, "total_tokens": 18043904}
{"current_steps": 18815, "total_steps": 58920, "loss": 0.0247, "lr": 1.7210003746509095e-06, "epoch": 1.5966564833672776, "percentage": 31.93, "elapsed_time": "0:29:37", "remaining_time": "1:03:09", "throughput": 10153.75, "total_tokens": 18049344}
{"current_steps": 18820, "total_steps": 58920, "loss": 0.0016, "lr": 1.7207950817937448e-06, "epoch": 1.597080787508486, "percentage": 31.94, "elapsed_time": "0:29:37", "remaining_time": "1:03:08", "throughput": 10154.24, "total_tokens": 18054080}
{"current_steps": 18825, "total_steps": 58920, "loss": 0.0309, "lr": 1.7205897256894145e-06, "epoch": 1.5975050916496945, "percentage": 31.95, "elapsed_time": "0:29:38", "remaining_time": "1:03:07", "throughput": 10154.54, "total_tokens": 18058432}
{"current_steps": 18830, "total_steps": 58920, "loss": 0.0013, "lr": 1.7203843063559371e-06, "epoch": 1.5979293957909029, "percentage": 31.96, "elapsed_time": "0:29:38", "remaining_time": "1:03:07", "throughput": 10154.99, "total_tokens": 18063104}
{"current_steps": 18835, "total_steps": 58920, "loss": 0.0383, "lr": 1.720178823811338e-06, "epoch": 1.5983536999321113, "percentage": 31.97, "elapsed_time": "0:29:39", "remaining_time": "1:03:06", "throughput": 10155.3, "total_tokens": 18067456}
{"current_steps": 18840, "total_steps": 58920, "loss": 0.0005, "lr": 1.719973278073647e-06, "epoch": 1.5987780040733197, "percentage": 31.98, "elapsed_time": "0:29:39", "remaining_time": "1:03:05", "throughput": 10155.64, "total_tokens": 18071872}
{"current_steps": 18845, "total_steps": 58920, "loss": 0.0398, "lr": 1.7197676691609009e-06, "epoch": 1.5992023082145281, "percentage": 31.98, "elapsed_time": "0:29:39", "remaining_time": "1:03:04", "throughput": 10156.09, "total_tokens": 18076480}
{"current_steps": 18850, "total_steps": 58920, "loss": 0.0676, "lr": 1.7195619970911402e-06, "epoch": 1.5996266123557366, "percentage": 31.99, "elapsed_time": "0:29:40", "remaining_time": "1:03:04", "throughput": 10156.95, "total_tokens": 18082112}
{"current_steps": 18855, "total_steps": 58920, "loss": 0.0877, "lr": 1.719356261882412e-06, "epoch": 1.600050916496945, "percentage": 32.0, "elapsed_time": "0:29:40", "remaining_time": "1:03:03", "throughput": 10157.33, "total_tokens": 18086656}
{"current_steps": 18860, "total_steps": 58920, "loss": 0.0274, "lr": 1.7191504635527694e-06, "epoch": 1.6004752206381534, "percentage": 32.01, "elapsed_time": "0:29:41", "remaining_time": "1:03:03", "throughput": 10157.68, "total_tokens": 18091136}
{"current_steps": 18865, "total_steps": 58920, "loss": 0.0546, "lr": 1.7189446021202698e-06, "epoch": 1.6008995247793618, "percentage": 32.02, "elapsed_time": "0:29:41", "remaining_time": "1:03:02", "throughput": 10158.14, "total_tokens": 18095808}
{"current_steps": 18870, "total_steps": 58920, "loss": 0.0257, "lr": 1.7187386776029773e-06, "epoch": 1.6013238289205702, "percentage": 32.03, "elapsed_time": "0:29:41", "remaining_time": "1:03:01", "throughput": 10158.53, "total_tokens": 18100288}
{"current_steps": 18875, "total_steps": 58920, "loss": 0.1138, "lr": 1.7185326900189608e-06, "epoch": 1.6017481330617787, "percentage": 32.03, "elapsed_time": "0:29:42", "remaining_time": "1:03:01", "throughput": 10158.87, "total_tokens": 18104704}
{"current_steps": 18880, "total_steps": 58920, "loss": 0.0012, "lr": 1.718326639386295e-06, "epoch": 1.602172437202987, "percentage": 32.04, "elapsed_time": "0:29:42", "remaining_time": "1:03:00", "throughput": 10159.49, "total_tokens": 18109696}
{"current_steps": 18885, "total_steps": 58920, "loss": 0.0428, "lr": 1.71812052572306e-06, "epoch": 1.6025967413441955, "percentage": 32.05, "elapsed_time": "0:29:42", "remaining_time": "1:02:59", "throughput": 10159.92, "total_tokens": 18114304}
{"current_steps": 18890, "total_steps": 58920, "loss": 0.0468, "lr": 1.7179143490473415e-06, "epoch": 1.603021045485404, "percentage": 32.06, "elapsed_time": "0:29:43", "remaining_time": "1:02:59", "throughput": 10160.33, "total_tokens": 18118912}
{"current_steps": 18895, "total_steps": 58920, "loss": 0.0446, "lr": 1.7177081093772312e-06, "epoch": 1.6034453496266123, "percentage": 32.07, "elapsed_time": "0:29:43", "remaining_time": "1:02:58", "throughput": 10160.92, "total_tokens": 18123904}
{"current_steps": 18900, "total_steps": 58920, "loss": 0.042, "lr": 1.7175018067308256e-06, "epoch": 1.6038696537678208, "percentage": 32.08, "elapsed_time": "0:29:44", "remaining_time": "1:02:57", "throughput": 10161.76, "total_tokens": 18129472}
{"current_steps": 18905, "total_steps": 58920, "loss": 0.0373, "lr": 1.717295441126227e-06, "epoch": 1.6042939579090292, "percentage": 32.09, "elapsed_time": "0:29:44", "remaining_time": "1:02:57", "throughput": 10162.37, "total_tokens": 18134528}
{"current_steps": 18910, "total_steps": 58920, "loss": 0.0287, "lr": 1.717089012581543e-06, "epoch": 1.6047182620502376, "percentage": 32.09, "elapsed_time": "0:29:44", "remaining_time": "1:02:56", "throughput": 10162.77, "total_tokens": 18139072}
{"current_steps": 18915, "total_steps": 58920, "loss": 0.0013, "lr": 1.7168825211148871e-06, "epoch": 1.605142566191446, "percentage": 32.1, "elapsed_time": "0:29:45", "remaining_time": "1:02:55", "throughput": 10163.16, "total_tokens": 18143616}
{"current_steps": 18920, "total_steps": 58920, "loss": 0.0649, "lr": 1.7166759667443786e-06, "epoch": 1.6055668703326544, "percentage": 32.11, "elapsed_time": "0:29:45", "remaining_time": "1:02:55", "throughput": 10163.6, "total_tokens": 18148288}
{"current_steps": 18925, "total_steps": 58920, "loss": 0.0429, "lr": 1.7164693494881416e-06, "epoch": 1.6059911744738629, "percentage": 32.12, "elapsed_time": "0:29:46", "remaining_time": "1:02:54", "throughput": 10164.46, "total_tokens": 18153920}
{"current_steps": 18930, "total_steps": 58920, "loss": 0.0258, "lr": 1.7162626693643057e-06, "epoch": 1.6064154786150713, "percentage": 32.13, "elapsed_time": "0:29:46", "remaining_time": "1:02:53", "throughput": 10164.79, "total_tokens": 18158272}
{"current_steps": 18935, "total_steps": 58920, "loss": 0.0309, "lr": 1.7160559263910067e-06, "epoch": 1.6068397827562797, "percentage": 32.14, "elapsed_time": "0:29:46", "remaining_time": "1:02:53", "throughput": 10165.13, "total_tokens": 18162688}
{"current_steps": 18940, "total_steps": 58920, "loss": 0.0009, "lr": 1.7158491205863855e-06, "epoch": 1.6072640868974881, "percentage": 32.15, "elapsed_time": "0:29:47", "remaining_time": "1:02:52", "throughput": 10165.81, "total_tokens": 18167872}
{"current_steps": 18945, "total_steps": 58920, "loss": 0.0611, "lr": 1.7156422519685885e-06, "epoch": 1.6076883910386965, "percentage": 32.15, "elapsed_time": "0:29:47", "remaining_time": "1:02:51", "throughput": 10166.25, "total_tokens": 18172544}
{"current_steps": 18950, "total_steps": 58920, "loss": 0.0555, "lr": 1.7154353205557675e-06, "epoch": 1.608112695179905, "percentage": 32.16, "elapsed_time": "0:29:47", "remaining_time": "1:02:51", "throughput": 10166.94, "total_tokens": 18177728}
{"current_steps": 18955, "total_steps": 58920, "loss": 0.0668, "lr": 1.7152283263660806e-06, "epoch": 1.6085369993211134, "percentage": 32.17, "elapsed_time": "0:29:48", "remaining_time": "1:02:50", "throughput": 10167.32, "total_tokens": 18182208}
{"current_steps": 18960, "total_steps": 58920, "loss": 0.0016, "lr": 1.71502126941769e-06, "epoch": 1.6089613034623218, "percentage": 32.18, "elapsed_time": "0:29:48", "remaining_time": "1:02:49", "throughput": 10167.68, "total_tokens": 18186688}
{"current_steps": 18965, "total_steps": 58920, "loss": 0.0008, "lr": 1.714814149728765e-06, "epoch": 1.6093856076035302, "percentage": 32.19, "elapsed_time": "0:29:49", "remaining_time": "1:02:49", "throughput": 10168.05, "total_tokens": 18191168}
{"current_steps": 18970, "total_steps": 58920, "loss": 0.0392, "lr": 1.7146069673174788e-06, "epoch": 1.6098099117447386, "percentage": 32.2, "elapsed_time": "0:29:49", "remaining_time": "1:02:48", "throughput": 10168.6, "total_tokens": 18196096}
{"current_steps": 18975, "total_steps": 58920, "loss": 0.0343, "lr": 1.7143997222020117e-06, "epoch": 1.610234215885947, "percentage": 32.2, "elapsed_time": "0:29:49", "remaining_time": "1:02:47", "throughput": 10168.88, "total_tokens": 18200448}
{"current_steps": 18980, "total_steps": 58920, "loss": 0.0557, "lr": 1.7141924144005477e-06, "epoch": 1.6106585200271555, "percentage": 32.21, "elapsed_time": "0:29:50", "remaining_time": "1:02:47", "throughput": 10169.25, "total_tokens": 18204928}
{"current_steps": 18985, "total_steps": 58920, "loss": 0.0253, "lr": 1.7139850439312787e-06, "epoch": 1.611082824168364, "percentage": 32.22, "elapsed_time": "0:29:50", "remaining_time": "1:02:46", "throughput": 10169.83, "total_tokens": 18209920}
{"current_steps": 18990, "total_steps": 58920, "loss": 0.0725, "lr": 1.7137776108123994e-06, "epoch": 1.6115071283095723, "percentage": 32.23, "elapsed_time": "0:29:50", "remaining_time": "1:02:45", "throughput": 10170.31, "total_tokens": 18214656}
{"current_steps": 18995, "total_steps": 58920, "loss": 0.0007, "lr": 1.713570115062112e-06, "epoch": 1.6119314324507807, "percentage": 32.24, "elapsed_time": "0:29:51", "remaining_time": "1:02:45", "throughput": 10170.78, "total_tokens": 18219392}
{"current_steps": 19000, "total_steps": 58920, "loss": 0.0233, "lr": 1.7133625566986231e-06, "epoch": 1.6123557365919892, "percentage": 32.25, "elapsed_time": "0:29:51", "remaining_time": "1:02:44", "throughput": 10171.37, "total_tokens": 18224448}
{"current_steps": 19005, "total_steps": 58920, "loss": 0.0048, "lr": 1.7131549357401455e-06, "epoch": 1.6127800407331976, "percentage": 32.26, "elapsed_time": "0:29:52", "remaining_time": "1:02:43", "throughput": 10171.89, "total_tokens": 18229312}
{"current_steps": 19010, "total_steps": 58920, "loss": 0.0006, "lr": 1.7129472522048973e-06, "epoch": 1.613204344874406, "percentage": 32.26, "elapsed_time": "0:29:52", "remaining_time": "1:02:43", "throughput": 10172.32, "total_tokens": 18233920}
{"current_steps": 19015, "total_steps": 58920, "loss": 0.0279, "lr": 1.7127395061111018e-06, "epoch": 1.6136286490156144, "percentage": 32.27, "elapsed_time": "0:29:52", "remaining_time": "1:02:42", "throughput": 10172.73, "total_tokens": 18238464}
{"current_steps": 19020, "total_steps": 58920, "loss": 0.0216, "lr": 1.712531697476988e-06, "epoch": 1.6140529531568228, "percentage": 32.28, "elapsed_time": "0:29:53", "remaining_time": "1:02:41", "throughput": 10173.14, "total_tokens": 18243072}
{"current_steps": 19025, "total_steps": 58920, "loss": 0.0519, "lr": 1.7123238263207901e-06, "epoch": 1.6144772572980313, "percentage": 32.29, "elapsed_time": "0:29:53", "remaining_time": "1:02:41", "throughput": 10173.74, "total_tokens": 18248064}
{"current_steps": 19030, "total_steps": 58920, "loss": 0.0694, "lr": 1.7121158926607487e-06, "epoch": 1.6149015614392397, "percentage": 32.3, "elapsed_time": "0:29:54", "remaining_time": "1:02:40", "throughput": 10174.13, "total_tokens": 18252608}
{"current_steps": 19035, "total_steps": 58920, "loss": 0.0281, "lr": 1.7119078965151084e-06, "epoch": 1.615325865580448, "percentage": 32.31, "elapsed_time": "0:29:54", "remaining_time": "1:02:39", "throughput": 10174.53, "total_tokens": 18257152}
{"current_steps": 19040, "total_steps": 58920, "loss": 0.0402, "lr": 1.7116998379021208e-06, "epoch": 1.6157501697216565, "percentage": 32.32, "elapsed_time": "0:29:54", "remaining_time": "1:02:39", "throughput": 10174.91, "total_tokens": 18261696}
{"current_steps": 19045, "total_steps": 58920, "loss": 0.0328, "lr": 1.7114917168400416e-06, "epoch": 1.616174473862865, "percentage": 32.32, "elapsed_time": "0:29:55", "remaining_time": "1:02:38", "throughput": 10175.47, "total_tokens": 18266624}
{"current_steps": 19050, "total_steps": 58920, "loss": 0.0333, "lr": 1.7112835333471333e-06, "epoch": 1.6165987780040734, "percentage": 32.33, "elapsed_time": "0:29:55", "remaining_time": "1:02:37", "throughput": 10175.82, "total_tokens": 18271040}
{"current_steps": 19055, "total_steps": 58920, "loss": 0.1636, "lr": 1.7110752874416631e-06, "epoch": 1.6170230821452818, "percentage": 32.34, "elapsed_time": "0:29:55", "remaining_time": "1:02:37", "throughput": 10176.3, "total_tokens": 18275776}
{"current_steps": 19060, "total_steps": 58920, "loss": 0.0027, "lr": 1.7108669791419036e-06, "epoch": 1.6174473862864902, "percentage": 32.35, "elapsed_time": "0:29:56", "remaining_time": "1:02:36", "throughput": 10176.61, "total_tokens": 18280128}
{"current_steps": 19065, "total_steps": 58920, "loss": 0.0016, "lr": 1.7106586084661336e-06, "epoch": 1.6178716904276986, "percentage": 32.36, "elapsed_time": "0:29:56", "remaining_time": "1:02:35", "throughput": 10177.12, "total_tokens": 18284928}
{"current_steps": 19070, "total_steps": 58920, "loss": 0.058, "lr": 1.7104501754326362e-06, "epoch": 1.618295994568907, "percentage": 32.37, "elapsed_time": "0:29:57", "remaining_time": "1:02:35", "throughput": 10177.48, "total_tokens": 18289408}
{"current_steps": 19075, "total_steps": 58920, "loss": 0.0629, "lr": 1.7102416800597012e-06, "epoch": 1.6187202987101155, "percentage": 32.37, "elapsed_time": "0:29:57", "remaining_time": "1:02:34", "throughput": 10177.88, "total_tokens": 18294016}
{"current_steps": 19080, "total_steps": 58920, "loss": 0.0347, "lr": 1.710033122365623e-06, "epoch": 1.6191446028513239, "percentage": 32.38, "elapsed_time": "0:29:57", "remaining_time": "1:02:33", "throughput": 10178.26, "total_tokens": 18298560}
{"current_steps": 19085, "total_steps": 58920, "loss": 0.022, "lr": 1.7098245023687019e-06, "epoch": 1.6195689069925323, "percentage": 32.39, "elapsed_time": "0:29:58", "remaining_time": "1:02:33", "throughput": 10178.66, "total_tokens": 18303104}
{"current_steps": 19090, "total_steps": 58920, "loss": 0.0411, "lr": 1.7096158200872432e-06, "epoch": 1.6199932111337407, "percentage": 32.4, "elapsed_time": "0:29:58", "remaining_time": "1:02:32", "throughput": 10179.03, "total_tokens": 18307584}
{"current_steps": 19095, "total_steps": 58920, "loss": 0.0014, "lr": 1.7094070755395588e-06, "epoch": 1.6204175152749491, "percentage": 32.41, "elapsed_time": "0:29:58", "remaining_time": "1:02:31", "throughput": 10179.36, "total_tokens": 18312000}
{"current_steps": 19100, "total_steps": 58920, "loss": 0.0004, "lr": 1.7091982687439647e-06, "epoch": 1.6208418194161576, "percentage": 32.42, "elapsed_time": "0:29:59", "remaining_time": "1:02:31", "throughput": 10179.84, "total_tokens": 18316800}
{"current_steps": 19105, "total_steps": 58920, "loss": 0.0623, "lr": 1.7089893997187829e-06, "epoch": 1.621266123557366, "percentage": 32.43, "elapsed_time": "0:29:59", "remaining_time": "1:02:30", "throughput": 10180.04, "total_tokens": 18320896}
{"current_steps": 19110, "total_steps": 58920, "loss": 0.0425, "lr": 1.7087804684823411e-06, "epoch": 1.6216904276985744, "percentage": 32.43, "elapsed_time": "0:30:00", "remaining_time": "1:02:29", "throughput": 10181.24, "total_tokens": 18327360}
{"current_steps": 19115, "total_steps": 58920, "loss": 0.0284, "lr": 1.7085714750529726e-06, "epoch": 1.6221147318397828, "percentage": 32.44, "elapsed_time": "0:30:00", "remaining_time": "1:02:29", "throughput": 10181.48, "total_tokens": 18331584}
{"current_steps": 19120, "total_steps": 58920, "loss": 0.0401, "lr": 1.708362419449015e-06, "epoch": 1.6225390359809913, "percentage": 32.45, "elapsed_time": "0:30:00", "remaining_time": "1:02:28", "throughput": 10181.8, "total_tokens": 18335936}
{"current_steps": 19125, "total_steps": 58920, "loss": 0.014, "lr": 1.7081533016888128e-06, "epoch": 1.6229633401221997, "percentage": 32.46, "elapsed_time": "0:30:01", "remaining_time": "1:02:27", "throughput": 10182.2, "total_tokens": 18340544}
{"current_steps": 19130, "total_steps": 58920, "loss": 0.0594, "lr": 1.707944121790715e-06, "epoch": 1.623387644263408, "percentage": 32.47, "elapsed_time": "0:30:01", "remaining_time": "1:02:27", "throughput": 10182.75, "total_tokens": 18345472}
{"current_steps": 19135, "total_steps": 58920, "loss": 0.0176, "lr": 1.7077348797730768e-06, "epoch": 1.6238119484046165, "percentage": 32.48, "elapsed_time": "0:30:02", "remaining_time": "1:02:26", "throughput": 10183.36, "total_tokens": 18350528}
{"current_steps": 19140, "total_steps": 58920, "loss": 0.0566, "lr": 1.707525575654258e-06, "epoch": 1.624236252545825, "percentage": 32.48, "elapsed_time": "0:30:02", "remaining_time": "1:02:26", "throughput": 10183.83, "total_tokens": 18355264}
{"current_steps": 19145, "total_steps": 58920, "loss": 0.1037, "lr": 1.7073162094526245e-06, "epoch": 1.6246605566870334, "percentage": 32.49, "elapsed_time": "0:30:02", "remaining_time": "1:02:25", "throughput": 10184.48, "total_tokens": 18360384}
{"current_steps": 19150, "total_steps": 58920, "loss": 0.0006, "lr": 1.7071067811865474e-06, "epoch": 1.6250848608282418, "percentage": 32.5, "elapsed_time": "0:30:03", "remaining_time": "1:02:24", "throughput": 10184.75, "total_tokens": 18364672}
{"current_steps": 19155, "total_steps": 58920, "loss": 0.0276, "lr": 1.7068972908744032e-06, "epoch": 1.6255091649694502, "percentage": 32.51, "elapsed_time": "0:30:03", "remaining_time": "1:02:24", "throughput": 10185.37, "total_tokens": 18369728}
{"current_steps": 19160, "total_steps": 58920, "loss": 0.0652, "lr": 1.706687738534574e-06, "epoch": 1.6259334691106586, "percentage": 32.52, "elapsed_time": "0:30:03", "remaining_time": "1:02:23", "throughput": 10185.84, "total_tokens": 18374464}
{"current_steps": 19165, "total_steps": 58920, "loss": 0.0131, "lr": 1.7064781241854474e-06, "epoch": 1.626357773251867, "percentage": 32.53, "elapsed_time": "0:30:04", "remaining_time": "1:02:22", "throughput": 10186.26, "total_tokens": 18379072}
{"current_steps": 19170, "total_steps": 58920, "loss": 0.0016, "lr": 1.7062684478454158e-06, "epoch": 1.6267820773930755, "percentage": 32.54, "elapsed_time": "0:30:04", "remaining_time": "1:02:22", "throughput": 10186.7, "total_tokens": 18383744}
{"current_steps": 19175, "total_steps": 58920, "loss": 0.0119, "lr": 1.7060587095328783e-06, "epoch": 1.6272063815342839, "percentage": 32.54, "elapsed_time": "0:30:05", "remaining_time": "1:02:21", "throughput": 10187.08, "total_tokens": 18388288}
{"current_steps": 19180, "total_steps": 58920, "loss": 0.0588, "lr": 1.7058489092662378e-06, "epoch": 1.6276306856754923, "percentage": 32.55, "elapsed_time": "0:30:05", "remaining_time": "1:02:20", "throughput": 10187.5, "total_tokens": 18392896}
{"current_steps": 19185, "total_steps": 58920, "loss": 0.05, "lr": 1.705639047063904e-06, "epoch": 1.6280549898167007, "percentage": 32.56, "elapsed_time": "0:30:05", "remaining_time": "1:02:20", "throughput": 10187.91, "total_tokens": 18397504}
{"current_steps": 19190, "total_steps": 58920, "loss": 0.0146, "lr": 1.7054291229442916e-06, "epoch": 1.6284792939579091, "percentage": 32.57, "elapsed_time": "0:30:06", "remaining_time": "1:02:19", "throughput": 10188.57, "total_tokens": 18402688}
{"current_steps": 19195, "total_steps": 58920, "loss": 0.0264, "lr": 1.705219136925821e-06, "epoch": 1.6289035980991176, "percentage": 32.58, "elapsed_time": "0:30:06", "remaining_time": "1:02:18", "throughput": 10189.11, "total_tokens": 18407616}
{"current_steps": 19200, "total_steps": 58920, "loss": 0.0684, "lr": 1.7050090890269168e-06, "epoch": 1.629327902240326, "percentage": 32.59, "elapsed_time": "0:30:06", "remaining_time": "1:02:18", "throughput": 10189.55, "total_tokens": 18412224}
{"current_steps": 19205, "total_steps": 58920, "loss": 0.0216, "lr": 1.7047989792660107e-06, "epoch": 1.6297522063815344, "percentage": 32.6, "elapsed_time": "0:30:07", "remaining_time": "1:02:17", "throughput": 10190.1, "total_tokens": 18417088}
{"current_steps": 19210, "total_steps": 58920, "loss": 0.0173, "lr": 1.7045888076615388e-06, "epoch": 1.6301765105227428, "percentage": 32.6, "elapsed_time": "0:30:07", "remaining_time": "1:02:16", "throughput": 10190.87, "total_tokens": 18422592}
{"current_steps": 19215, "total_steps": 58920, "loss": 0.0282, "lr": 1.704378574231943e-06, "epoch": 1.6306008146639512, "percentage": 32.61, "elapsed_time": "0:30:08", "remaining_time": "1:02:16", "throughput": 10191.5, "total_tokens": 18427712}
{"current_steps": 19220, "total_steps": 58920, "loss": 0.0143, "lr": 1.7041682789956701e-06, "epoch": 1.6310251188051597, "percentage": 32.62, "elapsed_time": "0:30:08", "remaining_time": "1:02:15", "throughput": 10192.24, "total_tokens": 18433152}
{"current_steps": 19225, "total_steps": 58920, "loss": 0.0237, "lr": 1.7039579219711735e-06, "epoch": 1.631449422946368, "percentage": 32.63, "elapsed_time": "0:30:08", "remaining_time": "1:02:14", "throughput": 10192.56, "total_tokens": 18437568}
{"current_steps": 19230, "total_steps": 58920, "loss": 0.004, "lr": 1.7037475031769108e-06, "epoch": 1.6318737270875765, "percentage": 32.64, "elapsed_time": "0:30:09", "remaining_time": "1:02:14", "throughput": 10192.8, "total_tokens": 18441856}
{"current_steps": 19235, "total_steps": 58920, "loss": 0.0903, "lr": 1.7035370226313454e-06, "epoch": 1.632298031228785, "percentage": 32.65, "elapsed_time": "0:30:09", "remaining_time": "1:02:13", "throughput": 10193.3, "total_tokens": 18446656}
{"current_steps": 19240, "total_steps": 58920, "loss": 0.0233, "lr": 1.7033264803529468e-06, "epoch": 1.6327223353699933, "percentage": 32.65, "elapsed_time": "0:30:10", "remaining_time": "1:02:13", "throughput": 10193.71, "total_tokens": 18451264}
{"current_steps": 19245, "total_steps": 58920, "loss": 0.0403, "lr": 1.7031158763601885e-06, "epoch": 1.6331466395112018, "percentage": 32.66, "elapsed_time": "0:30:10", "remaining_time": "1:02:12", "throughput": 10194.28, "total_tokens": 18456256}
{"current_steps": 19250, "total_steps": 58920, "loss": 0.0236, "lr": 1.7029052106715507e-06, "epoch": 1.6335709436524102, "percentage": 32.67, "elapsed_time": "0:30:10", "remaining_time": "1:02:11", "throughput": 10194.8, "total_tokens": 18461184}
{"current_steps": 19255, "total_steps": 58920, "loss": 0.0415, "lr": 1.7026944833055189e-06, "epoch": 1.6339952477936186, "percentage": 32.68, "elapsed_time": "0:30:11", "remaining_time": "1:02:11", "throughput": 10195.2, "total_tokens": 18465792}
{"current_steps": 19260, "total_steps": 58920, "loss": 0.0314, "lr": 1.7024836942805828e-06, "epoch": 1.634419551934827, "percentage": 32.69, "elapsed_time": "0:30:11", "remaining_time": "1:02:10", "throughput": 10195.69, "total_tokens": 18470592}
{"current_steps": 19265, "total_steps": 58920, "loss": 0.0736, "lr": 1.7022728436152386e-06, "epoch": 1.6348438560760354, "percentage": 32.7, "elapsed_time": "0:30:11", "remaining_time": "1:02:09", "throughput": 10196.21, "total_tokens": 18475456}
{"current_steps": 19270, "total_steps": 58920, "loss": 0.0501, "lr": 1.7020619313279886e-06, "epoch": 1.6352681602172439, "percentage": 32.71, "elapsed_time": "0:30:12", "remaining_time": "1:02:09", "throughput": 10196.37, "total_tokens": 18479488}
{"current_steps": 19275, "total_steps": 58920, "loss": 0.0258, "lr": 1.7018509574373384e-06, "epoch": 1.6356924643584523, "percentage": 32.71, "elapsed_time": "0:30:12", "remaining_time": "1:02:08", "throughput": 10197.07, "total_tokens": 18484800}
{"current_steps": 19280, "total_steps": 58920, "loss": 0.0851, "lr": 1.7016399219618006e-06, "epoch": 1.6361167684996607, "percentage": 32.72, "elapsed_time": "0:30:13", "remaining_time": "1:02:07", "throughput": 10197.33, "total_tokens": 18489088}
{"current_steps": 19285, "total_steps": 58920, "loss": 0.0097, "lr": 1.7014288249198933e-06, "epoch": 1.6365410726408691, "percentage": 32.73, "elapsed_time": "0:30:13", "remaining_time": "1:02:07", "throughput": 10197.87, "total_tokens": 18494016}
{"current_steps": 19290, "total_steps": 58920, "loss": 0.09, "lr": 1.7012176663301392e-06, "epoch": 1.6369653767820775, "percentage": 32.74, "elapsed_time": "0:30:13", "remaining_time": "1:02:06", "throughput": 10198.63, "total_tokens": 18499520}
{"current_steps": 19295, "total_steps": 58920, "loss": 0.0337, "lr": 1.7010064462110662e-06, "epoch": 1.637389680923286, "percentage": 32.75, "elapsed_time": "0:30:14", "remaining_time": "1:02:05", "throughput": 10199.37, "total_tokens": 18504960}
{"current_steps": 19300, "total_steps": 58920, "loss": 0.0964, "lr": 1.700795164581209e-06, "epoch": 1.6378139850644944, "percentage": 32.76, "elapsed_time": "0:30:14", "remaining_time": "1:02:05", "throughput": 10199.5, "total_tokens": 18509120}
{"current_steps": 19305, "total_steps": 58920, "loss": 0.0481, "lr": 1.700583821459106e-06, "epoch": 1.6382382892057028, "percentage": 32.76, "elapsed_time": "0:30:15", "remaining_time": "1:02:04", "throughput": 10200.37, "total_tokens": 18514880}
{"current_steps": 19310, "total_steps": 58920, "loss": 0.0125, "lr": 1.700372416863302e-06, "epoch": 1.6386625933469112, "percentage": 32.77, "elapsed_time": "0:30:15", "remaining_time": "1:02:04", "throughput": 10200.96, "total_tokens": 18519936}
{"current_steps": 19315, "total_steps": 58920, "loss": 0.0251, "lr": 1.7001609508123474e-06, "epoch": 1.6390868974881196, "percentage": 32.78, "elapsed_time": "0:30:15", "remaining_time": "1:02:03", "throughput": 10201.19, "total_tokens": 18524160}
{"current_steps": 19320, "total_steps": 58920, "loss": 0.0328, "lr": 1.6999494233247972e-06, "epoch": 1.639511201629328, "percentage": 32.79, "elapsed_time": "0:30:16", "remaining_time": "1:02:02", "throughput": 10201.65, "total_tokens": 18528832}
{"current_steps": 19325, "total_steps": 58920, "loss": 0.0315, "lr": 1.699737834419212e-06, "epoch": 1.6399355057705365, "percentage": 32.8, "elapsed_time": "0:30:16", "remaining_time": "1:02:02", "throughput": 10202.2, "total_tokens": 18533760}
{"current_steps": 19330, "total_steps": 58920, "loss": 0.027, "lr": 1.6995261841141583e-06, "epoch": 1.640359809911745, "percentage": 32.81, "elapsed_time": "0:30:17", "remaining_time": "1:02:01", "throughput": 10202.66, "total_tokens": 18538432}
{"current_steps": 19335, "total_steps": 58920, "loss": 0.0232, "lr": 1.6993144724282077e-06, "epoch": 1.640784114052953, "percentage": 32.82, "elapsed_time": "0:30:17", "remaining_time": "1:02:00", "throughput": 10203.27, "total_tokens": 18543488}
{"current_steps": 19340, "total_steps": 58920, "loss": 0.0585, "lr": 1.6991026993799374e-06, "epoch": 1.6412084181941615, "percentage": 32.82, "elapsed_time": "0:30:17", "remaining_time": "1:02:00", "throughput": 10203.56, "total_tokens": 18547840}
{"current_steps": 19345, "total_steps": 58920, "loss": 0.0025, "lr": 1.6988908649879287e-06, "epoch": 1.64163272233537, "percentage": 32.83, "elapsed_time": "0:30:18", "remaining_time": "1:01:59", "throughput": 10203.85, "total_tokens": 18552192}
{"current_steps": 19350, "total_steps": 58920, "loss": 0.0096, "lr": 1.6986789692707704e-06, "epoch": 1.6420570264765784, "percentage": 32.84, "elapsed_time": "0:30:18", "remaining_time": "1:01:58", "throughput": 10204.49, "total_tokens": 18557312}
{"current_steps": 19355, "total_steps": 58920, "loss": 0.0233, "lr": 1.6984670122470548e-06, "epoch": 1.6424813306177868, "percentage": 32.85, "elapsed_time": "0:30:18", "remaining_time": "1:01:58", "throughput": 10205.11, "total_tokens": 18562432}
{"current_steps": 19360, "total_steps": 58920, "loss": 0.049, "lr": 1.6982549939353806e-06, "epoch": 1.6429056347589952, "percentage": 32.86, "elapsed_time": "0:30:19", "remaining_time": "1:01:57", "throughput": 10205.56, "total_tokens": 18567104}
{"current_steps": 19365, "total_steps": 58920, "loss": 0.0446, "lr": 1.698042914354352e-06, "epoch": 1.6433299389002036, "percentage": 32.87, "elapsed_time": "0:30:19", "remaining_time": "1:01:56", "throughput": 10206.01, "total_tokens": 18571840}
{"current_steps": 19370, "total_steps": 58920, "loss": 0.0015, "lr": 1.6978307735225778e-06, "epoch": 1.643754243041412, "percentage": 32.88, "elapsed_time": "0:30:20", "remaining_time": "1:01:56", "throughput": 10206.49, "total_tokens": 18576640}
{"current_steps": 19375, "total_steps": 58920, "loss": 0.0215, "lr": 1.6976185714586726e-06, "epoch": 1.6441785471826205, "percentage": 32.88, "elapsed_time": "0:30:20", "remaining_time": "1:01:55", "throughput": 10206.87, "total_tokens": 18581184}
{"current_steps": 19380, "total_steps": 58920, "loss": 0.0264, "lr": 1.6974063081812568e-06, "epoch": 1.6446028513238289, "percentage": 32.89, "elapsed_time": "0:30:20", "remaining_time": "1:01:54", "throughput": 10207.17, "total_tokens": 18585536}
{"current_steps": 19385, "total_steps": 58920, "loss": 0.0193, "lr": 1.6971939837089555e-06, "epoch": 1.6450271554650373, "percentage": 32.9, "elapsed_time": "0:30:21", "remaining_time": "1:01:54", "throughput": 10207.76, "total_tokens": 18590592}
{"current_steps": 19390, "total_steps": 58920, "loss": 0.0866, "lr": 1.696981598060399e-06, "epoch": 1.6454514596062457, "percentage": 32.91, "elapsed_time": "0:30:21", "remaining_time": "1:01:53", "throughput": 10208.68, "total_tokens": 18596480}
{"current_steps": 19395, "total_steps": 58920, "loss": 0.0804, "lr": 1.696769151254224e-06, "epoch": 1.6458757637474541, "percentage": 32.92, "elapsed_time": "0:30:22", "remaining_time": "1:01:53", "throughput": 10209.25, "total_tokens": 18601472}
{"current_steps": 19400, "total_steps": 58920, "loss": 0.0598, "lr": 1.6965566433090715e-06, "epoch": 1.6463000678886626, "percentage": 32.93, "elapsed_time": "0:30:22", "remaining_time": "1:01:52", "throughput": 10209.84, "total_tokens": 18606528}
{"current_steps": 19405, "total_steps": 58920, "loss": 0.0024, "lr": 1.6963440742435884e-06, "epoch": 1.646724372029871, "percentage": 32.93, "elapsed_time": "0:30:22", "remaining_time": "1:01:51", "throughput": 10210.3, "total_tokens": 18611264}
{"current_steps": 19410, "total_steps": 58920, "loss": 0.0522, "lr": 1.696131444076427e-06, "epoch": 1.6471486761710794, "percentage": 32.94, "elapsed_time": "0:30:23", "remaining_time": "1:01:51", "throughput": 10210.6, "total_tokens": 18615616}
{"current_steps": 19415, "total_steps": 58920, "loss": 0.0867, "lr": 1.6959187528262446e-06, "epoch": 1.6475729803122878, "percentage": 32.95, "elapsed_time": "0:30:23", "remaining_time": "1:01:50", "throughput": 10211.0, "total_tokens": 18620224}
{"current_steps": 19420, "total_steps": 58920, "loss": 0.0615, "lr": 1.6957060005117043e-06, "epoch": 1.6479972844534962, "percentage": 32.96, "elapsed_time": "0:30:23", "remaining_time": "1:01:49", "throughput": 10211.5, "total_tokens": 18625024}
{"current_steps": 19425, "total_steps": 58920, "loss": 0.0104, "lr": 1.6954931871514745e-06, "epoch": 1.6484215885947047, "percentage": 32.97, "elapsed_time": "0:30:24", "remaining_time": "1:01:49", "throughput": 10211.9, "total_tokens": 18629632}
{"current_steps": 19430, "total_steps": 58920, "loss": 0.0009, "lr": 1.6952803127642285e-06, "epoch": 1.648845892735913, "percentage": 32.98, "elapsed_time": "0:30:24", "remaining_time": "1:01:48", "throughput": 10212.2, "total_tokens": 18633984}
{"current_steps": 19435, "total_steps": 58920, "loss": 0.0986, "lr": 1.6950673773686455e-06, "epoch": 1.6492701968771215, "percentage": 32.99, "elapsed_time": "0:30:25", "remaining_time": "1:01:47", "throughput": 10212.88, "total_tokens": 18639168}
{"current_steps": 19440, "total_steps": 58920, "loss": 0.0008, "lr": 1.6948543809834092e-06, "epoch": 1.64969450101833, "percentage": 32.99, "elapsed_time": "0:30:25", "remaining_time": "1:01:47", "throughput": 10213.39, "total_tokens": 18643968}
{"current_steps": 19445, "total_steps": 58920, "loss": 0.0006, "lr": 1.69464132362721e-06, "epoch": 1.6501188051595383, "percentage": 33.0, "elapsed_time": "0:30:25", "remaining_time": "1:01:46", "throughput": 10213.88, "total_tokens": 18648768}
{"current_steps": 19450, "total_steps": 58920, "loss": 0.0248, "lr": 1.6944282053187427e-06, "epoch": 1.6505431093007468, "percentage": 33.01, "elapsed_time": "0:30:26", "remaining_time": "1:01:45", "throughput": 10214.4, "total_tokens": 18653632}
{"current_steps": 19455, "total_steps": 58920, "loss": 0.0067, "lr": 1.6942150260767076e-06, "epoch": 1.6509674134419552, "percentage": 33.02, "elapsed_time": "0:30:26", "remaining_time": "1:01:45", "throughput": 10214.94, "total_tokens": 18658560}
{"current_steps": 19460, "total_steps": 58920, "loss": 0.0004, "lr": 1.6940017859198105e-06, "epoch": 1.6513917175831636, "percentage": 33.03, "elapsed_time": "0:30:26", "remaining_time": "1:01:44", "throughput": 10215.19, "total_tokens": 18662848}
{"current_steps": 19465, "total_steps": 58920, "loss": 0.0789, "lr": 1.6937884848667624e-06, "epoch": 1.651816021724372, "percentage": 33.04, "elapsed_time": "0:30:27", "remaining_time": "1:01:43", "throughput": 10215.68, "total_tokens": 18667648}
{"current_steps": 19470, "total_steps": 58920, "loss": 0.0492, "lr": 1.6935751229362795e-06, "epoch": 1.6522403258655805, "percentage": 33.04, "elapsed_time": "0:30:27", "remaining_time": "1:01:43", "throughput": 10216.18, "total_tokens": 18672448}
{"current_steps": 19475, "total_steps": 58920, "loss": 0.0582, "lr": 1.6933617001470836e-06, "epoch": 1.6526646300067889, "percentage": 33.05, "elapsed_time": "0:30:28", "remaining_time": "1:01:42", "throughput": 10216.63, "total_tokens": 18677120}
{"current_steps": 19480, "total_steps": 58920, "loss": 0.0124, "lr": 1.6931482165179021e-06, "epoch": 1.6530889341479973, "percentage": 33.06, "elapsed_time": "0:30:28", "remaining_time": "1:01:42", "throughput": 10217.05, "total_tokens": 18681728}
{"current_steps": 19485, "total_steps": 58920, "loss": 0.0008, "lr": 1.6929346720674671e-06, "epoch": 1.6535132382892057, "percentage": 33.07, "elapsed_time": "0:30:28", "remaining_time": "1:01:41", "throughput": 10217.26, "total_tokens": 18685888}
{"current_steps": 19490, "total_steps": 58920, "loss": 0.0003, "lr": 1.6927210668145163e-06, "epoch": 1.6539375424304141, "percentage": 33.08, "elapsed_time": "0:30:29", "remaining_time": "1:01:40", "throughput": 10217.75, "total_tokens": 18690688}
{"current_steps": 19495, "total_steps": 58920, "loss": 0.0043, "lr": 1.6925074007777931e-06, "epoch": 1.6543618465716226, "percentage": 33.09, "elapsed_time": "0:30:29", "remaining_time": "1:01:40", "throughput": 10218.26, "total_tokens": 18695552}
{"current_steps": 19500, "total_steps": 58920, "loss": 0.0474, "lr": 1.692293673976046e-06, "epoch": 1.654786150712831, "percentage": 33.1, "elapsed_time": "0:30:29", "remaining_time": "1:01:39", "throughput": 10218.65, "total_tokens": 18700096}
{"current_steps": 19505, "total_steps": 58920, "loss": 0.1206, "lr": 1.6920798864280281e-06, "epoch": 1.6552104548540394, "percentage": 33.1, "elapsed_time": "0:30:30", "remaining_time": "1:01:38", "throughput": 10219.16, "total_tokens": 18704896}
{"current_steps": 19510, "total_steps": 58920, "loss": 0.023, "lr": 1.6918660381524995e-06, "epoch": 1.6556347589952478, "percentage": 33.11, "elapsed_time": "0:30:30", "remaining_time": "1:01:38", "throughput": 10219.53, "total_tokens": 18709440}
{"current_steps": 19515, "total_steps": 58920, "loss": 0.0036, "lr": 1.6916521291682236e-06, "epoch": 1.6560590631364562, "percentage": 33.12, "elapsed_time": "0:30:31", "remaining_time": "1:01:37", "throughput": 10220.48, "total_tokens": 18715392}
{"current_steps": 19520, "total_steps": 58920, "loss": 0.0007, "lr": 1.6914381594939704e-06, "epoch": 1.6564833672776647, "percentage": 33.13, "elapsed_time": "0:30:31", "remaining_time": "1:01:36", "throughput": 10220.79, "total_tokens": 18719808}
{"current_steps": 19525, "total_steps": 58920, "loss": 0.1346, "lr": 1.6912241291485153e-06, "epoch": 1.656907671418873, "percentage": 33.14, "elapsed_time": "0:30:31", "remaining_time": "1:01:36", "throughput": 10221.26, "total_tokens": 18724544}
{"current_steps": 19530, "total_steps": 58920, "loss": 0.0541, "lr": 1.6910100381506384e-06, "epoch": 1.6573319755600815, "percentage": 33.15, "elapsed_time": "0:30:32", "remaining_time": "1:01:35", "throughput": 10221.82, "total_tokens": 18729472}
{"current_steps": 19535, "total_steps": 58920, "loss": 0.0662, "lr": 1.6907958865191258e-06, "epoch": 1.65775627970129, "percentage": 33.16, "elapsed_time": "0:30:32", "remaining_time": "1:01:34", "throughput": 10222.48, "total_tokens": 18734720}
{"current_steps": 19540, "total_steps": 58920, "loss": 0.0309, "lr": 1.690581674272768e-06, "epoch": 1.6581805838424983, "percentage": 33.16, "elapsed_time": "0:30:33", "remaining_time": "1:01:34", "throughput": 10222.87, "total_tokens": 18739264}
{"current_steps": 19545, "total_steps": 58920, "loss": 0.0476, "lr": 1.690367401430362e-06, "epoch": 1.6586048879837068, "percentage": 33.17, "elapsed_time": "0:30:33", "remaining_time": "1:01:33", "throughput": 10223.25, "total_tokens": 18743808}
{"current_steps": 19550, "total_steps": 58920, "loss": 0.0836, "lr": 1.690153068010709e-06, "epoch": 1.6590291921249152, "percentage": 33.18, "elapsed_time": "0:30:33", "remaining_time": "1:01:32", "throughput": 10223.74, "total_tokens": 18748608}
{"current_steps": 19555, "total_steps": 58920, "loss": 0.0514, "lr": 1.689938674032616e-06, "epoch": 1.6594534962661236, "percentage": 33.19, "elapsed_time": "0:30:34", "remaining_time": "1:01:32", "throughput": 10224.1, "total_tokens": 18753152}
{"current_steps": 19560, "total_steps": 58920, "loss": 0.0227, "lr": 1.689724219514895e-06, "epoch": 1.659877800407332, "percentage": 33.2, "elapsed_time": "0:30:34", "remaining_time": "1:01:31", "throughput": 10224.7, "total_tokens": 18758272}
{"current_steps": 19565, "total_steps": 58920, "loss": 0.0011, "lr": 1.6895097044763645e-06, "epoch": 1.6603021045485404, "percentage": 33.21, "elapsed_time": "0:30:34", "remaining_time": "1:01:31", "throughput": 10225.35, "total_tokens": 18763456}
{"current_steps": 19570, "total_steps": 58920, "loss": 0.0755, "lr": 1.6892951289358469e-06, "epoch": 1.6607264086897489, "percentage": 33.21, "elapsed_time": "0:30:35", "remaining_time": "1:01:30", "throughput": 10225.78, "total_tokens": 18768128}
{"current_steps": 19575, "total_steps": 58920, "loss": 0.0018, "lr": 1.6890804929121698e-06, "epoch": 1.6611507128309573, "percentage": 33.22, "elapsed_time": "0:30:35", "remaining_time": "1:01:29", "throughput": 10226.19, "total_tokens": 18772736}
{"current_steps": 19580, "total_steps": 58920, "loss": 0.0012, "lr": 1.688865796424168e-06, "epoch": 1.6615750169721657, "percentage": 33.23, "elapsed_time": "0:30:36", "remaining_time": "1:01:29", "throughput": 10226.67, "total_tokens": 18777536}
{"current_steps": 19585, "total_steps": 58920, "loss": 0.1158, "lr": 1.6886510394906794e-06, "epoch": 1.6619993211133741, "percentage": 33.24, "elapsed_time": "0:30:36", "remaining_time": "1:01:28", "throughput": 10227.13, "total_tokens": 18782272}
{"current_steps": 19590, "total_steps": 58920, "loss": 0.0668, "lr": 1.6884362221305486e-06, "epoch": 1.6624236252545825, "percentage": 33.25, "elapsed_time": "0:30:36", "remaining_time": "1:01:27", "throughput": 10227.73, "total_tokens": 18787328}
{"current_steps": 19595, "total_steps": 58920, "loss": 0.0262, "lr": 1.6882213443626249e-06, "epoch": 1.662847929395791, "percentage": 33.26, "elapsed_time": "0:30:37", "remaining_time": "1:01:27", "throughput": 10228.02, "total_tokens": 18791680}
{"current_steps": 19600, "total_steps": 58920, "loss": 0.026, "lr": 1.6880064062057629e-06, "epoch": 1.6632722335369992, "percentage": 33.27, "elapsed_time": "0:30:37", "remaining_time": "1:01:26", "throughput": 10228.22, "total_tokens": 18795840}
{"current_steps": 19605, "total_steps": 58920, "loss": 0.0582, "lr": 1.6877914076788228e-06, "epoch": 1.6636965376782076, "percentage": 33.27, "elapsed_time": "0:30:38", "remaining_time": "1:01:25", "throughput": 10228.57, "total_tokens": 18800320}
{"current_steps": 19610, "total_steps": 58920, "loss": 0.0912, "lr": 1.68757634880067e-06, "epoch": 1.664120841819416, "percentage": 33.28, "elapsed_time": "0:30:38", "remaining_time": "1:01:25", "throughput": 10228.95, "total_tokens": 18804928}
{"current_steps": 19615, "total_steps": 58920, "loss": 0.0506, "lr": 1.687361229590175e-06, "epoch": 1.6645451459606244, "percentage": 33.29, "elapsed_time": "0:30:38", "remaining_time": "1:01:24", "throughput": 10229.24, "total_tokens": 18809280}
{"current_steps": 19620, "total_steps": 58920, "loss": 0.0149, "lr": 1.687146050066214e-06, "epoch": 1.6649694501018328, "percentage": 33.3, "elapsed_time": "0:30:39", "remaining_time": "1:01:23", "throughput": 10229.93, "total_tokens": 18814592}
{"current_steps": 19625, "total_steps": 58920, "loss": 0.0237, "lr": 1.6869308102476678e-06, "epoch": 1.6653937542430413, "percentage": 33.31, "elapsed_time": "0:30:39", "remaining_time": "1:01:23", "throughput": 10230.4, "total_tokens": 18819328}
{"current_steps": 19630, "total_steps": 58920, "loss": 0.0519, "lr": 1.6867155101534233e-06, "epoch": 1.6658180583842497, "percentage": 33.32, "elapsed_time": "0:30:39", "remaining_time": "1:01:22", "throughput": 10230.71, "total_tokens": 18823744}
{"current_steps": 19635, "total_steps": 58920, "loss": 0.1196, "lr": 1.6865001498023724e-06, "epoch": 1.666242362525458, "percentage": 33.32, "elapsed_time": "0:30:40", "remaining_time": "1:01:22", "throughput": 10231.35, "total_tokens": 18828928}
{"current_steps": 19640, "total_steps": 58920, "loss": 0.0869, "lr": 1.6862847292134115e-06, "epoch": 1.6666666666666665, "percentage": 33.33, "elapsed_time": "0:30:40", "remaining_time": "1:01:21", "throughput": 10232.1, "total_tokens": 18834368}
{"current_steps": 19645, "total_steps": 58920, "loss": 0.1132, "lr": 1.6860692484054436e-06, "epoch": 1.667090970807875, "percentage": 33.34, "elapsed_time": "0:30:41", "remaining_time": "1:01:20", "throughput": 10232.85, "total_tokens": 18839808}
{"current_steps": 19650, "total_steps": 58920, "loss": 0.0609, "lr": 1.6858537073973761e-06, "epoch": 1.6675152749490834, "percentage": 33.35, "elapsed_time": "0:30:41", "remaining_time": "1:01:20", "throughput": 10233.21, "total_tokens": 18844288}
{"current_steps": 19655, "total_steps": 58920, "loss": 0.0987, "lr": 1.685638106208122e-06, "epoch": 1.6679395790902918, "percentage": 33.36, "elapsed_time": "0:30:41", "remaining_time": "1:01:19", "throughput": 10233.68, "total_tokens": 18849024}
{"current_steps": 19660, "total_steps": 58920, "loss": 0.0543, "lr": 1.6854224448565999e-06, "epoch": 1.6683638832315002, "percentage": 33.37, "elapsed_time": "0:30:42", "remaining_time": "1:01:18", "throughput": 10234.02, "total_tokens": 18853504}
{"current_steps": 19665, "total_steps": 58920, "loss": 0.047, "lr": 1.6852067233617332e-06, "epoch": 1.6687881873727086, "percentage": 33.38, "elapsed_time": "0:30:42", "remaining_time": "1:01:18", "throughput": 10234.43, "total_tokens": 18858112}
{"current_steps": 19670, "total_steps": 58920, "loss": 0.026, "lr": 1.6849909417424498e-06, "epoch": 1.669212491513917, "percentage": 33.38, "elapsed_time": "0:30:43", "remaining_time": "1:01:17", "throughput": 10235.15, "total_tokens": 18863488}
{"current_steps": 19675, "total_steps": 58920, "loss": 0.0068, "lr": 1.6847751000176848e-06, "epoch": 1.6696367956551255, "percentage": 33.39, "elapsed_time": "0:30:43", "remaining_time": "1:01:16", "throughput": 10235.62, "total_tokens": 18868288}
{"current_steps": 19680, "total_steps": 58920, "loss": 0.085, "lr": 1.684559198206377e-06, "epoch": 1.6700610997963339, "percentage": 33.4, "elapsed_time": "0:30:43", "remaining_time": "1:01:16", "throughput": 10236.24, "total_tokens": 18873472}
{"current_steps": 19685, "total_steps": 58920, "loss": 0.0758, "lr": 1.684343236327471e-06, "epoch": 1.6704854039375423, "percentage": 33.41, "elapsed_time": "0:30:44", "remaining_time": "1:01:15", "throughput": 10236.65, "total_tokens": 18878080}
{"current_steps": 19690, "total_steps": 58920, "loss": 0.0259, "lr": 1.684127214399917e-06, "epoch": 1.6709097080787507, "percentage": 33.42, "elapsed_time": "0:30:44", "remaining_time": "1:01:15", "throughput": 10237.25, "total_tokens": 18883200}
{"current_steps": 19695, "total_steps": 58920, "loss": 0.0021, "lr": 1.6839111324426698e-06, "epoch": 1.6713340122199591, "percentage": 33.43, "elapsed_time": "0:30:44", "remaining_time": "1:01:14", "throughput": 10237.62, "total_tokens": 18887744}
{"current_steps": 19700, "total_steps": 58920, "loss": 0.0229, "lr": 1.6836949904746903e-06, "epoch": 1.6717583163611676, "percentage": 33.44, "elapsed_time": "0:30:45", "remaining_time": "1:01:13", "throughput": 10238.07, "total_tokens": 18892480}
{"current_steps": 19705, "total_steps": 58920, "loss": 0.034, "lr": 1.6834787885149435e-06, "epoch": 1.672182620502376, "percentage": 33.44, "elapsed_time": "0:30:45", "remaining_time": "1:01:13", "throughput": 10238.63, "total_tokens": 18897472}
{"current_steps": 19710, "total_steps": 58920, "loss": 0.0564, "lr": 1.6832625265824013e-06, "epoch": 1.6726069246435844, "percentage": 33.45, "elapsed_time": "0:30:46", "remaining_time": "1:01:12", "throughput": 10239.03, "total_tokens": 18902080}
{"current_steps": 19715, "total_steps": 58920, "loss": 0.016, "lr": 1.6830462046960387e-06, "epoch": 1.6730312287847928, "percentage": 33.46, "elapsed_time": "0:30:46", "remaining_time": "1:01:11", "throughput": 10239.47, "total_tokens": 18906752}
{"current_steps": 19720, "total_steps": 58920, "loss": 0.034, "lr": 1.6828298228748378e-06, "epoch": 1.6734555329260012, "percentage": 33.47, "elapsed_time": "0:30:46", "remaining_time": "1:01:11", "throughput": 10239.74, "total_tokens": 18911040}
{"current_steps": 19725, "total_steps": 58920, "loss": 0.061, "lr": 1.6826133811377855e-06, "epoch": 1.6738798370672097, "percentage": 33.48, "elapsed_time": "0:30:47", "remaining_time": "1:01:10", "throughput": 10240.1, "total_tokens": 18915584}
{"current_steps": 19730, "total_steps": 58920, "loss": 0.0557, "lr": 1.6823968795038736e-06, "epoch": 1.674304141208418, "percentage": 33.49, "elapsed_time": "0:30:47", "remaining_time": "1:01:09", "throughput": 10240.74, "total_tokens": 18920768}
{"current_steps": 19735, "total_steps": 58920, "loss": 0.0855, "lr": 1.6821803179920992e-06, "epoch": 1.6747284453496265, "percentage": 33.49, "elapsed_time": "0:30:47", "remaining_time": "1:01:09", "throughput": 10241.14, "total_tokens": 18925376}
{"current_steps": 19740, "total_steps": 58920, "loss": 0.1031, "lr": 1.681963696621465e-06, "epoch": 1.675152749490835, "percentage": 33.5, "elapsed_time": "0:30:48", "remaining_time": "1:01:08", "throughput": 10241.57, "total_tokens": 18930048}
{"current_steps": 19745, "total_steps": 58920, "loss": 0.0214, "lr": 1.6817470154109784e-06, "epoch": 1.6755770536320433, "percentage": 33.51, "elapsed_time": "0:30:48", "remaining_time": "1:01:07", "throughput": 10241.99, "total_tokens": 18934720}
{"current_steps": 19750, "total_steps": 58920, "loss": 0.0026, "lr": 1.681530274379653e-06, "epoch": 1.6760013577732518, "percentage": 33.52, "elapsed_time": "0:30:49", "remaining_time": "1:01:07", "throughput": 10241.0, "total_tokens": 18939456}
{"current_steps": 19755, "total_steps": 58920, "loss": 0.0705, "lr": 1.6813134735465063e-06, "epoch": 1.6764256619144602, "percentage": 33.53, "elapsed_time": "0:30:49", "remaining_time": "1:01:07", "throughput": 10241.25, "total_tokens": 18943744}
{"current_steps": 19760, "total_steps": 58920, "loss": 0.0104, "lr": 1.6810966129305623e-06, "epoch": 1.6768499660556686, "percentage": 33.54, "elapsed_time": "0:30:50", "remaining_time": "1:01:06", "throughput": 10241.94, "total_tokens": 18949056}
{"current_steps": 19765, "total_steps": 58920, "loss": 0.0703, "lr": 1.68087969255085e-06, "epoch": 1.677274270196877, "percentage": 33.55, "elapsed_time": "0:30:50", "remaining_time": "1:01:05", "throughput": 10242.47, "total_tokens": 18953920}
{"current_steps": 19770, "total_steps": 58920, "loss": 0.0972, "lr": 1.6806627124264026e-06, "epoch": 1.6776985743380854, "percentage": 33.55, "elapsed_time": "0:30:50", "remaining_time": "1:01:05", "throughput": 10242.97, "total_tokens": 18958848}
{"current_steps": 19775, "total_steps": 58920, "loss": 0.0262, "lr": 1.6804456725762597e-06, "epoch": 1.6781228784792939, "percentage": 33.56, "elapsed_time": "0:30:51", "remaining_time": "1:01:04", "throughput": 10243.7, "total_tokens": 18964288}
{"current_steps": 19780, "total_steps": 58920, "loss": 0.0575, "lr": 1.6802285730194657e-06, "epoch": 1.6785471826205023, "percentage": 33.57, "elapsed_time": "0:30:51", "remaining_time": "1:01:04", "throughput": 10243.95, "total_tokens": 18968576}
{"current_steps": 19785, "total_steps": 58920, "loss": 0.0045, "lr": 1.6800114137750705e-06, "epoch": 1.6789714867617107, "percentage": 33.58, "elapsed_time": "0:30:52", "remaining_time": "1:01:03", "throughput": 10244.32, "total_tokens": 18973120}
{"current_steps": 19790, "total_steps": 58920, "loss": 0.0032, "lr": 1.6797941948621289e-06, "epoch": 1.6793957909029191, "percentage": 33.59, "elapsed_time": "0:30:52", "remaining_time": "1:01:02", "throughput": 10244.61, "total_tokens": 18977472}
{"current_steps": 19795, "total_steps": 58920, "loss": 0.0013, "lr": 1.679576916299701e-06, "epoch": 1.6798200950441275, "percentage": 33.6, "elapsed_time": "0:30:52", "remaining_time": "1:01:02", "throughput": 10245.09, "total_tokens": 18982272}
{"current_steps": 19800, "total_steps": 58920, "loss": 0.0141, "lr": 1.6793595781068524e-06, "epoch": 1.680244399185336, "percentage": 33.6, "elapsed_time": "0:30:53", "remaining_time": "1:01:01", "throughput": 10245.51, "total_tokens": 18986944}
{"current_steps": 19805, "total_steps": 58920, "loss": 0.1253, "lr": 1.6791421803026538e-06, "epoch": 1.6806687033265444, "percentage": 33.61, "elapsed_time": "0:30:53", "remaining_time": "1:01:00", "throughput": 10245.82, "total_tokens": 18991360}
{"current_steps": 19810, "total_steps": 58920, "loss": 0.0399, "lr": 1.6789247229061804e-06, "epoch": 1.6810930074677528, "percentage": 33.62, "elapsed_time": "0:30:53", "remaining_time": "1:01:00", "throughput": 10246.18, "total_tokens": 18995904}
{"current_steps": 19815, "total_steps": 58920, "loss": 0.0385, "lr": 1.6787072059365145e-06, "epoch": 1.6815173116089612, "percentage": 33.63, "elapsed_time": "0:30:54", "remaining_time": "1:00:59", "throughput": 10246.46, "total_tokens": 19000256}
{"current_steps": 19820, "total_steps": 58920, "loss": 0.0297, "lr": 1.6784896294127412e-06, "epoch": 1.6819416157501696, "percentage": 33.64, "elapsed_time": "0:30:54", "remaining_time": "1:00:58", "throughput": 10247.05, "total_tokens": 19005376}
{"current_steps": 19825, "total_steps": 58920, "loss": 0.0522, "lr": 1.6782719933539529e-06, "epoch": 1.682365919891378, "percentage": 33.65, "elapsed_time": "0:30:55", "remaining_time": "1:00:58", "throughput": 10247.72, "total_tokens": 19010624}
{"current_steps": 19830, "total_steps": 58920, "loss": 0.032, "lr": 1.678054297779246e-06, "epoch": 1.6827902240325865, "percentage": 33.66, "elapsed_time": "0:30:55", "remaining_time": "1:00:57", "throughput": 10248.02, "total_tokens": 19014976}
{"current_steps": 19835, "total_steps": 58920, "loss": 0.0304, "lr": 1.6778365427077223e-06, "epoch": 1.683214528173795, "percentage": 33.66, "elapsed_time": "0:30:55", "remaining_time": "1:00:56", "throughput": 10248.5, "total_tokens": 19019776}
{"current_steps": 19840, "total_steps": 58920, "loss": 0.027, "lr": 1.6776187281584896e-06, "epoch": 1.6836388323150033, "percentage": 33.67, "elapsed_time": "0:30:56", "remaining_time": "1:00:56", "throughput": 10249.15, "total_tokens": 19024960}
{"current_steps": 19845, "total_steps": 58920, "loss": 0.1502, "lr": 1.67740085415066e-06, "epoch": 1.6840631364562118, "percentage": 33.68, "elapsed_time": "0:30:56", "remaining_time": "1:00:55", "throughput": 10250.12, "total_tokens": 19031040}
{"current_steps": 19850, "total_steps": 58920, "loss": 0.0818, "lr": 1.6771829207033513e-06, "epoch": 1.6844874405974202, "percentage": 33.69, "elapsed_time": "0:30:57", "remaining_time": "1:00:55", "throughput": 10250.69, "total_tokens": 19036096}
{"current_steps": 19855, "total_steps": 58920, "loss": 0.0695, "lr": 1.676964927835686e-06, "epoch": 1.6849117447386286, "percentage": 33.7, "elapsed_time": "0:30:57", "remaining_time": "1:00:54", "throughput": 10251.04, "total_tokens": 19040576}
{"current_steps": 19860, "total_steps": 58920, "loss": 0.0255, "lr": 1.6767468755667926e-06, "epoch": 1.685336048879837, "percentage": 33.71, "elapsed_time": "0:30:57", "remaining_time": "1:00:53", "throughput": 10251.59, "total_tokens": 19045568}
{"current_steps": 19865, "total_steps": 58920, "loss": 0.1069, "lr": 1.6765287639158042e-06, "epoch": 1.6857603530210454, "percentage": 33.72, "elapsed_time": "0:30:58", "remaining_time": "1:00:53", "throughput": 10252.23, "total_tokens": 19050816}
{"current_steps": 19870, "total_steps": 58920, "loss": 0.013, "lr": 1.6763105929018595e-06, "epoch": 1.6861846571622539, "percentage": 33.72, "elapsed_time": "0:30:58", "remaining_time": "1:00:52", "throughput": 10252.73, "total_tokens": 19055616}
{"current_steps": 19875, "total_steps": 58920, "loss": 0.0681, "lr": 1.676092362544102e-06, "epoch": 1.6866089613034623, "percentage": 33.73, "elapsed_time": "0:30:58", "remaining_time": "1:00:51", "throughput": 10253.1, "total_tokens": 19060160}
{"current_steps": 19880, "total_steps": 58920, "loss": 0.0367, "lr": 1.6758740728616806e-06, "epoch": 1.6870332654446707, "percentage": 33.74, "elapsed_time": "0:30:59", "remaining_time": "1:00:51", "throughput": 10253.52, "total_tokens": 19064832}
{"current_steps": 19885, "total_steps": 58920, "loss": 0.0399, "lr": 1.6756557238737498e-06, "epoch": 1.6874575695858791, "percentage": 33.75, "elapsed_time": "0:30:59", "remaining_time": "1:00:50", "throughput": 10254.13, "total_tokens": 19070016}
{"current_steps": 19890, "total_steps": 58920, "loss": 0.0273, "lr": 1.6754373155994683e-06, "epoch": 1.6878818737270875, "percentage": 33.76, "elapsed_time": "0:31:00", "remaining_time": "1:00:50", "throughput": 10254.51, "total_tokens": 19074560}
{"current_steps": 19895, "total_steps": 58920, "loss": 0.0554, "lr": 1.6752188480580013e-06, "epoch": 1.688306177868296, "percentage": 33.77, "elapsed_time": "0:31:00", "remaining_time": "1:00:49", "throughput": 10254.91, "total_tokens": 19079296}
{"current_steps": 19900, "total_steps": 58920, "loss": 0.0089, "lr": 1.6750003212685182e-06, "epoch": 1.6887304820095044, "percentage": 33.77, "elapsed_time": "0:31:00", "remaining_time": "1:00:48", "throughput": 10255.45, "total_tokens": 19084288}
{"current_steps": 19905, "total_steps": 58920, "loss": 0.1147, "lr": 1.6747817352501938e-06, "epoch": 1.6891547861507128, "percentage": 33.78, "elapsed_time": "0:31:01", "remaining_time": "1:00:48", "throughput": 10255.78, "total_tokens": 19088768}
{"current_steps": 19910, "total_steps": 58920, "loss": 0.0135, "lr": 1.6745630900222087e-06, "epoch": 1.6895790902919212, "percentage": 33.79, "elapsed_time": "0:31:01", "remaining_time": "1:00:47", "throughput": 10256.27, "total_tokens": 19093568}
{"current_steps": 19915, "total_steps": 58920, "loss": 0.0179, "lr": 1.674344385603748e-06, "epoch": 1.6900033944331296, "percentage": 33.8, "elapsed_time": "0:31:02", "remaining_time": "1:00:46", "throughput": 10256.74, "total_tokens": 19098368}
{"current_steps": 19920, "total_steps": 58920, "loss": 0.0741, "lr": 1.6741256220140018e-06, "epoch": 1.690427698574338, "percentage": 33.81, "elapsed_time": "0:31:02", "remaining_time": "1:00:46", "throughput": 10257.12, "total_tokens": 19102912}
{"current_steps": 19925, "total_steps": 58920, "loss": 0.0209, "lr": 1.6739067992721665e-06, "epoch": 1.6908520027155465, "percentage": 33.82, "elapsed_time": "0:31:02", "remaining_time": "1:00:45", "throughput": 10257.59, "total_tokens": 19107712}
{"current_steps": 19930, "total_steps": 58920, "loss": 0.0369, "lr": 1.6736879173974425e-06, "epoch": 1.691276306856755, "percentage": 33.83, "elapsed_time": "0:31:03", "remaining_time": "1:00:45", "throughput": 10258.14, "total_tokens": 19112640}
{"current_steps": 19935, "total_steps": 58920, "loss": 0.0713, "lr": 1.6734689764090363e-06, "epoch": 1.6917006109979633, "percentage": 33.83, "elapsed_time": "0:31:03", "remaining_time": "1:00:44", "throughput": 10258.54, "total_tokens": 19117248}
{"current_steps": 19940, "total_steps": 58920, "loss": 0.0385, "lr": 1.6732499763261587e-06, "epoch": 1.6921249151391717, "percentage": 33.84, "elapsed_time": "0:31:03", "remaining_time": "1:00:43", "throughput": 10258.93, "total_tokens": 19121856}
{"current_steps": 19945, "total_steps": 58920, "loss": 0.055, "lr": 1.6730309171680265e-06, "epoch": 1.6925492192803802, "percentage": 33.85, "elapsed_time": "0:31:04", "remaining_time": "1:00:43", "throughput": 10259.28, "total_tokens": 19126336}
{"current_steps": 19950, "total_steps": 58920, "loss": 0.001, "lr": 1.6728117989538615e-06, "epoch": 1.6929735234215886, "percentage": 33.86, "elapsed_time": "0:31:04", "remaining_time": "1:00:42", "throughput": 10259.74, "total_tokens": 19131136}
{"current_steps": 19955, "total_steps": 58920, "loss": 0.0728, "lr": 1.6725926217028903e-06, "epoch": 1.693397827562797, "percentage": 33.87, "elapsed_time": "0:31:05", "remaining_time": "1:00:41", "throughput": 10260.19, "total_tokens": 19135872}
{"current_steps": 19960, "total_steps": 58920, "loss": 0.055, "lr": 1.6723733854343447e-06, "epoch": 1.6938221317040054, "percentage": 33.88, "elapsed_time": "0:31:05", "remaining_time": "1:00:41", "throughput": 10260.87, "total_tokens": 19141184}
{"current_steps": 19965, "total_steps": 58920, "loss": 0.0248, "lr": 1.6721540901674622e-06, "epoch": 1.6942464358452138, "percentage": 33.88, "elapsed_time": "0:31:05", "remaining_time": "1:00:40", "throughput": 10261.73, "total_tokens": 19146944}
{"current_steps": 19970, "total_steps": 58920, "loss": 0.0515, "lr": 1.6719347359214852e-06, "epoch": 1.6946707399864223, "percentage": 33.89, "elapsed_time": "0:31:06", "remaining_time": "1:00:39", "throughput": 10262.2, "total_tokens": 19151744}
{"current_steps": 19975, "total_steps": 58920, "loss": 0.0262, "lr": 1.671715322715661e-06, "epoch": 1.6950950441276307, "percentage": 33.9, "elapsed_time": "0:31:06", "remaining_time": "1:00:39", "throughput": 10262.8, "total_tokens": 19156864}
{"current_steps": 19980, "total_steps": 58920, "loss": 0.03, "lr": 1.6714958505692428e-06, "epoch": 1.695519348268839, "percentage": 33.91, "elapsed_time": "0:31:07", "remaining_time": "1:00:38", "throughput": 10263.15, "total_tokens": 19161408}
{"current_steps": 19985, "total_steps": 58920, "loss": 0.0469, "lr": 1.6712763195014877e-06, "epoch": 1.6959436524100475, "percentage": 33.92, "elapsed_time": "0:31:07", "remaining_time": "1:00:38", "throughput": 10263.46, "total_tokens": 19165824}
{"current_steps": 19990, "total_steps": 58920, "loss": 0.0582, "lr": 1.6710567295316593e-06, "epoch": 1.696367956551256, "percentage": 33.93, "elapsed_time": "0:31:07", "remaining_time": "1:00:37", "throughput": 10263.89, "total_tokens": 19170560}
{"current_steps": 19995, "total_steps": 58920, "loss": 0.0535, "lr": 1.6708370806790256e-06, "epoch": 1.6967922606924644, "percentage": 33.94, "elapsed_time": "0:31:08", "remaining_time": "1:00:36", "throughput": 10264.46, "total_tokens": 19175616}
{"current_steps": 20000, "total_steps": 58920, "loss": 0.0008, "lr": 1.6706173729628605e-06, "epoch": 1.6972165648336728, "percentage": 33.94, "elapsed_time": "0:31:08", "remaining_time": "1:00:36", "throughput": 10264.99, "total_tokens": 19180608}
{"current_steps": 20005, "total_steps": 58920, "loss": 0.0525, "lr": 1.6703976064024418e-06, "epoch": 1.6976408689748812, "percentage": 33.95, "elapsed_time": "0:31:08", "remaining_time": "1:00:35", "throughput": 10265.59, "total_tokens": 19185728}
{"current_steps": 20010, "total_steps": 58920, "loss": 0.0745, "lr": 1.670177781017054e-06, "epoch": 1.6980651731160896, "percentage": 33.96, "elapsed_time": "0:31:09", "remaining_time": "1:00:34", "throughput": 10266.1, "total_tokens": 19190656}
{"current_steps": 20015, "total_steps": 58920, "loss": 0.0298, "lr": 1.6699578968259855e-06, "epoch": 1.698489477257298, "percentage": 33.97, "elapsed_time": "0:31:09", "remaining_time": "1:00:34", "throughput": 10266.88, "total_tokens": 19196224}
{"current_steps": 20020, "total_steps": 58920, "loss": 0.0198, "lr": 1.6697379538485303e-06, "epoch": 1.6989137813985065, "percentage": 33.98, "elapsed_time": "0:31:10", "remaining_time": "1:00:33", "throughput": 10267.43, "total_tokens": 19201280}
{"current_steps": 20025, "total_steps": 58920, "loss": 0.0406, "lr": 1.6695179521039874e-06, "epoch": 1.6993380855397149, "percentage": 33.99, "elapsed_time": "0:31:10", "remaining_time": "1:00:33", "throughput": 10267.84, "total_tokens": 19205952}
{"current_steps": 20030, "total_steps": 58920, "loss": 0.0014, "lr": 1.669297891611662e-06, "epoch": 1.6997623896809233, "percentage": 34.0, "elapsed_time": "0:31:10", "remaining_time": "1:00:32", "throughput": 10268.32, "total_tokens": 19210752}
{"current_steps": 20035, "total_steps": 58920, "loss": 0.0312, "lr": 1.6690777723908628e-06, "epoch": 1.7001866938221317, "percentage": 34.0, "elapsed_time": "0:31:11", "remaining_time": "1:00:31", "throughput": 10268.51, "total_tokens": 19214912}
{"current_steps": 20040, "total_steps": 58920, "loss": 0.0439, "lr": 1.6688575944609049e-06, "epoch": 1.7006109979633401, "percentage": 34.01, "elapsed_time": "0:31:11", "remaining_time": "1:00:31", "throughput": 10268.88, "total_tokens": 19219456}
{"current_steps": 20045, "total_steps": 58920, "loss": 0.0567, "lr": 1.6686373578411083e-06, "epoch": 1.7010353021045486, "percentage": 34.02, "elapsed_time": "0:31:12", "remaining_time": "1:00:30", "throughput": 10269.23, "total_tokens": 19224000}
{"current_steps": 20050, "total_steps": 58920, "loss": 0.045, "lr": 1.6684170625507972e-06, "epoch": 1.701459606245757, "percentage": 34.03, "elapsed_time": "0:31:12", "remaining_time": "1:00:29", "throughput": 10269.91, "total_tokens": 19229440}
{"current_steps": 20055, "total_steps": 58920, "loss": 0.0204, "lr": 1.6681967086093022e-06, "epoch": 1.7018839103869654, "percentage": 34.04, "elapsed_time": "0:31:12", "remaining_time": "1:00:29", "throughput": 10270.28, "total_tokens": 19234048}
{"current_steps": 20060, "total_steps": 58920, "loss": 0.099, "lr": 1.6679762960359586e-06, "epoch": 1.7023082145281738, "percentage": 34.05, "elapsed_time": "0:31:13", "remaining_time": "1:00:28", "throughput": 10270.8, "total_tokens": 19238976}
{"current_steps": 20065, "total_steps": 58920, "loss": 0.0322, "lr": 1.6677558248501068e-06, "epoch": 1.7027325186693822, "percentage": 34.05, "elapsed_time": "0:31:13", "remaining_time": "1:00:28", "throughput": 10271.13, "total_tokens": 19243520}
{"current_steps": 20070, "total_steps": 58920, "loss": 0.013, "lr": 1.6675352950710923e-06, "epoch": 1.7031568228105907, "percentage": 34.06, "elapsed_time": "0:31:13", "remaining_time": "1:00:27", "throughput": 10271.84, "total_tokens": 19248960}
{"current_steps": 20075, "total_steps": 58920, "loss": 0.1641, "lr": 1.6673147067182658e-06, "epoch": 1.703581126951799, "percentage": 34.07, "elapsed_time": "0:31:14", "remaining_time": "1:00:26", "throughput": 10272.42, "total_tokens": 19254080}
{"current_steps": 20080, "total_steps": 58920, "loss": 0.0333, "lr": 1.6670940598109828e-06, "epoch": 1.7040054310930075, "percentage": 34.08, "elapsed_time": "0:31:14", "remaining_time": "1:00:26", "throughput": 10272.83, "total_tokens": 19258752}
{"current_steps": 20085, "total_steps": 58920, "loss": 0.0985, "lr": 1.6668733543686048e-06, "epoch": 1.704429735234216, "percentage": 34.09, "elapsed_time": "0:31:15", "remaining_time": "1:00:25", "throughput": 10273.33, "total_tokens": 19263680}
{"current_steps": 20090, "total_steps": 58920, "loss": 0.0325, "lr": 1.6666525904104978e-06, "epoch": 1.7048540393754243, "percentage": 34.1, "elapsed_time": "0:31:15", "remaining_time": "1:00:24", "throughput": 10273.56, "total_tokens": 19267904}
{"current_steps": 20095, "total_steps": 58920, "loss": 0.0013, "lr": 1.6664317679560331e-06, "epoch": 1.7052783435166328, "percentage": 34.11, "elapsed_time": "0:31:15", "remaining_time": "1:00:24", "throughput": 10273.86, "total_tokens": 19272384}
{"current_steps": 20100, "total_steps": 58920, "loss": 0.0187, "lr": 1.6662108870245866e-06, "epoch": 1.7057026476578412, "percentage": 34.11, "elapsed_time": "0:31:16", "remaining_time": "1:00:23", "throughput": 10274.44, "total_tokens": 19277504}
{"current_steps": 20105, "total_steps": 58920, "loss": 0.0288, "lr": 1.6659899476355401e-06, "epoch": 1.7061269517990496, "percentage": 34.12, "elapsed_time": "0:31:16", "remaining_time": "1:00:23", "throughput": 10274.81, "total_tokens": 19282048}
{"current_steps": 20110, "total_steps": 58920, "loss": 0.0655, "lr": 1.6657689498082803e-06, "epoch": 1.706551255940258, "percentage": 34.13, "elapsed_time": "0:31:17", "remaining_time": "1:00:22", "throughput": 10275.33, "total_tokens": 19287040}
{"current_steps": 20115, "total_steps": 58920, "loss": 0.0848, "lr": 1.665547893562199e-06, "epoch": 1.7069755600814664, "percentage": 34.14, "elapsed_time": "0:31:17", "remaining_time": "1:00:21", "throughput": 10275.79, "total_tokens": 19291776}
{"current_steps": 20120, "total_steps": 58920, "loss": 0.0444, "lr": 1.6653267789166926e-06, "epoch": 1.7073998642226749, "percentage": 34.15, "elapsed_time": "0:31:17", "remaining_time": "1:00:21", "throughput": 10276.11, "total_tokens": 19296256}
{"current_steps": 20125, "total_steps": 58920, "loss": 0.0235, "lr": 1.6651056058911638e-06, "epoch": 1.7078241683638833, "percentage": 34.16, "elapsed_time": "0:31:18", "remaining_time": "1:00:20", "throughput": 10276.46, "total_tokens": 19300736}
{"current_steps": 20130, "total_steps": 58920, "loss": 0.008, "lr": 1.6648843745050197e-06, "epoch": 1.7082484725050917, "percentage": 34.16, "elapsed_time": "0:31:18", "remaining_time": "1:00:19", "throughput": 10277.4, "total_tokens": 19306688}
{"current_steps": 20135, "total_steps": 58920, "loss": 0.0567, "lr": 1.6646630847776722e-06, "epoch": 1.7086727766463001, "percentage": 34.17, "elapsed_time": "0:31:18", "remaining_time": "1:00:19", "throughput": 10277.84, "total_tokens": 19311424}
{"current_steps": 20140, "total_steps": 58920, "loss": 0.0023, "lr": 1.6644417367285386e-06, "epoch": 1.7090970807875085, "percentage": 34.18, "elapsed_time": "0:31:19", "remaining_time": "1:00:18", "throughput": 10278.31, "total_tokens": 19316288}
{"current_steps": 20145, "total_steps": 58920, "loss": 0.0646, "lr": 1.6642203303770414e-06, "epoch": 1.709521384928717, "percentage": 34.19, "elapsed_time": "0:31:19", "remaining_time": "1:00:18", "throughput": 10278.79, "total_tokens": 19321088}
{"current_steps": 20150, "total_steps": 58920, "loss": 0.0252, "lr": 1.6639988657426085e-06, "epoch": 1.7099456890699254, "percentage": 34.2, "elapsed_time": "0:31:20", "remaining_time": "1:00:17", "throughput": 10278.97, "total_tokens": 19325184}
{"current_steps": 20155, "total_steps": 58920, "loss": 0.076, "lr": 1.6637773428446727e-06, "epoch": 1.7103699932111338, "percentage": 34.21, "elapsed_time": "0:31:20", "remaining_time": "1:00:16", "throughput": 10279.34, "total_tokens": 19329792}
{"current_steps": 20160, "total_steps": 58920, "loss": 0.0799, "lr": 1.6635557617026712e-06, "epoch": 1.7107942973523422, "percentage": 34.22, "elapsed_time": "0:31:20", "remaining_time": "1:00:16", "throughput": 10279.74, "total_tokens": 19334464}
{"current_steps": 20165, "total_steps": 58920, "loss": 0.0367, "lr": 1.6633341223360478e-06, "epoch": 1.7112186014935507, "percentage": 34.22, "elapsed_time": "0:31:21", "remaining_time": "1:00:15", "throughput": 10280.19, "total_tokens": 19339200}
{"current_steps": 20170, "total_steps": 58920, "loss": 0.027, "lr": 1.6631124247642498e-06, "epoch": 1.711642905634759, "percentage": 34.23, "elapsed_time": "0:31:21", "remaining_time": "1:00:14", "throughput": 10280.93, "total_tokens": 19344704}
{"current_steps": 20175, "total_steps": 58920, "loss": 0.0013, "lr": 1.662890669006731e-06, "epoch": 1.7120672097759675, "percentage": 34.24, "elapsed_time": "0:31:21", "remaining_time": "1:00:14", "throughput": 10281.33, "total_tokens": 19349376}
{"current_steps": 20180, "total_steps": 58920, "loss": 0.0318, "lr": 1.6626688550829493e-06, "epoch": 1.712491513917176, "percentage": 34.25, "elapsed_time": "0:31:22", "remaining_time": "1:00:13", "throughput": 10281.54, "total_tokens": 19353536}
{"current_steps": 20185, "total_steps": 58920, "loss": 0.1248, "lr": 1.662446983012368e-06, "epoch": 1.7129158180583843, "percentage": 34.26, "elapsed_time": "0:31:22", "remaining_time": "1:00:12", "throughput": 10282.15, "total_tokens": 19358720}
{"current_steps": 20190, "total_steps": 58920, "loss": 0.0355, "lr": 1.6622250528144556e-06, "epoch": 1.7133401221995928, "percentage": 34.27, "elapsed_time": "0:31:23", "remaining_time": "1:00:12", "throughput": 10282.8, "total_tokens": 19363968}
{"current_steps": 20195, "total_steps": 58920, "loss": 0.0581, "lr": 1.6620030645086857e-06, "epoch": 1.7137644263408012, "percentage": 34.28, "elapsed_time": "0:31:23", "remaining_time": "1:00:11", "throughput": 10283.2, "total_tokens": 19368640}
{"current_steps": 20200, "total_steps": 58920, "loss": 0.0164, "lr": 1.6617810181145374e-06, "epoch": 1.7141887304820096, "percentage": 34.28, "elapsed_time": "0:31:23", "remaining_time": "1:00:11", "throughput": 10283.63, "total_tokens": 19373376}
{"current_steps": 20205, "total_steps": 58920, "loss": 0.0446, "lr": 1.6615589136514937e-06, "epoch": 1.714613034623218, "percentage": 34.29, "elapsed_time": "0:31:24", "remaining_time": "1:00:10", "throughput": 10284.07, "total_tokens": 19378176}
{"current_steps": 20210, "total_steps": 58920, "loss": 0.0436, "lr": 1.6613367511390442e-06, "epoch": 1.7150373387644264, "percentage": 34.3, "elapsed_time": "0:31:24", "remaining_time": "1:00:09", "throughput": 10284.59, "total_tokens": 19383104}
{"current_steps": 20215, "total_steps": 58920, "loss": 0.0975, "lr": 1.6611145305966825e-06, "epoch": 1.7154616429056349, "percentage": 34.31, "elapsed_time": "0:31:25", "remaining_time": "1:00:09", "throughput": 10285.18, "total_tokens": 19388224}
{"current_steps": 20220, "total_steps": 58920, "loss": 0.0668, "lr": 1.6608922520439078e-06, "epoch": 1.7158859470468433, "percentage": 34.32, "elapsed_time": "0:31:25", "remaining_time": "1:00:08", "throughput": 10285.68, "total_tokens": 19393088}
{"current_steps": 20225, "total_steps": 58920, "loss": 0.0594, "lr": 1.6606699155002238e-06, "epoch": 1.7163102511880517, "percentage": 34.33, "elapsed_time": "0:31:25", "remaining_time": "1:00:08", "throughput": 10286.62, "total_tokens": 19399104}
{"current_steps": 20230, "total_steps": 58920, "loss": 0.0239, "lr": 1.66044752098514e-06, "epoch": 1.7167345553292601, "percentage": 34.33, "elapsed_time": "0:31:26", "remaining_time": "1:00:07", "throughput": 10287.04, "total_tokens": 19403840}
{"current_steps": 20235, "total_steps": 58920, "loss": 0.0015, "lr": 1.6602250685181712e-06, "epoch": 1.7171588594704685, "percentage": 34.34, "elapsed_time": "0:31:26", "remaining_time": "1:00:06", "throughput": 10287.71, "total_tokens": 19409152}
{"current_steps": 20240, "total_steps": 58920, "loss": 0.0285, "lr": 1.660002558118836e-06, "epoch": 1.717583163611677, "percentage": 34.35, "elapsed_time": "0:31:27", "remaining_time": "1:00:06", "throughput": 10288.09, "total_tokens": 19413760}
{"current_steps": 20245, "total_steps": 58920, "loss": 0.0031, "lr": 1.6597799898066597e-06, "epoch": 1.7180074677528854, "percentage": 34.36, "elapsed_time": "0:31:27", "remaining_time": "1:00:05", "throughput": 10288.74, "total_tokens": 19419072}
{"current_steps": 20250, "total_steps": 58920, "loss": 0.0232, "lr": 1.6595573636011708e-06, "epoch": 1.7184317718940938, "percentage": 34.37, "elapsed_time": "0:31:27", "remaining_time": "1:00:04", "throughput": 10289.3, "total_tokens": 19424128}
{"current_steps": 20255, "total_steps": 58920, "loss": 0.0694, "lr": 1.6593346795219047e-06, "epoch": 1.7188560760353022, "percentage": 34.38, "elapsed_time": "0:31:28", "remaining_time": "1:00:04", "throughput": 10289.67, "total_tokens": 19428736}
{"current_steps": 20260, "total_steps": 58920, "loss": 0.0552, "lr": 1.6591119375884013e-06, "epoch": 1.7192803801765106, "percentage": 34.39, "elapsed_time": "0:31:28", "remaining_time": "1:00:03", "throughput": 10290.05, "total_tokens": 19433344}
{"current_steps": 20265, "total_steps": 58920, "loss": 0.1343, "lr": 1.6588891378202053e-06, "epoch": 1.719704684317719, "percentage": 34.39, "elapsed_time": "0:31:28", "remaining_time": "1:00:03", "throughput": 10290.53, "total_tokens": 19438208}
{"current_steps": 20270, "total_steps": 58920, "loss": 0.0682, "lr": 1.6586662802368657e-06, "epoch": 1.7201289884589275, "percentage": 34.4, "elapsed_time": "0:31:29", "remaining_time": "1:00:02", "throughput": 10290.87, "total_tokens": 19442688}
{"current_steps": 20275, "total_steps": 58920, "loss": 0.0024, "lr": 1.6584433648579385e-06, "epoch": 1.720553292600136, "percentage": 34.41, "elapsed_time": "0:31:29", "remaining_time": "1:00:01", "throughput": 10291.49, "total_tokens": 19447872}
{"current_steps": 20280, "total_steps": 58920, "loss": 0.045, "lr": 1.6582203917029834e-06, "epoch": 1.7209775967413443, "percentage": 34.42, "elapsed_time": "0:31:30", "remaining_time": "1:00:01", "throughput": 10291.89, "total_tokens": 19452480}
{"current_steps": 20285, "total_steps": 58920, "loss": 0.0247, "lr": 1.6579973607915652e-06, "epoch": 1.7214019008825527, "percentage": 34.43, "elapsed_time": "0:31:30", "remaining_time": "1:00:00", "throughput": 10292.21, "total_tokens": 19456960}
{"current_steps": 20290, "total_steps": 58920, "loss": 0.0206, "lr": 1.6577742721432543e-06, "epoch": 1.7218262050237612, "percentage": 34.44, "elapsed_time": "0:31:30", "remaining_time": "0:59:59", "throughput": 10292.66, "total_tokens": 19461760}
{"current_steps": 20295, "total_steps": 58920, "loss": 0.1315, "lr": 1.657551125777626e-06, "epoch": 1.7222505091649696, "percentage": 34.45, "elapsed_time": "0:31:31", "remaining_time": "0:59:59", "throughput": 10293.31, "total_tokens": 19467072}
{"current_steps": 20300, "total_steps": 58920, "loss": 0.0007, "lr": 1.6573279217142605e-06, "epoch": 1.722674813306178, "percentage": 34.45, "elapsed_time": "0:31:31", "remaining_time": "0:59:58", "throughput": 10294.05, "total_tokens": 19472576}
{"current_steps": 20305, "total_steps": 58920, "loss": 0.1027, "lr": 1.6571046599727433e-06, "epoch": 1.7230991174473864, "percentage": 34.46, "elapsed_time": "0:31:32", "remaining_time": "0:59:58", "throughput": 10294.57, "total_tokens": 19477568}
{"current_steps": 20310, "total_steps": 58920, "loss": 0.0676, "lr": 1.6568813405726644e-06, "epoch": 1.7235234215885948, "percentage": 34.47, "elapsed_time": "0:31:32", "remaining_time": "0:59:57", "throughput": 10294.96, "total_tokens": 19482240}
{"current_steps": 20315, "total_steps": 58920, "loss": 0.0381, "lr": 1.6566579635336196e-06, "epoch": 1.7239477257298033, "percentage": 34.48, "elapsed_time": "0:31:32", "remaining_time": "0:59:56", "throughput": 10295.23, "total_tokens": 19486592}
{"current_steps": 20320, "total_steps": 58920, "loss": 0.0186, "lr": 1.6564345288752093e-06, "epoch": 1.7243720298710117, "percentage": 34.49, "elapsed_time": "0:31:33", "remaining_time": "0:59:56", "throughput": 10295.6, "total_tokens": 19491200}
{"current_steps": 20325, "total_steps": 58920, "loss": 0.031, "lr": 1.656211036617039e-06, "epoch": 1.72479633401222, "percentage": 34.5, "elapsed_time": "0:31:33", "remaining_time": "0:59:55", "throughput": 10296.34, "total_tokens": 19496704}
{"current_steps": 20330, "total_steps": 58920, "loss": 0.0689, "lr": 1.6559874867787198e-06, "epoch": 1.7252206381534285, "percentage": 34.5, "elapsed_time": "0:31:33", "remaining_time": "0:59:55", "throughput": 10296.87, "total_tokens": 19501696}
{"current_steps": 20335, "total_steps": 58920, "loss": 0.0231, "lr": 1.655763879379867e-06, "epoch": 1.725644942294637, "percentage": 34.51, "elapsed_time": "0:31:34", "remaining_time": "0:59:54", "throughput": 10297.26, "total_tokens": 19506304}
{"current_steps": 20340, "total_steps": 58920, "loss": 0.0013, "lr": 1.6555402144401014e-06, "epoch": 1.7260692464358454, "percentage": 34.52, "elapsed_time": "0:31:34", "remaining_time": "0:59:53", "throughput": 10298.01, "total_tokens": 19511872}
{"current_steps": 20345, "total_steps": 58920, "loss": 0.003, "lr": 1.6553164919790488e-06, "epoch": 1.7264935505770538, "percentage": 34.53, "elapsed_time": "0:31:35", "remaining_time": "0:59:53", "throughput": 10298.36, "total_tokens": 19516480}
{"current_steps": 20350, "total_steps": 58920, "loss": 0.0155, "lr": 1.6550927120163398e-06, "epoch": 1.7269178547182622, "percentage": 34.54, "elapsed_time": "0:31:35", "remaining_time": "0:59:52", "throughput": 10298.93, "total_tokens": 19521536}
{"current_steps": 20355, "total_steps": 58920, "loss": 0.0405, "lr": 1.6548688745716109e-06, "epoch": 1.7273421588594706, "percentage": 34.55, "elapsed_time": "0:31:35", "remaining_time": "0:59:51", "throughput": 10299.55, "total_tokens": 19526784}
{"current_steps": 20360, "total_steps": 58920, "loss": 0.0037, "lr": 1.6546449796645024e-06, "epoch": 1.727766463000679, "percentage": 34.56, "elapsed_time": "0:31:36", "remaining_time": "0:59:51", "throughput": 10299.96, "total_tokens": 19531520}
{"current_steps": 20365, "total_steps": 58920, "loss": 0.0766, "lr": 1.6544210273146606e-06, "epoch": 1.7281907671418875, "percentage": 34.56, "elapsed_time": "0:31:36", "remaining_time": "0:59:50", "throughput": 10300.49, "total_tokens": 19536512}
{"current_steps": 20370, "total_steps": 58920, "loss": 0.073, "lr": 1.6541970175417363e-06, "epoch": 1.7286150712830959, "percentage": 34.57, "elapsed_time": "0:31:37", "remaining_time": "0:59:50", "throughput": 10300.98, "total_tokens": 19541376}
{"current_steps": 20375, "total_steps": 58920, "loss": 0.0458, "lr": 1.653972950365386e-06, "epoch": 1.7290393754243043, "percentage": 34.58, "elapsed_time": "0:31:37", "remaining_time": "0:59:49", "throughput": 10301.45, "total_tokens": 19546240}
{"current_steps": 20380, "total_steps": 58920, "loss": 0.0021, "lr": 1.6537488258052701e-06, "epoch": 1.7294636795655127, "percentage": 34.59, "elapsed_time": "0:31:37", "remaining_time": "0:59:48", "throughput": 10301.9, "total_tokens": 19551040}
{"current_steps": 20385, "total_steps": 58920, "loss": 0.0349, "lr": 1.6535246438810554e-06, "epoch": 1.7298879837067211, "percentage": 34.6, "elapsed_time": "0:31:38", "remaining_time": "0:59:48", "throughput": 10302.33, "total_tokens": 19555776}
{"current_steps": 20390, "total_steps": 58920, "loss": 0.0209, "lr": 1.6533004046124125e-06, "epoch": 1.7303122878479293, "percentage": 34.61, "elapsed_time": "0:31:38", "remaining_time": "0:59:47", "throughput": 10303.17, "total_tokens": 19561536}
{"current_steps": 20395, "total_steps": 58920, "loss": 0.0773, "lr": 1.6530761080190178e-06, "epoch": 1.7307365919891378, "percentage": 34.61, "elapsed_time": "0:31:38", "remaining_time": "0:59:47", "throughput": 10303.63, "total_tokens": 19566400}
{"current_steps": 20400, "total_steps": 58920, "loss": 0.0693, "lr": 1.6528517541205527e-06, "epoch": 1.7311608961303462, "percentage": 34.62, "elapsed_time": "0:31:39", "remaining_time": "0:59:46", "throughput": 10303.97, "total_tokens": 19570944}
{"current_steps": 20405, "total_steps": 58920, "loss": 0.0006, "lr": 1.6526273429367032e-06, "epoch": 1.7315852002715546, "percentage": 34.63, "elapsed_time": "0:31:39", "remaining_time": "0:59:45", "throughput": 10304.38, "total_tokens": 19575616}
{"current_steps": 20410, "total_steps": 58920, "loss": 0.0493, "lr": 1.6524028744871607e-06, "epoch": 1.732009504412763, "percentage": 34.64, "elapsed_time": "0:31:40", "remaining_time": "0:59:45", "throughput": 10304.71, "total_tokens": 19580096}
{"current_steps": 20415, "total_steps": 58920, "loss": 0.0006, "lr": 1.6521783487916214e-06, "epoch": 1.7324338085539714, "percentage": 34.65, "elapsed_time": "0:31:40", "remaining_time": "0:59:44", "throughput": 10305.0, "total_tokens": 19584512}
{"current_steps": 20420, "total_steps": 58920, "loss": 0.095, "lr": 1.651953765869787e-06, "epoch": 1.7328581126951799, "percentage": 34.66, "elapsed_time": "0:31:40", "remaining_time": "0:59:43", "throughput": 10305.6, "total_tokens": 19589632}
{"current_steps": 20425, "total_steps": 58920, "loss": 0.0139, "lr": 1.651729125741363e-06, "epoch": 1.7332824168363883, "percentage": 34.67, "elapsed_time": "0:31:41", "remaining_time": "0:59:43", "throughput": 10306.06, "total_tokens": 19594496}
{"current_steps": 20430, "total_steps": 58920, "loss": 0.05, "lr": 1.6515044284260618e-06, "epoch": 1.7337067209775967, "percentage": 34.67, "elapsed_time": "0:31:41", "remaining_time": "0:59:42", "throughput": 10306.5, "total_tokens": 19599232}
{"current_steps": 20435, "total_steps": 58920, "loss": 0.0982, "lr": 1.6512796739435988e-06, "epoch": 1.7341310251188051, "percentage": 34.68, "elapsed_time": "0:31:42", "remaining_time": "0:59:42", "throughput": 10307.19, "total_tokens": 19604608}
{"current_steps": 20440, "total_steps": 58920, "loss": 0.0606, "lr": 1.6510548623136962e-06, "epoch": 1.7345553292600135, "percentage": 34.69, "elapsed_time": "0:31:42", "remaining_time": "0:59:41", "throughput": 10308.09, "total_tokens": 19610560}
{"current_steps": 20445, "total_steps": 58920, "loss": 0.053, "lr": 1.6508299935560797e-06, "epoch": 1.734979633401222, "percentage": 34.7, "elapsed_time": "0:31:42", "remaining_time": "0:59:40", "throughput": 10308.47, "total_tokens": 19615232}
{"current_steps": 20450, "total_steps": 58920, "loss": 0.0008, "lr": 1.6506050676904813e-06, "epoch": 1.7354039375424304, "percentage": 34.71, "elapsed_time": "0:31:43", "remaining_time": "0:59:40", "throughput": 10308.66, "total_tokens": 19619392}
{"current_steps": 20455, "total_steps": 58920, "loss": 0.0438, "lr": 1.650380084736637e-06, "epoch": 1.7358282416836388, "percentage": 34.72, "elapsed_time": "0:31:43", "remaining_time": "0:59:39", "throughput": 10308.99, "total_tokens": 19623936}
{"current_steps": 20460, "total_steps": 58920, "loss": 0.0142, "lr": 1.6501550447142888e-06, "epoch": 1.7362525458248472, "percentage": 34.73, "elapsed_time": "0:31:43", "remaining_time": "0:59:38", "throughput": 10309.26, "total_tokens": 19628288}
{"current_steps": 20465, "total_steps": 58920, "loss": 0.0658, "lr": 1.6499299476431826e-06, "epoch": 1.7366768499660556, "percentage": 34.73, "elapsed_time": "0:31:44", "remaining_time": "0:59:38", "throughput": 10309.72, "total_tokens": 19633152}
{"current_steps": 20470, "total_steps": 58920, "loss": 0.005, "lr": 1.64970479354307e-06, "epoch": 1.737101154107264, "percentage": 34.74, "elapsed_time": "0:31:44", "remaining_time": "0:59:37", "throughput": 10310.07, "total_tokens": 19637760}
{"current_steps": 20475, "total_steps": 58920, "loss": 0.0404, "lr": 1.6494795824337079e-06, "epoch": 1.7375254582484725, "percentage": 34.75, "elapsed_time": "0:31:45", "remaining_time": "0:59:37", "throughput": 10310.51, "total_tokens": 19642560}
{"current_steps": 20480, "total_steps": 58920, "loss": 0.0728, "lr": 1.6492543143348568e-06, "epoch": 1.737949762389681, "percentage": 34.76, "elapsed_time": "0:31:45", "remaining_time": "0:59:36", "throughput": 10310.98, "total_tokens": 19647360}
{"current_steps": 20485, "total_steps": 58920, "loss": 0.0014, "lr": 1.649028989266284e-06, "epoch": 1.7383740665308893, "percentage": 34.77, "elapsed_time": "0:31:45", "remaining_time": "0:59:35", "throughput": 10311.46, "total_tokens": 19652224}
{"current_steps": 20490, "total_steps": 58920, "loss": 0.0519, "lr": 1.648803607247761e-06, "epoch": 1.7387983706720977, "percentage": 34.78, "elapsed_time": "0:31:46", "remaining_time": "0:59:35", "throughput": 10311.88, "total_tokens": 19656960}
{"current_steps": 20495, "total_steps": 58920, "loss": 0.0736, "lr": 1.6485781682990634e-06, "epoch": 1.7392226748133062, "percentage": 34.78, "elapsed_time": "0:31:46", "remaining_time": "0:59:34", "throughput": 10312.17, "total_tokens": 19661376}
{"current_steps": 20500, "total_steps": 58920, "loss": 0.0555, "lr": 1.6483526724399735e-06, "epoch": 1.7396469789545146, "percentage": 34.79, "elapsed_time": "0:31:46", "remaining_time": "0:59:33", "throughput": 10312.56, "total_tokens": 19666048}
{"current_steps": 20505, "total_steps": 58920, "loss": 0.0535, "lr": 1.6481271196902774e-06, "epoch": 1.740071283095723, "percentage": 34.8, "elapsed_time": "0:31:47", "remaining_time": "0:59:33", "throughput": 10313.68, "total_tokens": 19672576}
{"current_steps": 20510, "total_steps": 58920, "loss": 0.0011, "lr": 1.6479015100697668e-06, "epoch": 1.7404955872369314, "percentage": 34.81, "elapsed_time": "0:31:47", "remaining_time": "0:59:32", "throughput": 10314.18, "total_tokens": 19677504}
{"current_steps": 20515, "total_steps": 58920, "loss": 0.0204, "lr": 1.6476758435982378e-06, "epoch": 1.7409198913781398, "percentage": 34.82, "elapsed_time": "0:31:48", "remaining_time": "0:59:32", "throughput": 10314.7, "total_tokens": 19682496}
{"current_steps": 20520, "total_steps": 58920, "loss": 0.0616, "lr": 1.647450120295492e-06, "epoch": 1.7413441955193483, "percentage": 34.83, "elapsed_time": "0:31:48", "remaining_time": "0:59:31", "throughput": 10315.0, "total_tokens": 19686912}
{"current_steps": 20525, "total_steps": 58920, "loss": 0.0208, "lr": 1.6472243401813354e-06, "epoch": 1.7417684996605567, "percentage": 34.84, "elapsed_time": "0:31:48", "remaining_time": "0:59:30", "throughput": 10315.33, "total_tokens": 19691392}
{"current_steps": 20530, "total_steps": 58920, "loss": 0.05, "lr": 1.6469985032755803e-06, "epoch": 1.742192803801765, "percentage": 34.84, "elapsed_time": "0:31:49", "remaining_time": "0:59:30", "throughput": 10315.44, "total_tokens": 19695360}
{"current_steps": 20535, "total_steps": 58920, "loss": 0.0772, "lr": 1.646772609598042e-06, "epoch": 1.7426171079429735, "percentage": 34.85, "elapsed_time": "0:31:49", "remaining_time": "0:59:29", "throughput": 10315.98, "total_tokens": 19700352}
{"current_steps": 20540, "total_steps": 58920, "loss": 0.0301, "lr": 1.6465466591685426e-06, "epoch": 1.743041412084182, "percentage": 34.86, "elapsed_time": "0:31:50", "remaining_time": "0:59:29", "throughput": 10316.22, "total_tokens": 19704640}
{"current_steps": 20545, "total_steps": 58920, "loss": 0.0734, "lr": 1.6463206520069082e-06, "epoch": 1.7434657162253904, "percentage": 34.87, "elapsed_time": "0:31:50", "remaining_time": "0:59:28", "throughput": 10316.6, "total_tokens": 19709248}
{"current_steps": 20550, "total_steps": 58920, "loss": 0.0409, "lr": 1.6460945881329703e-06, "epoch": 1.7438900203665988, "percentage": 34.88, "elapsed_time": "0:31:50", "remaining_time": "0:59:27", "throughput": 10317.09, "total_tokens": 19714176}
{"current_steps": 20555, "total_steps": 58920, "loss": 0.0815, "lr": 1.645868467566565e-06, "epoch": 1.7443143245078072, "percentage": 34.89, "elapsed_time": "0:31:51", "remaining_time": "0:59:27", "throughput": 10317.79, "total_tokens": 19719616}
{"current_steps": 20560, "total_steps": 58920, "loss": 0.0855, "lr": 1.6456422903275333e-06, "epoch": 1.7447386286490156, "percentage": 34.89, "elapsed_time": "0:31:51", "remaining_time": "0:59:26", "throughput": 10318.18, "total_tokens": 19724224}
{"current_steps": 20565, "total_steps": 58920, "loss": 0.0039, "lr": 1.6454160564357218e-06, "epoch": 1.745162932790224, "percentage": 34.9, "elapsed_time": "0:31:51", "remaining_time": "0:59:25", "throughput": 10318.7, "total_tokens": 19729216}
{"current_steps": 20570, "total_steps": 58920, "loss": 0.0279, "lr": 1.6451897659109814e-06, "epoch": 1.7455872369314325, "percentage": 34.91, "elapsed_time": "0:31:52", "remaining_time": "0:59:25", "throughput": 10318.97, "total_tokens": 19733568}
{"current_steps": 20575, "total_steps": 58920, "loss": 0.0135, "lr": 1.644963418773169e-06, "epoch": 1.746011541072641, "percentage": 34.92, "elapsed_time": "0:31:52", "remaining_time": "0:59:24", "throughput": 10319.31, "total_tokens": 19738176}
{"current_steps": 20580, "total_steps": 58920, "loss": 0.078, "lr": 1.644737015042145e-06, "epoch": 1.7464358452138493, "percentage": 34.93, "elapsed_time": "0:31:53", "remaining_time": "0:59:24", "throughput": 10319.83, "total_tokens": 19743168}
{"current_steps": 20585, "total_steps": 58920, "loss": 0.0475, "lr": 1.6445105547377755e-06, "epoch": 1.7468601493550577, "percentage": 34.94, "elapsed_time": "0:31:53", "remaining_time": "0:59:23", "throughput": 10320.28, "total_tokens": 19747968}
{"current_steps": 20590, "total_steps": 58920, "loss": 0.0311, "lr": 1.6442840378799318e-06, "epoch": 1.7472844534962662, "percentage": 34.95, "elapsed_time": "0:31:53", "remaining_time": "0:59:22", "throughput": 10320.47, "total_tokens": 19752128}
{"current_steps": 20595, "total_steps": 58920, "loss": 0.0025, "lr": 1.6440574644884906e-06, "epoch": 1.7477087576374746, "percentage": 34.95, "elapsed_time": "0:31:54", "remaining_time": "0:59:22", "throughput": 10320.97, "total_tokens": 19757056}
{"current_steps": 20600, "total_steps": 58920, "loss": 0.0221, "lr": 1.6438308345833316e-06, "epoch": 1.748133061778683, "percentage": 34.96, "elapsed_time": "0:31:54", "remaining_time": "0:59:21", "throughput": 10321.52, "total_tokens": 19762112}
{"current_steps": 20605, "total_steps": 58920, "loss": 0.027, "lr": 1.643604148184342e-06, "epoch": 1.7485573659198914, "percentage": 34.97, "elapsed_time": "0:31:55", "remaining_time": "0:59:20", "throughput": 10321.78, "total_tokens": 19766464}
{"current_steps": 20610, "total_steps": 58920, "loss": 0.0006, "lr": 1.6433774053114116e-06, "epoch": 1.7489816700610998, "percentage": 34.98, "elapsed_time": "0:31:55", "remaining_time": "0:59:20", "throughput": 10322.19, "total_tokens": 19771200}
{"current_steps": 20615, "total_steps": 58920, "loss": 0.0554, "lr": 1.6431506059844366e-06, "epoch": 1.7494059742023083, "percentage": 34.99, "elapsed_time": "0:31:55", "remaining_time": "0:59:19", "throughput": 10322.63, "total_tokens": 19775936}
{"current_steps": 20620, "total_steps": 58920, "loss": 0.0084, "lr": 1.6429237502233187e-06, "epoch": 1.7498302783435167, "percentage": 35.0, "elapsed_time": "0:31:56", "remaining_time": "0:59:19", "throughput": 10322.82, "total_tokens": 19780160}
{"current_steps": 20622, "total_steps": 58920, "eval_loss": 0.08258260786533356, "epoch": 1.75, "percentage": 35.0, "elapsed_time": "0:32:12", "remaining_time": "0:59:49", "throughput": 10235.9, "total_tokens": 19782400}
{"current_steps": 20625, "total_steps": 58920, "loss": 0.0376, "lr": 1.6426968380479625e-06, "epoch": 1.750254582484725, "percentage": 35.01, "elapsed_time": "0:32:48", "remaining_time": "1:00:54", "throughput": 10051.01, "total_tokens": 19785280}
{"current_steps": 20630, "total_steps": 58920, "loss": 0.0921, "lr": 1.6424698694782793e-06, "epoch": 1.7506788866259335, "percentage": 35.01, "elapsed_time": "0:32:48", "remaining_time": "1:00:54", "throughput": 10051.43, "total_tokens": 19789952}
{"current_steps": 20635, "total_steps": 58920, "loss": 0.0587, "lr": 1.6422428445341846e-06, "epoch": 1.751103190767142, "percentage": 35.02, "elapsed_time": "0:32:49", "remaining_time": "1:00:53", "throughput": 10052.07, "total_tokens": 19795200}
{"current_steps": 20640, "total_steps": 58920, "loss": 0.0008, "lr": 1.6420157632355993e-06, "epoch": 1.7515274949083504, "percentage": 35.03, "elapsed_time": "0:32:49", "remaining_time": "1:00:53", "throughput": 10052.56, "total_tokens": 19800000}
{"current_steps": 20645, "total_steps": 58920, "loss": 0.0013, "lr": 1.6417886256024488e-06, "epoch": 1.7519517990495588, "percentage": 35.04, "elapsed_time": "0:32:50", "remaining_time": "1:00:52", "throughput": 10053.05, "total_tokens": 19804800}
{"current_steps": 20650, "total_steps": 58920, "loss": 0.0028, "lr": 1.6415614316546633e-06, "epoch": 1.752376103190767, "percentage": 35.05, "elapsed_time": "0:32:50", "remaining_time": "1:00:51", "throughput": 10053.56, "total_tokens": 19809664}
{"current_steps": 20655, "total_steps": 58920, "loss": 0.0007, "lr": 1.6413341814121788e-06, "epoch": 1.7528004073319754, "percentage": 35.06, "elapsed_time": "0:32:50", "remaining_time": "1:00:51", "throughput": 10053.9, "total_tokens": 19814080}
{"current_steps": 20660, "total_steps": 58920, "loss": 0.0567, "lr": 1.6411068748949352e-06, "epoch": 1.7532247114731838, "percentage": 35.06, "elapsed_time": "0:32:51", "remaining_time": "1:00:50", "throughput": 10054.36, "total_tokens": 19818816}
{"current_steps": 20665, "total_steps": 58920, "loss": 0.0629, "lr": 1.6408795121228783e-06, "epoch": 1.7536490156143922, "percentage": 35.07, "elapsed_time": "0:32:51", "remaining_time": "1:00:49", "throughput": 10054.8, "total_tokens": 19823488}
{"current_steps": 20670, "total_steps": 58920, "loss": 0.0292, "lr": 1.6406520931159577e-06, "epoch": 1.7540733197556007, "percentage": 35.08, "elapsed_time": "0:32:51", "remaining_time": "1:00:49", "throughput": 10055.16, "total_tokens": 19828032}
{"current_steps": 20675, "total_steps": 58920, "loss": 0.1283, "lr": 1.6404246178941295e-06, "epoch": 1.754497623896809, "percentage": 35.09, "elapsed_time": "0:32:52", "remaining_time": "1:00:48", "throughput": 10055.6, "total_tokens": 19832704}
{"current_steps": 20680, "total_steps": 58920, "loss": 0.1071, "lr": 1.6401970864773528e-06, "epoch": 1.7549219280380175, "percentage": 35.1, "elapsed_time": "0:32:52", "remaining_time": "1:00:47", "throughput": 10055.9, "total_tokens": 19837056}
{"current_steps": 20685, "total_steps": 58920, "loss": 0.0161, "lr": 1.6399694988855936e-06, "epoch": 1.755346232179226, "percentage": 35.11, "elapsed_time": "0:32:53", "remaining_time": "1:00:47", "throughput": 10056.35, "total_tokens": 19841792}
{"current_steps": 20690, "total_steps": 58920, "loss": 0.0628, "lr": 1.6397418551388213e-06, "epoch": 1.7557705363204343, "percentage": 35.12, "elapsed_time": "0:32:53", "remaining_time": "1:00:46", "throughput": 10057.11, "total_tokens": 19847296}
{"current_steps": 20695, "total_steps": 58920, "loss": 0.0191, "lr": 1.639514155257011e-06, "epoch": 1.7561948404616428, "percentage": 35.12, "elapsed_time": "0:32:53", "remaining_time": "1:00:45", "throughput": 10057.72, "total_tokens": 19852416}
{"current_steps": 20700, "total_steps": 58920, "loss": 0.0541, "lr": 1.6392863992601425e-06, "epoch": 1.7566191446028512, "percentage": 35.13, "elapsed_time": "0:32:54", "remaining_time": "1:00:45", "throughput": 10058.26, "total_tokens": 19857344}
{"current_steps": 20705, "total_steps": 58920, "loss": 0.055, "lr": 1.6390585871682005e-06, "epoch": 1.7570434487440596, "percentage": 35.14, "elapsed_time": "0:32:54", "remaining_time": "1:00:44", "throughput": 10058.67, "total_tokens": 19861952}
{"current_steps": 20710, "total_steps": 58920, "loss": 0.0348, "lr": 1.638830719001175e-06, "epoch": 1.757467752885268, "percentage": 35.15, "elapsed_time": "0:32:54", "remaining_time": "1:00:43", "throughput": 10059.19, "total_tokens": 19866880}
{"current_steps": 20715, "total_steps": 58920, "loss": 0.0834, "lr": 1.6386027947790603e-06, "epoch": 1.7578920570264764, "percentage": 35.16, "elapsed_time": "0:32:55", "remaining_time": "1:00:43", "throughput": 10059.48, "total_tokens": 19871232}
{"current_steps": 20720, "total_steps": 58920, "loss": 0.0582, "lr": 1.6383748145218561e-06, "epoch": 1.7583163611676849, "percentage": 35.17, "elapsed_time": "0:32:55", "remaining_time": "1:00:42", "throughput": 10059.94, "total_tokens": 19875904}
{"current_steps": 20725, "total_steps": 58920, "loss": 0.0815, "lr": 1.6381467782495667e-06, "epoch": 1.7587406653088933, "percentage": 35.17, "elapsed_time": "0:32:56", "remaining_time": "1:00:41", "throughput": 10060.28, "total_tokens": 19880384}
{"current_steps": 20730, "total_steps": 58920, "loss": 0.0255, "lr": 1.6379186859822016e-06, "epoch": 1.7591649694501017, "percentage": 35.18, "elapsed_time": "0:32:56", "remaining_time": "1:00:41", "throughput": 10060.69, "total_tokens": 19884992}
{"current_steps": 20735, "total_steps": 58920, "loss": 0.0015, "lr": 1.637690537739775e-06, "epoch": 1.7595892735913101, "percentage": 35.19, "elapsed_time": "0:32:56", "remaining_time": "1:00:40", "throughput": 10061.05, "total_tokens": 19889472}
{"current_steps": 20740, "total_steps": 58920, "loss": 0.0188, "lr": 1.637462333542306e-06, "epoch": 1.7600135777325185, "percentage": 35.2, "elapsed_time": "0:32:57", "remaining_time": "1:00:39", "throughput": 10061.61, "total_tokens": 19894464}
{"current_steps": 20745, "total_steps": 58920, "loss": 0.0069, "lr": 1.6372340734098187e-06, "epoch": 1.760437881873727, "percentage": 35.21, "elapsed_time": "0:32:57", "remaining_time": "1:00:39", "throughput": 10062.05, "total_tokens": 19899136}
{"current_steps": 20750, "total_steps": 58920, "loss": 0.0006, "lr": 1.6370057573623425e-06, "epoch": 1.7608621860149354, "percentage": 35.22, "elapsed_time": "0:32:58", "remaining_time": "1:00:38", "throughput": 10062.63, "total_tokens": 19904192}
{"current_steps": 20755, "total_steps": 58920, "loss": 0.0467, "lr": 1.6367773854199104e-06, "epoch": 1.7612864901561438, "percentage": 35.23, "elapsed_time": "0:32:58", "remaining_time": "1:00:37", "throughput": 10063.2, "total_tokens": 19909248}
{"current_steps": 20760, "total_steps": 58920, "loss": 0.0608, "lr": 1.6365489576025625e-06, "epoch": 1.7617107942973522, "percentage": 35.23, "elapsed_time": "0:32:58", "remaining_time": "1:00:37", "throughput": 10063.7, "total_tokens": 19914112}
{"current_steps": 20765, "total_steps": 58920, "loss": 0.0229, "lr": 1.6363204739303413e-06, "epoch": 1.7621350984385606, "percentage": 35.24, "elapsed_time": "0:32:59", "remaining_time": "1:00:36", "throughput": 10064.09, "total_tokens": 19918656}
{"current_steps": 20770, "total_steps": 58920, "loss": 0.124, "lr": 1.636091934423296e-06, "epoch": 1.762559402579769, "percentage": 35.25, "elapsed_time": "0:32:59", "remaining_time": "1:00:36", "throughput": 10064.48, "total_tokens": 19923264}
{"current_steps": 20775, "total_steps": 58920, "loss": 0.0788, "lr": 1.6358633391014802e-06, "epoch": 1.7629837067209775, "percentage": 35.26, "elapsed_time": "0:32:59", "remaining_time": "1:00:35", "throughput": 10064.92, "total_tokens": 19927936}
{"current_steps": 20780, "total_steps": 58920, "loss": 0.0255, "lr": 1.6356346879849524e-06, "epoch": 1.763408010862186, "percentage": 35.27, "elapsed_time": "0:33:00", "remaining_time": "1:00:34", "throughput": 10065.36, "total_tokens": 19932672}
{"current_steps": 20785, "total_steps": 58920, "loss": 0.0258, "lr": 1.6354059810937755e-06, "epoch": 1.7638323150033943, "percentage": 35.28, "elapsed_time": "0:33:00", "remaining_time": "1:00:34", "throughput": 10065.74, "total_tokens": 19937216}
{"current_steps": 20790, "total_steps": 58920, "loss": 0.0541, "lr": 1.6351772184480175e-06, "epoch": 1.7642566191446027, "percentage": 35.29, "elapsed_time": "0:33:01", "remaining_time": "1:00:33", "throughput": 10066.1, "total_tokens": 19941760}
{"current_steps": 20795, "total_steps": 58920, "loss": 0.0985, "lr": 1.6349484000677523e-06, "epoch": 1.7646809232858112, "percentage": 35.29, "elapsed_time": "0:33:01", "remaining_time": "1:00:32", "throughput": 10066.48, "total_tokens": 19946304}
{"current_steps": 20800, "total_steps": 58920, "loss": 0.0161, "lr": 1.6347195259730575e-06, "epoch": 1.7651052274270196, "percentage": 35.3, "elapsed_time": "0:33:01", "remaining_time": "1:00:32", "throughput": 10067.14, "total_tokens": 19951552}
{"current_steps": 20805, "total_steps": 58920, "loss": 0.0686, "lr": 1.634490596184016e-06, "epoch": 1.765529531568228, "percentage": 35.31, "elapsed_time": "0:33:02", "remaining_time": "1:00:31", "throughput": 10067.56, "total_tokens": 19956160}
{"current_steps": 20810, "total_steps": 58920, "loss": 0.0897, "lr": 1.6342616107207152e-06, "epoch": 1.7659538357094364, "percentage": 35.32, "elapsed_time": "0:33:02", "remaining_time": "1:00:30", "throughput": 10067.86, "total_tokens": 19960512}
{"current_steps": 20815, "total_steps": 58920, "loss": 0.0881, "lr": 1.634032569603248e-06, "epoch": 1.7663781398506448, "percentage": 35.33, "elapsed_time": "0:33:02", "remaining_time": "1:00:30", "throughput": 10068.42, "total_tokens": 19965440}
{"current_steps": 20820, "total_steps": 58920, "loss": 0.0443, "lr": 1.6338034728517122e-06, "epoch": 1.7668024439918533, "percentage": 35.34, "elapsed_time": "0:33:03", "remaining_time": "1:00:29", "throughput": 10069.25, "total_tokens": 19971136}
{"current_steps": 20825, "total_steps": 58920, "loss": 0.0639, "lr": 1.63357432048621e-06, "epoch": 1.7672267481330617, "percentage": 35.34, "elapsed_time": "0:33:03", "remaining_time": "1:00:28", "throughput": 10069.7, "total_tokens": 19975808}
{"current_steps": 20830, "total_steps": 58920, "loss": 0.0444, "lr": 1.6333451125268484e-06, "epoch": 1.76765105227427, "percentage": 35.35, "elapsed_time": "0:33:04", "remaining_time": "1:00:28", "throughput": 10070.19, "total_tokens": 19980672}
{"current_steps": 20835, "total_steps": 58920, "loss": 0.0279, "lr": 1.6331158489937403e-06, "epoch": 1.7680753564154785, "percentage": 35.36, "elapsed_time": "0:33:04", "remaining_time": "1:00:27", "throughput": 10070.61, "total_tokens": 19985344}
{"current_steps": 20840, "total_steps": 58920, "loss": 0.0182, "lr": 1.632886529907002e-06, "epoch": 1.768499660556687, "percentage": 35.37, "elapsed_time": "0:33:04", "remaining_time": "1:00:26", "throughput": 10071.09, "total_tokens": 19990144}
{"current_steps": 20845, "total_steps": 58920, "loss": 0.0919, "lr": 1.6326571552867558e-06, "epoch": 1.7689239646978954, "percentage": 35.38, "elapsed_time": "0:33:05", "remaining_time": "1:00:26", "throughput": 10071.43, "total_tokens": 19994624}
{"current_steps": 20850, "total_steps": 58920, "loss": 0.073, "lr": 1.6324277251531286e-06, "epoch": 1.7693482688391038, "percentage": 35.39, "elapsed_time": "0:33:05", "remaining_time": "1:00:25", "throughput": 10072.13, "total_tokens": 20000064}
{"current_steps": 20855, "total_steps": 58920, "loss": 0.0281, "lr": 1.632198239526252e-06, "epoch": 1.7697725729803122, "percentage": 35.4, "elapsed_time": "0:33:06", "remaining_time": "1:00:25", "throughput": 10072.8, "total_tokens": 20005376}
{"current_steps": 20860, "total_steps": 58920, "loss": 0.0024, "lr": 1.6319686984262617e-06, "epoch": 1.7701968771215206, "percentage": 35.4, "elapsed_time": "0:33:06", "remaining_time": "1:00:24", "throughput": 10073.41, "total_tokens": 20010560}
{"current_steps": 20865, "total_steps": 58920, "loss": 0.0178, "lr": 1.6317391018733005e-06, "epoch": 1.770621181262729, "percentage": 35.41, "elapsed_time": "0:33:06", "remaining_time": "1:00:23", "throughput": 10074.06, "total_tokens": 20015872}
{"current_steps": 20870, "total_steps": 58920, "loss": 0.0771, "lr": 1.6315094498875138e-06, "epoch": 1.7710454854039375, "percentage": 35.42, "elapsed_time": "0:33:07", "remaining_time": "1:00:23", "throughput": 10074.79, "total_tokens": 20021376}
{"current_steps": 20875, "total_steps": 58920, "loss": 0.1417, "lr": 1.631279742489053e-06, "epoch": 1.771469789545146, "percentage": 35.43, "elapsed_time": "0:33:07", "remaining_time": "1:00:22", "throughput": 10075.13, "total_tokens": 20025856}
{"current_steps": 20880, "total_steps": 58920, "loss": 0.0011, "lr": 1.6310499796980736e-06, "epoch": 1.7718940936863543, "percentage": 35.44, "elapsed_time": "0:33:08", "remaining_time": "1:00:21", "throughput": 10075.45, "total_tokens": 20030272}
{"current_steps": 20885, "total_steps": 58920, "loss": 0.0284, "lr": 1.6308201615347375e-06, "epoch": 1.7723183978275627, "percentage": 35.45, "elapsed_time": "0:33:08", "remaining_time": "1:00:21", "throughput": 10075.88, "total_tokens": 20035008}
{"current_steps": 20890, "total_steps": 58920, "loss": 0.0708, "lr": 1.6305902880192095e-06, "epoch": 1.7727427019687712, "percentage": 35.45, "elapsed_time": "0:33:08", "remaining_time": "1:00:20", "throughput": 10076.39, "total_tokens": 20039936}
{"current_steps": 20895, "total_steps": 58920, "loss": 0.0086, "lr": 1.6303603591716603e-06, "epoch": 1.7731670061099796, "percentage": 35.46, "elapsed_time": "0:33:09", "remaining_time": "1:00:19", "throughput": 10076.92, "total_tokens": 20044928}
{"current_steps": 20900, "total_steps": 58920, "loss": 0.0624, "lr": 1.630130375012266e-06, "epoch": 1.773591310251188, "percentage": 35.47, "elapsed_time": "0:33:09", "remaining_time": "1:00:19", "throughput": 10077.42, "total_tokens": 20049792}
{"current_steps": 20905, "total_steps": 58920, "loss": 0.001, "lr": 1.6299003355612058e-06, "epoch": 1.7740156143923964, "percentage": 35.48, "elapsed_time": "0:33:09", "remaining_time": "1:00:18", "throughput": 10077.81, "total_tokens": 20054336}
{"current_steps": 20910, "total_steps": 58920, "loss": 0.0189, "lr": 1.6296702408386658e-06, "epoch": 1.7744399185336048, "percentage": 35.49, "elapsed_time": "0:33:10", "remaining_time": "1:00:17", "throughput": 10078.28, "total_tokens": 20059072}
{"current_steps": 20915, "total_steps": 58920, "loss": 0.0027, "lr": 1.6294400908648354e-06, "epoch": 1.7748642226748133, "percentage": 35.5, "elapsed_time": "0:33:10", "remaining_time": "1:00:17", "throughput": 10079.05, "total_tokens": 20064640}
{"current_steps": 20920, "total_steps": 58920, "loss": 0.09, "lr": 1.6292098856599094e-06, "epoch": 1.7752885268160217, "percentage": 35.51, "elapsed_time": "0:33:11", "remaining_time": "1:00:16", "throughput": 10079.66, "total_tokens": 20069824}
{"current_steps": 20925, "total_steps": 58920, "loss": 0.0005, "lr": 1.6289796252440879e-06, "epoch": 1.77571283095723, "percentage": 35.51, "elapsed_time": "0:33:11", "remaining_time": "1:00:16", "throughput": 10080.04, "total_tokens": 20074432}
{"current_steps": 20930, "total_steps": 58920, "loss": 0.0005, "lr": 1.6287493096375755e-06, "epoch": 1.7761371350984385, "percentage": 35.52, "elapsed_time": "0:33:11", "remaining_time": "1:00:15", "throughput": 10080.31, "total_tokens": 20078720}
{"current_steps": 20935, "total_steps": 58920, "loss": 0.0019, "lr": 1.6285189388605809e-06, "epoch": 1.776561439239647, "percentage": 35.53, "elapsed_time": "0:33:12", "remaining_time": "1:00:14", "throughput": 10080.8, "total_tokens": 20083584}
{"current_steps": 20940, "total_steps": 58920, "loss": 0.003, "lr": 1.628288512933319e-06, "epoch": 1.7769857433808554, "percentage": 35.54, "elapsed_time": "0:33:12", "remaining_time": "1:00:14", "throughput": 10081.23, "total_tokens": 20088384}
{"current_steps": 20945, "total_steps": 58920, "loss": 0.0857, "lr": 1.628058031876008e-06, "epoch": 1.7774100475220638, "percentage": 35.55, "elapsed_time": "0:33:13", "remaining_time": "1:00:13", "throughput": 10081.77, "total_tokens": 20093440}
{"current_steps": 20950, "total_steps": 58920, "loss": 0.079, "lr": 1.6278274957088726e-06, "epoch": 1.7778343516632722, "percentage": 35.56, "elapsed_time": "0:33:13", "remaining_time": "1:00:12", "throughput": 10082.17, "total_tokens": 20098112}
{"current_steps": 20955, "total_steps": 58920, "loss": 0.0005, "lr": 1.6275969044521412e-06, "epoch": 1.7782586558044806, "percentage": 35.57, "elapsed_time": "0:33:13", "remaining_time": "1:00:12", "throughput": 10082.64, "total_tokens": 20102912}
{"current_steps": 20960, "total_steps": 58920, "loss": 0.0004, "lr": 1.6273662581260473e-06, "epoch": 1.778682959945689, "percentage": 35.57, "elapsed_time": "0:33:14", "remaining_time": "1:00:11", "throughput": 10083.0, "total_tokens": 20107456}
{"current_steps": 20965, "total_steps": 58920, "loss": 0.0145, "lr": 1.6271355567508294e-06, "epoch": 1.7791072640868975, "percentage": 35.58, "elapsed_time": "0:33:14", "remaining_time": "1:00:10", "throughput": 10083.46, "total_tokens": 20112256}
{"current_steps": 20970, "total_steps": 58920, "loss": 0.061, "lr": 1.6269048003467307e-06, "epoch": 1.7795315682281059, "percentage": 35.59, "elapsed_time": "0:33:14", "remaining_time": "1:00:10", "throughput": 10083.81, "total_tokens": 20116800}
{"current_steps": 20975, "total_steps": 58920, "loss": 0.0311, "lr": 1.6266739889339994e-06, "epoch": 1.7799558723693143, "percentage": 35.6, "elapsed_time": "0:33:15", "remaining_time": "1:00:09", "throughput": 10084.31, "total_tokens": 20121728}
{"current_steps": 20980, "total_steps": 58920, "loss": 0.0513, "lr": 1.6264431225328876e-06, "epoch": 1.7803801765105227, "percentage": 35.61, "elapsed_time": "0:33:15", "remaining_time": "1:00:09", "throughput": 10084.7, "total_tokens": 20126400}
{"current_steps": 20985, "total_steps": 58920, "loss": 0.0126, "lr": 1.6262122011636539e-06, "epoch": 1.7808044806517311, "percentage": 35.62, "elapsed_time": "0:33:16", "remaining_time": "1:00:08", "throughput": 10085.26, "total_tokens": 20131520}
{"current_steps": 20990, "total_steps": 58920, "loss": 0.0023, "lr": 1.6259812248465606e-06, "epoch": 1.7812287847929396, "percentage": 35.62, "elapsed_time": "0:33:16", "remaining_time": "1:00:07", "throughput": 10085.76, "total_tokens": 20136448}
{"current_steps": 20995, "total_steps": 58920, "loss": 0.001, "lr": 1.6257501936018747e-06, "epoch": 1.781653088934148, "percentage": 35.63, "elapsed_time": "0:33:16", "remaining_time": "1:00:07", "throughput": 10086.26, "total_tokens": 20141312}
{"current_steps": 21000, "total_steps": 58920, "loss": 0.0004, "lr": 1.6255191074498686e-06, "epoch": 1.7820773930753564, "percentage": 35.64, "elapsed_time": "0:33:17", "remaining_time": "1:00:06", "throughput": 10086.72, "total_tokens": 20146112}
{"current_steps": 21005, "total_steps": 58920, "loss": 0.0352, "lr": 1.6252879664108193e-06, "epoch": 1.7825016972165648, "percentage": 35.65, "elapsed_time": "0:33:17", "remaining_time": "1:00:05", "throughput": 10087.17, "total_tokens": 20150848}
{"current_steps": 21010, "total_steps": 58920, "loss": 0.0454, "lr": 1.6250567705050085e-06, "epoch": 1.7829260013577732, "percentage": 35.66, "elapsed_time": "0:33:18", "remaining_time": "1:00:05", "throughput": 10087.86, "total_tokens": 20156288}
{"current_steps": 21015, "total_steps": 58920, "loss": 0.1038, "lr": 1.624825519752723e-06, "epoch": 1.7833503054989817, "percentage": 35.67, "elapsed_time": "0:33:18", "remaining_time": "1:00:04", "throughput": 10088.3, "total_tokens": 20161024}
{"current_steps": 21020, "total_steps": 58920, "loss": 0.0779, "lr": 1.624594214174254e-06, "epoch": 1.78377460964019, "percentage": 35.68, "elapsed_time": "0:33:18", "remaining_time": "1:00:04", "throughput": 10088.84, "total_tokens": 20166016}
{"current_steps": 21025, "total_steps": 58920, "loss": 0.0715, "lr": 1.624362853789898e-06, "epoch": 1.7841989137813985, "percentage": 35.68, "elapsed_time": "0:33:19", "remaining_time": "1:00:03", "throughput": 10089.36, "total_tokens": 20171008}
{"current_steps": 21030, "total_steps": 58920, "loss": 0.0334, "lr": 1.6241314386199552e-06, "epoch": 1.784623217922607, "percentage": 35.69, "elapsed_time": "0:33:19", "remaining_time": "1:00:02", "throughput": 10089.75, "total_tokens": 20175680}
{"current_steps": 21035, "total_steps": 58920, "loss": 0.0903, "lr": 1.6238999686847325e-06, "epoch": 1.7850475220638153, "percentage": 35.7, "elapsed_time": "0:33:20", "remaining_time": "1:00:02", "throughput": 10090.22, "total_tokens": 20180480}
{"current_steps": 21040, "total_steps": 58920, "loss": 0.0253, "lr": 1.62366844400454e-06, "epoch": 1.7854718262050238, "percentage": 35.71, "elapsed_time": "0:33:20", "remaining_time": "1:00:01", "throughput": 10090.63, "total_tokens": 20185216}
{"current_steps": 21045, "total_steps": 58920, "loss": 0.0015, "lr": 1.6234368645996935e-06, "epoch": 1.7858961303462322, "percentage": 35.72, "elapsed_time": "0:33:20", "remaining_time": "1:00:00", "throughput": 10091.03, "total_tokens": 20189888}
{"current_steps": 21050, "total_steps": 58920, "loss": 0.0266, "lr": 1.6232052304905129e-06, "epoch": 1.7863204344874406, "percentage": 35.73, "elapsed_time": "0:33:21", "remaining_time": "1:00:00", "throughput": 10091.51, "total_tokens": 20194752}
{"current_steps": 21055, "total_steps": 58920, "loss": 0.0744, "lr": 1.6229735416973233e-06, "epoch": 1.786744738628649, "percentage": 35.73, "elapsed_time": "0:33:21", "remaining_time": "0:59:59", "throughput": 10091.93, "total_tokens": 20199488}
{"current_steps": 21060, "total_steps": 58920, "loss": 0.0475, "lr": 1.622741798240455e-06, "epoch": 1.7871690427698574, "percentage": 35.74, "elapsed_time": "0:33:21", "remaining_time": "0:59:58", "throughput": 10092.43, "total_tokens": 20204352}
{"current_steps": 21065, "total_steps": 58920, "loss": 0.001, "lr": 1.6225100001402422e-06, "epoch": 1.7875933469110659, "percentage": 35.75, "elapsed_time": "0:33:22", "remaining_time": "0:59:58", "throughput": 10092.9, "total_tokens": 20209152}
{"current_steps": 21070, "total_steps": 58920, "loss": 0.0605, "lr": 1.6222781474170241e-06, "epoch": 1.7880176510522743, "percentage": 35.76, "elapsed_time": "0:33:22", "remaining_time": "0:59:57", "throughput": 10093.33, "total_tokens": 20213888}
{"current_steps": 21075, "total_steps": 58920, "loss": 0.0242, "lr": 1.6220462400911457e-06, "epoch": 1.7884419551934827, "percentage": 35.77, "elapsed_time": "0:33:23", "remaining_time": "0:59:56", "throughput": 10093.64, "total_tokens": 20218240}
{"current_steps": 21080, "total_steps": 58920, "loss": 0.0532, "lr": 1.6218142781829553e-06, "epoch": 1.7888662593346911, "percentage": 35.78, "elapsed_time": "0:33:23", "remaining_time": "0:59:56", "throughput": 10094.16, "total_tokens": 20223296}
{"current_steps": 21085, "total_steps": 58920, "loss": 0.0268, "lr": 1.6215822617128072e-06, "epoch": 1.7892905634758995, "percentage": 35.79, "elapsed_time": "0:33:23", "remaining_time": "0:59:55", "throughput": 10094.72, "total_tokens": 20228480}
{"current_steps": 21090, "total_steps": 58920, "loss": 0.1429, "lr": 1.6213501907010597e-06, "epoch": 1.789714867617108, "percentage": 35.79, "elapsed_time": "0:33:24", "remaining_time": "0:59:55", "throughput": 10095.18, "total_tokens": 20233408}
{"current_steps": 21095, "total_steps": 58920, "loss": 0.0228, "lr": 1.6211180651680768e-06, "epoch": 1.7901391717583164, "percentage": 35.8, "elapsed_time": "0:33:24", "remaining_time": "0:59:54", "throughput": 10095.41, "total_tokens": 20237696}
{"current_steps": 21100, "total_steps": 58920, "loss": 0.001, "lr": 1.6208858851342257e-06, "epoch": 1.7905634758995248, "percentage": 35.81, "elapsed_time": "0:33:25", "remaining_time": "0:59:53", "throughput": 10095.8, "total_tokens": 20242368}
{"current_steps": 21105, "total_steps": 58920, "loss": 0.0232, "lr": 1.62065365061988e-06, "epoch": 1.7909877800407332, "percentage": 35.82, "elapsed_time": "0:33:25", "remaining_time": "0:59:53", "throughput": 10096.05, "total_tokens": 20246656}
{"current_steps": 21110, "total_steps": 58920, "loss": 0.0007, "lr": 1.6204213616454174e-06, "epoch": 1.7914120841819416, "percentage": 35.83, "elapsed_time": "0:33:25", "remaining_time": "0:59:52", "throughput": 10096.37, "total_tokens": 20251136}
{"current_steps": 21115, "total_steps": 58920, "loss": 0.091, "lr": 1.6201890182312202e-06, "epoch": 1.79183638832315, "percentage": 35.84, "elapsed_time": "0:33:26", "remaining_time": "0:59:51", "throughput": 10096.77, "total_tokens": 20255872}
{"current_steps": 21120, "total_steps": 58920, "loss": 0.0784, "lr": 1.619956620397676e-06, "epoch": 1.7922606924643585, "percentage": 35.85, "elapsed_time": "0:33:26", "remaining_time": "0:59:51", "throughput": 10097.24, "total_tokens": 20260736}
{"current_steps": 21125, "total_steps": 58920, "loss": 0.0016, "lr": 1.6197241681651769e-06, "epoch": 1.792684996605567, "percentage": 35.85, "elapsed_time": "0:33:26", "remaining_time": "0:59:50", "throughput": 10097.53, "total_tokens": 20265152}
{"current_steps": 21130, "total_steps": 58920, "loss": 0.0203, "lr": 1.6194916615541193e-06, "epoch": 1.7931093007467753, "percentage": 35.86, "elapsed_time": "0:33:27", "remaining_time": "0:59:50", "throughput": 10098.04, "total_tokens": 20270208}
{"current_steps": 21135, "total_steps": 58920, "loss": 0.0824, "lr": 1.619259100584905e-06, "epoch": 1.7935336048879837, "percentage": 35.87, "elapsed_time": "0:33:27", "remaining_time": "0:59:49", "throughput": 10098.17, "total_tokens": 20274240}
{"current_steps": 21140, "total_steps": 58920, "loss": 0.0006, "lr": 1.6190264852779406e-06, "epoch": 1.7939579090291922, "percentage": 35.88, "elapsed_time": "0:33:28", "remaining_time": "0:59:48", "throughput": 10098.56, "total_tokens": 20278912}
{"current_steps": 21145, "total_steps": 58920, "loss": 0.0411, "lr": 1.618793815653637e-06, "epoch": 1.7943822131704006, "percentage": 35.89, "elapsed_time": "0:33:28", "remaining_time": "0:59:48", "throughput": 10099.13, "total_tokens": 20284032}
{"current_steps": 21150, "total_steps": 58920, "loss": 0.0006, "lr": 1.6185610917324102e-06, "epoch": 1.794806517311609, "percentage": 35.9, "elapsed_time": "0:33:28", "remaining_time": "0:59:47", "throughput": 10099.82, "total_tokens": 20289536}
{"current_steps": 21155, "total_steps": 58920, "loss": 0.0222, "lr": 1.618328313534681e-06, "epoch": 1.7952308214528174, "percentage": 35.9, "elapsed_time": "0:33:29", "remaining_time": "0:59:46", "throughput": 10100.29, "total_tokens": 20294400}
{"current_steps": 21160, "total_steps": 58920, "loss": 0.0005, "lr": 1.6180954810808747e-06, "epoch": 1.7956551255940258, "percentage": 35.91, "elapsed_time": "0:33:29", "remaining_time": "0:59:46", "throughput": 10101.09, "total_tokens": 20300160}
{"current_steps": 21165, "total_steps": 58920, "loss": 0.0349, "lr": 1.6178625943914214e-06, "epoch": 1.7960794297352343, "percentage": 35.92, "elapsed_time": "0:33:30", "remaining_time": "0:59:45", "throughput": 10101.48, "total_tokens": 20304768}
{"current_steps": 21170, "total_steps": 58920, "loss": 0.0327, "lr": 1.6176296534867567e-06, "epoch": 1.7965037338764427, "percentage": 35.93, "elapsed_time": "0:33:30", "remaining_time": "0:59:45", "throughput": 10102.41, "total_tokens": 20310912}
{"current_steps": 21175, "total_steps": 58920, "loss": 0.0227, "lr": 1.6173966583873193e-06, "epoch": 1.796928038017651, "percentage": 35.94, "elapsed_time": "0:33:30", "remaining_time": "0:59:44", "throughput": 10102.88, "total_tokens": 20315776}
{"current_steps": 21180, "total_steps": 58920, "loss": 0.0465, "lr": 1.6171636091135547e-06, "epoch": 1.7973523421588595, "percentage": 35.95, "elapsed_time": "0:33:31", "remaining_time": "0:59:43", "throughput": 10103.43, "total_tokens": 20320832}
{"current_steps": 21185, "total_steps": 58920, "loss": 0.0308, "lr": 1.6169305056859113e-06, "epoch": 1.797776646300068, "percentage": 35.96, "elapsed_time": "0:33:31", "remaining_time": "0:59:43", "throughput": 10104.09, "total_tokens": 20326144}
{"current_steps": 21190, "total_steps": 58920, "loss": 0.0239, "lr": 1.6166973481248438e-06, "epoch": 1.7982009504412764, "percentage": 35.96, "elapsed_time": "0:33:32", "remaining_time": "0:59:42", "throughput": 10104.36, "total_tokens": 20330496}
{"current_steps": 21195, "total_steps": 58920, "loss": 0.0018, "lr": 1.6164641364508102e-06, "epoch": 1.7986252545824848, "percentage": 35.97, "elapsed_time": "0:33:32", "remaining_time": "0:59:41", "throughput": 10104.79, "total_tokens": 20335232}
{"current_steps": 21200, "total_steps": 58920, "loss": 0.013, "lr": 1.6162308706842743e-06, "epoch": 1.7990495587236932, "percentage": 35.98, "elapsed_time": "0:33:32", "remaining_time": "0:59:41", "throughput": 10105.22, "total_tokens": 20339968}
{"current_steps": 21205, "total_steps": 58920, "loss": 0.0342, "lr": 1.6159975508457047e-06, "epoch": 1.7994738628649016, "percentage": 35.99, "elapsed_time": "0:33:33", "remaining_time": "0:59:40", "throughput": 10105.49, "total_tokens": 20344320}
{"current_steps": 21210, "total_steps": 58920, "loss": 0.0003, "lr": 1.6157641769555742e-06, "epoch": 1.79989816700611, "percentage": 36.0, "elapsed_time": "0:33:33", "remaining_time": "0:59:39", "throughput": 10105.8, "total_tokens": 20348736}
{"current_steps": 21215, "total_steps": 58920, "loss": 0.0689, "lr": 1.61553074903436e-06, "epoch": 1.8003224711473185, "percentage": 36.01, "elapsed_time": "0:33:33", "remaining_time": "0:59:39", "throughput": 10106.35, "total_tokens": 20353728}
{"current_steps": 21220, "total_steps": 58920, "loss": 0.0726, "lr": 1.6152972671025451e-06, "epoch": 1.800746775288527, "percentage": 36.01, "elapsed_time": "0:33:34", "remaining_time": "0:59:38", "throughput": 10106.95, "total_tokens": 20358912}
{"current_steps": 21225, "total_steps": 58920, "loss": 0.0816, "lr": 1.6150637311806165e-06, "epoch": 1.8011710794297353, "percentage": 36.02, "elapsed_time": "0:33:34", "remaining_time": "0:59:38", "throughput": 10107.36, "total_tokens": 20363584}
{"current_steps": 21230, "total_steps": 58920, "loss": 0.0773, "lr": 1.6148301412890662e-06, "epoch": 1.8015953835709437, "percentage": 36.03, "elapsed_time": "0:33:35", "remaining_time": "0:59:37", "throughput": 10107.73, "total_tokens": 20368192}
{"current_steps": 21235, "total_steps": 58920, "loss": 0.134, "lr": 1.614596497448391e-06, "epoch": 1.8020196877121522, "percentage": 36.04, "elapsed_time": "0:33:35", "remaining_time": "0:59:36", "throughput": 10108.15, "total_tokens": 20372928}
{"current_steps": 21240, "total_steps": 58920, "loss": 0.0845, "lr": 1.6143627996790921e-06, "epoch": 1.8024439918533606, "percentage": 36.05, "elapsed_time": "0:33:35", "remaining_time": "0:59:36", "throughput": 10108.83, "total_tokens": 20378304}
{"current_steps": 21245, "total_steps": 58920, "loss": 0.0307, "lr": 1.614129048001675e-06, "epoch": 1.802868295994569, "percentage": 36.06, "elapsed_time": "0:33:36", "remaining_time": "0:59:35", "throughput": 10109.48, "total_tokens": 20383616}
{"current_steps": 21250, "total_steps": 58920, "loss": 0.0351, "lr": 1.613895242436652e-06, "epoch": 1.8032926001357774, "percentage": 36.07, "elapsed_time": "0:33:36", "remaining_time": "0:59:34", "throughput": 10109.84, "total_tokens": 20388160}
{"current_steps": 21255, "total_steps": 58920, "loss": 0.0249, "lr": 1.6136613830045379e-06, "epoch": 1.8037169042769858, "percentage": 36.07, "elapsed_time": "0:33:37", "remaining_time": "0:59:34", "throughput": 10110.19, "total_tokens": 20392640}
{"current_steps": 21260, "total_steps": 58920, "loss": 0.0713, "lr": 1.6134274697258527e-06, "epoch": 1.8041412084181943, "percentage": 36.08, "elapsed_time": "0:33:37", "remaining_time": "0:59:33", "throughput": 10111.12, "total_tokens": 20398720}
{"current_steps": 21265, "total_steps": 58920, "loss": 0.0753, "lr": 1.6131935026211223e-06, "epoch": 1.8045655125594027, "percentage": 36.09, "elapsed_time": "0:33:37", "remaining_time": "0:59:33", "throughput": 10111.58, "total_tokens": 20403584}
{"current_steps": 21270, "total_steps": 58920, "loss": 0.0281, "lr": 1.6129594817108755e-06, "epoch": 1.804989816700611, "percentage": 36.1, "elapsed_time": "0:33:38", "remaining_time": "0:59:32", "throughput": 10112.15, "total_tokens": 20408640}
{"current_steps": 21275, "total_steps": 58920, "loss": 0.0368, "lr": 1.6127254070156474e-06, "epoch": 1.8054141208418195, "percentage": 36.11, "elapsed_time": "0:33:38", "remaining_time": "0:59:31", "throughput": 10112.76, "total_tokens": 20413824}
{"current_steps": 21280, "total_steps": 58920, "loss": 0.0625, "lr": 1.6124912785559773e-06, "epoch": 1.805838424983028, "percentage": 36.12, "elapsed_time": "0:33:39", "remaining_time": "0:59:31", "throughput": 10113.25, "total_tokens": 20418688}
{"current_steps": 21285, "total_steps": 58920, "loss": 0.0231, "lr": 1.6122570963524085e-06, "epoch": 1.8062627291242364, "percentage": 36.13, "elapsed_time": "0:33:39", "remaining_time": "0:59:30", "throughput": 10113.51, "total_tokens": 20423040}
{"current_steps": 21290, "total_steps": 58920, "loss": 0.002, "lr": 1.6120228604254902e-06, "epoch": 1.8066870332654448, "percentage": 36.13, "elapsed_time": "0:33:39", "remaining_time": "0:59:29", "throughput": 10113.84, "total_tokens": 20427456}
{"current_steps": 21295, "total_steps": 58920, "loss": 0.0843, "lr": 1.6117885707957756e-06, "epoch": 1.8071113374066532, "percentage": 36.14, "elapsed_time": "0:33:40", "remaining_time": "0:59:29", "throughput": 10114.2, "total_tokens": 20432064}
{"current_steps": 21300, "total_steps": 58920, "loss": 0.0018, "lr": 1.6115542274838227e-06, "epoch": 1.8075356415478616, "percentage": 36.15, "elapsed_time": "0:33:40", "remaining_time": "0:59:28", "throughput": 10114.46, "total_tokens": 20436416}
{"current_steps": 21305, "total_steps": 58920, "loss": 0.0436, "lr": 1.6113198305101947e-06, "epoch": 1.80795994568907, "percentage": 36.16, "elapsed_time": "0:33:40", "remaining_time": "0:59:27", "throughput": 10114.75, "total_tokens": 20440768}
{"current_steps": 21310, "total_steps": 58920, "loss": 0.0347, "lr": 1.6110853798954584e-06, "epoch": 1.8083842498302785, "percentage": 36.17, "elapsed_time": "0:33:41", "remaining_time": "0:59:27", "throughput": 10115.08, "total_tokens": 20445248}
{"current_steps": 21315, "total_steps": 58920, "loss": 0.0272, "lr": 1.6108508756601865e-06, "epoch": 1.8088085539714869, "percentage": 36.18, "elapsed_time": "0:33:41", "remaining_time": "0:59:26", "throughput": 10115.46, "total_tokens": 20449856}
{"current_steps": 21320, "total_steps": 58920, "loss": 0.04, "lr": 1.6106163178249553e-06, "epoch": 1.8092328581126953, "percentage": 36.18, "elapsed_time": "0:33:42", "remaining_time": "0:59:26", "throughput": 10116.03, "total_tokens": 20454976}
{"current_steps": 21325, "total_steps": 58920, "loss": 0.0274, "lr": 1.6103817064103472e-06, "epoch": 1.8096571622539037, "percentage": 36.19, "elapsed_time": "0:33:42", "remaining_time": "0:59:25", "throughput": 10116.73, "total_tokens": 20460416}
{"current_steps": 21330, "total_steps": 58920, "loss": 0.0867, "lr": 1.6101470414369482e-06, "epoch": 1.8100814663951121, "percentage": 36.2, "elapsed_time": "0:33:42", "remaining_time": "0:59:24", "throughput": 10117.33, "total_tokens": 20465600}
{"current_steps": 21335, "total_steps": 58920, "loss": 0.041, "lr": 1.609912322925349e-06, "epoch": 1.8105057705363206, "percentage": 36.21, "elapsed_time": "0:33:43", "remaining_time": "0:59:24", "throughput": 10117.89, "total_tokens": 20470656}
{"current_steps": 21340, "total_steps": 58920, "loss": 0.084, "lr": 1.6096775508961457e-06, "epoch": 1.810930074677529, "percentage": 36.22, "elapsed_time": "0:33:43", "remaining_time": "0:59:23", "throughput": 10118.28, "total_tokens": 20475264}
{"current_steps": 21345, "total_steps": 58920, "loss": 0.054, "lr": 1.6094427253699388e-06, "epoch": 1.8113543788187374, "percentage": 36.23, "elapsed_time": "0:33:44", "remaining_time": "0:59:22", "throughput": 10119.13, "total_tokens": 20481152}
{"current_steps": 21350, "total_steps": 58920, "loss": 0.0396, "lr": 1.6092078463673326e-06, "epoch": 1.8117786829599458, "percentage": 36.24, "elapsed_time": "0:33:44", "remaining_time": "0:59:22", "throughput": 10119.69, "total_tokens": 20486208}
{"current_steps": 21355, "total_steps": 58920, "loss": 0.0873, "lr": 1.6089729139089378e-06, "epoch": 1.8122029871011542, "percentage": 36.24, "elapsed_time": "0:33:44", "remaining_time": "0:59:21", "throughput": 10120.01, "total_tokens": 20490688}
{"current_steps": 21360, "total_steps": 58920, "loss": 0.0265, "lr": 1.6087379280153687e-06, "epoch": 1.8126272912423627, "percentage": 36.25, "elapsed_time": "0:33:45", "remaining_time": "0:59:21", "throughput": 10120.43, "total_tokens": 20495424}
{"current_steps": 21365, "total_steps": 58920, "loss": 0.0351, "lr": 1.6085028887072435e-06, "epoch": 1.813051595383571, "percentage": 36.26, "elapsed_time": "0:33:45", "remaining_time": "0:59:20", "throughput": 10120.84, "total_tokens": 20500096}
{"current_steps": 21370, "total_steps": 58920, "loss": 0.0112, "lr": 1.6082677960051874e-06, "epoch": 1.8134758995247795, "percentage": 36.27, "elapsed_time": "0:33:45", "remaining_time": "0:59:19", "throughput": 10121.26, "total_tokens": 20504832}
{"current_steps": 21375, "total_steps": 58920, "loss": 0.0312, "lr": 1.6080326499298281e-06, "epoch": 1.813900203665988, "percentage": 36.28, "elapsed_time": "0:33:46", "remaining_time": "0:59:19", "throughput": 10121.74, "total_tokens": 20509696}
{"current_steps": 21380, "total_steps": 58920, "loss": 0.0189, "lr": 1.607797450501799e-06, "epoch": 1.8143245078071963, "percentage": 36.29, "elapsed_time": "0:33:46", "remaining_time": "0:59:18", "throughput": 10122.0, "total_tokens": 20513984}
{"current_steps": 21385, "total_steps": 58920, "loss": 0.0449, "lr": 1.6075621977417381e-06, "epoch": 1.8147488119484048, "percentage": 36.29, "elapsed_time": "0:33:47", "remaining_time": "0:59:17", "throughput": 10122.58, "total_tokens": 20519104}
{"current_steps": 21390, "total_steps": 58920, "loss": 0.0596, "lr": 1.6073268916702884e-06, "epoch": 1.8151731160896132, "percentage": 36.3, "elapsed_time": "0:33:47", "remaining_time": "0:59:17", "throughput": 10123.28, "total_tokens": 20524544}
{"current_steps": 21395, "total_steps": 58920, "loss": 0.0008, "lr": 1.6070915323080962e-06, "epoch": 1.8155974202308216, "percentage": 36.31, "elapsed_time": "0:33:47", "remaining_time": "0:59:16", "throughput": 10123.79, "total_tokens": 20529536}
{"current_steps": 21400, "total_steps": 58920, "loss": 0.0668, "lr": 1.6068561196758141e-06, "epoch": 1.81602172437203, "percentage": 36.32, "elapsed_time": "0:33:48", "remaining_time": "0:59:16", "throughput": 10124.1, "total_tokens": 20533952}
{"current_steps": 21405, "total_steps": 58920, "loss": 0.0336, "lr": 1.6066206537940987e-06, "epoch": 1.8164460285132384, "percentage": 36.33, "elapsed_time": "0:33:48", "remaining_time": "0:59:15", "throughput": 10124.53, "total_tokens": 20538688}
{"current_steps": 21410, "total_steps": 58920, "loss": 0.074, "lr": 1.606385134683611e-06, "epoch": 1.8168703326544469, "percentage": 36.34, "elapsed_time": "0:33:48", "remaining_time": "0:59:14", "throughput": 10124.96, "total_tokens": 20543424}
{"current_steps": 21415, "total_steps": 58920, "loss": 0.0603, "lr": 1.6061495623650167e-06, "epoch": 1.8172946367956553, "percentage": 36.35, "elapsed_time": "0:33:49", "remaining_time": "0:59:14", "throughput": 10125.45, "total_tokens": 20548352}
{"current_steps": 21420, "total_steps": 58920, "loss": 0.061, "lr": 1.6059139368589874e-06, "epoch": 1.8177189409368637, "percentage": 36.35, "elapsed_time": "0:33:49", "remaining_time": "0:59:13", "throughput": 10125.94, "total_tokens": 20553280}
{"current_steps": 21425, "total_steps": 58920, "loss": 0.0214, "lr": 1.6056782581861974e-06, "epoch": 1.8181432450780721, "percentage": 36.36, "elapsed_time": "0:33:50", "remaining_time": "0:59:12", "throughput": 10126.36, "total_tokens": 20558016}
{"current_steps": 21430, "total_steps": 58920, "loss": 0.0225, "lr": 1.605442526367327e-06, "epoch": 1.8185675492192805, "percentage": 36.37, "elapsed_time": "0:33:50", "remaining_time": "0:59:12", "throughput": 10126.64, "total_tokens": 20562368}
{"current_steps": 21435, "total_steps": 58920, "loss": 0.0605, "lr": 1.605206741423061e-06, "epoch": 1.818991853360489, "percentage": 36.38, "elapsed_time": "0:33:50", "remaining_time": "0:59:11", "throughput": 10127.12, "total_tokens": 20567232}
{"current_steps": 21440, "total_steps": 58920, "loss": 0.0239, "lr": 1.6049709033740886e-06, "epoch": 1.8194161575016972, "percentage": 36.39, "elapsed_time": "0:33:51", "remaining_time": "0:59:10", "throughput": 10127.79, "total_tokens": 20572608}
{"current_steps": 21445, "total_steps": 58920, "loss": 0.0772, "lr": 1.6047350122411037e-06, "epoch": 1.8198404616429056, "percentage": 36.4, "elapsed_time": "0:33:51", "remaining_time": "0:59:10", "throughput": 10128.09, "total_tokens": 20577024}
{"current_steps": 21450, "total_steps": 58920, "loss": 0.0496, "lr": 1.6044990680448047e-06, "epoch": 1.820264765784114, "percentage": 36.41, "elapsed_time": "0:33:52", "remaining_time": "0:59:09", "throughput": 10128.41, "total_tokens": 20581504}
{"current_steps": 21455, "total_steps": 58920, "loss": 0.047, "lr": 1.604263070805895e-06, "epoch": 1.8206890699253224, "percentage": 36.41, "elapsed_time": "0:33:52", "remaining_time": "0:59:09", "throughput": 10128.77, "total_tokens": 20586048}
{"current_steps": 21460, "total_steps": 58920, "loss": 0.0666, "lr": 1.6040270205450826e-06, "epoch": 1.8211133740665308, "percentage": 36.42, "elapsed_time": "0:33:52", "remaining_time": "0:59:08", "throughput": 10129.28, "total_tokens": 20591040}
{"current_steps": 21465, "total_steps": 58920, "loss": 0.0845, "lr": 1.6037909172830799e-06, "epoch": 1.8215376782077393, "percentage": 36.43, "elapsed_time": "0:33:53", "remaining_time": "0:59:07", "throughput": 10129.7, "total_tokens": 20595712}
{"current_steps": 21470, "total_steps": 58920, "loss": 0.057, "lr": 1.6035547610406041e-06, "epoch": 1.8219619823489477, "percentage": 36.44, "elapsed_time": "0:33:53", "remaining_time": "0:59:07", "throughput": 10130.3, "total_tokens": 20600960}
{"current_steps": 21475, "total_steps": 58920, "loss": 0.0388, "lr": 1.6033185518383776e-06, "epoch": 1.822386286490156, "percentage": 36.45, "elapsed_time": "0:33:53", "remaining_time": "0:59:06", "throughput": 10130.9, "total_tokens": 20606144}
{"current_steps": 21480, "total_steps": 58920, "loss": 0.0458, "lr": 1.603082289697126e-06, "epoch": 1.8228105906313645, "percentage": 36.46, "elapsed_time": "0:33:54", "remaining_time": "0:59:05", "throughput": 10131.47, "total_tokens": 20611264}
{"current_steps": 21485, "total_steps": 58920, "loss": 0.0227, "lr": 1.602845974637581e-06, "epoch": 1.823234894772573, "percentage": 36.46, "elapsed_time": "0:33:54", "remaining_time": "0:59:05", "throughput": 10131.97, "total_tokens": 20616192}
{"current_steps": 21490, "total_steps": 58920, "loss": 0.0149, "lr": 1.6026096066804783e-06, "epoch": 1.8236591989137814, "percentage": 36.47, "elapsed_time": "0:33:55", "remaining_time": "0:59:04", "throughput": 10132.31, "total_tokens": 20620736}
{"current_steps": 21495, "total_steps": 58920, "loss": 0.0861, "lr": 1.6023731858465585e-06, "epoch": 1.8240835030549898, "percentage": 36.48, "elapsed_time": "0:33:55", "remaining_time": "0:59:04", "throughput": 10132.73, "total_tokens": 20625472}
{"current_steps": 21500, "total_steps": 58920, "loss": 0.0011, "lr": 1.6021367121565663e-06, "epoch": 1.8245078071961982, "percentage": 36.49, "elapsed_time": "0:33:55", "remaining_time": "0:59:03", "throughput": 10133.18, "total_tokens": 20630272}
{"current_steps": 21505, "total_steps": 58920, "loss": 0.0011, "lr": 1.6019001856312517e-06, "epoch": 1.8249321113374066, "percentage": 36.5, "elapsed_time": "0:33:56", "remaining_time": "0:59:02", "throughput": 10133.54, "total_tokens": 20634816}
{"current_steps": 21510, "total_steps": 58920, "loss": 0.0372, "lr": 1.601663606291369e-06, "epoch": 1.825356415478615, "percentage": 36.51, "elapsed_time": "0:33:56", "remaining_time": "0:59:02", "throughput": 10134.26, "total_tokens": 20640384}
{"current_steps": 21515, "total_steps": 58920, "loss": 0.1032, "lr": 1.6014269741576771e-06, "epoch": 1.8257807196198235, "percentage": 36.52, "elapsed_time": "0:33:57", "remaining_time": "0:59:01", "throughput": 10134.76, "total_tokens": 20645312}
{"current_steps": 21520, "total_steps": 58920, "loss": 0.001, "lr": 1.6011902892509397e-06, "epoch": 1.8262050237610319, "percentage": 36.52, "elapsed_time": "0:33:57", "remaining_time": "0:59:00", "throughput": 10135.15, "total_tokens": 20649920}
{"current_steps": 21525, "total_steps": 58920, "loss": 0.0007, "lr": 1.600953551591925e-06, "epoch": 1.8266293279022403, "percentage": 36.53, "elapsed_time": "0:33:57", "remaining_time": "0:59:00", "throughput": 10135.59, "total_tokens": 20654720}
{"current_steps": 21530, "total_steps": 58920, "loss": 0.0799, "lr": 1.600716761201406e-06, "epoch": 1.8270536320434487, "percentage": 36.54, "elapsed_time": "0:33:58", "remaining_time": "0:58:59", "throughput": 10136.16, "total_tokens": 20659840}
{"current_steps": 21535, "total_steps": 58920, "loss": 0.0592, "lr": 1.60047991810016e-06, "epoch": 1.8274779361846571, "percentage": 36.55, "elapsed_time": "0:33:58", "remaining_time": "0:58:59", "throughput": 10136.58, "total_tokens": 20664576}
{"current_steps": 21540, "total_steps": 58920, "loss": 0.0223, "lr": 1.6002430223089688e-06, "epoch": 1.8279022403258656, "percentage": 36.56, "elapsed_time": "0:33:58", "remaining_time": "0:58:58", "throughput": 10137.03, "total_tokens": 20669312}
{"current_steps": 21545, "total_steps": 58920, "loss": 0.0392, "lr": 1.6000060738486201e-06, "epoch": 1.828326544467074, "percentage": 36.57, "elapsed_time": "0:33:59", "remaining_time": "0:58:57", "throughput": 10137.38, "total_tokens": 20673856}
{"current_steps": 21550, "total_steps": 58920, "loss": 0.0607, "lr": 1.5997690727399044e-06, "epoch": 1.8287508486082824, "percentage": 36.58, "elapsed_time": "0:33:59", "remaining_time": "0:58:57", "throughput": 10137.74, "total_tokens": 20678400}
{"current_steps": 21555, "total_steps": 58920, "loss": 0.0709, "lr": 1.5995320190036182e-06, "epoch": 1.8291751527494908, "percentage": 36.58, "elapsed_time": "0:34:00", "remaining_time": "0:58:56", "throughput": 10138.46, "total_tokens": 20683968}
{"current_steps": 21560, "total_steps": 58920, "loss": 0.0696, "lr": 1.5992949126605619e-06, "epoch": 1.8295994568906992, "percentage": 36.59, "elapsed_time": "0:34:00", "remaining_time": "0:58:55", "throughput": 10139.0, "total_tokens": 20689024}
{"current_steps": 21565, "total_steps": 58920, "loss": 0.0471, "lr": 1.5990577537315409e-06, "epoch": 1.8300237610319077, "percentage": 36.6, "elapsed_time": "0:34:00", "remaining_time": "0:58:55", "throughput": 10139.38, "total_tokens": 20693632}
{"current_steps": 21570, "total_steps": 58920, "loss": 0.0016, "lr": 1.5988205422373647e-06, "epoch": 1.830448065173116, "percentage": 36.61, "elapsed_time": "0:34:01", "remaining_time": "0:58:54", "throughput": 10139.69, "total_tokens": 20698112}
{"current_steps": 21575, "total_steps": 58920, "loss": 0.0202, "lr": 1.598583278198848e-06, "epoch": 1.8308723693143245, "percentage": 36.62, "elapsed_time": "0:34:01", "remaining_time": "0:58:54", "throughput": 10140.45, "total_tokens": 20703744}
{"current_steps": 21580, "total_steps": 58920, "loss": 0.0817, "lr": 1.5983459616368095e-06, "epoch": 1.831296673455533, "percentage": 36.63, "elapsed_time": "0:34:02", "remaining_time": "0:58:53", "throughput": 10140.98, "total_tokens": 20708736}
{"current_steps": 21585, "total_steps": 58920, "loss": 0.0125, "lr": 1.5981085925720734e-06, "epoch": 1.8317209775967414, "percentage": 36.63, "elapsed_time": "0:34:02", "remaining_time": "0:58:52", "throughput": 10141.51, "total_tokens": 20713792}
{"current_steps": 21590, "total_steps": 58920, "loss": 0.0596, "lr": 1.597871171025468e-06, "epoch": 1.8321452817379498, "percentage": 36.64, "elapsed_time": "0:34:02", "remaining_time": "0:58:52", "throughput": 10141.93, "total_tokens": 20718528}
{"current_steps": 21595, "total_steps": 58920, "loss": 0.0566, "lr": 1.597633697017826e-06, "epoch": 1.8325695858791582, "percentage": 36.65, "elapsed_time": "0:34:03", "remaining_time": "0:58:51", "throughput": 10142.49, "total_tokens": 20723648}
{"current_steps": 21600, "total_steps": 58920, "loss": 0.0983, "lr": 1.5973961705699846e-06, "epoch": 1.8329938900203666, "percentage": 36.66, "elapsed_time": "0:34:03", "remaining_time": "0:58:50", "throughput": 10142.96, "total_tokens": 20728512}
{"current_steps": 21605, "total_steps": 58920, "loss": 0.06, "lr": 1.5971585917027862e-06, "epoch": 1.833418194161575, "percentage": 36.67, "elapsed_time": "0:34:04", "remaining_time": "0:58:50", "throughput": 10143.29, "total_tokens": 20732992}
{"current_steps": 21610, "total_steps": 58920, "loss": 0.0113, "lr": 1.5969209604370772e-06, "epoch": 1.8338424983027835, "percentage": 36.68, "elapsed_time": "0:34:04", "remaining_time": "0:58:49", "throughput": 10143.86, "total_tokens": 20738112}
{"current_steps": 21615, "total_steps": 58920, "loss": 0.0354, "lr": 1.5966832767937093e-06, "epoch": 1.8342668024439919, "percentage": 36.69, "elapsed_time": "0:34:04", "remaining_time": "0:58:49", "throughput": 10144.54, "total_tokens": 20743552}
{"current_steps": 21620, "total_steps": 58920, "loss": 0.0662, "lr": 1.5964455407935383e-06, "epoch": 1.8346911065852003, "percentage": 36.69, "elapsed_time": "0:34:05", "remaining_time": "0:58:48", "throughput": 10145.23, "total_tokens": 20748992}
{"current_steps": 21625, "total_steps": 58920, "loss": 0.0481, "lr": 1.5962077524574245e-06, "epoch": 1.8351154107264087, "percentage": 36.7, "elapsed_time": "0:34:05", "remaining_time": "0:58:47", "throughput": 10145.72, "total_tokens": 20753920}
{"current_steps": 21630, "total_steps": 58920, "loss": 0.0223, "lr": 1.595969911806233e-06, "epoch": 1.8355397148676171, "percentage": 36.71, "elapsed_time": "0:34:05", "remaining_time": "0:58:47", "throughput": 10146.19, "total_tokens": 20758784}
{"current_steps": 21635, "total_steps": 58920, "loss": 0.0706, "lr": 1.5957320188608331e-06, "epoch": 1.8359640190088256, "percentage": 36.72, "elapsed_time": "0:34:06", "remaining_time": "0:58:46", "throughput": 10146.79, "total_tokens": 20763968}
{"current_steps": 21640, "total_steps": 58920, "loss": 0.033, "lr": 1.5954940736421e-06, "epoch": 1.836388323150034, "percentage": 36.73, "elapsed_time": "0:34:06", "remaining_time": "0:58:45", "throughput": 10147.09, "total_tokens": 20768384}
{"current_steps": 21645, "total_steps": 58920, "loss": 0.0396, "lr": 1.5952560761709115e-06, "epoch": 1.8368126272912424, "percentage": 36.74, "elapsed_time": "0:34:07", "remaining_time": "0:58:45", "throughput": 10147.49, "total_tokens": 20773056}
{"current_steps": 21650, "total_steps": 58920, "loss": 0.0498, "lr": 1.5950180264681517e-06, "epoch": 1.8372369314324508, "percentage": 36.74, "elapsed_time": "0:34:07", "remaining_time": "0:58:44", "throughput": 10147.95, "total_tokens": 20777920}
{"current_steps": 21655, "total_steps": 58920, "loss": 0.0158, "lr": 1.5947799245547083e-06, "epoch": 1.8376612355736592, "percentage": 36.75, "elapsed_time": "0:34:07", "remaining_time": "0:58:44", "throughput": 10148.49, "total_tokens": 20782976}
{"current_steps": 21660, "total_steps": 58920, "loss": 0.0506, "lr": 1.5945417704514741e-06, "epoch": 1.8380855397148677, "percentage": 36.76, "elapsed_time": "0:34:08", "remaining_time": "0:58:43", "throughput": 10148.94, "total_tokens": 20787776}
{"current_steps": 21665, "total_steps": 58920, "loss": 0.0781, "lr": 1.5943035641793458e-06, "epoch": 1.838509843856076, "percentage": 36.77, "elapsed_time": "0:34:08", "remaining_time": "0:58:42", "throughput": 10149.47, "total_tokens": 20792832}
{"current_steps": 21670, "total_steps": 58920, "loss": 0.054, "lr": 1.5940653057592259e-06, "epoch": 1.8389341479972845, "percentage": 36.78, "elapsed_time": "0:34:09", "remaining_time": "0:58:42", "throughput": 10150.14, "total_tokens": 20798272}
{"current_steps": 21675, "total_steps": 58920, "loss": 0.0402, "lr": 1.59382699521202e-06, "epoch": 1.839358452138493, "percentage": 36.79, "elapsed_time": "0:34:09", "remaining_time": "0:58:41", "throughput": 10150.39, "total_tokens": 20802560}
{"current_steps": 21680, "total_steps": 58920, "loss": 0.0197, "lr": 1.5935886325586393e-06, "epoch": 1.8397827562797013, "percentage": 36.8, "elapsed_time": "0:34:09", "remaining_time": "0:58:40", "throughput": 10150.8, "total_tokens": 20807232}
{"current_steps": 21685, "total_steps": 58920, "loss": 0.0637, "lr": 1.5933502178199995e-06, "epoch": 1.8402070604209098, "percentage": 36.8, "elapsed_time": "0:34:10", "remaining_time": "0:58:40", "throughput": 10151.35, "total_tokens": 20812288}
{"current_steps": 21690, "total_steps": 58920, "loss": 0.0185, "lr": 1.5931117510170203e-06, "epoch": 1.8406313645621182, "percentage": 36.81, "elapsed_time": "0:34:10", "remaining_time": "0:58:39", "throughput": 10151.63, "total_tokens": 20816640}
{"current_steps": 21695, "total_steps": 58920, "loss": 0.0456, "lr": 1.5928732321706262e-06, "epoch": 1.8410556687033266, "percentage": 36.82, "elapsed_time": "0:34:10", "remaining_time": "0:58:39", "throughput": 10152.18, "total_tokens": 20821696}
{"current_steps": 21700, "total_steps": 58920, "loss": 0.1245, "lr": 1.5926346613017464e-06, "epoch": 1.841479972844535, "percentage": 36.83, "elapsed_time": "0:34:11", "remaining_time": "0:58:38", "throughput": 10152.85, "total_tokens": 20827072}
{"current_steps": 21705, "total_steps": 58920, "loss": 0.053, "lr": 1.5923960384313151e-06, "epoch": 1.8419042769857432, "percentage": 36.84, "elapsed_time": "0:34:11", "remaining_time": "0:58:37", "throughput": 10153.12, "total_tokens": 20831424}
{"current_steps": 21710, "total_steps": 58920, "loss": 0.045, "lr": 1.59215736358027e-06, "epoch": 1.8423285811269516, "percentage": 36.85, "elapsed_time": "0:34:12", "remaining_time": "0:58:37", "throughput": 10153.74, "total_tokens": 20836736}
{"current_steps": 21715, "total_steps": 58920, "loss": 0.0215, "lr": 1.5919186367695544e-06, "epoch": 1.84275288526816, "percentage": 36.86, "elapsed_time": "0:34:12", "remaining_time": "0:58:36", "throughput": 10154.04, "total_tokens": 20841152}
{"current_steps": 21720, "total_steps": 58920, "loss": 0.007, "lr": 1.5916798580201155e-06, "epoch": 1.8431771894093685, "percentage": 36.86, "elapsed_time": "0:34:12", "remaining_time": "0:58:36", "throughput": 10154.79, "total_tokens": 20846784}
{"current_steps": 21725, "total_steps": 58920, "loss": 0.061, "lr": 1.5914410273529052e-06, "epoch": 1.843601493550577, "percentage": 36.87, "elapsed_time": "0:34:13", "remaining_time": "0:58:35", "throughput": 10155.22, "total_tokens": 20851520}
{"current_steps": 21730, "total_steps": 58920, "loss": 0.0996, "lr": 1.5912021447888804e-06, "epoch": 1.8440257976917853, "percentage": 36.88, "elapsed_time": "0:34:13", "remaining_time": "0:58:34", "throughput": 10155.74, "total_tokens": 20856512}
{"current_steps": 21735, "total_steps": 58920, "loss": 0.0557, "lr": 1.5909632103490016e-06, "epoch": 1.8444501018329937, "percentage": 36.89, "elapsed_time": "0:34:14", "remaining_time": "0:58:34", "throughput": 10156.21, "total_tokens": 20861376}
{"current_steps": 21740, "total_steps": 58920, "loss": 0.0295, "lr": 1.590724224054235e-06, "epoch": 1.8448744059742022, "percentage": 36.9, "elapsed_time": "0:34:14", "remaining_time": "0:58:33", "throughput": 10156.55, "total_tokens": 20865920}
{"current_steps": 21745, "total_steps": 58920, "loss": 0.047, "lr": 1.5904851859255506e-06, "epoch": 1.8452987101154106, "percentage": 36.91, "elapsed_time": "0:34:14", "remaining_time": "0:58:32", "throughput": 10156.96, "total_tokens": 20870592}
{"current_steps": 21750, "total_steps": 58920, "loss": 0.024, "lr": 1.5902460959839229e-06, "epoch": 1.845723014256619, "percentage": 36.91, "elapsed_time": "0:34:15", "remaining_time": "0:58:32", "throughput": 10157.29, "total_tokens": 20875072}
{"current_steps": 21755, "total_steps": 58920, "loss": 0.0384, "lr": 1.5900069542503313e-06, "epoch": 1.8461473183978274, "percentage": 36.92, "elapsed_time": "0:34:15", "remaining_time": "0:58:31", "throughput": 10157.45, "total_tokens": 20879104}
{"current_steps": 21760, "total_steps": 58920, "loss": 0.0543, "lr": 1.5897677607457597e-06, "epoch": 1.8465716225390358, "percentage": 36.93, "elapsed_time": "0:34:15", "remaining_time": "0:58:30", "throughput": 10157.81, "total_tokens": 20883648}
{"current_steps": 21765, "total_steps": 58920, "loss": 0.0385, "lr": 1.5895285154911965e-06, "epoch": 1.8469959266802443, "percentage": 36.94, "elapsed_time": "0:34:16", "remaining_time": "0:58:30", "throughput": 10158.16, "total_tokens": 20888192}
{"current_steps": 21770, "total_steps": 58920, "loss": 0.0274, "lr": 1.5892892185076345e-06, "epoch": 1.8474202308214527, "percentage": 36.95, "elapsed_time": "0:34:16", "remaining_time": "0:58:29", "throughput": 10158.66, "total_tokens": 20893120}
{"current_steps": 21775, "total_steps": 58920, "loss": 0.0025, "lr": 1.5890498698160713e-06, "epoch": 1.847844534962661, "percentage": 36.96, "elapsed_time": "0:34:17", "remaining_time": "0:58:29", "throughput": 10158.85, "total_tokens": 20897280}
{"current_steps": 21780, "total_steps": 58920, "loss": 0.013, "lr": 1.588810469437509e-06, "epoch": 1.8482688391038695, "percentage": 36.97, "elapsed_time": "0:34:17", "remaining_time": "0:58:28", "throughput": 10159.56, "total_tokens": 20902848}
{"current_steps": 21785, "total_steps": 58920, "loss": 0.0468, "lr": 1.5885710173929531e-06, "epoch": 1.848693143245078, "percentage": 36.97, "elapsed_time": "0:34:17", "remaining_time": "0:58:27", "throughput": 10160.24, "total_tokens": 20908288}
{"current_steps": 21790, "total_steps": 58920, "loss": 0.0909, "lr": 1.5883315137034164e-06, "epoch": 1.8491174473862864, "percentage": 36.98, "elapsed_time": "0:34:18", "remaining_time": "0:58:27", "throughput": 10160.73, "total_tokens": 20913216}
{"current_steps": 21795, "total_steps": 58920, "loss": 0.061, "lr": 1.588091958389913e-06, "epoch": 1.8495417515274948, "percentage": 36.99, "elapsed_time": "0:34:18", "remaining_time": "0:58:26", "throughput": 10161.21, "total_tokens": 20918080}
{"current_steps": 21800, "total_steps": 58920, "loss": 0.0015, "lr": 1.5878523514734634e-06, "epoch": 1.8499660556687032, "percentage": 37.0, "elapsed_time": "0:34:19", "remaining_time": "0:58:25", "throughput": 10161.77, "total_tokens": 20923200}
{"current_steps": 21805, "total_steps": 58920, "loss": 0.0356, "lr": 1.5876126929750928e-06, "epoch": 1.8503903598099116, "percentage": 37.01, "elapsed_time": "0:34:19", "remaining_time": "0:58:25", "throughput": 10162.35, "total_tokens": 20928384}
{"current_steps": 21810, "total_steps": 58920, "loss": 0.0038, "lr": 1.5873729829158297e-06, "epoch": 1.85081466395112, "percentage": 37.02, "elapsed_time": "0:34:19", "remaining_time": "0:58:24", "throughput": 10162.77, "total_tokens": 20933120}
{"current_steps": 21815, "total_steps": 58920, "loss": 0.0278, "lr": 1.5871332213167083e-06, "epoch": 1.8512389680923285, "percentage": 37.02, "elapsed_time": "0:34:20", "remaining_time": "0:58:24", "throughput": 10162.94, "total_tokens": 20937216}
{"current_steps": 21820, "total_steps": 58920, "loss": 0.0579, "lr": 1.5868934081987665e-06, "epoch": 1.8516632722335369, "percentage": 37.03, "elapsed_time": "0:34:20", "remaining_time": "0:58:23", "throughput": 10163.37, "total_tokens": 20941952}
{"current_steps": 21825, "total_steps": 58920, "loss": 0.0026, "lr": 1.5866535435830468e-06, "epoch": 1.8520875763747453, "percentage": 37.04, "elapsed_time": "0:34:20", "remaining_time": "0:58:22", "throughput": 10163.87, "total_tokens": 20946816}
{"current_steps": 21830, "total_steps": 58920, "loss": 0.0422, "lr": 1.586413627490597e-06, "epoch": 1.8525118805159537, "percentage": 37.05, "elapsed_time": "0:34:21", "remaining_time": "0:58:22", "throughput": 10164.52, "total_tokens": 20952192}
{"current_steps": 21835, "total_steps": 58920, "loss": 0.0845, "lr": 1.5861736599424686e-06, "epoch": 1.8529361846571621, "percentage": 37.06, "elapsed_time": "0:34:21", "remaining_time": "0:58:21", "throughput": 10165.23, "total_tokens": 20957760}
{"current_steps": 21840, "total_steps": 58920, "loss": 0.0287, "lr": 1.585933640959718e-06, "epoch": 1.8533604887983706, "percentage": 37.07, "elapsed_time": "0:34:22", "remaining_time": "0:58:21", "throughput": 10165.88, "total_tokens": 20963136}
{"current_steps": 21845, "total_steps": 58920, "loss": 0.0022, "lr": 1.5856935705634058e-06, "epoch": 1.853784792939579, "percentage": 37.08, "elapsed_time": "0:34:22", "remaining_time": "0:58:20", "throughput": 10166.15, "total_tokens": 20967488}
{"current_steps": 21850, "total_steps": 58920, "loss": 0.0333, "lr": 1.5854534487745977e-06, "epoch": 1.8542090970807874, "percentage": 37.08, "elapsed_time": "0:34:22", "remaining_time": "0:58:19", "throughput": 10166.54, "total_tokens": 20972160}
{"current_steps": 21855, "total_steps": 58920, "loss": 0.0774, "lr": 1.5852132756143628e-06, "epoch": 1.8546334012219958, "percentage": 37.09, "elapsed_time": "0:34:23", "remaining_time": "0:58:19", "throughput": 10167.17, "total_tokens": 20977472}
{"current_steps": 21860, "total_steps": 58920, "loss": 0.0011, "lr": 1.584973051103776e-06, "epoch": 1.8550577053632042, "percentage": 37.1, "elapsed_time": "0:34:23", "remaining_time": "0:58:18", "throughput": 10167.65, "total_tokens": 20982400}
{"current_steps": 21865, "total_steps": 58920, "loss": 0.0688, "lr": 1.5847327752639158e-06, "epoch": 1.8554820095044127, "percentage": 37.11, "elapsed_time": "0:34:24", "remaining_time": "0:58:17", "throughput": 10168.27, "total_tokens": 20987712}
{"current_steps": 21870, "total_steps": 58920, "loss": 0.0684, "lr": 1.5844924481158662e-06, "epoch": 1.855906313645621, "percentage": 37.12, "elapsed_time": "0:34:24", "remaining_time": "0:58:17", "throughput": 10168.79, "total_tokens": 20992704}
{"current_steps": 21875, "total_steps": 58920, "loss": 0.041, "lr": 1.5842520696807143e-06, "epoch": 1.8563306177868295, "percentage": 37.13, "elapsed_time": "0:34:24", "remaining_time": "0:58:16", "throughput": 10168.96, "total_tokens": 20996800}
{"current_steps": 21880, "total_steps": 58920, "loss": 0.0811, "lr": 1.584011639979553e-06, "epoch": 1.856754921928038, "percentage": 37.14, "elapsed_time": "0:34:25", "remaining_time": "0:58:16", "throughput": 10169.36, "total_tokens": 21001472}
{"current_steps": 21885, "total_steps": 58920, "loss": 0.0563, "lr": 1.5837711590334786e-06, "epoch": 1.8571792260692463, "percentage": 37.14, "elapsed_time": "0:34:25", "remaining_time": "0:58:15", "throughput": 10169.77, "total_tokens": 21006208}
{"current_steps": 21890, "total_steps": 58920, "loss": 0.0275, "lr": 1.5835306268635925e-06, "epoch": 1.8576035302104548, "percentage": 37.15, "elapsed_time": "0:34:25", "remaining_time": "0:58:14", "throughput": 10169.91, "total_tokens": 21010240}
{"current_steps": 21895, "total_steps": 58920, "loss": 0.055, "lr": 1.5832900434910012e-06, "epoch": 1.8580278343516632, "percentage": 37.16, "elapsed_time": "0:34:26", "remaining_time": "0:58:14", "throughput": 10170.6, "total_tokens": 21015680}
{"current_steps": 21900, "total_steps": 58920, "loss": 0.041, "lr": 1.5830494089368142e-06, "epoch": 1.8584521384928716, "percentage": 37.17, "elapsed_time": "0:34:26", "remaining_time": "0:58:13", "throughput": 10171.11, "total_tokens": 21020672}
{"current_steps": 21905, "total_steps": 58920, "loss": 0.0181, "lr": 1.582808723222147e-06, "epoch": 1.85887644263408, "percentage": 37.18, "elapsed_time": "0:34:27", "remaining_time": "0:58:12", "throughput": 10171.58, "total_tokens": 21025472}
{"current_steps": 21910, "total_steps": 58920, "loss": 0.0013, "lr": 1.5825679863681182e-06, "epoch": 1.8593007467752884, "percentage": 37.19, "elapsed_time": "0:34:27", "remaining_time": "0:58:12", "throughput": 10171.86, "total_tokens": 21029824}
{"current_steps": 21915, "total_steps": 58920, "loss": 0.0581, "lr": 1.582327198395852e-06, "epoch": 1.8597250509164969, "percentage": 37.19, "elapsed_time": "0:34:27", "remaining_time": "0:58:11", "throughput": 10172.33, "total_tokens": 21034688}
{"current_steps": 21920, "total_steps": 58920, "loss": 0.026, "lr": 1.5820863593264768e-06, "epoch": 1.8601493550577053, "percentage": 37.2, "elapsed_time": "0:34:28", "remaining_time": "0:58:11", "throughput": 10172.45, "total_tokens": 21038656}
{"current_steps": 21925, "total_steps": 58920, "loss": 0.004, "lr": 1.581845469181125e-06, "epoch": 1.8605736591989137, "percentage": 37.21, "elapsed_time": "0:34:28", "remaining_time": "0:58:10", "throughput": 10173.11, "total_tokens": 21044032}
{"current_steps": 21930, "total_steps": 58920, "loss": 0.0253, "lr": 1.581604527980934e-06, "epoch": 1.8609979633401221, "percentage": 37.22, "elapsed_time": "0:34:28", "remaining_time": "0:58:09", "throughput": 10173.65, "total_tokens": 21049088}
{"current_steps": 21935, "total_steps": 58920, "loss": 0.0217, "lr": 1.5813635357470458e-06, "epoch": 1.8614222674813306, "percentage": 37.23, "elapsed_time": "0:34:29", "remaining_time": "0:58:09", "throughput": 10173.93, "total_tokens": 21053504}
{"current_steps": 21940, "total_steps": 58920, "loss": 0.066, "lr": 1.581122492500606e-06, "epoch": 1.861846571622539, "percentage": 37.24, "elapsed_time": "0:34:29", "remaining_time": "0:58:08", "throughput": 10174.41, "total_tokens": 21058432}
{"current_steps": 21945, "total_steps": 58920, "loss": 0.0314, "lr": 1.580881398262766e-06, "epoch": 1.8622708757637474, "percentage": 37.25, "elapsed_time": "0:34:30", "remaining_time": "0:58:07", "throughput": 10174.95, "total_tokens": 21063488}
{"current_steps": 21950, "total_steps": 58920, "loss": 0.0937, "lr": 1.5806402530546806e-06, "epoch": 1.8626951799049558, "percentage": 37.25, "elapsed_time": "0:34:30", "remaining_time": "0:58:07", "throughput": 10175.36, "total_tokens": 21068224}
{"current_steps": 21955, "total_steps": 58920, "loss": 0.0452, "lr": 1.580399056897509e-06, "epoch": 1.8631194840461642, "percentage": 37.26, "elapsed_time": "0:34:30", "remaining_time": "0:58:06", "throughput": 10175.74, "total_tokens": 21072832}
{"current_steps": 21960, "total_steps": 58920, "loss": 0.0613, "lr": 1.5801578098124159e-06, "epoch": 1.8635437881873727, "percentage": 37.27, "elapsed_time": "0:34:31", "remaining_time": "0:58:06", "throughput": 10176.24, "total_tokens": 21077824}
{"current_steps": 21965, "total_steps": 58920, "loss": 0.0523, "lr": 1.5799165118205693e-06, "epoch": 1.863968092328581, "percentage": 37.28, "elapsed_time": "0:34:31", "remaining_time": "0:58:05", "throughput": 10176.55, "total_tokens": 21082304}
{"current_steps": 21970, "total_steps": 58920, "loss": 0.0784, "lr": 1.5796751629431428e-06, "epoch": 1.8643923964697895, "percentage": 37.29, "elapsed_time": "0:34:32", "remaining_time": "0:58:04", "throughput": 10176.93, "total_tokens": 21086976}
{"current_steps": 21975, "total_steps": 58920, "loss": 0.1146, "lr": 1.579433763201314e-06, "epoch": 1.864816700610998, "percentage": 37.3, "elapsed_time": "0:34:32", "remaining_time": "0:58:04", "throughput": 10177.28, "total_tokens": 21091520}
{"current_steps": 21980, "total_steps": 58920, "loss": 0.036, "lr": 1.5791923126162642e-06, "epoch": 1.8652410047522063, "percentage": 37.3, "elapsed_time": "0:34:32", "remaining_time": "0:58:03", "throughput": 10177.65, "total_tokens": 21096128}
{"current_steps": 21985, "total_steps": 58920, "loss": 0.0273, "lr": 1.57895081120918e-06, "epoch": 1.8656653088934148, "percentage": 37.31, "elapsed_time": "0:34:33", "remaining_time": "0:58:02", "throughput": 10178.06, "total_tokens": 21100800}
{"current_steps": 21990, "total_steps": 58920, "loss": 0.0182, "lr": 1.5787092590012528e-06, "epoch": 1.8660896130346232, "percentage": 37.32, "elapsed_time": "0:34:33", "remaining_time": "0:58:02", "throughput": 10178.6, "total_tokens": 21105856}
{"current_steps": 21995, "total_steps": 58920, "loss": 0.0522, "lr": 1.5784676560136775e-06, "epoch": 1.8665139171758316, "percentage": 37.33, "elapsed_time": "0:34:33", "remaining_time": "0:58:01", "throughput": 10179.1, "total_tokens": 21110784}
{"current_steps": 22000, "total_steps": 58920, "loss": 0.0229, "lr": 1.5782260022676534e-06, "epoch": 1.86693822131704, "percentage": 37.34, "elapsed_time": "0:34:34", "remaining_time": "0:58:01", "throughput": 10179.81, "total_tokens": 21116352}
{"current_steps": 22005, "total_steps": 58920, "loss": 0.024, "lr": 1.5779842977843858e-06, "epoch": 1.8673625254582484, "percentage": 37.35, "elapsed_time": "0:34:34", "remaining_time": "0:58:00", "throughput": 10180.16, "total_tokens": 21120896}
{"current_steps": 22010, "total_steps": 58920, "loss": 0.0009, "lr": 1.5777425425850828e-06, "epoch": 1.8677868295994569, "percentage": 37.36, "elapsed_time": "0:34:35", "remaining_time": "0:57:59", "throughput": 10180.52, "total_tokens": 21125504}
{"current_steps": 22015, "total_steps": 58920, "loss": 0.0008, "lr": 1.5775007366909577e-06, "epoch": 1.8682111337406653, "percentage": 37.36, "elapsed_time": "0:34:35", "remaining_time": "0:57:59", "throughput": 10181.12, "total_tokens": 21130752}
{"current_steps": 22020, "total_steps": 58920, "loss": 0.0188, "lr": 1.5772588801232277e-06, "epoch": 1.8686354378818737, "percentage": 37.37, "elapsed_time": "0:34:35", "remaining_time": "0:57:58", "throughput": 10181.72, "total_tokens": 21135936}
{"current_steps": 22025, "total_steps": 58920, "loss": 0.0426, "lr": 1.577016972903115e-06, "epoch": 1.8690597420230821, "percentage": 37.38, "elapsed_time": "0:34:36", "remaining_time": "0:57:58", "throughput": 10182.15, "total_tokens": 21140736}
{"current_steps": 22030, "total_steps": 58920, "loss": 0.0162, "lr": 1.5767750150518467e-06, "epoch": 1.8694840461642905, "percentage": 37.39, "elapsed_time": "0:34:36", "remaining_time": "0:57:57", "throughput": 10182.52, "total_tokens": 21145408}
{"current_steps": 22035, "total_steps": 58920, "loss": 0.0424, "lr": 1.576533006590653e-06, "epoch": 1.869908350305499, "percentage": 37.4, "elapsed_time": "0:34:37", "remaining_time": "0:57:56", "throughput": 10183.01, "total_tokens": 21150336}
{"current_steps": 22040, "total_steps": 58920, "loss": 0.0014, "lr": 1.5762909475407695e-06, "epoch": 1.8703326544467074, "percentage": 37.41, "elapsed_time": "0:34:37", "remaining_time": "0:57:56", "throughput": 10183.35, "total_tokens": 21154816}
{"current_steps": 22045, "total_steps": 58920, "loss": 0.104, "lr": 1.5760488379234364e-06, "epoch": 1.8707569585879158, "percentage": 37.42, "elapsed_time": "0:34:37", "remaining_time": "0:57:55", "throughput": 10183.76, "total_tokens": 21159552}
{"current_steps": 22050, "total_steps": 58920, "loss": 0.0845, "lr": 1.5758066777598974e-06, "epoch": 1.8711812627291242, "percentage": 37.42, "elapsed_time": "0:34:38", "remaining_time": "0:57:54", "throughput": 10184.31, "total_tokens": 21164608}
{"current_steps": 22055, "total_steps": 58920, "loss": 0.0721, "lr": 1.5755644670714012e-06, "epoch": 1.8716055668703326, "percentage": 37.43, "elapsed_time": "0:34:38", "remaining_time": "0:57:54", "throughput": 10184.76, "total_tokens": 21169472}
{"current_steps": 22060, "total_steps": 58920, "loss": 0.0516, "lr": 1.5753222058792015e-06, "epoch": 1.872029871011541, "percentage": 37.44, "elapsed_time": "0:34:38", "remaining_time": "0:57:53", "throughput": 10185.12, "total_tokens": 21174080}
{"current_steps": 22065, "total_steps": 58920, "loss": 0.0605, "lr": 1.575079894204555e-06, "epoch": 1.8724541751527495, "percentage": 37.45, "elapsed_time": "0:34:39", "remaining_time": "0:57:53", "throughput": 10185.55, "total_tokens": 21178880}
{"current_steps": 22070, "total_steps": 58920, "loss": 0.0294, "lr": 1.5748375320687242e-06, "epoch": 1.872878479293958, "percentage": 37.46, "elapsed_time": "0:34:39", "remaining_time": "0:57:52", "throughput": 10185.9, "total_tokens": 21183488}
{"current_steps": 22075, "total_steps": 58920, "loss": 0.0014, "lr": 1.5745951194929754e-06, "epoch": 1.8733027834351663, "percentage": 37.47, "elapsed_time": "0:34:40", "remaining_time": "0:57:51", "throughput": 10186.22, "total_tokens": 21187968}
{"current_steps": 22080, "total_steps": 58920, "loss": 0.0333, "lr": 1.5743526564985796e-06, "epoch": 1.8737270875763747, "percentage": 37.47, "elapsed_time": "0:34:40", "remaining_time": "0:57:51", "throughput": 10186.52, "total_tokens": 21192448}
{"current_steps": 22085, "total_steps": 58920, "loss": 0.0558, "lr": 1.5741101431068119e-06, "epoch": 1.8741513917175832, "percentage": 37.48, "elapsed_time": "0:34:40", "remaining_time": "0:57:50", "throughput": 10186.93, "total_tokens": 21197184}
{"current_steps": 22090, "total_steps": 58920, "loss": 0.0297, "lr": 1.5738675793389516e-06, "epoch": 1.8745756958587916, "percentage": 37.49, "elapsed_time": "0:34:41", "remaining_time": "0:57:49", "throughput": 10187.2, "total_tokens": 21201536}
{"current_steps": 22095, "total_steps": 58920, "loss": 0.0567, "lr": 1.5736249652162834e-06, "epoch": 1.875, "percentage": 37.5, "elapsed_time": "0:34:41", "remaining_time": "0:57:49", "throughput": 10187.87, "total_tokens": 21206976}
{"current_steps": 22100, "total_steps": 58920, "loss": 0.0009, "lr": 1.5733823007600954e-06, "epoch": 1.8754243041412084, "percentage": 37.51, "elapsed_time": "0:34:41", "remaining_time": "0:57:48", "throughput": 10188.4, "total_tokens": 21212096}
{"current_steps": 22105, "total_steps": 58920, "loss": 0.0276, "lr": 1.573139585991681e-06, "epoch": 1.8758486082824168, "percentage": 37.52, "elapsed_time": "0:34:42", "remaining_time": "0:57:48", "throughput": 10188.69, "total_tokens": 21216512}
{"current_steps": 22110, "total_steps": 58920, "loss": 0.0294, "lr": 1.5728968209323371e-06, "epoch": 1.8762729124236253, "percentage": 37.53, "elapsed_time": "0:34:42", "remaining_time": "0:57:47", "throughput": 10189.06, "total_tokens": 21221184}
{"current_steps": 22115, "total_steps": 58920, "loss": 0.0318, "lr": 1.5726540056033654e-06, "epoch": 1.8766972165648337, "percentage": 37.53, "elapsed_time": "0:34:43", "remaining_time": "0:57:46", "throughput": 10189.53, "total_tokens": 21226048}
{"current_steps": 22120, "total_steps": 58920, "loss": 0.0591, "lr": 1.5724111400260727e-06, "epoch": 1.877121520706042, "percentage": 37.54, "elapsed_time": "0:34:43", "remaining_time": "0:57:46", "throughput": 10189.87, "total_tokens": 21230592}
{"current_steps": 22125, "total_steps": 58920, "loss": 0.0918, "lr": 1.5721682242217686e-06, "epoch": 1.8775458248472505, "percentage": 37.55, "elapsed_time": "0:34:43", "remaining_time": "0:57:45", "throughput": 10190.41, "total_tokens": 21235648}
{"current_steps": 22130, "total_steps": 58920, "loss": 0.0252, "lr": 1.5719252582117691e-06, "epoch": 1.877970128988459, "percentage": 37.56, "elapsed_time": "0:34:44", "remaining_time": "0:57:45", "throughput": 10191.1, "total_tokens": 21241152}
{"current_steps": 22135, "total_steps": 58920, "loss": 0.0288, "lr": 1.5716822420173929e-06, "epoch": 1.8783944331296674, "percentage": 37.57, "elapsed_time": "0:34:44", "remaining_time": "0:57:44", "throughput": 10191.35, "total_tokens": 21245504}
{"current_steps": 22140, "total_steps": 58920, "loss": 0.0008, "lr": 1.571439175659964e-06, "epoch": 1.8788187372708758, "percentage": 37.58, "elapsed_time": "0:34:45", "remaining_time": "0:57:43", "throughput": 10192.22, "total_tokens": 21251520}
{"current_steps": 22145, "total_steps": 58920, "loss": 0.0593, "lr": 1.5711960591608108e-06, "epoch": 1.8792430414120842, "percentage": 37.58, "elapsed_time": "0:34:45", "remaining_time": "0:57:43", "throughput": 10192.51, "total_tokens": 21255936}
{"current_steps": 22150, "total_steps": 58920, "loss": 0.0438, "lr": 1.5709528925412654e-06, "epoch": 1.8796673455532926, "percentage": 37.59, "elapsed_time": "0:34:45", "remaining_time": "0:57:42", "throughput": 10192.91, "total_tokens": 21260672}
{"current_steps": 22155, "total_steps": 58920, "loss": 0.0273, "lr": 1.5707096758226654e-06, "epoch": 1.880091649694501, "percentage": 37.6, "elapsed_time": "0:34:46", "remaining_time": "0:57:41", "throughput": 10193.27, "total_tokens": 21265280}
{"current_steps": 22160, "total_steps": 58920, "loss": 0.0403, "lr": 1.5704664090263517e-06, "epoch": 1.8805159538357095, "percentage": 37.61, "elapsed_time": "0:34:46", "remaining_time": "0:57:41", "throughput": 10193.66, "total_tokens": 21269952}
{"current_steps": 22165, "total_steps": 58920, "loss": 0.0143, "lr": 1.5702230921736703e-06, "epoch": 1.8809402579769179, "percentage": 37.62, "elapsed_time": "0:34:46", "remaining_time": "0:57:40", "throughput": 10193.79, "total_tokens": 21273984}
{"current_steps": 22170, "total_steps": 58920, "loss": 0.0212, "lr": 1.5699797252859715e-06, "epoch": 1.8813645621181263, "percentage": 37.63, "elapsed_time": "0:34:47", "remaining_time": "0:57:40", "throughput": 10194.03, "total_tokens": 21278272}
{"current_steps": 22175, "total_steps": 58920, "loss": 0.0731, "lr": 1.5697363083846095e-06, "epoch": 1.8817888662593347, "percentage": 37.64, "elapsed_time": "0:34:47", "remaining_time": "0:57:39", "throughput": 10194.35, "total_tokens": 21282752}
{"current_steps": 22180, "total_steps": 58920, "loss": 0.0258, "lr": 1.5694928414909434e-06, "epoch": 1.8822131704005431, "percentage": 37.64, "elapsed_time": "0:34:48", "remaining_time": "0:57:38", "throughput": 10194.77, "total_tokens": 21287488}
{"current_steps": 22185, "total_steps": 58920, "loss": 0.0432, "lr": 1.569249324626337e-06, "epoch": 1.8826374745417516, "percentage": 37.65, "elapsed_time": "0:34:48", "remaining_time": "0:57:38", "throughput": 10195.35, "total_tokens": 21292672}
{"current_steps": 22190, "total_steps": 58920, "loss": 0.0222, "lr": 1.5690057578121572e-06, "epoch": 1.88306177868296, "percentage": 37.66, "elapsed_time": "0:34:48", "remaining_time": "0:57:37", "throughput": 10195.91, "total_tokens": 21297792}
{"current_steps": 22195, "total_steps": 58920, "loss": 0.0376, "lr": 1.5687621410697766e-06, "epoch": 1.8834860828241684, "percentage": 37.67, "elapsed_time": "0:34:49", "remaining_time": "0:57:36", "throughput": 10196.21, "total_tokens": 21302208}
{"current_steps": 22200, "total_steps": 58920, "loss": 0.0018, "lr": 1.568518474420572e-06, "epoch": 1.8839103869653768, "percentage": 37.68, "elapsed_time": "0:34:49", "remaining_time": "0:57:36", "throughput": 10196.44, "total_tokens": 21306496}
{"current_steps": 22205, "total_steps": 58920, "loss": 0.0009, "lr": 1.5682747578859235e-06, "epoch": 1.8843346911065852, "percentage": 37.69, "elapsed_time": "0:34:49", "remaining_time": "0:57:35", "throughput": 10196.87, "total_tokens": 21311232}
{"current_steps": 22210, "total_steps": 58920, "loss": 0.096, "lr": 1.5680309914872169e-06, "epoch": 1.8847589952477937, "percentage": 37.7, "elapsed_time": "0:34:50", "remaining_time": "0:57:35", "throughput": 10197.23, "total_tokens": 21315904}
{"current_steps": 22215, "total_steps": 58920, "loss": 0.0569, "lr": 1.5677871752458416e-06, "epoch": 1.885183299389002, "percentage": 37.7, "elapsed_time": "0:34:50", "remaining_time": "0:57:34", "throughput": 10197.62, "total_tokens": 21320576}
{"current_steps": 22220, "total_steps": 58920, "loss": 0.0273, "lr": 1.5675433091831917e-06, "epoch": 1.8856076035302105, "percentage": 37.71, "elapsed_time": "0:34:51", "remaining_time": "0:57:33", "throughput": 10198.23, "total_tokens": 21325888}
{"current_steps": 22225, "total_steps": 58920, "loss": 0.0005, "lr": 1.5672993933206655e-06, "epoch": 1.886031907671419, "percentage": 37.72, "elapsed_time": "0:34:51", "remaining_time": "0:57:33", "throughput": 10198.75, "total_tokens": 21330944}
{"current_steps": 22230, "total_steps": 58920, "loss": 0.0175, "lr": 1.5670554276796662e-06, "epoch": 1.8864562118126273, "percentage": 37.73, "elapsed_time": "0:34:51", "remaining_time": "0:57:32", "throughput": 10199.16, "total_tokens": 21335680}
{"current_steps": 22235, "total_steps": 58920, "loss": 0.069, "lr": 1.5668114122815998e-06, "epoch": 1.8868805159538358, "percentage": 37.74, "elapsed_time": "0:34:52", "remaining_time": "0:57:32", "throughput": 10199.53, "total_tokens": 21340352}
{"current_steps": 22240, "total_steps": 58920, "loss": 0.0008, "lr": 1.5665673471478786e-06, "epoch": 1.8873048200950442, "percentage": 37.75, "elapsed_time": "0:34:52", "remaining_time": "0:57:31", "throughput": 10199.79, "total_tokens": 21344704}
{"current_steps": 22245, "total_steps": 58920, "loss": 0.0878, "lr": 1.5663232322999184e-06, "epoch": 1.8877291242362526, "percentage": 37.75, "elapsed_time": "0:34:53", "remaining_time": "0:57:30", "throughput": 10200.04, "total_tokens": 21349056}
{"current_steps": 22250, "total_steps": 58920, "loss": 0.0953, "lr": 1.5660790677591394e-06, "epoch": 1.888153428377461, "percentage": 37.76, "elapsed_time": "0:34:53", "remaining_time": "0:57:30", "throughput": 10200.78, "total_tokens": 21354688}
{"current_steps": 22255, "total_steps": 58920, "loss": 0.0005, "lr": 1.5658348535469656e-06, "epoch": 1.8885777325186694, "percentage": 37.77, "elapsed_time": "0:34:53", "remaining_time": "0:57:29", "throughput": 10201.51, "total_tokens": 21360320}
{"current_steps": 22260, "total_steps": 58920, "loss": 0.0282, "lr": 1.5655905896848267e-06, "epoch": 1.8890020366598779, "percentage": 37.78, "elapsed_time": "0:34:54", "remaining_time": "0:57:28", "throughput": 10201.89, "total_tokens": 21364928}
{"current_steps": 22265, "total_steps": 58920, "loss": 0.0601, "lr": 1.5653462761941554e-06, "epoch": 1.8894263408010863, "percentage": 37.79, "elapsed_time": "0:34:54", "remaining_time": "0:57:28", "throughput": 10202.29, "total_tokens": 21369664}
{"current_steps": 22270, "total_steps": 58920, "loss": 0.01, "lr": 1.56510191309639e-06, "epoch": 1.8898506449422947, "percentage": 37.8, "elapsed_time": "0:34:54", "remaining_time": "0:57:27", "throughput": 10202.75, "total_tokens": 21374528}
{"current_steps": 22275, "total_steps": 58920, "loss": 0.0277, "lr": 1.5648575004129714e-06, "epoch": 1.8902749490835031, "percentage": 37.81, "elapsed_time": "0:34:55", "remaining_time": "0:57:27", "throughput": 10203.32, "total_tokens": 21379712}
{"current_steps": 22280, "total_steps": 58920, "loss": 0.0331, "lr": 1.5646130381653469e-06, "epoch": 1.8906992532247116, "percentage": 37.81, "elapsed_time": "0:34:55", "remaining_time": "0:57:26", "throughput": 10203.83, "total_tokens": 21384704}
{"current_steps": 22285, "total_steps": 58920, "loss": 0.031, "lr": 1.5643685263749666e-06, "epoch": 1.89112355736592, "percentage": 37.82, "elapsed_time": "0:34:56", "remaining_time": "0:57:25", "throughput": 10204.27, "total_tokens": 21389504}
{"current_steps": 22290, "total_steps": 58920, "loss": 0.0921, "lr": 1.564123965063286e-06, "epoch": 1.8915478615071284, "percentage": 37.83, "elapsed_time": "0:34:56", "remaining_time": "0:57:25", "throughput": 10204.57, "total_tokens": 21393920}
{"current_steps": 22295, "total_steps": 58920, "loss": 0.0202, "lr": 1.5638793542517643e-06, "epoch": 1.8919721656483368, "percentage": 37.84, "elapsed_time": "0:34:56", "remaining_time": "0:57:24", "throughput": 10205.11, "total_tokens": 21398976}
{"current_steps": 22300, "total_steps": 58920, "loss": 0.0824, "lr": 1.5636346939618647e-06, "epoch": 1.8923964697895452, "percentage": 37.85, "elapsed_time": "0:34:57", "remaining_time": "0:57:24", "throughput": 10205.54, "total_tokens": 21403776}
{"current_steps": 22305, "total_steps": 58920, "loss": 0.0174, "lr": 1.563389984215056e-06, "epoch": 1.8928207739307537, "percentage": 37.86, "elapsed_time": "0:34:57", "remaining_time": "0:57:23", "throughput": 10205.99, "total_tokens": 21408640}
{"current_steps": 22310, "total_steps": 58920, "loss": 0.037, "lr": 1.5631452250328106e-06, "epoch": 1.893245078071962, "percentage": 37.86, "elapsed_time": "0:34:58", "remaining_time": "0:57:22", "throughput": 10206.31, "total_tokens": 21413184}
{"current_steps": 22315, "total_steps": 58920, "loss": 0.0003, "lr": 1.5629004164366043e-06, "epoch": 1.8936693822131705, "percentage": 37.87, "elapsed_time": "0:34:58", "remaining_time": "0:57:22", "throughput": 10206.66, "total_tokens": 21417792}
{"current_steps": 22320, "total_steps": 58920, "loss": 0.0702, "lr": 1.5626555584479193e-06, "epoch": 1.894093686354379, "percentage": 37.88, "elapsed_time": "0:34:58", "remaining_time": "0:57:21", "throughput": 10207.31, "total_tokens": 21423232}
{"current_steps": 22325, "total_steps": 58920, "loss": 0.0094, "lr": 1.5624106510882401e-06, "epoch": 1.8945179904955873, "percentage": 37.89, "elapsed_time": "0:34:59", "remaining_time": "0:57:21", "throughput": 10207.9, "total_tokens": 21428480}
{"current_steps": 22330, "total_steps": 58920, "loss": 0.0013, "lr": 1.5621656943790571e-06, "epoch": 1.8949422946367958, "percentage": 37.9, "elapsed_time": "0:34:59", "remaining_time": "0:57:20", "throughput": 10208.34, "total_tokens": 21433344}
{"current_steps": 22335, "total_steps": 58920, "loss": 0.0007, "lr": 1.561920688341864e-06, "epoch": 1.8953665987780042, "percentage": 37.91, "elapsed_time": "0:34:59", "remaining_time": "0:57:19", "throughput": 10208.77, "total_tokens": 21438144}
{"current_steps": 22340, "total_steps": 58920, "loss": 0.0668, "lr": 1.5616756329981592e-06, "epoch": 1.8957909029192126, "percentage": 37.92, "elapsed_time": "0:35:00", "remaining_time": "0:57:19", "throughput": 10209.33, "total_tokens": 21443264}
{"current_steps": 22345, "total_steps": 58920, "loss": 0.1494, "lr": 1.561430528369446e-06, "epoch": 1.896215207060421, "percentage": 37.92, "elapsed_time": "0:35:00", "remaining_time": "0:57:18", "throughput": 10209.65, "total_tokens": 21447808}
{"current_steps": 22350, "total_steps": 58920, "loss": 0.0667, "lr": 1.5611853744772307e-06, "epoch": 1.8966395112016294, "percentage": 37.93, "elapsed_time": "0:35:01", "remaining_time": "0:57:17", "throughput": 10210.16, "total_tokens": 21452864}
{"current_steps": 22355, "total_steps": 58920, "loss": 0.0299, "lr": 1.560940171343025e-06, "epoch": 1.8970638153428379, "percentage": 37.94, "elapsed_time": "0:35:01", "remaining_time": "0:57:17", "throughput": 10210.69, "total_tokens": 21457920}
{"current_steps": 22360, "total_steps": 58920, "loss": 0.0233, "lr": 1.5606949189883442e-06, "epoch": 1.8974881194840463, "percentage": 37.95, "elapsed_time": "0:35:01", "remaining_time": "0:57:16", "throughput": 10211.02, "total_tokens": 21462464}
{"current_steps": 22365, "total_steps": 58920, "loss": 0.0204, "lr": 1.5604496174347088e-06, "epoch": 1.8979124236252547, "percentage": 37.96, "elapsed_time": "0:35:02", "remaining_time": "0:57:16", "throughput": 10211.53, "total_tokens": 21467456}
{"current_steps": 22370, "total_steps": 58920, "loss": 0.0328, "lr": 1.5602042667036433e-06, "epoch": 1.8983367277664631, "percentage": 37.97, "elapsed_time": "0:35:02", "remaining_time": "0:57:15", "throughput": 10211.98, "total_tokens": 21472320}
{"current_steps": 22375, "total_steps": 58920, "loss": 0.0708, "lr": 1.5599588668166757e-06, "epoch": 1.8987610319076715, "percentage": 37.98, "elapsed_time": "0:35:03", "remaining_time": "0:57:14", "throughput": 10212.62, "total_tokens": 21477696}
{"current_steps": 22380, "total_steps": 58920, "loss": 0.0008, "lr": 1.559713417795339e-06, "epoch": 1.89918533604888, "percentage": 37.98, "elapsed_time": "0:35:03", "remaining_time": "0:57:14", "throughput": 10212.99, "total_tokens": 21482304}
{"current_steps": 22385, "total_steps": 58920, "loss": 0.0644, "lr": 1.5594679196611713e-06, "epoch": 1.8996096401900884, "percentage": 37.99, "elapsed_time": "0:35:03", "remaining_time": "0:57:13", "throughput": 10213.65, "total_tokens": 21487744}
{"current_steps": 22390, "total_steps": 58920, "loss": 0.0863, "lr": 1.5592223724357134e-06, "epoch": 1.9000339443312968, "percentage": 38.0, "elapsed_time": "0:35:04", "remaining_time": "0:57:13", "throughput": 10214.34, "total_tokens": 21493248}
{"current_steps": 22395, "total_steps": 58920, "loss": 0.0331, "lr": 1.5589767761405112e-06, "epoch": 1.9004582484725052, "percentage": 38.01, "elapsed_time": "0:35:04", "remaining_time": "0:57:12", "throughput": 10214.7, "total_tokens": 21497856}
{"current_steps": 22400, "total_steps": 58920, "loss": 0.0678, "lr": 1.5587311307971152e-06, "epoch": 1.9008825526137136, "percentage": 38.02, "elapsed_time": "0:35:04", "remaining_time": "0:57:11", "throughput": 10215.13, "total_tokens": 21502656}
{"current_steps": 22405, "total_steps": 58920, "loss": 0.0235, "lr": 1.5584854364270798e-06, "epoch": 1.901306856754922, "percentage": 38.03, "elapsed_time": "0:35:05", "remaining_time": "0:57:11", "throughput": 10215.52, "total_tokens": 21507392}
{"current_steps": 22410, "total_steps": 58920, "loss": 0.0532, "lr": 1.5582396930519636e-06, "epoch": 1.9017311608961305, "percentage": 38.03, "elapsed_time": "0:35:05", "remaining_time": "0:57:10", "throughput": 10216.09, "total_tokens": 21512576}
{"current_steps": 22415, "total_steps": 58920, "loss": 0.0167, "lr": 1.55799390069333e-06, "epoch": 1.902155465037339, "percentage": 38.04, "elapsed_time": "0:35:06", "remaining_time": "0:57:10", "throughput": 10216.39, "total_tokens": 21517056}
{"current_steps": 22420, "total_steps": 58920, "loss": 0.0449, "lr": 1.5577480593727463e-06, "epoch": 1.9025797691785473, "percentage": 38.05, "elapsed_time": "0:35:06", "remaining_time": "0:57:09", "throughput": 10216.72, "total_tokens": 21521600}
{"current_steps": 22425, "total_steps": 58920, "loss": 0.0499, "lr": 1.557502169111784e-06, "epoch": 1.9030040733197557, "percentage": 38.06, "elapsed_time": "0:35:06", "remaining_time": "0:57:08", "throughput": 10217.12, "total_tokens": 21526336}
{"current_steps": 22430, "total_steps": 58920, "loss": 0.0345, "lr": 1.5572562299320192e-06, "epoch": 1.9034283774609642, "percentage": 38.07, "elapsed_time": "0:35:07", "remaining_time": "0:57:08", "throughput": 10217.56, "total_tokens": 21531136}
{"current_steps": 22435, "total_steps": 58920, "loss": 0.0023, "lr": 1.5570102418550324e-06, "epoch": 1.9038526816021726, "percentage": 38.08, "elapsed_time": "0:35:07", "remaining_time": "0:57:07", "throughput": 10217.99, "total_tokens": 21536000}
{"current_steps": 22440, "total_steps": 58920, "loss": 0.1112, "lr": 1.5567642049024078e-06, "epoch": 1.904276985743381, "percentage": 38.09, "elapsed_time": "0:35:08", "remaining_time": "0:57:06", "throughput": 10218.58, "total_tokens": 21541248}
{"current_steps": 22445, "total_steps": 58920, "loss": 0.0445, "lr": 1.5565181190957342e-06, "epoch": 1.9047012898845894, "percentage": 38.09, "elapsed_time": "0:35:08", "remaining_time": "0:57:06", "throughput": 10219.28, "total_tokens": 21546816}
{"current_steps": 22450, "total_steps": 58920, "loss": 0.003, "lr": 1.5562719844566052e-06, "epoch": 1.9051255940257978, "percentage": 38.1, "elapsed_time": "0:35:08", "remaining_time": "0:57:05", "throughput": 10219.67, "total_tokens": 21551488}
{"current_steps": 22455, "total_steps": 58920, "loss": 0.0201, "lr": 1.5560258010066178e-06, "epoch": 1.9055498981670063, "percentage": 38.11, "elapsed_time": "0:35:09", "remaining_time": "0:57:05", "throughput": 10220.34, "total_tokens": 21556992}
{"current_steps": 22460, "total_steps": 58920, "loss": 0.0498, "lr": 1.5557795687673744e-06, "epoch": 1.9059742023082147, "percentage": 38.12, "elapsed_time": "0:35:09", "remaining_time": "0:57:04", "throughput": 10220.95, "total_tokens": 21562304}
{"current_steps": 22465, "total_steps": 58920, "loss": 0.0744, "lr": 1.5555332877604799e-06, "epoch": 1.906398506449423, "percentage": 38.13, "elapsed_time": "0:35:10", "remaining_time": "0:57:03", "throughput": 10221.34, "total_tokens": 21567040}
{"current_steps": 22470, "total_steps": 58920, "loss": 0.0205, "lr": 1.5552869580075452e-06, "epoch": 1.9068228105906315, "percentage": 38.14, "elapsed_time": "0:35:10", "remaining_time": "0:57:03", "throughput": 10221.82, "total_tokens": 21572032}
{"current_steps": 22475, "total_steps": 58920, "loss": 0.066, "lr": 1.555040579530185e-06, "epoch": 1.90724711473184, "percentage": 38.14, "elapsed_time": "0:35:10", "remaining_time": "0:57:02", "throughput": 10222.37, "total_tokens": 21577216}
{"current_steps": 22480, "total_steps": 58920, "loss": 0.0216, "lr": 1.5547941523500178e-06, "epoch": 1.9076714188730484, "percentage": 38.15, "elapsed_time": "0:35:11", "remaining_time": "0:57:02", "throughput": 10222.79, "total_tokens": 21582016}
{"current_steps": 22485, "total_steps": 58920, "loss": 0.0598, "lr": 1.554547676488667e-06, "epoch": 1.9080957230142568, "percentage": 38.16, "elapsed_time": "0:35:11", "remaining_time": "0:57:01", "throughput": 10223.52, "total_tokens": 21587648}
{"current_steps": 22490, "total_steps": 58920, "loss": 0.0721, "lr": 1.5543011519677594e-06, "epoch": 1.908520027155465, "percentage": 38.17, "elapsed_time": "0:35:11", "remaining_time": "0:57:00", "throughput": 10223.87, "total_tokens": 21592256}
{"current_steps": 22495, "total_steps": 58920, "loss": 0.1103, "lr": 1.5540545788089271e-06, "epoch": 1.9089443312966734, "percentage": 38.18, "elapsed_time": "0:35:12", "remaining_time": "0:57:00", "throughput": 10224.34, "total_tokens": 21597184}
{"current_steps": 22500, "total_steps": 58920, "loss": 0.0441, "lr": 1.5538079570338064e-06, "epoch": 1.9093686354378818, "percentage": 38.19, "elapsed_time": "0:35:12", "remaining_time": "0:56:59", "throughput": 10224.71, "total_tokens": 21601856}
{"current_steps": 22505, "total_steps": 58920, "loss": 0.0363, "lr": 1.5535612866640364e-06, "epoch": 1.9097929395790902, "percentage": 38.2, "elapsed_time": "0:35:13", "remaining_time": "0:56:59", "throughput": 10225.24, "total_tokens": 21606976}
{"current_steps": 22510, "total_steps": 58920, "loss": 0.0248, "lr": 1.5533145677212621e-06, "epoch": 1.9102172437202987, "percentage": 38.2, "elapsed_time": "0:35:13", "remaining_time": "0:56:58", "throughput": 10225.58, "total_tokens": 21611520}
{"current_steps": 22515, "total_steps": 58920, "loss": 0.0019, "lr": 1.5530678002271328e-06, "epoch": 1.910641547861507, "percentage": 38.21, "elapsed_time": "0:35:13", "remaining_time": "0:56:57", "throughput": 10225.98, "total_tokens": 21616256}
{"current_steps": 22520, "total_steps": 58920, "loss": 0.0394, "lr": 1.5528209842033007e-06, "epoch": 1.9110658520027155, "percentage": 38.22, "elapsed_time": "0:35:14", "remaining_time": "0:56:57", "throughput": 10226.37, "total_tokens": 21620992}
{"current_steps": 22525, "total_steps": 58920, "loss": 0.0016, "lr": 1.552574119671423e-06, "epoch": 1.911490156143924, "percentage": 38.23, "elapsed_time": "0:35:14", "remaining_time": "0:56:56", "throughput": 10226.88, "total_tokens": 21626112}
{"current_steps": 22530, "total_steps": 58920, "loss": 0.0435, "lr": 1.5523272066531612e-06, "epoch": 1.9119144602851323, "percentage": 38.24, "elapsed_time": "0:35:15", "remaining_time": "0:56:56", "throughput": 10227.31, "total_tokens": 21630912}
{"current_steps": 22535, "total_steps": 58920, "loss": 0.0598, "lr": 1.5520802451701816e-06, "epoch": 1.9123387644263408, "percentage": 38.25, "elapsed_time": "0:35:15", "remaining_time": "0:56:55", "throughput": 10227.63, "total_tokens": 21635456}
{"current_steps": 22540, "total_steps": 58920, "loss": 0.0705, "lr": 1.5518332352441533e-06, "epoch": 1.9127630685675492, "percentage": 38.26, "elapsed_time": "0:35:15", "remaining_time": "0:56:54", "throughput": 10228.13, "total_tokens": 21640448}
{"current_steps": 22545, "total_steps": 58920, "loss": 0.0667, "lr": 1.5515861768967514e-06, "epoch": 1.9131873727087576, "percentage": 38.26, "elapsed_time": "0:35:16", "remaining_time": "0:56:54", "throughput": 10228.65, "total_tokens": 21645504}
{"current_steps": 22550, "total_steps": 58920, "loss": 0.0069, "lr": 1.5513390701496535e-06, "epoch": 1.913611676849966, "percentage": 38.27, "elapsed_time": "0:35:16", "remaining_time": "0:56:53", "throughput": 10228.89, "total_tokens": 21649856}
{"current_steps": 22555, "total_steps": 58920, "loss": 0.0692, "lr": 1.5510919150245433e-06, "epoch": 1.9140359809911744, "percentage": 38.28, "elapsed_time": "0:35:16", "remaining_time": "0:56:53", "throughput": 10229.13, "total_tokens": 21654144}
{"current_steps": 22560, "total_steps": 58920, "loss": 0.0009, "lr": 1.550844711543107e-06, "epoch": 1.9144602851323829, "percentage": 38.29, "elapsed_time": "0:35:17", "remaining_time": "0:56:52", "throughput": 10229.45, "total_tokens": 21658624}
{"current_steps": 22565, "total_steps": 58920, "loss": 0.0501, "lr": 1.5505974597270361e-06, "epoch": 1.9148845892735913, "percentage": 38.3, "elapsed_time": "0:35:17", "remaining_time": "0:56:51", "throughput": 10229.69, "total_tokens": 21662912}
{"current_steps": 22570, "total_steps": 58920, "loss": 0.0422, "lr": 1.5503501595980262e-06, "epoch": 1.9153088934147997, "percentage": 38.31, "elapsed_time": "0:35:18", "remaining_time": "0:56:51", "throughput": 10230.11, "total_tokens": 21667712}
{"current_steps": 22575, "total_steps": 58920, "loss": 0.0876, "lr": 1.5501028111777767e-06, "epoch": 1.9157331975560081, "percentage": 38.31, "elapsed_time": "0:35:18", "remaining_time": "0:56:50", "throughput": 10230.54, "total_tokens": 21672576}
{"current_steps": 22580, "total_steps": 58920, "loss": 0.0013, "lr": 1.5498554144879916e-06, "epoch": 1.9161575016972165, "percentage": 38.32, "elapsed_time": "0:35:18", "remaining_time": "0:56:50", "throughput": 10231.24, "total_tokens": 21678144}
{"current_steps": 22585, "total_steps": 58920, "loss": 0.0654, "lr": 1.5496079695503793e-06, "epoch": 1.916581805838425, "percentage": 38.33, "elapsed_time": "0:35:19", "remaining_time": "0:56:49", "throughput": 10231.49, "total_tokens": 21682496}
{"current_steps": 22590, "total_steps": 58920, "loss": 0.0804, "lr": 1.5493604763866518e-06, "epoch": 1.9170061099796334, "percentage": 38.34, "elapsed_time": "0:35:19", "remaining_time": "0:56:48", "throughput": 10231.77, "total_tokens": 21686912}
{"current_steps": 22595, "total_steps": 58920, "loss": 0.0025, "lr": 1.5491129350185262e-06, "epoch": 1.9174304141208418, "percentage": 38.35, "elapsed_time": "0:35:19", "remaining_time": "0:56:48", "throughput": 10232.44, "total_tokens": 21692480}
{"current_steps": 22600, "total_steps": 58920, "loss": 0.0492, "lr": 1.5488653454677228e-06, "epoch": 1.9178547182620502, "percentage": 38.36, "elapsed_time": "0:35:20", "remaining_time": "0:56:47", "throughput": 10233.04, "total_tokens": 21697792}
{"current_steps": 22605, "total_steps": 58920, "loss": 0.0972, "lr": 1.5486177077559672e-06, "epoch": 1.9182790224032586, "percentage": 38.37, "elapsed_time": "0:35:20", "remaining_time": "0:56:46", "throughput": 10233.45, "total_tokens": 21702528}
{"current_steps": 22610, "total_steps": 58920, "loss": 0.0015, "lr": 1.5483700219049887e-06, "epoch": 1.918703326544467, "percentage": 38.37, "elapsed_time": "0:35:21", "remaining_time": "0:56:46", "throughput": 10233.93, "total_tokens": 21707520}
{"current_steps": 22615, "total_steps": 58920, "loss": 0.0525, "lr": 1.5481222879365204e-06, "epoch": 1.9191276306856755, "percentage": 38.38, "elapsed_time": "0:35:21", "remaining_time": "0:56:45", "throughput": 10234.45, "total_tokens": 21712576}
{"current_steps": 22620, "total_steps": 58920, "loss": 0.0023, "lr": 1.5478745058723001e-06, "epoch": 1.919551934826884, "percentage": 38.39, "elapsed_time": "0:35:21", "remaining_time": "0:56:45", "throughput": 10234.66, "total_tokens": 21716800}
{"current_steps": 22625, "total_steps": 58920, "loss": 0.0433, "lr": 1.5476266757340706e-06, "epoch": 1.9199762389680923, "percentage": 38.4, "elapsed_time": "0:35:22", "remaining_time": "0:56:44", "throughput": 10235.03, "total_tokens": 21721472}
{"current_steps": 22630, "total_steps": 58920, "loss": 0.0229, "lr": 1.547378797543577e-06, "epoch": 1.9204005431093008, "percentage": 38.41, "elapsed_time": "0:35:22", "remaining_time": "0:56:43", "throughput": 10235.36, "total_tokens": 21726016}
{"current_steps": 22635, "total_steps": 58920, "loss": 0.0287, "lr": 1.5471308713225705e-06, "epoch": 1.9208248472505092, "percentage": 38.42, "elapsed_time": "0:35:23", "remaining_time": "0:56:43", "throughput": 10235.69, "total_tokens": 21730624}
{"current_steps": 22640, "total_steps": 58920, "loss": 0.0546, "lr": 1.5468828970928054e-06, "epoch": 1.9212491513917176, "percentage": 38.42, "elapsed_time": "0:35:23", "remaining_time": "0:56:42", "throughput": 10236.18, "total_tokens": 21735616}
{"current_steps": 22645, "total_steps": 58920, "loss": 0.0343, "lr": 1.5466348748760405e-06, "epoch": 1.921673455532926, "percentage": 38.43, "elapsed_time": "0:35:23", "remaining_time": "0:56:42", "throughput": 10236.64, "total_tokens": 21740544}
{"current_steps": 22650, "total_steps": 58920, "loss": 0.0376, "lr": 1.546386804694039e-06, "epoch": 1.9220977596741344, "percentage": 38.44, "elapsed_time": "0:35:24", "remaining_time": "0:56:41", "throughput": 10237.13, "total_tokens": 21745600}
{"current_steps": 22655, "total_steps": 58920, "loss": 0.0697, "lr": 1.5461386865685682e-06, "epoch": 1.9225220638153429, "percentage": 38.45, "elapsed_time": "0:35:24", "remaining_time": "0:56:40", "throughput": 10237.55, "total_tokens": 21750400}
{"current_steps": 22660, "total_steps": 58920, "loss": 0.0713, "lr": 1.5458905205213992e-06, "epoch": 1.9229463679565513, "percentage": 38.46, "elapsed_time": "0:35:24", "remaining_time": "0:56:40", "throughput": 10238.16, "total_tokens": 21755776}
{"current_steps": 22665, "total_steps": 58920, "loss": 0.0206, "lr": 1.5456423065743083e-06, "epoch": 1.9233706720977597, "percentage": 38.47, "elapsed_time": "0:35:25", "remaining_time": "0:56:39", "throughput": 10238.47, "total_tokens": 21760256}
{"current_steps": 22670, "total_steps": 58920, "loss": 0.0485, "lr": 1.5453940447490747e-06, "epoch": 1.9237949762389681, "percentage": 38.48, "elapsed_time": "0:35:25", "remaining_time": "0:56:39", "throughput": 10238.68, "total_tokens": 21764544}
{"current_steps": 22675, "total_steps": 58920, "loss": 0.1479, "lr": 1.545145735067483e-06, "epoch": 1.9242192803801765, "percentage": 38.48, "elapsed_time": "0:35:26", "remaining_time": "0:56:38", "throughput": 10239.07, "total_tokens": 21769280}
{"current_steps": 22680, "total_steps": 58920, "loss": 0.0145, "lr": 1.5448973775513214e-06, "epoch": 1.924643584521385, "percentage": 38.49, "elapsed_time": "0:35:26", "remaining_time": "0:56:37", "throughput": 10239.65, "total_tokens": 21774528}
{"current_steps": 22685, "total_steps": 58920, "loss": 0.0269, "lr": 1.5446489722223821e-06, "epoch": 1.9250678886625934, "percentage": 38.5, "elapsed_time": "0:35:26", "remaining_time": "0:56:37", "throughput": 10240.32, "total_tokens": 21780096}
{"current_steps": 22690, "total_steps": 58920, "loss": 0.0466, "lr": 1.544400519102462e-06, "epoch": 1.9254921928038018, "percentage": 38.51, "elapsed_time": "0:35:27", "remaining_time": "0:56:36", "throughput": 10240.63, "total_tokens": 21784640}
{"current_steps": 22695, "total_steps": 58920, "loss": 0.0011, "lr": 1.5441520182133619e-06, "epoch": 1.9259164969450102, "percentage": 38.52, "elapsed_time": "0:35:27", "remaining_time": "0:56:36", "throughput": 10241.29, "total_tokens": 21790144}
{"current_steps": 22700, "total_steps": 58920, "loss": 0.0012, "lr": 1.543903469576887e-06, "epoch": 1.9263408010862186, "percentage": 38.53, "elapsed_time": "0:35:28", "remaining_time": "0:56:35", "throughput": 10241.67, "total_tokens": 21794880}
{"current_steps": 22705, "total_steps": 58920, "loss": 0.0599, "lr": 1.543654873214846e-06, "epoch": 1.926765105227427, "percentage": 38.54, "elapsed_time": "0:35:28", "remaining_time": "0:56:34", "throughput": 10241.84, "total_tokens": 21799040}
{"current_steps": 22710, "total_steps": 58920, "loss": 0.0022, "lr": 1.543406229149053e-06, "epoch": 1.9271894093686355, "percentage": 38.54, "elapsed_time": "0:35:28", "remaining_time": "0:56:34", "throughput": 10242.31, "total_tokens": 21803968}
{"current_steps": 22715, "total_steps": 58920, "loss": 0.0215, "lr": 1.5431575374013252e-06, "epoch": 1.927613713509844, "percentage": 38.55, "elapsed_time": "0:35:29", "remaining_time": "0:56:33", "throughput": 10242.83, "total_tokens": 21809088}
{"current_steps": 22720, "total_steps": 58920, "loss": 0.0441, "lr": 1.5429087979934846e-06, "epoch": 1.9280380176510523, "percentage": 38.56, "elapsed_time": "0:35:29", "remaining_time": "0:56:33", "throughput": 10243.21, "total_tokens": 21813760}
{"current_steps": 22725, "total_steps": 58920, "loss": 0.0012, "lr": 1.5426600109473573e-06, "epoch": 1.9284623217922607, "percentage": 38.57, "elapsed_time": "0:35:29", "remaining_time": "0:56:32", "throughput": 10243.43, "total_tokens": 21818048}
{"current_steps": 22730, "total_steps": 58920, "loss": 0.0349, "lr": 1.5424111762847733e-06, "epoch": 1.9288866259334692, "percentage": 38.58, "elapsed_time": "0:35:30", "remaining_time": "0:56:31", "throughput": 10243.6, "total_tokens": 21822208}
{"current_steps": 22735, "total_steps": 58920, "loss": 0.048, "lr": 1.542162294027567e-06, "epoch": 1.9293109300746776, "percentage": 38.59, "elapsed_time": "0:35:30", "remaining_time": "0:56:31", "throughput": 10244.19, "total_tokens": 21827520}
{"current_steps": 22740, "total_steps": 58920, "loss": 0.0381, "lr": 1.5419133641975766e-06, "epoch": 1.929735234215886, "percentage": 38.59, "elapsed_time": "0:35:31", "remaining_time": "0:56:30", "throughput": 10244.45, "total_tokens": 21831936}
{"current_steps": 22745, "total_steps": 58920, "loss": 0.0323, "lr": 1.5416643868166452e-06, "epoch": 1.9301595383570944, "percentage": 38.6, "elapsed_time": "0:35:31", "remaining_time": "0:56:30", "throughput": 10244.78, "total_tokens": 21836480}
{"current_steps": 22750, "total_steps": 58920, "loss": 0.0589, "lr": 1.5414153619066195e-06, "epoch": 1.9305838424983028, "percentage": 38.61, "elapsed_time": "0:35:31", "remaining_time": "0:56:29", "throughput": 10244.97, "total_tokens": 21840704}
{"current_steps": 22755, "total_steps": 58920, "loss": 0.0381, "lr": 1.5411662894893506e-06, "epoch": 1.931008146639511, "percentage": 38.62, "elapsed_time": "0:35:32", "remaining_time": "0:56:28", "throughput": 10245.48, "total_tokens": 21845760}
{"current_steps": 22760, "total_steps": 58920, "loss": 0.0583, "lr": 1.5409171695866936e-06, "epoch": 1.9314324507807195, "percentage": 38.63, "elapsed_time": "0:35:32", "remaining_time": "0:56:28", "throughput": 10245.99, "total_tokens": 21850880}
{"current_steps": 22765, "total_steps": 58920, "loss": 0.0582, "lr": 1.5406680022205078e-06, "epoch": 1.9318567549219279, "percentage": 38.64, "elapsed_time": "0:35:33", "remaining_time": "0:56:27", "throughput": 10246.35, "total_tokens": 21855552}
{"current_steps": 22770, "total_steps": 58920, "loss": 0.0196, "lr": 1.5404187874126575e-06, "epoch": 1.9322810590631363, "percentage": 38.65, "elapsed_time": "0:35:33", "remaining_time": "0:56:27", "throughput": 10246.94, "total_tokens": 21860864}
{"current_steps": 22775, "total_steps": 58920, "loss": 0.0092, "lr": 1.5401695251850093e-06, "epoch": 1.9327053632043447, "percentage": 38.65, "elapsed_time": "0:35:33", "remaining_time": "0:56:26", "throughput": 10247.2, "total_tokens": 21865280}
{"current_steps": 22780, "total_steps": 58920, "loss": 0.0548, "lr": 1.5399202155594354e-06, "epoch": 1.9331296673455531, "percentage": 38.66, "elapsed_time": "0:35:34", "remaining_time": "0:56:25", "throughput": 10247.56, "total_tokens": 21869952}
{"current_steps": 22785, "total_steps": 58920, "loss": 0.022, "lr": 1.5396708585578123e-06, "epoch": 1.9335539714867616, "percentage": 38.67, "elapsed_time": "0:35:34", "remaining_time": "0:56:25", "throughput": 10248.37, "total_tokens": 21875968}
{"current_steps": 22790, "total_steps": 58920, "loss": 0.0874, "lr": 1.5394214542020196e-06, "epoch": 1.93397827562797, "percentage": 38.68, "elapsed_time": "0:35:34", "remaining_time": "0:56:24", "throughput": 10248.82, "total_tokens": 21880896}
{"current_steps": 22795, "total_steps": 58920, "loss": 0.0206, "lr": 1.539172002513942e-06, "epoch": 1.9344025797691784, "percentage": 38.69, "elapsed_time": "0:35:35", "remaining_time": "0:56:24", "throughput": 10249.4, "total_tokens": 21886208}
{"current_steps": 22800, "total_steps": 58920, "loss": 0.02, "lr": 1.5389225035154678e-06, "epoch": 1.9348268839103868, "percentage": 38.7, "elapsed_time": "0:35:35", "remaining_time": "0:56:23", "throughput": 10249.89, "total_tokens": 21891200}
{"current_steps": 22805, "total_steps": 58920, "loss": 0.0225, "lr": 1.5386729572284897e-06, "epoch": 1.9352511880515952, "percentage": 38.71, "elapsed_time": "0:35:36", "remaining_time": "0:56:22", "throughput": 10250.24, "total_tokens": 21895808}
{"current_steps": 22810, "total_steps": 58920, "loss": 0.0197, "lr": 1.5384233636749045e-06, "epoch": 1.9356754921928037, "percentage": 38.71, "elapsed_time": "0:35:36", "remaining_time": "0:56:22", "throughput": 10250.67, "total_tokens": 21900672}
{"current_steps": 22815, "total_steps": 58920, "loss": 0.1064, "lr": 1.5381737228766132e-06, "epoch": 1.936099796334012, "percentage": 38.72, "elapsed_time": "0:35:36", "remaining_time": "0:56:21", "throughput": 10251.15, "total_tokens": 21905664}
{"current_steps": 22820, "total_steps": 58920, "loss": 0.0009, "lr": 1.5379240348555205e-06, "epoch": 1.9365241004752205, "percentage": 38.73, "elapsed_time": "0:35:37", "remaining_time": "0:56:21", "throughput": 10251.69, "total_tokens": 21910848}
{"current_steps": 22825, "total_steps": 58920, "loss": 0.0421, "lr": 1.5376742996335361e-06, "epoch": 1.936948404616429, "percentage": 38.74, "elapsed_time": "0:35:37", "remaining_time": "0:56:20", "throughput": 10252.04, "total_tokens": 21915520}
{"current_steps": 22830, "total_steps": 58920, "loss": 0.0358, "lr": 1.5374245172325732e-06, "epoch": 1.9373727087576373, "percentage": 38.75, "elapsed_time": "0:35:38", "remaining_time": "0:56:19", "throughput": 10252.55, "total_tokens": 21920576}
{"current_steps": 22835, "total_steps": 58920, "loss": 0.044, "lr": 1.5371746876745491e-06, "epoch": 1.9377970128988458, "percentage": 38.76, "elapsed_time": "0:35:38", "remaining_time": "0:56:19", "throughput": 10253.03, "total_tokens": 21925568}
{"current_steps": 22840, "total_steps": 58920, "loss": 0.0216, "lr": 1.536924810981386e-06, "epoch": 1.9382213170400542, "percentage": 38.76, "elapsed_time": "0:35:38", "remaining_time": "0:56:18", "throughput": 10253.52, "total_tokens": 21930624}
{"current_steps": 22845, "total_steps": 58920, "loss": 0.0577, "lr": 1.536674887175009e-06, "epoch": 1.9386456211812626, "percentage": 38.77, "elapsed_time": "0:35:39", "remaining_time": "0:56:18", "throughput": 10253.65, "total_tokens": 21934656}
{"current_steps": 22850, "total_steps": 58920, "loss": 0.0011, "lr": 1.536424916277348e-06, "epoch": 1.939069925322471, "percentage": 38.78, "elapsed_time": "0:35:39", "remaining_time": "0:56:17", "throughput": 10254.14, "total_tokens": 21939584}
{"current_steps": 22855, "total_steps": 58920, "loss": 0.0625, "lr": 1.536174898310338e-06, "epoch": 1.9394942294636794, "percentage": 38.79, "elapsed_time": "0:35:39", "remaining_time": "0:56:16", "throughput": 10254.65, "total_tokens": 21944640}
{"current_steps": 22860, "total_steps": 58920, "loss": 0.0436, "lr": 1.5359248332959162e-06, "epoch": 1.9399185336048879, "percentage": 38.8, "elapsed_time": "0:35:40", "remaining_time": "0:56:16", "throughput": 10255.01, "total_tokens": 21949376}
{"current_steps": 22865, "total_steps": 58920, "loss": 0.03, "lr": 1.5356747212560253e-06, "epoch": 1.9403428377460963, "percentage": 38.81, "elapsed_time": "0:35:40", "remaining_time": "0:56:15", "throughput": 10255.51, "total_tokens": 21954432}
{"current_steps": 22870, "total_steps": 58920, "loss": 0.1197, "lr": 1.5354245622126117e-06, "epoch": 1.9407671418873047, "percentage": 38.82, "elapsed_time": "0:35:41", "remaining_time": "0:56:15", "throughput": 10255.86, "total_tokens": 21959040}
{"current_steps": 22875, "total_steps": 58920, "loss": 0.0315, "lr": 1.5351743561876255e-06, "epoch": 1.9411914460285131, "percentage": 38.82, "elapsed_time": "0:35:41", "remaining_time": "0:56:14", "throughput": 10256.36, "total_tokens": 21964160}
{"current_steps": 22880, "total_steps": 58920, "loss": 0.0483, "lr": 1.5349241032030221e-06, "epoch": 1.9416157501697215, "percentage": 38.83, "elapsed_time": "0:35:41", "remaining_time": "0:56:13", "throughput": 10256.77, "total_tokens": 21968960}
{"current_steps": 22885, "total_steps": 58920, "loss": 0.014, "lr": 1.53467380328076e-06, "epoch": 1.94204005431093, "percentage": 38.84, "elapsed_time": "0:35:42", "remaining_time": "0:56:13", "throughput": 10257.26, "total_tokens": 21974016}
{"current_steps": 22890, "total_steps": 58920, "loss": 0.0384, "lr": 1.534423456442802e-06, "epoch": 1.9424643584521384, "percentage": 38.85, "elapsed_time": "0:35:42", "remaining_time": "0:56:12", "throughput": 10257.78, "total_tokens": 21979200}
{"current_steps": 22895, "total_steps": 58920, "loss": 0.005, "lr": 1.5341730627111155e-06, "epoch": 1.9428886625933468, "percentage": 38.86, "elapsed_time": "0:35:43", "remaining_time": "0:56:12", "throughput": 10258.06, "total_tokens": 21983680}
{"current_steps": 22900, "total_steps": 58920, "loss": 0.0443, "lr": 1.5339226221076712e-06, "epoch": 1.9433129667345552, "percentage": 38.87, "elapsed_time": "0:35:43", "remaining_time": "0:56:11", "throughput": 10258.51, "total_tokens": 21988544}
{"current_steps": 22905, "total_steps": 58920, "loss": 0.0236, "lr": 1.5336721346544443e-06, "epoch": 1.9437372708757636, "percentage": 38.87, "elapsed_time": "0:35:43", "remaining_time": "0:56:10", "throughput": 10259.01, "total_tokens": 21993600}
{"current_steps": 22910, "total_steps": 58920, "loss": 0.0712, "lr": 1.5334216003734147e-06, "epoch": 1.944161575016972, "percentage": 38.88, "elapsed_time": "0:35:44", "remaining_time": "0:56:10", "throughput": 10259.38, "total_tokens": 21998336}
{"current_steps": 22915, "total_steps": 58920, "loss": 0.0459, "lr": 1.5331710192865654e-06, "epoch": 1.9445858791581805, "percentage": 38.89, "elapsed_time": "0:35:44", "remaining_time": "0:56:09", "throughput": 10259.71, "total_tokens": 22002944}
{"current_steps": 22920, "total_steps": 58920, "loss": 0.0423, "lr": 1.5329203914158844e-06, "epoch": 1.945010183299389, "percentage": 38.9, "elapsed_time": "0:35:44", "remaining_time": "0:56:09", "throughput": 10260.06, "total_tokens": 22007552}
{"current_steps": 22925, "total_steps": 58920, "loss": 0.0774, "lr": 1.532669716783363e-06, "epoch": 1.9454344874405973, "percentage": 38.91, "elapsed_time": "0:35:45", "remaining_time": "0:56:08", "throughput": 10260.39, "total_tokens": 22012160}
{"current_steps": 22930, "total_steps": 58920, "loss": 0.0184, "lr": 1.532418995410997e-06, "epoch": 1.9458587915818057, "percentage": 38.92, "elapsed_time": "0:35:45", "remaining_time": "0:56:07", "throughput": 10260.98, "total_tokens": 22017472}
{"current_steps": 22935, "total_steps": 58920, "loss": 0.0011, "lr": 1.5321682273207866e-06, "epoch": 1.9462830957230142, "percentage": 38.93, "elapsed_time": "0:35:46", "remaining_time": "0:56:07", "throughput": 10261.54, "total_tokens": 22022720}
{"current_steps": 22940, "total_steps": 58920, "loss": 0.0018, "lr": 1.5319174125347357e-06, "epoch": 1.9467073998642226, "percentage": 38.93, "elapsed_time": "0:35:46", "remaining_time": "0:56:06", "throughput": 10261.85, "total_tokens": 22027264}
{"current_steps": 22945, "total_steps": 58920, "loss": 0.0018, "lr": 1.5316665510748523e-06, "epoch": 1.947131704005431, "percentage": 38.94, "elapsed_time": "0:35:46", "remaining_time": "0:56:06", "throughput": 10262.24, "total_tokens": 22032000}
{"current_steps": 22950, "total_steps": 58920, "loss": 0.0405, "lr": 1.5314156429631483e-06, "epoch": 1.9475560081466394, "percentage": 38.95, "elapsed_time": "0:35:47", "remaining_time": "0:56:05", "throughput": 10262.74, "total_tokens": 22037056}
{"current_steps": 22955, "total_steps": 58920, "loss": 0.048, "lr": 1.5311646882216409e-06, "epoch": 1.9479803122878478, "percentage": 38.96, "elapsed_time": "0:35:47", "remaining_time": "0:56:04", "throughput": 10263.15, "total_tokens": 22041856}
{"current_steps": 22960, "total_steps": 58920, "loss": 0.0488, "lr": 1.5309136868723496e-06, "epoch": 1.9484046164290563, "percentage": 38.97, "elapsed_time": "0:35:48", "remaining_time": "0:56:04", "throughput": 10263.54, "total_tokens": 22046592}
{"current_steps": 22965, "total_steps": 58920, "loss": 0.0501, "lr": 1.530662638937299e-06, "epoch": 1.9488289205702647, "percentage": 38.98, "elapsed_time": "0:35:48", "remaining_time": "0:56:03", "throughput": 10263.98, "total_tokens": 22051456}
{"current_steps": 22970, "total_steps": 58920, "loss": 0.0235, "lr": 1.5304115444385178e-06, "epoch": 1.949253224711473, "percentage": 38.99, "elapsed_time": "0:35:48", "remaining_time": "0:56:03", "throughput": 10264.27, "total_tokens": 22055936}
{"current_steps": 22975, "total_steps": 58920, "loss": 0.1094, "lr": 1.5301604033980384e-06, "epoch": 1.9496775288526815, "percentage": 38.99, "elapsed_time": "0:35:49", "remaining_time": "0:56:02", "throughput": 10264.8, "total_tokens": 22061120}
{"current_steps": 22980, "total_steps": 58920, "loss": 0.0006, "lr": 1.5299092158378984e-06, "epoch": 1.95010183299389, "percentage": 39.0, "elapsed_time": "0:35:49", "remaining_time": "0:56:01", "throughput": 10265.18, "total_tokens": 22065856}
{"current_steps": 22985, "total_steps": 58920, "loss": 0.0257, "lr": 1.5296579817801373e-06, "epoch": 1.9505261371350984, "percentage": 39.01, "elapsed_time": "0:35:49", "remaining_time": "0:56:01", "throughput": 10265.44, "total_tokens": 22070272}
{"current_steps": 22990, "total_steps": 58920, "loss": 0.0006, "lr": 1.529406701246801e-06, "epoch": 1.9509504412763068, "percentage": 39.02, "elapsed_time": "0:35:50", "remaining_time": "0:56:00", "throughput": 10265.92, "total_tokens": 22075328}
{"current_steps": 22995, "total_steps": 58920, "loss": 0.0854, "lr": 1.529155374259938e-06, "epoch": 1.9513747454175152, "percentage": 39.03, "elapsed_time": "0:35:50", "remaining_time": "0:56:00", "throughput": 10266.01, "total_tokens": 22079296}
{"current_steps": 23000, "total_steps": 58920, "loss": 0.034, "lr": 1.5289040008416011e-06, "epoch": 1.9517990495587236, "percentage": 39.04, "elapsed_time": "0:35:51", "remaining_time": "0:55:59", "throughput": 10266.47, "total_tokens": 22084288}
{"current_steps": 23005, "total_steps": 58920, "loss": 0.0318, "lr": 1.5286525810138483e-06, "epoch": 1.952223353699932, "percentage": 39.04, "elapsed_time": "0:35:51", "remaining_time": "0:55:58", "throughput": 10266.93, "total_tokens": 22089216}
{"current_steps": 23010, "total_steps": 58920, "loss": 0.0582, "lr": 1.5284011147987399e-06, "epoch": 1.9526476578411405, "percentage": 39.05, "elapsed_time": "0:35:51", "remaining_time": "0:55:58", "throughput": 10267.27, "total_tokens": 22093824}
{"current_steps": 23015, "total_steps": 58920, "loss": 0.0121, "lr": 1.5281496022183413e-06, "epoch": 1.953071961982349, "percentage": 39.06, "elapsed_time": "0:35:52", "remaining_time": "0:55:57", "throughput": 10267.88, "total_tokens": 22099200}
{"current_steps": 23020, "total_steps": 58920, "loss": 0.0207, "lr": 1.5278980432947224e-06, "epoch": 1.9534962661235573, "percentage": 39.07, "elapsed_time": "0:35:52", "remaining_time": "0:55:57", "throughput": 10268.36, "total_tokens": 22104256}
{"current_steps": 23025, "total_steps": 58920, "loss": 0.0572, "lr": 1.5276464380499556e-06, "epoch": 1.9539205702647657, "percentage": 39.08, "elapsed_time": "0:35:53", "remaining_time": "0:55:56", "throughput": 10268.93, "total_tokens": 22109504}
{"current_steps": 23030, "total_steps": 58920, "loss": 0.0288, "lr": 1.5273947865061195e-06, "epoch": 1.9543448744059742, "percentage": 39.09, "elapsed_time": "0:35:53", "remaining_time": "0:55:55", "throughput": 10269.28, "total_tokens": 22114176}
{"current_steps": 23035, "total_steps": 58920, "loss": 0.0013, "lr": 1.5271430886852947e-06, "epoch": 1.9547691785471826, "percentage": 39.1, "elapsed_time": "0:35:53", "remaining_time": "0:55:55", "throughput": 10269.51, "total_tokens": 22118464}
{"current_steps": 23040, "total_steps": 58920, "loss": 0.077, "lr": 1.5268913446095674e-06, "epoch": 1.955193482688391, "percentage": 39.1, "elapsed_time": "0:35:54", "remaining_time": "0:55:54", "throughput": 10270.12, "total_tokens": 22123840}
{"current_steps": 23045, "total_steps": 58920, "loss": 0.012, "lr": 1.5266395543010267e-06, "epoch": 1.9556177868295994, "percentage": 39.11, "elapsed_time": "0:35:54", "remaining_time": "0:55:54", "throughput": 10270.48, "total_tokens": 22128512}
{"current_steps": 23050, "total_steps": 58920, "loss": 0.0171, "lr": 1.5263877177817667e-06, "epoch": 1.9560420909708078, "percentage": 39.12, "elapsed_time": "0:35:54", "remaining_time": "0:55:53", "throughput": 10270.75, "total_tokens": 22132928}
{"current_steps": 23055, "total_steps": 58920, "loss": 0.0109, "lr": 1.5261358350738847e-06, "epoch": 1.9564663951120163, "percentage": 39.13, "elapsed_time": "0:35:55", "remaining_time": "0:55:52", "throughput": 10271.24, "total_tokens": 22137984}
{"current_steps": 23060, "total_steps": 58920, "loss": 0.0763, "lr": 1.5258839061994828e-06, "epoch": 1.9568906992532247, "percentage": 39.14, "elapsed_time": "0:35:55", "remaining_time": "0:55:52", "throughput": 10271.68, "total_tokens": 22142848}
{"current_steps": 23065, "total_steps": 58920, "loss": 0.0573, "lr": 1.525631931180667e-06, "epoch": 1.957315003394433, "percentage": 39.15, "elapsed_time": "0:35:56", "remaining_time": "0:55:51", "throughput": 10272.09, "total_tokens": 22147648}
{"current_steps": 23070, "total_steps": 58920, "loss": 0.0554, "lr": 1.5253799100395467e-06, "epoch": 1.9577393075356415, "percentage": 39.15, "elapsed_time": "0:35:56", "remaining_time": "0:55:51", "throughput": 10272.48, "total_tokens": 22152384}
{"current_steps": 23075, "total_steps": 58920, "loss": 0.0669, "lr": 1.5251278427982369e-06, "epoch": 1.95816361167685, "percentage": 39.16, "elapsed_time": "0:35:56", "remaining_time": "0:55:50", "throughput": 10272.81, "total_tokens": 22156992}
{"current_steps": 23080, "total_steps": 58920, "loss": 0.0393, "lr": 1.5248757294788544e-06, "epoch": 1.9585879158180584, "percentage": 39.17, "elapsed_time": "0:35:57", "remaining_time": "0:55:49", "throughput": 10273.44, "total_tokens": 22162496}
{"current_steps": 23085, "total_steps": 58920, "loss": 0.0472, "lr": 1.5246235701035218e-06, "epoch": 1.9590122199592668, "percentage": 39.18, "elapsed_time": "0:35:57", "remaining_time": "0:55:49", "throughput": 10273.81, "total_tokens": 22167168}
{"current_steps": 23090, "total_steps": 58920, "loss": 0.1305, "lr": 1.5243713646943646e-06, "epoch": 1.9594365241004752, "percentage": 39.19, "elapsed_time": "0:35:58", "remaining_time": "0:55:48", "throughput": 10274.21, "total_tokens": 22171968}
{"current_steps": 23095, "total_steps": 58920, "loss": 0.047, "lr": 1.5241191132735139e-06, "epoch": 1.9598608282416836, "percentage": 39.2, "elapsed_time": "0:35:58", "remaining_time": "0:55:48", "throughput": 10274.63, "total_tokens": 22176832}
{"current_steps": 23100, "total_steps": 58920, "loss": 0.0595, "lr": 1.5238668158631032e-06, "epoch": 1.960285132382892, "percentage": 39.21, "elapsed_time": "0:35:58", "remaining_time": "0:55:47", "throughput": 10274.76, "total_tokens": 22180864}
{"current_steps": 23105, "total_steps": 58920, "loss": 0.0032, "lr": 1.5236144724852708e-06, "epoch": 1.9607094365241005, "percentage": 39.21, "elapsed_time": "0:35:59", "remaining_time": "0:55:46", "throughput": 10275.1, "total_tokens": 22185472}
{"current_steps": 23110, "total_steps": 58920, "loss": 0.0033, "lr": 1.523362083162159e-06, "epoch": 1.9611337406653089, "percentage": 39.22, "elapsed_time": "0:35:59", "remaining_time": "0:55:46", "throughput": 10275.47, "total_tokens": 22190208}
{"current_steps": 23115, "total_steps": 58920, "loss": 0.0104, "lr": 1.523109647915914e-06, "epoch": 1.9615580448065173, "percentage": 39.23, "elapsed_time": "0:35:59", "remaining_time": "0:55:45", "throughput": 10275.93, "total_tokens": 22195136}
{"current_steps": 23120, "total_steps": 58920, "loss": 0.0424, "lr": 1.522857166768686e-06, "epoch": 1.9619823489477257, "percentage": 39.24, "elapsed_time": "0:36:00", "remaining_time": "0:55:45", "throughput": 10276.18, "total_tokens": 22199488}
{"current_steps": 23125, "total_steps": 58920, "loss": 0.0356, "lr": 1.5226046397426294e-06, "epoch": 1.9624066530889341, "percentage": 39.25, "elapsed_time": "0:36:00", "remaining_time": "0:55:44", "throughput": 10276.58, "total_tokens": 22204288}
{"current_steps": 23130, "total_steps": 58920, "loss": 0.0381, "lr": 1.5223520668599023e-06, "epoch": 1.9628309572301426, "percentage": 39.26, "elapsed_time": "0:36:01", "remaining_time": "0:55:43", "throughput": 10276.89, "total_tokens": 22208832}
{"current_steps": 23135, "total_steps": 58920, "loss": 0.0578, "lr": 1.5220994481426676e-06, "epoch": 1.963255261371351, "percentage": 39.27, "elapsed_time": "0:36:01", "remaining_time": "0:55:43", "throughput": 10277.25, "total_tokens": 22213504}
{"current_steps": 23140, "total_steps": 58920, "loss": 0.0249, "lr": 1.5218467836130913e-06, "epoch": 1.9636795655125594, "percentage": 39.27, "elapsed_time": "0:36:01", "remaining_time": "0:55:42", "throughput": 10277.83, "total_tokens": 22218816}
{"current_steps": 23145, "total_steps": 58920, "loss": 0.149, "lr": 1.5215940732933442e-06, "epoch": 1.9641038696537678, "percentage": 39.28, "elapsed_time": "0:36:02", "remaining_time": "0:55:42", "throughput": 10278.27, "total_tokens": 22223680}
{"current_steps": 23150, "total_steps": 58920, "loss": 0.0041, "lr": 1.5213413172055995e-06, "epoch": 1.9645281737949762, "percentage": 39.29, "elapsed_time": "0:36:02", "remaining_time": "0:55:41", "throughput": 10278.87, "total_tokens": 22229056}
{"current_steps": 23155, "total_steps": 58920, "loss": 0.046, "lr": 1.5210885153720373e-06, "epoch": 1.9649524779361847, "percentage": 39.3, "elapsed_time": "0:36:02", "remaining_time": "0:55:40", "throughput": 10279.22, "total_tokens": 22233728}
{"current_steps": 23160, "total_steps": 58920, "loss": 0.1085, "lr": 1.520835667814839e-06, "epoch": 1.965376782077393, "percentage": 39.31, "elapsed_time": "0:36:03", "remaining_time": "0:55:40", "throughput": 10279.91, "total_tokens": 22239360}
{"current_steps": 23165, "total_steps": 58920, "loss": 0.0219, "lr": 1.5205827745561911e-06, "epoch": 1.9658010862186015, "percentage": 39.32, "elapsed_time": "0:36:03", "remaining_time": "0:55:39", "throughput": 10280.28, "total_tokens": 22244096}
{"current_steps": 23170, "total_steps": 58920, "loss": 0.0019, "lr": 1.5203298356182845e-06, "epoch": 1.96622539035981, "percentage": 39.32, "elapsed_time": "0:36:04", "remaining_time": "0:55:39", "throughput": 10280.57, "total_tokens": 22248576}
{"current_steps": 23175, "total_steps": 58920, "loss": 0.0746, "lr": 1.5200768510233136e-06, "epoch": 1.9666496945010183, "percentage": 39.33, "elapsed_time": "0:36:04", "remaining_time": "0:55:38", "throughput": 10280.92, "total_tokens": 22253248}
{"current_steps": 23180, "total_steps": 58920, "loss": 0.0891, "lr": 1.5198238207934764e-06, "epoch": 1.9670739986422268, "percentage": 39.34, "elapsed_time": "0:36:04", "remaining_time": "0:55:37", "throughput": 10281.35, "total_tokens": 22258112}
{"current_steps": 23185, "total_steps": 58920, "loss": 0.0743, "lr": 1.5195707449509757e-06, "epoch": 1.9674983027834352, "percentage": 39.35, "elapsed_time": "0:36:05", "remaining_time": "0:55:37", "throughput": 10281.91, "total_tokens": 22263360}
{"current_steps": 23190, "total_steps": 58920, "loss": 0.0115, "lr": 1.5193176235180185e-06, "epoch": 1.9679226069246436, "percentage": 39.36, "elapsed_time": "0:36:05", "remaining_time": "0:55:36", "throughput": 10282.22, "total_tokens": 22267904}
{"current_steps": 23195, "total_steps": 58920, "loss": 0.0285, "lr": 1.5190644565168146e-06, "epoch": 1.968346911065852, "percentage": 39.37, "elapsed_time": "0:36:06", "remaining_time": "0:55:36", "throughput": 10282.45, "total_tokens": 22272256}
{"current_steps": 23200, "total_steps": 58920, "loss": 0.005, "lr": 1.518811243969579e-06, "epoch": 1.9687712152070604, "percentage": 39.38, "elapsed_time": "0:36:06", "remaining_time": "0:55:35", "throughput": 10282.9, "total_tokens": 22277184}
{"current_steps": 23205, "total_steps": 58920, "loss": 0.0507, "lr": 1.5185579858985293e-06, "epoch": 1.9691955193482689, "percentage": 39.38, "elapsed_time": "0:36:06", "remaining_time": "0:55:34", "throughput": 10283.38, "total_tokens": 22282240}
{"current_steps": 23210, "total_steps": 58920, "loss": 0.0237, "lr": 1.5183046823258891e-06, "epoch": 1.9696198234894773, "percentage": 39.39, "elapsed_time": "0:36:07", "remaining_time": "0:55:34", "throughput": 10283.88, "total_tokens": 22287360}
{"current_steps": 23215, "total_steps": 58920, "loss": 0.0442, "lr": 1.5180513332738837e-06, "epoch": 1.9700441276306857, "percentage": 39.4, "elapsed_time": "0:36:07", "remaining_time": "0:55:33", "throughput": 10284.2, "total_tokens": 22291968}
{"current_steps": 23220, "total_steps": 58920, "loss": 0.0024, "lr": 1.5177979387647448e-06, "epoch": 1.9704684317718941, "percentage": 39.41, "elapsed_time": "0:36:07", "remaining_time": "0:55:33", "throughput": 10284.61, "total_tokens": 22296832}
{"current_steps": 23225, "total_steps": 58920, "loss": 0.0024, "lr": 1.5175444988207062e-06, "epoch": 1.9708927359131025, "percentage": 39.42, "elapsed_time": "0:36:08", "remaining_time": "0:55:32", "throughput": 10284.96, "total_tokens": 22301568}
{"current_steps": 23230, "total_steps": 58920, "loss": 0.0483, "lr": 1.5172910134640065e-06, "epoch": 1.971317040054311, "percentage": 39.43, "elapsed_time": "0:36:08", "remaining_time": "0:55:32", "throughput": 10285.55, "total_tokens": 22306944}
{"current_steps": 23235, "total_steps": 58920, "loss": 0.0007, "lr": 1.5170374827168879e-06, "epoch": 1.9717413441955194, "percentage": 39.43, "elapsed_time": "0:36:09", "remaining_time": "0:55:31", "throughput": 10285.85, "total_tokens": 22311424}
{"current_steps": 23240, "total_steps": 58920, "loss": 0.0009, "lr": 1.516783906601597e-06, "epoch": 1.9721656483367278, "percentage": 39.44, "elapsed_time": "0:36:09", "remaining_time": "0:55:30", "throughput": 10286.23, "total_tokens": 22316160}
{"current_steps": 23245, "total_steps": 58920, "loss": 0.1598, "lr": 1.5165302851403841e-06, "epoch": 1.9725899524779362, "percentage": 39.45, "elapsed_time": "0:36:09", "remaining_time": "0:55:30", "throughput": 10286.74, "total_tokens": 22321280}
{"current_steps": 23250, "total_steps": 58920, "loss": 0.005, "lr": 1.5162766183555036e-06, "epoch": 1.9730142566191446, "percentage": 39.46, "elapsed_time": "0:36:10", "remaining_time": "0:55:29", "throughput": 10287.14, "total_tokens": 22326080}
{"current_steps": 23255, "total_steps": 58920, "loss": 0.0345, "lr": 1.5160229062692138e-06, "epoch": 1.973438560760353, "percentage": 39.47, "elapsed_time": "0:36:10", "remaining_time": "0:55:29", "throughput": 10287.57, "total_tokens": 22330944}
{"current_steps": 23260, "total_steps": 58920, "loss": 0.0462, "lr": 1.515769148903777e-06, "epoch": 1.9738628649015615, "percentage": 39.48, "elapsed_time": "0:36:11", "remaining_time": "0:55:28", "throughput": 10288.27, "total_tokens": 22336640}
{"current_steps": 23265, "total_steps": 58920, "loss": 0.0749, "lr": 1.5155153462814598e-06, "epoch": 1.97428716904277, "percentage": 39.49, "elapsed_time": "0:36:11", "remaining_time": "0:55:27", "throughput": 10288.54, "total_tokens": 22341056}
{"current_steps": 23270, "total_steps": 58920, "loss": 0.0961, "lr": 1.515261498424532e-06, "epoch": 1.9747114731839783, "percentage": 39.49, "elapsed_time": "0:36:11", "remaining_time": "0:55:27", "throughput": 10288.9, "total_tokens": 22345728}
{"current_steps": 23275, "total_steps": 58920, "loss": 0.0003, "lr": 1.5150076053552683e-06, "epoch": 1.9751357773251867, "percentage": 39.5, "elapsed_time": "0:36:12", "remaining_time": "0:55:26", "throughput": 10289.13, "total_tokens": 22350080}
{"current_steps": 23280, "total_steps": 58920, "loss": 0.0609, "lr": 1.5147536670959466e-06, "epoch": 1.9755600814663952, "percentage": 39.51, "elapsed_time": "0:36:12", "remaining_time": "0:55:26", "throughput": 10289.7, "total_tokens": 22355392}
{"current_steps": 23285, "total_steps": 58920, "loss": 0.0597, "lr": 1.5144996836688489e-06, "epoch": 1.9759843856076036, "percentage": 39.52, "elapsed_time": "0:36:12", "remaining_time": "0:55:25", "throughput": 10290.09, "total_tokens": 22360192}
{"current_steps": 23290, "total_steps": 58920, "loss": 0.0265, "lr": 1.5142456550962619e-06, "epoch": 1.976408689748812, "percentage": 39.53, "elapsed_time": "0:36:13", "remaining_time": "0:55:24", "throughput": 10290.47, "total_tokens": 22364928}
{"current_steps": 23295, "total_steps": 58920, "loss": 0.0279, "lr": 1.5139915814004752e-06, "epoch": 1.9768329938900204, "percentage": 39.54, "elapsed_time": "0:36:13", "remaining_time": "0:55:24", "throughput": 10290.86, "total_tokens": 22369664}
{"current_steps": 23300, "total_steps": 58920, "loss": 0.0004, "lr": 1.5137374626037826e-06, "epoch": 1.9772572980312288, "percentage": 39.55, "elapsed_time": "0:36:14", "remaining_time": "0:55:23", "throughput": 10291.28, "total_tokens": 22374528}
{"current_steps": 23305, "total_steps": 58920, "loss": 0.0943, "lr": 1.5134832987284826e-06, "epoch": 1.9776816021724373, "percentage": 39.55, "elapsed_time": "0:36:14", "remaining_time": "0:55:23", "throughput": 10291.64, "total_tokens": 22379264}
{"current_steps": 23310, "total_steps": 58920, "loss": 0.059, "lr": 1.5132290897968773e-06, "epoch": 1.9781059063136457, "percentage": 39.56, "elapsed_time": "0:36:14", "remaining_time": "0:55:22", "throughput": 10291.97, "total_tokens": 22383872}
{"current_steps": 23315, "total_steps": 58920, "loss": 0.0853, "lr": 1.5129748358312729e-06, "epoch": 1.978530210454854, "percentage": 39.57, "elapsed_time": "0:36:15", "remaining_time": "0:55:21", "throughput": 10292.68, "total_tokens": 22389568}
{"current_steps": 23320, "total_steps": 58920, "loss": 0.0024, "lr": 1.5127205368539779e-06, "epoch": 1.9789545145960625, "percentage": 39.58, "elapsed_time": "0:36:15", "remaining_time": "0:55:21", "throughput": 10293.22, "total_tokens": 22394816}
{"current_steps": 23325, "total_steps": 58920, "loss": 0.0728, "lr": 1.5124661928873073e-06, "epoch": 1.979378818737271, "percentage": 39.59, "elapsed_time": "0:36:16", "remaining_time": "0:55:20", "throughput": 10293.58, "total_tokens": 22399488}
{"current_steps": 23330, "total_steps": 58920, "loss": 0.0427, "lr": 1.5122118039535785e-06, "epoch": 1.9798031228784794, "percentage": 39.6, "elapsed_time": "0:36:16", "remaining_time": "0:55:20", "throughput": 10294.08, "total_tokens": 22404608}
{"current_steps": 23335, "total_steps": 58920, "loss": 0.0009, "lr": 1.5119573700751132e-06, "epoch": 1.9802274270196878, "percentage": 39.6, "elapsed_time": "0:36:16", "remaining_time": "0:55:19", "throughput": 10294.55, "total_tokens": 22409600}
{"current_steps": 23340, "total_steps": 58920, "loss": 0.0009, "lr": 1.5117028912742372e-06, "epoch": 1.9806517311608962, "percentage": 39.61, "elapsed_time": "0:36:17", "remaining_time": "0:55:19", "throughput": 10294.9, "total_tokens": 22414272}
{"current_steps": 23345, "total_steps": 58920, "loss": 0.0291, "lr": 1.5114483675732798e-06, "epoch": 1.9810760353021046, "percentage": 39.62, "elapsed_time": "0:36:17", "remaining_time": "0:55:18", "throughput": 10295.32, "total_tokens": 22419136}
{"current_steps": 23350, "total_steps": 58920, "loss": 0.0008, "lr": 1.5111937989945748e-06, "epoch": 1.981500339443313, "percentage": 39.63, "elapsed_time": "0:36:17", "remaining_time": "0:55:17", "throughput": 10295.8, "total_tokens": 22424192}
{"current_steps": 23355, "total_steps": 58920, "loss": 0.0311, "lr": 1.5109391855604598e-06, "epoch": 1.9819246435845215, "percentage": 39.64, "elapsed_time": "0:36:18", "remaining_time": "0:55:17", "throughput": 10296.25, "total_tokens": 22429248}
{"current_steps": 23360, "total_steps": 58920, "loss": 0.0016, "lr": 1.510684527293276e-06, "epoch": 1.98234894772573, "percentage": 39.65, "elapsed_time": "0:36:18", "remaining_time": "0:55:16", "throughput": 10296.83, "total_tokens": 22434560}
{"current_steps": 23365, "total_steps": 58920, "loss": 0.1214, "lr": 1.510429824215368e-06, "epoch": 1.9827732518669383, "percentage": 39.66, "elapsed_time": "0:36:19", "remaining_time": "0:55:16", "throughput": 10297.05, "total_tokens": 22438848}
{"current_steps": 23370, "total_steps": 58920, "loss": 0.0466, "lr": 1.5101750763490868e-06, "epoch": 1.9831975560081467, "percentage": 39.66, "elapsed_time": "0:36:19", "remaining_time": "0:55:15", "throughput": 10297.41, "total_tokens": 22443520}
{"current_steps": 23375, "total_steps": 58920, "loss": 0.0718, "lr": 1.5099202837167842e-06, "epoch": 1.9836218601493552, "percentage": 39.67, "elapsed_time": "0:36:19", "remaining_time": "0:55:14", "throughput": 10297.81, "total_tokens": 22448320}
{"current_steps": 23380, "total_steps": 58920, "loss": 0.0061, "lr": 1.5096654463408176e-06, "epoch": 1.9840461642905636, "percentage": 39.68, "elapsed_time": "0:36:20", "remaining_time": "0:55:14", "throughput": 10298.28, "total_tokens": 22453312}
{"current_steps": 23385, "total_steps": 58920, "loss": 0.0628, "lr": 1.5094105642435485e-06, "epoch": 1.984470468431772, "percentage": 39.69, "elapsed_time": "0:36:20", "remaining_time": "0:55:13", "throughput": 10298.73, "total_tokens": 22458304}
{"current_steps": 23390, "total_steps": 58920, "loss": 0.0434, "lr": 1.5091556374473418e-06, "epoch": 1.9848947725729804, "percentage": 39.7, "elapsed_time": "0:36:21", "remaining_time": "0:55:13", "throughput": 10299.33, "total_tokens": 22463680}
{"current_steps": 23395, "total_steps": 58920, "loss": 0.0009, "lr": 1.5089006659745659e-06, "epoch": 1.9853190767141888, "percentage": 39.71, "elapsed_time": "0:36:21", "remaining_time": "0:55:12", "throughput": 10299.58, "total_tokens": 22468096}
{"current_steps": 23400, "total_steps": 58920, "loss": 0.0328, "lr": 1.5086456498475938e-06, "epoch": 1.9857433808553973, "percentage": 39.71, "elapsed_time": "0:36:21", "remaining_time": "0:55:11", "throughput": 10300.06, "total_tokens": 22473152}
{"current_steps": 23405, "total_steps": 58920, "loss": 0.0194, "lr": 1.5083905890888024e-06, "epoch": 1.9861676849966057, "percentage": 39.72, "elapsed_time": "0:36:22", "remaining_time": "0:55:11", "throughput": 10300.45, "total_tokens": 22477888}
{"current_steps": 23410, "total_steps": 58920, "loss": 0.0932, "lr": 1.5081354837205727e-06, "epoch": 1.986591989137814, "percentage": 39.73, "elapsed_time": "0:36:22", "remaining_time": "0:55:10", "throughput": 10300.72, "total_tokens": 22482304}
{"current_steps": 23415, "total_steps": 58920, "loss": 0.0733, "lr": 1.5078803337652889e-06, "epoch": 1.9870162932790225, "percentage": 39.74, "elapsed_time": "0:36:22", "remaining_time": "0:55:10", "throughput": 10301.08, "total_tokens": 22486976}
{"current_steps": 23420, "total_steps": 58920, "loss": 0.1544, "lr": 1.5076251392453393e-06, "epoch": 1.987440597420231, "percentage": 39.75, "elapsed_time": "0:36:23", "remaining_time": "0:55:09", "throughput": 10301.36, "total_tokens": 22491456}
{"current_steps": 23425, "total_steps": 58920, "loss": 0.0288, "lr": 1.5073699001831167e-06, "epoch": 1.9878649015614394, "percentage": 39.76, "elapsed_time": "0:36:23", "remaining_time": "0:55:08", "throughput": 10301.5, "total_tokens": 22495552}
{"current_steps": 23430, "total_steps": 58920, "loss": 0.0262, "lr": 1.5071146166010165e-06, "epoch": 1.9882892057026478, "percentage": 39.77, "elapsed_time": "0:36:24", "remaining_time": "0:55:08", "throughput": 10301.68, "total_tokens": 22499776}
{"current_steps": 23435, "total_steps": 58920, "loss": 0.0283, "lr": 1.5068592885214403e-06, "epoch": 1.9887135098438562, "percentage": 39.77, "elapsed_time": "0:36:24", "remaining_time": "0:55:07", "throughput": 10301.98, "total_tokens": 22504320}
{"current_steps": 23440, "total_steps": 58920, "loss": 0.02, "lr": 1.5066039159667916e-06, "epoch": 1.9891378139850646, "percentage": 39.78, "elapsed_time": "0:36:24", "remaining_time": "0:55:07", "throughput": 10302.32, "total_tokens": 22508992}
{"current_steps": 23445, "total_steps": 58920, "loss": 0.0551, "lr": 1.506348498959478e-06, "epoch": 1.989562118126273, "percentage": 39.79, "elapsed_time": "0:36:25", "remaining_time": "0:55:06", "throughput": 10302.61, "total_tokens": 22513472}
{"current_steps": 23450, "total_steps": 58920, "loss": 0.0236, "lr": 1.5060930375219122e-06, "epoch": 1.9899864222674815, "percentage": 39.8, "elapsed_time": "0:36:25", "remaining_time": "0:55:05", "throughput": 10303.0, "total_tokens": 22518272}
{"current_steps": 23455, "total_steps": 58920, "loss": 0.0033, "lr": 1.5058375316765093e-06, "epoch": 1.9904107264086899, "percentage": 39.81, "elapsed_time": "0:36:25", "remaining_time": "0:55:05", "throughput": 10303.52, "total_tokens": 22523456}
{"current_steps": 23460, "total_steps": 58920, "loss": 0.0329, "lr": 1.5055819814456893e-06, "epoch": 1.9908350305498983, "percentage": 39.82, "elapsed_time": "0:36:26", "remaining_time": "0:55:04", "throughput": 10303.73, "total_tokens": 22527744}
{"current_steps": 23465, "total_steps": 58920, "loss": 0.0631, "lr": 1.5053263868518759e-06, "epoch": 1.9912593346911067, "percentage": 39.83, "elapsed_time": "0:36:26", "remaining_time": "0:55:04", "throughput": 10304.18, "total_tokens": 22532736}
{"current_steps": 23470, "total_steps": 58920, "loss": 0.0023, "lr": 1.5050707479174964e-06, "epoch": 1.9916836388323151, "percentage": 39.83, "elapsed_time": "0:36:27", "remaining_time": "0:55:03", "throughput": 10304.49, "total_tokens": 22537280}
{"current_steps": 23475, "total_steps": 58920, "loss": 0.0027, "lr": 1.5048150646649825e-06, "epoch": 1.9921079429735236, "percentage": 39.84, "elapsed_time": "0:36:27", "remaining_time": "0:55:02", "throughput": 10304.77, "total_tokens": 22541760}
{"current_steps": 23480, "total_steps": 58920, "loss": 0.0108, "lr": 1.5045593371167696e-06, "epoch": 1.992532247114732, "percentage": 39.85, "elapsed_time": "0:36:27", "remaining_time": "0:55:02", "throughput": 10305.06, "total_tokens": 22546240}
{"current_steps": 23485, "total_steps": 58920, "loss": 0.0186, "lr": 1.504303565295296e-06, "epoch": 1.9929565512559404, "percentage": 39.86, "elapsed_time": "0:36:28", "remaining_time": "0:55:01", "throughput": 10305.52, "total_tokens": 22551232}
{"current_steps": 23490, "total_steps": 58920, "loss": 0.0546, "lr": 1.5040477492230052e-06, "epoch": 1.9933808553971488, "percentage": 39.87, "elapsed_time": "0:36:28", "remaining_time": "0:55:01", "throughput": 10305.65, "total_tokens": 22555328}
{"current_steps": 23495, "total_steps": 58920, "loss": 0.0054, "lr": 1.5037918889223447e-06, "epoch": 1.9938051595383572, "percentage": 39.88, "elapsed_time": "0:36:29", "remaining_time": "0:55:00", "throughput": 10305.94, "total_tokens": 22559808}
{"current_steps": 23500, "total_steps": 58920, "loss": 0.0329, "lr": 1.5035359844157648e-06, "epoch": 1.9942294636795657, "percentage": 39.88, "elapsed_time": "0:36:29", "remaining_time": "0:54:59", "throughput": 10306.24, "total_tokens": 22564352}
{"current_steps": 23505, "total_steps": 58920, "loss": 0.0766, "lr": 1.5032800357257202e-06, "epoch": 1.994653767820774, "percentage": 39.89, "elapsed_time": "0:36:29", "remaining_time": "0:54:59", "throughput": 10306.44, "total_tokens": 22568640}
{"current_steps": 23510, "total_steps": 58920, "loss": 0.0562, "lr": 1.50302404287467e-06, "epoch": 1.9950780719619825, "percentage": 39.9, "elapsed_time": "0:36:30", "remaining_time": "0:54:58", "throughput": 10306.73, "total_tokens": 22573120}
{"current_steps": 23515, "total_steps": 58920, "loss": 0.0537, "lr": 1.5027680058850757e-06, "epoch": 1.995502376103191, "percentage": 39.91, "elapsed_time": "0:36:30", "remaining_time": "0:54:58", "throughput": 10306.94, "total_tokens": 22577408}
{"current_steps": 23520, "total_steps": 58920, "loss": 0.0321, "lr": 1.5025119247794042e-06, "epoch": 1.9959266802443993, "percentage": 39.92, "elapsed_time": "0:36:30", "remaining_time": "0:54:57", "throughput": 10307.39, "total_tokens": 22582336}
{"current_steps": 23525, "total_steps": 58920, "loss": 0.0002, "lr": 1.5022557995801255e-06, "epoch": 1.9963509843856078, "percentage": 39.93, "elapsed_time": "0:36:31", "remaining_time": "0:54:56", "throughput": 10308.07, "total_tokens": 22587968}
{"current_steps": 23530, "total_steps": 58920, "loss": 0.0225, "lr": 1.501999630309714e-06, "epoch": 1.9967752885268162, "percentage": 39.94, "elapsed_time": "0:36:31", "remaining_time": "0:54:56", "throughput": 10308.35, "total_tokens": 22592448}
{"current_steps": 23535, "total_steps": 58920, "loss": 0.1195, "lr": 1.5017434169906473e-06, "epoch": 1.9971995926680246, "percentage": 39.94, "elapsed_time": "0:36:32", "remaining_time": "0:54:55", "throughput": 10308.7, "total_tokens": 22597120}
{"current_steps": 23540, "total_steps": 58920, "loss": 0.0428, "lr": 1.5014871596454076e-06, "epoch": 1.997623896809233, "percentage": 39.95, "elapsed_time": "0:36:32", "remaining_time": "0:54:55", "throughput": 10309.06, "total_tokens": 22601792}
{"current_steps": 23545, "total_steps": 58920, "loss": 0.1006, "lr": 1.5012308582964796e-06, "epoch": 1.9980482009504412, "percentage": 39.96, "elapsed_time": "0:36:32", "remaining_time": "0:54:54", "throughput": 10309.46, "total_tokens": 22606592}
{"current_steps": 23550, "total_steps": 58920, "loss": 0.024, "lr": 1.5009745129663538e-06, "epoch": 1.9984725050916496, "percentage": 39.97, "elapsed_time": "0:36:33", "remaining_time": "0:54:53", "throughput": 10309.76, "total_tokens": 22611136}
{"current_steps": 23555, "total_steps": 58920, "loss": 0.0003, "lr": 1.5007181236775233e-06, "epoch": 1.998896809232858, "percentage": 39.98, "elapsed_time": "0:36:33", "remaining_time": "0:54:53", "throughput": 10310.55, "total_tokens": 22617152}
{"current_steps": 23560, "total_steps": 58920, "loss": 0.0332, "lr": 1.5004616904524854e-06, "epoch": 1.9993211133740665, "percentage": 39.99, "elapsed_time": "0:36:33", "remaining_time": "0:54:52", "throughput": 10310.91, "total_tokens": 22621952}
{"current_steps": 23565, "total_steps": 58920, "loss": 0.0205, "lr": 1.500205213313741e-06, "epoch": 1.999745417515275, "percentage": 39.99, "elapsed_time": "0:36:34", "remaining_time": "0:54:52", "throughput": 10311.34, "total_tokens": 22626816}
{"current_steps": 23568, "total_steps": 58920, "eval_loss": 0.08462928235530853, "epoch": 2.0, "percentage": 40.0, "elapsed_time": "0:36:50", "remaining_time": "0:55:16", "throughput": 10234.98, "total_tokens": 22629440}
{"current_steps": 23570, "total_steps": 58920, "loss": 0.0003, "lr": 1.4999486922837953e-06, "epoch": 2.0001697216564835, "percentage": 40.0, "elapsed_time": "0:37:26", "remaining_time": "0:56:09", "throughput": 10074.49, "total_tokens": 22631424}
{"current_steps": 23575, "total_steps": 58920, "loss": 0.0002, "lr": 1.4996921273851566e-06, "epoch": 2.000594025797692, "percentage": 40.01, "elapsed_time": "0:37:26", "remaining_time": "0:56:08", "throughput": 10074.85, "total_tokens": 22636032}
{"current_steps": 23580, "total_steps": 58920, "loss": 0.0002, "lr": 1.4994355186403375e-06, "epoch": 2.0010183299389004, "percentage": 40.02, "elapsed_time": "0:37:27", "remaining_time": "0:56:07", "throughput": 10075.1, "total_tokens": 22640320}
{"current_steps": 23585, "total_steps": 58920, "loss": 0.0065, "lr": 1.4991788660718555e-06, "epoch": 2.001442634080109, "percentage": 40.03, "elapsed_time": "0:37:27", "remaining_time": "0:56:07", "throughput": 10075.49, "total_tokens": 22645056}
{"current_steps": 23590, "total_steps": 58920, "loss": 0.0001, "lr": 1.4989221697022301e-06, "epoch": 2.0018669382213172, "percentage": 40.04, "elapsed_time": "0:37:27", "remaining_time": "0:56:06", "throughput": 10075.89, "total_tokens": 22649792}
{"current_steps": 23595, "total_steps": 58920, "loss": 0.0274, "lr": 1.4986654295539856e-06, "epoch": 2.0022912423625256, "percentage": 40.05, "elapsed_time": "0:37:28", "remaining_time": "0:56:06", "throughput": 10076.27, "total_tokens": 22654464}
{"current_steps": 23600, "total_steps": 58920, "loss": 0.0002, "lr": 1.4984086456496502e-06, "epoch": 2.002715546503734, "percentage": 40.05, "elapsed_time": "0:37:28", "remaining_time": "0:56:05", "throughput": 10076.71, "total_tokens": 22659264}
{"current_steps": 23605, "total_steps": 58920, "loss": 0.0082, "lr": 1.4981518180117556e-06, "epoch": 2.0031398506449425, "percentage": 40.06, "elapsed_time": "0:37:29", "remaining_time": "0:56:04", "throughput": 10076.95, "total_tokens": 22663552}
{"current_steps": 23610, "total_steps": 58920, "loss": 0.0012, "lr": 1.4978949466628371e-06, "epoch": 2.003564154786151, "percentage": 40.07, "elapsed_time": "0:37:29", "remaining_time": "0:56:04", "throughput": 10077.41, "total_tokens": 22668480}
{"current_steps": 23615, "total_steps": 58920, "loss": 0.0003, "lr": 1.4976380316254352e-06, "epoch": 2.0039884589273593, "percentage": 40.08, "elapsed_time": "0:37:29", "remaining_time": "0:56:03", "throughput": 10077.84, "total_tokens": 22673344}
{"current_steps": 23620, "total_steps": 58920, "loss": 0.0645, "lr": 1.4973810729220926e-06, "epoch": 2.0044127630685677, "percentage": 40.09, "elapsed_time": "0:37:30", "remaining_time": "0:56:02", "throughput": 10078.21, "total_tokens": 22678016}
{"current_steps": 23625, "total_steps": 58920, "loss": 0.0001, "lr": 1.4971240705753565e-06, "epoch": 2.004837067209776, "percentage": 40.1, "elapsed_time": "0:37:30", "remaining_time": "0:56:02", "throughput": 10078.6, "total_tokens": 22682688}
{"current_steps": 23630, "total_steps": 58920, "loss": 0.0002, "lr": 1.4968670246077784e-06, "epoch": 2.0052613713509846, "percentage": 40.11, "elapsed_time": "0:37:30", "remaining_time": "0:56:01", "throughput": 10079.01, "total_tokens": 22687488}
{"current_steps": 23635, "total_steps": 58920, "loss": 0.0259, "lr": 1.4966099350419126e-06, "epoch": 2.005685675492193, "percentage": 40.11, "elapsed_time": "0:37:31", "remaining_time": "0:56:01", "throughput": 10079.23, "total_tokens": 22691712}
{"current_steps": 23640, "total_steps": 58920, "loss": 0.0205, "lr": 1.496352801900318e-06, "epoch": 2.0061099796334014, "percentage": 40.12, "elapsed_time": "0:37:31", "remaining_time": "0:56:00", "throughput": 10079.43, "total_tokens": 22695872}
{"current_steps": 23645, "total_steps": 58920, "loss": 0.0288, "lr": 1.496095625205557e-06, "epoch": 2.00653428377461, "percentage": 40.13, "elapsed_time": "0:37:32", "remaining_time": "0:55:59", "throughput": 10079.73, "total_tokens": 22700352}
{"current_steps": 23650, "total_steps": 58920, "loss": 0.0003, "lr": 1.4958384049801962e-06, "epoch": 2.0069585879158183, "percentage": 40.14, "elapsed_time": "0:37:32", "remaining_time": "0:55:59", "throughput": 10080.14, "total_tokens": 22705088}
{"current_steps": 23655, "total_steps": 58920, "loss": 0.0169, "lr": 1.4955811412468055e-06, "epoch": 2.0073828920570267, "percentage": 40.15, "elapsed_time": "0:37:32", "remaining_time": "0:55:58", "throughput": 10080.59, "total_tokens": 22710016}
{"current_steps": 23660, "total_steps": 58920, "loss": 0.0274, "lr": 1.495323834027959e-06, "epoch": 2.007807196198235, "percentage": 40.16, "elapsed_time": "0:37:33", "remaining_time": "0:55:57", "throughput": 10080.88, "total_tokens": 22714432}
{"current_steps": 23665, "total_steps": 58920, "loss": 0.0146, "lr": 1.4950664833462346e-06, "epoch": 2.0082315003394435, "percentage": 40.16, "elapsed_time": "0:37:33", "remaining_time": "0:55:57", "throughput": 10081.26, "total_tokens": 22719104}
{"current_steps": 23670, "total_steps": 58920, "loss": 0.0473, "lr": 1.4948090892242133e-06, "epoch": 2.008655804480652, "percentage": 40.17, "elapsed_time": "0:37:33", "remaining_time": "0:55:56", "throughput": 10081.58, "total_tokens": 22723648}
{"current_steps": 23675, "total_steps": 58920, "loss": 0.0036, "lr": 1.4945516516844809e-06, "epoch": 2.00908010862186, "percentage": 40.18, "elapsed_time": "0:37:34", "remaining_time": "0:55:56", "throughput": 10081.92, "total_tokens": 22728256}
{"current_steps": 23680, "total_steps": 58920, "loss": 0.0003, "lr": 1.494294170749627e-06, "epoch": 2.0095044127630683, "percentage": 40.19, "elapsed_time": "0:37:34", "remaining_time": "0:55:55", "throughput": 10082.23, "total_tokens": 22732736}
{"current_steps": 23685, "total_steps": 58920, "loss": 0.0003, "lr": 1.4940366464422443e-06, "epoch": 2.0099287169042768, "percentage": 40.2, "elapsed_time": "0:37:35", "remaining_time": "0:55:54", "throughput": 10082.79, "total_tokens": 22737920}
{"current_steps": 23690, "total_steps": 58920, "loss": 0.0002, "lr": 1.4937790787849297e-06, "epoch": 2.010353021045485, "percentage": 40.21, "elapsed_time": "0:37:35", "remaining_time": "0:55:54", "throughput": 10083.18, "total_tokens": 22742656}
{"current_steps": 23695, "total_steps": 58920, "loss": 0.0001, "lr": 1.493521467800283e-06, "epoch": 2.0107773251866936, "percentage": 40.22, "elapsed_time": "0:37:35", "remaining_time": "0:55:53", "throughput": 10083.97, "total_tokens": 22748544}
{"current_steps": 23700, "total_steps": 58920, "loss": 0.0003, "lr": 1.4932638135109098e-06, "epoch": 2.011201629327902, "percentage": 40.22, "elapsed_time": "0:37:36", "remaining_time": "0:55:53", "throughput": 10084.27, "total_tokens": 22753024}
{"current_steps": 23705, "total_steps": 58920, "loss": 0.0376, "lr": 1.493006115939418e-06, "epoch": 2.0116259334691104, "percentage": 40.23, "elapsed_time": "0:37:36", "remaining_time": "0:55:52", "throughput": 10084.78, "total_tokens": 22758144}
{"current_steps": 23710, "total_steps": 58920, "loss": 0.0003, "lr": 1.4927483751084193e-06, "epoch": 2.012050237610319, "percentage": 40.24, "elapsed_time": "0:37:37", "remaining_time": "0:55:51", "throughput": 10085.32, "total_tokens": 22763328}
{"current_steps": 23715, "total_steps": 58920, "loss": 0.0273, "lr": 1.4924905910405299e-06, "epoch": 2.0124745417515273, "percentage": 40.25, "elapsed_time": "0:37:37", "remaining_time": "0:55:51", "throughput": 10085.57, "total_tokens": 22767680}
{"current_steps": 23720, "total_steps": 58920, "loss": 0.0489, "lr": 1.4922327637583694e-06, "epoch": 2.0128988458927357, "percentage": 40.26, "elapsed_time": "0:37:37", "remaining_time": "0:55:50", "throughput": 10086.0, "total_tokens": 22772544}
{"current_steps": 23725, "total_steps": 58920, "loss": 0.0001, "lr": 1.4919748932845609e-06, "epoch": 2.013323150033944, "percentage": 40.27, "elapsed_time": "0:37:38", "remaining_time": "0:55:49", "throughput": 10086.68, "total_tokens": 22778048}
{"current_steps": 23730, "total_steps": 58920, "loss": 0.0001, "lr": 1.4917169796417318e-06, "epoch": 2.0137474541751526, "percentage": 40.27, "elapsed_time": "0:37:38", "remaining_time": "0:55:49", "throughput": 10087.32, "total_tokens": 22783616}
{"current_steps": 23735, "total_steps": 58920, "loss": 0.0267, "lr": 1.491459022852513e-06, "epoch": 2.014171758316361, "percentage": 40.28, "elapsed_time": "0:37:39", "remaining_time": "0:55:48", "throughput": 10087.73, "total_tokens": 22788416}
{"current_steps": 23740, "total_steps": 58920, "loss": 0.0122, "lr": 1.4912010229395392e-06, "epoch": 2.0145960624575694, "percentage": 40.29, "elapsed_time": "0:37:39", "remaining_time": "0:55:48", "throughput": 10088.17, "total_tokens": 22793280}
{"current_steps": 23745, "total_steps": 58920, "loss": 0.0002, "lr": 1.4909429799254493e-06, "epoch": 2.015020366598778, "percentage": 40.3, "elapsed_time": "0:37:39", "remaining_time": "0:55:47", "throughput": 10088.47, "total_tokens": 22797760}
{"current_steps": 23750, "total_steps": 58920, "loss": 0.0075, "lr": 1.4906848938328855e-06, "epoch": 2.0154446707399862, "percentage": 40.31, "elapsed_time": "0:37:40", "remaining_time": "0:55:46", "throughput": 10089.09, "total_tokens": 22803200}
{"current_steps": 23755, "total_steps": 58920, "loss": 0.0002, "lr": 1.490426764684494e-06, "epoch": 2.0158689748811947, "percentage": 40.32, "elapsed_time": "0:37:40", "remaining_time": "0:55:46", "throughput": 10089.58, "total_tokens": 22808192}
{"current_steps": 23760, "total_steps": 58920, "loss": 0.0001, "lr": 1.4901685925029245e-06, "epoch": 2.016293279022403, "percentage": 40.33, "elapsed_time": "0:37:40", "remaining_time": "0:55:45", "throughput": 10089.95, "total_tokens": 22812928}
{"current_steps": 23765, "total_steps": 58920, "loss": 0.0002, "lr": 1.4899103773108304e-06, "epoch": 2.0167175831636115, "percentage": 40.33, "elapsed_time": "0:37:41", "remaining_time": "0:55:45", "throughput": 10090.36, "total_tokens": 22817728}
{"current_steps": 23770, "total_steps": 58920, "loss": 0.0001, "lr": 1.4896521191308697e-06, "epoch": 2.01714188730482, "percentage": 40.34, "elapsed_time": "0:37:41", "remaining_time": "0:55:44", "throughput": 10090.78, "total_tokens": 22822464}
{"current_steps": 23775, "total_steps": 58920, "loss": 0.026, "lr": 1.4893938179857037e-06, "epoch": 2.0175661914460283, "percentage": 40.35, "elapsed_time": "0:37:42", "remaining_time": "0:55:43", "throughput": 10091.26, "total_tokens": 22827456}
{"current_steps": 23780, "total_steps": 58920, "loss": 0.0003, "lr": 1.489135473897997e-06, "epoch": 2.0179904955872368, "percentage": 40.36, "elapsed_time": "0:37:42", "remaining_time": "0:55:43", "throughput": 10091.57, "total_tokens": 22831936}
{"current_steps": 23785, "total_steps": 58920, "loss": 0.0001, "lr": 1.4888770868904183e-06, "epoch": 2.018414799728445, "percentage": 40.37, "elapsed_time": "0:37:42", "remaining_time": "0:55:42", "throughput": 10091.93, "total_tokens": 22836544}
{"current_steps": 23790, "total_steps": 58920, "loss": 0.0001, "lr": 1.4886186569856405e-06, "epoch": 2.0188391038696536, "percentage": 40.38, "elapsed_time": "0:37:43", "remaining_time": "0:55:42", "throughput": 10092.26, "total_tokens": 22841088}
{"current_steps": 23795, "total_steps": 58920, "loss": 0.0205, "lr": 1.4883601842063396e-06, "epoch": 2.019263408010862, "percentage": 40.39, "elapsed_time": "0:37:43", "remaining_time": "0:55:41", "throughput": 10092.75, "total_tokens": 22846080}
{"current_steps": 23800, "total_steps": 58920, "loss": 0.0474, "lr": 1.4881016685751956e-06, "epoch": 2.0196877121520704, "percentage": 40.39, "elapsed_time": "0:37:43", "remaining_time": "0:55:40", "throughput": 10092.97, "total_tokens": 22850304}
{"current_steps": 23805, "total_steps": 58920, "loss": 0.0433, "lr": 1.4878431101148927e-06, "epoch": 2.020112016293279, "percentage": 40.4, "elapsed_time": "0:37:44", "remaining_time": "0:55:40", "throughput": 10093.39, "total_tokens": 22855104}
{"current_steps": 23810, "total_steps": 58920, "loss": 0.0101, "lr": 1.4875845088481183e-06, "epoch": 2.0205363204344873, "percentage": 40.41, "elapsed_time": "0:37:44", "remaining_time": "0:55:39", "throughput": 10093.75, "total_tokens": 22859776}
{"current_steps": 23815, "total_steps": 58920, "loss": 0.0, "lr": 1.4873258647975634e-06, "epoch": 2.0209606245756957, "percentage": 40.42, "elapsed_time": "0:37:45", "remaining_time": "0:55:38", "throughput": 10094.22, "total_tokens": 22864768}
{"current_steps": 23820, "total_steps": 58920, "loss": 0.0002, "lr": 1.4870671779859239e-06, "epoch": 2.021384928716904, "percentage": 40.43, "elapsed_time": "0:37:45", "remaining_time": "0:55:38", "throughput": 10094.54, "total_tokens": 22869376}
{"current_steps": 23825, "total_steps": 58920, "loss": 0.0001, "lr": 1.4868084484358974e-06, "epoch": 2.0218092328581125, "percentage": 40.44, "elapsed_time": "0:37:45", "remaining_time": "0:55:37", "throughput": 10094.95, "total_tokens": 22874176}
{"current_steps": 23830, "total_steps": 58920, "loss": 0.0001, "lr": 1.4865496761701874e-06, "epoch": 2.022233536999321, "percentage": 40.44, "elapsed_time": "0:37:46", "remaining_time": "0:55:37", "throughput": 10095.24, "total_tokens": 22878592}
{"current_steps": 23835, "total_steps": 58920, "loss": 0.0375, "lr": 1.4862908612115e-06, "epoch": 2.0226578411405294, "percentage": 40.45, "elapsed_time": "0:37:46", "remaining_time": "0:55:36", "throughput": 10095.57, "total_tokens": 22883200}
{"current_steps": 23840, "total_steps": 58920, "loss": 0.0403, "lr": 1.4860320035825454e-06, "epoch": 2.023082145281738, "percentage": 40.46, "elapsed_time": "0:37:47", "remaining_time": "0:55:35", "throughput": 10095.75, "total_tokens": 22887424}
{"current_steps": 23845, "total_steps": 58920, "loss": 0.039, "lr": 1.485773103306037e-06, "epoch": 2.023506449422946, "percentage": 40.47, "elapsed_time": "0:37:47", "remaining_time": "0:55:35", "throughput": 10096.11, "total_tokens": 22892096}
{"current_steps": 23850, "total_steps": 58920, "loss": 0.0002, "lr": 1.485514160404693e-06, "epoch": 2.0239307535641546, "percentage": 40.48, "elapsed_time": "0:37:47", "remaining_time": "0:55:34", "throughput": 10096.38, "total_tokens": 22896512}
{"current_steps": 23855, "total_steps": 58920, "loss": 0.0003, "lr": 1.4852551749012344e-06, "epoch": 2.024355057705363, "percentage": 40.49, "elapsed_time": "0:37:48", "remaining_time": "0:55:34", "throughput": 10096.79, "total_tokens": 22901312}
{"current_steps": 23860, "total_steps": 58920, "loss": 0.0005, "lr": 1.484996146818386e-06, "epoch": 2.0247793618465715, "percentage": 40.5, "elapsed_time": "0:37:48", "remaining_time": "0:55:33", "throughput": 10097.23, "total_tokens": 22906240}
{"current_steps": 23865, "total_steps": 58920, "loss": 0.0154, "lr": 1.4847370761788766e-06, "epoch": 2.02520366598778, "percentage": 40.5, "elapsed_time": "0:37:48", "remaining_time": "0:55:32", "throughput": 10097.64, "total_tokens": 22911040}
{"current_steps": 23870, "total_steps": 58920, "loss": 0.0002, "lr": 1.4844779630054394e-06, "epoch": 2.0256279701289883, "percentage": 40.51, "elapsed_time": "0:37:49", "remaining_time": "0:55:32", "throughput": 10097.88, "total_tokens": 22915392}
{"current_steps": 23875, "total_steps": 58920, "loss": 0.0072, "lr": 1.4842188073208098e-06, "epoch": 2.0260522742701967, "percentage": 40.52, "elapsed_time": "0:37:49", "remaining_time": "0:55:31", "throughput": 10098.18, "total_tokens": 22919872}
{"current_steps": 23880, "total_steps": 58920, "loss": 0.0001, "lr": 1.4839596091477283e-06, "epoch": 2.026476578411405, "percentage": 40.53, "elapsed_time": "0:37:50", "remaining_time": "0:55:30", "throughput": 10098.52, "total_tokens": 22924480}
{"current_steps": 23885, "total_steps": 58920, "loss": 0.0022, "lr": 1.4837003685089382e-06, "epoch": 2.0269008825526136, "percentage": 40.54, "elapsed_time": "0:37:50", "remaining_time": "0:55:30", "throughput": 10099.0, "total_tokens": 22929472}
{"current_steps": 23890, "total_steps": 58920, "loss": 0.0001, "lr": 1.483441085427187e-06, "epoch": 2.027325186693822, "percentage": 40.55, "elapsed_time": "0:37:50", "remaining_time": "0:55:29", "throughput": 10099.47, "total_tokens": 22934464}
{"current_steps": 23895, "total_steps": 58920, "loss": 0.0001, "lr": 1.4831817599252264e-06, "epoch": 2.0277494908350304, "percentage": 40.55, "elapsed_time": "0:37:51", "remaining_time": "0:55:29", "throughput": 10099.8, "total_tokens": 22939008}
{"current_steps": 23900, "total_steps": 58920, "loss": 0.0002, "lr": 1.482922392025811e-06, "epoch": 2.028173794976239, "percentage": 40.56, "elapsed_time": "0:37:51", "remaining_time": "0:55:28", "throughput": 10100.03, "total_tokens": 22943360}
{"current_steps": 23905, "total_steps": 58920, "loss": 0.0002, "lr": 1.482662981751699e-06, "epoch": 2.0285980991174473, "percentage": 40.57, "elapsed_time": "0:37:51", "remaining_time": "0:55:27", "throughput": 10100.31, "total_tokens": 22947840}
{"current_steps": 23910, "total_steps": 58920, "loss": 0.0356, "lr": 1.482403529125653e-06, "epoch": 2.0290224032586557, "percentage": 40.58, "elapsed_time": "0:37:52", "remaining_time": "0:55:27", "throughput": 10100.5, "total_tokens": 22952000}
{"current_steps": 23915, "total_steps": 58920, "loss": 0.0279, "lr": 1.482144034170439e-06, "epoch": 2.029446707399864, "percentage": 40.59, "elapsed_time": "0:37:52", "remaining_time": "0:55:26", "throughput": 10100.88, "total_tokens": 22956736}
{"current_steps": 23920, "total_steps": 58920, "loss": 0.0611, "lr": 1.4818844969088268e-06, "epoch": 2.0298710115410725, "percentage": 40.6, "elapsed_time": "0:37:53", "remaining_time": "0:55:26", "throughput": 10101.08, "total_tokens": 22960960}
{"current_steps": 23925, "total_steps": 58920, "loss": 0.0324, "lr": 1.48162491736359e-06, "epoch": 2.030295315682281, "percentage": 40.61, "elapsed_time": "0:37:53", "remaining_time": "0:55:25", "throughput": 10101.38, "total_tokens": 22965440}
{"current_steps": 23930, "total_steps": 58920, "loss": 0.035, "lr": 1.4813652955575056e-06, "epoch": 2.0307196198234894, "percentage": 40.61, "elapsed_time": "0:37:53", "remaining_time": "0:55:24", "throughput": 10101.76, "total_tokens": 22970240}
{"current_steps": 23935, "total_steps": 58920, "loss": 0.0002, "lr": 1.4811056315133544e-06, "epoch": 2.031143923964698, "percentage": 40.62, "elapsed_time": "0:37:54", "remaining_time": "0:55:24", "throughput": 10102.19, "total_tokens": 22975104}
{"current_steps": 23940, "total_steps": 58920, "loss": 0.0002, "lr": 1.4808459252539211e-06, "epoch": 2.031568228105906, "percentage": 40.63, "elapsed_time": "0:37:54", "remaining_time": "0:55:23", "throughput": 10102.83, "total_tokens": 22980608}
{"current_steps": 23945, "total_steps": 58920, "loss": 0.0006, "lr": 1.4805861768019938e-06, "epoch": 2.0319925322471146, "percentage": 40.64, "elapsed_time": "0:37:55", "remaining_time": "0:55:23", "throughput": 10103.1, "total_tokens": 22985024}
{"current_steps": 23950, "total_steps": 58920, "loss": 0.0003, "lr": 1.4803263861803647e-06, "epoch": 2.032416836388323, "percentage": 40.65, "elapsed_time": "0:37:55", "remaining_time": "0:55:22", "throughput": 10103.3, "total_tokens": 22989248}
{"current_steps": 23955, "total_steps": 58920, "loss": 0.0252, "lr": 1.4800665534118295e-06, "epoch": 2.0328411405295315, "percentage": 40.66, "elapsed_time": "0:37:55", "remaining_time": "0:55:21", "throughput": 10103.64, "total_tokens": 22993920}
{"current_steps": 23960, "total_steps": 58920, "loss": 0.0003, "lr": 1.4798066785191874e-06, "epoch": 2.03326544467074, "percentage": 40.67, "elapsed_time": "0:37:56", "remaining_time": "0:55:21", "throughput": 10103.97, "total_tokens": 22998528}
{"current_steps": 23965, "total_steps": 58920, "loss": 0.0192, "lr": 1.4795467615252416e-06, "epoch": 2.0336897488119483, "percentage": 40.67, "elapsed_time": "0:37:56", "remaining_time": "0:55:20", "throughput": 10104.24, "total_tokens": 23002944}
{"current_steps": 23970, "total_steps": 58920, "loss": 0.0001, "lr": 1.4792868024527992e-06, "epoch": 2.0341140529531567, "percentage": 40.68, "elapsed_time": "0:37:56", "remaining_time": "0:55:19", "throughput": 10104.74, "total_tokens": 23008000}
{"current_steps": 23975, "total_steps": 58920, "loss": 0.0002, "lr": 1.47902680132467e-06, "epoch": 2.034538357094365, "percentage": 40.69, "elapsed_time": "0:37:57", "remaining_time": "0:55:19", "throughput": 10105.12, "total_tokens": 23012736}
{"current_steps": 23980, "total_steps": 58920, "loss": 0.0046, "lr": 1.4787667581636682e-06, "epoch": 2.0349626612355736, "percentage": 40.7, "elapsed_time": "0:37:57", "remaining_time": "0:55:18", "throughput": 10105.54, "total_tokens": 23017600}
{"current_steps": 23985, "total_steps": 58920, "loss": 0.0669, "lr": 1.4785066729926125e-06, "epoch": 2.035386965376782, "percentage": 40.71, "elapsed_time": "0:37:58", "remaining_time": "0:55:18", "throughput": 10106.14, "total_tokens": 23022976}
{"current_steps": 23990, "total_steps": 58920, "loss": 0.0001, "lr": 1.478246545834324e-06, "epoch": 2.0358112695179904, "percentage": 40.72, "elapsed_time": "0:37:58", "remaining_time": "0:55:17", "throughput": 10106.64, "total_tokens": 23028096}
{"current_steps": 23995, "total_steps": 58920, "loss": 0.0004, "lr": 1.4779863767116273e-06, "epoch": 2.036235573659199, "percentage": 40.72, "elapsed_time": "0:37:58", "remaining_time": "0:55:16", "throughput": 10106.94, "total_tokens": 23032576}
{"current_steps": 24000, "total_steps": 58920, "loss": 0.0001, "lr": 1.4777261656473521e-06, "epoch": 2.0366598778004072, "percentage": 40.73, "elapsed_time": "0:37:59", "remaining_time": "0:55:16", "throughput": 10107.34, "total_tokens": 23037376}
{"current_steps": 24005, "total_steps": 58920, "loss": 0.0001, "lr": 1.4774659126643307e-06, "epoch": 2.0370841819416157, "percentage": 40.74, "elapsed_time": "0:37:59", "remaining_time": "0:55:15", "throughput": 10107.86, "total_tokens": 23042560}
{"current_steps": 24010, "total_steps": 58920, "loss": 0.0001, "lr": 1.4772056177853992e-06, "epoch": 2.037508486082824, "percentage": 40.75, "elapsed_time": "0:38:00", "remaining_time": "0:55:15", "throughput": 10108.14, "total_tokens": 23046976}
{"current_steps": 24015, "total_steps": 58920, "loss": 0.0535, "lr": 1.4769452810333975e-06, "epoch": 2.0379327902240325, "percentage": 40.76, "elapsed_time": "0:38:00", "remaining_time": "0:55:14", "throughput": 10108.79, "total_tokens": 23052544}
{"current_steps": 24020, "total_steps": 58920, "loss": 0.0004, "lr": 1.47668490243117e-06, "epoch": 2.038357094365241, "percentage": 40.77, "elapsed_time": "0:38:00", "remaining_time": "0:55:13", "throughput": 10109.25, "total_tokens": 23057472}
{"current_steps": 24025, "total_steps": 58920, "loss": 0.0518, "lr": 1.476424482001563e-06, "epoch": 2.0387813985064493, "percentage": 40.78, "elapsed_time": "0:38:01", "remaining_time": "0:55:13", "throughput": 10109.47, "total_tokens": 23061760}
{"current_steps": 24030, "total_steps": 58920, "loss": 0.0008, "lr": 1.476164019767428e-06, "epoch": 2.0392057026476578, "percentage": 40.78, "elapsed_time": "0:38:01", "remaining_time": "0:55:12", "throughput": 10109.84, "total_tokens": 23066432}
{"current_steps": 24035, "total_steps": 58920, "loss": 0.0404, "lr": 1.475903515751619e-06, "epoch": 2.039630006788866, "percentage": 40.79, "elapsed_time": "0:38:01", "remaining_time": "0:55:12", "throughput": 10110.32, "total_tokens": 23071488}
{"current_steps": 24040, "total_steps": 58920, "loss": 0.0002, "lr": 1.4756429699769947e-06, "epoch": 2.0400543109300746, "percentage": 40.8, "elapsed_time": "0:38:02", "remaining_time": "0:55:11", "throughput": 10110.72, "total_tokens": 23076288}
{"current_steps": 24045, "total_steps": 58920, "loss": 0.0187, "lr": 1.4753823824664176e-06, "epoch": 2.040478615071283, "percentage": 40.81, "elapsed_time": "0:38:02", "remaining_time": "0:55:10", "throughput": 10111.07, "total_tokens": 23080896}
{"current_steps": 24050, "total_steps": 58920, "loss": 0.0002, "lr": 1.4751217532427528e-06, "epoch": 2.0409029192124915, "percentage": 40.82, "elapsed_time": "0:38:03", "remaining_time": "0:55:10", "throughput": 10111.64, "total_tokens": 23086208}
{"current_steps": 24055, "total_steps": 58920, "loss": 0.0001, "lr": 1.4748610823288691e-06, "epoch": 2.0413272233537, "percentage": 40.83, "elapsed_time": "0:38:03", "remaining_time": "0:55:09", "throughput": 10112.2, "total_tokens": 23091520}
{"current_steps": 24060, "total_steps": 58920, "loss": 0.0005, "lr": 1.4746003697476404e-06, "epoch": 2.0417515274949083, "percentage": 40.84, "elapsed_time": "0:38:03", "remaining_time": "0:55:09", "throughput": 10112.75, "total_tokens": 23096832}
{"current_steps": 24065, "total_steps": 58920, "loss": 0.0001, "lr": 1.4743396155219428e-06, "epoch": 2.0421758316361167, "percentage": 40.84, "elapsed_time": "0:38:04", "remaining_time": "0:55:08", "throughput": 10113.21, "total_tokens": 23101824}
{"current_steps": 24070, "total_steps": 58920, "loss": 0.0213, "lr": 1.4740788196746562e-06, "epoch": 2.042600135777325, "percentage": 40.85, "elapsed_time": "0:38:04", "remaining_time": "0:55:07", "throughput": 10113.53, "total_tokens": 23106432}
{"current_steps": 24075, "total_steps": 58920, "loss": 0.0002, "lr": 1.473817982228665e-06, "epoch": 2.0430244399185336, "percentage": 40.86, "elapsed_time": "0:38:05", "remaining_time": "0:55:07", "throughput": 10113.9, "total_tokens": 23111104}
{"current_steps": 24080, "total_steps": 58920, "loss": 0.024, "lr": 1.4735571032068563e-06, "epoch": 2.043448744059742, "percentage": 40.87, "elapsed_time": "0:38:05", "remaining_time": "0:55:06", "throughput": 10114.41, "total_tokens": 23116288}
{"current_steps": 24085, "total_steps": 58920, "loss": 0.0076, "lr": 1.4732961826321217e-06, "epoch": 2.0438730482009504, "percentage": 40.88, "elapsed_time": "0:38:05", "remaining_time": "0:55:06", "throughput": 10114.77, "total_tokens": 23121024}
{"current_steps": 24090, "total_steps": 58920, "loss": 0.0001, "lr": 1.4730352205273561e-06, "epoch": 2.044297352342159, "percentage": 40.89, "elapsed_time": "0:38:06", "remaining_time": "0:55:05", "throughput": 10114.93, "total_tokens": 23125184}
{"current_steps": 24095, "total_steps": 58920, "loss": 0.0235, "lr": 1.4727742169154577e-06, "epoch": 2.0447216564833672, "percentage": 40.89, "elapsed_time": "0:38:06", "remaining_time": "0:55:04", "throughput": 10115.42, "total_tokens": 23130240}
{"current_steps": 24100, "total_steps": 58920, "loss": 0.0364, "lr": 1.4725131718193287e-06, "epoch": 2.0451459606245757, "percentage": 40.9, "elapsed_time": "0:38:07", "remaining_time": "0:55:04", "throughput": 10115.71, "total_tokens": 23134784}
{"current_steps": 24105, "total_steps": 58920, "loss": 0.0003, "lr": 1.4722520852618746e-06, "epoch": 2.045570264765784, "percentage": 40.91, "elapsed_time": "0:38:07", "remaining_time": "0:55:03", "throughput": 10115.99, "total_tokens": 23139200}
{"current_steps": 24110, "total_steps": 58920, "loss": 0.0306, "lr": 1.4719909572660056e-06, "epoch": 2.0459945689069925, "percentage": 40.92, "elapsed_time": "0:38:07", "remaining_time": "0:55:03", "throughput": 10116.47, "total_tokens": 23144320}
{"current_steps": 24115, "total_steps": 58920, "loss": 0.017, "lr": 1.471729787854634e-06, "epoch": 2.046418873048201, "percentage": 40.93, "elapsed_time": "0:38:08", "remaining_time": "0:55:02", "throughput": 10116.71, "total_tokens": 23148736}
{"current_steps": 24120, "total_steps": 58920, "loss": 0.0003, "lr": 1.4714685770506766e-06, "epoch": 2.0468431771894093, "percentage": 40.94, "elapsed_time": "0:38:08", "remaining_time": "0:55:01", "throughput": 10116.97, "total_tokens": 23153152}
{"current_steps": 24125, "total_steps": 58920, "loss": 0.0, "lr": 1.4712073248770538e-06, "epoch": 2.0472674813306178, "percentage": 40.95, "elapsed_time": "0:38:08", "remaining_time": "0:55:01", "throughput": 10117.39, "total_tokens": 23158016}
{"current_steps": 24130, "total_steps": 58920, "loss": 0.0433, "lr": 1.4709460313566898e-06, "epoch": 2.047691785471826, "percentage": 40.95, "elapsed_time": "0:38:09", "remaining_time": "0:55:00", "throughput": 10117.84, "total_tokens": 23163008}
{"current_steps": 24135, "total_steps": 58920, "loss": 0.0108, "lr": 1.4706846965125112e-06, "epoch": 2.0481160896130346, "percentage": 40.96, "elapsed_time": "0:38:09", "remaining_time": "0:55:00", "throughput": 10118.32, "total_tokens": 23168064}
{"current_steps": 24140, "total_steps": 58920, "loss": 0.0224, "lr": 1.4704233203674505e-06, "epoch": 2.048540393754243, "percentage": 40.97, "elapsed_time": "0:38:10", "remaining_time": "0:54:59", "throughput": 10118.66, "total_tokens": 23172736}
{"current_steps": 24145, "total_steps": 58920, "loss": 0.0095, "lr": 1.4701619029444417e-06, "epoch": 2.0489646978954514, "percentage": 40.98, "elapsed_time": "0:38:10", "remaining_time": "0:54:58", "throughput": 10118.92, "total_tokens": 23177216}
{"current_steps": 24150, "total_steps": 58920, "loss": 0.0001, "lr": 1.4699004442664236e-06, "epoch": 2.04938900203666, "percentage": 40.99, "elapsed_time": "0:38:10", "remaining_time": "0:54:58", "throughput": 10119.39, "total_tokens": 23182272}
{"current_steps": 24155, "total_steps": 58920, "loss": 0.0001, "lr": 1.469638944356338e-06, "epoch": 2.0498133061778683, "percentage": 41.0, "elapsed_time": "0:38:11", "remaining_time": "0:54:57", "throughput": 10119.65, "total_tokens": 23186688}
{"current_steps": 24160, "total_steps": 58920, "loss": 0.0002, "lr": 1.4693774032371304e-06, "epoch": 2.0502376103190767, "percentage": 41.0, "elapsed_time": "0:38:11", "remaining_time": "0:54:57", "throughput": 10120.21, "total_tokens": 23191936}
{"current_steps": 24165, "total_steps": 58920, "loss": 0.0441, "lr": 1.4691158209317505e-06, "epoch": 2.050661914460285, "percentage": 41.01, "elapsed_time": "0:38:12", "remaining_time": "0:54:56", "throughput": 10120.56, "total_tokens": 23196608}
{"current_steps": 24170, "total_steps": 58920, "loss": 0.0001, "lr": 1.4688541974631513e-06, "epoch": 2.0510862186014935, "percentage": 41.02, "elapsed_time": "0:38:12", "remaining_time": "0:54:55", "throughput": 10120.95, "total_tokens": 23201408}
{"current_steps": 24175, "total_steps": 58920, "loss": 0.0002, "lr": 1.4685925328542887e-06, "epoch": 2.051510522742702, "percentage": 41.03, "elapsed_time": "0:38:12", "remaining_time": "0:54:55", "throughput": 10121.24, "total_tokens": 23205888}
{"current_steps": 24180, "total_steps": 58920, "loss": 0.0002, "lr": 1.4683308271281234e-06, "epoch": 2.0519348268839104, "percentage": 41.04, "elapsed_time": "0:38:13", "remaining_time": "0:54:54", "throughput": 10121.76, "total_tokens": 23211008}
{"current_steps": 24185, "total_steps": 58920, "loss": 0.0424, "lr": 1.4680690803076187e-06, "epoch": 2.052359131025119, "percentage": 41.05, "elapsed_time": "0:38:13", "remaining_time": "0:54:54", "throughput": 10122.06, "total_tokens": 23215488}
{"current_steps": 24190, "total_steps": 58920, "loss": 0.0001, "lr": 1.4678072924157425e-06, "epoch": 2.052783435166327, "percentage": 41.06, "elapsed_time": "0:38:13", "remaining_time": "0:54:53", "throughput": 10122.39, "total_tokens": 23220160}
{"current_steps": 24195, "total_steps": 58920, "loss": 0.0001, "lr": 1.4675454634754652e-06, "epoch": 2.0532077393075356, "percentage": 41.06, "elapsed_time": "0:38:14", "remaining_time": "0:54:52", "throughput": 10122.76, "total_tokens": 23224896}
{"current_steps": 24200, "total_steps": 58920, "loss": 0.0068, "lr": 1.4672835935097616e-06, "epoch": 2.053632043448744, "percentage": 41.07, "elapsed_time": "0:38:14", "remaining_time": "0:54:52", "throughput": 10123.14, "total_tokens": 23229632}
{"current_steps": 24205, "total_steps": 58920, "loss": 0.0004, "lr": 1.4670216825416098e-06, "epoch": 2.0540563475899525, "percentage": 41.08, "elapsed_time": "0:38:15", "remaining_time": "0:54:51", "throughput": 10123.43, "total_tokens": 23234112}
{"current_steps": 24210, "total_steps": 58920, "loss": 0.0029, "lr": 1.4667597305939915e-06, "epoch": 2.054480651731161, "percentage": 41.09, "elapsed_time": "0:38:15", "remaining_time": "0:54:51", "throughput": 10123.78, "total_tokens": 23238784}
{"current_steps": 24215, "total_steps": 58920, "loss": 0.032, "lr": 1.4664977376898922e-06, "epoch": 2.0549049558723693, "percentage": 41.1, "elapsed_time": "0:38:15", "remaining_time": "0:54:50", "throughput": 10124.06, "total_tokens": 23243264}
{"current_steps": 24220, "total_steps": 58920, "loss": 0.0042, "lr": 1.4662357038523005e-06, "epoch": 2.0553292600135777, "percentage": 41.11, "elapsed_time": "0:38:16", "remaining_time": "0:54:49", "throughput": 10124.36, "total_tokens": 23247744}
{"current_steps": 24225, "total_steps": 58920, "loss": 0.0001, "lr": 1.4659736291042092e-06, "epoch": 2.055753564154786, "percentage": 41.12, "elapsed_time": "0:38:16", "remaining_time": "0:54:49", "throughput": 10125.01, "total_tokens": 23253312}
{"current_steps": 24230, "total_steps": 58920, "loss": 0.0008, "lr": 1.465711513468614e-06, "epoch": 2.0561778682959946, "percentage": 41.12, "elapsed_time": "0:38:17", "remaining_time": "0:54:48", "throughput": 10125.52, "total_tokens": 23258432}
{"current_steps": 24235, "total_steps": 58920, "loss": 0.0001, "lr": 1.4654493569685156e-06, "epoch": 2.056602172437203, "percentage": 41.13, "elapsed_time": "0:38:17", "remaining_time": "0:54:48", "throughput": 10125.86, "total_tokens": 23263040}
{"current_steps": 24240, "total_steps": 58920, "loss": 0.0341, "lr": 1.4651871596269163e-06, "epoch": 2.0570264765784114, "percentage": 41.14, "elapsed_time": "0:38:17", "remaining_time": "0:54:47", "throughput": 10126.14, "total_tokens": 23267456}
{"current_steps": 24245, "total_steps": 58920, "loss": 0.0323, "lr": 1.4649249214668234e-06, "epoch": 2.05745078071962, "percentage": 41.15, "elapsed_time": "0:38:18", "remaining_time": "0:54:46", "throughput": 10126.57, "total_tokens": 23272320}
{"current_steps": 24250, "total_steps": 58920, "loss": 0.0189, "lr": 1.464662642511247e-06, "epoch": 2.0578750848608283, "percentage": 41.16, "elapsed_time": "0:38:18", "remaining_time": "0:54:46", "throughput": 10127.31, "total_tokens": 23278144}
{"current_steps": 24255, "total_steps": 58920, "loss": 0.0002, "lr": 1.4644003227832014e-06, "epoch": 2.0582993890020367, "percentage": 41.17, "elapsed_time": "0:38:18", "remaining_time": "0:54:45", "throughput": 10127.6, "total_tokens": 23282624}
{"current_steps": 24260, "total_steps": 58920, "loss": 0.0002, "lr": 1.464137962305704e-06, "epoch": 2.058723693143245, "percentage": 41.17, "elapsed_time": "0:38:19", "remaining_time": "0:54:45", "throughput": 10128.12, "total_tokens": 23287744}
{"current_steps": 24265, "total_steps": 58920, "loss": 0.0281, "lr": 1.4638755611017768e-06, "epoch": 2.0591479972844535, "percentage": 41.18, "elapsed_time": "0:38:19", "remaining_time": "0:54:44", "throughput": 10128.39, "total_tokens": 23292160}
{"current_steps": 24270, "total_steps": 58920, "loss": 0.001, "lr": 1.4636131191944437e-06, "epoch": 2.059572301425662, "percentage": 41.19, "elapsed_time": "0:38:20", "remaining_time": "0:54:43", "throughput": 10128.78, "total_tokens": 23296896}
{"current_steps": 24275, "total_steps": 58920, "loss": 0.0001, "lr": 1.4633506366067332e-06, "epoch": 2.0599966055668704, "percentage": 41.2, "elapsed_time": "0:38:20", "remaining_time": "0:54:43", "throughput": 10129.14, "total_tokens": 23301568}
{"current_steps": 24280, "total_steps": 58920, "loss": 0.0399, "lr": 1.4630881133616773e-06, "epoch": 2.060420909708079, "percentage": 41.21, "elapsed_time": "0:38:20", "remaining_time": "0:54:42", "throughput": 10129.49, "total_tokens": 23306240}
{"current_steps": 24285, "total_steps": 58920, "loss": 0.0002, "lr": 1.4628255494823112e-06, "epoch": 2.060845213849287, "percentage": 41.22, "elapsed_time": "0:38:21", "remaining_time": "0:54:41", "throughput": 10130.01, "total_tokens": 23311424}
{"current_steps": 24290, "total_steps": 58920, "loss": 0.0319, "lr": 1.4625629449916742e-06, "epoch": 2.0612695179904956, "percentage": 41.23, "elapsed_time": "0:38:21", "remaining_time": "0:54:41", "throughput": 10130.41, "total_tokens": 23316160}
{"current_steps": 24295, "total_steps": 58920, "loss": 0.0003, "lr": 1.462300299912809e-06, "epoch": 2.061693822131704, "percentage": 41.23, "elapsed_time": "0:38:21", "remaining_time": "0:54:40", "throughput": 10130.73, "total_tokens": 23320704}
{"current_steps": 24300, "total_steps": 58920, "loss": 0.0001, "lr": 1.4620376142687617e-06, "epoch": 2.0621181262729125, "percentage": 41.24, "elapsed_time": "0:38:22", "remaining_time": "0:54:40", "throughput": 10131.26, "total_tokens": 23325888}
{"current_steps": 24305, "total_steps": 58920, "loss": 0.0238, "lr": 1.4617748880825818e-06, "epoch": 2.062542430414121, "percentage": 41.25, "elapsed_time": "0:38:22", "remaining_time": "0:54:39", "throughput": 10131.58, "total_tokens": 23330432}
{"current_steps": 24310, "total_steps": 58920, "loss": 0.0587, "lr": 1.4615121213773224e-06, "epoch": 2.0629667345553293, "percentage": 41.26, "elapsed_time": "0:38:23", "remaining_time": "0:54:38", "throughput": 10131.97, "total_tokens": 23335232}
{"current_steps": 24315, "total_steps": 58920, "loss": 0.0002, "lr": 1.4612493141760412e-06, "epoch": 2.0633910386965377, "percentage": 41.27, "elapsed_time": "0:38:23", "remaining_time": "0:54:38", "throughput": 10132.33, "total_tokens": 23339904}
{"current_steps": 24320, "total_steps": 58920, "loss": 0.0002, "lr": 1.4609864665017977e-06, "epoch": 2.063815342837746, "percentage": 41.28, "elapsed_time": "0:38:23", "remaining_time": "0:54:37", "throughput": 10132.86, "total_tokens": 23345024}
{"current_steps": 24325, "total_steps": 58920, "loss": 0.0003, "lr": 1.4607235783776562e-06, "epoch": 2.0642396469789546, "percentage": 41.28, "elapsed_time": "0:38:24", "remaining_time": "0:54:37", "throughput": 10133.43, "total_tokens": 23350272}
{"current_steps": 24330, "total_steps": 58920, "loss": 0.051, "lr": 1.460460649826684e-06, "epoch": 2.064663951120163, "percentage": 41.29, "elapsed_time": "0:38:24", "remaining_time": "0:54:36", "throughput": 10133.84, "total_tokens": 23355136}
{"current_steps": 24335, "total_steps": 58920, "loss": 0.0245, "lr": 1.4601976808719525e-06, "epoch": 2.0650882552613714, "percentage": 41.3, "elapsed_time": "0:38:25", "remaining_time": "0:54:35", "throughput": 10134.23, "total_tokens": 23359936}
{"current_steps": 24340, "total_steps": 58920, "loss": 0.0002, "lr": 1.459934671536536e-06, "epoch": 2.06551255940258, "percentage": 41.31, "elapsed_time": "0:38:25", "remaining_time": "0:54:35", "throughput": 10134.73, "total_tokens": 23365056}
{"current_steps": 24345, "total_steps": 58920, "loss": 0.0295, "lr": 1.4596716218435125e-06, "epoch": 2.0659368635437882, "percentage": 41.32, "elapsed_time": "0:38:25", "remaining_time": "0:54:34", "throughput": 10135.1, "total_tokens": 23369792}
{"current_steps": 24350, "total_steps": 58920, "loss": 0.0001, "lr": 1.4594085318159637e-06, "epoch": 2.0663611676849967, "percentage": 41.33, "elapsed_time": "0:38:26", "remaining_time": "0:54:34", "throughput": 10135.39, "total_tokens": 23374272}
{"current_steps": 24355, "total_steps": 58920, "loss": 0.0823, "lr": 1.459145401476975e-06, "epoch": 2.066785471826205, "percentage": 41.34, "elapsed_time": "0:38:26", "remaining_time": "0:54:33", "throughput": 10135.66, "total_tokens": 23378688}
{"current_steps": 24360, "total_steps": 58920, "loss": 0.0171, "lr": 1.4588822308496355e-06, "epoch": 2.0672097759674135, "percentage": 41.34, "elapsed_time": "0:38:26", "remaining_time": "0:54:32", "throughput": 10135.86, "total_tokens": 23382912}
{"current_steps": 24365, "total_steps": 58920, "loss": 0.0002, "lr": 1.4586190199570369e-06, "epoch": 2.067634080108622, "percentage": 41.35, "elapsed_time": "0:38:27", "remaining_time": "0:54:32", "throughput": 10136.16, "total_tokens": 23387392}
{"current_steps": 24370, "total_steps": 58920, "loss": 0.0001, "lr": 1.458355768822275e-06, "epoch": 2.0680583842498304, "percentage": 41.36, "elapsed_time": "0:38:27", "remaining_time": "0:54:31", "throughput": 10136.53, "total_tokens": 23392128}
{"current_steps": 24375, "total_steps": 58920, "loss": 0.036, "lr": 1.4580924774684488e-06, "epoch": 2.0684826883910388, "percentage": 41.37, "elapsed_time": "0:38:28", "remaining_time": "0:54:31", "throughput": 10136.87, "total_tokens": 23396736}
{"current_steps": 24380, "total_steps": 58920, "loss": 0.0014, "lr": 1.4578291459186623e-06, "epoch": 2.068906992532247, "percentage": 41.38, "elapsed_time": "0:38:28", "remaining_time": "0:54:30", "throughput": 10137.33, "total_tokens": 23401728}
{"current_steps": 24385, "total_steps": 58920, "loss": 0.0007, "lr": 1.457565774196021e-06, "epoch": 2.0693312966734556, "percentage": 41.39, "elapsed_time": "0:38:28", "remaining_time": "0:54:29", "throughput": 10137.81, "total_tokens": 23406784}
{"current_steps": 24390, "total_steps": 58920, "loss": 0.0002, "lr": 1.4573023623236349e-06, "epoch": 2.069755600814664, "percentage": 41.4, "elapsed_time": "0:38:29", "remaining_time": "0:54:29", "throughput": 10138.54, "total_tokens": 23412544}
{"current_steps": 24395, "total_steps": 58920, "loss": 0.0001, "lr": 1.4570389103246179e-06, "epoch": 2.0701799049558725, "percentage": 41.4, "elapsed_time": "0:38:29", "remaining_time": "0:54:28", "throughput": 10139.35, "total_tokens": 23418624}
{"current_steps": 24400, "total_steps": 58920, "loss": 0.0005, "lr": 1.4567754182220867e-06, "epoch": 2.070604209097081, "percentage": 41.41, "elapsed_time": "0:38:30", "remaining_time": "0:54:28", "throughput": 10139.75, "total_tokens": 23423424}
{"current_steps": 24405, "total_steps": 58920, "loss": 0.0225, "lr": 1.4565118860391612e-06, "epoch": 2.0710285132382893, "percentage": 41.42, "elapsed_time": "0:38:30", "remaining_time": "0:54:27", "throughput": 10140.05, "total_tokens": 23427904}
{"current_steps": 24410, "total_steps": 58920, "loss": 0.019, "lr": 1.4562483137989663e-06, "epoch": 2.0714528173794977, "percentage": 41.43, "elapsed_time": "0:38:30", "remaining_time": "0:54:26", "throughput": 10140.37, "total_tokens": 23432512}
{"current_steps": 24415, "total_steps": 58920, "loss": 0.0005, "lr": 1.4559847015246291e-06, "epoch": 2.071877121520706, "percentage": 41.44, "elapsed_time": "0:38:31", "remaining_time": "0:54:26", "throughput": 10140.78, "total_tokens": 23437312}
{"current_steps": 24420, "total_steps": 58920, "loss": 0.0006, "lr": 1.4557210492392806e-06, "epoch": 2.0723014256619146, "percentage": 41.45, "elapsed_time": "0:38:31", "remaining_time": "0:54:25", "throughput": 10141.04, "total_tokens": 23441728}
{"current_steps": 24425, "total_steps": 58920, "loss": 0.034, "lr": 1.4554573569660555e-06, "epoch": 2.072725729803123, "percentage": 41.45, "elapsed_time": "0:38:31", "remaining_time": "0:54:25", "throughput": 10141.62, "total_tokens": 23447040}
{"current_steps": 24430, "total_steps": 58920, "loss": 0.0339, "lr": 1.4551936247280917e-06, "epoch": 2.0731500339443314, "percentage": 41.46, "elapsed_time": "0:38:32", "remaining_time": "0:54:24", "throughput": 10142.05, "total_tokens": 23451904}
{"current_steps": 24435, "total_steps": 58920, "loss": 0.0003, "lr": 1.454929852548531e-06, "epoch": 2.07357433808554, "percentage": 41.47, "elapsed_time": "0:38:32", "remaining_time": "0:54:23", "throughput": 10142.54, "total_tokens": 23456960}
{"current_steps": 24440, "total_steps": 58920, "loss": 0.0034, "lr": 1.4546660404505178e-06, "epoch": 2.0739986422267482, "percentage": 41.48, "elapsed_time": "0:38:33", "remaining_time": "0:54:23", "throughput": 10143.11, "total_tokens": 23462272}
{"current_steps": 24445, "total_steps": 58920, "loss": 0.0002, "lr": 1.4544021884572016e-06, "epoch": 2.0744229463679567, "percentage": 41.49, "elapsed_time": "0:38:33", "remaining_time": "0:54:22", "throughput": 10143.36, "total_tokens": 23466624}
{"current_steps": 24450, "total_steps": 58920, "loss": 0.011, "lr": 1.4541382965917336e-06, "epoch": 2.074847250509165, "percentage": 41.5, "elapsed_time": "0:38:33", "remaining_time": "0:54:22", "throughput": 10143.78, "total_tokens": 23471488}
{"current_steps": 24455, "total_steps": 58920, "loss": 0.0003, "lr": 1.45387436487727e-06, "epoch": 2.0752715546503735, "percentage": 41.51, "elapsed_time": "0:38:34", "remaining_time": "0:54:21", "throughput": 10144.14, "total_tokens": 23476160}
{"current_steps": 24460, "total_steps": 58920, "loss": 0.0001, "lr": 1.4536103933369695e-06, "epoch": 2.075695858791582, "percentage": 41.51, "elapsed_time": "0:38:34", "remaining_time": "0:54:20", "throughput": 10144.6, "total_tokens": 23481152}
{"current_steps": 24465, "total_steps": 58920, "loss": 0.0319, "lr": 1.4533463819939948e-06, "epoch": 2.0761201629327903, "percentage": 41.52, "elapsed_time": "0:38:35", "remaining_time": "0:54:20", "throughput": 10144.88, "total_tokens": 23485568}
{"current_steps": 24470, "total_steps": 58920, "loss": 0.0309, "lr": 1.4530823308715117e-06, "epoch": 2.0765444670739988, "percentage": 41.53, "elapsed_time": "0:38:35", "remaining_time": "0:54:19", "throughput": 10145.35, "total_tokens": 23490560}
{"current_steps": 24475, "total_steps": 58920, "loss": 0.0001, "lr": 1.4528182399926899e-06, "epoch": 2.076968771215207, "percentage": 41.54, "elapsed_time": "0:38:35", "remaining_time": "0:54:19", "throughput": 10145.68, "total_tokens": 23495168}
{"current_steps": 24480, "total_steps": 58920, "loss": 0.0, "lr": 1.4525541093807025e-06, "epoch": 2.0773930753564156, "percentage": 41.55, "elapsed_time": "0:38:36", "remaining_time": "0:54:18", "throughput": 10146.26, "total_tokens": 23500544}
{"current_steps": 24485, "total_steps": 58920, "loss": 0.0001, "lr": 1.4522899390587262e-06, "epoch": 2.077817379497624, "percentage": 41.56, "elapsed_time": "0:38:36", "remaining_time": "0:54:17", "throughput": 10146.8, "total_tokens": 23505792}
{"current_steps": 24490, "total_steps": 58920, "loss": 0.0001, "lr": 1.4520257290499407e-06, "epoch": 2.0782416836388324, "percentage": 41.56, "elapsed_time": "0:38:36", "remaining_time": "0:54:17", "throughput": 10147.13, "total_tokens": 23510400}
{"current_steps": 24495, "total_steps": 58920, "loss": 0.0, "lr": 1.4517614793775293e-06, "epoch": 2.078665987780041, "percentage": 41.57, "elapsed_time": "0:38:37", "remaining_time": "0:54:16", "throughput": 10147.78, "total_tokens": 23515968}
{"current_steps": 24500, "total_steps": 58920, "loss": 0.0001, "lr": 1.451497190064679e-06, "epoch": 2.0790902919212493, "percentage": 41.58, "elapsed_time": "0:38:37", "remaining_time": "0:54:16", "throughput": 10148.17, "total_tokens": 23520704}
{"current_steps": 24505, "total_steps": 58920, "loss": 0.0007, "lr": 1.4512328611345805e-06, "epoch": 2.0795145960624577, "percentage": 41.59, "elapsed_time": "0:38:38", "remaining_time": "0:54:15", "throughput": 10148.65, "total_tokens": 23525760}
{"current_steps": 24510, "total_steps": 58920, "loss": 0.0, "lr": 1.4509684926104279e-06, "epoch": 2.079938900203666, "percentage": 41.6, "elapsed_time": "0:38:38", "remaining_time": "0:54:14", "throughput": 10149.09, "total_tokens": 23530688}
{"current_steps": 24515, "total_steps": 58920, "loss": 0.0309, "lr": 1.4507040845154182e-06, "epoch": 2.0803632043448745, "percentage": 41.61, "elapsed_time": "0:38:38", "remaining_time": "0:54:14", "throughput": 10149.35, "total_tokens": 23535104}
{"current_steps": 24520, "total_steps": 58920, "loss": 0.0, "lr": 1.4504396368727522e-06, "epoch": 2.080787508486083, "percentage": 41.62, "elapsed_time": "0:38:39", "remaining_time": "0:54:13", "throughput": 10149.82, "total_tokens": 23540096}
{"current_steps": 24525, "total_steps": 58920, "loss": 0.0001, "lr": 1.4501751497056344e-06, "epoch": 2.0812118126272914, "percentage": 41.62, "elapsed_time": "0:38:39", "remaining_time": "0:54:13", "throughput": 10150.41, "total_tokens": 23545472}
{"current_steps": 24530, "total_steps": 58920, "loss": 0.0257, "lr": 1.4499106230372724e-06, "epoch": 2.0816361167685, "percentage": 41.63, "elapsed_time": "0:38:40", "remaining_time": "0:54:12", "throughput": 10150.69, "total_tokens": 23549952}
{"current_steps": 24535, "total_steps": 58920, "loss": 0.0001, "lr": 1.4496460568908778e-06, "epoch": 2.082060420909708, "percentage": 41.64, "elapsed_time": "0:38:40", "remaining_time": "0:54:11", "throughput": 10150.94, "total_tokens": 23554304}
{"current_steps": 24540, "total_steps": 58920, "loss": 0.0, "lr": 1.4493814512896651e-06, "epoch": 2.0824847250509166, "percentage": 41.65, "elapsed_time": "0:38:40", "remaining_time": "0:54:11", "throughput": 10151.54, "total_tokens": 23559744}
{"current_steps": 24545, "total_steps": 58920, "loss": 0.0, "lr": 1.4491168062568526e-06, "epoch": 2.082909029192125, "percentage": 41.66, "elapsed_time": "0:38:41", "remaining_time": "0:54:10", "throughput": 10151.94, "total_tokens": 23564544}
{"current_steps": 24550, "total_steps": 58920, "loss": 0.0001, "lr": 1.4488521218156619e-06, "epoch": 2.0833333333333335, "percentage": 41.67, "elapsed_time": "0:38:41", "remaining_time": "0:54:10", "throughput": 10152.45, "total_tokens": 23569664}
{"current_steps": 24555, "total_steps": 58920, "loss": 0.0724, "lr": 1.448587397989318e-06, "epoch": 2.083757637474542, "percentage": 41.68, "elapsed_time": "0:38:41", "remaining_time": "0:54:09", "throughput": 10152.92, "total_tokens": 23574656}
{"current_steps": 24560, "total_steps": 58920, "loss": 0.0923, "lr": 1.4483226348010498e-06, "epoch": 2.0841819416157503, "percentage": 41.68, "elapsed_time": "0:38:42", "remaining_time": "0:54:09", "throughput": 10153.3, "total_tokens": 23579392}
{"current_steps": 24565, "total_steps": 58920, "loss": 0.0327, "lr": 1.4480578322740885e-06, "epoch": 2.0846062457569587, "percentage": 41.69, "elapsed_time": "0:38:42", "remaining_time": "0:54:08", "throughput": 10153.75, "total_tokens": 23584320}
{"current_steps": 24570, "total_steps": 58920, "loss": 0.0001, "lr": 1.4477929904316708e-06, "epoch": 2.085030549898167, "percentage": 41.7, "elapsed_time": "0:38:43", "remaining_time": "0:54:07", "throughput": 10154.36, "total_tokens": 23589760}
{"current_steps": 24575, "total_steps": 58920, "loss": 0.0145, "lr": 1.4475281092970347e-06, "epoch": 2.0854548540393756, "percentage": 41.71, "elapsed_time": "0:38:43", "remaining_time": "0:54:07", "throughput": 10154.8, "total_tokens": 23594752}
{"current_steps": 24580, "total_steps": 58920, "loss": 0.0156, "lr": 1.4472631888934226e-06, "epoch": 2.085879158180584, "percentage": 41.72, "elapsed_time": "0:38:43", "remaining_time": "0:54:06", "throughput": 10155.12, "total_tokens": 23599296}
{"current_steps": 24585, "total_steps": 58920, "loss": 0.0003, "lr": 1.4469982292440805e-06, "epoch": 2.0863034623217924, "percentage": 41.73, "elapsed_time": "0:38:44", "remaining_time": "0:54:06", "throughput": 10155.39, "total_tokens": 23603776}
{"current_steps": 24590, "total_steps": 58920, "loss": 0.0413, "lr": 1.446733230372258e-06, "epoch": 2.086727766463001, "percentage": 41.73, "elapsed_time": "0:38:44", "remaining_time": "0:54:05", "throughput": 10155.66, "total_tokens": 23608128}
{"current_steps": 24595, "total_steps": 58920, "loss": 0.0002, "lr": 1.4464681923012069e-06, "epoch": 2.0871520706042093, "percentage": 41.74, "elapsed_time": "0:38:45", "remaining_time": "0:54:04", "throughput": 10156.07, "total_tokens": 23612992}
{"current_steps": 24600, "total_steps": 58920, "loss": 0.0001, "lr": 1.4462031150541843e-06, "epoch": 2.0875763747454177, "percentage": 41.75, "elapsed_time": "0:38:45", "remaining_time": "0:54:04", "throughput": 10156.35, "total_tokens": 23617472}
{"current_steps": 24605, "total_steps": 58920, "loss": 0.0001, "lr": 1.4459379986544494e-06, "epoch": 2.088000678886626, "percentage": 41.76, "elapsed_time": "0:38:45", "remaining_time": "0:54:03", "throughput": 10156.88, "total_tokens": 23622656}
{"current_steps": 24610, "total_steps": 58920, "loss": 0.0212, "lr": 1.4456728431252652e-06, "epoch": 2.0884249830278345, "percentage": 41.77, "elapsed_time": "0:38:46", "remaining_time": "0:54:03", "throughput": 10157.18, "total_tokens": 23627200}
{"current_steps": 24615, "total_steps": 58920, "loss": 0.0001, "lr": 1.445407648489898e-06, "epoch": 2.088849287169043, "percentage": 41.78, "elapsed_time": "0:38:46", "remaining_time": "0:54:02", "throughput": 10157.67, "total_tokens": 23632256}
{"current_steps": 24620, "total_steps": 58920, "loss": 0.0365, "lr": 1.4451424147716176e-06, "epoch": 2.0892735913102514, "percentage": 41.79, "elapsed_time": "0:38:46", "remaining_time": "0:54:01", "throughput": 10158.14, "total_tokens": 23637248}
{"current_steps": 24625, "total_steps": 58920, "loss": 0.0279, "lr": 1.4448771419936977e-06, "epoch": 2.08969789545146, "percentage": 41.79, "elapsed_time": "0:38:47", "remaining_time": "0:54:01", "throughput": 10158.4, "total_tokens": 23641664}
{"current_steps": 24630, "total_steps": 58920, "loss": 0.0001, "lr": 1.4446118301794145e-06, "epoch": 2.090122199592668, "percentage": 41.8, "elapsed_time": "0:38:47", "remaining_time": "0:54:00", "throughput": 10158.8, "total_tokens": 23646464}
{"current_steps": 24635, "total_steps": 58920, "loss": 0.0377, "lr": 1.444346479352049e-06, "epoch": 2.0905465037338766, "percentage": 41.81, "elapsed_time": "0:38:48", "remaining_time": "0:54:00", "throughput": 10159.08, "total_tokens": 23650944}
{"current_steps": 24640, "total_steps": 58920, "loss": 0.0001, "lr": 1.4440810895348841e-06, "epoch": 2.090970807875085, "percentage": 41.82, "elapsed_time": "0:38:48", "remaining_time": "0:53:59", "throughput": 10159.39, "total_tokens": 23655488}
{"current_steps": 24645, "total_steps": 58920, "loss": 0.0003, "lr": 1.4438156607512067e-06, "epoch": 2.0913951120162935, "percentage": 41.83, "elapsed_time": "0:38:48", "remaining_time": "0:53:58", "throughput": 10159.68, "total_tokens": 23659968}
{"current_steps": 24650, "total_steps": 58920, "loss": 0.0065, "lr": 1.4435501930243074e-06, "epoch": 2.091819416157502, "percentage": 41.84, "elapsed_time": "0:38:49", "remaining_time": "0:53:58", "throughput": 10160.19, "total_tokens": 23665152}
{"current_steps": 24655, "total_steps": 58920, "loss": 0.0395, "lr": 1.4432846863774804e-06, "epoch": 2.0922437202987103, "percentage": 41.84, "elapsed_time": "0:38:49", "remaining_time": "0:53:57", "throughput": 10160.59, "total_tokens": 23670016}
{"current_steps": 24660, "total_steps": 58920, "loss": 0.0296, "lr": 1.4430191408340227e-06, "epoch": 2.0926680244399187, "percentage": 41.85, "elapsed_time": "0:38:49", "remaining_time": "0:53:57", "throughput": 10160.97, "total_tokens": 23674816}
{"current_steps": 24665, "total_steps": 58920, "loss": 0.0003, "lr": 1.4427535564172345e-06, "epoch": 2.093092328581127, "percentage": 41.86, "elapsed_time": "0:38:50", "remaining_time": "0:53:56", "throughput": 10161.49, "total_tokens": 23680000}
{"current_steps": 24670, "total_steps": 58920, "loss": 0.0003, "lr": 1.4424879331504205e-06, "epoch": 2.0935166327223356, "percentage": 41.87, "elapsed_time": "0:38:50", "remaining_time": "0:53:55", "throughput": 10161.83, "total_tokens": 23684608}
{"current_steps": 24675, "total_steps": 58920, "loss": 0.0003, "lr": 1.4422222710568881e-06, "epoch": 2.093940936863544, "percentage": 41.88, "elapsed_time": "0:38:51", "remaining_time": "0:53:55", "throughput": 10162.15, "total_tokens": 23689152}
{"current_steps": 24680, "total_steps": 58920, "loss": 0.0003, "lr": 1.441956570159948e-06, "epoch": 2.0943652410047524, "percentage": 41.89, "elapsed_time": "0:38:51", "remaining_time": "0:53:54", "throughput": 10162.49, "total_tokens": 23693824}
{"current_steps": 24685, "total_steps": 58920, "loss": 0.0001, "lr": 1.4416908304829141e-06, "epoch": 2.094789545145961, "percentage": 41.9, "elapsed_time": "0:38:51", "remaining_time": "0:53:54", "throughput": 10162.79, "total_tokens": 23698368}
{"current_steps": 24690, "total_steps": 58920, "loss": 0.0003, "lr": 1.441425052049105e-06, "epoch": 2.0952138492871692, "percentage": 41.9, "elapsed_time": "0:38:52", "remaining_time": "0:53:53", "throughput": 10163.04, "total_tokens": 23702784}
{"current_steps": 24695, "total_steps": 58920, "loss": 0.0001, "lr": 1.4411592348818413e-06, "epoch": 2.0956381534283777, "percentage": 41.91, "elapsed_time": "0:38:52", "remaining_time": "0:53:52", "throughput": 10163.38, "total_tokens": 23707456}
{"current_steps": 24700, "total_steps": 58920, "loss": 0.0001, "lr": 1.4408933790044476e-06, "epoch": 2.096062457569586, "percentage": 41.92, "elapsed_time": "0:38:53", "remaining_time": "0:53:52", "throughput": 10163.92, "total_tokens": 23712704}
{"current_steps": 24705, "total_steps": 58920, "loss": 0.0001, "lr": 1.4406274844402515e-06, "epoch": 2.0964867617107945, "percentage": 41.93, "elapsed_time": "0:38:53", "remaining_time": "0:53:51", "throughput": 10164.5, "total_tokens": 23718080}
{"current_steps": 24710, "total_steps": 58920, "loss": 0.0001, "lr": 1.440361551212585e-06, "epoch": 2.0969110658520025, "percentage": 41.94, "elapsed_time": "0:38:53", "remaining_time": "0:53:51", "throughput": 10165.08, "total_tokens": 23723520}
{"current_steps": 24715, "total_steps": 58920, "loss": 0.0001, "lr": 1.4400955793447815e-06, "epoch": 2.0973353699932114, "percentage": 41.95, "elapsed_time": "0:38:54", "remaining_time": "0:53:50", "throughput": 10165.53, "total_tokens": 23728512}
{"current_steps": 24720, "total_steps": 58920, "loss": 0.0005, "lr": 1.4398295688601802e-06, "epoch": 2.0977596741344193, "percentage": 41.96, "elapsed_time": "0:38:54", "remaining_time": "0:53:49", "throughput": 10165.78, "total_tokens": 23732928}
{"current_steps": 24725, "total_steps": 58920, "loss": 0.0, "lr": 1.4395635197821226e-06, "epoch": 2.098183978275628, "percentage": 41.96, "elapsed_time": "0:38:54", "remaining_time": "0:53:49", "throughput": 10166.29, "total_tokens": 23738048}
{"current_steps": 24730, "total_steps": 58920, "loss": 0.0244, "lr": 1.4392974321339529e-06, "epoch": 2.098608282416836, "percentage": 41.97, "elapsed_time": "0:38:55", "remaining_time": "0:53:48", "throughput": 10166.59, "total_tokens": 23742592}
{"current_steps": 24735, "total_steps": 58920, "loss": 0.0, "lr": 1.4390313059390197e-06, "epoch": 2.099032586558045, "percentage": 41.98, "elapsed_time": "0:38:55", "remaining_time": "0:53:48", "throughput": 10166.8, "total_tokens": 23746880}
{"current_steps": 24740, "total_steps": 58920, "loss": 0.0286, "lr": 1.4387651412206745e-06, "epoch": 2.099456890699253, "percentage": 41.99, "elapsed_time": "0:38:56", "remaining_time": "0:53:47", "throughput": 10167.06, "total_tokens": 23751296}
{"current_steps": 24745, "total_steps": 58920, "loss": 0.0507, "lr": 1.438498938002272e-06, "epoch": 2.0998811948404614, "percentage": 42.0, "elapsed_time": "0:38:56", "remaining_time": "0:53:46", "throughput": 10167.38, "total_tokens": 23755840}
{"current_steps": 24750, "total_steps": 58920, "loss": 0.0306, "lr": 1.438232696307171e-06, "epoch": 2.10030549898167, "percentage": 42.01, "elapsed_time": "0:38:56", "remaining_time": "0:53:46", "throughput": 10167.85, "total_tokens": 23760960}
{"current_steps": 24755, "total_steps": 58920, "loss": 0.0246, "lr": 1.4379664161587335e-06, "epoch": 2.1007298031228783, "percentage": 42.01, "elapsed_time": "0:38:57", "remaining_time": "0:53:45", "throughput": 10168.36, "total_tokens": 23766080}
{"current_steps": 24760, "total_steps": 58920, "loss": 0.0222, "lr": 1.437700097580324e-06, "epoch": 2.1011541072640867, "percentage": 42.02, "elapsed_time": "0:38:57", "remaining_time": "0:53:45", "throughput": 10168.68, "total_tokens": 23770688}
{"current_steps": 24765, "total_steps": 58920, "loss": 0.0003, "lr": 1.4374337405953113e-06, "epoch": 2.101578411405295, "percentage": 42.03, "elapsed_time": "0:38:58", "remaining_time": "0:53:44", "throughput": 10169.44, "total_tokens": 23776640}
{"current_steps": 24770, "total_steps": 58920, "loss": 0.0002, "lr": 1.437167345227067e-06, "epoch": 2.1020027155465035, "percentage": 42.04, "elapsed_time": "0:38:58", "remaining_time": "0:53:43", "throughput": 10169.73, "total_tokens": 23781120}
{"current_steps": 24775, "total_steps": 58920, "loss": 0.0002, "lr": 1.436900911498967e-06, "epoch": 2.102427019687712, "percentage": 42.05, "elapsed_time": "0:38:58", "remaining_time": "0:53:43", "throughput": 10170.31, "total_tokens": 23786560}
{"current_steps": 24780, "total_steps": 58920, "loss": 0.0163, "lr": 1.436634439434389e-06, "epoch": 2.1028513238289204, "percentage": 42.06, "elapsed_time": "0:38:59", "remaining_time": "0:53:42", "throughput": 10170.73, "total_tokens": 23791424}
{"current_steps": 24785, "total_steps": 58920, "loss": 0.0001, "lr": 1.4363679290567156e-06, "epoch": 2.103275627970129, "percentage": 42.07, "elapsed_time": "0:38:59", "remaining_time": "0:53:42", "throughput": 10171.1, "total_tokens": 23796160}
{"current_steps": 24790, "total_steps": 58920, "loss": 0.0008, "lr": 1.4361013803893317e-06, "epoch": 2.103699932111337, "percentage": 42.07, "elapsed_time": "0:38:59", "remaining_time": "0:53:41", "throughput": 10171.41, "total_tokens": 23800704}
{"current_steps": 24795, "total_steps": 58920, "loss": 0.0002, "lr": 1.4358347934556268e-06, "epoch": 2.1041242362525456, "percentage": 42.08, "elapsed_time": "0:39:00", "remaining_time": "0:53:40", "throughput": 10171.66, "total_tokens": 23805120}
{"current_steps": 24800, "total_steps": 58920, "loss": 0.0051, "lr": 1.4355681682789917e-06, "epoch": 2.104548540393754, "percentage": 42.09, "elapsed_time": "0:39:00", "remaining_time": "0:53:40", "throughput": 10172.03, "total_tokens": 23809856}
{"current_steps": 24805, "total_steps": 58920, "loss": 0.0004, "lr": 1.4353015048828228e-06, "epoch": 2.1049728445349625, "percentage": 42.1, "elapsed_time": "0:39:01", "remaining_time": "0:53:39", "throughput": 10172.39, "total_tokens": 23814592}
{"current_steps": 24810, "total_steps": 58920, "loss": 0.0327, "lr": 1.4350348032905183e-06, "epoch": 2.105397148676171, "percentage": 42.11, "elapsed_time": "0:39:01", "remaining_time": "0:53:39", "throughput": 10172.6, "total_tokens": 23818880}
{"current_steps": 24815, "total_steps": 58920, "loss": 0.0318, "lr": 1.4347680635254805e-06, "epoch": 2.1058214528173793, "percentage": 42.12, "elapsed_time": "0:39:01", "remaining_time": "0:53:38", "throughput": 10173.08, "total_tokens": 23823936}
{"current_steps": 24820, "total_steps": 58920, "loss": 0.0001, "lr": 1.434501285611115e-06, "epoch": 2.1062457569585877, "percentage": 42.12, "elapsed_time": "0:39:02", "remaining_time": "0:53:38", "throughput": 10173.68, "total_tokens": 23829376}
{"current_steps": 24825, "total_steps": 58920, "loss": 0.0002, "lr": 1.4342344695708307e-06, "epoch": 2.106670061099796, "percentage": 42.13, "elapsed_time": "0:39:02", "remaining_time": "0:53:37", "throughput": 10174.01, "total_tokens": 23833984}
{"current_steps": 24830, "total_steps": 58920, "loss": 0.0383, "lr": 1.433967615428039e-06, "epoch": 2.1070943652410046, "percentage": 42.14, "elapsed_time": "0:39:03", "remaining_time": "0:53:36", "throughput": 10174.35, "total_tokens": 23838656}
{"current_steps": 24835, "total_steps": 58920, "loss": 0.0372, "lr": 1.433700723206156e-06, "epoch": 2.107518669382213, "percentage": 42.15, "elapsed_time": "0:39:03", "remaining_time": "0:53:36", "throughput": 10174.57, "total_tokens": 23842944}
{"current_steps": 24840, "total_steps": 58920, "loss": 0.0445, "lr": 1.4334337929286004e-06, "epoch": 2.1079429735234214, "percentage": 42.16, "elapsed_time": "0:39:03", "remaining_time": "0:53:35", "throughput": 10174.96, "total_tokens": 23847744}
{"current_steps": 24845, "total_steps": 58920, "loss": 0.0001, "lr": 1.4331668246187944e-06, "epoch": 2.10836727766463, "percentage": 42.17, "elapsed_time": "0:39:04", "remaining_time": "0:53:35", "throughput": 10175.26, "total_tokens": 23852288}
{"current_steps": 24850, "total_steps": 58920, "loss": 0.0202, "lr": 1.4328998183001635e-06, "epoch": 2.1087915818058383, "percentage": 42.18, "elapsed_time": "0:39:04", "remaining_time": "0:53:34", "throughput": 10175.52, "total_tokens": 23856704}
{"current_steps": 24855, "total_steps": 58920, "loss": 0.0002, "lr": 1.4326327739961368e-06, "epoch": 2.1092158859470467, "percentage": 42.18, "elapsed_time": "0:39:04", "remaining_time": "0:53:33", "throughput": 10175.82, "total_tokens": 23861248}
{"current_steps": 24860, "total_steps": 58920, "loss": 0.0002, "lr": 1.432365691730146e-06, "epoch": 2.109640190088255, "percentage": 42.19, "elapsed_time": "0:39:05", "remaining_time": "0:53:33", "throughput": 10176.11, "total_tokens": 23865792}
{"current_steps": 24865, "total_steps": 58920, "loss": 0.0573, "lr": 1.4320985715256265e-06, "epoch": 2.1100644942294635, "percentage": 42.2, "elapsed_time": "0:39:05", "remaining_time": "0:53:32", "throughput": 10176.21, "total_tokens": 23869760}
{"current_steps": 24870, "total_steps": 58920, "loss": 0.0001, "lr": 1.4318314134060177e-06, "epoch": 2.110488798370672, "percentage": 42.21, "elapsed_time": "0:39:06", "remaining_time": "0:53:31", "throughput": 10176.45, "total_tokens": 23874176}
{"current_steps": 24875, "total_steps": 58920, "loss": 0.039, "lr": 1.4315642173947615e-06, "epoch": 2.1109131025118804, "percentage": 42.22, "elapsed_time": "0:39:06", "remaining_time": "0:53:31", "throughput": 10176.62, "total_tokens": 23878336}
{"current_steps": 24880, "total_steps": 58920, "loss": 0.0003, "lr": 1.4312969835153034e-06, "epoch": 2.1113374066530888, "percentage": 42.23, "elapsed_time": "0:39:06", "remaining_time": "0:53:30", "throughput": 10176.97, "total_tokens": 23883008}
{"current_steps": 24885, "total_steps": 58920, "loss": 0.0004, "lr": 1.4310297117910924e-06, "epoch": 2.111761710794297, "percentage": 42.24, "elapsed_time": "0:39:07", "remaining_time": "0:53:30", "throughput": 10177.42, "total_tokens": 23888000}
{"current_steps": 24890, "total_steps": 58920, "loss": 0.0005, "lr": 1.43076240224558e-06, "epoch": 2.1121860149355056, "percentage": 42.24, "elapsed_time": "0:39:07", "remaining_time": "0:53:29", "throughput": 10177.89, "total_tokens": 23893056}
{"current_steps": 24895, "total_steps": 58920, "loss": 0.0003, "lr": 1.4304950549022224e-06, "epoch": 2.112610319076714, "percentage": 42.25, "elapsed_time": "0:39:07", "remaining_time": "0:53:28", "throughput": 10178.15, "total_tokens": 23897472}
{"current_steps": 24900, "total_steps": 58920, "loss": 0.0001, "lr": 1.4302276697844774e-06, "epoch": 2.1130346232179225, "percentage": 42.26, "elapsed_time": "0:39:08", "remaining_time": "0:53:28", "throughput": 10178.58, "total_tokens": 23902400}
{"current_steps": 24905, "total_steps": 58920, "loss": 0.0002, "lr": 1.4299602469158085e-06, "epoch": 2.113458927359131, "percentage": 42.27, "elapsed_time": "0:39:08", "remaining_time": "0:53:27", "throughput": 10178.84, "total_tokens": 23906816}
{"current_steps": 24910, "total_steps": 58920, "loss": 0.0232, "lr": 1.42969278631968e-06, "epoch": 2.1138832315003393, "percentage": 42.28, "elapsed_time": "0:39:09", "remaining_time": "0:53:27", "throughput": 10179.19, "total_tokens": 23911488}
{"current_steps": 24915, "total_steps": 58920, "loss": 0.0002, "lr": 1.4294252880195608e-06, "epoch": 2.1143075356415477, "percentage": 42.29, "elapsed_time": "0:39:09", "remaining_time": "0:53:26", "throughput": 10179.42, "total_tokens": 23915840}
{"current_steps": 24920, "total_steps": 58920, "loss": 0.0005, "lr": 1.4291577520389231e-06, "epoch": 2.114731839782756, "percentage": 42.29, "elapsed_time": "0:39:09", "remaining_time": "0:53:26", "throughput": 10179.73, "total_tokens": 23920448}
{"current_steps": 24925, "total_steps": 58920, "loss": 0.0335, "lr": 1.4288901784012422e-06, "epoch": 2.1151561439239646, "percentage": 42.3, "elapsed_time": "0:39:10", "remaining_time": "0:53:25", "throughput": 10179.99, "total_tokens": 23924864}
{"current_steps": 24930, "total_steps": 58920, "loss": 0.0144, "lr": 1.4286225671299962e-06, "epoch": 2.115580448065173, "percentage": 42.31, "elapsed_time": "0:39:10", "remaining_time": "0:53:24", "throughput": 10180.25, "total_tokens": 23929280}
{"current_steps": 24935, "total_steps": 58920, "loss": 0.0003, "lr": 1.4283549182486678e-06, "epoch": 2.1160047522063814, "percentage": 42.32, "elapsed_time": "0:39:10", "remaining_time": "0:53:24", "throughput": 10180.5, "total_tokens": 23933632}
{"current_steps": 24940, "total_steps": 58920, "loss": 0.0002, "lr": 1.428087231780742e-06, "epoch": 2.11642905634759, "percentage": 42.33, "elapsed_time": "0:39:11", "remaining_time": "0:53:23", "throughput": 10180.9, "total_tokens": 23938496}
{"current_steps": 24945, "total_steps": 58920, "loss": 0.0509, "lr": 1.4278195077497072e-06, "epoch": 2.1168533604887982, "percentage": 42.34, "elapsed_time": "0:39:11", "remaining_time": "0:53:23", "throughput": 10181.43, "total_tokens": 23943744}
{"current_steps": 24950, "total_steps": 58920, "loss": 0.0001, "lr": 1.4275517461790551e-06, "epoch": 2.1172776646300067, "percentage": 42.35, "elapsed_time": "0:39:12", "remaining_time": "0:53:22", "throughput": 10181.82, "total_tokens": 23948608}
{"current_steps": 24955, "total_steps": 58920, "loss": 0.0155, "lr": 1.427283947092281e-06, "epoch": 2.117701968771215, "percentage": 42.35, "elapsed_time": "0:39:12", "remaining_time": "0:53:21", "throughput": 10182.33, "total_tokens": 23953792}
{"current_steps": 24960, "total_steps": 58920, "loss": 0.0001, "lr": 1.4270161105128834e-06, "epoch": 2.1181262729124235, "percentage": 42.36, "elapsed_time": "0:39:12", "remaining_time": "0:53:21", "throughput": 10182.71, "total_tokens": 23958592}
{"current_steps": 24965, "total_steps": 58920, "loss": 0.0003, "lr": 1.4267482364643635e-06, "epoch": 2.118550577053632, "percentage": 42.37, "elapsed_time": "0:39:13", "remaining_time": "0:53:20", "throughput": 10182.96, "total_tokens": 23963008}
{"current_steps": 24970, "total_steps": 58920, "loss": 0.0001, "lr": 1.426480324970227e-06, "epoch": 2.1189748811948403, "percentage": 42.38, "elapsed_time": "0:39:13", "remaining_time": "0:53:20", "throughput": 10183.21, "total_tokens": 23967424}
{"current_steps": 24975, "total_steps": 58920, "loss": 0.0001, "lr": 1.4262123760539814e-06, "epoch": 2.1193991853360488, "percentage": 42.39, "elapsed_time": "0:39:14", "remaining_time": "0:53:19", "throughput": 10183.74, "total_tokens": 23972736}
{"current_steps": 24980, "total_steps": 58920, "loss": 0.0005, "lr": 1.4259443897391387e-06, "epoch": 2.119823489477257, "percentage": 42.4, "elapsed_time": "0:39:14", "remaining_time": "0:53:18", "throughput": 10184.17, "total_tokens": 23977664}
{"current_steps": 24985, "total_steps": 58920, "loss": 0.0001, "lr": 1.4256763660492139e-06, "epoch": 2.1202477936184656, "percentage": 42.4, "elapsed_time": "0:39:14", "remaining_time": "0:53:18", "throughput": 10184.41, "total_tokens": 23982080}
{"current_steps": 24990, "total_steps": 58920, "loss": 0.0144, "lr": 1.4254083050077248e-06, "epoch": 2.120672097759674, "percentage": 42.41, "elapsed_time": "0:39:15", "remaining_time": "0:53:17", "throughput": 10185.0, "total_tokens": 23987520}
{"current_steps": 24995, "total_steps": 58920, "loss": 0.0264, "lr": 1.4251402066381928e-06, "epoch": 2.1210964019008824, "percentage": 42.42, "elapsed_time": "0:39:15", "remaining_time": "0:53:17", "throughput": 10185.44, "total_tokens": 23992512}
{"current_steps": 25000, "total_steps": 58920, "loss": 0.0001, "lr": 1.4248720709641427e-06, "epoch": 2.121520706042091, "percentage": 42.43, "elapsed_time": "0:39:15", "remaining_time": "0:53:16", "throughput": 10185.89, "total_tokens": 23997504}
{"current_steps": 25005, "total_steps": 58920, "loss": 0.0001, "lr": 1.4246038980091025e-06, "epoch": 2.1219450101832993, "percentage": 42.44, "elapsed_time": "0:39:16", "remaining_time": "0:53:15", "throughput": 10186.41, "total_tokens": 24002752}
{"current_steps": 25010, "total_steps": 58920, "loss": 0.0, "lr": 1.4243356877966028e-06, "epoch": 2.1223693143245077, "percentage": 42.45, "elapsed_time": "0:39:16", "remaining_time": "0:53:15", "throughput": 10186.78, "total_tokens": 24007552}
{"current_steps": 25015, "total_steps": 58920, "loss": 0.0964, "lr": 1.424067440350179e-06, "epoch": 2.122793618465716, "percentage": 42.46, "elapsed_time": "0:39:17", "remaining_time": "0:53:14", "throughput": 10187.25, "total_tokens": 24012608}
{"current_steps": 25020, "total_steps": 58920, "loss": 0.0001, "lr": 1.423799155693368e-06, "epoch": 2.1232179226069245, "percentage": 42.46, "elapsed_time": "0:39:17", "remaining_time": "0:53:14", "throughput": 10187.81, "total_tokens": 24017984}
{"current_steps": 25025, "total_steps": 58920, "loss": 0.0001, "lr": 1.4235308338497116e-06, "epoch": 2.123642226748133, "percentage": 42.47, "elapsed_time": "0:39:17", "remaining_time": "0:53:13", "throughput": 10188.2, "total_tokens": 24022784}
{"current_steps": 25030, "total_steps": 58920, "loss": 0.0553, "lr": 1.4232624748427538e-06, "epoch": 2.1240665308893414, "percentage": 42.48, "elapsed_time": "0:39:18", "remaining_time": "0:53:13", "throughput": 10188.38, "total_tokens": 24027008}
{"current_steps": 25035, "total_steps": 58920, "loss": 0.039, "lr": 1.4229940786960418e-06, "epoch": 2.12449083503055, "percentage": 42.49, "elapsed_time": "0:39:18", "remaining_time": "0:53:12", "throughput": 10188.8, "total_tokens": 24031936}
{"current_steps": 25040, "total_steps": 58920, "loss": 0.0298, "lr": 1.4227256454331264e-06, "epoch": 2.1249151391717582, "percentage": 42.5, "elapsed_time": "0:39:19", "remaining_time": "0:53:11", "throughput": 10189.32, "total_tokens": 24037120}
{"current_steps": 25045, "total_steps": 58920, "loss": 0.0002, "lr": 1.4224571750775623e-06, "epoch": 2.1253394433129666, "percentage": 42.51, "elapsed_time": "0:39:19", "remaining_time": "0:53:11", "throughput": 10189.6, "total_tokens": 24041600}
{"current_steps": 25050, "total_steps": 58920, "loss": 0.0239, "lr": 1.4221886676529055e-06, "epoch": 2.125763747454175, "percentage": 42.52, "elapsed_time": "0:39:19", "remaining_time": "0:53:10", "throughput": 10189.87, "total_tokens": 24046080}
{"current_steps": 25055, "total_steps": 58920, "loss": 0.0003, "lr": 1.4219201231827183e-06, "epoch": 2.1261880515953835, "percentage": 42.52, "elapsed_time": "0:39:20", "remaining_time": "0:53:10", "throughput": 10190.22, "total_tokens": 24050752}
{"current_steps": 25060, "total_steps": 58920, "loss": 0.0004, "lr": 1.4216515416905633e-06, "epoch": 2.126612355736592, "percentage": 42.53, "elapsed_time": "0:39:20", "remaining_time": "0:53:09", "throughput": 10190.43, "total_tokens": 24055040}
{"current_steps": 25065, "total_steps": 58920, "loss": 0.0002, "lr": 1.4213829232000078e-06, "epoch": 2.1270366598778003, "percentage": 42.54, "elapsed_time": "0:39:20", "remaining_time": "0:53:08", "throughput": 10190.63, "total_tokens": 24059264}
{"current_steps": 25070, "total_steps": 58920, "loss": 0.0002, "lr": 1.4211142677346226e-06, "epoch": 2.1274609640190087, "percentage": 42.55, "elapsed_time": "0:39:21", "remaining_time": "0:53:08", "throughput": 10191.14, "total_tokens": 24064448}
{"current_steps": 25075, "total_steps": 58920, "loss": 0.0002, "lr": 1.4208455753179807e-06, "epoch": 2.127885268160217, "percentage": 42.56, "elapsed_time": "0:39:21", "remaining_time": "0:53:07", "throughput": 10191.51, "total_tokens": 24069184}
{"current_steps": 25080, "total_steps": 58920, "loss": 0.0189, "lr": 1.4205768459736584e-06, "epoch": 2.1283095723014256, "percentage": 42.57, "elapsed_time": "0:39:22", "remaining_time": "0:53:07", "throughput": 10191.92, "total_tokens": 24074112}
{"current_steps": 25085, "total_steps": 58920, "loss": 0.0002, "lr": 1.420308079725237e-06, "epoch": 2.128733876442634, "percentage": 42.57, "elapsed_time": "0:39:22", "remaining_time": "0:53:06", "throughput": 10192.43, "total_tokens": 24079296}
{"current_steps": 25090, "total_steps": 58920, "loss": 0.0192, "lr": 1.420039276596299e-06, "epoch": 2.1291581805838424, "percentage": 42.58, "elapsed_time": "0:39:22", "remaining_time": "0:53:05", "throughput": 10192.67, "total_tokens": 24083648}
{"current_steps": 25095, "total_steps": 58920, "loss": 0.0002, "lr": 1.4197704366104309e-06, "epoch": 2.129582484725051, "percentage": 42.59, "elapsed_time": "0:39:23", "remaining_time": "0:53:05", "throughput": 10192.9, "total_tokens": 24088064}
{"current_steps": 25100, "total_steps": 58920, "loss": 0.0245, "lr": 1.4195015597912225e-06, "epoch": 2.1300067888662593, "percentage": 42.6, "elapsed_time": "0:39:23", "remaining_time": "0:53:04", "throughput": 10193.23, "total_tokens": 24092672}
{"current_steps": 25105, "total_steps": 58920, "loss": 0.0002, "lr": 1.4192326461622671e-06, "epoch": 2.1304310930074677, "percentage": 42.61, "elapsed_time": "0:39:23", "remaining_time": "0:53:04", "throughput": 10193.47, "total_tokens": 24097088}
{"current_steps": 25110, "total_steps": 58920, "loss": 0.0328, "lr": 1.4189636957471604e-06, "epoch": 2.130855397148676, "percentage": 42.62, "elapsed_time": "0:39:24", "remaining_time": "0:53:03", "throughput": 10193.66, "total_tokens": 24101312}
{"current_steps": 25115, "total_steps": 58920, "loss": 0.0001, "lr": 1.4186947085695023e-06, "epoch": 2.1312797012898845, "percentage": 42.63, "elapsed_time": "0:39:24", "remaining_time": "0:53:02", "throughput": 10193.99, "total_tokens": 24105984}
{"current_steps": 25120, "total_steps": 58920, "loss": 0.0001, "lr": 1.418425684652895e-06, "epoch": 2.131704005431093, "percentage": 42.63, "elapsed_time": "0:39:25", "remaining_time": "0:53:02", "throughput": 10194.14, "total_tokens": 24110080}
{"current_steps": 25125, "total_steps": 58920, "loss": 0.0252, "lr": 1.4181566240209446e-06, "epoch": 2.1321283095723014, "percentage": 42.64, "elapsed_time": "0:39:25", "remaining_time": "0:53:01", "throughput": 10194.5, "total_tokens": 24114816}
{"current_steps": 25130, "total_steps": 58920, "loss": 0.0051, "lr": 1.4178875266972602e-06, "epoch": 2.13255261371351, "percentage": 42.65, "elapsed_time": "0:39:25", "remaining_time": "0:53:01", "throughput": 10194.82, "total_tokens": 24119424}
{"current_steps": 25135, "total_steps": 58920, "loss": 0.0002, "lr": 1.4176183927054544e-06, "epoch": 2.132976917854718, "percentage": 42.66, "elapsed_time": "0:39:26", "remaining_time": "0:53:00", "throughput": 10195.41, "total_tokens": 24124864}
{"current_steps": 25140, "total_steps": 58920, "loss": 0.0216, "lr": 1.417349222069142e-06, "epoch": 2.1334012219959266, "percentage": 42.67, "elapsed_time": "0:39:26", "remaining_time": "0:52:59", "throughput": 10195.91, "total_tokens": 24129984}
{"current_steps": 25145, "total_steps": 58920, "loss": 0.0303, "lr": 1.4170800148119422e-06, "epoch": 2.133825526137135, "percentage": 42.68, "elapsed_time": "0:39:27", "remaining_time": "0:52:59", "throughput": 10196.39, "total_tokens": 24135168}
{"current_steps": 25150, "total_steps": 58920, "loss": 0.0319, "lr": 1.4168107709574772e-06, "epoch": 2.1342498302783435, "percentage": 42.68, "elapsed_time": "0:39:27", "remaining_time": "0:52:58", "throughput": 10196.87, "total_tokens": 24140288}
{"current_steps": 25155, "total_steps": 58920, "loss": 0.0747, "lr": 1.4165414905293721e-06, "epoch": 2.134674134419552, "percentage": 42.69, "elapsed_time": "0:39:27", "remaining_time": "0:52:58", "throughput": 10197.3, "total_tokens": 24145216}
{"current_steps": 25160, "total_steps": 58920, "loss": 0.0382, "lr": 1.416272173551255e-06, "epoch": 2.1350984385607603, "percentage": 42.7, "elapsed_time": "0:39:28", "remaining_time": "0:52:57", "throughput": 10197.6, "total_tokens": 24149760}
{"current_steps": 25165, "total_steps": 58920, "loss": 0.024, "lr": 1.4160028200467576e-06, "epoch": 2.1355227427019687, "percentage": 42.71, "elapsed_time": "0:39:28", "remaining_time": "0:52:57", "throughput": 10198.03, "total_tokens": 24154752}
{"current_steps": 25170, "total_steps": 58920, "loss": 0.0001, "lr": 1.4157334300395145e-06, "epoch": 2.135947046843177, "percentage": 42.72, "elapsed_time": "0:39:28", "remaining_time": "0:52:56", "throughput": 10198.37, "total_tokens": 24159424}
{"current_steps": 25175, "total_steps": 58920, "loss": 0.0366, "lr": 1.415464003553164e-06, "epoch": 2.1363713509843856, "percentage": 42.73, "elapsed_time": "0:39:29", "remaining_time": "0:52:55", "throughput": 10198.98, "total_tokens": 24164928}
{"current_steps": 25180, "total_steps": 58920, "loss": 0.032, "lr": 1.4151945406113472e-06, "epoch": 2.136795655125594, "percentage": 42.74, "elapsed_time": "0:39:29", "remaining_time": "0:52:55", "throughput": 10199.26, "total_tokens": 24169472}
{"current_steps": 25185, "total_steps": 58920, "loss": 0.0003, "lr": 1.4149250412377087e-06, "epoch": 2.1372199592668024, "percentage": 42.74, "elapsed_time": "0:39:30", "remaining_time": "0:52:54", "throughput": 10199.6, "total_tokens": 24174144}
{"current_steps": 25190, "total_steps": 58920, "loss": 0.0109, "lr": 1.4146555054558958e-06, "epoch": 2.137644263408011, "percentage": 42.75, "elapsed_time": "0:39:30", "remaining_time": "0:52:54", "throughput": 10199.91, "total_tokens": 24178688}
{"current_steps": 25195, "total_steps": 58920, "loss": 0.0584, "lr": 1.4143859332895596e-06, "epoch": 2.1380685675492193, "percentage": 42.76, "elapsed_time": "0:39:30", "remaining_time": "0:52:53", "throughput": 10200.27, "total_tokens": 24183424}
{"current_steps": 25200, "total_steps": 58920, "loss": 0.0196, "lr": 1.4141163247623539e-06, "epoch": 2.1384928716904277, "percentage": 42.77, "elapsed_time": "0:39:31", "remaining_time": "0:52:52", "throughput": 10200.72, "total_tokens": 24188480}
{"current_steps": 25205, "total_steps": 58920, "loss": 0.034, "lr": 1.4138466798979351e-06, "epoch": 2.138917175831636, "percentage": 42.78, "elapsed_time": "0:39:31", "remaining_time": "0:52:52", "throughput": 10201.03, "total_tokens": 24193088}
{"current_steps": 25210, "total_steps": 58920, "loss": 0.0003, "lr": 1.413576998719965e-06, "epoch": 2.1393414799728445, "percentage": 42.79, "elapsed_time": "0:39:32", "remaining_time": "0:52:51", "throughput": 10201.61, "total_tokens": 24198528}
{"current_steps": 25215, "total_steps": 58920, "loss": 0.0225, "lr": 1.4133072812521066e-06, "epoch": 2.139765784114053, "percentage": 42.8, "elapsed_time": "0:39:32", "remaining_time": "0:52:51", "throughput": 10202.14, "total_tokens": 24203776}
{"current_steps": 25220, "total_steps": 58920, "loss": 0.0151, "lr": 1.4130375275180262e-06, "epoch": 2.1401900882552614, "percentage": 42.8, "elapsed_time": "0:39:32", "remaining_time": "0:52:50", "throughput": 10202.56, "total_tokens": 24208704}
{"current_steps": 25225, "total_steps": 58920, "loss": 0.0008, "lr": 1.412767737541394e-06, "epoch": 2.14061439239647, "percentage": 42.81, "elapsed_time": "0:39:33", "remaining_time": "0:52:50", "throughput": 10202.83, "total_tokens": 24213184}
{"current_steps": 25230, "total_steps": 58920, "loss": 0.0302, "lr": 1.4124979113458833e-06, "epoch": 2.141038696537678, "percentage": 42.82, "elapsed_time": "0:39:33", "remaining_time": "0:52:49", "throughput": 10203.48, "total_tokens": 24218880}
{"current_steps": 25235, "total_steps": 58920, "loss": 0.0052, "lr": 1.4122280489551701e-06, "epoch": 2.1414630006788866, "percentage": 42.83, "elapsed_time": "0:39:34", "remaining_time": "0:52:48", "throughput": 10204.23, "total_tokens": 24224896}
{"current_steps": 25240, "total_steps": 58920, "loss": 0.0001, "lr": 1.411958150392934e-06, "epoch": 2.141887304820095, "percentage": 42.84, "elapsed_time": "0:39:34", "remaining_time": "0:52:48", "throughput": 10204.56, "total_tokens": 24229504}
{"current_steps": 25245, "total_steps": 58920, "loss": 0.0015, "lr": 1.4116882156828575e-06, "epoch": 2.1423116089613035, "percentage": 42.85, "elapsed_time": "0:39:34", "remaining_time": "0:52:47", "throughput": 10204.93, "total_tokens": 24234240}
{"current_steps": 25250, "total_steps": 58920, "loss": 0.0244, "lr": 1.4114182448486265e-06, "epoch": 2.142735913102512, "percentage": 42.85, "elapsed_time": "0:39:35", "remaining_time": "0:52:47", "throughput": 10205.43, "total_tokens": 24239424}
{"current_steps": 25255, "total_steps": 58920, "loss": 0.0002, "lr": 1.4111482379139298e-06, "epoch": 2.1431602172437203, "percentage": 42.86, "elapsed_time": "0:39:35", "remaining_time": "0:52:46", "throughput": 10205.78, "total_tokens": 24244160}
{"current_steps": 25260, "total_steps": 58920, "loss": 0.0295, "lr": 1.41087819490246e-06, "epoch": 2.1435845213849287, "percentage": 42.87, "elapsed_time": "0:39:35", "remaining_time": "0:52:45", "throughput": 10206.16, "total_tokens": 24248896}
{"current_steps": 25265, "total_steps": 58920, "loss": 0.0001, "lr": 1.4106081158379119e-06, "epoch": 2.144008825526137, "percentage": 42.88, "elapsed_time": "0:39:36", "remaining_time": "0:52:45", "throughput": 10206.49, "total_tokens": 24253504}
{"current_steps": 25270, "total_steps": 58920, "loss": 0.0002, "lr": 1.4103380007439838e-06, "epoch": 2.1444331296673456, "percentage": 42.89, "elapsed_time": "0:39:36", "remaining_time": "0:52:44", "throughput": 10206.98, "total_tokens": 24258688}
{"current_steps": 25275, "total_steps": 58920, "loss": 0.0001, "lr": 1.410067849644378e-06, "epoch": 2.144857433808554, "percentage": 42.9, "elapsed_time": "0:39:37", "remaining_time": "0:52:44", "throughput": 10207.23, "total_tokens": 24263104}
{"current_steps": 25280, "total_steps": 58920, "loss": 0.0376, "lr": 1.4097976625627992e-06, "epoch": 2.1452817379497624, "percentage": 42.91, "elapsed_time": "0:39:37", "remaining_time": "0:52:43", "throughput": 10207.58, "total_tokens": 24267840}
{"current_steps": 25285, "total_steps": 58920, "loss": 0.0001, "lr": 1.4095274395229547e-06, "epoch": 2.145706042090971, "percentage": 42.91, "elapsed_time": "0:39:37", "remaining_time": "0:52:43", "throughput": 10207.86, "total_tokens": 24272320}
{"current_steps": 25290, "total_steps": 58920, "loss": 0.0, "lr": 1.409257180548556e-06, "epoch": 2.1461303462321792, "percentage": 42.92, "elapsed_time": "0:39:38", "remaining_time": "0:52:42", "throughput": 10208.36, "total_tokens": 24277504}
{"current_steps": 25295, "total_steps": 58920, "loss": 0.0002, "lr": 1.4089868856633174e-06, "epoch": 2.1465546503733877, "percentage": 42.93, "elapsed_time": "0:39:38", "remaining_time": "0:52:41", "throughput": 10208.77, "total_tokens": 24282432}
{"current_steps": 25300, "total_steps": 58920, "loss": 0.0001, "lr": 1.4087165548909561e-06, "epoch": 2.146978954514596, "percentage": 42.94, "elapsed_time": "0:39:38", "remaining_time": "0:52:41", "throughput": 10209.24, "total_tokens": 24287488}
{"current_steps": 25305, "total_steps": 58920, "loss": 0.0001, "lr": 1.4084461882551928e-06, "epoch": 2.1474032586558045, "percentage": 42.95, "elapsed_time": "0:39:39", "remaining_time": "0:52:40", "throughput": 10209.7, "total_tokens": 24292544}
{"current_steps": 25310, "total_steps": 58920, "loss": 0.0244, "lr": 1.4081757857797513e-06, "epoch": 2.147827562797013, "percentage": 42.96, "elapsed_time": "0:39:39", "remaining_time": "0:52:40", "throughput": 10210.03, "total_tokens": 24297152}
{"current_steps": 25315, "total_steps": 58920, "loss": 0.0186, "lr": 1.4079053474883582e-06, "epoch": 2.1482518669382213, "percentage": 42.97, "elapsed_time": "0:39:40", "remaining_time": "0:52:39", "throughput": 10210.28, "total_tokens": 24301568}
{"current_steps": 25320, "total_steps": 58920, "loss": 0.0001, "lr": 1.407634873404744e-06, "epoch": 2.1486761710794298, "percentage": 42.97, "elapsed_time": "0:39:40", "remaining_time": "0:52:38", "throughput": 10210.67, "total_tokens": 24306432}
{"current_steps": 25325, "total_steps": 58920, "loss": 0.0002, "lr": 1.4073643635526408e-06, "epoch": 2.149100475220638, "percentage": 42.98, "elapsed_time": "0:39:40", "remaining_time": "0:52:38", "throughput": 10210.93, "total_tokens": 24310848}
{"current_steps": 25330, "total_steps": 58920, "loss": 0.0286, "lr": 1.4070938179557858e-06, "epoch": 2.1495247793618466, "percentage": 42.99, "elapsed_time": "0:39:41", "remaining_time": "0:52:37", "throughput": 10211.51, "total_tokens": 24316288}
{"current_steps": 25335, "total_steps": 58920, "loss": 0.0, "lr": 1.4068232366379181e-06, "epoch": 2.149949083503055, "percentage": 43.0, "elapsed_time": "0:39:41", "remaining_time": "0:52:37", "throughput": 10212.0, "total_tokens": 24321408}
{"current_steps": 25340, "total_steps": 58920, "loss": 0.0299, "lr": 1.40655261962278e-06, "epoch": 2.1503733876442634, "percentage": 43.01, "elapsed_time": "0:39:42", "remaining_time": "0:52:36", "throughput": 10212.28, "total_tokens": 24325888}
{"current_steps": 25345, "total_steps": 58920, "loss": 0.0113, "lr": 1.4062819669341175e-06, "epoch": 2.150797691785472, "percentage": 43.02, "elapsed_time": "0:39:42", "remaining_time": "0:52:36", "throughput": 10212.81, "total_tokens": 24331200}
{"current_steps": 25350, "total_steps": 58920, "loss": 0.0001, "lr": 1.4060112785956795e-06, "epoch": 2.1512219959266803, "percentage": 43.02, "elapsed_time": "0:39:42", "remaining_time": "0:52:35", "throughput": 10213.18, "total_tokens": 24336000}
{"current_steps": 25355, "total_steps": 58920, "loss": 0.0001, "lr": 1.4057405546312175e-06, "epoch": 2.1516463000678887, "percentage": 43.03, "elapsed_time": "0:39:43", "remaining_time": "0:52:34", "throughput": 10213.47, "total_tokens": 24340544}
{"current_steps": 25360, "total_steps": 58920, "loss": 0.0, "lr": 1.4054697950644865e-06, "epoch": 2.152070604209097, "percentage": 43.04, "elapsed_time": "0:39:43", "remaining_time": "0:52:34", "throughput": 10214.25, "total_tokens": 24346688}
{"current_steps": 25365, "total_steps": 58920, "loss": 0.1033, "lr": 1.4051989999192452e-06, "epoch": 2.1524949083503055, "percentage": 43.05, "elapsed_time": "0:39:43", "remaining_time": "0:52:33", "throughput": 10214.73, "total_tokens": 24351808}
{"current_steps": 25370, "total_steps": 58920, "loss": 0.0217, "lr": 1.4049281692192548e-06, "epoch": 2.152919212491514, "percentage": 43.06, "elapsed_time": "0:39:44", "remaining_time": "0:52:33", "throughput": 10215.08, "total_tokens": 24356544}
{"current_steps": 25375, "total_steps": 58920, "loss": 0.0001, "lr": 1.4046573029882793e-06, "epoch": 2.1533435166327224, "percentage": 43.07, "elapsed_time": "0:39:44", "remaining_time": "0:52:32", "throughput": 10215.62, "total_tokens": 24361856}
{"current_steps": 25380, "total_steps": 58920, "loss": 0.0006, "lr": 1.4043864012500866e-06, "epoch": 2.153767820773931, "percentage": 43.08, "elapsed_time": "0:39:45", "remaining_time": "0:52:32", "throughput": 10216.1, "total_tokens": 24366976}
{"current_steps": 25385, "total_steps": 58920, "loss": 0.0976, "lr": 1.4041154640284472e-06, "epoch": 2.1541921249151392, "percentage": 43.08, "elapsed_time": "0:39:45", "remaining_time": "0:52:31", "throughput": 10216.42, "total_tokens": 24371648}
{"current_steps": 25390, "total_steps": 58920, "loss": 0.0385, "lr": 1.4038444913471346e-06, "epoch": 2.1546164290563476, "percentage": 43.09, "elapsed_time": "0:39:45", "remaining_time": "0:52:30", "throughput": 10217.06, "total_tokens": 24377280}
{"current_steps": 25395, "total_steps": 58920, "loss": 0.0111, "lr": 1.4035734832299259e-06, "epoch": 2.155040733197556, "percentage": 43.1, "elapsed_time": "0:39:46", "remaining_time": "0:52:30", "throughput": 10217.36, "total_tokens": 24381888}
{"current_steps": 25400, "total_steps": 58920, "loss": 0.0002, "lr": 1.4033024397006017e-06, "epoch": 2.1554650373387645, "percentage": 43.11, "elapsed_time": "0:39:46", "remaining_time": "0:52:29", "throughput": 10217.73, "total_tokens": 24386688}
{"current_steps": 25405, "total_steps": 58920, "loss": 0.0002, "lr": 1.4030313607829443e-06, "epoch": 2.155889341479973, "percentage": 43.12, "elapsed_time": "0:39:47", "remaining_time": "0:52:29", "throughput": 10218.08, "total_tokens": 24391424}
{"current_steps": 25410, "total_steps": 58920, "loss": 0.0001, "lr": 1.4027602465007402e-06, "epoch": 2.1563136456211813, "percentage": 43.13, "elapsed_time": "0:39:47", "remaining_time": "0:52:28", "throughput": 10218.32, "total_tokens": 24395776}
{"current_steps": 25415, "total_steps": 58920, "loss": 0.0002, "lr": 1.4024890968777785e-06, "epoch": 2.1567379497623897, "percentage": 43.13, "elapsed_time": "0:39:47", "remaining_time": "0:52:27", "throughput": 10219.01, "total_tokens": 24401664}
{"current_steps": 25420, "total_steps": 58920, "loss": 0.0455, "lr": 1.4022179119378516e-06, "epoch": 2.157162253903598, "percentage": 43.14, "elapsed_time": "0:39:48", "remaining_time": "0:52:27", "throughput": 10219.68, "total_tokens": 24407360}
{"current_steps": 25425, "total_steps": 58920, "loss": 0.0001, "lr": 1.4019466917047553e-06, "epoch": 2.1575865580448066, "percentage": 43.15, "elapsed_time": "0:39:48", "remaining_time": "0:52:26", "throughput": 10220.07, "total_tokens": 24412160}
{"current_steps": 25430, "total_steps": 58920, "loss": 0.0001, "lr": 1.401675436202288e-06, "epoch": 2.158010862186015, "percentage": 43.16, "elapsed_time": "0:39:49", "remaining_time": "0:52:26", "throughput": 10220.36, "total_tokens": 24416704}
{"current_steps": 25435, "total_steps": 58920, "loss": 0.0005, "lr": 1.4014041454542514e-06, "epoch": 2.1584351663272234, "percentage": 43.17, "elapsed_time": "0:39:49", "remaining_time": "0:52:25", "throughput": 10220.74, "total_tokens": 24421504}
{"current_steps": 25440, "total_steps": 58920, "loss": 0.0001, "lr": 1.4011328194844503e-06, "epoch": 2.158859470468432, "percentage": 43.18, "elapsed_time": "0:39:49", "remaining_time": "0:52:25", "throughput": 10221.14, "total_tokens": 24426432}
{"current_steps": 25445, "total_steps": 58920, "loss": 0.0008, "lr": 1.4008614583166927e-06, "epoch": 2.1592837746096403, "percentage": 43.19, "elapsed_time": "0:39:50", "remaining_time": "0:52:24", "throughput": 10221.42, "total_tokens": 24430976}
{"current_steps": 25450, "total_steps": 58920, "loss": 0.0613, "lr": 1.4005900619747893e-06, "epoch": 2.1597080787508487, "percentage": 43.19, "elapsed_time": "0:39:50", "remaining_time": "0:52:23", "throughput": 10221.8, "total_tokens": 24435776}
{"current_steps": 25455, "total_steps": 58920, "loss": 0.0001, "lr": 1.4003186304825542e-06, "epoch": 2.160132382892057, "percentage": 43.2, "elapsed_time": "0:39:50", "remaining_time": "0:52:23", "throughput": 10222.41, "total_tokens": 24441408}
{"current_steps": 25460, "total_steps": 58920, "loss": 0.0001, "lr": 1.4000471638638046e-06, "epoch": 2.1605566870332655, "percentage": 43.21, "elapsed_time": "0:39:51", "remaining_time": "0:52:22", "throughput": 10222.98, "total_tokens": 24446848}
{"current_steps": 25465, "total_steps": 58920, "loss": 0.0258, "lr": 1.3997756621423612e-06, "epoch": 2.160980991174474, "percentage": 43.22, "elapsed_time": "0:39:51", "remaining_time": "0:52:22", "throughput": 10223.23, "total_tokens": 24451264}
{"current_steps": 25470, "total_steps": 58920, "loss": 0.0001, "lr": 1.3995041253420462e-06, "epoch": 2.1614052953156824, "percentage": 43.23, "elapsed_time": "0:39:52", "remaining_time": "0:52:21", "throughput": 10223.63, "total_tokens": 24456128}
{"current_steps": 25475, "total_steps": 58920, "loss": 0.0525, "lr": 1.399232553486687e-06, "epoch": 2.161829599456891, "percentage": 43.24, "elapsed_time": "0:39:52", "remaining_time": "0:52:21", "throughput": 10224.01, "total_tokens": 24460928}
{"current_steps": 25480, "total_steps": 58920, "loss": 0.0001, "lr": 1.3989609466001128e-06, "epoch": 2.162253903598099, "percentage": 43.25, "elapsed_time": "0:39:52", "remaining_time": "0:52:20", "throughput": 10224.64, "total_tokens": 24466560}
{"current_steps": 25485, "total_steps": 58920, "loss": 0.0368, "lr": 1.3986893047061555e-06, "epoch": 2.1626782077393076, "percentage": 43.25, "elapsed_time": "0:39:53", "remaining_time": "0:52:19", "throughput": 10224.95, "total_tokens": 24471168}
{"current_steps": 25490, "total_steps": 58920, "loss": 0.0001, "lr": 1.3984176278286514e-06, "epoch": 2.163102511880516, "percentage": 43.26, "elapsed_time": "0:39:53", "remaining_time": "0:52:19", "throughput": 10225.42, "total_tokens": 24476288}
{"current_steps": 25495, "total_steps": 58920, "loss": 0.0001, "lr": 1.398145915991439e-06, "epoch": 2.1635268160217245, "percentage": 43.27, "elapsed_time": "0:39:54", "remaining_time": "0:52:18", "throughput": 10225.73, "total_tokens": 24480896}
{"current_steps": 25500, "total_steps": 58920, "loss": 0.0001, "lr": 1.39787416921836e-06, "epoch": 2.163951120162933, "percentage": 43.28, "elapsed_time": "0:39:54", "remaining_time": "0:52:18", "throughput": 10226.17, "total_tokens": 24485824}
{"current_steps": 25505, "total_steps": 58920, "loss": 0.0001, "lr": 1.3976023875332592e-06, "epoch": 2.1643754243041413, "percentage": 43.29, "elapsed_time": "0:39:54", "remaining_time": "0:52:17", "throughput": 10226.54, "total_tokens": 24490624}
{"current_steps": 25510, "total_steps": 58920, "loss": 0.0056, "lr": 1.397330570959984e-06, "epoch": 2.1647997284453497, "percentage": 43.3, "elapsed_time": "0:39:55", "remaining_time": "0:52:16", "throughput": 10227.01, "total_tokens": 24495680}
{"current_steps": 25515, "total_steps": 58920, "loss": 0.0003, "lr": 1.3970587195223862e-06, "epoch": 2.165224032586558, "percentage": 43.3, "elapsed_time": "0:39:55", "remaining_time": "0:52:16", "throughput": 10227.32, "total_tokens": 24500288}
{"current_steps": 25520, "total_steps": 58920, "loss": 0.0, "lr": 1.3967868332443191e-06, "epoch": 2.1656483367277666, "percentage": 43.31, "elapsed_time": "0:39:55", "remaining_time": "0:52:15", "throughput": 10227.72, "total_tokens": 24505152}
{"current_steps": 25525, "total_steps": 58920, "loss": 0.0371, "lr": 1.3965149121496402e-06, "epoch": 2.166072640868975, "percentage": 43.32, "elapsed_time": "0:39:56", "remaining_time": "0:52:15", "throughput": 10228.06, "total_tokens": 24509824}
{"current_steps": 25530, "total_steps": 58920, "loss": 0.0145, "lr": 1.3962429562622095e-06, "epoch": 2.1664969450101834, "percentage": 43.33, "elapsed_time": "0:39:56", "remaining_time": "0:52:14", "throughput": 10228.31, "total_tokens": 24514240}
{"current_steps": 25535, "total_steps": 58920, "loss": 0.0298, "lr": 1.3959709656058897e-06, "epoch": 2.166921249151392, "percentage": 43.34, "elapsed_time": "0:39:57", "remaining_time": "0:52:14", "throughput": 10228.76, "total_tokens": 24519296}
{"current_steps": 25540, "total_steps": 58920, "loss": 0.0001, "lr": 1.3956989402045474e-06, "epoch": 2.1673455532926003, "percentage": 43.35, "elapsed_time": "0:39:57", "remaining_time": "0:52:13", "throughput": 10229.05, "total_tokens": 24523840}
{"current_steps": 25545, "total_steps": 58920, "loss": 0.0287, "lr": 1.3954268800820518e-06, "epoch": 2.1677698574338087, "percentage": 43.36, "elapsed_time": "0:39:57", "remaining_time": "0:52:12", "throughput": 10229.49, "total_tokens": 24528832}
{"current_steps": 25550, "total_steps": 58920, "loss": 0.0016, "lr": 1.3951547852622748e-06, "epoch": 2.168194161575017, "percentage": 43.36, "elapsed_time": "0:39:58", "remaining_time": "0:52:12", "throughput": 10229.85, "total_tokens": 24533632}
{"current_steps": 25555, "total_steps": 58920, "loss": 0.0001, "lr": 1.3948826557690926e-06, "epoch": 2.1686184657162255, "percentage": 43.37, "elapsed_time": "0:39:58", "remaining_time": "0:52:11", "throughput": 10230.14, "total_tokens": 24538176}
{"current_steps": 25560, "total_steps": 58920, "loss": 0.0, "lr": 1.3946104916263828e-06, "epoch": 2.169042769857434, "percentage": 43.38, "elapsed_time": "0:39:58", "remaining_time": "0:52:11", "throughput": 10230.38, "total_tokens": 24542592}
{"current_steps": 25565, "total_steps": 58920, "loss": 0.0001, "lr": 1.3943382928580274e-06, "epoch": 2.1694670739986424, "percentage": 43.39, "elapsed_time": "0:39:59", "remaining_time": "0:52:10", "throughput": 10230.75, "total_tokens": 24547392}
{"current_steps": 25570, "total_steps": 58920, "loss": 0.0436, "lr": 1.3940660594879102e-06, "epoch": 2.169891378139851, "percentage": 43.4, "elapsed_time": "0:39:59", "remaining_time": "0:52:09", "throughput": 10231.08, "total_tokens": 24552064}
{"current_steps": 25575, "total_steps": 58920, "loss": 0.0011, "lr": 1.3937937915399193e-06, "epoch": 2.170315682281059, "percentage": 43.41, "elapsed_time": "0:40:00", "remaining_time": "0:52:09", "throughput": 10231.48, "total_tokens": 24556992}
{"current_steps": 25580, "total_steps": 58920, "loss": 0.0, "lr": 1.3935214890379447e-06, "epoch": 2.1707399864222676, "percentage": 43.41, "elapsed_time": "0:40:00", "remaining_time": "0:52:08", "throughput": 10231.73, "total_tokens": 24561408}
{"current_steps": 25585, "total_steps": 58920, "loss": 0.0316, "lr": 1.3932491520058804e-06, "epoch": 2.171164290563476, "percentage": 43.42, "elapsed_time": "0:40:00", "remaining_time": "0:52:08", "throughput": 10232.16, "total_tokens": 24566400}
{"current_steps": 25590, "total_steps": 58920, "loss": 0.0004, "lr": 1.3929767804676228e-06, "epoch": 2.1715885947046845, "percentage": 43.43, "elapsed_time": "0:40:01", "remaining_time": "0:52:07", "throughput": 10232.48, "total_tokens": 24571008}
{"current_steps": 25595, "total_steps": 58920, "loss": 0.0466, "lr": 1.3927043744470716e-06, "epoch": 2.172012898845893, "percentage": 43.44, "elapsed_time": "0:40:01", "remaining_time": "0:52:06", "throughput": 10232.89, "total_tokens": 24575936}
{"current_steps": 25600, "total_steps": 58920, "loss": 0.0001, "lr": 1.3924319339681295e-06, "epoch": 2.1724372029871013, "percentage": 43.45, "elapsed_time": "0:40:02", "remaining_time": "0:52:06", "throughput": 10232.96, "total_tokens": 24579840}
{"current_steps": 25605, "total_steps": 58920, "loss": 0.0003, "lr": 1.3921594590547016e-06, "epoch": 2.1728615071283097, "percentage": 43.46, "elapsed_time": "0:40:02", "remaining_time": "0:52:05", "throughput": 10233.82, "total_tokens": 24586240}
{"current_steps": 25610, "total_steps": 58920, "loss": 0.0647, "lr": 1.3918869497306976e-06, "epoch": 2.173285811269518, "percentage": 43.47, "elapsed_time": "0:40:02", "remaining_time": "0:52:05", "throughput": 10234.43, "total_tokens": 24591808}
{"current_steps": 25615, "total_steps": 58920, "loss": 0.0003, "lr": 1.3916144060200288e-06, "epoch": 2.1737101154107266, "percentage": 43.47, "elapsed_time": "0:40:03", "remaining_time": "0:52:04", "throughput": 10234.74, "total_tokens": 24596416}
{"current_steps": 25620, "total_steps": 58920, "loss": 0.0399, "lr": 1.3913418279466094e-06, "epoch": 2.174134419551935, "percentage": 43.48, "elapsed_time": "0:40:03", "remaining_time": "0:52:04", "throughput": 10235.09, "total_tokens": 24601088}
{"current_steps": 25625, "total_steps": 58920, "loss": 0.0296, "lr": 1.3910692155343574e-06, "epoch": 2.1745587236931434, "percentage": 43.49, "elapsed_time": "0:40:03", "remaining_time": "0:52:03", "throughput": 10235.35, "total_tokens": 24605568}
{"current_steps": 25630, "total_steps": 58920, "loss": 0.0323, "lr": 1.3907965688071942e-06, "epoch": 2.174983027834352, "percentage": 43.5, "elapsed_time": "0:40:04", "remaining_time": "0:52:02", "throughput": 10235.82, "total_tokens": 24610752}
{"current_steps": 25635, "total_steps": 58920, "loss": 0.0001, "lr": 1.3905238877890423e-06, "epoch": 2.1754073319755602, "percentage": 43.51, "elapsed_time": "0:40:04", "remaining_time": "0:52:02", "throughput": 10236.16, "total_tokens": 24615424}
{"current_steps": 25640, "total_steps": 58920, "loss": 0.023, "lr": 1.3902511725038298e-06, "epoch": 2.1758316361167687, "percentage": 43.52, "elapsed_time": "0:40:05", "remaining_time": "0:52:01", "throughput": 10236.41, "total_tokens": 24619840}
{"current_steps": 25645, "total_steps": 58920, "loss": 0.0151, "lr": 1.3899784229754856e-06, "epoch": 2.176255940257977, "percentage": 43.53, "elapsed_time": "0:40:05", "remaining_time": "0:52:01", "throughput": 10236.84, "total_tokens": 24624832}
{"current_steps": 25650, "total_steps": 58920, "loss": 0.0006, "lr": 1.389705639227943e-06, "epoch": 2.1766802443991855, "percentage": 43.53, "elapsed_time": "0:40:05", "remaining_time": "0:52:00", "throughput": 10237.31, "total_tokens": 24629952}
{"current_steps": 25655, "total_steps": 58920, "loss": 0.0633, "lr": 1.389432821285138e-06, "epoch": 2.177104548540394, "percentage": 43.54, "elapsed_time": "0:40:06", "remaining_time": "0:52:00", "throughput": 10237.48, "total_tokens": 24634176}
{"current_steps": 25660, "total_steps": 58920, "loss": 0.0002, "lr": 1.389159969171008e-06, "epoch": 2.1775288526816023, "percentage": 43.55, "elapsed_time": "0:40:06", "remaining_time": "0:51:59", "throughput": 10237.63, "total_tokens": 24638336}
{"current_steps": 25665, "total_steps": 58920, "loss": 0.0001, "lr": 1.3888870829094962e-06, "epoch": 2.1779531568228108, "percentage": 43.56, "elapsed_time": "0:40:07", "remaining_time": "0:51:58", "throughput": 10238.11, "total_tokens": 24643520}
{"current_steps": 25670, "total_steps": 58920, "loss": 0.0001, "lr": 1.388614162524547e-06, "epoch": 2.178377460964019, "percentage": 43.57, "elapsed_time": "0:40:07", "remaining_time": "0:51:58", "throughput": 10238.5, "total_tokens": 24648384}
{"current_steps": 25675, "total_steps": 58920, "loss": 0.0562, "lr": 1.3883412080401082e-06, "epoch": 2.1788017651052276, "percentage": 43.58, "elapsed_time": "0:40:07", "remaining_time": "0:51:57", "throughput": 10238.82, "total_tokens": 24652992}
{"current_steps": 25680, "total_steps": 58920, "loss": 0.0011, "lr": 1.3880682194801306e-06, "epoch": 2.179226069246436, "percentage": 43.58, "elapsed_time": "0:40:08", "remaining_time": "0:51:57", "throughput": 10239.28, "total_tokens": 24658112}
{"current_steps": 25685, "total_steps": 58920, "loss": 0.0001, "lr": 1.3877951968685677e-06, "epoch": 2.1796503733876444, "percentage": 43.59, "elapsed_time": "0:40:08", "remaining_time": "0:51:56", "throughput": 10239.72, "total_tokens": 24663104}
{"current_steps": 25690, "total_steps": 58920, "loss": 0.0002, "lr": 1.3875221402293764e-06, "epoch": 2.180074677528853, "percentage": 43.6, "elapsed_time": "0:40:08", "remaining_time": "0:51:55", "throughput": 10240.14, "total_tokens": 24668096}
{"current_steps": 25695, "total_steps": 58920, "loss": 0.0002, "lr": 1.3872490495865163e-06, "epoch": 2.1804989816700613, "percentage": 43.61, "elapsed_time": "0:40:09", "remaining_time": "0:51:55", "throughput": 10240.35, "total_tokens": 24672384}
{"current_steps": 25700, "total_steps": 58920, "loss": 0.0245, "lr": 1.3869759249639505e-06, "epoch": 2.1809232858112697, "percentage": 43.62, "elapsed_time": "0:40:09", "remaining_time": "0:51:54", "throughput": 10240.55, "total_tokens": 24676672}
{"current_steps": 25705, "total_steps": 58920, "loss": 0.0001, "lr": 1.3867027663856442e-06, "epoch": 2.181347589952478, "percentage": 43.63, "elapsed_time": "0:40:10", "remaining_time": "0:51:54", "throughput": 10240.68, "total_tokens": 24680768}
{"current_steps": 25710, "total_steps": 58920, "loss": 0.0052, "lr": 1.3864295738755667e-06, "epoch": 2.1817718940936865, "percentage": 43.64, "elapsed_time": "0:40:10", "remaining_time": "0:51:53", "throughput": 10241.05, "total_tokens": 24685568}
{"current_steps": 25715, "total_steps": 58920, "loss": 0.0001, "lr": 1.386156347457689e-06, "epoch": 2.182196198234895, "percentage": 43.64, "elapsed_time": "0:40:10", "remaining_time": "0:51:53", "throughput": 10241.43, "total_tokens": 24690368}
{"current_steps": 25720, "total_steps": 58920, "loss": 0.0001, "lr": 1.385883087155986e-06, "epoch": 2.1826205023761034, "percentage": 43.65, "elapsed_time": "0:40:11", "remaining_time": "0:51:52", "throughput": 10241.91, "total_tokens": 24695488}
{"current_steps": 25725, "total_steps": 58920, "loss": 0.0001, "lr": 1.3856097929944354e-06, "epoch": 2.183044806517312, "percentage": 43.66, "elapsed_time": "0:40:11", "remaining_time": "0:51:51", "throughput": 10242.22, "total_tokens": 24700096}
{"current_steps": 25730, "total_steps": 58920, "loss": 0.0, "lr": 1.385336464997018e-06, "epoch": 2.1834691106585202, "percentage": 43.67, "elapsed_time": "0:40:11", "remaining_time": "0:51:51", "throughput": 10242.61, "total_tokens": 24704960}
{"current_steps": 25735, "total_steps": 58920, "loss": 0.0557, "lr": 1.3850631031877167e-06, "epoch": 2.1838934147997286, "percentage": 43.68, "elapsed_time": "0:40:12", "remaining_time": "0:51:50", "throughput": 10242.9, "total_tokens": 24709504}
{"current_steps": 25740, "total_steps": 58920, "loss": 0.0001, "lr": 1.3847897075905187e-06, "epoch": 2.184317718940937, "percentage": 43.69, "elapsed_time": "0:40:12", "remaining_time": "0:51:50", "throughput": 10243.61, "total_tokens": 24715456}
{"current_steps": 25745, "total_steps": 58920, "loss": 0.0, "lr": 1.3845162782294127e-06, "epoch": 2.184742023082145, "percentage": 43.69, "elapsed_time": "0:40:13", "remaining_time": "0:51:49", "throughput": 10244.09, "total_tokens": 24720576}
{"current_steps": 25750, "total_steps": 58920, "loss": 0.0001, "lr": 1.3842428151283918e-06, "epoch": 2.185166327223354, "percentage": 43.7, "elapsed_time": "0:40:13", "remaining_time": "0:51:48", "throughput": 10244.26, "total_tokens": 24724800}
{"current_steps": 25755, "total_steps": 58920, "loss": 0.0001, "lr": 1.383969318311451e-06, "epoch": 2.185590631364562, "percentage": 43.71, "elapsed_time": "0:40:13", "remaining_time": "0:51:48", "throughput": 10244.74, "total_tokens": 24729984}
{"current_steps": 25760, "total_steps": 58920, "loss": 0.0224, "lr": 1.3836957878025888e-06, "epoch": 2.1860149355057708, "percentage": 43.72, "elapsed_time": "0:40:14", "remaining_time": "0:51:47", "throughput": 10245.28, "total_tokens": 24735360}
{"current_steps": 25765, "total_steps": 58920, "loss": 0.0341, "lr": 1.3834222236258068e-06, "epoch": 2.1864392396469787, "percentage": 43.73, "elapsed_time": "0:40:14", "remaining_time": "0:51:47", "throughput": 10245.6, "total_tokens": 24740032}
{"current_steps": 25770, "total_steps": 58920, "loss": 0.045, "lr": 1.3831486258051089e-06, "epoch": 2.1868635437881876, "percentage": 43.74, "elapsed_time": "0:40:15", "remaining_time": "0:51:46", "throughput": 10246.19, "total_tokens": 24745536}
{"current_steps": 25775, "total_steps": 58920, "loss": 0.0001, "lr": 1.3828749943645025e-06, "epoch": 2.1872878479293956, "percentage": 43.75, "elapsed_time": "0:40:15", "remaining_time": "0:51:46", "throughput": 10246.7, "total_tokens": 24750848}
{"current_steps": 25780, "total_steps": 58920, "loss": 0.0668, "lr": 1.3826013293279978e-06, "epoch": 2.1877121520706044, "percentage": 43.75, "elapsed_time": "0:40:15", "remaining_time": "0:51:45", "throughput": 10246.99, "total_tokens": 24755456}
{"current_steps": 25785, "total_steps": 58920, "loss": 0.0278, "lr": 1.3823276307196076e-06, "epoch": 2.1881364562118124, "percentage": 43.76, "elapsed_time": "0:40:16", "remaining_time": "0:51:45", "throughput": 10247.42, "total_tokens": 24760448}
{"current_steps": 25790, "total_steps": 58920, "loss": 0.0001, "lr": 1.3820538985633484e-06, "epoch": 2.1885607603530213, "percentage": 43.77, "elapsed_time": "0:40:16", "remaining_time": "0:51:44", "throughput": 10247.7, "total_tokens": 24764992}
{"current_steps": 25795, "total_steps": 58920, "loss": 0.0004, "lr": 1.3817801328832387e-06, "epoch": 2.1889850644942292, "percentage": 43.78, "elapsed_time": "0:40:17", "remaining_time": "0:51:43", "throughput": 10248.01, "total_tokens": 24769600}
{"current_steps": 25800, "total_steps": 58920, "loss": 0.0676, "lr": 1.381506333703301e-06, "epoch": 2.189409368635438, "percentage": 43.79, "elapsed_time": "0:40:17", "remaining_time": "0:51:43", "throughput": 10248.27, "total_tokens": 24774016}
{"current_steps": 25805, "total_steps": 58920, "loss": 0.0004, "lr": 1.38123250104756e-06, "epoch": 2.189833672776646, "percentage": 43.8, "elapsed_time": "0:40:17", "remaining_time": "0:51:42", "throughput": 10248.77, "total_tokens": 24779264}
{"current_steps": 25810, "total_steps": 58920, "loss": 0.0004, "lr": 1.3809586349400434e-06, "epoch": 2.190257976917855, "percentage": 43.81, "elapsed_time": "0:40:18", "remaining_time": "0:51:42", "throughput": 10249.08, "total_tokens": 24783872}
{"current_steps": 25815, "total_steps": 58920, "loss": 0.0002, "lr": 1.380684735404782e-06, "epoch": 2.190682281059063, "percentage": 43.81, "elapsed_time": "0:40:18", "remaining_time": "0:51:41", "throughput": 10249.5, "total_tokens": 24788800}
{"current_steps": 25820, "total_steps": 58920, "loss": 0.0001, "lr": 1.3804108024658092e-06, "epoch": 2.1911065852002714, "percentage": 43.82, "elapsed_time": "0:40:18", "remaining_time": "0:51:40", "throughput": 10249.81, "total_tokens": 24793408}
{"current_steps": 25825, "total_steps": 58920, "loss": 0.0002, "lr": 1.3801368361471624e-06, "epoch": 2.1915308893414798, "percentage": 43.83, "elapsed_time": "0:40:19", "remaining_time": "0:51:40", "throughput": 10250.33, "total_tokens": 24798720}
{"current_steps": 25830, "total_steps": 58920, "loss": 0.0001, "lr": 1.3798628364728807e-06, "epoch": 2.191955193482688, "percentage": 43.84, "elapsed_time": "0:40:19", "remaining_time": "0:51:39", "throughput": 10250.69, "total_tokens": 24803456}
{"current_steps": 25835, "total_steps": 58920, "loss": 0.0117, "lr": 1.3795888034670064e-06, "epoch": 2.1923794976238966, "percentage": 43.85, "elapsed_time": "0:40:20", "remaining_time": "0:51:39", "throughput": 10250.98, "total_tokens": 24808064}
{"current_steps": 25840, "total_steps": 58920, "loss": 0.0004, "lr": 1.3793147371535851e-06, "epoch": 2.192803801765105, "percentage": 43.86, "elapsed_time": "0:40:20", "remaining_time": "0:51:38", "throughput": 10251.28, "total_tokens": 24812672}
{"current_steps": 25845, "total_steps": 58920, "loss": 0.0281, "lr": 1.3790406375566652e-06, "epoch": 2.1932281059063135, "percentage": 43.86, "elapsed_time": "0:40:20", "remaining_time": "0:51:38", "throughput": 10252.28, "total_tokens": 24819520}
{"current_steps": 25850, "total_steps": 58920, "loss": 0.0044, "lr": 1.3787665047002977e-06, "epoch": 2.193652410047522, "percentage": 43.87, "elapsed_time": "0:40:21", "remaining_time": "0:51:37", "throughput": 10252.72, "total_tokens": 24824576}
{"current_steps": 25855, "total_steps": 58920, "loss": 0.0, "lr": 1.3784923386085372e-06, "epoch": 2.1940767141887303, "percentage": 43.88, "elapsed_time": "0:40:21", "remaining_time": "0:51:36", "throughput": 10253.17, "total_tokens": 24829632}
{"current_steps": 25860, "total_steps": 58920, "loss": 0.0001, "lr": 1.3782181393054403e-06, "epoch": 2.1945010183299387, "percentage": 43.89, "elapsed_time": "0:40:22", "remaining_time": "0:51:36", "throughput": 10253.34, "total_tokens": 24833856}
{"current_steps": 25865, "total_steps": 58920, "loss": 0.0172, "lr": 1.3779439068150676e-06, "epoch": 2.194925322471147, "percentage": 43.9, "elapsed_time": "0:40:22", "remaining_time": "0:51:35", "throughput": 10253.83, "total_tokens": 24839040}
{"current_steps": 25870, "total_steps": 58920, "loss": 0.0251, "lr": 1.3776696411614814e-06, "epoch": 2.1953496266123556, "percentage": 43.91, "elapsed_time": "0:40:22", "remaining_time": "0:51:35", "throughput": 10254.41, "total_tokens": 24844544}
{"current_steps": 25875, "total_steps": 58920, "loss": 0.0266, "lr": 1.377395342368748e-06, "epoch": 2.195773930753564, "percentage": 43.92, "elapsed_time": "0:40:23", "remaining_time": "0:51:34", "throughput": 10254.65, "total_tokens": 24848960}
{"current_steps": 25880, "total_steps": 58920, "loss": 0.0071, "lr": 1.377121010460935e-06, "epoch": 2.1961982348947724, "percentage": 43.92, "elapsed_time": "0:40:23", "remaining_time": "0:51:34", "throughput": 10255.08, "total_tokens": 24853952}
{"current_steps": 25885, "total_steps": 58920, "loss": 0.0407, "lr": 1.3768466454621158e-06, "epoch": 2.196622539035981, "percentage": 43.93, "elapsed_time": "0:40:23", "remaining_time": "0:51:33", "throughput": 10255.47, "total_tokens": 24858816}
{"current_steps": 25890, "total_steps": 58920, "loss": 0.0007, "lr": 1.3765722473963637e-06, "epoch": 2.1970468431771892, "percentage": 43.94, "elapsed_time": "0:40:24", "remaining_time": "0:51:32", "throughput": 10255.68, "total_tokens": 24863168}
{"current_steps": 25895, "total_steps": 58920, "loss": 0.0001, "lr": 1.3762978162877568e-06, "epoch": 2.1974711473183977, "percentage": 43.95, "elapsed_time": "0:40:24", "remaining_time": "0:51:32", "throughput": 10255.94, "total_tokens": 24867648}
{"current_steps": 25900, "total_steps": 58920, "loss": 0.0001, "lr": 1.3760233521603747e-06, "epoch": 2.197895451459606, "percentage": 43.96, "elapsed_time": "0:40:25", "remaining_time": "0:51:31", "throughput": 10256.33, "total_tokens": 24872512}
{"current_steps": 25905, "total_steps": 58920, "loss": 0.0001, "lr": 1.3757488550383017e-06, "epoch": 2.1983197556008145, "percentage": 43.97, "elapsed_time": "0:40:25", "remaining_time": "0:51:31", "throughput": 10256.62, "total_tokens": 24877056}
{"current_steps": 25910, "total_steps": 58920, "loss": 0.0001, "lr": 1.375474324945623e-06, "epoch": 2.198744059742023, "percentage": 43.97, "elapsed_time": "0:40:25", "remaining_time": "0:51:30", "throughput": 10257.05, "total_tokens": 24882112}
{"current_steps": 25915, "total_steps": 58920, "loss": 0.0001, "lr": 1.3751997619064276e-06, "epoch": 2.1991683638832313, "percentage": 43.98, "elapsed_time": "0:40:26", "remaining_time": "0:51:30", "throughput": 10257.39, "total_tokens": 24886848}
{"current_steps": 25920, "total_steps": 58920, "loss": 0.0007, "lr": 1.374925165944808e-06, "epoch": 2.1995926680244398, "percentage": 43.99, "elapsed_time": "0:40:26", "remaining_time": "0:51:29", "throughput": 10257.69, "total_tokens": 24891456}
{"current_steps": 25925, "total_steps": 58920, "loss": 0.0001, "lr": 1.374650537084859e-06, "epoch": 2.200016972165648, "percentage": 44.0, "elapsed_time": "0:40:26", "remaining_time": "0:51:28", "throughput": 10257.95, "total_tokens": 24895936}
{"current_steps": 25930, "total_steps": 58920, "loss": 0.0001, "lr": 1.3743758753506777e-06, "epoch": 2.2004412763068566, "percentage": 44.01, "elapsed_time": "0:40:27", "remaining_time": "0:51:28", "throughput": 10258.35, "total_tokens": 24900864}
{"current_steps": 25935, "total_steps": 58920, "loss": 0.0008, "lr": 1.3741011807663649e-06, "epoch": 2.200865580448065, "percentage": 44.02, "elapsed_time": "0:40:27", "remaining_time": "0:51:27", "throughput": 10258.59, "total_tokens": 24905280}
{"current_steps": 25940, "total_steps": 58920, "loss": 0.0001, "lr": 1.3738264533560247e-06, "epoch": 2.2012898845892734, "percentage": 44.03, "elapsed_time": "0:40:28", "remaining_time": "0:51:27", "throughput": 10258.68, "total_tokens": 24909248}
{"current_steps": 25945, "total_steps": 58920, "loss": 0.0, "lr": 1.3735516931437623e-06, "epoch": 2.201714188730482, "percentage": 44.03, "elapsed_time": "0:40:28", "remaining_time": "0:51:26", "throughput": 10259.15, "total_tokens": 24914368}
{"current_steps": 25950, "total_steps": 58920, "loss": 0.0412, "lr": 1.373276900153688e-06, "epoch": 2.2021384928716903, "percentage": 44.04, "elapsed_time": "0:40:28", "remaining_time": "0:51:25", "throughput": 10259.43, "total_tokens": 24918912}
{"current_steps": 25955, "total_steps": 58920, "loss": 0.0001, "lr": 1.3730020744099133e-06, "epoch": 2.2025627970128987, "percentage": 44.05, "elapsed_time": "0:40:29", "remaining_time": "0:51:25", "throughput": 10259.69, "total_tokens": 24923392}
{"current_steps": 25960, "total_steps": 58920, "loss": 0.0, "lr": 1.3727272159365533e-06, "epoch": 2.202987101154107, "percentage": 44.06, "elapsed_time": "0:40:29", "remaining_time": "0:51:24", "throughput": 10260.04, "total_tokens": 24928192}
{"current_steps": 25965, "total_steps": 58920, "loss": 0.0, "lr": 1.3724523247577259e-06, "epoch": 2.2034114052953155, "percentage": 44.07, "elapsed_time": "0:40:30", "remaining_time": "0:51:24", "throughput": 10260.48, "total_tokens": 24933248}
{"current_steps": 25970, "total_steps": 58920, "loss": 0.0035, "lr": 1.3721774008975512e-06, "epoch": 2.203835709436524, "percentage": 44.08, "elapsed_time": "0:40:30", "remaining_time": "0:51:23", "throughput": 10260.75, "total_tokens": 24937728}
{"current_steps": 25975, "total_steps": 58920, "loss": 0.0178, "lr": 1.3719024443801538e-06, "epoch": 2.2042600135777324, "percentage": 44.09, "elapsed_time": "0:40:30", "remaining_time": "0:51:23", "throughput": 10260.95, "total_tokens": 24942016}
{"current_steps": 25980, "total_steps": 58920, "loss": 0.0011, "lr": 1.3716274552296595e-06, "epoch": 2.204684317718941, "percentage": 44.09, "elapsed_time": "0:40:31", "remaining_time": "0:51:22", "throughput": 10261.41, "total_tokens": 24947136}
{"current_steps": 25985, "total_steps": 58920, "loss": 0.0, "lr": 1.371352433470198e-06, "epoch": 2.205108621860149, "percentage": 44.1, "elapsed_time": "0:40:31", "remaining_time": "0:51:21", "throughput": 10261.65, "total_tokens": 24951552}
{"current_steps": 25990, "total_steps": 58920, "loss": 0.0, "lr": 1.3710773791259012e-06, "epoch": 2.2055329260013576, "percentage": 44.11, "elapsed_time": "0:40:31", "remaining_time": "0:51:21", "throughput": 10261.97, "total_tokens": 24956224}
{"current_steps": 25995, "total_steps": 58920, "loss": 0.0001, "lr": 1.3708022922209042e-06, "epoch": 2.205957230142566, "percentage": 44.12, "elapsed_time": "0:40:32", "remaining_time": "0:51:20", "throughput": 10262.37, "total_tokens": 24961152}
{"current_steps": 26000, "total_steps": 58920, "loss": 0.0, "lr": 1.3705271727793444e-06, "epoch": 2.2063815342837745, "percentage": 44.13, "elapsed_time": "0:40:32", "remaining_time": "0:51:20", "throughput": 10262.82, "total_tokens": 24966272}
{"current_steps": 26005, "total_steps": 58920, "loss": 0.0, "lr": 1.3702520208253631e-06, "epoch": 2.206805838424983, "percentage": 44.14, "elapsed_time": "0:40:33", "remaining_time": "0:51:19", "throughput": 10263.08, "total_tokens": 24970816}
{"current_steps": 26010, "total_steps": 58920, "loss": 0.0001, "lr": 1.369976836383104e-06, "epoch": 2.2072301425661913, "percentage": 44.14, "elapsed_time": "0:40:33", "remaining_time": "0:51:19", "throughput": 10263.54, "total_tokens": 24975936}
{"current_steps": 26015, "total_steps": 58920, "loss": 0.0, "lr": 1.369701619476713e-06, "epoch": 2.2076544467073997, "percentage": 44.15, "elapsed_time": "0:40:33", "remaining_time": "0:51:18", "throughput": 10263.72, "total_tokens": 24980224}
{"current_steps": 26020, "total_steps": 58920, "loss": 0.0001, "lr": 1.3694263701303399e-06, "epoch": 2.208078750848608, "percentage": 44.16, "elapsed_time": "0:40:34", "remaining_time": "0:51:17", "throughput": 10264.08, "total_tokens": 24985024}
{"current_steps": 26025, "total_steps": 58920, "loss": 0.0493, "lr": 1.3691510883681368e-06, "epoch": 2.2085030549898166, "percentage": 44.17, "elapsed_time": "0:40:34", "remaining_time": "0:51:17", "throughput": 10264.59, "total_tokens": 24990272}
{"current_steps": 26030, "total_steps": 58920, "loss": 0.0389, "lr": 1.3688757742142582e-06, "epoch": 2.208927359131025, "percentage": 44.18, "elapsed_time": "0:40:34", "remaining_time": "0:51:16", "throughput": 10265.0, "total_tokens": 24995264}
{"current_steps": 26035, "total_steps": 58920, "loss": 0.0001, "lr": 1.3686004276928624e-06, "epoch": 2.2093516632722334, "percentage": 44.19, "elapsed_time": "0:40:35", "remaining_time": "0:51:16", "throughput": 10265.46, "total_tokens": 25000320}
{"current_steps": 26040, "total_steps": 58920, "loss": 0.0002, "lr": 1.36832504882811e-06, "epoch": 2.209775967413442, "percentage": 44.2, "elapsed_time": "0:40:35", "remaining_time": "0:51:15", "throughput": 10266.01, "total_tokens": 25005760}
{"current_steps": 26045, "total_steps": 58920, "loss": 0.0597, "lr": 1.3680496376441641e-06, "epoch": 2.2102002715546503, "percentage": 44.2, "elapsed_time": "0:40:36", "remaining_time": "0:51:15", "throughput": 10266.55, "total_tokens": 25011136}
{"current_steps": 26050, "total_steps": 58920, "loss": 0.0247, "lr": 1.3677741941651916e-06, "epoch": 2.2106245756958587, "percentage": 44.21, "elapsed_time": "0:40:36", "remaining_time": "0:51:14", "throughput": 10266.82, "total_tokens": 25015680}
{"current_steps": 26055, "total_steps": 58920, "loss": 0.0551, "lr": 1.3674987184153613e-06, "epoch": 2.211048879837067, "percentage": 44.22, "elapsed_time": "0:40:36", "remaining_time": "0:51:13", "throughput": 10266.97, "total_tokens": 25019840}
{"current_steps": 26060, "total_steps": 58920, "loss": 0.0003, "lr": 1.3672232104188452e-06, "epoch": 2.2114731839782755, "percentage": 44.23, "elapsed_time": "0:40:37", "remaining_time": "0:51:13", "throughput": 10267.59, "total_tokens": 25025536}
{"current_steps": 26065, "total_steps": 58920, "loss": 0.0002, "lr": 1.3669476701998182e-06, "epoch": 2.211897488119484, "percentage": 44.24, "elapsed_time": "0:40:37", "remaining_time": "0:51:12", "throughput": 10267.94, "total_tokens": 25030336}
{"current_steps": 26070, "total_steps": 58920, "loss": 0.0074, "lr": 1.3666720977824582e-06, "epoch": 2.2123217922606924, "percentage": 44.25, "elapsed_time": "0:40:38", "remaining_time": "0:51:12", "throughput": 10268.31, "total_tokens": 25035200}
{"current_steps": 26075, "total_steps": 58920, "loss": 0.0459, "lr": 1.3663964931909456e-06, "epoch": 2.212746096401901, "percentage": 44.25, "elapsed_time": "0:40:38", "remaining_time": "0:51:11", "throughput": 10268.72, "total_tokens": 25040192}
{"current_steps": 26080, "total_steps": 58920, "loss": 0.0481, "lr": 1.3661208564494632e-06, "epoch": 2.213170400543109, "percentage": 44.26, "elapsed_time": "0:40:38", "remaining_time": "0:51:11", "throughput": 10269.04, "total_tokens": 25044864}
{"current_steps": 26085, "total_steps": 58920, "loss": 0.0006, "lr": 1.365845187582198e-06, "epoch": 2.2135947046843176, "percentage": 44.27, "elapsed_time": "0:40:39", "remaining_time": "0:51:10", "throughput": 10269.49, "total_tokens": 25049984}
{"current_steps": 26090, "total_steps": 58920, "loss": 0.0002, "lr": 1.3655694866133382e-06, "epoch": 2.214019008825526, "percentage": 44.28, "elapsed_time": "0:40:39", "remaining_time": "0:51:09", "throughput": 10269.73, "total_tokens": 25054464}
{"current_steps": 26095, "total_steps": 58920, "loss": 0.0068, "lr": 1.3652937535670756e-06, "epoch": 2.2144433129667345, "percentage": 44.29, "elapsed_time": "0:40:40", "remaining_time": "0:51:09", "throughput": 10270.1, "total_tokens": 25059264}
{"current_steps": 26100, "total_steps": 58920, "loss": 0.0003, "lr": 1.3650179884676053e-06, "epoch": 2.214867617107943, "percentage": 44.3, "elapsed_time": "0:40:40", "remaining_time": "0:51:08", "throughput": 10270.47, "total_tokens": 25064064}
{"current_steps": 26105, "total_steps": 58920, "loss": 0.0036, "lr": 1.3647421913391243e-06, "epoch": 2.2152919212491513, "percentage": 44.31, "elapsed_time": "0:40:40", "remaining_time": "0:51:08", "throughput": 10270.88, "total_tokens": 25069056}
{"current_steps": 26110, "total_steps": 58920, "loss": 0.0002, "lr": 1.364466362205833e-06, "epoch": 2.2157162253903597, "percentage": 44.31, "elapsed_time": "0:40:41", "remaining_time": "0:51:07", "throughput": 10271.19, "total_tokens": 25073728}
{"current_steps": 26115, "total_steps": 58920, "loss": 0.0001, "lr": 1.3641905010919344e-06, "epoch": 2.216140529531568, "percentage": 44.32, "elapsed_time": "0:40:41", "remaining_time": "0:51:07", "throughput": 10271.54, "total_tokens": 25078528}
{"current_steps": 26120, "total_steps": 58920, "loss": 0.0285, "lr": 1.3639146080216339e-06, "epoch": 2.2165648336727766, "percentage": 44.33, "elapsed_time": "0:40:41", "remaining_time": "0:51:06", "throughput": 10271.84, "total_tokens": 25083136}
{"current_steps": 26125, "total_steps": 58920, "loss": 0.0119, "lr": 1.3636386830191406e-06, "epoch": 2.216989137813985, "percentage": 44.34, "elapsed_time": "0:40:42", "remaining_time": "0:51:05", "throughput": 10272.25, "total_tokens": 25088128}
{"current_steps": 26130, "total_steps": 58920, "loss": 0.0001, "lr": 1.363362726108666e-06, "epoch": 2.2174134419551934, "percentage": 44.35, "elapsed_time": "0:40:42", "remaining_time": "0:51:05", "throughput": 10272.58, "total_tokens": 25092800}
{"current_steps": 26135, "total_steps": 58920, "loss": 0.0174, "lr": 1.363086737314424e-06, "epoch": 2.217837746096402, "percentage": 44.36, "elapsed_time": "0:40:43", "remaining_time": "0:51:04", "throughput": 10272.88, "total_tokens": 25097408}
{"current_steps": 26140, "total_steps": 58920, "loss": 0.0005, "lr": 1.3628107166606317e-06, "epoch": 2.2182620502376103, "percentage": 44.37, "elapsed_time": "0:40:43", "remaining_time": "0:51:04", "throughput": 10273.21, "total_tokens": 25102144}
{"current_steps": 26145, "total_steps": 58920, "loss": 0.0332, "lr": 1.3625346641715088e-06, "epoch": 2.2186863543788187, "percentage": 44.37, "elapsed_time": "0:40:43", "remaining_time": "0:51:03", "throughput": 10273.86, "total_tokens": 25107904}
{"current_steps": 26150, "total_steps": 58920, "loss": 0.0001, "lr": 1.3622585798712783e-06, "epoch": 2.219110658520027, "percentage": 44.38, "elapsed_time": "0:40:44", "remaining_time": "0:51:03", "throughput": 10274.17, "total_tokens": 25112512}
{"current_steps": 26155, "total_steps": 58920, "loss": 0.0002, "lr": 1.361982463784165e-06, "epoch": 2.2195349626612355, "percentage": 44.39, "elapsed_time": "0:40:44", "remaining_time": "0:51:02", "throughput": 10274.36, "total_tokens": 25116800}
{"current_steps": 26160, "total_steps": 58920, "loss": 0.0258, "lr": 1.3617063159343978e-06, "epoch": 2.219959266802444, "percentage": 44.4, "elapsed_time": "0:40:44", "remaining_time": "0:51:01", "throughput": 10274.69, "total_tokens": 25121536}
{"current_steps": 26165, "total_steps": 58920, "loss": 0.0001, "lr": 1.361430136346207e-06, "epoch": 2.2203835709436524, "percentage": 44.41, "elapsed_time": "0:40:45", "remaining_time": "0:51:01", "throughput": 10275.01, "total_tokens": 25126208}
{"current_steps": 26170, "total_steps": 58920, "loss": 0.0006, "lr": 1.3611539250438268e-06, "epoch": 2.2208078750848608, "percentage": 44.42, "elapsed_time": "0:40:45", "remaining_time": "0:51:00", "throughput": 10275.39, "total_tokens": 25131136}
{"current_steps": 26175, "total_steps": 58920, "loss": 0.0005, "lr": 1.3608776820514938e-06, "epoch": 2.221232179226069, "percentage": 44.42, "elapsed_time": "0:40:46", "remaining_time": "0:51:00", "throughput": 10275.73, "total_tokens": 25135872}
{"current_steps": 26180, "total_steps": 58920, "loss": 0.0001, "lr": 1.3606014073934469e-06, "epoch": 2.2216564833672776, "percentage": 44.43, "elapsed_time": "0:40:46", "remaining_time": "0:50:59", "throughput": 10276.01, "total_tokens": 25140416}
{"current_steps": 26185, "total_steps": 58920, "loss": 0.0001, "lr": 1.3603251010939284e-06, "epoch": 2.222080787508486, "percentage": 44.44, "elapsed_time": "0:40:46", "remaining_time": "0:50:58", "throughput": 10276.45, "total_tokens": 25145472}
{"current_steps": 26190, "total_steps": 58920, "loss": 0.0002, "lr": 1.3600487631771833e-06, "epoch": 2.2225050916496945, "percentage": 44.45, "elapsed_time": "0:40:47", "remaining_time": "0:50:58", "throughput": 10276.89, "total_tokens": 25150528}
{"current_steps": 26195, "total_steps": 58920, "loss": 0.0052, "lr": 1.3597723936674592e-06, "epoch": 2.222929395790903, "percentage": 44.46, "elapsed_time": "0:40:47", "remaining_time": "0:50:57", "throughput": 10277.2, "total_tokens": 25155200}
{"current_steps": 26200, "total_steps": 58920, "loss": 0.0002, "lr": 1.3594959925890067e-06, "epoch": 2.2233536999321113, "percentage": 44.47, "elapsed_time": "0:40:48", "remaining_time": "0:50:57", "throughput": 10277.74, "total_tokens": 25160576}
{"current_steps": 26205, "total_steps": 58920, "loss": 0.0, "lr": 1.3592195599660787e-06, "epoch": 2.2237780040733197, "percentage": 44.48, "elapsed_time": "0:40:48", "remaining_time": "0:50:56", "throughput": 10278.1, "total_tokens": 25165376}
{"current_steps": 26210, "total_steps": 58920, "loss": 0.0001, "lr": 1.3589430958229312e-06, "epoch": 2.224202308214528, "percentage": 44.48, "elapsed_time": "0:40:48", "remaining_time": "0:50:56", "throughput": 10278.49, "total_tokens": 25170240}
{"current_steps": 26215, "total_steps": 58920, "loss": 0.0004, "lr": 1.3586666001838229e-06, "epoch": 2.2246266123557366, "percentage": 44.49, "elapsed_time": "0:40:49", "remaining_time": "0:50:55", "throughput": 10278.79, "total_tokens": 25174912}
{"current_steps": 26220, "total_steps": 58920, "loss": 0.0, "lr": 1.3583900730730156e-06, "epoch": 2.225050916496945, "percentage": 44.5, "elapsed_time": "0:40:49", "remaining_time": "0:50:55", "throughput": 10279.33, "total_tokens": 25180352}
{"current_steps": 26225, "total_steps": 58920, "loss": 0.0001, "lr": 1.3581135145147731e-06, "epoch": 2.2254752206381534, "percentage": 44.51, "elapsed_time": "0:40:49", "remaining_time": "0:50:54", "throughput": 10279.61, "total_tokens": 25184960}
{"current_steps": 26230, "total_steps": 58920, "loss": 0.0, "lr": 1.357836924533363e-06, "epoch": 2.225899524779362, "percentage": 44.52, "elapsed_time": "0:40:50", "remaining_time": "0:50:53", "throughput": 10279.89, "total_tokens": 25189504}
{"current_steps": 26235, "total_steps": 58920, "loss": 0.0001, "lr": 1.3575603031530544e-06, "epoch": 2.2263238289205702, "percentage": 44.53, "elapsed_time": "0:40:50", "remaining_time": "0:50:53", "throughput": 10280.5, "total_tokens": 25195136}
{"current_steps": 26240, "total_steps": 58920, "loss": 0.0, "lr": 1.3572836503981204e-06, "epoch": 2.2267481330617787, "percentage": 44.53, "elapsed_time": "0:40:51", "remaining_time": "0:50:52", "throughput": 10280.85, "total_tokens": 25199936}
{"current_steps": 26245, "total_steps": 58920, "loss": 0.0, "lr": 1.3570069662928358e-06, "epoch": 2.227172437202987, "percentage": 44.54, "elapsed_time": "0:40:51", "remaining_time": "0:50:52", "throughput": 10281.28, "total_tokens": 25204992}
{"current_steps": 26250, "total_steps": 58920, "loss": 0.0295, "lr": 1.3567302508614792e-06, "epoch": 2.2275967413441955, "percentage": 44.55, "elapsed_time": "0:40:51", "remaining_time": "0:50:51", "throughput": 10281.56, "total_tokens": 25209600}
{"current_steps": 26255, "total_steps": 58920, "loss": 0.0, "lr": 1.356453504128331e-06, "epoch": 2.228021045485404, "percentage": 44.56, "elapsed_time": "0:40:52", "remaining_time": "0:50:51", "throughput": 10281.76, "total_tokens": 25213952}
{"current_steps": 26260, "total_steps": 58920, "loss": 0.0001, "lr": 1.3561767261176746e-06, "epoch": 2.2284453496266123, "percentage": 44.57, "elapsed_time": "0:40:52", "remaining_time": "0:50:50", "throughput": 10282.14, "total_tokens": 25218880}
{"current_steps": 26265, "total_steps": 58920, "loss": 0.0238, "lr": 1.3558999168537966e-06, "epoch": 2.2288696537678208, "percentage": 44.58, "elapsed_time": "0:40:53", "remaining_time": "0:50:49", "throughput": 10282.37, "total_tokens": 25223296}
{"current_steps": 26270, "total_steps": 58920, "loss": 0.0, "lr": 1.3556230763609858e-06, "epoch": 2.229293957909029, "percentage": 44.59, "elapsed_time": "0:40:53", "remaining_time": "0:50:49", "throughput": 10282.54, "total_tokens": 25227520}
{"current_steps": 26275, "total_steps": 58920, "loss": 0.0, "lr": 1.355346204663534e-06, "epoch": 2.2297182620502376, "percentage": 44.59, "elapsed_time": "0:40:53", "remaining_time": "0:50:48", "throughput": 10282.71, "total_tokens": 25231744}
{"current_steps": 26280, "total_steps": 58920, "loss": 0.0, "lr": 1.3550693017857356e-06, "epoch": 2.230142566191446, "percentage": 44.6, "elapsed_time": "0:40:54", "remaining_time": "0:50:48", "throughput": 10283.16, "total_tokens": 25236864}
{"current_steps": 26285, "total_steps": 58920, "loss": 0.0, "lr": 1.3547923677518882e-06, "epoch": 2.2305668703326544, "percentage": 44.61, "elapsed_time": "0:40:54", "remaining_time": "0:50:47", "throughput": 10283.44, "total_tokens": 25241472}
{"current_steps": 26290, "total_steps": 58920, "loss": 0.027, "lr": 1.3545154025862915e-06, "epoch": 2.230991174473863, "percentage": 44.62, "elapsed_time": "0:40:54", "remaining_time": "0:50:46", "throughput": 10283.93, "total_tokens": 25246720}
{"current_steps": 26295, "total_steps": 58920, "loss": 0.0, "lr": 1.354238406313248e-06, "epoch": 2.2314154786150713, "percentage": 44.63, "elapsed_time": "0:40:55", "remaining_time": "0:50:46", "throughput": 10284.58, "total_tokens": 25252480}
{"current_steps": 26300, "total_steps": 58920, "loss": 0.0, "lr": 1.3539613789570633e-06, "epoch": 2.2318397827562797, "percentage": 44.64, "elapsed_time": "0:40:55", "remaining_time": "0:50:45", "throughput": 10284.9, "total_tokens": 25257152}
{"current_steps": 26305, "total_steps": 58920, "loss": 0.0, "lr": 1.3536843205420457e-06, "epoch": 2.232264086897488, "percentage": 44.65, "elapsed_time": "0:40:56", "remaining_time": "0:50:45", "throughput": 10285.25, "total_tokens": 25261952}
{"current_steps": 26310, "total_steps": 58920, "loss": 0.0, "lr": 1.3534072310925059e-06, "epoch": 2.2326883910386965, "percentage": 44.65, "elapsed_time": "0:40:56", "remaining_time": "0:50:44", "throughput": 10285.52, "total_tokens": 25266496}
{"current_steps": 26315, "total_steps": 58920, "loss": 0.0, "lr": 1.3531301106327575e-06, "epoch": 2.233112695179905, "percentage": 44.66, "elapsed_time": "0:40:56", "remaining_time": "0:50:44", "throughput": 10285.78, "total_tokens": 25271040}
{"current_steps": 26320, "total_steps": 58920, "loss": 0.0047, "lr": 1.352852959187117e-06, "epoch": 2.2335369993211134, "percentage": 44.67, "elapsed_time": "0:40:57", "remaining_time": "0:50:43", "throughput": 10286.03, "total_tokens": 25275520}
{"current_steps": 26325, "total_steps": 58920, "loss": 0.0208, "lr": 1.3525757767799032e-06, "epoch": 2.233961303462322, "percentage": 44.68, "elapsed_time": "0:40:57", "remaining_time": "0:50:42", "throughput": 10286.29, "total_tokens": 25280000}
{"current_steps": 26330, "total_steps": 58920, "loss": 0.0344, "lr": 1.352298563435438e-06, "epoch": 2.23438560760353, "percentage": 44.69, "elapsed_time": "0:40:58", "remaining_time": "0:50:42", "throughput": 10286.65, "total_tokens": 25284864}
{"current_steps": 26335, "total_steps": 58920, "loss": 0.053, "lr": 1.3520213191780458e-06, "epoch": 2.2348099117447386, "percentage": 44.7, "elapsed_time": "0:40:58", "remaining_time": "0:50:41", "throughput": 10287.15, "total_tokens": 25290176}
{"current_steps": 26340, "total_steps": 58920, "loss": 0.0, "lr": 1.3517440440320539e-06, "epoch": 2.235234215885947, "percentage": 44.7, "elapsed_time": "0:40:58", "remaining_time": "0:50:41", "throughput": 10287.42, "total_tokens": 25294720}
{"current_steps": 26345, "total_steps": 58920, "loss": 0.0372, "lr": 1.351466738021792e-06, "epoch": 2.2356585200271555, "percentage": 44.71, "elapsed_time": "0:40:59", "remaining_time": "0:50:40", "throughput": 10287.9, "total_tokens": 25299968}
{"current_steps": 26350, "total_steps": 58920, "loss": 0.0001, "lr": 1.3511894011715928e-06, "epoch": 2.236082824168364, "percentage": 44.72, "elapsed_time": "0:40:59", "remaining_time": "0:50:40", "throughput": 10288.22, "total_tokens": 25304704}
{"current_steps": 26355, "total_steps": 58920, "loss": 0.069, "lr": 1.3509120335057915e-06, "epoch": 2.2365071283095723, "percentage": 44.73, "elapsed_time": "0:40:59", "remaining_time": "0:50:39", "throughput": 10288.47, "total_tokens": 25309184}
{"current_steps": 26360, "total_steps": 58920, "loss": 0.0012, "lr": 1.3506346350487264e-06, "epoch": 2.2369314324507807, "percentage": 44.74, "elapsed_time": "0:41:00", "remaining_time": "0:50:39", "throughput": 10288.81, "total_tokens": 25313920}
{"current_steps": 26365, "total_steps": 58920, "loss": 0.0066, "lr": 1.3503572058247379e-06, "epoch": 2.237355736591989, "percentage": 44.75, "elapsed_time": "0:41:00", "remaining_time": "0:50:38", "throughput": 10289.23, "total_tokens": 25318976}
{"current_steps": 26370, "total_steps": 58920, "loss": 0.0693, "lr": 1.3500797458581698e-06, "epoch": 2.2377800407331976, "percentage": 44.76, "elapsed_time": "0:41:01", "remaining_time": "0:50:37", "throughput": 10289.3, "total_tokens": 25322880}
{"current_steps": 26375, "total_steps": 58920, "loss": 0.0002, "lr": 1.3498022551733677e-06, "epoch": 2.238204344874406, "percentage": 44.76, "elapsed_time": "0:41:01", "remaining_time": "0:50:37", "throughput": 10289.56, "total_tokens": 25327424}
{"current_steps": 26380, "total_steps": 58920, "loss": 0.0002, "lr": 1.3495247337946808e-06, "epoch": 2.2386286490156144, "percentage": 44.77, "elapsed_time": "0:41:01", "remaining_time": "0:50:36", "throughput": 10289.84, "total_tokens": 25332032}
{"current_steps": 26385, "total_steps": 58920, "loss": 0.0002, "lr": 1.3492471817464606e-06, "epoch": 2.239052953156823, "percentage": 44.78, "elapsed_time": "0:41:02", "remaining_time": "0:50:36", "throughput": 10290.08, "total_tokens": 25336512}
{"current_steps": 26390, "total_steps": 58920, "loss": 0.0028, "lr": 1.348969599053061e-06, "epoch": 2.2394772572980313, "percentage": 44.79, "elapsed_time": "0:41:02", "remaining_time": "0:50:35", "throughput": 10290.65, "total_tokens": 25342080}
{"current_steps": 26395, "total_steps": 58920, "loss": 0.0001, "lr": 1.348691985738839e-06, "epoch": 2.2399015614392397, "percentage": 44.8, "elapsed_time": "0:41:03", "remaining_time": "0:50:35", "throughput": 10290.94, "total_tokens": 25346688}
{"current_steps": 26400, "total_steps": 58920, "loss": 0.0158, "lr": 1.348414341828154e-06, "epoch": 2.240325865580448, "percentage": 44.81, "elapsed_time": "0:41:03", "remaining_time": "0:50:34", "throughput": 10291.23, "total_tokens": 25351296}
{"current_steps": 26405, "total_steps": 58920, "loss": 0.0423, "lr": 1.3481366673453686e-06, "epoch": 2.2407501697216565, "percentage": 44.82, "elapsed_time": "0:41:03", "remaining_time": "0:50:33", "throughput": 10291.44, "total_tokens": 25355648}
{"current_steps": 26410, "total_steps": 58920, "loss": 0.0185, "lr": 1.3478589623148477e-06, "epoch": 2.241174473862865, "percentage": 44.82, "elapsed_time": "0:41:04", "remaining_time": "0:50:33", "throughput": 10291.8, "total_tokens": 25360448}
{"current_steps": 26415, "total_steps": 58920, "loss": 0.0001, "lr": 1.347581226760959e-06, "epoch": 2.2415987780040734, "percentage": 44.83, "elapsed_time": "0:41:04", "remaining_time": "0:50:32", "throughput": 10292.15, "total_tokens": 25365248}
{"current_steps": 26420, "total_steps": 58920, "loss": 0.0003, "lr": 1.3473034607080722e-06, "epoch": 2.242023082145282, "percentage": 44.84, "elapsed_time": "0:41:04", "remaining_time": "0:50:32", "throughput": 10292.67, "total_tokens": 25370624}
{"current_steps": 26425, "total_steps": 58920, "loss": 0.0, "lr": 1.3470256641805609e-06, "epoch": 2.24244738628649, "percentage": 44.85, "elapsed_time": "0:41:05", "remaining_time": "0:50:31", "throughput": 10292.9, "total_tokens": 25375040}
{"current_steps": 26430, "total_steps": 58920, "loss": 0.0373, "lr": 1.3467478372028e-06, "epoch": 2.2428716904276986, "percentage": 44.86, "elapsed_time": "0:41:05", "remaining_time": "0:50:31", "throughput": 10293.08, "total_tokens": 25379264}
{"current_steps": 26435, "total_steps": 58920, "loss": 0.0002, "lr": 1.3464699797991688e-06, "epoch": 2.243295994568907, "percentage": 44.87, "elapsed_time": "0:41:06", "remaining_time": "0:50:30", "throughput": 10293.4, "total_tokens": 25384000}
{"current_steps": 26440, "total_steps": 58920, "loss": 0.0638, "lr": 1.3461920919940477e-06, "epoch": 2.2437202987101155, "percentage": 44.87, "elapsed_time": "0:41:06", "remaining_time": "0:50:29", "throughput": 10293.61, "total_tokens": 25388352}
{"current_steps": 26445, "total_steps": 58920, "loss": 0.0002, "lr": 1.3459141738118205e-06, "epoch": 2.244144602851324, "percentage": 44.88, "elapsed_time": "0:41:06", "remaining_time": "0:50:29", "throughput": 10293.97, "total_tokens": 25393216}
{"current_steps": 26450, "total_steps": 58920, "loss": 0.0006, "lr": 1.3456362252768736e-06, "epoch": 2.2445689069925323, "percentage": 44.89, "elapsed_time": "0:41:07", "remaining_time": "0:50:28", "throughput": 10294.42, "total_tokens": 25398336}
{"current_steps": 26455, "total_steps": 58920, "loss": 0.0001, "lr": 1.3453582464135958e-06, "epoch": 2.2449932111337407, "percentage": 44.9, "elapsed_time": "0:41:07", "remaining_time": "0:50:28", "throughput": 10294.74, "total_tokens": 25403008}
{"current_steps": 26460, "total_steps": 58920, "loss": 0.0001, "lr": 1.3450802372463784e-06, "epoch": 2.245417515274949, "percentage": 44.91, "elapsed_time": "0:41:07", "remaining_time": "0:50:27", "throughput": 10295.03, "total_tokens": 25407616}
{"current_steps": 26465, "total_steps": 58920, "loss": 0.0536, "lr": 1.3448021977996163e-06, "epoch": 2.2458418194161576, "percentage": 44.92, "elapsed_time": "0:41:08", "remaining_time": "0:50:26", "throughput": 10295.26, "total_tokens": 25412032}
{"current_steps": 26470, "total_steps": 58920, "loss": 0.0001, "lr": 1.3445241280977064e-06, "epoch": 2.246266123557366, "percentage": 44.93, "elapsed_time": "0:41:08", "remaining_time": "0:50:26", "throughput": 10295.51, "total_tokens": 25416448}
{"current_steps": 26475, "total_steps": 58920, "loss": 0.0001, "lr": 1.344246028165048e-06, "epoch": 2.2466904276985744, "percentage": 44.93, "elapsed_time": "0:41:09", "remaining_time": "0:50:25", "throughput": 10295.95, "total_tokens": 25421568}
{"current_steps": 26480, "total_steps": 58920, "loss": 0.0001, "lr": 1.3439678980260437e-06, "epoch": 2.247114731839783, "percentage": 44.94, "elapsed_time": "0:41:09", "remaining_time": "0:50:25", "throughput": 10296.19, "total_tokens": 25426048}
{"current_steps": 26485, "total_steps": 58920, "loss": 0.0001, "lr": 1.343689737705098e-06, "epoch": 2.2475390359809913, "percentage": 44.95, "elapsed_time": "0:41:09", "remaining_time": "0:50:24", "throughput": 10296.52, "total_tokens": 25430784}
{"current_steps": 26490, "total_steps": 58920, "loss": 0.0001, "lr": 1.3434115472266188e-06, "epoch": 2.2479633401221997, "percentage": 44.96, "elapsed_time": "0:41:10", "remaining_time": "0:50:24", "throughput": 10297.04, "total_tokens": 25436160}
{"current_steps": 26495, "total_steps": 58920, "loss": 0.0004, "lr": 1.3431333266150163e-06, "epoch": 2.248387644263408, "percentage": 44.97, "elapsed_time": "0:41:10", "remaining_time": "0:50:23", "throughput": 10297.28, "total_tokens": 25440640}
{"current_steps": 26500, "total_steps": 58920, "loss": 0.0001, "lr": 1.342855075894703e-06, "epoch": 2.2488119484046165, "percentage": 44.98, "elapsed_time": "0:41:10", "remaining_time": "0:50:23", "throughput": 10297.57, "total_tokens": 25445248}
{"current_steps": 26505, "total_steps": 58920, "loss": 0.0002, "lr": 1.342576795090095e-06, "epoch": 2.249236252545825, "percentage": 44.98, "elapsed_time": "0:41:11", "remaining_time": "0:50:22", "throughput": 10298.06, "total_tokens": 25450496}
{"current_steps": 26510, "total_steps": 58920, "loss": 0.0001, "lr": 1.34229848422561e-06, "epoch": 2.2496605566870334, "percentage": 44.99, "elapsed_time": "0:41:11", "remaining_time": "0:50:21", "throughput": 10298.65, "total_tokens": 25456064}
{"current_steps": 26514, "total_steps": 58920, "eval_loss": 0.10741162300109863, "epoch": 2.25, "percentage": 45.0, "elapsed_time": "0:41:28", "remaining_time": "0:50:41", "throughput": 10231.11, "total_tokens": 25460032}
{"current_steps": 26515, "total_steps": 58920, "loss": 0.0449, "lr": 1.3420201433256689e-06, "epoch": 2.2500848608282418, "percentage": 45.0, "elapsed_time": "0:42:02", "remaining_time": "0:51:22", "throughput": 10094.92, "total_tokens": 25461440}
{"current_steps": 26520, "total_steps": 58920, "loss": 0.0113, "lr": 1.341741772414695e-06, "epoch": 2.25050916496945, "percentage": 45.01, "elapsed_time": "0:42:02", "remaining_time": "0:51:21", "throughput": 10095.12, "total_tokens": 25465728}
{"current_steps": 26525, "total_steps": 58920, "loss": 0.0003, "lr": 1.3414633715171142e-06, "epoch": 2.2509334691106586, "percentage": 45.02, "elapsed_time": "0:42:02", "remaining_time": "0:51:21", "throughput": 10095.66, "total_tokens": 25471104}
{"current_steps": 26530, "total_steps": 58920, "loss": 0.0287, "lr": 1.3411849406573556e-06, "epoch": 2.251357773251867, "percentage": 45.03, "elapsed_time": "0:42:03", "remaining_time": "0:51:20", "throughput": 10096.03, "total_tokens": 25475904}
{"current_steps": 26535, "total_steps": 58920, "loss": 0.0251, "lr": 1.3409064798598503e-06, "epoch": 2.2517820773930755, "percentage": 45.04, "elapsed_time": "0:42:03", "remaining_time": "0:51:20", "throughput": 10096.29, "total_tokens": 25480320}
{"current_steps": 26540, "total_steps": 58920, "loss": 0.0301, "lr": 1.3406279891490324e-06, "epoch": 2.252206381534284, "percentage": 45.04, "elapsed_time": "0:42:04", "remaining_time": "0:51:19", "throughput": 10096.65, "total_tokens": 25485056}
{"current_steps": 26545, "total_steps": 58920, "loss": 0.0002, "lr": 1.3403494685493381e-06, "epoch": 2.2526306856754923, "percentage": 45.05, "elapsed_time": "0:42:04", "remaining_time": "0:51:18", "throughput": 10096.99, "total_tokens": 25489792}
{"current_steps": 26550, "total_steps": 58920, "loss": 0.0001, "lr": 1.340070918085207e-06, "epoch": 2.2530549898167007, "percentage": 45.06, "elapsed_time": "0:42:04", "remaining_time": "0:51:18", "throughput": 10097.41, "total_tokens": 25494784}
{"current_steps": 26555, "total_steps": 58920, "loss": 0.0368, "lr": 1.3397923377810803e-06, "epoch": 2.253479293957909, "percentage": 45.07, "elapsed_time": "0:42:05", "remaining_time": "0:51:17", "throughput": 10098.19, "total_tokens": 25500992}
{"current_steps": 26560, "total_steps": 58920, "loss": 0.0002, "lr": 1.339513727661403e-06, "epoch": 2.2539035980991176, "percentage": 45.08, "elapsed_time": "0:42:05", "remaining_time": "0:51:17", "throughput": 10097.51, "total_tokens": 25505792}
{"current_steps": 26565, "total_steps": 58920, "loss": 0.0001, "lr": 1.3392350877506217e-06, "epoch": 2.254327902240326, "percentage": 45.09, "elapsed_time": "0:42:06", "remaining_time": "0:51:16", "throughput": 10097.8, "total_tokens": 25510336}
{"current_steps": 26570, "total_steps": 58920, "loss": 0.0002, "lr": 1.3389564180731865e-06, "epoch": 2.2547522063815344, "percentage": 45.1, "elapsed_time": "0:42:06", "remaining_time": "0:51:16", "throughput": 10098.17, "total_tokens": 25515200}
{"current_steps": 26575, "total_steps": 58920, "loss": 0.0001, "lr": 1.3386777186535493e-06, "epoch": 2.255176510522743, "percentage": 45.1, "elapsed_time": "0:42:07", "remaining_time": "0:51:15", "throughput": 10098.52, "total_tokens": 25519936}
{"current_steps": 26580, "total_steps": 58920, "loss": 0.0002, "lr": 1.3383989895161652e-06, "epoch": 2.2556008146639512, "percentage": 45.11, "elapsed_time": "0:42:07", "remaining_time": "0:51:15", "throughput": 10098.93, "total_tokens": 25524864}
{"current_steps": 26585, "total_steps": 58920, "loss": 0.0001, "lr": 1.3381202306854913e-06, "epoch": 2.2560251188051597, "percentage": 45.12, "elapsed_time": "0:42:07", "remaining_time": "0:51:14", "throughput": 10099.31, "total_tokens": 25529728}
{"current_steps": 26590, "total_steps": 58920, "loss": 0.0001, "lr": 1.337841442185988e-06, "epoch": 2.256449422946368, "percentage": 45.13, "elapsed_time": "0:42:08", "remaining_time": "0:51:14", "throughput": 10099.93, "total_tokens": 25535360}
{"current_steps": 26595, "total_steps": 58920, "loss": 0.0812, "lr": 1.3375626240421181e-06, "epoch": 2.2568737270875765, "percentage": 45.14, "elapsed_time": "0:42:08", "remaining_time": "0:51:13", "throughput": 10100.31, "total_tokens": 25540160}
{"current_steps": 26600, "total_steps": 58920, "loss": 0.0001, "lr": 1.3372837762783466e-06, "epoch": 2.257298031228785, "percentage": 45.15, "elapsed_time": "0:42:09", "remaining_time": "0:51:12", "throughput": 10100.57, "total_tokens": 25544704}
{"current_steps": 26605, "total_steps": 58920, "loss": 0.0563, "lr": 1.3370048989191416e-06, "epoch": 2.2577223353699933, "percentage": 45.15, "elapsed_time": "0:42:09", "remaining_time": "0:51:12", "throughput": 10101.05, "total_tokens": 25549888}
{"current_steps": 26610, "total_steps": 58920, "loss": 0.0006, "lr": 1.3367259919889732e-06, "epoch": 2.2581466395112018, "percentage": 45.16, "elapsed_time": "0:42:09", "remaining_time": "0:51:11", "throughput": 10101.33, "total_tokens": 25554432}
{"current_steps": 26615, "total_steps": 58920, "loss": 0.0031, "lr": 1.3364470555123151e-06, "epoch": 2.25857094365241, "percentage": 45.17, "elapsed_time": "0:42:10", "remaining_time": "0:51:11", "throughput": 10101.59, "total_tokens": 25558848}
{"current_steps": 26620, "total_steps": 58920, "loss": 0.0368, "lr": 1.3361680895136425e-06, "epoch": 2.2589952477936186, "percentage": 45.18, "elapsed_time": "0:42:10", "remaining_time": "0:51:10", "throughput": 10101.86, "total_tokens": 25563328}
{"current_steps": 26625, "total_steps": 58920, "loss": 0.0106, "lr": 1.3358890940174337e-06, "epoch": 2.259419551934827, "percentage": 45.19, "elapsed_time": "0:42:10", "remaining_time": "0:51:09", "throughput": 10102.2, "total_tokens": 25568064}
{"current_steps": 26630, "total_steps": 58920, "loss": 0.0006, "lr": 1.3356100690481695e-06, "epoch": 2.2598438560760354, "percentage": 45.2, "elapsed_time": "0:42:11", "remaining_time": "0:51:09", "throughput": 10102.5, "total_tokens": 25572608}
{"current_steps": 26635, "total_steps": 58920, "loss": 0.0003, "lr": 1.3353310146303335e-06, "epoch": 2.260268160217244, "percentage": 45.21, "elapsed_time": "0:42:11", "remaining_time": "0:51:08", "throughput": 10102.82, "total_tokens": 25577280}
{"current_steps": 26640, "total_steps": 58920, "loss": 0.0001, "lr": 1.335051930788412e-06, "epoch": 2.2606924643584523, "percentage": 45.21, "elapsed_time": "0:42:12", "remaining_time": "0:51:08", "throughput": 10103.07, "total_tokens": 25581696}
{"current_steps": 26645, "total_steps": 58920, "loss": 0.0002, "lr": 1.3347728175468928e-06, "epoch": 2.2611167684996607, "percentage": 45.22, "elapsed_time": "0:42:12", "remaining_time": "0:51:07", "throughput": 10103.55, "total_tokens": 25586880}
{"current_steps": 26650, "total_steps": 58920, "loss": 0.0001, "lr": 1.3344936749302677e-06, "epoch": 2.261541072640869, "percentage": 45.23, "elapsed_time": "0:42:12", "remaining_time": "0:51:06", "throughput": 10104.02, "total_tokens": 25592064}
{"current_steps": 26655, "total_steps": 58920, "loss": 0.0001, "lr": 1.3342145029630305e-06, "epoch": 2.2619653767820775, "percentage": 45.24, "elapsed_time": "0:42:13", "remaining_time": "0:51:06", "throughput": 10104.24, "total_tokens": 25596416}
{"current_steps": 26660, "total_steps": 58920, "loss": 0.0, "lr": 1.3339353016696775e-06, "epoch": 2.262389680923286, "percentage": 45.25, "elapsed_time": "0:42:13", "remaining_time": "0:51:05", "throughput": 10104.56, "total_tokens": 25601088}
{"current_steps": 26665, "total_steps": 58920, "loss": 0.0001, "lr": 1.333656071074707e-06, "epoch": 2.2628139850644944, "percentage": 45.26, "elapsed_time": "0:42:13", "remaining_time": "0:51:05", "throughput": 10104.78, "total_tokens": 25605440}
{"current_steps": 26670, "total_steps": 58920, "loss": 0.0, "lr": 1.3333768112026214e-06, "epoch": 2.263238289205703, "percentage": 45.26, "elapsed_time": "0:42:14", "remaining_time": "0:51:04", "throughput": 10104.93, "total_tokens": 25609600}
{"current_steps": 26675, "total_steps": 58920, "loss": 0.0, "lr": 1.3330975220779238e-06, "epoch": 2.2636625933469112, "percentage": 45.27, "elapsed_time": "0:42:14", "remaining_time": "0:51:04", "throughput": 10105.28, "total_tokens": 25614336}
{"current_steps": 26680, "total_steps": 58920, "loss": 0.0002, "lr": 1.3328182037251212e-06, "epoch": 2.2640868974881196, "percentage": 45.28, "elapsed_time": "0:42:15", "remaining_time": "0:51:03", "throughput": 10105.54, "total_tokens": 25618816}
{"current_steps": 26685, "total_steps": 58920, "loss": 0.0119, "lr": 1.3325388561687231e-06, "epoch": 2.264511201629328, "percentage": 45.29, "elapsed_time": "0:42:15", "remaining_time": "0:51:02", "throughput": 10105.8, "total_tokens": 25623232}
{"current_steps": 26690, "total_steps": 58920, "loss": 0.0641, "lr": 1.332259479433241e-06, "epoch": 2.2649355057705365, "percentage": 45.3, "elapsed_time": "0:42:15", "remaining_time": "0:51:02", "throughput": 10106.28, "total_tokens": 25628416}
{"current_steps": 26695, "total_steps": 58920, "loss": 0.1234, "lr": 1.3319800735431895e-06, "epoch": 2.265359809911745, "percentage": 45.31, "elapsed_time": "0:42:16", "remaining_time": "0:51:01", "throughput": 10106.68, "total_tokens": 25633408}
{"current_steps": 26700, "total_steps": 58920, "loss": 0.0001, "lr": 1.3317006385230849e-06, "epoch": 2.2657841140529533, "percentage": 45.32, "elapsed_time": "0:42:16", "remaining_time": "0:51:01", "throughput": 10106.97, "total_tokens": 25637952}
{"current_steps": 26705, "total_steps": 58920, "loss": 0.0004, "lr": 1.331421174397447e-06, "epoch": 2.2662084181941617, "percentage": 45.32, "elapsed_time": "0:42:17", "remaining_time": "0:51:00", "throughput": 10107.34, "total_tokens": 25642816}
{"current_steps": 26710, "total_steps": 58920, "loss": 0.0012, "lr": 1.331141681190797e-06, "epoch": 2.26663272233537, "percentage": 45.33, "elapsed_time": "0:42:17", "remaining_time": "0:50:59", "throughput": 10107.64, "total_tokens": 25647360}
{"current_steps": 26715, "total_steps": 58920, "loss": 0.0001, "lr": 1.3308621589276607e-06, "epoch": 2.2670570264765786, "percentage": 45.34, "elapsed_time": "0:42:17", "remaining_time": "0:50:59", "throughput": 10107.95, "total_tokens": 25652032}
{"current_steps": 26720, "total_steps": 58920, "loss": 0.0002, "lr": 1.3305826076325643e-06, "epoch": 2.267481330617787, "percentage": 45.35, "elapsed_time": "0:42:18", "remaining_time": "0:50:58", "throughput": 10108.17, "total_tokens": 25656384}
{"current_steps": 26725, "total_steps": 58920, "loss": 0.0446, "lr": 1.330303027330038e-06, "epoch": 2.2679056347589954, "percentage": 45.36, "elapsed_time": "0:42:18", "remaining_time": "0:50:58", "throughput": 10108.6, "total_tokens": 25661376}
{"current_steps": 26730, "total_steps": 58920, "loss": 0.0356, "lr": 1.3300234180446132e-06, "epoch": 2.268329938900204, "percentage": 45.37, "elapsed_time": "0:42:18", "remaining_time": "0:50:57", "throughput": 10109.04, "total_tokens": 25666432}
{"current_steps": 26735, "total_steps": 58920, "loss": 0.0003, "lr": 1.329743779800825e-06, "epoch": 2.2687542430414123, "percentage": 45.38, "elapsed_time": "0:42:19", "remaining_time": "0:50:56", "throughput": 10109.47, "total_tokens": 25671424}
{"current_steps": 26740, "total_steps": 58920, "loss": 0.0005, "lr": 1.3294641126232106e-06, "epoch": 2.2691785471826207, "percentage": 45.38, "elapsed_time": "0:42:19", "remaining_time": "0:50:56", "throughput": 10109.82, "total_tokens": 25676160}
{"current_steps": 26745, "total_steps": 58920, "loss": 0.0467, "lr": 1.3291844165363105e-06, "epoch": 2.269602851323829, "percentage": 45.39, "elapsed_time": "0:42:20", "remaining_time": "0:50:55", "throughput": 10110.23, "total_tokens": 25681088}
{"current_steps": 26750, "total_steps": 58920, "loss": 0.0002, "lr": 1.3289046915646657e-06, "epoch": 2.2700271554650375, "percentage": 45.4, "elapsed_time": "0:42:20", "remaining_time": "0:50:55", "throughput": 10110.59, "total_tokens": 25685888}
{"current_steps": 26755, "total_steps": 58920, "loss": 0.0288, "lr": 1.328624937732822e-06, "epoch": 2.270451459606246, "percentage": 45.41, "elapsed_time": "0:42:20", "remaining_time": "0:50:54", "throughput": 10110.91, "total_tokens": 25690560}
{"current_steps": 26760, "total_steps": 58920, "loss": 0.0002, "lr": 1.3283451550653264e-06, "epoch": 2.2708757637474544, "percentage": 45.42, "elapsed_time": "0:42:21", "remaining_time": "0:50:54", "throughput": 10111.22, "total_tokens": 25695168}
{"current_steps": 26765, "total_steps": 58920, "loss": 0.0001, "lr": 1.328065343586729e-06, "epoch": 2.271300067888663, "percentage": 45.43, "elapsed_time": "0:42:21", "remaining_time": "0:50:53", "throughput": 10111.6, "total_tokens": 25700032}
{"current_steps": 26770, "total_steps": 58920, "loss": 0.0003, "lr": 1.3277855033215818e-06, "epoch": 2.2717243720298708, "percentage": 45.43, "elapsed_time": "0:42:22", "remaining_time": "0:50:52", "throughput": 10111.89, "total_tokens": 25704576}
{"current_steps": 26775, "total_steps": 58920, "loss": 0.0001, "lr": 1.3275056342944404e-06, "epoch": 2.2721486761710796, "percentage": 45.44, "elapsed_time": "0:42:22", "remaining_time": "0:50:52", "throughput": 10112.26, "total_tokens": 25709440}
{"current_steps": 26780, "total_steps": 58920, "loss": 0.0298, "lr": 1.3272257365298623e-06, "epoch": 2.2725729803122876, "percentage": 45.45, "elapsed_time": "0:42:22", "remaining_time": "0:50:51", "throughput": 10112.67, "total_tokens": 25714368}
{"current_steps": 26785, "total_steps": 58920, "loss": 0.0012, "lr": 1.326945810052407e-06, "epoch": 2.2729972844534965, "percentage": 45.46, "elapsed_time": "0:42:23", "remaining_time": "0:50:51", "throughput": 10113.04, "total_tokens": 25719168}
{"current_steps": 26790, "total_steps": 58920, "loss": 0.0001, "lr": 1.3266658548866376e-06, "epoch": 2.2734215885947044, "percentage": 45.47, "elapsed_time": "0:42:23", "remaining_time": "0:50:50", "throughput": 10113.45, "total_tokens": 25724160}
{"current_steps": 26795, "total_steps": 58920, "loss": 0.039, "lr": 1.3263858710571186e-06, "epoch": 2.2738458927359133, "percentage": 45.48, "elapsed_time": "0:42:23", "remaining_time": "0:50:49", "throughput": 10113.86, "total_tokens": 25729152}
{"current_steps": 26800, "total_steps": 58920, "loss": 0.0001, "lr": 1.3261058585884177e-06, "epoch": 2.2742701968771213, "percentage": 45.49, "elapsed_time": "0:42:24", "remaining_time": "0:50:49", "throughput": 10114.15, "total_tokens": 25733824}
{"current_steps": 26805, "total_steps": 58920, "loss": 0.0001, "lr": 1.3258258175051053e-06, "epoch": 2.27469450101833, "percentage": 45.49, "elapsed_time": "0:42:24", "remaining_time": "0:50:48", "throughput": 10114.37, "total_tokens": 25738240}
{"current_steps": 26810, "total_steps": 58920, "loss": 0.0137, "lr": 1.3255457478317538e-06, "epoch": 2.275118805159538, "percentage": 45.5, "elapsed_time": "0:42:25", "remaining_time": "0:50:48", "throughput": 10114.85, "total_tokens": 25743424}
{"current_steps": 26815, "total_steps": 58920, "loss": 0.0001, "lr": 1.3252656495929384e-06, "epoch": 2.275543109300747, "percentage": 45.51, "elapsed_time": "0:42:25", "remaining_time": "0:50:47", "throughput": 10115.14, "total_tokens": 25748032}
{"current_steps": 26820, "total_steps": 58920, "loss": 0.0001, "lr": 1.3249855228132366e-06, "epoch": 2.275967413441955, "percentage": 45.52, "elapsed_time": "0:42:25", "remaining_time": "0:50:47", "throughput": 10115.49, "total_tokens": 25752832}
{"current_steps": 26825, "total_steps": 58920, "loss": 0.0001, "lr": 1.3247053675172285e-06, "epoch": 2.276391717583164, "percentage": 45.53, "elapsed_time": "0:42:26", "remaining_time": "0:50:46", "throughput": 10115.79, "total_tokens": 25757504}
{"current_steps": 26830, "total_steps": 58920, "loss": 0.0, "lr": 1.3244251837294965e-06, "epoch": 2.276816021724372, "percentage": 45.54, "elapsed_time": "0:42:26", "remaining_time": "0:50:45", "throughput": 10116.12, "total_tokens": 25762240}
{"current_steps": 26835, "total_steps": 58920, "loss": 0.0001, "lr": 1.324144971474626e-06, "epoch": 2.2772403258655807, "percentage": 45.54, "elapsed_time": "0:42:27", "remaining_time": "0:50:45", "throughput": 10116.8, "total_tokens": 25768128}
{"current_steps": 26840, "total_steps": 58920, "loss": 0.0002, "lr": 1.323864730777205e-06, "epoch": 2.2776646300067886, "percentage": 45.55, "elapsed_time": "0:42:27", "remaining_time": "0:50:44", "throughput": 10117.38, "total_tokens": 25773696}
{"current_steps": 26845, "total_steps": 58920, "loss": 0.0551, "lr": 1.3235844616618228e-06, "epoch": 2.2780889341479975, "percentage": 45.56, "elapsed_time": "0:42:27", "remaining_time": "0:50:44", "throughput": 10117.63, "total_tokens": 25778176}
{"current_steps": 26850, "total_steps": 58920, "loss": 0.1001, "lr": 1.3233041641530724e-06, "epoch": 2.2785132382892055, "percentage": 45.57, "elapsed_time": "0:42:28", "remaining_time": "0:50:43", "throughput": 10118.22, "total_tokens": 25783808}
{"current_steps": 26855, "total_steps": 58920, "loss": 0.0001, "lr": 1.323023838275549e-06, "epoch": 2.2789375424304144, "percentage": 45.58, "elapsed_time": "0:42:28", "remaining_time": "0:50:43", "throughput": 10118.38, "total_tokens": 25787968}
{"current_steps": 26860, "total_steps": 58920, "loss": 0.003, "lr": 1.3227434840538497e-06, "epoch": 2.2793618465716223, "percentage": 45.59, "elapsed_time": "0:42:29", "remaining_time": "0:50:42", "throughput": 10118.61, "total_tokens": 25792448}
{"current_steps": 26865, "total_steps": 58920, "loss": 0.0003, "lr": 1.3224631015125753e-06, "epoch": 2.279786150712831, "percentage": 45.6, "elapsed_time": "0:42:29", "remaining_time": "0:50:41", "throughput": 10118.8, "total_tokens": 25796736}
{"current_steps": 26870, "total_steps": 58920, "loss": 0.0003, "lr": 1.3221826906763282e-06, "epoch": 2.280210454854039, "percentage": 45.6, "elapsed_time": "0:42:29", "remaining_time": "0:50:41", "throughput": 10119.22, "total_tokens": 25801792}
{"current_steps": 26875, "total_steps": 58920, "loss": 0.0003, "lr": 1.3219022515697129e-06, "epoch": 2.280634758995248, "percentage": 45.61, "elapsed_time": "0:42:30", "remaining_time": "0:50:40", "throughput": 10119.53, "total_tokens": 25806464}
{"current_steps": 26880, "total_steps": 58920, "loss": 0.0551, "lr": 1.3216217842173374e-06, "epoch": 2.281059063136456, "percentage": 45.62, "elapsed_time": "0:42:30", "remaining_time": "0:50:40", "throughput": 10119.73, "total_tokens": 25810880}
{"current_steps": 26885, "total_steps": 58920, "loss": 0.0006, "lr": 1.3213412886438115e-06, "epoch": 2.281483367277665, "percentage": 45.63, "elapsed_time": "0:42:30", "remaining_time": "0:50:39", "throughput": 10120.28, "total_tokens": 25816384}
{"current_steps": 26890, "total_steps": 58920, "loss": 0.0315, "lr": 1.3210607648737474e-06, "epoch": 2.281907671418873, "percentage": 45.64, "elapsed_time": "0:42:31", "remaining_time": "0:50:39", "throughput": 10120.55, "total_tokens": 25820992}
{"current_steps": 26895, "total_steps": 58920, "loss": 0.0003, "lr": 1.3207802129317607e-06, "epoch": 2.2823319755600817, "percentage": 45.65, "elapsed_time": "0:42:31", "remaining_time": "0:50:38", "throughput": 10121.01, "total_tokens": 25826176}
{"current_steps": 26900, "total_steps": 58920, "loss": 0.0004, "lr": 1.3204996328424685e-06, "epoch": 2.2827562797012897, "percentage": 45.66, "elapsed_time": "0:42:32", "remaining_time": "0:50:37", "throughput": 10121.24, "total_tokens": 25830592}
{"current_steps": 26905, "total_steps": 58920, "loss": 0.0002, "lr": 1.3202190246304907e-06, "epoch": 2.283180583842498, "percentage": 45.66, "elapsed_time": "0:42:32", "remaining_time": "0:50:37", "throughput": 10121.5, "total_tokens": 25835136}
{"current_steps": 26910, "total_steps": 58920, "loss": 0.0001, "lr": 1.3199383883204497e-06, "epoch": 2.2836048879837065, "percentage": 45.67, "elapsed_time": "0:42:32", "remaining_time": "0:50:36", "throughput": 10121.86, "total_tokens": 25840000}
{"current_steps": 26915, "total_steps": 58920, "loss": 0.0005, "lr": 1.3196577239369702e-06, "epoch": 2.284029192124915, "percentage": 45.68, "elapsed_time": "0:42:33", "remaining_time": "0:50:36", "throughput": 10122.06, "total_tokens": 25844288}
{"current_steps": 26920, "total_steps": 58920, "loss": 0.028, "lr": 1.3193770315046792e-06, "epoch": 2.2844534962661234, "percentage": 45.69, "elapsed_time": "0:42:33", "remaining_time": "0:50:35", "throughput": 10122.26, "total_tokens": 25848576}
{"current_steps": 26925, "total_steps": 58920, "loss": 0.031, "lr": 1.3190963110482073e-06, "epoch": 2.284877800407332, "percentage": 45.7, "elapsed_time": "0:42:34", "remaining_time": "0:50:34", "throughput": 10122.64, "total_tokens": 25853376}
{"current_steps": 26930, "total_steps": 58920, "loss": 0.0002, "lr": 1.3188155625921858e-06, "epoch": 2.28530210454854, "percentage": 45.71, "elapsed_time": "0:42:34", "remaining_time": "0:50:34", "throughput": 10122.99, "total_tokens": 25858176}
{"current_steps": 26935, "total_steps": 58920, "loss": 0.0001, "lr": 1.3185347861612498e-06, "epoch": 2.2857264086897486, "percentage": 45.71, "elapsed_time": "0:42:34", "remaining_time": "0:50:33", "throughput": 10123.38, "total_tokens": 25863104}
{"current_steps": 26940, "total_steps": 58920, "loss": 0.0001, "lr": 1.3182539817800366e-06, "epoch": 2.286150712830957, "percentage": 45.72, "elapsed_time": "0:42:35", "remaining_time": "0:50:33", "throughput": 10123.56, "total_tokens": 25867392}
{"current_steps": 26945, "total_steps": 58920, "loss": 0.0001, "lr": 1.3179731494731855e-06, "epoch": 2.2865750169721655, "percentage": 45.73, "elapsed_time": "0:42:35", "remaining_time": "0:50:32", "throughput": 10123.95, "total_tokens": 25872320}
{"current_steps": 26950, "total_steps": 58920, "loss": 0.0175, "lr": 1.3176922892653383e-06, "epoch": 2.286999321113374, "percentage": 45.74, "elapsed_time": "0:42:35", "remaining_time": "0:50:32", "throughput": 10124.4, "total_tokens": 25877504}
{"current_steps": 26955, "total_steps": 58920, "loss": 0.0275, "lr": 1.3174114011811402e-06, "epoch": 2.2874236252545823, "percentage": 45.75, "elapsed_time": "0:42:36", "remaining_time": "0:50:31", "throughput": 10124.74, "total_tokens": 25882304}
{"current_steps": 26960, "total_steps": 58920, "loss": 0.0001, "lr": 1.3171304852452374e-06, "epoch": 2.2878479293957907, "percentage": 45.76, "elapsed_time": "0:42:36", "remaining_time": "0:50:30", "throughput": 10125.23, "total_tokens": 25887616}
{"current_steps": 26965, "total_steps": 58920, "loss": 0.0025, "lr": 1.3168495414822792e-06, "epoch": 2.288272233536999, "percentage": 45.77, "elapsed_time": "0:42:37", "remaining_time": "0:50:30", "throughput": 10125.49, "total_tokens": 25892160}
{"current_steps": 26970, "total_steps": 58920, "loss": 0.0001, "lr": 1.3165685699169183e-06, "epoch": 2.2886965376782076, "percentage": 45.77, "elapsed_time": "0:42:37", "remaining_time": "0:50:29", "throughput": 10125.76, "total_tokens": 25896704}
{"current_steps": 26975, "total_steps": 58920, "loss": 0.0157, "lr": 1.316287570573808e-06, "epoch": 2.289120841819416, "percentage": 45.78, "elapsed_time": "0:42:37", "remaining_time": "0:50:29", "throughput": 10126.25, "total_tokens": 25902016}
{"current_steps": 26980, "total_steps": 58920, "loss": 0.0001, "lr": 1.3160065434776056e-06, "epoch": 2.2895451459606244, "percentage": 45.79, "elapsed_time": "0:42:38", "remaining_time": "0:50:28", "throughput": 10126.65, "total_tokens": 25907008}
{"current_steps": 26985, "total_steps": 58920, "loss": 0.0691, "lr": 1.3157254886529693e-06, "epoch": 2.289969450101833, "percentage": 45.8, "elapsed_time": "0:42:38", "remaining_time": "0:50:28", "throughput": 10126.98, "total_tokens": 25911744}
{"current_steps": 26990, "total_steps": 58920, "loss": 0.031, "lr": 1.315444406124562e-06, "epoch": 2.2903937542430413, "percentage": 45.81, "elapsed_time": "0:42:39", "remaining_time": "0:50:27", "throughput": 10127.16, "total_tokens": 25915968}
{"current_steps": 26995, "total_steps": 58920, "loss": 0.0012, "lr": 1.3151632959170469e-06, "epoch": 2.2908180583842497, "percentage": 45.82, "elapsed_time": "0:42:39", "remaining_time": "0:50:26", "throughput": 10127.59, "total_tokens": 25921024}
{"current_steps": 27000, "total_steps": 58920, "loss": 0.0001, "lr": 1.3148821580550904e-06, "epoch": 2.291242362525458, "percentage": 45.82, "elapsed_time": "0:42:39", "remaining_time": "0:50:26", "throughput": 10127.94, "total_tokens": 25925760}
{"current_steps": 27005, "total_steps": 58920, "loss": 0.0177, "lr": 1.3146009925633613e-06, "epoch": 2.2916666666666665, "percentage": 45.83, "elapsed_time": "0:42:40", "remaining_time": "0:50:25", "throughput": 10128.19, "total_tokens": 25930240}
{"current_steps": 27010, "total_steps": 58920, "loss": 0.0001, "lr": 1.314319799466531e-06, "epoch": 2.292090970807875, "percentage": 45.84, "elapsed_time": "0:42:40", "remaining_time": "0:50:25", "throughput": 10128.52, "total_tokens": 25935040}
{"current_steps": 27015, "total_steps": 58920, "loss": 0.0001, "lr": 1.314038578789273e-06, "epoch": 2.2925152749490834, "percentage": 45.85, "elapsed_time": "0:42:40", "remaining_time": "0:50:24", "throughput": 10129.02, "total_tokens": 25940352}
{"current_steps": 27020, "total_steps": 58920, "loss": 0.0001, "lr": 1.3137573305562635e-06, "epoch": 2.292939579090292, "percentage": 45.86, "elapsed_time": "0:42:41", "remaining_time": "0:50:23", "throughput": 10129.15, "total_tokens": 25944448}
{"current_steps": 27025, "total_steps": 58920, "loss": 0.0316, "lr": 1.3134760547921812e-06, "epoch": 2.2933638832315, "percentage": 45.87, "elapsed_time": "0:42:41", "remaining_time": "0:50:23", "throughput": 10129.39, "total_tokens": 25948928}
{"current_steps": 27030, "total_steps": 58920, "loss": 0.0003, "lr": 1.313194751521707e-06, "epoch": 2.2937881873727086, "percentage": 45.88, "elapsed_time": "0:42:42", "remaining_time": "0:50:22", "throughput": 10129.62, "total_tokens": 25953344}
{"current_steps": 27035, "total_steps": 58920, "loss": 0.0001, "lr": 1.3129134207695243e-06, "epoch": 2.294212491513917, "percentage": 45.88, "elapsed_time": "0:42:42", "remaining_time": "0:50:22", "throughput": 10129.88, "total_tokens": 25957888}
{"current_steps": 27040, "total_steps": 58920, "loss": 0.0366, "lr": 1.3126320625603182e-06, "epoch": 2.2946367956551255, "percentage": 45.89, "elapsed_time": "0:42:42", "remaining_time": "0:50:21", "throughput": 10130.04, "total_tokens": 25962112}
{"current_steps": 27045, "total_steps": 58920, "loss": 0.0294, "lr": 1.3123506769187778e-06, "epoch": 2.295061099796334, "percentage": 45.9, "elapsed_time": "0:42:43", "remaining_time": "0:50:21", "throughput": 10130.4, "total_tokens": 25966912}
{"current_steps": 27050, "total_steps": 58920, "loss": 0.0001, "lr": 1.312069263869593e-06, "epoch": 2.2954854039375423, "percentage": 45.91, "elapsed_time": "0:42:43", "remaining_time": "0:50:20", "throughput": 10130.86, "total_tokens": 25972096}
{"current_steps": 27055, "total_steps": 58920, "loss": 0.0001, "lr": 1.311787823437457e-06, "epoch": 2.2959097080787507, "percentage": 45.92, "elapsed_time": "0:42:44", "remaining_time": "0:50:19", "throughput": 10131.21, "total_tokens": 25976960}
{"current_steps": 27060, "total_steps": 58920, "loss": 0.0487, "lr": 1.3115063556470653e-06, "epoch": 2.296334012219959, "percentage": 45.93, "elapsed_time": "0:42:44", "remaining_time": "0:50:19", "throughput": 10131.74, "total_tokens": 25982336}
{"current_steps": 27065, "total_steps": 58920, "loss": 0.0245, "lr": 1.3112248605231155e-06, "epoch": 2.2967583163611676, "percentage": 45.94, "elapsed_time": "0:42:44", "remaining_time": "0:50:18", "throughput": 10132.49, "total_tokens": 25988608}
{"current_steps": 27070, "total_steps": 58920, "loss": 0.0189, "lr": 1.310943338090308e-06, "epoch": 2.297182620502376, "percentage": 45.94, "elapsed_time": "0:42:45", "remaining_time": "0:50:18", "throughput": 10132.73, "total_tokens": 25993088}
{"current_steps": 27075, "total_steps": 58920, "loss": 0.0212, "lr": 1.3106617883733453e-06, "epoch": 2.2976069246435844, "percentage": 45.95, "elapsed_time": "0:42:45", "remaining_time": "0:50:17", "throughput": 10133.09, "total_tokens": 25997952}
{"current_steps": 27080, "total_steps": 58920, "loss": 0.0001, "lr": 1.3103802113969322e-06, "epoch": 2.298031228784793, "percentage": 45.96, "elapsed_time": "0:42:46", "remaining_time": "0:50:17", "throughput": 10133.52, "total_tokens": 26003072}
{"current_steps": 27085, "total_steps": 58920, "loss": 0.028, "lr": 1.310098607185776e-06, "epoch": 2.2984555329260012, "percentage": 45.97, "elapsed_time": "0:42:46", "remaining_time": "0:50:16", "throughput": 10133.79, "total_tokens": 26007680}
{"current_steps": 27090, "total_steps": 58920, "loss": 0.0003, "lr": 1.309816975764587e-06, "epoch": 2.2988798370672097, "percentage": 45.98, "elapsed_time": "0:42:46", "remaining_time": "0:50:15", "throughput": 10134.08, "total_tokens": 26012288}
{"current_steps": 27095, "total_steps": 58920, "loss": 0.0729, "lr": 1.3095353171580765e-06, "epoch": 2.299304141208418, "percentage": 45.99, "elapsed_time": "0:42:47", "remaining_time": "0:50:15", "throughput": 10134.58, "total_tokens": 26017600}
{"current_steps": 27100, "total_steps": 58920, "loss": 0.0017, "lr": 1.3092536313909599e-06, "epoch": 2.2997284453496265, "percentage": 45.99, "elapsed_time": "0:42:47", "remaining_time": "0:50:14", "throughput": 10135.11, "total_tokens": 26023040}
{"current_steps": 27105, "total_steps": 58920, "loss": 0.0046, "lr": 1.3089719184879533e-06, "epoch": 2.300152749490835, "percentage": 46.0, "elapsed_time": "0:42:47", "remaining_time": "0:50:14", "throughput": 10135.32, "total_tokens": 26027392}
{"current_steps": 27110, "total_steps": 58920, "loss": 0.0365, "lr": 1.3086901784737765e-06, "epoch": 2.3005770536320433, "percentage": 46.01, "elapsed_time": "0:42:48", "remaining_time": "0:50:13", "throughput": 10135.72, "total_tokens": 26032384}
{"current_steps": 27115, "total_steps": 58920, "loss": 0.0001, "lr": 1.3084084113731512e-06, "epoch": 2.3010013577732518, "percentage": 46.02, "elapsed_time": "0:42:48", "remaining_time": "0:50:13", "throughput": 10135.96, "total_tokens": 26036800}
{"current_steps": 27120, "total_steps": 58920, "loss": 0.0001, "lr": 1.3081266172108016e-06, "epoch": 2.30142566191446, "percentage": 46.03, "elapsed_time": "0:42:49", "remaining_time": "0:50:12", "throughput": 10136.5, "total_tokens": 26042240}
{"current_steps": 27125, "total_steps": 58920, "loss": 0.0258, "lr": 1.3078447960114537e-06, "epoch": 2.3018499660556686, "percentage": 46.04, "elapsed_time": "0:42:49", "remaining_time": "0:50:11", "throughput": 10136.8, "total_tokens": 26046848}
{"current_steps": 27130, "total_steps": 58920, "loss": 0.0325, "lr": 1.307562947799836e-06, "epoch": 2.302274270196877, "percentage": 46.05, "elapsed_time": "0:42:49", "remaining_time": "0:50:11", "throughput": 10137.2, "total_tokens": 26051776}
{"current_steps": 27135, "total_steps": 58920, "loss": 0.0304, "lr": 1.3072810726006803e-06, "epoch": 2.3026985743380854, "percentage": 46.05, "elapsed_time": "0:42:50", "remaining_time": "0:50:10", "throughput": 10137.57, "total_tokens": 26056640}
{"current_steps": 27140, "total_steps": 58920, "loss": 0.0401, "lr": 1.3069991704387198e-06, "epoch": 2.303122878479294, "percentage": 46.06, "elapsed_time": "0:42:50", "remaining_time": "0:50:10", "throughput": 10137.85, "total_tokens": 26061184}
{"current_steps": 27145, "total_steps": 58920, "loss": 0.0044, "lr": 1.3067172413386907e-06, "epoch": 2.3035471826205023, "percentage": 46.07, "elapsed_time": "0:42:51", "remaining_time": "0:50:09", "throughput": 10138.35, "total_tokens": 26066432}
{"current_steps": 27150, "total_steps": 58920, "loss": 0.0001, "lr": 1.3064352853253308e-06, "epoch": 2.3039714867617107, "percentage": 46.08, "elapsed_time": "0:42:51", "remaining_time": "0:50:09", "throughput": 10138.61, "total_tokens": 26070912}
{"current_steps": 27155, "total_steps": 58920, "loss": 0.092, "lr": 1.3061533024233815e-06, "epoch": 2.304395790902919, "percentage": 46.09, "elapsed_time": "0:42:51", "remaining_time": "0:50:08", "throughput": 10138.83, "total_tokens": 26075264}
{"current_steps": 27160, "total_steps": 58920, "loss": 0.0003, "lr": 1.305871292657585e-06, "epoch": 2.3048200950441275, "percentage": 46.1, "elapsed_time": "0:42:52", "remaining_time": "0:50:07", "throughput": 10139.12, "total_tokens": 26079872}
{"current_steps": 27165, "total_steps": 58920, "loss": 0.0001, "lr": 1.305589256052687e-06, "epoch": 2.305244399185336, "percentage": 46.1, "elapsed_time": "0:42:52", "remaining_time": "0:50:07", "throughput": 10139.54, "total_tokens": 26084864}
{"current_steps": 27170, "total_steps": 58920, "loss": 0.0012, "lr": 1.305307192633435e-06, "epoch": 2.3056687033265444, "percentage": 46.11, "elapsed_time": "0:42:52", "remaining_time": "0:50:06", "throughput": 10139.9, "total_tokens": 26089664}
{"current_steps": 27175, "total_steps": 58920, "loss": 0.0158, "lr": 1.305025102424579e-06, "epoch": 2.306093007467753, "percentage": 46.12, "elapsed_time": "0:42:53", "remaining_time": "0:50:06", "throughput": 10140.26, "total_tokens": 26094464}
{"current_steps": 27180, "total_steps": 58920, "loss": 0.0001, "lr": 1.3047429854508716e-06, "epoch": 2.3065173116089612, "percentage": 46.13, "elapsed_time": "0:42:53", "remaining_time": "0:50:05", "throughput": 10140.63, "total_tokens": 26099264}
{"current_steps": 27185, "total_steps": 58920, "loss": 0.0001, "lr": 1.3044608417370676e-06, "epoch": 2.3069416157501696, "percentage": 46.14, "elapsed_time": "0:42:54", "remaining_time": "0:50:04", "throughput": 10140.89, "total_tokens": 26103808}
{"current_steps": 27190, "total_steps": 58920, "loss": 0.0, "lr": 1.3041786713079242e-06, "epoch": 2.307365919891378, "percentage": 46.15, "elapsed_time": "0:42:54", "remaining_time": "0:50:04", "throughput": 10141.34, "total_tokens": 26108928}
{"current_steps": 27195, "total_steps": 58920, "loss": 0.0002, "lr": 1.3038964741882004e-06, "epoch": 2.3077902240325865, "percentage": 46.16, "elapsed_time": "0:42:54", "remaining_time": "0:50:03", "throughput": 10141.82, "total_tokens": 26114112}
{"current_steps": 27200, "total_steps": 58920, "loss": 0.0001, "lr": 1.303614250402658e-06, "epoch": 2.308214528173795, "percentage": 46.16, "elapsed_time": "0:42:55", "remaining_time": "0:50:03", "throughput": 10142.2, "total_tokens": 26118976}
{"current_steps": 27205, "total_steps": 58920, "loss": 0.0168, "lr": 1.3033319999760617e-06, "epoch": 2.3086388323150033, "percentage": 46.17, "elapsed_time": "0:42:55", "remaining_time": "0:50:02", "throughput": 10142.56, "total_tokens": 26123776}
{"current_steps": 27210, "total_steps": 58920, "loss": 0.0, "lr": 1.3030497229331775e-06, "epoch": 2.3090631364562118, "percentage": 46.18, "elapsed_time": "0:42:56", "remaining_time": "0:50:02", "throughput": 10142.84, "total_tokens": 26128384}
{"current_steps": 27215, "total_steps": 58920, "loss": 0.0001, "lr": 1.302767419298774e-06, "epoch": 2.30948744059742, "percentage": 46.19, "elapsed_time": "0:42:56", "remaining_time": "0:50:01", "throughput": 10143.07, "total_tokens": 26132736}
{"current_steps": 27220, "total_steps": 58920, "loss": 0.0001, "lr": 1.302485089097623e-06, "epoch": 2.3099117447386286, "percentage": 46.2, "elapsed_time": "0:42:56", "remaining_time": "0:50:00", "throughput": 10143.46, "total_tokens": 26137600}
{"current_steps": 27225, "total_steps": 58920, "loss": 0.0002, "lr": 1.3022027323544972e-06, "epoch": 2.310336048879837, "percentage": 46.21, "elapsed_time": "0:42:57", "remaining_time": "0:50:00", "throughput": 10143.86, "total_tokens": 26142528}
{"current_steps": 27230, "total_steps": 58920, "loss": 0.0001, "lr": 1.301920349094173e-06, "epoch": 2.3107603530210454, "percentage": 46.22, "elapsed_time": "0:42:57", "remaining_time": "0:49:59", "throughput": 10144.19, "total_tokens": 26147200}
{"current_steps": 27235, "total_steps": 58920, "loss": 0.0003, "lr": 1.3016379393414278e-06, "epoch": 2.311184657162254, "percentage": 46.22, "elapsed_time": "0:42:57", "remaining_time": "0:49:59", "throughput": 10144.44, "total_tokens": 26151616}
{"current_steps": 27240, "total_steps": 58920, "loss": 0.0301, "lr": 1.301355503121043e-06, "epoch": 2.3116089613034623, "percentage": 46.23, "elapsed_time": "0:42:58", "remaining_time": "0:49:58", "throughput": 10144.68, "total_tokens": 26156032}
{"current_steps": 27245, "total_steps": 58920, "loss": 0.0475, "lr": 1.3010730404578007e-06, "epoch": 2.3120332654446707, "percentage": 46.24, "elapsed_time": "0:42:58", "remaining_time": "0:49:57", "throughput": 10145.3, "total_tokens": 26161664}
{"current_steps": 27250, "total_steps": 58920, "loss": 0.048, "lr": 1.300790551376486e-06, "epoch": 2.312457569585879, "percentage": 46.25, "elapsed_time": "0:42:59", "remaining_time": "0:49:57", "throughput": 10145.73, "total_tokens": 26166784}
{"current_steps": 27255, "total_steps": 58920, "loss": 0.0087, "lr": 1.3005080359018863e-06, "epoch": 2.3128818737270875, "percentage": 46.26, "elapsed_time": "0:42:59", "remaining_time": "0:49:56", "throughput": 10146.26, "total_tokens": 26172096}
{"current_steps": 27260, "total_steps": 58920, "loss": 0.03, "lr": 1.3002254940587917e-06, "epoch": 2.313306177868296, "percentage": 46.27, "elapsed_time": "0:42:59", "remaining_time": "0:49:56", "throughput": 10146.75, "total_tokens": 26177408}
{"current_steps": 27265, "total_steps": 58920, "loss": 0.0001, "lr": 1.2999429258719937e-06, "epoch": 2.3137304820095044, "percentage": 46.27, "elapsed_time": "0:43:00", "remaining_time": "0:49:55", "throughput": 10147.08, "total_tokens": 26182080}
{"current_steps": 27270, "total_steps": 58920, "loss": 0.0002, "lr": 1.2996603313662871e-06, "epoch": 2.314154786150713, "percentage": 46.28, "elapsed_time": "0:43:00", "remaining_time": "0:49:55", "throughput": 10147.43, "total_tokens": 26186816}
{"current_steps": 27275, "total_steps": 58920, "loss": 0.0012, "lr": 1.2993777105664686e-06, "epoch": 2.314579090291921, "percentage": 46.29, "elapsed_time": "0:43:01", "remaining_time": "0:49:54", "throughput": 10147.73, "total_tokens": 26191488}
{"current_steps": 27280, "total_steps": 58920, "loss": 0.0003, "lr": 1.2990950634973364e-06, "epoch": 2.3150033944331296, "percentage": 46.3, "elapsed_time": "0:43:01", "remaining_time": "0:49:53", "throughput": 10148.08, "total_tokens": 26196288}
{"current_steps": 27285, "total_steps": 58920, "loss": 0.0001, "lr": 1.2988123901836924e-06, "epoch": 2.315427698574338, "percentage": 46.31, "elapsed_time": "0:43:01", "remaining_time": "0:49:53", "throughput": 10148.39, "total_tokens": 26200896}
{"current_steps": 27290, "total_steps": 58920, "loss": 0.0178, "lr": 1.2985296906503403e-06, "epoch": 2.3158520027155465, "percentage": 46.32, "elapsed_time": "0:43:02", "remaining_time": "0:49:52", "throughput": 10148.68, "total_tokens": 26205504}
{"current_steps": 27295, "total_steps": 58920, "loss": 0.0001, "lr": 1.2982469649220854e-06, "epoch": 2.316276306856755, "percentage": 46.33, "elapsed_time": "0:43:02", "remaining_time": "0:49:52", "throughput": 10149.01, "total_tokens": 26210240}
{"current_steps": 27300, "total_steps": 58920, "loss": 0.0264, "lr": 1.297964213023736e-06, "epoch": 2.3167006109979633, "percentage": 46.33, "elapsed_time": "0:43:02", "remaining_time": "0:49:51", "throughput": 10149.36, "total_tokens": 26214976}
{"current_steps": 27305, "total_steps": 58920, "loss": 0.0001, "lr": 1.2976814349801027e-06, "epoch": 2.3171249151391717, "percentage": 46.34, "elapsed_time": "0:43:03", "remaining_time": "0:49:51", "throughput": 10149.56, "total_tokens": 26219264}
{"current_steps": 27310, "total_steps": 58920, "loss": 0.0001, "lr": 1.2973986308159987e-06, "epoch": 2.31754921928038, "percentage": 46.35, "elapsed_time": "0:43:03", "remaining_time": "0:49:50", "throughput": 10149.84, "total_tokens": 26223872}
{"current_steps": 27315, "total_steps": 58920, "loss": 0.0001, "lr": 1.2971158005562385e-06, "epoch": 2.3179735234215886, "percentage": 46.36, "elapsed_time": "0:43:04", "remaining_time": "0:49:49", "throughput": 10150.24, "total_tokens": 26228800}
{"current_steps": 27320, "total_steps": 58920, "loss": 0.055, "lr": 1.296832944225639e-06, "epoch": 2.318397827562797, "percentage": 46.37, "elapsed_time": "0:43:04", "remaining_time": "0:49:49", "throughput": 10150.56, "total_tokens": 26233536}
{"current_steps": 27325, "total_steps": 58920, "loss": 0.0397, "lr": 1.2965500618490207e-06, "epoch": 2.3188221317040054, "percentage": 46.38, "elapsed_time": "0:43:04", "remaining_time": "0:49:48", "throughput": 10150.98, "total_tokens": 26238528}
{"current_steps": 27330, "total_steps": 58920, "loss": 0.0002, "lr": 1.2962671534512055e-06, "epoch": 2.319246435845214, "percentage": 46.38, "elapsed_time": "0:43:05", "remaining_time": "0:49:48", "throughput": 10151.44, "total_tokens": 26243712}
{"current_steps": 27335, "total_steps": 58920, "loss": 0.021, "lr": 1.2959842190570172e-06, "epoch": 2.3196707399864223, "percentage": 46.39, "elapsed_time": "0:43:05", "remaining_time": "0:49:47", "throughput": 10151.91, "total_tokens": 26248896}
{"current_steps": 27340, "total_steps": 58920, "loss": 0.0002, "lr": 1.2957012586912819e-06, "epoch": 2.3200950441276307, "percentage": 46.4, "elapsed_time": "0:43:06", "remaining_time": "0:49:47", "throughput": 10152.45, "total_tokens": 26254336}
{"current_steps": 27345, "total_steps": 58920, "loss": 0.0002, "lr": 1.295418272378829e-06, "epoch": 2.320519348268839, "percentage": 46.41, "elapsed_time": "0:43:06", "remaining_time": "0:49:46", "throughput": 10152.88, "total_tokens": 26259392}
{"current_steps": 27350, "total_steps": 58920, "loss": 0.0335, "lr": 1.295135260144489e-06, "epoch": 2.3209436524100475, "percentage": 46.42, "elapsed_time": "0:43:06", "remaining_time": "0:49:45", "throughput": 10153.13, "total_tokens": 26263872}
{"current_steps": 27355, "total_steps": 58920, "loss": 0.0363, "lr": 1.2948522220130958e-06, "epoch": 2.321367956551256, "percentage": 46.43, "elapsed_time": "0:43:07", "remaining_time": "0:49:45", "throughput": 10153.43, "total_tokens": 26268480}
{"current_steps": 27360, "total_steps": 58920, "loss": 0.0002, "lr": 1.2945691580094846e-06, "epoch": 2.3217922606924644, "percentage": 46.44, "elapsed_time": "0:43:07", "remaining_time": "0:49:44", "throughput": 10154.05, "total_tokens": 26274176}
{"current_steps": 27365, "total_steps": 58920, "loss": 0.0002, "lr": 1.2942860681584935e-06, "epoch": 2.322216564833673, "percentage": 46.44, "elapsed_time": "0:43:07", "remaining_time": "0:49:44", "throughput": 10154.31, "total_tokens": 26278656}
{"current_steps": 27370, "total_steps": 58920, "loss": 0.0001, "lr": 1.2940029524849625e-06, "epoch": 2.322640868974881, "percentage": 46.45, "elapsed_time": "0:43:08", "remaining_time": "0:49:43", "throughput": 10154.66, "total_tokens": 26283456}
{"current_steps": 27375, "total_steps": 58920, "loss": 0.0001, "lr": 1.2937198110137338e-06, "epoch": 2.3230651731160896, "percentage": 46.46, "elapsed_time": "0:43:08", "remaining_time": "0:49:43", "throughput": 10154.92, "total_tokens": 26287936}
{"current_steps": 27380, "total_steps": 58920, "loss": 0.0001, "lr": 1.2934366437696518e-06, "epoch": 2.323489477257298, "percentage": 46.47, "elapsed_time": "0:43:09", "remaining_time": "0:49:42", "throughput": 10155.34, "total_tokens": 26292928}
{"current_steps": 27385, "total_steps": 58920, "loss": 0.0001, "lr": 1.2931534507775638e-06, "epoch": 2.3239137813985065, "percentage": 46.48, "elapsed_time": "0:43:09", "remaining_time": "0:49:41", "throughput": 10155.55, "total_tokens": 26297280}
{"current_steps": 27390, "total_steps": 58920, "loss": 0.0001, "lr": 1.2928702320623193e-06, "epoch": 2.324338085539715, "percentage": 46.49, "elapsed_time": "0:43:09", "remaining_time": "0:49:41", "throughput": 10155.97, "total_tokens": 26302336}
{"current_steps": 27395, "total_steps": 58920, "loss": 0.0001, "lr": 1.2925869876487693e-06, "epoch": 2.3247623896809233, "percentage": 46.5, "elapsed_time": "0:43:10", "remaining_time": "0:49:40", "throughput": 10156.21, "total_tokens": 26306752}
{"current_steps": 27400, "total_steps": 58920, "loss": 0.0001, "lr": 1.2923037175617672e-06, "epoch": 2.3251866938221317, "percentage": 46.5, "elapsed_time": "0:43:10", "remaining_time": "0:49:40", "throughput": 10156.45, "total_tokens": 26311168}
{"current_steps": 27405, "total_steps": 58920, "loss": 0.0408, "lr": 1.2920204218261694e-06, "epoch": 2.32561099796334, "percentage": 46.51, "elapsed_time": "0:43:10", "remaining_time": "0:49:39", "throughput": 10156.75, "total_tokens": 26315840}
{"current_steps": 27410, "total_steps": 58920, "loss": 0.0001, "lr": 1.2917371004668341e-06, "epoch": 2.3260353021045486, "percentage": 46.52, "elapsed_time": "0:43:11", "remaining_time": "0:49:38", "throughput": 10157.1, "total_tokens": 26320576}
{"current_steps": 27415, "total_steps": 58920, "loss": 0.0001, "lr": 1.2914537535086214e-06, "epoch": 2.326459606245757, "percentage": 46.53, "elapsed_time": "0:43:11", "remaining_time": "0:49:38", "throughput": 10157.41, "total_tokens": 26325248}
{"current_steps": 27420, "total_steps": 58920, "loss": 0.0001, "lr": 1.291170380976394e-06, "epoch": 2.3268839103869654, "percentage": 46.54, "elapsed_time": "0:43:12", "remaining_time": "0:49:37", "throughput": 10157.64, "total_tokens": 26329664}
{"current_steps": 27425, "total_steps": 58920, "loss": 0.011, "lr": 1.2908869828950174e-06, "epoch": 2.327308214528174, "percentage": 46.55, "elapsed_time": "0:43:12", "remaining_time": "0:49:37", "throughput": 10157.91, "total_tokens": 26334208}
{"current_steps": 27430, "total_steps": 58920, "loss": 0.0072, "lr": 1.2906035592893578e-06, "epoch": 2.3277325186693822, "percentage": 46.55, "elapsed_time": "0:43:12", "remaining_time": "0:49:36", "throughput": 10158.04, "total_tokens": 26338304}
{"current_steps": 27435, "total_steps": 58920, "loss": 0.0185, "lr": 1.2903201101842854e-06, "epoch": 2.3281568228105907, "percentage": 46.56, "elapsed_time": "0:43:13", "remaining_time": "0:49:36", "throughput": 10158.51, "total_tokens": 26343552}
{"current_steps": 27440, "total_steps": 58920, "loss": 0.0278, "lr": 1.2900366356046711e-06, "epoch": 2.328581126951799, "percentage": 46.57, "elapsed_time": "0:43:13", "remaining_time": "0:49:35", "throughput": 10158.83, "total_tokens": 26348288}
{"current_steps": 27445, "total_steps": 58920, "loss": 0.0633, "lr": 1.2897531355753895e-06, "epoch": 2.3290054310930075, "percentage": 46.58, "elapsed_time": "0:43:14", "remaining_time": "0:49:34", "throughput": 10159.15, "total_tokens": 26352960}
{"current_steps": 27450, "total_steps": 58920, "loss": 0.0536, "lr": 1.2894696101213163e-06, "epoch": 2.329429735234216, "percentage": 46.59, "elapsed_time": "0:43:14", "remaining_time": "0:49:34", "throughput": 10159.42, "total_tokens": 26357504}
{"current_steps": 27455, "total_steps": 58920, "loss": 0.0002, "lr": 1.2891860592673302e-06, "epoch": 2.3298540393754243, "percentage": 46.6, "elapsed_time": "0:43:14", "remaining_time": "0:49:33", "throughput": 10159.66, "total_tokens": 26361920}
{"current_steps": 27460, "total_steps": 58920, "loss": 0.0018, "lr": 1.2889024830383114e-06, "epoch": 2.3302783435166328, "percentage": 46.61, "elapsed_time": "0:43:15", "remaining_time": "0:49:33", "throughput": 10160.22, "total_tokens": 26367424}
{"current_steps": 27465, "total_steps": 58920, "loss": 0.0003, "lr": 1.2886188814591427e-06, "epoch": 2.330702647657841, "percentage": 46.61, "elapsed_time": "0:43:15", "remaining_time": "0:49:32", "throughput": 10160.56, "total_tokens": 26372224}
{"current_steps": 27470, "total_steps": 58920, "loss": 0.0002, "lr": 1.288335254554709e-06, "epoch": 2.3311269517990496, "percentage": 46.62, "elapsed_time": "0:43:15", "remaining_time": "0:49:32", "throughput": 10160.91, "total_tokens": 26377024}
{"current_steps": 27475, "total_steps": 58920, "loss": 0.0027, "lr": 1.2880516023498979e-06, "epoch": 2.331551255940258, "percentage": 46.63, "elapsed_time": "0:43:16", "remaining_time": "0:49:31", "throughput": 10161.3, "total_tokens": 26382016}
{"current_steps": 27480, "total_steps": 58920, "loss": 0.0007, "lr": 1.2877679248695986e-06, "epoch": 2.3319755600814664, "percentage": 46.64, "elapsed_time": "0:43:16", "remaining_time": "0:49:30", "throughput": 10161.55, "total_tokens": 26386432}
{"current_steps": 27485, "total_steps": 58920, "loss": 0.0001, "lr": 1.2874842221387032e-06, "epoch": 2.332399864222675, "percentage": 46.65, "elapsed_time": "0:43:17", "remaining_time": "0:49:30", "throughput": 10161.94, "total_tokens": 26391360}
{"current_steps": 27490, "total_steps": 58920, "loss": 0.0002, "lr": 1.2872004941821053e-06, "epoch": 2.3328241683638833, "percentage": 46.66, "elapsed_time": "0:43:17", "remaining_time": "0:49:29", "throughput": 10162.25, "total_tokens": 26396032}
{"current_steps": 27495, "total_steps": 58920, "loss": 0.0004, "lr": 1.2869167410247007e-06, "epoch": 2.3332484725050917, "percentage": 46.66, "elapsed_time": "0:43:17", "remaining_time": "0:49:29", "throughput": 10162.59, "total_tokens": 26400832}
{"current_steps": 27500, "total_steps": 58920, "loss": 0.0086, "lr": 1.286632962691388e-06, "epoch": 2.3336727766463, "percentage": 46.67, "elapsed_time": "0:43:18", "remaining_time": "0:49:28", "throughput": 10162.86, "total_tokens": 26405376}
{"current_steps": 27505, "total_steps": 58920, "loss": 0.0144, "lr": 1.2863491592070678e-06, "epoch": 2.3340970807875085, "percentage": 46.68, "elapsed_time": "0:43:18", "remaining_time": "0:49:28", "throughput": 10163.19, "total_tokens": 26410112}
{"current_steps": 27510, "total_steps": 58920, "loss": 0.0001, "lr": 1.2860653305966427e-06, "epoch": 2.334521384928717, "percentage": 46.69, "elapsed_time": "0:43:18", "remaining_time": "0:49:27", "throughput": 10163.57, "total_tokens": 26415040}
{"current_steps": 27515, "total_steps": 58920, "loss": 0.0031, "lr": 1.2857814768850177e-06, "epoch": 2.3349456890699254, "percentage": 46.7, "elapsed_time": "0:43:19", "remaining_time": "0:49:26", "throughput": 10163.92, "total_tokens": 26419840}
{"current_steps": 27520, "total_steps": 58920, "loss": 0.0459, "lr": 1.2854975980970998e-06, "epoch": 2.335369993211134, "percentage": 46.71, "elapsed_time": "0:43:19", "remaining_time": "0:49:26", "throughput": 10164.22, "total_tokens": 26424512}
{"current_steps": 27525, "total_steps": 58920, "loss": 0.023, "lr": 1.2852136942577986e-06, "epoch": 2.3357942973523422, "percentage": 46.72, "elapsed_time": "0:43:20", "remaining_time": "0:49:25", "throughput": 10164.87, "total_tokens": 26430336}
{"current_steps": 27530, "total_steps": 58920, "loss": 0.0273, "lr": 1.2849297653920255e-06, "epoch": 2.3362186014935507, "percentage": 46.72, "elapsed_time": "0:43:20", "remaining_time": "0:49:25", "throughput": 10165.29, "total_tokens": 26435392}
{"current_steps": 27535, "total_steps": 58920, "loss": 0.0058, "lr": 1.2846458115246941e-06, "epoch": 2.336642905634759, "percentage": 46.73, "elapsed_time": "0:43:20", "remaining_time": "0:49:24", "throughput": 10165.5, "total_tokens": 26439808}
{"current_steps": 27540, "total_steps": 58920, "loss": 0.005, "lr": 1.2843618326807203e-06, "epoch": 2.3370672097759675, "percentage": 46.74, "elapsed_time": "0:43:21", "remaining_time": "0:49:24", "throughput": 10165.74, "total_tokens": 26444224}
{"current_steps": 27545, "total_steps": 58920, "loss": 0.0003, "lr": 1.2840778288850227e-06, "epoch": 2.337491513917176, "percentage": 46.75, "elapsed_time": "0:43:21", "remaining_time": "0:49:23", "throughput": 10166.04, "total_tokens": 26448896}
{"current_steps": 27550, "total_steps": 58920, "loss": 0.0001, "lr": 1.2837938001625213e-06, "epoch": 2.3379158180583843, "percentage": 46.76, "elapsed_time": "0:43:22", "remaining_time": "0:49:22", "throughput": 10166.27, "total_tokens": 26453312}
{"current_steps": 27555, "total_steps": 58920, "loss": 0.0238, "lr": 1.2835097465381383e-06, "epoch": 2.3383401221995928, "percentage": 46.77, "elapsed_time": "0:43:22", "remaining_time": "0:49:22", "throughput": 10166.45, "total_tokens": 26457536}
{"current_steps": 27560, "total_steps": 58920, "loss": 0.0189, "lr": 1.2832256680367987e-06, "epoch": 2.338764426340801, "percentage": 46.78, "elapsed_time": "0:43:22", "remaining_time": "0:49:21", "throughput": 10166.82, "total_tokens": 26462400}
{"current_steps": 27565, "total_steps": 58920, "loss": 0.0005, "lr": 1.2829415646834294e-06, "epoch": 2.3391887304820096, "percentage": 46.78, "elapsed_time": "0:43:23", "remaining_time": "0:49:21", "throughput": 10167.12, "total_tokens": 26467008}
{"current_steps": 27570, "total_steps": 58920, "loss": 0.0001, "lr": 1.2826574365029593e-06, "epoch": 2.339613034623218, "percentage": 46.79, "elapsed_time": "0:43:23", "remaining_time": "0:49:20", "throughput": 10167.42, "total_tokens": 26471616}
{"current_steps": 27575, "total_steps": 58920, "loss": 0.0, "lr": 1.2823732835203196e-06, "epoch": 2.3400373387644264, "percentage": 46.8, "elapsed_time": "0:43:23", "remaining_time": "0:49:19", "throughput": 10167.8, "total_tokens": 26476544}
{"current_steps": 27580, "total_steps": 58920, "loss": 0.0433, "lr": 1.282089105760444e-06, "epoch": 2.340461642905635, "percentage": 46.81, "elapsed_time": "0:43:24", "remaining_time": "0:49:19", "throughput": 10168.14, "total_tokens": 26481280}
{"current_steps": 27585, "total_steps": 58920, "loss": 0.0373, "lr": 1.2818049032482677e-06, "epoch": 2.3408859470468433, "percentage": 46.82, "elapsed_time": "0:43:24", "remaining_time": "0:49:18", "throughput": 10168.46, "total_tokens": 26486016}
{"current_steps": 27590, "total_steps": 58920, "loss": 0.0, "lr": 1.2815206760087286e-06, "epoch": 2.3413102511880517, "percentage": 46.83, "elapsed_time": "0:43:25", "remaining_time": "0:49:18", "throughput": 10168.68, "total_tokens": 26490368}
{"current_steps": 27595, "total_steps": 58920, "loss": 0.0, "lr": 1.2812364240667666e-06, "epoch": 2.34173455532926, "percentage": 46.83, "elapsed_time": "0:43:25", "remaining_time": "0:49:17", "throughput": 10168.96, "total_tokens": 26494912}
{"current_steps": 27600, "total_steps": 58920, "loss": 0.0294, "lr": 1.2809521474473237e-06, "epoch": 2.3421588594704685, "percentage": 46.84, "elapsed_time": "0:43:25", "remaining_time": "0:49:17", "throughput": 10169.26, "total_tokens": 26499520}
{"current_steps": 27605, "total_steps": 58920, "loss": 0.0383, "lr": 1.2806678461753444e-06, "epoch": 2.342583163611677, "percentage": 46.85, "elapsed_time": "0:43:26", "remaining_time": "0:49:16", "throughput": 10169.45, "total_tokens": 26503808}
{"current_steps": 27610, "total_steps": 58920, "loss": 0.0001, "lr": 1.2803835202757749e-06, "epoch": 2.3430074677528854, "percentage": 46.86, "elapsed_time": "0:43:26", "remaining_time": "0:49:15", "throughput": 10169.76, "total_tokens": 26508480}
{"current_steps": 27615, "total_steps": 58920, "loss": 0.0001, "lr": 1.280099169773564e-06, "epoch": 2.343431771894094, "percentage": 46.87, "elapsed_time": "0:43:26", "remaining_time": "0:49:15", "throughput": 10170.23, "total_tokens": 26513664}
{"current_steps": 27620, "total_steps": 58920, "loss": 0.0001, "lr": 1.279814794693662e-06, "epoch": 2.343856076035302, "percentage": 46.88, "elapsed_time": "0:43:27", "remaining_time": "0:49:14", "throughput": 10170.57, "total_tokens": 26518464}
{"current_steps": 27625, "total_steps": 58920, "loss": 0.0001, "lr": 1.2795303950610222e-06, "epoch": 2.3442803801765106, "percentage": 46.89, "elapsed_time": "0:43:27", "remaining_time": "0:49:14", "throughput": 10170.83, "total_tokens": 26522944}
{"current_steps": 27630, "total_steps": 58920, "loss": 0.0001, "lr": 1.2792459709005992e-06, "epoch": 2.344704684317719, "percentage": 46.89, "elapsed_time": "0:43:28", "remaining_time": "0:49:13", "throughput": 10171.11, "total_tokens": 26527488}
{"current_steps": 27635, "total_steps": 58920, "loss": 0.0001, "lr": 1.2789615222373506e-06, "epoch": 2.3451289884589275, "percentage": 46.9, "elapsed_time": "0:43:28", "remaining_time": "0:49:13", "throughput": 10171.32, "total_tokens": 26531904}
{"current_steps": 27640, "total_steps": 58920, "loss": 0.0417, "lr": 1.2786770490962356e-06, "epoch": 2.345553292600136, "percentage": 46.91, "elapsed_time": "0:43:28", "remaining_time": "0:49:12", "throughput": 10171.77, "total_tokens": 26537088}
{"current_steps": 27645, "total_steps": 58920, "loss": 0.0001, "lr": 1.2783925515022159e-06, "epoch": 2.3459775967413443, "percentage": 46.92, "elapsed_time": "0:43:29", "remaining_time": "0:49:11", "throughput": 10172.02, "total_tokens": 26541568}
{"current_steps": 27650, "total_steps": 58920, "loss": 0.0078, "lr": 1.2781080294802547e-06, "epoch": 2.3464019008825527, "percentage": 46.93, "elapsed_time": "0:43:29", "remaining_time": "0:49:11", "throughput": 10172.38, "total_tokens": 26546432}
{"current_steps": 27655, "total_steps": 58920, "loss": 0.0348, "lr": 1.277823483055318e-06, "epoch": 2.346826205023761, "percentage": 46.94, "elapsed_time": "0:43:30", "remaining_time": "0:49:10", "throughput": 10172.63, "total_tokens": 26550912}
{"current_steps": 27660, "total_steps": 58920, "loss": 0.0453, "lr": 1.2775389122523739e-06, "epoch": 2.3472505091649696, "percentage": 46.95, "elapsed_time": "0:43:30", "remaining_time": "0:49:10", "throughput": 10172.77, "total_tokens": 26555008}
{"current_steps": 27665, "total_steps": 58920, "loss": 0.0286, "lr": 1.2772543170963924e-06, "epoch": 2.347674813306178, "percentage": 46.95, "elapsed_time": "0:43:30", "remaining_time": "0:49:09", "throughput": 10173.02, "total_tokens": 26559488}
{"current_steps": 27670, "total_steps": 58920, "loss": 0.0002, "lr": 1.2769696976123454e-06, "epoch": 2.3480991174473864, "percentage": 46.96, "elapsed_time": "0:43:31", "remaining_time": "0:49:08", "throughput": 10173.25, "total_tokens": 26563904}
{"current_steps": 27675, "total_steps": 58920, "loss": 0.0001, "lr": 1.2766850538252073e-06, "epoch": 2.348523421588595, "percentage": 46.97, "elapsed_time": "0:43:31", "remaining_time": "0:49:08", "throughput": 10173.57, "total_tokens": 26568576}
{"current_steps": 27680, "total_steps": 58920, "loss": 0.0001, "lr": 1.276400385759955e-06, "epoch": 2.3489477257298033, "percentage": 46.98, "elapsed_time": "0:43:31", "remaining_time": "0:49:07", "throughput": 10173.85, "total_tokens": 26573184}
{"current_steps": 27685, "total_steps": 58920, "loss": 0.0003, "lr": 1.2761156934415668e-06, "epoch": 2.3493720298710117, "percentage": 46.99, "elapsed_time": "0:43:32", "remaining_time": "0:49:07", "throughput": 10174.21, "total_tokens": 26577984}
{"current_steps": 27690, "total_steps": 58920, "loss": 0.0001, "lr": 1.2758309768950231e-06, "epoch": 2.34979633401222, "percentage": 47.0, "elapsed_time": "0:43:32", "remaining_time": "0:49:06", "throughput": 10174.42, "total_tokens": 26582336}
{"current_steps": 27695, "total_steps": 58920, "loss": 0.0444, "lr": 1.2755462361453071e-06, "epoch": 2.3502206381534285, "percentage": 47.0, "elapsed_time": "0:43:33", "remaining_time": "0:49:06", "throughput": 10174.88, "total_tokens": 26587520}
{"current_steps": 27700, "total_steps": 58920, "loss": 0.0001, "lr": 1.275261471217404e-06, "epoch": 2.350644942294637, "percentage": 47.01, "elapsed_time": "0:43:33", "remaining_time": "0:49:05", "throughput": 10175.14, "total_tokens": 26592064}
{"current_steps": 27705, "total_steps": 58920, "loss": 0.0001, "lr": 1.2749766821363007e-06, "epoch": 2.3510692464358454, "percentage": 47.02, "elapsed_time": "0:43:33", "remaining_time": "0:49:04", "throughput": 10175.62, "total_tokens": 26597312}
{"current_steps": 27710, "total_steps": 58920, "loss": 0.0001, "lr": 1.274691868926986e-06, "epoch": 2.351493550577054, "percentage": 47.03, "elapsed_time": "0:43:34", "remaining_time": "0:49:04", "throughput": 10175.92, "total_tokens": 26601984}
{"current_steps": 27715, "total_steps": 58920, "loss": 0.0317, "lr": 1.2744070316144515e-06, "epoch": 2.351917854718262, "percentage": 47.04, "elapsed_time": "0:43:34", "remaining_time": "0:49:03", "throughput": 10176.3, "total_tokens": 26606848}
{"current_steps": 27720, "total_steps": 58920, "loss": 0.0, "lr": 1.2741221702236908e-06, "epoch": 2.3523421588594706, "percentage": 47.05, "elapsed_time": "0:43:34", "remaining_time": "0:49:03", "throughput": 10176.57, "total_tokens": 26611392}
{"current_steps": 27725, "total_steps": 58920, "loss": 0.0, "lr": 1.2738372847796997e-06, "epoch": 2.352766463000679, "percentage": 47.06, "elapsed_time": "0:43:35", "remaining_time": "0:49:02", "throughput": 10176.98, "total_tokens": 26616384}
{"current_steps": 27730, "total_steps": 58920, "loss": 0.0003, "lr": 1.2735523753074752e-06, "epoch": 2.3531907671418875, "percentage": 47.06, "elapsed_time": "0:43:35", "remaining_time": "0:49:02", "throughput": 10177.32, "total_tokens": 26621184}
{"current_steps": 27735, "total_steps": 58920, "loss": 0.0, "lr": 1.2732674418320177e-06, "epoch": 2.353615071283096, "percentage": 47.07, "elapsed_time": "0:43:36", "remaining_time": "0:49:01", "throughput": 10177.73, "total_tokens": 26626176}
{"current_steps": 27740, "total_steps": 58920, "loss": 0.0086, "lr": 1.2729824843783287e-06, "epoch": 2.3540393754243043, "percentage": 47.08, "elapsed_time": "0:43:36", "remaining_time": "0:49:00", "throughput": 10178.13, "total_tokens": 26631232}
{"current_steps": 27745, "total_steps": 58920, "loss": 0.0001, "lr": 1.2726975029714123e-06, "epoch": 2.3544636795655127, "percentage": 47.09, "elapsed_time": "0:43:36", "remaining_time": "0:49:00", "throughput": 10178.54, "total_tokens": 26636288}
{"current_steps": 27750, "total_steps": 58920, "loss": 0.0, "lr": 1.2724124976362744e-06, "epoch": 2.354887983706721, "percentage": 47.1, "elapsed_time": "0:43:37", "remaining_time": "0:48:59", "throughput": 10178.89, "total_tokens": 26641152}
{"current_steps": 27755, "total_steps": 58920, "loss": 0.0, "lr": 1.2721274683979236e-06, "epoch": 2.3553122878479296, "percentage": 47.11, "elapsed_time": "0:43:37", "remaining_time": "0:48:59", "throughput": 10179.23, "total_tokens": 26645888}
{"current_steps": 27760, "total_steps": 58920, "loss": 0.0, "lr": 1.2718424152813698e-06, "epoch": 2.355736591989138, "percentage": 47.11, "elapsed_time": "0:43:38", "remaining_time": "0:48:58", "throughput": 10179.57, "total_tokens": 26650624}
{"current_steps": 27765, "total_steps": 58920, "loss": 0.0001, "lr": 1.2715573383116258e-06, "epoch": 2.3561608961303464, "percentage": 47.12, "elapsed_time": "0:43:38", "remaining_time": "0:48:58", "throughput": 10179.88, "total_tokens": 26655360}
{"current_steps": 27770, "total_steps": 58920, "loss": 0.0, "lr": 1.2712722375137056e-06, "epoch": 2.356585200271555, "percentage": 47.13, "elapsed_time": "0:43:38", "remaining_time": "0:48:57", "throughput": 10180.07, "total_tokens": 26659648}
{"current_steps": 27775, "total_steps": 58920, "loss": 0.0379, "lr": 1.270987112912626e-06, "epoch": 2.3570095044127632, "percentage": 47.14, "elapsed_time": "0:43:39", "remaining_time": "0:48:57", "throughput": 10180.71, "total_tokens": 26665472}
{"current_steps": 27780, "total_steps": 58920, "loss": 0.0001, "lr": 1.2707019645334053e-06, "epoch": 2.3574338085539717, "percentage": 47.15, "elapsed_time": "0:43:39", "remaining_time": "0:48:56", "throughput": 10180.89, "total_tokens": 26669696}
{"current_steps": 27785, "total_steps": 58920, "loss": 0.0238, "lr": 1.270416792401065e-06, "epoch": 2.35785811269518, "percentage": 47.16, "elapsed_time": "0:43:39", "remaining_time": "0:48:55", "throughput": 10181.38, "total_tokens": 26674944}
{"current_steps": 27790, "total_steps": 58920, "loss": 0.0, "lr": 1.2701315965406279e-06, "epoch": 2.3582824168363885, "percentage": 47.17, "elapsed_time": "0:43:40", "remaining_time": "0:48:55", "throughput": 10181.71, "total_tokens": 26679680}
{"current_steps": 27795, "total_steps": 58920, "loss": 0.0113, "lr": 1.269846376977118e-06, "epoch": 2.358706720977597, "percentage": 47.17, "elapsed_time": "0:43:40", "remaining_time": "0:48:54", "throughput": 10181.98, "total_tokens": 26684224}
{"current_steps": 27800, "total_steps": 58920, "loss": 0.0002, "lr": 1.2695611337355628e-06, "epoch": 2.3591310251188053, "percentage": 47.18, "elapsed_time": "0:43:41", "remaining_time": "0:48:54", "throughput": 10182.32, "total_tokens": 26689024}
{"current_steps": 27805, "total_steps": 58920, "loss": 0.0846, "lr": 1.2692758668409913e-06, "epoch": 2.3595553292600138, "percentage": 47.19, "elapsed_time": "0:43:41", "remaining_time": "0:48:53", "throughput": 10182.62, "total_tokens": 26693696}
{"current_steps": 27810, "total_steps": 58920, "loss": 0.0457, "lr": 1.2689905763184348e-06, "epoch": 2.359979633401222, "percentage": 47.2, "elapsed_time": "0:43:41", "remaining_time": "0:48:53", "throughput": 10183.17, "total_tokens": 26699200}
{"current_steps": 27815, "total_steps": 58920, "loss": 0.0543, "lr": 1.2687052621929264e-06, "epoch": 2.3604039375424306, "percentage": 47.21, "elapsed_time": "0:43:42", "remaining_time": "0:48:52", "throughput": 10183.69, "total_tokens": 26704576}
{"current_steps": 27820, "total_steps": 58920, "loss": 0.0001, "lr": 1.2684199244895015e-06, "epoch": 2.360828241683639, "percentage": 47.22, "elapsed_time": "0:43:42", "remaining_time": "0:48:51", "throughput": 10184.06, "total_tokens": 26709440}
{"current_steps": 27825, "total_steps": 58920, "loss": 0.0007, "lr": 1.2681345632331972e-06, "epoch": 2.361252545824847, "percentage": 47.23, "elapsed_time": "0:43:43", "remaining_time": "0:48:51", "throughput": 10184.41, "total_tokens": 26714240}
{"current_steps": 27830, "total_steps": 58920, "loss": 0.0244, "lr": 1.2678491784490533e-06, "epoch": 2.361676849966056, "percentage": 47.23, "elapsed_time": "0:43:43", "remaining_time": "0:48:50", "throughput": 10184.63, "total_tokens": 26718656}
{"current_steps": 27835, "total_steps": 58920, "loss": 0.0348, "lr": 1.267563770162111e-06, "epoch": 2.362101154107264, "percentage": 47.24, "elapsed_time": "0:43:43", "remaining_time": "0:48:50", "throughput": 10184.89, "total_tokens": 26723136}
{"current_steps": 27840, "total_steps": 58920, "loss": 0.0314, "lr": 1.2672783383974138e-06, "epoch": 2.3625254582484727, "percentage": 47.25, "elapsed_time": "0:43:44", "remaining_time": "0:48:49", "throughput": 10185.07, "total_tokens": 26727360}
{"current_steps": 27845, "total_steps": 58920, "loss": 0.0001, "lr": 1.2669928831800072e-06, "epoch": 2.3629497623896807, "percentage": 47.26, "elapsed_time": "0:43:44", "remaining_time": "0:48:49", "throughput": 10185.51, "total_tokens": 26732480}
{"current_steps": 27850, "total_steps": 58920, "loss": 0.0355, "lr": 1.2667074045349393e-06, "epoch": 2.3633740665308896, "percentage": 47.27, "elapsed_time": "0:43:44", "remaining_time": "0:48:48", "throughput": 10186.02, "total_tokens": 26737856}
{"current_steps": 27855, "total_steps": 58920, "loss": 0.0002, "lr": 1.2664219024872596e-06, "epoch": 2.3637983706720975, "percentage": 47.28, "elapsed_time": "0:43:45", "remaining_time": "0:48:47", "throughput": 10186.21, "total_tokens": 26742144}
{"current_steps": 27860, "total_steps": 58920, "loss": 0.0394, "lr": 1.26613637706202e-06, "epoch": 2.3642226748133064, "percentage": 47.28, "elapsed_time": "0:43:45", "remaining_time": "0:48:47", "throughput": 10186.48, "total_tokens": 26746752}
{"current_steps": 27865, "total_steps": 58920, "loss": 0.0003, "lr": 1.265850828284274e-06, "epoch": 2.3646469789545144, "percentage": 47.29, "elapsed_time": "0:43:46", "remaining_time": "0:48:46", "throughput": 10187.19, "total_tokens": 26752832}
{"current_steps": 27870, "total_steps": 58920, "loss": 0.0001, "lr": 1.2655652561790778e-06, "epoch": 2.3650712830957232, "percentage": 47.3, "elapsed_time": "0:43:46", "remaining_time": "0:48:46", "throughput": 10187.53, "total_tokens": 26757568}
{"current_steps": 27875, "total_steps": 58920, "loss": 0.0649, "lr": 1.2652796607714891e-06, "epoch": 2.365495587236931, "percentage": 47.31, "elapsed_time": "0:43:46", "remaining_time": "0:48:45", "throughput": 10187.96, "total_tokens": 26762688}
{"current_steps": 27880, "total_steps": 58920, "loss": 0.0588, "lr": 1.264994042086568e-06, "epoch": 2.36591989137814, "percentage": 47.32, "elapsed_time": "0:43:47", "remaining_time": "0:48:45", "throughput": 10188.26, "total_tokens": 26767360}
{"current_steps": 27885, "total_steps": 58920, "loss": 0.0361, "lr": 1.2647084001493765e-06, "epoch": 2.366344195519348, "percentage": 47.33, "elapsed_time": "0:43:47", "remaining_time": "0:48:44", "throughput": 10188.61, "total_tokens": 26772224}
{"current_steps": 27890, "total_steps": 58920, "loss": 0.0005, "lr": 1.2644227349849784e-06, "epoch": 2.366768499660557, "percentage": 47.34, "elapsed_time": "0:43:48", "remaining_time": "0:48:43", "throughput": 10188.84, "total_tokens": 26776576}
{"current_steps": 27895, "total_steps": 58920, "loss": 0.0001, "lr": 1.2641370466184402e-06, "epoch": 2.367192803801765, "percentage": 47.34, "elapsed_time": "0:43:48", "remaining_time": "0:48:43", "throughput": 10189.17, "total_tokens": 26781312}
{"current_steps": 27900, "total_steps": 58920, "loss": 0.0004, "lr": 1.2638513350748297e-06, "epoch": 2.3676171079429738, "percentage": 47.35, "elapsed_time": "0:43:48", "remaining_time": "0:48:42", "throughput": 10189.37, "total_tokens": 26785600}
{"current_steps": 27905, "total_steps": 58920, "loss": 0.0001, "lr": 1.263565600379217e-06, "epoch": 2.3680414120841817, "percentage": 47.36, "elapsed_time": "0:43:49", "remaining_time": "0:48:42", "throughput": 10189.69, "total_tokens": 26790336}
{"current_steps": 27910, "total_steps": 58920, "loss": 0.0198, "lr": 1.263279842556675e-06, "epoch": 2.3684657162253906, "percentage": 47.37, "elapsed_time": "0:43:49", "remaining_time": "0:48:41", "throughput": 10190.11, "total_tokens": 26795392}
{"current_steps": 27915, "total_steps": 58920, "loss": 0.0001, "lr": 1.2629940616322772e-06, "epoch": 2.3688900203665986, "percentage": 47.38, "elapsed_time": "0:43:49", "remaining_time": "0:48:41", "throughput": 10190.48, "total_tokens": 26800256}
{"current_steps": 27920, "total_steps": 58920, "loss": 0.0901, "lr": 1.2627082576310999e-06, "epoch": 2.3693143245078074, "percentage": 47.39, "elapsed_time": "0:43:50", "remaining_time": "0:48:40", "throughput": 10190.73, "total_tokens": 26804736}
{"current_steps": 27925, "total_steps": 58920, "loss": 0.0001, "lr": 1.2624224305782213e-06, "epoch": 2.3697386286490154, "percentage": 47.39, "elapsed_time": "0:43:50", "remaining_time": "0:48:39", "throughput": 10191.02, "total_tokens": 26809408}
{"current_steps": 27930, "total_steps": 58920, "loss": 0.0001, "lr": 1.262136580498722e-06, "epoch": 2.3701629327902243, "percentage": 47.4, "elapsed_time": "0:43:51", "remaining_time": "0:48:39", "throughput": 10191.21, "total_tokens": 26813696}
{"current_steps": 27935, "total_steps": 58920, "loss": 0.0213, "lr": 1.2618507074176842e-06, "epoch": 2.3705872369314323, "percentage": 47.41, "elapsed_time": "0:43:51", "remaining_time": "0:48:38", "throughput": 10191.82, "total_tokens": 26819456}
{"current_steps": 27940, "total_steps": 58920, "loss": 0.0132, "lr": 1.2615648113601926e-06, "epoch": 2.371011541072641, "percentage": 47.42, "elapsed_time": "0:43:51", "remaining_time": "0:48:38", "throughput": 10192.17, "total_tokens": 26824256}
{"current_steps": 27945, "total_steps": 58920, "loss": 0.0349, "lr": 1.261278892351333e-06, "epoch": 2.371435845213849, "percentage": 47.43, "elapsed_time": "0:43:52", "remaining_time": "0:48:37", "throughput": 10192.4, "total_tokens": 26828736}
{"current_steps": 27950, "total_steps": 58920, "loss": 0.0001, "lr": 1.2609929504161938e-06, "epoch": 2.3718601493550575, "percentage": 47.44, "elapsed_time": "0:43:52", "remaining_time": "0:48:37", "throughput": 10192.71, "total_tokens": 26833408}
{"current_steps": 27955, "total_steps": 58920, "loss": 0.0324, "lr": 1.2607069855798657e-06, "epoch": 2.372284453496266, "percentage": 47.45, "elapsed_time": "0:43:52", "remaining_time": "0:48:36", "throughput": 10192.88, "total_tokens": 26837632}
{"current_steps": 27960, "total_steps": 58920, "loss": 0.0136, "lr": 1.2604209978674408e-06, "epoch": 2.3727087576374744, "percentage": 47.45, "elapsed_time": "0:43:53", "remaining_time": "0:48:35", "throughput": 10193.08, "total_tokens": 26841920}
{"current_steps": 27965, "total_steps": 58920, "loss": 0.0186, "lr": 1.2601349873040134e-06, "epoch": 2.3731330617786828, "percentage": 47.46, "elapsed_time": "0:43:53", "remaining_time": "0:48:35", "throughput": 10193.54, "total_tokens": 26847104}
{"current_steps": 27970, "total_steps": 58920, "loss": 0.0346, "lr": 1.2598489539146804e-06, "epoch": 2.373557365919891, "percentage": 47.47, "elapsed_time": "0:43:54", "remaining_time": "0:48:34", "throughput": 10193.91, "total_tokens": 26851968}
{"current_steps": 27975, "total_steps": 58920, "loss": 0.0001, "lr": 1.2595628977245397e-06, "epoch": 2.3739816700610996, "percentage": 47.48, "elapsed_time": "0:43:54", "remaining_time": "0:48:34", "throughput": 10194.26, "total_tokens": 26856832}
{"current_steps": 27980, "total_steps": 58920, "loss": 0.0405, "lr": 1.2592768187586918e-06, "epoch": 2.374405974202308, "percentage": 47.49, "elapsed_time": "0:43:54", "remaining_time": "0:48:33", "throughput": 10194.8, "total_tokens": 26862336}
{"current_steps": 27985, "total_steps": 58920, "loss": 0.0007, "lr": 1.2589907170422392e-06, "epoch": 2.3748302783435165, "percentage": 47.5, "elapsed_time": "0:43:55", "remaining_time": "0:48:33", "throughput": 10195.06, "total_tokens": 26866880}
{"current_steps": 27990, "total_steps": 58920, "loss": 0.031, "lr": 1.2587045926002864e-06, "epoch": 2.375254582484725, "percentage": 47.51, "elapsed_time": "0:43:55", "remaining_time": "0:48:32", "throughput": 10195.32, "total_tokens": 26871424}
{"current_steps": 27995, "total_steps": 58920, "loss": 0.0004, "lr": 1.2584184454579397e-06, "epoch": 2.3756788866259333, "percentage": 47.51, "elapsed_time": "0:43:56", "remaining_time": "0:48:31", "throughput": 10195.64, "total_tokens": 26876160}
{"current_steps": 28000, "total_steps": 58920, "loss": 0.0001, "lr": 1.2581322756403073e-06, "epoch": 2.3761031907671417, "percentage": 47.52, "elapsed_time": "0:43:56", "remaining_time": "0:48:31", "throughput": 10196.06, "total_tokens": 26881216}
{"current_steps": 28005, "total_steps": 58920, "loss": 0.0005, "lr": 1.2578460831724996e-06, "epoch": 2.37652749490835, "percentage": 47.53, "elapsed_time": "0:43:56", "remaining_time": "0:48:30", "throughput": 10196.33, "total_tokens": 26885824}
{"current_steps": 28010, "total_steps": 58920, "loss": 0.0004, "lr": 1.257559868079629e-06, "epoch": 2.3769517990495586, "percentage": 47.54, "elapsed_time": "0:43:57", "remaining_time": "0:48:30", "throughput": 10196.52, "total_tokens": 26890112}
{"current_steps": 28015, "total_steps": 58920, "loss": 0.0001, "lr": 1.2572736303868102e-06, "epoch": 2.377376103190767, "percentage": 47.55, "elapsed_time": "0:43:57", "remaining_time": "0:48:29", "throughput": 10196.91, "total_tokens": 26895040}
{"current_steps": 28020, "total_steps": 58920, "loss": 0.0001, "lr": 1.2569873701191588e-06, "epoch": 2.3778004073319754, "percentage": 47.56, "elapsed_time": "0:43:57", "remaining_time": "0:48:29", "throughput": 10197.36, "total_tokens": 26900288}
{"current_steps": 28025, "total_steps": 58920, "loss": 0.0001, "lr": 1.2567010873017938e-06, "epoch": 2.378224711473184, "percentage": 47.56, "elapsed_time": "0:43:58", "remaining_time": "0:48:28", "throughput": 10197.72, "total_tokens": 26905152}
{"current_steps": 28030, "total_steps": 58920, "loss": 0.0001, "lr": 1.256414781959835e-06, "epoch": 2.3786490156143922, "percentage": 47.57, "elapsed_time": "0:43:58", "remaining_time": "0:48:27", "throughput": 10197.94, "total_tokens": 26909568}
{"current_steps": 28035, "total_steps": 58920, "loss": 0.0001, "lr": 1.2561284541184053e-06, "epoch": 2.3790733197556007, "percentage": 47.58, "elapsed_time": "0:43:59", "remaining_time": "0:48:27", "throughput": 10199.32, "total_tokens": 26918208}
{"current_steps": 28040, "total_steps": 58920, "loss": 0.0439, "lr": 1.2558421038026284e-06, "epoch": 2.379497623896809, "percentage": 47.59, "elapsed_time": "0:43:59", "remaining_time": "0:48:26", "throughput": 10199.7, "total_tokens": 26923136}
{"current_steps": 28045, "total_steps": 58920, "loss": 0.0123, "lr": 1.2555557310376304e-06, "epoch": 2.3799219280380175, "percentage": 47.6, "elapsed_time": "0:43:59", "remaining_time": "0:48:26", "throughput": 10200.04, "total_tokens": 26927872}
{"current_steps": 28050, "total_steps": 58920, "loss": 0.0002, "lr": 1.2552693358485397e-06, "epoch": 2.380346232179226, "percentage": 47.61, "elapsed_time": "0:44:00", "remaining_time": "0:48:25", "throughput": 10200.43, "total_tokens": 26932800}
{"current_steps": 28055, "total_steps": 58920, "loss": 0.0293, "lr": 1.2549829182604863e-06, "epoch": 2.3807705363204343, "percentage": 47.62, "elapsed_time": "0:44:00", "remaining_time": "0:48:25", "throughput": 10200.91, "total_tokens": 26938112}
{"current_steps": 28060, "total_steps": 58920, "loss": 0.0, "lr": 1.2546964782986026e-06, "epoch": 2.3811948404616428, "percentage": 47.62, "elapsed_time": "0:44:01", "remaining_time": "0:48:24", "throughput": 10201.42, "total_tokens": 26943488}
{"current_steps": 28065, "total_steps": 58920, "loss": 0.0307, "lr": 1.2544100159880225e-06, "epoch": 2.381619144602851, "percentage": 47.63, "elapsed_time": "0:44:01", "remaining_time": "0:48:24", "throughput": 10201.72, "total_tokens": 26948096}
{"current_steps": 28070, "total_steps": 58920, "loss": 0.0278, "lr": 1.2541235313538818e-06, "epoch": 2.3820434487440596, "percentage": 47.64, "elapsed_time": "0:44:01", "remaining_time": "0:48:23", "throughput": 10202.09, "total_tokens": 26952960}
{"current_steps": 28075, "total_steps": 58920, "loss": 0.0095, "lr": 1.253837024421319e-06, "epoch": 2.382467752885268, "percentage": 47.65, "elapsed_time": "0:44:02", "remaining_time": "0:48:22", "throughput": 10202.47, "total_tokens": 26957888}
{"current_steps": 28080, "total_steps": 58920, "loss": 0.0001, "lr": 1.2535504952154738e-06, "epoch": 2.3828920570264764, "percentage": 47.66, "elapsed_time": "0:44:02", "remaining_time": "0:48:22", "throughput": 10202.87, "total_tokens": 26962880}
{"current_steps": 28085, "total_steps": 58920, "loss": 0.0001, "lr": 1.253263943761488e-06, "epoch": 2.383316361167685, "percentage": 47.67, "elapsed_time": "0:44:03", "remaining_time": "0:48:21", "throughput": 10203.42, "total_tokens": 26968448}
{"current_steps": 28090, "total_steps": 58920, "loss": 0.0193, "lr": 1.2529773700845057e-06, "epoch": 2.3837406653088933, "percentage": 47.67, "elapsed_time": "0:44:03", "remaining_time": "0:48:21", "throughput": 10203.79, "total_tokens": 26973376}
{"current_steps": 28095, "total_steps": 58920, "loss": 0.0002, "lr": 1.2526907742096725e-06, "epoch": 2.3841649694501017, "percentage": 47.68, "elapsed_time": "0:44:03", "remaining_time": "0:48:20", "throughput": 10204.15, "total_tokens": 26978176}
{"current_steps": 28100, "total_steps": 58920, "loss": 0.0001, "lr": 1.252404156162136e-06, "epoch": 2.38458927359131, "percentage": 47.69, "elapsed_time": "0:44:04", "remaining_time": "0:48:20", "throughput": 10204.59, "total_tokens": 26983360}
{"current_steps": 28105, "total_steps": 58920, "loss": 0.0502, "lr": 1.2521175159670462e-06, "epoch": 2.3850135777325185, "percentage": 47.7, "elapsed_time": "0:44:04", "remaining_time": "0:48:19", "throughput": 10204.96, "total_tokens": 26988288}
{"current_steps": 28110, "total_steps": 58920, "loss": 0.0001, "lr": 1.2518308536495544e-06, "epoch": 2.385437881873727, "percentage": 47.71, "elapsed_time": "0:44:05", "remaining_time": "0:48:19", "throughput": 10205.5, "total_tokens": 26993728}
{"current_steps": 28115, "total_steps": 58920, "loss": 0.034, "lr": 1.251544169234815e-06, "epoch": 2.3858621860149354, "percentage": 47.72, "elapsed_time": "0:44:05", "remaining_time": "0:48:18", "throughput": 10205.83, "total_tokens": 26998528}
{"current_steps": 28120, "total_steps": 58920, "loss": 0.0006, "lr": 1.2512574627479825e-06, "epoch": 2.386286490156144, "percentage": 47.73, "elapsed_time": "0:44:05", "remaining_time": "0:48:17", "throughput": 10206.17, "total_tokens": 27003264}
{"current_steps": 28125, "total_steps": 58920, "loss": 0.0002, "lr": 1.2509707342142152e-06, "epoch": 2.3867107942973522, "percentage": 47.73, "elapsed_time": "0:44:06", "remaining_time": "0:48:17", "throughput": 10206.47, "total_tokens": 27007936}
{"current_steps": 28130, "total_steps": 58920, "loss": 0.0224, "lr": 1.2506839836586718e-06, "epoch": 2.3871350984385606, "percentage": 47.74, "elapsed_time": "0:44:06", "remaining_time": "0:48:16", "throughput": 10206.77, "total_tokens": 27012608}
{"current_steps": 28135, "total_steps": 58920, "loss": 0.021, "lr": 1.250397211106514e-06, "epoch": 2.387559402579769, "percentage": 47.75, "elapsed_time": "0:44:06", "remaining_time": "0:48:16", "throughput": 10207.13, "total_tokens": 27017536}
{"current_steps": 28140, "total_steps": 58920, "loss": 0.0001, "lr": 1.2501104165829048e-06, "epoch": 2.3879837067209775, "percentage": 47.76, "elapsed_time": "0:44:07", "remaining_time": "0:48:15", "throughput": 10207.51, "total_tokens": 27022400}
{"current_steps": 28145, "total_steps": 58920, "loss": 0.0481, "lr": 1.2498236001130096e-06, "epoch": 2.388408010862186, "percentage": 47.77, "elapsed_time": "0:44:07", "remaining_time": "0:48:15", "throughput": 10207.99, "total_tokens": 27027648}
{"current_steps": 28150, "total_steps": 58920, "loss": 0.0, "lr": 1.2495367617219953e-06, "epoch": 2.3888323150033943, "percentage": 47.78, "elapsed_time": "0:44:08", "remaining_time": "0:48:14", "throughput": 10208.17, "total_tokens": 27031936}
{"current_steps": 28155, "total_steps": 58920, "loss": 0.0002, "lr": 1.2492499014350316e-06, "epoch": 2.3892566191446027, "percentage": 47.79, "elapsed_time": "0:44:08", "remaining_time": "0:48:13", "throughput": 10208.47, "total_tokens": 27036608}
{"current_steps": 28160, "total_steps": 58920, "loss": 0.0274, "lr": 1.2489630192772885e-06, "epoch": 2.389680923285811, "percentage": 47.79, "elapsed_time": "0:44:08", "remaining_time": "0:48:13", "throughput": 10208.79, "total_tokens": 27041344}
{"current_steps": 28165, "total_steps": 58920, "loss": 0.0001, "lr": 1.24867611527394e-06, "epoch": 2.3901052274270196, "percentage": 47.8, "elapsed_time": "0:44:09", "remaining_time": "0:48:12", "throughput": 10209.23, "total_tokens": 27046464}
{"current_steps": 28170, "total_steps": 58920, "loss": 0.0003, "lr": 1.24838918945016e-06, "epoch": 2.390529531568228, "percentage": 47.81, "elapsed_time": "0:44:09", "remaining_time": "0:48:12", "throughput": 10209.67, "total_tokens": 27051648}
{"current_steps": 28175, "total_steps": 58920, "loss": 0.0001, "lr": 1.248102241831125e-06, "epoch": 2.3909538357094364, "percentage": 47.82, "elapsed_time": "0:44:09", "remaining_time": "0:48:11", "throughput": 10210.0, "total_tokens": 27056448}
{"current_steps": 28180, "total_steps": 58920, "loss": 0.0001, "lr": 1.247815272442014e-06, "epoch": 2.391378139850645, "percentage": 47.83, "elapsed_time": "0:44:10", "remaining_time": "0:48:11", "throughput": 10210.25, "total_tokens": 27060928}
{"current_steps": 28185, "total_steps": 58920, "loss": 0.0014, "lr": 1.247528281308008e-06, "epoch": 2.3918024439918533, "percentage": 47.84, "elapsed_time": "0:44:10", "remaining_time": "0:48:10", "throughput": 10210.5, "total_tokens": 27065408}
{"current_steps": 28190, "total_steps": 58920, "loss": 0.0252, "lr": 1.2472412684542888e-06, "epoch": 2.3922267481330617, "percentage": 47.84, "elapsed_time": "0:44:11", "remaining_time": "0:48:09", "throughput": 10210.88, "total_tokens": 27070336}
{"current_steps": 28195, "total_steps": 58920, "loss": 0.0001, "lr": 1.2469542339060413e-06, "epoch": 2.39265105227427, "percentage": 47.85, "elapsed_time": "0:44:11", "remaining_time": "0:48:09", "throughput": 10211.22, "total_tokens": 27075136}
{"current_steps": 28200, "total_steps": 58920, "loss": 0.0001, "lr": 1.246667177688451e-06, "epoch": 2.3930753564154785, "percentage": 47.86, "elapsed_time": "0:44:11", "remaining_time": "0:48:08", "throughput": 10211.56, "total_tokens": 27079936}
{"current_steps": 28205, "total_steps": 58920, "loss": 0.057, "lr": 1.2463800998267067e-06, "epoch": 2.393499660556687, "percentage": 47.87, "elapsed_time": "0:44:12", "remaining_time": "0:48:08", "throughput": 10211.89, "total_tokens": 27084672}
{"current_steps": 28210, "total_steps": 58920, "loss": 0.0245, "lr": 1.246093000345998e-06, "epoch": 2.3939239646978954, "percentage": 47.88, "elapsed_time": "0:44:12", "remaining_time": "0:48:07", "throughput": 10212.26, "total_tokens": 27089600}
{"current_steps": 28215, "total_steps": 58920, "loss": 0.0089, "lr": 1.245805879271517e-06, "epoch": 2.394348268839104, "percentage": 47.89, "elapsed_time": "0:44:13", "remaining_time": "0:48:07", "throughput": 10212.56, "total_tokens": 27094336}
{"current_steps": 28220, "total_steps": 58920, "loss": 0.0001, "lr": 1.2455187366284578e-06, "epoch": 2.394772572980312, "percentage": 47.9, "elapsed_time": "0:44:13", "remaining_time": "0:48:06", "throughput": 10212.89, "total_tokens": 27099136}
{"current_steps": 28225, "total_steps": 58920, "loss": 0.0002, "lr": 1.2452315724420158e-06, "epoch": 2.3951968771215206, "percentage": 47.9, "elapsed_time": "0:44:13", "remaining_time": "0:48:06", "throughput": 10213.16, "total_tokens": 27103680}
{"current_steps": 28230, "total_steps": 58920, "loss": 0.0003, "lr": 1.2449443867373886e-06, "epoch": 2.395621181262729, "percentage": 47.91, "elapsed_time": "0:44:14", "remaining_time": "0:48:05", "throughput": 10213.59, "total_tokens": 27108800}
{"current_steps": 28235, "total_steps": 58920, "loss": 0.0, "lr": 1.244657179539776e-06, "epoch": 2.3960454854039375, "percentage": 47.92, "elapsed_time": "0:44:14", "remaining_time": "0:48:04", "throughput": 10213.85, "total_tokens": 27113344}
{"current_steps": 28240, "total_steps": 58920, "loss": 0.0001, "lr": 1.244369950874379e-06, "epoch": 2.396469789545146, "percentage": 47.93, "elapsed_time": "0:44:14", "remaining_time": "0:48:04", "throughput": 10214.1, "total_tokens": 27117824}
{"current_steps": 28245, "total_steps": 58920, "loss": 0.0365, "lr": 1.2440827007664011e-06, "epoch": 2.3968940936863543, "percentage": 47.94, "elapsed_time": "0:44:15", "remaining_time": "0:48:03", "throughput": 10214.49, "total_tokens": 27122816}
{"current_steps": 28250, "total_steps": 58920, "loss": 0.054, "lr": 1.2437954292410479e-06, "epoch": 2.3973183978275627, "percentage": 47.95, "elapsed_time": "0:44:15", "remaining_time": "0:48:03", "throughput": 10214.76, "total_tokens": 27127424}
{"current_steps": 28255, "total_steps": 58920, "loss": 0.0195, "lr": 1.2435081363235258e-06, "epoch": 2.397742701968771, "percentage": 47.95, "elapsed_time": "0:44:16", "remaining_time": "0:48:02", "throughput": 10215.19, "total_tokens": 27132544}
{"current_steps": 28260, "total_steps": 58920, "loss": 0.0396, "lr": 1.243220822039044e-06, "epoch": 2.3981670061099796, "percentage": 47.96, "elapsed_time": "0:44:16", "remaining_time": "0:48:02", "throughput": 10215.71, "total_tokens": 27137984}
{"current_steps": 28265, "total_steps": 58920, "loss": 0.0272, "lr": 1.2429334864128129e-06, "epoch": 2.398591310251188, "percentage": 47.97, "elapsed_time": "0:44:16", "remaining_time": "0:48:01", "throughput": 10215.96, "total_tokens": 27142528}
{"current_steps": 28270, "total_steps": 58920, "loss": 0.0, "lr": 1.2426461294700454e-06, "epoch": 2.3990156143923964, "percentage": 47.98, "elapsed_time": "0:44:17", "remaining_time": "0:48:00", "throughput": 10216.48, "total_tokens": 27147968}
{"current_steps": 28275, "total_steps": 58920, "loss": 0.015, "lr": 1.2423587512359564e-06, "epoch": 2.399439918533605, "percentage": 47.99, "elapsed_time": "0:44:17", "remaining_time": "0:48:00", "throughput": 10216.67, "total_tokens": 27152256}
{"current_steps": 28280, "total_steps": 58920, "loss": 0.0258, "lr": 1.242071351735762e-06, "epoch": 2.3998642226748133, "percentage": 48.0, "elapsed_time": "0:44:18", "remaining_time": "0:47:59", "throughput": 10216.87, "total_tokens": 27156608}
{"current_steps": 28285, "total_steps": 58920, "loss": 0.0002, "lr": 1.2417839309946804e-06, "epoch": 2.4002885268160217, "percentage": 48.01, "elapsed_time": "0:44:18", "remaining_time": "0:47:59", "throughput": 10217.1, "total_tokens": 27161024}
{"current_steps": 28290, "total_steps": 58920, "loss": 0.0, "lr": 1.241496489037932e-06, "epoch": 2.40071283095723, "percentage": 48.01, "elapsed_time": "0:44:18", "remaining_time": "0:47:58", "throughput": 10217.33, "total_tokens": 27165504}
{"current_steps": 28295, "total_steps": 58920, "loss": 0.0, "lr": 1.2412090258907387e-06, "epoch": 2.4011371350984385, "percentage": 48.02, "elapsed_time": "0:44:19", "remaining_time": "0:47:58", "throughput": 10217.73, "total_tokens": 27170496}
{"current_steps": 28300, "total_steps": 58920, "loss": 0.0694, "lr": 1.2409215415783236e-06, "epoch": 2.401561439239647, "percentage": 48.03, "elapsed_time": "0:44:19", "remaining_time": "0:47:57", "throughput": 10218.12, "total_tokens": 27175488}
{"current_steps": 28305, "total_steps": 58920, "loss": 0.0001, "lr": 1.2406340361259136e-06, "epoch": 2.4019857433808554, "percentage": 48.04, "elapsed_time": "0:44:19", "remaining_time": "0:47:56", "throughput": 10218.39, "total_tokens": 27180096}
{"current_steps": 28310, "total_steps": 58920, "loss": 0.0004, "lr": 1.2403465095587358e-06, "epoch": 2.4024100475220638, "percentage": 48.05, "elapsed_time": "0:44:20", "remaining_time": "0:47:56", "throughput": 10218.69, "total_tokens": 27184768}
{"current_steps": 28315, "total_steps": 58920, "loss": 0.0001, "lr": 1.2400589619020192e-06, "epoch": 2.402834351663272, "percentage": 48.06, "elapsed_time": "0:44:20", "remaining_time": "0:47:55", "throughput": 10218.88, "total_tokens": 27189056}
{"current_steps": 28320, "total_steps": 58920, "loss": 0.0, "lr": 1.2397713931809958e-06, "epoch": 2.4032586558044806, "percentage": 48.07, "elapsed_time": "0:44:21", "remaining_time": "0:47:55", "throughput": 10219.29, "total_tokens": 27194048}
{"current_steps": 28325, "total_steps": 58920, "loss": 0.0347, "lr": 1.239483803420898e-06, "epoch": 2.403682959945689, "percentage": 48.07, "elapsed_time": "0:44:21", "remaining_time": "0:47:54", "throughput": 10219.62, "total_tokens": 27198848}
{"current_steps": 28330, "total_steps": 58920, "loss": 0.0, "lr": 1.239196192646961e-06, "epoch": 2.4041072640868975, "percentage": 48.08, "elapsed_time": "0:44:21", "remaining_time": "0:47:54", "throughput": 10219.86, "total_tokens": 27203328}
{"current_steps": 28335, "total_steps": 58920, "loss": 0.0003, "lr": 1.2389085608844223e-06, "epoch": 2.404531568228106, "percentage": 48.09, "elapsed_time": "0:44:22", "remaining_time": "0:47:53", "throughput": 10220.26, "total_tokens": 27208384}
{"current_steps": 28340, "total_steps": 58920, "loss": 0.0245, "lr": 1.2386209081585196e-06, "epoch": 2.4049558723693143, "percentage": 48.1, "elapsed_time": "0:44:22", "remaining_time": "0:47:53", "throughput": 10220.64, "total_tokens": 27213312}
{"current_steps": 28345, "total_steps": 58920, "loss": 0.0, "lr": 1.2383332344944937e-06, "epoch": 2.4053801765105227, "percentage": 48.11, "elapsed_time": "0:44:22", "remaining_time": "0:47:52", "throughput": 10220.99, "total_tokens": 27218112}
{"current_steps": 28350, "total_steps": 58920, "loss": 0.0348, "lr": 1.2380455399175872e-06, "epoch": 2.405804480651731, "percentage": 48.12, "elapsed_time": "0:44:23", "remaining_time": "0:47:51", "throughput": 10221.33, "total_tokens": 27222912}
{"current_steps": 28355, "total_steps": 58920, "loss": 0.0, "lr": 1.2377578244530438e-06, "epoch": 2.4062287847929396, "percentage": 48.12, "elapsed_time": "0:44:23", "remaining_time": "0:47:51", "throughput": 10221.68, "total_tokens": 27227776}
{"current_steps": 28360, "total_steps": 58920, "loss": 0.0059, "lr": 1.2374700881261098e-06, "epoch": 2.406653088934148, "percentage": 48.13, "elapsed_time": "0:44:24", "remaining_time": "0:47:50", "throughput": 10221.93, "total_tokens": 27232320}
{"current_steps": 28365, "total_steps": 58920, "loss": 0.0001, "lr": 1.2371823309620325e-06, "epoch": 2.4070773930753564, "percentage": 48.14, "elapsed_time": "0:44:24", "remaining_time": "0:47:50", "throughput": 10222.29, "total_tokens": 27237248}
{"current_steps": 28370, "total_steps": 58920, "loss": 0.0, "lr": 1.2368945529860625e-06, "epoch": 2.407501697216565, "percentage": 48.15, "elapsed_time": "0:44:24", "remaining_time": "0:47:49", "throughput": 10222.47, "total_tokens": 27241536}
{"current_steps": 28375, "total_steps": 58920, "loss": 0.0, "lr": 1.236606754223451e-06, "epoch": 2.4079260013577732, "percentage": 48.16, "elapsed_time": "0:44:25", "remaining_time": "0:47:49", "throughput": 10222.75, "total_tokens": 27246208}
{"current_steps": 28380, "total_steps": 58920, "loss": 0.0849, "lr": 1.236318934699451e-06, "epoch": 2.4083503054989817, "percentage": 48.17, "elapsed_time": "0:44:25", "remaining_time": "0:47:48", "throughput": 10223.02, "total_tokens": 27250752}
{"current_steps": 28385, "total_steps": 58920, "loss": 0.0329, "lr": 1.2360310944393173e-06, "epoch": 2.40877460964019, "percentage": 48.18, "elapsed_time": "0:44:26", "remaining_time": "0:47:47", "throughput": 10223.42, "total_tokens": 27255744}
{"current_steps": 28390, "total_steps": 58920, "loss": 0.0, "lr": 1.2357432334683073e-06, "epoch": 2.4091989137813985, "percentage": 48.18, "elapsed_time": "0:44:26", "remaining_time": "0:47:47", "throughput": 10223.85, "total_tokens": 27260864}
{"current_steps": 28395, "total_steps": 58920, "loss": 0.0001, "lr": 1.23545535181168e-06, "epoch": 2.409623217922607, "percentage": 48.19, "elapsed_time": "0:44:26", "remaining_time": "0:47:46", "throughput": 10224.26, "total_tokens": 27265984}
{"current_steps": 28400, "total_steps": 58920, "loss": 0.0002, "lr": 1.2351674494946954e-06, "epoch": 2.4100475220638153, "percentage": 48.2, "elapsed_time": "0:44:27", "remaining_time": "0:47:46", "throughput": 10224.46, "total_tokens": 27270336}
{"current_steps": 28405, "total_steps": 58920, "loss": 0.0007, "lr": 1.2348795265426164e-06, "epoch": 2.4104718262050238, "percentage": 48.21, "elapsed_time": "0:44:27", "remaining_time": "0:47:45", "throughput": 10224.82, "total_tokens": 27275200}
{"current_steps": 28410, "total_steps": 58920, "loss": 0.0002, "lr": 1.234591582980707e-06, "epoch": 2.410896130346232, "percentage": 48.22, "elapsed_time": "0:44:27", "remaining_time": "0:47:45", "throughput": 10225.1, "total_tokens": 27279808}
{"current_steps": 28415, "total_steps": 58920, "loss": 0.001, "lr": 1.2343036188342332e-06, "epoch": 2.4113204344874406, "percentage": 48.23, "elapsed_time": "0:44:28", "remaining_time": "0:47:44", "throughput": 10225.36, "total_tokens": 27284352}
{"current_steps": 28420, "total_steps": 58920, "loss": 0.0318, "lr": 1.2340156341284624e-06, "epoch": 2.411744738628649, "percentage": 48.23, "elapsed_time": "0:44:28", "remaining_time": "0:47:43", "throughput": 10225.58, "total_tokens": 27288768}
{"current_steps": 28425, "total_steps": 58920, "loss": 0.0, "lr": 1.233727628888665e-06, "epoch": 2.4121690427698574, "percentage": 48.24, "elapsed_time": "0:44:29", "remaining_time": "0:47:43", "throughput": 10225.83, "total_tokens": 27293312}
{"current_steps": 28430, "total_steps": 58920, "loss": 0.0001, "lr": 1.233439603140112e-06, "epoch": 2.412593346911066, "percentage": 48.25, "elapsed_time": "0:44:29", "remaining_time": "0:47:42", "throughput": 10226.06, "total_tokens": 27297728}
{"current_steps": 28435, "total_steps": 58920, "loss": 0.0126, "lr": 1.2331515569080766e-06, "epoch": 2.4130176510522743, "percentage": 48.26, "elapsed_time": "0:44:29", "remaining_time": "0:47:42", "throughput": 10226.27, "total_tokens": 27302144}
{"current_steps": 28440, "total_steps": 58920, "loss": 0.0244, "lr": 1.2328634902178338e-06, "epoch": 2.4134419551934827, "percentage": 48.27, "elapsed_time": "0:44:30", "remaining_time": "0:47:41", "throughput": 10226.52, "total_tokens": 27306624}
{"current_steps": 28445, "total_steps": 58920, "loss": 0.0189, "lr": 1.2325754030946607e-06, "epoch": 2.413866259334691, "percentage": 48.28, "elapsed_time": "0:44:30", "remaining_time": "0:47:41", "throughput": 10226.87, "total_tokens": 27311488}
{"current_steps": 28450, "total_steps": 58920, "loss": 0.0001, "lr": 1.2322872955638355e-06, "epoch": 2.4142905634758995, "percentage": 48.29, "elapsed_time": "0:44:30", "remaining_time": "0:47:40", "throughput": 10227.14, "total_tokens": 27316032}
{"current_steps": 28455, "total_steps": 58920, "loss": 0.0003, "lr": 1.2319991676506387e-06, "epoch": 2.414714867617108, "percentage": 48.29, "elapsed_time": "0:44:31", "remaining_time": "0:47:40", "throughput": 10227.47, "total_tokens": 27320768}
{"current_steps": 28460, "total_steps": 58920, "loss": 0.0546, "lr": 1.2317110193803528e-06, "epoch": 2.4151391717583164, "percentage": 48.3, "elapsed_time": "0:44:31", "remaining_time": "0:47:39", "throughput": 10227.76, "total_tokens": 27325440}
{"current_steps": 28465, "total_steps": 58920, "loss": 0.001, "lr": 1.2314228507782613e-06, "epoch": 2.415563475899525, "percentage": 48.31, "elapsed_time": "0:44:32", "remaining_time": "0:47:38", "throughput": 10228.13, "total_tokens": 27330432}
{"current_steps": 28470, "total_steps": 58920, "loss": 0.0284, "lr": 1.2311346618696506e-06, "epoch": 2.4159877800407332, "percentage": 48.32, "elapsed_time": "0:44:32", "remaining_time": "0:47:38", "throughput": 10228.37, "total_tokens": 27334912}
{"current_steps": 28475, "total_steps": 58920, "loss": 0.0001, "lr": 1.2308464526798076e-06, "epoch": 2.4164120841819416, "percentage": 48.33, "elapsed_time": "0:44:32", "remaining_time": "0:47:37", "throughput": 10228.61, "total_tokens": 27339392}
{"current_steps": 28480, "total_steps": 58920, "loss": 0.0002, "lr": 1.2305582232340217e-06, "epoch": 2.41683638832315, "percentage": 48.34, "elapsed_time": "0:44:33", "remaining_time": "0:47:37", "throughput": 10229.01, "total_tokens": 27344448}
{"current_steps": 28485, "total_steps": 58920, "loss": 0.0001, "lr": 1.230269973557584e-06, "epoch": 2.4172606924643585, "percentage": 48.35, "elapsed_time": "0:44:33", "remaining_time": "0:47:36", "throughput": 10229.11, "total_tokens": 27348480}
{"current_steps": 28490, "total_steps": 58920, "loss": 0.0, "lr": 1.2299817036757878e-06, "epoch": 2.417684996605567, "percentage": 48.35, "elapsed_time": "0:44:33", "remaining_time": "0:47:36", "throughput": 10229.49, "total_tokens": 27353472}
{"current_steps": 28495, "total_steps": 58920, "loss": 0.0002, "lr": 1.2296934136139271e-06, "epoch": 2.4181093007467753, "percentage": 48.36, "elapsed_time": "0:44:34", "remaining_time": "0:47:35", "throughput": 10230.08, "total_tokens": 27359168}
{"current_steps": 28500, "total_steps": 58920, "loss": 0.0001, "lr": 1.2294051033972993e-06, "epoch": 2.4185336048879837, "percentage": 48.37, "elapsed_time": "0:44:34", "remaining_time": "0:47:34", "throughput": 10230.36, "total_tokens": 27363776}
{"current_steps": 28505, "total_steps": 58920, "loss": 0.014, "lr": 1.2291167730512016e-06, "epoch": 2.418957909029192, "percentage": 48.38, "elapsed_time": "0:44:35", "remaining_time": "0:47:34", "throughput": 10230.58, "total_tokens": 27368192}
{"current_steps": 28510, "total_steps": 58920, "loss": 0.0001, "lr": 1.2288284226009343e-06, "epoch": 2.4193822131704006, "percentage": 48.39, "elapsed_time": "0:44:35", "remaining_time": "0:47:33", "throughput": 10231.0, "total_tokens": 27373312}
{"current_steps": 28515, "total_steps": 58920, "loss": 0.0001, "lr": 1.228540052071799e-06, "epoch": 2.419806517311609, "percentage": 48.4, "elapsed_time": "0:44:35", "remaining_time": "0:47:33", "throughput": 10231.29, "total_tokens": 27377984}
{"current_steps": 28520, "total_steps": 58920, "loss": 0.0281, "lr": 1.228251661489099e-06, "epoch": 2.4202308214528174, "percentage": 48.4, "elapsed_time": "0:44:36", "remaining_time": "0:47:32", "throughput": 10231.74, "total_tokens": 27383232}
{"current_steps": 28525, "total_steps": 58920, "loss": 0.0, "lr": 1.2279632508781403e-06, "epoch": 2.420655125594026, "percentage": 48.41, "elapsed_time": "0:44:36", "remaining_time": "0:47:32", "throughput": 10231.97, "total_tokens": 27387712}
{"current_steps": 28530, "total_steps": 58920, "loss": 0.0, "lr": 1.2276748202642292e-06, "epoch": 2.4210794297352343, "percentage": 48.42, "elapsed_time": "0:44:37", "remaining_time": "0:47:31", "throughput": 10232.32, "total_tokens": 27392576}
{"current_steps": 28535, "total_steps": 58920, "loss": 0.0001, "lr": 1.227386369672675e-06, "epoch": 2.4215037338764427, "percentage": 48.43, "elapsed_time": "0:44:37", "remaining_time": "0:47:31", "throughput": 10232.66, "total_tokens": 27397376}
{"current_steps": 28540, "total_steps": 58920, "loss": 0.0549, "lr": 1.2270978991287875e-06, "epoch": 2.421928038017651, "percentage": 48.44, "elapsed_time": "0:44:37", "remaining_time": "0:47:30", "throughput": 10232.95, "total_tokens": 27402048}
{"current_steps": 28545, "total_steps": 58920, "loss": 0.0218, "lr": 1.2268094086578794e-06, "epoch": 2.4223523421588595, "percentage": 48.45, "elapsed_time": "0:44:38", "remaining_time": "0:47:29", "throughput": 10233.17, "total_tokens": 27406464}
{"current_steps": 28550, "total_steps": 58920, "loss": 0.0, "lr": 1.2265208982852644e-06, "epoch": 2.422776646300068, "percentage": 48.46, "elapsed_time": "0:44:38", "remaining_time": "0:47:29", "throughput": 10233.74, "total_tokens": 27412160}
{"current_steps": 28555, "total_steps": 58920, "loss": 0.0002, "lr": 1.2262323680362584e-06, "epoch": 2.4232009504412764, "percentage": 48.46, "elapsed_time": "0:44:38", "remaining_time": "0:47:28", "throughput": 10234.09, "total_tokens": 27417088}
{"current_steps": 28560, "total_steps": 58920, "loss": 0.0001, "lr": 1.2259438179361791e-06, "epoch": 2.423625254582485, "percentage": 48.47, "elapsed_time": "0:44:39", "remaining_time": "0:47:28", "throughput": 10234.56, "total_tokens": 27422336}
{"current_steps": 28565, "total_steps": 58920, "loss": 0.0824, "lr": 1.2256552480103455e-06, "epoch": 2.424049558723693, "percentage": 48.48, "elapsed_time": "0:44:39", "remaining_time": "0:47:27", "throughput": 10234.85, "total_tokens": 27427008}
{"current_steps": 28570, "total_steps": 58920, "loss": 0.0, "lr": 1.2253666582840785e-06, "epoch": 2.4244738628649016, "percentage": 48.49, "elapsed_time": "0:44:40", "remaining_time": "0:47:27", "throughput": 10235.3, "total_tokens": 27432256}
{"current_steps": 28575, "total_steps": 58920, "loss": 0.0301, "lr": 1.2250780487827011e-06, "epoch": 2.42489816700611, "percentage": 48.5, "elapsed_time": "0:44:40", "remaining_time": "0:47:26", "throughput": 10235.58, "total_tokens": 27436928}
{"current_steps": 28580, "total_steps": 58920, "loss": 0.0109, "lr": 1.224789419531537e-06, "epoch": 2.4253224711473185, "percentage": 48.51, "elapsed_time": "0:44:40", "remaining_time": "0:47:26", "throughput": 10235.81, "total_tokens": 27441344}
{"current_steps": 28585, "total_steps": 58920, "loss": 0.0372, "lr": 1.2245007705559138e-06, "epoch": 2.425746775288527, "percentage": 48.51, "elapsed_time": "0:44:41", "remaining_time": "0:47:25", "throughput": 10236.4, "total_tokens": 27447040}
{"current_steps": 28590, "total_steps": 58920, "loss": 0.0545, "lr": 1.2242121018811582e-06, "epoch": 2.4261710794297353, "percentage": 48.52, "elapsed_time": "0:44:41", "remaining_time": "0:47:24", "throughput": 10236.69, "total_tokens": 27451712}
{"current_steps": 28595, "total_steps": 58920, "loss": 0.0001, "lr": 1.2239234135325999e-06, "epoch": 2.4265953835709437, "percentage": 48.53, "elapsed_time": "0:44:42", "remaining_time": "0:47:24", "throughput": 10236.98, "total_tokens": 27456320}
{"current_steps": 28600, "total_steps": 58920, "loss": 0.0268, "lr": 1.223634705535571e-06, "epoch": 2.427019687712152, "percentage": 48.54, "elapsed_time": "0:44:42", "remaining_time": "0:47:23", "throughput": 10237.3, "total_tokens": 27461120}
{"current_steps": 28605, "total_steps": 58920, "loss": 0.0405, "lr": 1.2233459779154036e-06, "epoch": 2.4274439918533606, "percentage": 48.55, "elapsed_time": "0:44:42", "remaining_time": "0:47:23", "throughput": 10237.6, "total_tokens": 27465856}
{"current_steps": 28610, "total_steps": 58920, "loss": 0.0003, "lr": 1.2230572306974334e-06, "epoch": 2.427868295994569, "percentage": 48.56, "elapsed_time": "0:44:43", "remaining_time": "0:47:22", "throughput": 10237.84, "total_tokens": 27470336}
{"current_steps": 28615, "total_steps": 58920, "loss": 0.0024, "lr": 1.2227684639069963e-06, "epoch": 2.4282926001357774, "percentage": 48.57, "elapsed_time": "0:44:43", "remaining_time": "0:47:22", "throughput": 10238.26, "total_tokens": 27475456}
{"current_steps": 28620, "total_steps": 58920, "loss": 0.0006, "lr": 1.222479677569431e-06, "epoch": 2.428716904276986, "percentage": 48.57, "elapsed_time": "0:44:43", "remaining_time": "0:47:21", "throughput": 10238.6, "total_tokens": 27480256}
{"current_steps": 28625, "total_steps": 58920, "loss": 0.0001, "lr": 1.2221908717100772e-06, "epoch": 2.4291412084181943, "percentage": 48.58, "elapsed_time": "0:44:44", "remaining_time": "0:47:20", "throughput": 10238.79, "total_tokens": 27484608}
{"current_steps": 28630, "total_steps": 58920, "loss": 0.0, "lr": 1.221902046354277e-06, "epoch": 2.4295655125594027, "percentage": 48.59, "elapsed_time": "0:44:44", "remaining_time": "0:47:20", "throughput": 10239.2, "total_tokens": 27489600}
{"current_steps": 28635, "total_steps": 58920, "loss": 0.0002, "lr": 1.2216132015273727e-06, "epoch": 2.429989816700611, "percentage": 48.6, "elapsed_time": "0:44:45", "remaining_time": "0:47:19", "throughput": 10239.38, "total_tokens": 27493952}
{"current_steps": 28640, "total_steps": 58920, "loss": 0.0001, "lr": 1.2213243372547104e-06, "epoch": 2.4304141208418195, "percentage": 48.61, "elapsed_time": "0:44:45", "remaining_time": "0:47:19", "throughput": 10239.65, "total_tokens": 27498560}
{"current_steps": 28645, "total_steps": 58920, "loss": 0.0318, "lr": 1.2210354535616364e-06, "epoch": 2.430838424983028, "percentage": 48.62, "elapsed_time": "0:44:45", "remaining_time": "0:47:18", "throughput": 10239.96, "total_tokens": 27503296}
{"current_steps": 28650, "total_steps": 58920, "loss": 0.0748, "lr": 1.2207465504734998e-06, "epoch": 2.4312627291242364, "percentage": 48.63, "elapsed_time": "0:44:46", "remaining_time": "0:47:18", "throughput": 10240.12, "total_tokens": 27507520}
{"current_steps": 28655, "total_steps": 58920, "loss": 0.0001, "lr": 1.2204576280156502e-06, "epoch": 2.4316870332654448, "percentage": 48.63, "elapsed_time": "0:44:46", "remaining_time": "0:47:17", "throughput": 10240.41, "total_tokens": 27512192}
{"current_steps": 28660, "total_steps": 58920, "loss": 0.0272, "lr": 1.2201686862134397e-06, "epoch": 2.432111337406653, "percentage": 48.64, "elapsed_time": "0:44:47", "remaining_time": "0:47:17", "throughput": 10240.7, "total_tokens": 27516800}
{"current_steps": 28665, "total_steps": 58920, "loss": 0.0007, "lr": 1.219879725092222e-06, "epoch": 2.4325356415478616, "percentage": 48.65, "elapsed_time": "0:44:47", "remaining_time": "0:47:16", "throughput": 10241.01, "total_tokens": 27521536}
{"current_steps": 28670, "total_steps": 58920, "loss": 0.0001, "lr": 1.2195907446773522e-06, "epoch": 2.43295994568907, "percentage": 48.66, "elapsed_time": "0:44:47", "remaining_time": "0:47:15", "throughput": 10241.46, "total_tokens": 27526784}
{"current_steps": 28675, "total_steps": 58920, "loss": 0.0016, "lr": 1.2193017449941874e-06, "epoch": 2.4333842498302785, "percentage": 48.67, "elapsed_time": "0:44:48", "remaining_time": "0:47:15", "throughput": 10241.73, "total_tokens": 27531392}
{"current_steps": 28680, "total_steps": 58920, "loss": 0.0041, "lr": 1.2190127260680863e-06, "epoch": 2.433808553971487, "percentage": 48.68, "elapsed_time": "0:44:48", "remaining_time": "0:47:14", "throughput": 10241.89, "total_tokens": 27535616}
{"current_steps": 28685, "total_steps": 58920, "loss": 0.0001, "lr": 1.2187236879244091e-06, "epoch": 2.4342328581126953, "percentage": 48.68, "elapsed_time": "0:44:48", "remaining_time": "0:47:14", "throughput": 10242.5, "total_tokens": 27541440}
{"current_steps": 28690, "total_steps": 58920, "loss": 0.0003, "lr": 1.218434630588518e-06, "epoch": 2.4346571622539037, "percentage": 48.69, "elapsed_time": "0:44:49", "remaining_time": "0:47:13", "throughput": 10242.83, "total_tokens": 27546304}
{"current_steps": 28695, "total_steps": 58920, "loss": 0.0123, "lr": 1.2181455540857768e-06, "epoch": 2.435081466395112, "percentage": 48.7, "elapsed_time": "0:44:49", "remaining_time": "0:47:13", "throughput": 10243.09, "total_tokens": 27550848}
{"current_steps": 28700, "total_steps": 58920, "loss": 0.0001, "lr": 1.2178564584415507e-06, "epoch": 2.4355057705363206, "percentage": 48.71, "elapsed_time": "0:44:50", "remaining_time": "0:47:12", "throughput": 10243.5, "total_tokens": 27555904}
{"current_steps": 28705, "total_steps": 58920, "loss": 0.0309, "lr": 1.217567343681207e-06, "epoch": 2.435930074677529, "percentage": 48.72, "elapsed_time": "0:44:50", "remaining_time": "0:47:11", "throughput": 10243.73, "total_tokens": 27560384}
{"current_steps": 28710, "total_steps": 58920, "loss": 0.0, "lr": 1.2172782098301145e-06, "epoch": 2.4363543788187374, "percentage": 48.73, "elapsed_time": "0:44:50", "remaining_time": "0:47:11", "throughput": 10244.08, "total_tokens": 27565312}
{"current_steps": 28715, "total_steps": 58920, "loss": 0.0177, "lr": 1.2169890569136439e-06, "epoch": 2.436778682959946, "percentage": 48.74, "elapsed_time": "0:44:51", "remaining_time": "0:47:10", "throughput": 10244.45, "total_tokens": 27570304}
{"current_steps": 28720, "total_steps": 58920, "loss": 0.0405, "lr": 1.2166998849571666e-06, "epoch": 2.4372029871011542, "percentage": 48.74, "elapsed_time": "0:44:51", "remaining_time": "0:47:10", "throughput": 10244.95, "total_tokens": 27575616}
{"current_steps": 28725, "total_steps": 58920, "loss": 0.0001, "lr": 1.2164106939860567e-06, "epoch": 2.4376272912423627, "percentage": 48.75, "elapsed_time": "0:44:52", "remaining_time": "0:47:09", "throughput": 10245.31, "total_tokens": 27580544}
{"current_steps": 28730, "total_steps": 58920, "loss": 0.0209, "lr": 1.2161214840256898e-06, "epoch": 2.438051595383571, "percentage": 48.76, "elapsed_time": "0:44:52", "remaining_time": "0:47:09", "throughput": 10245.65, "total_tokens": 27585344}
{"current_steps": 28735, "total_steps": 58920, "loss": 0.0001, "lr": 1.215832255101443e-06, "epoch": 2.4384758995247795, "percentage": 48.77, "elapsed_time": "0:44:52", "remaining_time": "0:47:08", "throughput": 10245.86, "total_tokens": 27589760}
{"current_steps": 28740, "total_steps": 58920, "loss": 0.0, "lr": 1.2155430072386953e-06, "epoch": 2.438900203665988, "percentage": 48.78, "elapsed_time": "0:44:53", "remaining_time": "0:47:08", "throughput": 10246.21, "total_tokens": 27594688}
{"current_steps": 28745, "total_steps": 58920, "loss": 0.0002, "lr": 1.2152537404628264e-06, "epoch": 2.4393245078071963, "percentage": 48.79, "elapsed_time": "0:44:53", "remaining_time": "0:47:07", "throughput": 10246.6, "total_tokens": 27599680}
{"current_steps": 28750, "total_steps": 58920, "loss": 0.0, "lr": 1.2149644547992197e-06, "epoch": 2.4397488119484048, "percentage": 48.79, "elapsed_time": "0:44:53", "remaining_time": "0:47:06", "throughput": 10246.83, "total_tokens": 27604160}
{"current_steps": 28755, "total_steps": 58920, "loss": 0.0245, "lr": 1.2146751502732578e-06, "epoch": 2.440173116089613, "percentage": 48.8, "elapsed_time": "0:44:54", "remaining_time": "0:47:06", "throughput": 10247.11, "total_tokens": 27608832}
{"current_steps": 28760, "total_steps": 58920, "loss": 0.0001, "lr": 1.2143858269103264e-06, "epoch": 2.4405974202308216, "percentage": 48.81, "elapsed_time": "0:44:54", "remaining_time": "0:47:05", "throughput": 10247.47, "total_tokens": 27613760}
{"current_steps": 28765, "total_steps": 58920, "loss": 0.0226, "lr": 1.2140964847358128e-06, "epoch": 2.44102172437203, "percentage": 48.82, "elapsed_time": "0:44:55", "remaining_time": "0:47:05", "throughput": 10247.73, "total_tokens": 27618368}
{"current_steps": 28770, "total_steps": 58920, "loss": 0.0571, "lr": 1.2138071237751057e-06, "epoch": 2.4414460285132384, "percentage": 48.83, "elapsed_time": "0:44:55", "remaining_time": "0:47:04", "throughput": 10248.0, "total_tokens": 27622976}
{"current_steps": 28775, "total_steps": 58920, "loss": 0.0002, "lr": 1.2135177440535955e-06, "epoch": 2.441870332654447, "percentage": 48.84, "elapsed_time": "0:44:55", "remaining_time": "0:47:04", "throughput": 10248.31, "total_tokens": 27627712}
{"current_steps": 28780, "total_steps": 58920, "loss": 0.0001, "lr": 1.2132283455966743e-06, "epoch": 2.4422946367956553, "percentage": 48.85, "elapsed_time": "0:44:56", "remaining_time": "0:47:03", "throughput": 10248.48, "total_tokens": 27632000}
{"current_steps": 28785, "total_steps": 58920, "loss": 0.0009, "lr": 1.2129389284297356e-06, "epoch": 2.4427189409368637, "percentage": 48.85, "elapsed_time": "0:44:56", "remaining_time": "0:47:03", "throughput": 10248.7, "total_tokens": 27636416}
{"current_steps": 28790, "total_steps": 58920, "loss": 0.0043, "lr": 1.2126494925781745e-06, "epoch": 2.443143245078072, "percentage": 48.86, "elapsed_time": "0:44:56", "remaining_time": "0:47:02", "throughput": 10248.92, "total_tokens": 27640832}
{"current_steps": 28795, "total_steps": 58920, "loss": 0.0009, "lr": 1.2123600380673884e-06, "epoch": 2.4435675492192805, "percentage": 48.87, "elapsed_time": "0:44:57", "remaining_time": "0:47:01", "throughput": 10249.39, "total_tokens": 27646144}
{"current_steps": 28800, "total_steps": 58920, "loss": 0.0001, "lr": 1.2120705649227756e-06, "epoch": 2.443991853360489, "percentage": 48.88, "elapsed_time": "0:44:57", "remaining_time": "0:47:01", "throughput": 10249.64, "total_tokens": 27650688}
{"current_steps": 28805, "total_steps": 58920, "loss": 0.0398, "lr": 1.2117810731697361e-06, "epoch": 2.4444161575016974, "percentage": 48.89, "elapsed_time": "0:44:58", "remaining_time": "0:47:00", "throughput": 10250.15, "total_tokens": 27656128}
{"current_steps": 28810, "total_steps": 58920, "loss": 0.0001, "lr": 1.2114915628336725e-06, "epoch": 2.444840461642906, "percentage": 48.9, "elapsed_time": "0:44:58", "remaining_time": "0:47:00", "throughput": 10250.55, "total_tokens": 27661248}
{"current_steps": 28815, "total_steps": 58920, "loss": 0.0178, "lr": 1.2112020339399878e-06, "epoch": 2.4452647657841142, "percentage": 48.91, "elapsed_time": "0:44:58", "remaining_time": "0:46:59", "throughput": 10250.81, "total_tokens": 27665792}
{"current_steps": 28820, "total_steps": 58920, "loss": 0.0036, "lr": 1.2109124865140868e-06, "epoch": 2.4456890699253226, "percentage": 48.91, "elapsed_time": "0:44:59", "remaining_time": "0:46:59", "throughput": 10251.27, "total_tokens": 27671104}
{"current_steps": 28825, "total_steps": 58920, "loss": 0.0046, "lr": 1.210622920581377e-06, "epoch": 2.446113374066531, "percentage": 48.92, "elapsed_time": "0:44:59", "remaining_time": "0:46:58", "throughput": 10251.64, "total_tokens": 27676032}
{"current_steps": 28830, "total_steps": 58920, "loss": 0.0606, "lr": 1.2103333361672662e-06, "epoch": 2.4465376782077395, "percentage": 48.93, "elapsed_time": "0:45:00", "remaining_time": "0:46:58", "throughput": 10251.87, "total_tokens": 27680512}
{"current_steps": 28835, "total_steps": 58920, "loss": 0.0191, "lr": 1.210043733297165e-06, "epoch": 2.446961982348948, "percentage": 48.94, "elapsed_time": "0:45:00", "remaining_time": "0:46:57", "throughput": 10252.12, "total_tokens": 27685056}
{"current_steps": 28840, "total_steps": 58920, "loss": 0.0001, "lr": 1.209754111996484e-06, "epoch": 2.4473862864901563, "percentage": 48.95, "elapsed_time": "0:45:00", "remaining_time": "0:46:56", "throughput": 10252.46, "total_tokens": 27689920}
{"current_steps": 28845, "total_steps": 58920, "loss": 0.0476, "lr": 1.2094644722906372e-06, "epoch": 2.4478105906313647, "percentage": 48.96, "elapsed_time": "0:45:01", "remaining_time": "0:46:56", "throughput": 10252.82, "total_tokens": 27694848}
{"current_steps": 28850, "total_steps": 58920, "loss": 0.0001, "lr": 1.209174814205039e-06, "epoch": 2.448234894772573, "percentage": 48.96, "elapsed_time": "0:45:01", "remaining_time": "0:46:55", "throughput": 10253.16, "total_tokens": 27699776}
{"current_steps": 28855, "total_steps": 58920, "loss": 0.0294, "lr": 1.2088851377651064e-06, "epoch": 2.4486591989137816, "percentage": 48.97, "elapsed_time": "0:45:01", "remaining_time": "0:46:55", "throughput": 10253.29, "total_tokens": 27703872}
{"current_steps": 28860, "total_steps": 58920, "loss": 0.0001, "lr": 1.2085954429962568e-06, "epoch": 2.44908350305499, "percentage": 48.98, "elapsed_time": "0:45:02", "remaining_time": "0:46:54", "throughput": 10253.52, "total_tokens": 27708352}
{"current_steps": 28865, "total_steps": 58920, "loss": 0.0001, "lr": 1.2083057299239106e-06, "epoch": 2.4495078071961984, "percentage": 48.99, "elapsed_time": "0:45:02", "remaining_time": "0:46:54", "throughput": 10253.77, "total_tokens": 27712896}
{"current_steps": 28870, "total_steps": 58920, "loss": 0.0164, "lr": 1.2080159985734884e-06, "epoch": 2.4499321113374064, "percentage": 49.0, "elapsed_time": "0:45:03", "remaining_time": "0:46:53", "throughput": 10254.02, "total_tokens": 27717440}
{"current_steps": 28875, "total_steps": 58920, "loss": 0.0023, "lr": 1.2077262489704137e-06, "epoch": 2.4503564154786153, "percentage": 49.01, "elapsed_time": "0:45:03", "remaining_time": "0:46:53", "throughput": 10254.38, "total_tokens": 27722368}
{"current_steps": 28880, "total_steps": 58920, "loss": 0.0007, "lr": 1.20743648114011e-06, "epoch": 2.4507807196198232, "percentage": 49.02, "elapsed_time": "0:45:03", "remaining_time": "0:46:52", "throughput": 10254.54, "total_tokens": 27726592}
{"current_steps": 28885, "total_steps": 58920, "loss": 0.0001, "lr": 1.2071466951080047e-06, "epoch": 2.451205023761032, "percentage": 49.02, "elapsed_time": "0:45:04", "remaining_time": "0:46:51", "throughput": 10254.88, "total_tokens": 27731456}
{"current_steps": 28890, "total_steps": 58920, "loss": 0.0001, "lr": 1.2068568908995246e-06, "epoch": 2.45162932790224, "percentage": 49.03, "elapsed_time": "0:45:04", "remaining_time": "0:46:51", "throughput": 10255.31, "total_tokens": 27736640}
{"current_steps": 28895, "total_steps": 58920, "loss": 0.0004, "lr": 1.2065670685400991e-06, "epoch": 2.452053632043449, "percentage": 49.04, "elapsed_time": "0:45:05", "remaining_time": "0:46:50", "throughput": 10255.72, "total_tokens": 27741760}
{"current_steps": 28900, "total_steps": 58920, "loss": 0.0288, "lr": 1.206277228055159e-06, "epoch": 2.452477936184657, "percentage": 49.05, "elapsed_time": "0:45:05", "remaining_time": "0:46:50", "throughput": 10256.16, "total_tokens": 27747008}
{"current_steps": 28905, "total_steps": 58920, "loss": 0.0001, "lr": 1.205987369470137e-06, "epoch": 2.452902240325866, "percentage": 49.06, "elapsed_time": "0:45:05", "remaining_time": "0:46:49", "throughput": 10256.41, "total_tokens": 27751552}
{"current_steps": 28910, "total_steps": 58920, "loss": 0.0, "lr": 1.2056974928104673e-06, "epoch": 2.4533265444670738, "percentage": 49.07, "elapsed_time": "0:45:06", "remaining_time": "0:46:49", "throughput": 10256.77, "total_tokens": 27756480}
{"current_steps": 28915, "total_steps": 58920, "loss": 0.0023, "lr": 1.2054075981015848e-06, "epoch": 2.4537508486082826, "percentage": 49.08, "elapsed_time": "0:45:06", "remaining_time": "0:46:48", "throughput": 10257.07, "total_tokens": 27761216}
{"current_steps": 28920, "total_steps": 58920, "loss": 0.0008, "lr": 1.2051176853689275e-06, "epoch": 2.4541751527494906, "percentage": 49.08, "elapsed_time": "0:45:06", "remaining_time": "0:46:48", "throughput": 10257.33, "total_tokens": 27765824}
{"current_steps": 28925, "total_steps": 58920, "loss": 0.0001, "lr": 1.204827754637934e-06, "epoch": 2.4545994568906995, "percentage": 49.09, "elapsed_time": "0:45:07", "remaining_time": "0:46:47", "throughput": 10257.67, "total_tokens": 27770688}
{"current_steps": 28930, "total_steps": 58920, "loss": 0.0009, "lr": 1.2045378059340443e-06, "epoch": 2.4550237610319074, "percentage": 49.1, "elapsed_time": "0:45:07", "remaining_time": "0:46:46", "throughput": 10258.21, "total_tokens": 27776256}
{"current_steps": 28935, "total_steps": 58920, "loss": 0.0775, "lr": 1.2042478392827007e-06, "epoch": 2.4554480651731163, "percentage": 49.11, "elapsed_time": "0:45:08", "remaining_time": "0:46:46", "throughput": 10258.56, "total_tokens": 27781248}
{"current_steps": 28940, "total_steps": 58920, "loss": 0.0, "lr": 1.2039578547093467e-06, "epoch": 2.4558723693143243, "percentage": 49.12, "elapsed_time": "0:45:08", "remaining_time": "0:46:45", "throughput": 10258.95, "total_tokens": 27786304}
{"current_steps": 28945, "total_steps": 58920, "loss": 0.0473, "lr": 1.203667852239427e-06, "epoch": 2.456296673455533, "percentage": 49.13, "elapsed_time": "0:45:08", "remaining_time": "0:46:45", "throughput": 10259.48, "total_tokens": 27791808}
{"current_steps": 28950, "total_steps": 58920, "loss": 0.0, "lr": 1.203377831898389e-06, "epoch": 2.456720977596741, "percentage": 49.13, "elapsed_time": "0:45:09", "remaining_time": "0:46:44", "throughput": 10259.79, "total_tokens": 27796608}
{"current_steps": 28955, "total_steps": 58920, "loss": 0.062, "lr": 1.2030877937116803e-06, "epoch": 2.45714528173795, "percentage": 49.14, "elapsed_time": "0:45:09", "remaining_time": "0:46:44", "throughput": 10260.25, "total_tokens": 27801920}
{"current_steps": 28960, "total_steps": 58920, "loss": 0.0003, "lr": 1.2027977377047514e-06, "epoch": 2.457569585879158, "percentage": 49.15, "elapsed_time": "0:45:10", "remaining_time": "0:46:43", "throughput": 10260.6, "total_tokens": 27806784}
{"current_steps": 28965, "total_steps": 58920, "loss": 0.086, "lr": 1.2025076639030528e-06, "epoch": 2.457993890020367, "percentage": 49.16, "elapsed_time": "0:45:10", "remaining_time": "0:46:43", "throughput": 10260.92, "total_tokens": 27811584}
{"current_steps": 28970, "total_steps": 58920, "loss": 0.0135, "lr": 1.202217572332038e-06, "epoch": 2.458418194161575, "percentage": 49.17, "elapsed_time": "0:45:10", "remaining_time": "0:46:42", "throughput": 10261.15, "total_tokens": 27816064}
{"current_steps": 28975, "total_steps": 58920, "loss": 0.0003, "lr": 1.2019274630171612e-06, "epoch": 2.4588424983027837, "percentage": 49.18, "elapsed_time": "0:45:11", "remaining_time": "0:46:41", "throughput": 10261.43, "total_tokens": 27820672}
{"current_steps": 28980, "total_steps": 58920, "loss": 0.0001, "lr": 1.2016373359838786e-06, "epoch": 2.4592668024439917, "percentage": 49.19, "elapsed_time": "0:45:11", "remaining_time": "0:46:41", "throughput": 10261.82, "total_tokens": 27825728}
{"current_steps": 28985, "total_steps": 58920, "loss": 0.0246, "lr": 1.2013471912576478e-06, "epoch": 2.4596911065852005, "percentage": 49.19, "elapsed_time": "0:45:11", "remaining_time": "0:46:40", "throughput": 10262.04, "total_tokens": 27830144}
{"current_steps": 28990, "total_steps": 58920, "loss": 0.0, "lr": 1.2010570288639279e-06, "epoch": 2.4601154107264085, "percentage": 49.2, "elapsed_time": "0:45:12", "remaining_time": "0:46:40", "throughput": 10262.27, "total_tokens": 27834688}
{"current_steps": 28995, "total_steps": 58920, "loss": 0.0003, "lr": 1.2007668488281797e-06, "epoch": 2.4605397148676174, "percentage": 49.21, "elapsed_time": "0:45:12", "remaining_time": "0:46:39", "throughput": 10262.67, "total_tokens": 27839744}
{"current_steps": 29000, "total_steps": 58920, "loss": 0.0146, "lr": 1.2004766511758655e-06, "epoch": 2.4609640190088253, "percentage": 49.22, "elapsed_time": "0:45:13", "remaining_time": "0:46:39", "throughput": 10263.1, "total_tokens": 27844928}
{"current_steps": 29005, "total_steps": 58920, "loss": 0.0001, "lr": 1.2001864359324488e-06, "epoch": 2.4613883231500338, "percentage": 49.23, "elapsed_time": "0:45:13", "remaining_time": "0:46:38", "throughput": 10263.31, "total_tokens": 27849344}
{"current_steps": 29010, "total_steps": 58920, "loss": 0.0001, "lr": 1.1998962031233952e-06, "epoch": 2.461812627291242, "percentage": 49.24, "elapsed_time": "0:45:13", "remaining_time": "0:46:38", "throughput": 10263.65, "total_tokens": 27854400}
{"current_steps": 29015, "total_steps": 58920, "loss": 0.0002, "lr": 1.1996059527741713e-06, "epoch": 2.4622369314324506, "percentage": 49.24, "elapsed_time": "0:45:14", "remaining_time": "0:46:37", "throughput": 10264.07, "total_tokens": 27859520}
{"current_steps": 29020, "total_steps": 58920, "loss": 0.0001, "lr": 1.199315684910246e-06, "epoch": 2.462661235573659, "percentage": 49.25, "elapsed_time": "0:45:14", "remaining_time": "0:46:36", "throughput": 10264.33, "total_tokens": 27864128}
{"current_steps": 29025, "total_steps": 58920, "loss": 0.0034, "lr": 1.199025399557089e-06, "epoch": 2.4630855397148674, "percentage": 49.26, "elapsed_time": "0:45:15", "remaining_time": "0:46:36", "throughput": 10264.93, "total_tokens": 27869888}
{"current_steps": 29030, "total_steps": 58920, "loss": 0.0, "lr": 1.1987350967401716e-06, "epoch": 2.463509843856076, "percentage": 49.27, "elapsed_time": "0:45:15", "remaining_time": "0:46:35", "throughput": 10265.5, "total_tokens": 27875584}
{"current_steps": 29035, "total_steps": 58920, "loss": 0.0, "lr": 1.1984447764849669e-06, "epoch": 2.4639341479972843, "percentage": 49.28, "elapsed_time": "0:45:15", "remaining_time": "0:46:35", "throughput": 10265.78, "total_tokens": 27880256}
{"current_steps": 29040, "total_steps": 58920, "loss": 0.0, "lr": 1.1981544388169494e-06, "epoch": 2.4643584521384927, "percentage": 49.29, "elapsed_time": "0:45:16", "remaining_time": "0:46:34", "throughput": 10266.05, "total_tokens": 27884864}
{"current_steps": 29045, "total_steps": 58920, "loss": 0.0689, "lr": 1.197864083761596e-06, "epoch": 2.464782756279701, "percentage": 49.3, "elapsed_time": "0:45:16", "remaining_time": "0:46:34", "throughput": 10266.17, "total_tokens": 27888960}
{"current_steps": 29050, "total_steps": 58920, "loss": 0.0001, "lr": 1.197573711344383e-06, "epoch": 2.4652070604209095, "percentage": 49.3, "elapsed_time": "0:45:16", "remaining_time": "0:46:33", "throughput": 10266.5, "total_tokens": 27893824}
{"current_steps": 29055, "total_steps": 58920, "loss": 0.0278, "lr": 1.1972833215907906e-06, "epoch": 2.465631364562118, "percentage": 49.31, "elapsed_time": "0:45:17", "remaining_time": "0:46:33", "throughput": 10266.96, "total_tokens": 27899136}
{"current_steps": 29060, "total_steps": 58920, "loss": 0.0001, "lr": 1.1969929145262987e-06, "epoch": 2.4660556687033264, "percentage": 49.32, "elapsed_time": "0:45:17", "remaining_time": "0:46:32", "throughput": 10267.46, "total_tokens": 27904576}
{"current_steps": 29065, "total_steps": 58920, "loss": 0.0362, "lr": 1.1967024901763896e-06, "epoch": 2.466479972844535, "percentage": 49.33, "elapsed_time": "0:45:18", "remaining_time": "0:46:32", "throughput": 10267.83, "total_tokens": 27909568}
{"current_steps": 29070, "total_steps": 58920, "loss": 0.0, "lr": 1.1964120485665475e-06, "epoch": 2.466904276985743, "percentage": 49.34, "elapsed_time": "0:45:18", "remaining_time": "0:46:31", "throughput": 10268.12, "total_tokens": 27914240}
{"current_steps": 29075, "total_steps": 58920, "loss": 0.0, "lr": 1.196121589722257e-06, "epoch": 2.4673285811269516, "percentage": 49.35, "elapsed_time": "0:45:18", "remaining_time": "0:46:30", "throughput": 10268.44, "total_tokens": 27919040}
{"current_steps": 29080, "total_steps": 58920, "loss": 0.0541, "lr": 1.1958311136690056e-06, "epoch": 2.46775288526816, "percentage": 49.36, "elapsed_time": "0:45:19", "remaining_time": "0:46:30", "throughput": 10268.61, "total_tokens": 27923328}
{"current_steps": 29085, "total_steps": 58920, "loss": 0.08, "lr": 1.195540620432281e-06, "epoch": 2.4681771894093685, "percentage": 49.36, "elapsed_time": "0:45:19", "remaining_time": "0:46:29", "throughput": 10268.8, "total_tokens": 27927680}
{"current_steps": 29090, "total_steps": 58920, "loss": 0.0315, "lr": 1.1952501100375728e-06, "epoch": 2.468601493550577, "percentage": 49.37, "elapsed_time": "0:45:20", "remaining_time": "0:46:29", "throughput": 10269.07, "total_tokens": 27932288}
{"current_steps": 29095, "total_steps": 58920, "loss": 0.0001, "lr": 1.194959582510372e-06, "epoch": 2.4690257976917853, "percentage": 49.38, "elapsed_time": "0:45:20", "remaining_time": "0:46:28", "throughput": 10269.23, "total_tokens": 27936512}
{"current_steps": 29100, "total_steps": 58920, "loss": 0.0002, "lr": 1.1946690378761721e-06, "epoch": 2.4694501018329937, "percentage": 49.39, "elapsed_time": "0:45:20", "remaining_time": "0:46:28", "throughput": 10269.53, "total_tokens": 27941248}
{"current_steps": 29105, "total_steps": 58920, "loss": 0.0001, "lr": 1.194378476160467e-06, "epoch": 2.469874405974202, "percentage": 49.4, "elapsed_time": "0:45:21", "remaining_time": "0:46:27", "throughput": 10269.94, "total_tokens": 27946368}
{"current_steps": 29110, "total_steps": 58920, "loss": 0.0004, "lr": 1.1940878973887523e-06, "epoch": 2.4702987101154106, "percentage": 49.41, "elapsed_time": "0:45:21", "remaining_time": "0:46:27", "throughput": 10270.3, "total_tokens": 27951296}
{"current_steps": 29115, "total_steps": 58920, "loss": 0.0001, "lr": 1.1937973015865252e-06, "epoch": 2.470723014256619, "percentage": 49.41, "elapsed_time": "0:45:21", "remaining_time": "0:46:26", "throughput": 10270.54, "total_tokens": 27955776}
{"current_steps": 29120, "total_steps": 58920, "loss": 0.0001, "lr": 1.193506688779285e-06, "epoch": 2.4711473183978274, "percentage": 49.42, "elapsed_time": "0:45:22", "remaining_time": "0:46:25", "throughput": 10270.73, "total_tokens": 27960320}
{"current_steps": 29125, "total_steps": 58920, "loss": 0.0006, "lr": 1.1932160589925313e-06, "epoch": 2.471571622539036, "percentage": 49.43, "elapsed_time": "0:45:22", "remaining_time": "0:46:25", "throughput": 10271.07, "total_tokens": 27965184}
{"current_steps": 29130, "total_steps": 58920, "loss": 0.0253, "lr": 1.192925412251766e-06, "epoch": 2.4719959266802443, "percentage": 49.44, "elapsed_time": "0:45:23", "remaining_time": "0:46:24", "throughput": 10271.29, "total_tokens": 27969664}
{"current_steps": 29135, "total_steps": 58920, "loss": 0.0002, "lr": 1.1926347485824924e-06, "epoch": 2.4724202308214527, "percentage": 49.45, "elapsed_time": "0:45:23", "remaining_time": "0:46:24", "throughput": 10271.62, "total_tokens": 27974464}
{"current_steps": 29140, "total_steps": 58920, "loss": 0.0002, "lr": 1.192344068010215e-06, "epoch": 2.472844534962661, "percentage": 49.46, "elapsed_time": "0:45:23", "remaining_time": "0:46:23", "throughput": 10271.91, "total_tokens": 27979200}
{"current_steps": 29145, "total_steps": 58920, "loss": 0.0691, "lr": 1.19205337056044e-06, "epoch": 2.4732688391038695, "percentage": 49.47, "elapsed_time": "0:45:24", "remaining_time": "0:46:23", "throughput": 10272.17, "total_tokens": 27983744}
{"current_steps": 29150, "total_steps": 58920, "loss": 0.0095, "lr": 1.1917626562586756e-06, "epoch": 2.473693143245078, "percentage": 49.47, "elapsed_time": "0:45:24", "remaining_time": "0:46:22", "throughput": 10272.88, "total_tokens": 27989952}
{"current_steps": 29155, "total_steps": 58920, "loss": 0.0001, "lr": 1.19147192513043e-06, "epoch": 2.4741174473862864, "percentage": 49.48, "elapsed_time": "0:45:25", "remaining_time": "0:46:22", "throughput": 10273.2, "total_tokens": 27994752}
{"current_steps": 29160, "total_steps": 58920, "loss": 0.0725, "lr": 1.1911811772012143e-06, "epoch": 2.474541751527495, "percentage": 49.49, "elapsed_time": "0:45:25", "remaining_time": "0:46:21", "throughput": 10273.59, "total_tokens": 27999808}
{"current_steps": 29165, "total_steps": 58920, "loss": 0.0, "lr": 1.1908904124965407e-06, "epoch": 2.474966055668703, "percentage": 49.5, "elapsed_time": "0:45:25", "remaining_time": "0:46:20", "throughput": 10273.89, "total_tokens": 28004544}
{"current_steps": 29170, "total_steps": 58920, "loss": 0.0001, "lr": 1.1905996310419227e-06, "epoch": 2.4753903598099116, "percentage": 49.51, "elapsed_time": "0:45:26", "remaining_time": "0:46:20", "throughput": 10274.09, "total_tokens": 28009088}
{"current_steps": 29175, "total_steps": 58920, "loss": 0.0159, "lr": 1.1903088328628751e-06, "epoch": 2.47581466395112, "percentage": 49.52, "elapsed_time": "0:45:26", "remaining_time": "0:46:19", "throughput": 10274.34, "total_tokens": 28013632}
{"current_steps": 29180, "total_steps": 58920, "loss": 0.0002, "lr": 1.1900180179849147e-06, "epoch": 2.4762389680923285, "percentage": 49.52, "elapsed_time": "0:45:26", "remaining_time": "0:46:19", "throughput": 10274.78, "total_tokens": 28018880}
{"current_steps": 29185, "total_steps": 58920, "loss": 0.0, "lr": 1.1897271864335593e-06, "epoch": 2.476663272233537, "percentage": 49.53, "elapsed_time": "0:45:27", "remaining_time": "0:46:18", "throughput": 10275.05, "total_tokens": 28023552}
{"current_steps": 29190, "total_steps": 58920, "loss": 0.0, "lr": 1.1894363382343277e-06, "epoch": 2.4770875763747453, "percentage": 49.54, "elapsed_time": "0:45:27", "remaining_time": "0:46:18", "throughput": 10275.3, "total_tokens": 28028096}
{"current_steps": 29195, "total_steps": 58920, "loss": 0.0398, "lr": 1.1891454734127419e-06, "epoch": 2.4775118805159537, "percentage": 49.55, "elapsed_time": "0:45:28", "remaining_time": "0:46:17", "throughput": 10275.61, "total_tokens": 28032896}
{"current_steps": 29200, "total_steps": 58920, "loss": 0.0002, "lr": 1.1888545919943236e-06, "epoch": 2.477936184657162, "percentage": 49.56, "elapsed_time": "0:45:28", "remaining_time": "0:46:17", "throughput": 10275.83, "total_tokens": 28037312}
{"current_steps": 29205, "total_steps": 58920, "loss": 0.0002, "lr": 1.1885636940045968e-06, "epoch": 2.4783604887983706, "percentage": 49.57, "elapsed_time": "0:45:28", "remaining_time": "0:46:16", "throughput": 10276.08, "total_tokens": 28041856}
{"current_steps": 29210, "total_steps": 58920, "loss": 0.0001, "lr": 1.1882727794690868e-06, "epoch": 2.478784792939579, "percentage": 49.58, "elapsed_time": "0:45:29", "remaining_time": "0:46:15", "throughput": 10276.38, "total_tokens": 28046656}
{"current_steps": 29215, "total_steps": 58920, "loss": 0.0214, "lr": 1.1879818484133198e-06, "epoch": 2.4792090970807874, "percentage": 49.58, "elapsed_time": "0:45:29", "remaining_time": "0:46:15", "throughput": 10276.67, "total_tokens": 28051456}
{"current_steps": 29220, "total_steps": 58920, "loss": 0.0, "lr": 1.1876909008628245e-06, "epoch": 2.479633401221996, "percentage": 49.59, "elapsed_time": "0:45:30", "remaining_time": "0:46:14", "throughput": 10277.21, "total_tokens": 28057088}
{"current_steps": 29225, "total_steps": 58920, "loss": 0.0284, "lr": 1.1873999368431303e-06, "epoch": 2.4800577053632042, "percentage": 49.6, "elapsed_time": "0:45:30", "remaining_time": "0:46:14", "throughput": 10277.51, "total_tokens": 28061824}
{"current_steps": 29230, "total_steps": 58920, "loss": 0.0, "lr": 1.1871089563797682e-06, "epoch": 2.4804820095044127, "percentage": 49.61, "elapsed_time": "0:45:30", "remaining_time": "0:46:13", "throughput": 10277.79, "total_tokens": 28066560}
{"current_steps": 29235, "total_steps": 58920, "loss": 0.0016, "lr": 1.1868179594982708e-06, "epoch": 2.480906313645621, "percentage": 49.62, "elapsed_time": "0:45:31", "remaining_time": "0:46:13", "throughput": 10277.94, "total_tokens": 28070784}
{"current_steps": 29240, "total_steps": 58920, "loss": 0.0001, "lr": 1.1865269462241718e-06, "epoch": 2.4813306177868295, "percentage": 49.63, "elapsed_time": "0:45:31", "remaining_time": "0:46:12", "throughput": 10278.28, "total_tokens": 28075648}
{"current_steps": 29245, "total_steps": 58920, "loss": 0.0, "lr": 1.1862359165830069e-06, "epoch": 2.481754921928038, "percentage": 49.64, "elapsed_time": "0:45:31", "remaining_time": "0:46:12", "throughput": 10278.67, "total_tokens": 28080768}
{"current_steps": 29250, "total_steps": 58920, "loss": 0.0337, "lr": 1.1859448706003127e-06, "epoch": 2.4821792260692463, "percentage": 49.64, "elapsed_time": "0:45:32", "remaining_time": "0:46:11", "throughput": 10278.9, "total_tokens": 28085312}
{"current_steps": 29255, "total_steps": 58920, "loss": 0.0003, "lr": 1.1856538083016275e-06, "epoch": 2.4826035302104548, "percentage": 49.65, "elapsed_time": "0:45:32", "remaining_time": "0:46:10", "throughput": 10279.07, "total_tokens": 28089600}
{"current_steps": 29260, "total_steps": 58920, "loss": 0.0041, "lr": 1.1853627297124906e-06, "epoch": 2.483027834351663, "percentage": 49.66, "elapsed_time": "0:45:33", "remaining_time": "0:46:10", "throughput": 10279.23, "total_tokens": 28093824}
{"current_steps": 29265, "total_steps": 58920, "loss": 0.0088, "lr": 1.1850716348584437e-06, "epoch": 2.4834521384928716, "percentage": 49.67, "elapsed_time": "0:45:33", "remaining_time": "0:46:09", "throughput": 10279.5, "total_tokens": 28098432}
{"current_steps": 29270, "total_steps": 58920, "loss": 0.0001, "lr": 1.184780523765029e-06, "epoch": 2.48387644263408, "percentage": 49.68, "elapsed_time": "0:45:33", "remaining_time": "0:46:09", "throughput": 10279.83, "total_tokens": 28103296}
{"current_steps": 29275, "total_steps": 58920, "loss": 0.0563, "lr": 1.1844893964577905e-06, "epoch": 2.4843007467752884, "percentage": 49.69, "elapsed_time": "0:45:34", "remaining_time": "0:46:08", "throughput": 10280.12, "total_tokens": 28108032}
{"current_steps": 29280, "total_steps": 58920, "loss": 0.0231, "lr": 1.1841982529622733e-06, "epoch": 2.484725050916497, "percentage": 49.69, "elapsed_time": "0:45:34", "remaining_time": "0:46:08", "throughput": 10280.58, "total_tokens": 28113344}
{"current_steps": 29285, "total_steps": 58920, "loss": 0.0001, "lr": 1.1839070933040247e-06, "epoch": 2.4851493550577053, "percentage": 49.7, "elapsed_time": "0:45:34", "remaining_time": "0:46:07", "throughput": 10280.79, "total_tokens": 28117760}
{"current_steps": 29290, "total_steps": 58920, "loss": 0.0258, "lr": 1.1836159175085927e-06, "epoch": 2.4855736591989137, "percentage": 49.71, "elapsed_time": "0:45:35", "remaining_time": "0:46:07", "throughput": 10280.96, "total_tokens": 28122048}
{"current_steps": 29295, "total_steps": 58920, "loss": 0.0002, "lr": 1.183324725601527e-06, "epoch": 2.485997963340122, "percentage": 49.72, "elapsed_time": "0:45:35", "remaining_time": "0:46:06", "throughput": 10281.21, "total_tokens": 28126656}
{"current_steps": 29300, "total_steps": 58920, "loss": 0.0001, "lr": 1.1830335176083783e-06, "epoch": 2.4864222674813306, "percentage": 49.73, "elapsed_time": "0:45:36", "remaining_time": "0:46:05", "throughput": 10281.43, "total_tokens": 28131136}
{"current_steps": 29305, "total_steps": 58920, "loss": 0.0007, "lr": 1.1827422935546993e-06, "epoch": 2.486846571622539, "percentage": 49.74, "elapsed_time": "0:45:36", "remaining_time": "0:46:05", "throughput": 10281.83, "total_tokens": 28136192}
{"current_steps": 29310, "total_steps": 58920, "loss": 0.0249, "lr": 1.1824510534660436e-06, "epoch": 2.4872708757637474, "percentage": 49.75, "elapsed_time": "0:45:36", "remaining_time": "0:46:04", "throughput": 10282.28, "total_tokens": 28141440}
{"current_steps": 29315, "total_steps": 58920, "loss": 0.0501, "lr": 1.182159797367967e-06, "epoch": 2.487695179904956, "percentage": 49.75, "elapsed_time": "0:45:37", "remaining_time": "0:46:04", "throughput": 10282.52, "total_tokens": 28145984}
{"current_steps": 29320, "total_steps": 58920, "loss": 0.0006, "lr": 1.1818685252860258e-06, "epoch": 2.4881194840461642, "percentage": 49.76, "elapsed_time": "0:45:37", "remaining_time": "0:46:03", "throughput": 10282.82, "total_tokens": 28150848}
{"current_steps": 29325, "total_steps": 58920, "loss": 0.0003, "lr": 1.1815772372457782e-06, "epoch": 2.4885437881873727, "percentage": 49.77, "elapsed_time": "0:45:38", "remaining_time": "0:46:03", "throughput": 10283.22, "total_tokens": 28156032}
{"current_steps": 29330, "total_steps": 58920, "loss": 0.0205, "lr": 1.1812859332727835e-06, "epoch": 2.488968092328581, "percentage": 49.78, "elapsed_time": "0:45:38", "remaining_time": "0:46:02", "throughput": 10283.47, "total_tokens": 28160576}
{"current_steps": 29335, "total_steps": 58920, "loss": 0.0193, "lr": 1.180994613392603e-06, "epoch": 2.4893923964697895, "percentage": 49.79, "elapsed_time": "0:45:38", "remaining_time": "0:46:02", "throughput": 10284.01, "total_tokens": 28166208}
{"current_steps": 29340, "total_steps": 58920, "loss": 0.0226, "lr": 1.180703277630798e-06, "epoch": 2.489816700610998, "percentage": 49.8, "elapsed_time": "0:45:39", "remaining_time": "0:46:01", "throughput": 10284.41, "total_tokens": 28171264}
{"current_steps": 29345, "total_steps": 58920, "loss": 0.0294, "lr": 1.1804119260129336e-06, "epoch": 2.4902410047522063, "percentage": 49.8, "elapsed_time": "0:45:39", "remaining_time": "0:46:01", "throughput": 10284.64, "total_tokens": 28175808}
{"current_steps": 29350, "total_steps": 58920, "loss": 0.0003, "lr": 1.1801205585645735e-06, "epoch": 2.4906653088934148, "percentage": 49.81, "elapsed_time": "0:45:39", "remaining_time": "0:46:00", "throughput": 10284.98, "total_tokens": 28180672}
{"current_steps": 29355, "total_steps": 58920, "loss": 0.0002, "lr": 1.1798291753112848e-06, "epoch": 2.491089613034623, "percentage": 49.82, "elapsed_time": "0:45:40", "remaining_time": "0:45:59", "throughput": 10285.26, "total_tokens": 28185344}
{"current_steps": 29360, "total_steps": 58920, "loss": 0.0001, "lr": 1.1795377762786354e-06, "epoch": 2.4915139171758316, "percentage": 49.83, "elapsed_time": "0:45:40", "remaining_time": "0:45:59", "throughput": 10285.55, "total_tokens": 28190016}
{"current_steps": 29365, "total_steps": 58920, "loss": 0.0002, "lr": 1.1792463614921943e-06, "epoch": 2.49193822131704, "percentage": 49.84, "elapsed_time": "0:45:41", "remaining_time": "0:45:58", "throughput": 10285.79, "total_tokens": 28194560}
{"current_steps": 29370, "total_steps": 58920, "loss": 0.0003, "lr": 1.1789549309775322e-06, "epoch": 2.4923625254582484, "percentage": 49.85, "elapsed_time": "0:45:41", "remaining_time": "0:45:58", "throughput": 10286.0, "total_tokens": 28198976}
{"current_steps": 29375, "total_steps": 58920, "loss": 0.0163, "lr": 1.1786634847602207e-06, "epoch": 2.492786829599457, "percentage": 49.86, "elapsed_time": "0:45:41", "remaining_time": "0:45:57", "throughput": 10286.24, "total_tokens": 28203520}
{"current_steps": 29380, "total_steps": 58920, "loss": 0.0001, "lr": 1.1783720228658339e-06, "epoch": 2.4932111337406653, "percentage": 49.86, "elapsed_time": "0:45:42", "remaining_time": "0:45:57", "throughput": 10286.57, "total_tokens": 28208384}
{"current_steps": 29385, "total_steps": 58920, "loss": 0.0001, "lr": 1.1780805453199458e-06, "epoch": 2.4936354378818737, "percentage": 49.87, "elapsed_time": "0:45:42", "remaining_time": "0:45:56", "throughput": 10286.89, "total_tokens": 28213184}
{"current_steps": 29390, "total_steps": 58920, "loss": 0.0001, "lr": 1.177789052148133e-06, "epoch": 2.494059742023082, "percentage": 49.88, "elapsed_time": "0:45:43", "remaining_time": "0:45:56", "throughput": 10287.34, "total_tokens": 28218496}
{"current_steps": 29395, "total_steps": 58920, "loss": 0.0001, "lr": 1.1774975433759726e-06, "epoch": 2.4944840461642905, "percentage": 49.89, "elapsed_time": "0:45:43", "remaining_time": "0:45:55", "throughput": 10287.52, "total_tokens": 28222848}
{"current_steps": 29400, "total_steps": 58920, "loss": 0.0002, "lr": 1.1772060190290438e-06, "epoch": 2.494908350305499, "percentage": 49.9, "elapsed_time": "0:45:43", "remaining_time": "0:45:54", "throughput": 10287.78, "total_tokens": 28227456}
{"current_steps": 29405, "total_steps": 58920, "loss": 0.0001, "lr": 1.1769144791329264e-06, "epoch": 2.4953326544467074, "percentage": 49.91, "elapsed_time": "0:45:44", "remaining_time": "0:45:54", "throughput": 10288.03, "total_tokens": 28232064}
{"current_steps": 29410, "total_steps": 58920, "loss": 0.0001, "lr": 1.1766229237132023e-06, "epoch": 2.495756958587916, "percentage": 49.92, "elapsed_time": "0:45:44", "remaining_time": "0:45:53", "throughput": 10288.42, "total_tokens": 28237120}
{"current_steps": 29415, "total_steps": 58920, "loss": 0.0633, "lr": 1.1763313527954544e-06, "epoch": 2.496181262729124, "percentage": 49.92, "elapsed_time": "0:45:44", "remaining_time": "0:45:53", "throughput": 10288.86, "total_tokens": 28242368}
{"current_steps": 29420, "total_steps": 58920, "loss": 0.0223, "lr": 1.1760397664052672e-06, "epoch": 2.4966055668703326, "percentage": 49.93, "elapsed_time": "0:45:45", "remaining_time": "0:45:52", "throughput": 10289.17, "total_tokens": 28247104}
{"current_steps": 29425, "total_steps": 58920, "loss": 0.0, "lr": 1.1757481645682257e-06, "epoch": 2.497029871011541, "percentage": 49.94, "elapsed_time": "0:45:45", "remaining_time": "0:45:52", "throughput": 10289.42, "total_tokens": 28251840}
{"current_steps": 29430, "total_steps": 58920, "loss": 0.0001, "lr": 1.1754565473099173e-06, "epoch": 2.4974541751527495, "percentage": 49.95, "elapsed_time": "0:45:46", "remaining_time": "0:45:51", "throughput": 10289.56, "total_tokens": 28256064}
{"current_steps": 29435, "total_steps": 58920, "loss": 0.0251, "lr": 1.1751649146559304e-06, "epoch": 2.497878479293958, "percentage": 49.96, "elapsed_time": "0:45:46", "remaining_time": "0:45:51", "throughput": 10289.79, "total_tokens": 28260544}
{"current_steps": 29440, "total_steps": 58920, "loss": 0.0091, "lr": 1.1748732666318548e-06, "epoch": 2.4983027834351663, "percentage": 49.97, "elapsed_time": "0:45:46", "remaining_time": "0:45:50", "throughput": 10290.04, "total_tokens": 28265152}
{"current_steps": 29445, "total_steps": 58920, "loss": 0.0339, "lr": 1.1745816032632814e-06, "epoch": 2.4987270875763747, "percentage": 49.97, "elapsed_time": "0:45:47", "remaining_time": "0:45:50", "throughput": 10290.31, "total_tokens": 28269824}
{"current_steps": 29450, "total_steps": 58920, "loss": 0.0001, "lr": 1.1742899245758024e-06, "epoch": 2.499151391717583, "percentage": 49.98, "elapsed_time": "0:45:47", "remaining_time": "0:45:49", "throughput": 10290.76, "total_tokens": 28275072}
{"current_steps": 29455, "total_steps": 58920, "loss": 0.0224, "lr": 1.1739982305950123e-06, "epoch": 2.4995756958587916, "percentage": 49.99, "elapsed_time": "0:45:47", "remaining_time": "0:45:48", "throughput": 10291.08, "total_tokens": 28279872}
{"current_steps": 29460, "total_steps": 58920, "loss": 0.0001, "lr": 1.1737065213465052e-06, "epoch": 2.5, "percentage": 50.0, "elapsed_time": "0:45:48", "remaining_time": "0:45:48", "throughput": 10291.38, "total_tokens": 28284608}
{"current_steps": 29460, "total_steps": 58920, "eval_loss": 0.11146481335163116, "epoch": 2.5, "percentage": 50.0, "elapsed_time": "0:46:04", "remaining_time": "0:46:04", "throughput": 10230.33, "total_tokens": 28284608}
{"current_steps": 29465, "total_steps": 58920, "loss": 0.0001, "lr": 1.1734147968558783e-06, "epoch": 2.5004243041412084, "percentage": 50.01, "elapsed_time": "0:46:43", "remaining_time": "0:46:42", "throughput": 10090.88, "total_tokens": 28289088}
{"current_steps": 29470, "total_steps": 58920, "loss": 0.0017, "lr": 1.173123057148729e-06, "epoch": 2.500848608282417, "percentage": 50.02, "elapsed_time": "0:46:43", "remaining_time": "0:46:41", "throughput": 10091.28, "total_tokens": 28294144}
{"current_steps": 29475, "total_steps": 58920, "loss": 0.0001, "lr": 1.1728313022506564e-06, "epoch": 2.5012729124236253, "percentage": 50.03, "elapsed_time": "0:46:44", "remaining_time": "0:46:41", "throughput": 10091.42, "total_tokens": 28298304}
{"current_steps": 29480, "total_steps": 58920, "loss": 0.0001, "lr": 1.172539532187261e-06, "epoch": 2.5016972165648337, "percentage": 50.03, "elapsed_time": "0:46:44", "remaining_time": "0:46:40", "throughput": 10091.79, "total_tokens": 28303232}
{"current_steps": 29485, "total_steps": 58920, "loss": 0.0003, "lr": 1.1722477469841447e-06, "epoch": 2.502121520706042, "percentage": 50.04, "elapsed_time": "0:46:44", "remaining_time": "0:46:40", "throughput": 10092.14, "total_tokens": 28308096}
{"current_steps": 29490, "total_steps": 58920, "loss": 0.0457, "lr": 1.1719559466669106e-06, "epoch": 2.5025458248472505, "percentage": 50.05, "elapsed_time": "0:46:45", "remaining_time": "0:46:39", "throughput": 10092.5, "total_tokens": 28312960}
{"current_steps": 29495, "total_steps": 58920, "loss": 0.0297, "lr": 1.171664131261163e-06, "epoch": 2.502970128988459, "percentage": 50.06, "elapsed_time": "0:46:45", "remaining_time": "0:46:39", "throughput": 10092.86, "total_tokens": 28317824}
{"current_steps": 29500, "total_steps": 58920, "loss": 0.0405, "lr": 1.1713723007925073e-06, "epoch": 2.5033944331296674, "percentage": 50.07, "elapsed_time": "0:46:46", "remaining_time": "0:46:38", "throughput": 10093.07, "total_tokens": 28322176}
{"current_steps": 29505, "total_steps": 58920, "loss": 0.033, "lr": 1.1710804552865515e-06, "epoch": 2.503818737270876, "percentage": 50.08, "elapsed_time": "0:46:46", "remaining_time": "0:46:37", "throughput": 10093.35, "total_tokens": 28326784}
{"current_steps": 29510, "total_steps": 58920, "loss": 0.0001, "lr": 1.170788594768903e-06, "epoch": 2.504243041412084, "percentage": 50.08, "elapsed_time": "0:46:46", "remaining_time": "0:46:37", "throughput": 10093.71, "total_tokens": 28331712}
{"current_steps": 29515, "total_steps": 58920, "loss": 0.0003, "lr": 1.1704967192651723e-06, "epoch": 2.5046673455532926, "percentage": 50.09, "elapsed_time": "0:46:47", "remaining_time": "0:46:36", "throughput": 10094.17, "total_tokens": 28336960}
{"current_steps": 29520, "total_steps": 58920, "loss": 0.0008, "lr": 1.1702048288009698e-06, "epoch": 2.505091649694501, "percentage": 50.1, "elapsed_time": "0:46:47", "remaining_time": "0:46:36", "throughput": 10094.47, "total_tokens": 28341632}
{"current_steps": 29525, "total_steps": 58920, "loss": 0.0002, "lr": 1.169912923401908e-06, "epoch": 2.5055159538357095, "percentage": 50.11, "elapsed_time": "0:46:48", "remaining_time": "0:46:35", "throughput": 10094.84, "total_tokens": 28346496}
{"current_steps": 29530, "total_steps": 58920, "loss": 0.0001, "lr": 1.169621003093601e-06, "epoch": 2.505940257976918, "percentage": 50.12, "elapsed_time": "0:46:48", "remaining_time": "0:46:35", "throughput": 10095.08, "total_tokens": 28350976}
{"current_steps": 29535, "total_steps": 58920, "loss": 0.0001, "lr": 1.1693290679016632e-06, "epoch": 2.5063645621181263, "percentage": 50.13, "elapsed_time": "0:46:48", "remaining_time": "0:46:34", "throughput": 10095.43, "total_tokens": 28355840}
{"current_steps": 29540, "total_steps": 58920, "loss": 0.0, "lr": 1.169037117851711e-06, "epoch": 2.5067888662593347, "percentage": 50.14, "elapsed_time": "0:46:49", "remaining_time": "0:46:33", "throughput": 10095.67, "total_tokens": 28360320}
{"current_steps": 29545, "total_steps": 58920, "loss": 0.0001, "lr": 1.1687451529693623e-06, "epoch": 2.507213170400543, "percentage": 50.14, "elapsed_time": "0:46:49", "remaining_time": "0:46:33", "throughput": 10096.09, "total_tokens": 28365440}
{"current_steps": 29550, "total_steps": 58920, "loss": 0.0001, "lr": 1.1684531732802353e-06, "epoch": 2.5076374745417516, "percentage": 50.15, "elapsed_time": "0:46:49", "remaining_time": "0:46:32", "throughput": 10096.42, "total_tokens": 28370240}
{"current_steps": 29555, "total_steps": 58920, "loss": 0.0001, "lr": 1.1681611788099506e-06, "epoch": 2.50806177868296, "percentage": 50.16, "elapsed_time": "0:46:50", "remaining_time": "0:46:32", "throughput": 10096.84, "total_tokens": 28375360}
{"current_steps": 29560, "total_steps": 58920, "loss": 0.0, "lr": 1.1678691695841295e-06, "epoch": 2.5084860828241684, "percentage": 50.17, "elapsed_time": "0:46:50", "remaining_time": "0:46:31", "throughput": 10097.15, "total_tokens": 28380096}
{"current_steps": 29565, "total_steps": 58920, "loss": 0.0, "lr": 1.1675771456283952e-06, "epoch": 2.508910386965377, "percentage": 50.18, "elapsed_time": "0:46:51", "remaining_time": "0:46:31", "throughput": 10097.46, "total_tokens": 28384896}
{"current_steps": 29570, "total_steps": 58920, "loss": 0.0018, "lr": 1.1672851069683713e-06, "epoch": 2.5093346911065852, "percentage": 50.19, "elapsed_time": "0:46:51", "remaining_time": "0:46:30", "throughput": 10097.77, "total_tokens": 28389632}
{"current_steps": 29575, "total_steps": 58920, "loss": 0.0, "lr": 1.1669930536296833e-06, "epoch": 2.5097589952477937, "percentage": 50.2, "elapsed_time": "0:46:51", "remaining_time": "0:46:29", "throughput": 10098.01, "total_tokens": 28394112}
{"current_steps": 29580, "total_steps": 58920, "loss": 0.0007, "lr": 1.1667009856379578e-06, "epoch": 2.510183299389002, "percentage": 50.2, "elapsed_time": "0:46:52", "remaining_time": "0:46:29", "throughput": 10098.29, "total_tokens": 28398720}
{"current_steps": 29585, "total_steps": 58920, "loss": 0.0278, "lr": 1.1664089030188225e-06, "epoch": 2.5106076035302105, "percentage": 50.21, "elapsed_time": "0:46:52", "remaining_time": "0:46:28", "throughput": 10098.58, "total_tokens": 28403392}
{"current_steps": 29590, "total_steps": 58920, "loss": 0.0299, "lr": 1.1661168057979067e-06, "epoch": 2.511031907671419, "percentage": 50.22, "elapsed_time": "0:46:52", "remaining_time": "0:46:28", "throughput": 10098.87, "total_tokens": 28408000}
{"current_steps": 29595, "total_steps": 58920, "loss": 0.0362, "lr": 1.1658246940008412e-06, "epoch": 2.5114562118126273, "percentage": 50.23, "elapsed_time": "0:46:53", "remaining_time": "0:46:27", "throughput": 10099.15, "total_tokens": 28412608}
{"current_steps": 29600, "total_steps": 58920, "loss": 0.0, "lr": 1.1655325676532572e-06, "epoch": 2.5118805159538358, "percentage": 50.24, "elapsed_time": "0:46:53", "remaining_time": "0:46:27", "throughput": 10099.35, "total_tokens": 28416960}
{"current_steps": 29605, "total_steps": 58920, "loss": 0.0, "lr": 1.1652404267807882e-06, "epoch": 2.512304820095044, "percentage": 50.25, "elapsed_time": "0:46:54", "remaining_time": "0:46:26", "throughput": 10099.65, "total_tokens": 28421632}
{"current_steps": 29610, "total_steps": 58920, "loss": 0.0251, "lr": 1.1649482714090686e-06, "epoch": 2.5127291242362526, "percentage": 50.25, "elapsed_time": "0:46:54", "remaining_time": "0:46:25", "throughput": 10099.94, "total_tokens": 28426304}
{"current_steps": 29615, "total_steps": 58920, "loss": 0.0, "lr": 1.1646561015637336e-06, "epoch": 2.513153428377461, "percentage": 50.26, "elapsed_time": "0:46:54", "remaining_time": "0:46:25", "throughput": 10100.39, "total_tokens": 28431552}
{"current_steps": 29620, "total_steps": 58920, "loss": 0.0486, "lr": 1.1643639172704198e-06, "epoch": 2.5135777325186694, "percentage": 50.27, "elapsed_time": "0:46:55", "remaining_time": "0:46:24", "throughput": 10100.68, "total_tokens": 28436160}
{"current_steps": 29625, "total_steps": 58920, "loss": 0.0001, "lr": 1.164071718554766e-06, "epoch": 2.514002036659878, "percentage": 50.28, "elapsed_time": "0:46:55", "remaining_time": "0:46:24", "throughput": 10101.02, "total_tokens": 28441024}
{"current_steps": 29630, "total_steps": 58920, "loss": 0.0579, "lr": 1.1637795054424113e-06, "epoch": 2.5144263408010863, "percentage": 50.29, "elapsed_time": "0:46:56", "remaining_time": "0:46:23", "throughput": 10101.3, "total_tokens": 28445632}
{"current_steps": 29635, "total_steps": 58920, "loss": 0.0003, "lr": 1.1634872779589964e-06, "epoch": 2.5148506449422947, "percentage": 50.3, "elapsed_time": "0:46:56", "remaining_time": "0:46:23", "throughput": 10101.6, "total_tokens": 28450304}
{"current_steps": 29640, "total_steps": 58920, "loss": 0.0001, "lr": 1.163195036130163e-06, "epoch": 2.515274949083503, "percentage": 50.31, "elapsed_time": "0:46:56", "remaining_time": "0:46:22", "throughput": 10102.14, "total_tokens": 28455872}
{"current_steps": 29645, "total_steps": 58920, "loss": 0.0001, "lr": 1.1629027799815542e-06, "epoch": 2.5156992532247116, "percentage": 50.31, "elapsed_time": "0:46:57", "remaining_time": "0:46:22", "throughput": 10102.72, "total_tokens": 28461632}
{"current_steps": 29650, "total_steps": 58920, "loss": 0.0001, "lr": 1.1626105095388148e-06, "epoch": 2.51612355736592, "percentage": 50.32, "elapsed_time": "0:46:57", "remaining_time": "0:46:21", "throughput": 10102.93, "total_tokens": 28465984}
{"current_steps": 29655, "total_steps": 58920, "loss": 0.0001, "lr": 1.1623182248275903e-06, "epoch": 2.5165478615071284, "percentage": 50.33, "elapsed_time": "0:46:57", "remaining_time": "0:46:20", "throughput": 10103.08, "total_tokens": 28470208}
{"current_steps": 29660, "total_steps": 58920, "loss": 0.0001, "lr": 1.1620259258735277e-06, "epoch": 2.516972165648337, "percentage": 50.34, "elapsed_time": "0:46:58", "remaining_time": "0:46:20", "throughput": 10103.38, "total_tokens": 28474880}
{"current_steps": 29665, "total_steps": 58920, "loss": 0.0, "lr": 1.161733612702275e-06, "epoch": 2.5173964697895452, "percentage": 50.35, "elapsed_time": "0:46:58", "remaining_time": "0:46:19", "throughput": 10103.67, "total_tokens": 28479552}
{"current_steps": 29670, "total_steps": 58920, "loss": 0.0001, "lr": 1.1614412853394819e-06, "epoch": 2.5178207739307537, "percentage": 50.36, "elapsed_time": "0:46:59", "remaining_time": "0:46:19", "throughput": 10103.86, "total_tokens": 28483904}
{"current_steps": 29675, "total_steps": 58920, "loss": 0.0238, "lr": 1.1611489438107985e-06, "epoch": 2.518245078071962, "percentage": 50.36, "elapsed_time": "0:46:59", "remaining_time": "0:46:18", "throughput": 10104.17, "total_tokens": 28488640}
{"current_steps": 29680, "total_steps": 58920, "loss": 0.0288, "lr": 1.1608565881418774e-06, "epoch": 2.5186693822131705, "percentage": 50.37, "elapsed_time": "0:46:59", "remaining_time": "0:46:18", "throughput": 10104.56, "total_tokens": 28493696}
{"current_steps": 29685, "total_steps": 58920, "loss": 0.0001, "lr": 1.1605642183583716e-06, "epoch": 2.519093686354379, "percentage": 50.38, "elapsed_time": "0:47:00", "remaining_time": "0:46:17", "throughput": 10104.81, "total_tokens": 28498176}
{"current_steps": 29690, "total_steps": 58920, "loss": 0.0292, "lr": 1.160271834485935e-06, "epoch": 2.5195179904955873, "percentage": 50.39, "elapsed_time": "0:47:00", "remaining_time": "0:46:16", "throughput": 10105.07, "total_tokens": 28502720}
{"current_steps": 29695, "total_steps": 58920, "loss": 0.0423, "lr": 1.1599794365502238e-06, "epoch": 2.5199422946367958, "percentage": 50.4, "elapsed_time": "0:47:01", "remaining_time": "0:46:16", "throughput": 10105.46, "total_tokens": 28507776}
{"current_steps": 29700, "total_steps": 58920, "loss": 0.0492, "lr": 1.1596870245768947e-06, "epoch": 2.520366598778004, "percentage": 50.41, "elapsed_time": "0:47:01", "remaining_time": "0:46:15", "throughput": 10105.68, "total_tokens": 28512192}
{"current_steps": 29705, "total_steps": 58920, "loss": 0.0001, "lr": 1.1593945985916055e-06, "epoch": 2.5207909029192126, "percentage": 50.42, "elapsed_time": "0:47:01", "remaining_time": "0:46:15", "throughput": 10106.18, "total_tokens": 28517696}
{"current_steps": 29710, "total_steps": 58920, "loss": 0.0165, "lr": 1.1591021586200159e-06, "epoch": 2.521215207060421, "percentage": 50.42, "elapsed_time": "0:47:02", "remaining_time": "0:46:14", "throughput": 10106.54, "total_tokens": 28522624}
{"current_steps": 29715, "total_steps": 58920, "loss": 0.0002, "lr": 1.1588097046877862e-06, "epoch": 2.5216395112016294, "percentage": 50.43, "elapsed_time": "0:47:02", "remaining_time": "0:46:14", "throughput": 10106.79, "total_tokens": 28527168}
{"current_steps": 29720, "total_steps": 58920, "loss": 0.0001, "lr": 1.1585172368205785e-06, "epoch": 2.522063815342838, "percentage": 50.44, "elapsed_time": "0:47:02", "remaining_time": "0:46:13", "throughput": 10107.09, "total_tokens": 28531840}
{"current_steps": 29725, "total_steps": 58920, "loss": 0.0002, "lr": 1.1582247550440553e-06, "epoch": 2.5224881194840463, "percentage": 50.45, "elapsed_time": "0:47:03", "remaining_time": "0:46:13", "throughput": 10107.59, "total_tokens": 28537344}
{"current_steps": 29730, "total_steps": 58920, "loss": 0.0323, "lr": 1.1579322593838817e-06, "epoch": 2.5229124236252547, "percentage": 50.46, "elapsed_time": "0:47:03", "remaining_time": "0:46:12", "throughput": 10108.08, "total_tokens": 28542720}
{"current_steps": 29735, "total_steps": 58920, "loss": 0.0641, "lr": 1.157639749865722e-06, "epoch": 2.523336727766463, "percentage": 50.47, "elapsed_time": "0:47:04", "remaining_time": "0:46:11", "throughput": 10108.3, "total_tokens": 28547264}
{"current_steps": 29740, "total_steps": 58920, "loss": 0.0245, "lr": 1.1573472265152433e-06, "epoch": 2.5237610319076715, "percentage": 50.48, "elapsed_time": "0:47:04", "remaining_time": "0:46:11", "throughput": 10108.65, "total_tokens": 28552128}
{"current_steps": 29745, "total_steps": 58920, "loss": 0.0878, "lr": 1.1570546893581138e-06, "epoch": 2.52418533604888, "percentage": 50.48, "elapsed_time": "0:47:04", "remaining_time": "0:46:10", "throughput": 10108.95, "total_tokens": 28556864}
{"current_steps": 29750, "total_steps": 58920, "loss": 0.017, "lr": 1.1567621384200023e-06, "epoch": 2.5246096401900884, "percentage": 50.49, "elapsed_time": "0:47:05", "remaining_time": "0:46:10", "throughput": 10109.3, "total_tokens": 28561728}
{"current_steps": 29755, "total_steps": 58920, "loss": 0.001, "lr": 1.1564695737265795e-06, "epoch": 2.525033944331297, "percentage": 50.5, "elapsed_time": "0:47:05", "remaining_time": "0:46:09", "throughput": 10109.8, "total_tokens": 28567168}
{"current_steps": 29760, "total_steps": 58920, "loss": 0.0003, "lr": 1.1561769953035164e-06, "epoch": 2.525458248472505, "percentage": 50.51, "elapsed_time": "0:47:06", "remaining_time": "0:46:09", "throughput": 10110.08, "total_tokens": 28571776}
{"current_steps": 29765, "total_steps": 58920, "loss": 0.0016, "lr": 1.1558844031764855e-06, "epoch": 2.5258825526137136, "percentage": 50.52, "elapsed_time": "0:47:06", "remaining_time": "0:46:08", "throughput": 10110.34, "total_tokens": 28576320}
{"current_steps": 29770, "total_steps": 58920, "loss": 0.0374, "lr": 1.1555917973711614e-06, "epoch": 2.526306856754922, "percentage": 50.53, "elapsed_time": "0:47:06", "remaining_time": "0:46:07", "throughput": 10110.76, "total_tokens": 28581440}
{"current_steps": 29775, "total_steps": 58920, "loss": 0.0006, "lr": 1.1552991779132187e-06, "epoch": 2.5267311608961305, "percentage": 50.53, "elapsed_time": "0:47:07", "remaining_time": "0:46:07", "throughput": 10111.29, "total_tokens": 28587008}
{"current_steps": 29780, "total_steps": 58920, "loss": 0.0177, "lr": 1.1550065448283336e-06, "epoch": 2.527155465037339, "percentage": 50.54, "elapsed_time": "0:47:07", "remaining_time": "0:46:06", "throughput": 10111.62, "total_tokens": 28591808}
{"current_steps": 29785, "total_steps": 58920, "loss": 0.0003, "lr": 1.1547138981421842e-06, "epoch": 2.5275797691785473, "percentage": 50.55, "elapsed_time": "0:47:07", "remaining_time": "0:46:06", "throughput": 10111.85, "total_tokens": 28596224}
{"current_steps": 29790, "total_steps": 58920, "loss": 0.0239, "lr": 1.1544212378804488e-06, "epoch": 2.5280040733197557, "percentage": 50.56, "elapsed_time": "0:47:08", "remaining_time": "0:46:05", "throughput": 10112.27, "total_tokens": 28601344}
{"current_steps": 29795, "total_steps": 58920, "loss": 0.0002, "lr": 1.1541285640688072e-06, "epoch": 2.528428377460964, "percentage": 50.57, "elapsed_time": "0:47:08", "remaining_time": "0:46:05", "throughput": 10112.54, "total_tokens": 28605952}
{"current_steps": 29800, "total_steps": 58920, "loss": 0.0309, "lr": 1.1538358767329403e-06, "epoch": 2.5288526816021726, "percentage": 50.58, "elapsed_time": "0:47:09", "remaining_time": "0:46:04", "throughput": 10112.83, "total_tokens": 28610624}
{"current_steps": 29805, "total_steps": 58920, "loss": 0.0003, "lr": 1.1535431758985311e-06, "epoch": 2.529276985743381, "percentage": 50.59, "elapsed_time": "0:47:09", "remaining_time": "0:46:04", "throughput": 10113.1, "total_tokens": 28615232}
{"current_steps": 29810, "total_steps": 58920, "loss": 0.0003, "lr": 1.1532504615912625e-06, "epoch": 2.5297012898845894, "percentage": 50.59, "elapsed_time": "0:47:09", "remaining_time": "0:46:03", "throughput": 10113.48, "total_tokens": 28620224}
{"current_steps": 29815, "total_steps": 58920, "loss": 0.001, "lr": 1.1529577338368191e-06, "epoch": 2.530125594025798, "percentage": 50.6, "elapsed_time": "0:47:10", "remaining_time": "0:46:02", "throughput": 10113.74, "total_tokens": 28624832}
{"current_steps": 29820, "total_steps": 58920, "loss": 0.0366, "lr": 1.152664992660887e-06, "epoch": 2.5305498981670063, "percentage": 50.61, "elapsed_time": "0:47:10", "remaining_time": "0:46:02", "throughput": 10114.1, "total_tokens": 28629760}
{"current_steps": 29825, "total_steps": 58920, "loss": 0.0003, "lr": 1.1523722380891526e-06, "epoch": 2.5309742023082147, "percentage": 50.62, "elapsed_time": "0:47:11", "remaining_time": "0:46:01", "throughput": 10114.5, "total_tokens": 28634816}
{"current_steps": 29830, "total_steps": 58920, "loss": 0.0002, "lr": 1.1520794701473048e-06, "epoch": 2.531398506449423, "percentage": 50.63, "elapsed_time": "0:47:11", "remaining_time": "0:46:01", "throughput": 10114.7, "total_tokens": 28639232}
{"current_steps": 29835, "total_steps": 58920, "loss": 0.0001, "lr": 1.1517866888610322e-06, "epoch": 2.5318228105906315, "percentage": 50.64, "elapsed_time": "0:47:11", "remaining_time": "0:46:00", "throughput": 10115.14, "total_tokens": 28644480}
{"current_steps": 29840, "total_steps": 58920, "loss": 0.0358, "lr": 1.1514938942560259e-06, "epoch": 2.53224711473184, "percentage": 50.64, "elapsed_time": "0:47:12", "remaining_time": "0:46:00", "throughput": 10115.47, "total_tokens": 28649280}
{"current_steps": 29845, "total_steps": 58920, "loss": 0.0002, "lr": 1.1512010863579775e-06, "epoch": 2.5326714188730484, "percentage": 50.65, "elapsed_time": "0:47:12", "remaining_time": "0:45:59", "throughput": 10115.73, "total_tokens": 28653824}
{"current_steps": 29850, "total_steps": 58920, "loss": 0.0001, "lr": 1.1509082651925796e-06, "epoch": 2.533095723014257, "percentage": 50.66, "elapsed_time": "0:47:12", "remaining_time": "0:45:58", "throughput": 10116.12, "total_tokens": 28658880}
{"current_steps": 29855, "total_steps": 58920, "loss": 0.0663, "lr": 1.1506154307855262e-06, "epoch": 2.5335200271554648, "percentage": 50.67, "elapsed_time": "0:47:13", "remaining_time": "0:45:58", "throughput": 10116.35, "total_tokens": 28663360}
{"current_steps": 29860, "total_steps": 58920, "loss": 0.0001, "lr": 1.1503225831625125e-06, "epoch": 2.5339443312966736, "percentage": 50.68, "elapsed_time": "0:47:13", "remaining_time": "0:45:57", "throughput": 10116.55, "total_tokens": 28667712}
{"current_steps": 29865, "total_steps": 58920, "loss": 0.0002, "lr": 1.1500297223492349e-06, "epoch": 2.5343686354378816, "percentage": 50.69, "elapsed_time": "0:47:14", "remaining_time": "0:45:57", "throughput": 10116.65, "total_tokens": 28671808}
{"current_steps": 29870, "total_steps": 58920, "loss": 0.0303, "lr": 1.1497368483713907e-06, "epoch": 2.5347929395790905, "percentage": 50.7, "elapsed_time": "0:47:14", "remaining_time": "0:45:56", "throughput": 10116.89, "total_tokens": 28676352}
{"current_steps": 29875, "total_steps": 58920, "loss": 0.0003, "lr": 1.149443961254679e-06, "epoch": 2.5352172437202984, "percentage": 50.7, "elapsed_time": "0:47:14", "remaining_time": "0:45:56", "throughput": 10117.29, "total_tokens": 28681408}
{"current_steps": 29880, "total_steps": 58920, "loss": 0.0395, "lr": 1.1491510610247992e-06, "epoch": 2.5356415478615073, "percentage": 50.71, "elapsed_time": "0:47:15", "remaining_time": "0:45:55", "throughput": 10117.62, "total_tokens": 28686272}
{"current_steps": 29885, "total_steps": 58920, "loss": 0.0337, "lr": 1.1488581477074523e-06, "epoch": 2.5360658520027153, "percentage": 50.72, "elapsed_time": "0:47:15", "remaining_time": "0:45:55", "throughput": 10117.84, "total_tokens": 28690688}
{"current_steps": 29890, "total_steps": 58920, "loss": 0.0001, "lr": 1.14856522132834e-06, "epoch": 2.536490156143924, "percentage": 50.73, "elapsed_time": "0:47:16", "remaining_time": "0:45:54", "throughput": 10118.1, "total_tokens": 28695296}
{"current_steps": 29895, "total_steps": 58920, "loss": 0.0168, "lr": 1.1482722819131663e-06, "epoch": 2.536914460285132, "percentage": 50.74, "elapsed_time": "0:47:16", "remaining_time": "0:45:53", "throughput": 10118.27, "total_tokens": 28699584}
{"current_steps": 29900, "total_steps": 58920, "loss": 0.0532, "lr": 1.1479793294876351e-06, "epoch": 2.537338764426341, "percentage": 50.75, "elapsed_time": "0:47:16", "remaining_time": "0:45:53", "throughput": 10118.62, "total_tokens": 28704512}
{"current_steps": 29905, "total_steps": 58920, "loss": 0.0001, "lr": 1.1476863640774522e-06, "epoch": 2.537763068567549, "percentage": 50.76, "elapsed_time": "0:47:17", "remaining_time": "0:45:52", "throughput": 10118.91, "total_tokens": 28709184}
{"current_steps": 29910, "total_steps": 58920, "loss": 0.0318, "lr": 1.1473933857083237e-06, "epoch": 2.538187372708758, "percentage": 50.76, "elapsed_time": "0:47:17", "remaining_time": "0:45:52", "throughput": 10119.33, "total_tokens": 28714368}
{"current_steps": 29915, "total_steps": 58920, "loss": 0.0001, "lr": 1.147100394405958e-06, "epoch": 2.538611676849966, "percentage": 50.77, "elapsed_time": "0:47:17", "remaining_time": "0:45:51", "throughput": 10119.67, "total_tokens": 28719232}
{"current_steps": 29920, "total_steps": 58920, "loss": 0.0031, "lr": 1.1468073901960637e-06, "epoch": 2.5390359809911747, "percentage": 50.78, "elapsed_time": "0:47:18", "remaining_time": "0:45:51", "throughput": 10119.93, "total_tokens": 28723840}
{"current_steps": 29925, "total_steps": 58920, "loss": 0.0001, "lr": 1.1465143731043512e-06, "epoch": 2.5394602851323826, "percentage": 50.79, "elapsed_time": "0:47:18", "remaining_time": "0:45:50", "throughput": 10120.22, "total_tokens": 28728512}
{"current_steps": 29930, "total_steps": 58920, "loss": 0.0005, "lr": 1.1462213431565312e-06, "epoch": 2.5398845892735915, "percentage": 50.8, "elapsed_time": "0:47:19", "remaining_time": "0:45:49", "throughput": 10120.57, "total_tokens": 28733440}
{"current_steps": 29935, "total_steps": 58920, "loss": 0.0232, "lr": 1.1459283003783165e-06, "epoch": 2.5403088934147995, "percentage": 50.81, "elapsed_time": "0:47:19", "remaining_time": "0:45:49", "throughput": 10120.83, "total_tokens": 28738048}
{"current_steps": 29940, "total_steps": 58920, "loss": 0.0565, "lr": 1.14563524479542e-06, "epoch": 2.5407331975560083, "percentage": 50.81, "elapsed_time": "0:47:19", "remaining_time": "0:45:48", "throughput": 10121.12, "total_tokens": 28742784}
{"current_steps": 29945, "total_steps": 58920, "loss": 0.0001, "lr": 1.145342176433557e-06, "epoch": 2.5411575016972163, "percentage": 50.82, "elapsed_time": "0:47:20", "remaining_time": "0:45:48", "throughput": 10121.38, "total_tokens": 28747328}
{"current_steps": 29950, "total_steps": 58920, "loss": 0.0, "lr": 1.1450490953184424e-06, "epoch": 2.541581805838425, "percentage": 50.83, "elapsed_time": "0:47:20", "remaining_time": "0:45:47", "throughput": 10121.74, "total_tokens": 28752256}
{"current_steps": 29955, "total_steps": 58920, "loss": 0.0001, "lr": 1.1447560014757932e-06, "epoch": 2.542006109979633, "percentage": 50.84, "elapsed_time": "0:47:21", "remaining_time": "0:45:47", "throughput": 10122.1, "total_tokens": 28757184}
{"current_steps": 29960, "total_steps": 58920, "loss": 0.0001, "lr": 1.144462894931328e-06, "epoch": 2.542430414120842, "percentage": 50.85, "elapsed_time": "0:47:21", "remaining_time": "0:45:46", "throughput": 10122.46, "total_tokens": 28762112}
{"current_steps": 29965, "total_steps": 58920, "loss": 0.0514, "lr": 1.1441697757107654e-06, "epoch": 2.54285471826205, "percentage": 50.86, "elapsed_time": "0:47:21", "remaining_time": "0:45:46", "throughput": 10122.76, "total_tokens": 28766848}
{"current_steps": 29970, "total_steps": 58920, "loss": 0.0295, "lr": 1.1438766438398252e-06, "epoch": 2.543279022403259, "percentage": 50.87, "elapsed_time": "0:47:22", "remaining_time": "0:45:45", "throughput": 10122.99, "total_tokens": 28771328}
{"current_steps": 29975, "total_steps": 58920, "loss": 0.028, "lr": 1.143583499344229e-06, "epoch": 2.543703326544467, "percentage": 50.87, "elapsed_time": "0:47:22", "remaining_time": "0:45:44", "throughput": 10123.45, "total_tokens": 28776704}
{"current_steps": 29980, "total_steps": 58920, "loss": 0.0001, "lr": 1.1432903422496992e-06, "epoch": 2.5441276306856757, "percentage": 50.88, "elapsed_time": "0:47:22", "remaining_time": "0:45:44", "throughput": 10123.78, "total_tokens": 28781504}
{"current_steps": 29985, "total_steps": 58920, "loss": 0.0001, "lr": 1.1429971725819589e-06, "epoch": 2.5445519348268837, "percentage": 50.89, "elapsed_time": "0:47:23", "remaining_time": "0:45:43", "throughput": 10124.27, "total_tokens": 28787008}
{"current_steps": 29990, "total_steps": 58920, "loss": 0.0001, "lr": 1.1427039903667332e-06, "epoch": 2.5449762389680926, "percentage": 50.9, "elapsed_time": "0:47:23", "remaining_time": "0:45:43", "throughput": 10124.45, "total_tokens": 28791296}
{"current_steps": 29995, "total_steps": 58920, "loss": 0.0605, "lr": 1.1424107956297478e-06, "epoch": 2.5454005431093005, "percentage": 50.91, "elapsed_time": "0:47:24", "remaining_time": "0:45:42", "throughput": 10124.85, "total_tokens": 28796480}
{"current_steps": 30000, "total_steps": 58920, "loss": 0.0003, "lr": 1.1421175883967292e-06, "epoch": 2.5458248472505094, "percentage": 50.92, "elapsed_time": "0:47:24", "remaining_time": "0:45:42", "throughput": 10125.15, "total_tokens": 28801216}
{"current_steps": 30005, "total_steps": 58920, "loss": 0.0001, "lr": 1.1418243686934054e-06, "epoch": 2.5462491513917174, "percentage": 50.92, "elapsed_time": "0:47:24", "remaining_time": "0:45:41", "throughput": 10125.58, "total_tokens": 28806464}
{"current_steps": 30010, "total_steps": 58920, "loss": 0.0001, "lr": 1.1415311365455052e-06, "epoch": 2.5466734555329262, "percentage": 50.93, "elapsed_time": "0:47:25", "remaining_time": "0:45:41", "throughput": 10125.94, "total_tokens": 28811456}
{"current_steps": 30015, "total_steps": 58920, "loss": 0.0001, "lr": 1.1412378919787583e-06, "epoch": 2.547097759674134, "percentage": 50.94, "elapsed_time": "0:47:25", "remaining_time": "0:45:40", "throughput": 10126.31, "total_tokens": 28816448}
{"current_steps": 30020, "total_steps": 58920, "loss": 0.0001, "lr": 1.1409446350188969e-06, "epoch": 2.547522063815343, "percentage": 50.95, "elapsed_time": "0:47:26", "remaining_time": "0:45:39", "throughput": 10126.52, "total_tokens": 28820864}
{"current_steps": 30025, "total_steps": 58920, "loss": 0.0341, "lr": 1.1406513656916526e-06, "epoch": 2.547946367956551, "percentage": 50.96, "elapsed_time": "0:47:26", "remaining_time": "0:45:39", "throughput": 10126.76, "total_tokens": 28825344}
{"current_steps": 30030, "total_steps": 58920, "loss": 0.0001, "lr": 1.1403580840227584e-06, "epoch": 2.54837067209776, "percentage": 50.97, "elapsed_time": "0:47:26", "remaining_time": "0:45:38", "throughput": 10127.1, "total_tokens": 28830208}
{"current_steps": 30035, "total_steps": 58920, "loss": 0.0001, "lr": 1.1400647900379495e-06, "epoch": 2.548794976238968, "percentage": 50.98, "elapsed_time": "0:47:27", "remaining_time": "0:45:38", "throughput": 10127.28, "total_tokens": 28834560}
{"current_steps": 30040, "total_steps": 58920, "loss": 0.0202, "lr": 1.1397714837629608e-06, "epoch": 2.5492192803801768, "percentage": 50.98, "elapsed_time": "0:47:27", "remaining_time": "0:45:37", "throughput": 10127.61, "total_tokens": 28839488}
{"current_steps": 30045, "total_steps": 58920, "loss": 0.0001, "lr": 1.139478165223529e-06, "epoch": 2.5496435845213847, "percentage": 50.99, "elapsed_time": "0:47:28", "remaining_time": "0:45:37", "throughput": 10128.17, "total_tokens": 28845312}
{"current_steps": 30050, "total_steps": 58920, "loss": 0.0, "lr": 1.139184834445392e-06, "epoch": 2.5500678886625936, "percentage": 51.0, "elapsed_time": "0:47:28", "remaining_time": "0:45:36", "throughput": 10128.58, "total_tokens": 28850496}
{"current_steps": 30055, "total_steps": 58920, "loss": 0.0282, "lr": 1.1388914914542883e-06, "epoch": 2.5504921928038016, "percentage": 51.01, "elapsed_time": "0:47:28", "remaining_time": "0:45:36", "throughput": 10128.84, "total_tokens": 28855168}
{"current_steps": 30060, "total_steps": 58920, "loss": 0.0001, "lr": 1.1385981362759574e-06, "epoch": 2.5509164969450104, "percentage": 51.02, "elapsed_time": "0:47:29", "remaining_time": "0:45:35", "throughput": 10129.26, "total_tokens": 28860416}
{"current_steps": 30065, "total_steps": 58920, "loss": 0.0001, "lr": 1.1383047689361407e-06, "epoch": 2.5513408010862184, "percentage": 51.03, "elapsed_time": "0:47:29", "remaining_time": "0:45:34", "throughput": 10129.73, "total_tokens": 28865792}
{"current_steps": 30070, "total_steps": 58920, "loss": 0.023, "lr": 1.1380113894605795e-06, "epoch": 2.5517651052274273, "percentage": 51.04, "elapsed_time": "0:47:29", "remaining_time": "0:45:34", "throughput": 10129.95, "total_tokens": 28870272}
{"current_steps": 30075, "total_steps": 58920, "loss": 0.0002, "lr": 1.1377179978750175e-06, "epoch": 2.5521894093686353, "percentage": 51.04, "elapsed_time": "0:47:30", "remaining_time": "0:45:33", "throughput": 10130.67, "total_tokens": 28876672}
{"current_steps": 30080, "total_steps": 58920, "loss": 0.0001, "lr": 1.1374245942051984e-06, "epoch": 2.552613713509844, "percentage": 51.05, "elapsed_time": "0:47:30", "remaining_time": "0:45:33", "throughput": 10130.97, "total_tokens": 28881472}
{"current_steps": 30085, "total_steps": 58920, "loss": 0.0335, "lr": 1.1371311784768672e-06, "epoch": 2.553038017651052, "percentage": 51.06, "elapsed_time": "0:47:31", "remaining_time": "0:45:32", "throughput": 10131.23, "total_tokens": 28886144}
{"current_steps": 30090, "total_steps": 58920, "loss": 0.0271, "lr": 1.1368377507157706e-06, "epoch": 2.553462321792261, "percentage": 51.07, "elapsed_time": "0:47:31", "remaining_time": "0:45:32", "throughput": 10131.45, "total_tokens": 28890624}
{"current_steps": 30095, "total_steps": 58920, "loss": 0.0, "lr": 1.136544310947655e-06, "epoch": 2.553886625933469, "percentage": 51.08, "elapsed_time": "0:47:31", "remaining_time": "0:45:31", "throughput": 10131.74, "total_tokens": 28895360}
{"current_steps": 30100, "total_steps": 58920, "loss": 0.0, "lr": 1.1362508591982692e-06, "epoch": 2.554310930074678, "percentage": 51.09, "elapsed_time": "0:47:32", "remaining_time": "0:45:31", "throughput": 10131.96, "total_tokens": 28899776}
{"current_steps": 30105, "total_steps": 58920, "loss": 0.0184, "lr": 1.1359573954933623e-06, "epoch": 2.5547352342158858, "percentage": 51.09, "elapsed_time": "0:47:32", "remaining_time": "0:45:30", "throughput": 10132.29, "total_tokens": 28904640}
{"current_steps": 30110, "total_steps": 58920, "loss": 0.0365, "lr": 1.1356639198586848e-06, "epoch": 2.5551595383570946, "percentage": 51.1, "elapsed_time": "0:47:33", "remaining_time": "0:45:29", "throughput": 10132.73, "total_tokens": 28909952}
{"current_steps": 30115, "total_steps": 58920, "loss": 0.0002, "lr": 1.1353704323199884e-06, "epoch": 2.5555838424983026, "percentage": 51.11, "elapsed_time": "0:47:33", "remaining_time": "0:45:29", "throughput": 10132.98, "total_tokens": 28914432}
{"current_steps": 30120, "total_steps": 58920, "loss": 0.0001, "lr": 1.1350769329030251e-06, "epoch": 2.556008146639511, "percentage": 51.12, "elapsed_time": "0:47:33", "remaining_time": "0:45:28", "throughput": 10133.34, "total_tokens": 28919424}
{"current_steps": 30125, "total_steps": 58920, "loss": 0.0, "lr": 1.1347834216335487e-06, "epoch": 2.5564324507807195, "percentage": 51.13, "elapsed_time": "0:47:34", "remaining_time": "0:45:28", "throughput": 10133.75, "total_tokens": 28924544}
{"current_steps": 30130, "total_steps": 58920, "loss": 0.0004, "lr": 1.1344898985373142e-06, "epoch": 2.556856754921928, "percentage": 51.14, "elapsed_time": "0:47:34", "remaining_time": "0:45:27", "throughput": 10133.95, "total_tokens": 28928896}
{"current_steps": 30135, "total_steps": 58920, "loss": 0.0001, "lr": 1.134196363640076e-06, "epoch": 2.5572810590631363, "percentage": 51.15, "elapsed_time": "0:47:35", "remaining_time": "0:45:27", "throughput": 10134.23, "total_tokens": 28933568}
{"current_steps": 30140, "total_steps": 58920, "loss": 0.0, "lr": 1.1339028169675915e-06, "epoch": 2.5577053632043447, "percentage": 51.15, "elapsed_time": "0:47:35", "remaining_time": "0:45:26", "throughput": 10134.45, "total_tokens": 28937984}
{"current_steps": 30145, "total_steps": 58920, "loss": 0.0366, "lr": 1.1336092585456186e-06, "epoch": 2.558129667345553, "percentage": 51.16, "elapsed_time": "0:47:35", "remaining_time": "0:45:26", "throughput": 10134.78, "total_tokens": 28942784}
{"current_steps": 30150, "total_steps": 58920, "loss": 0.0445, "lr": 1.1333156883999153e-06, "epoch": 2.5585539714867616, "percentage": 51.17, "elapsed_time": "0:47:36", "remaining_time": "0:45:25", "throughput": 10135.15, "total_tokens": 28947712}
{"current_steps": 30155, "total_steps": 58920, "loss": 0.028, "lr": 1.1330221065562418e-06, "epoch": 2.55897827562797, "percentage": 51.18, "elapsed_time": "0:47:36", "remaining_time": "0:45:24", "throughput": 10135.45, "total_tokens": 28952448}
{"current_steps": 30160, "total_steps": 58920, "loss": 0.0, "lr": 1.1327285130403587e-06, "epoch": 2.5594025797691784, "percentage": 51.19, "elapsed_time": "0:47:36", "remaining_time": "0:45:24", "throughput": 10135.77, "total_tokens": 28957248}
{"current_steps": 30165, "total_steps": 58920, "loss": 0.0336, "lr": 1.132434907878028e-06, "epoch": 2.559826883910387, "percentage": 51.2, "elapsed_time": "0:47:37", "remaining_time": "0:45:23", "throughput": 10136.38, "total_tokens": 28963136}
{"current_steps": 30170, "total_steps": 58920, "loss": 0.021, "lr": 1.1321412910950122e-06, "epoch": 2.5602511880515952, "percentage": 51.21, "elapsed_time": "0:47:37", "remaining_time": "0:45:23", "throughput": 10136.74, "total_tokens": 28968064}
{"current_steps": 30175, "total_steps": 58920, "loss": 0.0003, "lr": 1.131847662717075e-06, "epoch": 2.5606754921928037, "percentage": 51.21, "elapsed_time": "0:47:38", "remaining_time": "0:45:22", "throughput": 10136.97, "total_tokens": 28972544}
{"current_steps": 30180, "total_steps": 58920, "loss": 0.0494, "lr": 1.1315540227699815e-06, "epoch": 2.561099796334012, "percentage": 51.22, "elapsed_time": "0:47:38", "remaining_time": "0:45:22", "throughput": 10137.22, "total_tokens": 28977088}
{"current_steps": 30185, "total_steps": 58920, "loss": 0.0001, "lr": 1.1312603712794978e-06, "epoch": 2.5615241004752205, "percentage": 51.23, "elapsed_time": "0:47:38", "remaining_time": "0:45:21", "throughput": 10137.61, "total_tokens": 28982144}
{"current_steps": 30190, "total_steps": 58920, "loss": 0.0, "lr": 1.13096670827139e-06, "epoch": 2.561948404616429, "percentage": 51.24, "elapsed_time": "0:47:39", "remaining_time": "0:45:20", "throughput": 10137.92, "total_tokens": 28986944}
{"current_steps": 30195, "total_steps": 58920, "loss": 0.0001, "lr": 1.1306730337714265e-06, "epoch": 2.5623727087576373, "percentage": 51.25, "elapsed_time": "0:47:39", "remaining_time": "0:45:20", "throughput": 10138.31, "total_tokens": 28992000}
{"current_steps": 30200, "total_steps": 58920, "loss": 0.0001, "lr": 1.130379347805376e-06, "epoch": 2.5627970128988458, "percentage": 51.26, "elapsed_time": "0:47:40", "remaining_time": "0:45:19", "throughput": 10138.5, "total_tokens": 28996352}
{"current_steps": 30205, "total_steps": 58920, "loss": 0.0383, "lr": 1.1300856503990087e-06, "epoch": 2.563221317040054, "percentage": 51.26, "elapsed_time": "0:47:40", "remaining_time": "0:45:19", "throughput": 10139.01, "total_tokens": 29001856}
{"current_steps": 30210, "total_steps": 58920, "loss": 0.0203, "lr": 1.129791941578095e-06, "epoch": 2.5636456211812626, "percentage": 51.27, "elapsed_time": "0:47:40", "remaining_time": "0:45:18", "throughput": 10139.11, "total_tokens": 29005888}
{"current_steps": 30215, "total_steps": 58920, "loss": 0.0004, "lr": 1.1294982213684074e-06, "epoch": 2.564069925322471, "percentage": 51.28, "elapsed_time": "0:47:41", "remaining_time": "0:45:18", "throughput": 10139.51, "total_tokens": 29011008}
{"current_steps": 30220, "total_steps": 58920, "loss": 0.0001, "lr": 1.1292044897957182e-06, "epoch": 2.5644942294636794, "percentage": 51.29, "elapsed_time": "0:47:41", "remaining_time": "0:45:17", "throughput": 10139.78, "total_tokens": 29015616}
{"current_steps": 30225, "total_steps": 58920, "loss": 0.0, "lr": 1.1289107468858018e-06, "epoch": 2.564918533604888, "percentage": 51.3, "elapsed_time": "0:47:41", "remaining_time": "0:45:17", "throughput": 10140.11, "total_tokens": 29020480}
{"current_steps": 30230, "total_steps": 58920, "loss": 0.0392, "lr": 1.1286169926644322e-06, "epoch": 2.5653428377460963, "percentage": 51.31, "elapsed_time": "0:47:42", "remaining_time": "0:45:16", "throughput": 10140.27, "total_tokens": 29024704}
{"current_steps": 30235, "total_steps": 58920, "loss": 0.0, "lr": 1.128323227157386e-06, "epoch": 2.5657671418873047, "percentage": 51.32, "elapsed_time": "0:47:42", "remaining_time": "0:45:15", "throughput": 10140.56, "total_tokens": 29029376}
{"current_steps": 30240, "total_steps": 58920, "loss": 0.0, "lr": 1.1280294503904404e-06, "epoch": 2.566191446028513, "percentage": 51.32, "elapsed_time": "0:47:43", "remaining_time": "0:45:15", "throughput": 10141.04, "total_tokens": 29034752}
{"current_steps": 30245, "total_steps": 58920, "loss": 0.0003, "lr": 1.1277356623893726e-06, "epoch": 2.5666157501697215, "percentage": 51.33, "elapsed_time": "0:47:43", "remaining_time": "0:45:14", "throughput": 10141.35, "total_tokens": 29039488}
{"current_steps": 30250, "total_steps": 58920, "loss": 0.0, "lr": 1.1274418631799614e-06, "epoch": 2.56704005431093, "percentage": 51.34, "elapsed_time": "0:47:43", "remaining_time": "0:45:14", "throughput": 10141.52, "total_tokens": 29043840}
{"current_steps": 30255, "total_steps": 58920, "loss": 0.0495, "lr": 1.1271480527879871e-06, "epoch": 2.5674643584521384, "percentage": 51.35, "elapsed_time": "0:47:44", "remaining_time": "0:45:13", "throughput": 10141.93, "total_tokens": 29048960}
{"current_steps": 30260, "total_steps": 58920, "loss": 0.0, "lr": 1.12685423123923e-06, "epoch": 2.567888662593347, "percentage": 51.36, "elapsed_time": "0:47:44", "remaining_time": "0:45:13", "throughput": 10142.34, "total_tokens": 29054144}
{"current_steps": 30265, "total_steps": 58920, "loss": 0.0003, "lr": 1.126560398559472e-06, "epoch": 2.5683129667345552, "percentage": 51.37, "elapsed_time": "0:47:45", "remaining_time": "0:45:12", "throughput": 10142.65, "total_tokens": 29058880}
{"current_steps": 30270, "total_steps": 58920, "loss": 0.0001, "lr": 1.1262665547744964e-06, "epoch": 2.5687372708757636, "percentage": 51.37, "elapsed_time": "0:47:45", "remaining_time": "0:45:12", "throughput": 10143.13, "total_tokens": 29064256}
{"current_steps": 30275, "total_steps": 58920, "loss": 0.0001, "lr": 1.1259726999100864e-06, "epoch": 2.569161575016972, "percentage": 51.38, "elapsed_time": "0:47:45", "remaining_time": "0:45:11", "throughput": 10143.93, "total_tokens": 29070912}
{"current_steps": 30280, "total_steps": 58920, "loss": 0.0001, "lr": 1.1256788339920264e-06, "epoch": 2.5695858791581805, "percentage": 51.39, "elapsed_time": "0:47:46", "remaining_time": "0:45:10", "throughput": 10144.31, "total_tokens": 29075968}
{"current_steps": 30285, "total_steps": 58920, "loss": 0.0086, "lr": 1.1253849570461028e-06, "epoch": 2.570010183299389, "percentage": 51.4, "elapsed_time": "0:47:46", "remaining_time": "0:45:10", "throughput": 10144.57, "total_tokens": 29080512}
{"current_steps": 30290, "total_steps": 58920, "loss": 0.0001, "lr": 1.125091069098102e-06, "epoch": 2.5704344874405973, "percentage": 51.41, "elapsed_time": "0:47:46", "remaining_time": "0:45:09", "throughput": 10144.88, "total_tokens": 29085312}
{"current_steps": 30295, "total_steps": 58920, "loss": 0.0, "lr": 1.124797170173811e-06, "epoch": 2.5708587915818057, "percentage": 51.42, "elapsed_time": "0:47:47", "remaining_time": "0:45:09", "throughput": 10145.05, "total_tokens": 29089600}
{"current_steps": 30300, "total_steps": 58920, "loss": 0.0001, "lr": 1.1245032602990197e-06, "epoch": 2.571283095723014, "percentage": 51.43, "elapsed_time": "0:47:47", "remaining_time": "0:45:08", "throughput": 10145.49, "total_tokens": 29094912}
{"current_steps": 30305, "total_steps": 58920, "loss": 0.019, "lr": 1.1242093394995162e-06, "epoch": 2.5717073998642226, "percentage": 51.43, "elapsed_time": "0:47:48", "remaining_time": "0:45:08", "throughput": 10145.67, "total_tokens": 29099200}
{"current_steps": 30310, "total_steps": 58920, "loss": 0.0495, "lr": 1.123915407801092e-06, "epoch": 2.572131704005431, "percentage": 51.44, "elapsed_time": "0:47:48", "remaining_time": "0:45:07", "throughput": 10145.97, "total_tokens": 29103936}
{"current_steps": 30315, "total_steps": 58920, "loss": 0.0, "lr": 1.1236214652295378e-06, "epoch": 2.5725560081466394, "percentage": 51.45, "elapsed_time": "0:47:48", "remaining_time": "0:45:07", "throughput": 10146.14, "total_tokens": 29108160}
{"current_steps": 30320, "total_steps": 58920, "loss": 0.0, "lr": 1.1233275118106466e-06, "epoch": 2.572980312287848, "percentage": 51.46, "elapsed_time": "0:47:49", "remaining_time": "0:45:06", "throughput": 10146.41, "total_tokens": 29112768}
{"current_steps": 30325, "total_steps": 58920, "loss": 0.0, "lr": 1.1230335475702113e-06, "epoch": 2.5734046164290563, "percentage": 51.47, "elapsed_time": "0:47:49", "remaining_time": "0:45:05", "throughput": 10146.84, "total_tokens": 29117952}
{"current_steps": 30330, "total_steps": 58920, "loss": 0.0001, "lr": 1.1227395725340268e-06, "epoch": 2.5738289205702647, "percentage": 51.48, "elapsed_time": "0:47:50", "remaining_time": "0:45:05", "throughput": 10147.19, "total_tokens": 29122880}
{"current_steps": 30335, "total_steps": 58920, "loss": 0.0, "lr": 1.1224455867278874e-06, "epoch": 2.574253224711473, "percentage": 51.49, "elapsed_time": "0:47:50", "remaining_time": "0:45:04", "throughput": 10147.38, "total_tokens": 29127232}
{"current_steps": 30340, "total_steps": 58920, "loss": 0.0, "lr": 1.1221515901775906e-06, "epoch": 2.5746775288526815, "percentage": 51.49, "elapsed_time": "0:47:50", "remaining_time": "0:45:04", "throughput": 10147.66, "total_tokens": 29131904}
{"current_steps": 30345, "total_steps": 58920, "loss": 0.0281, "lr": 1.1218575829089323e-06, "epoch": 2.57510183299389, "percentage": 51.5, "elapsed_time": "0:47:51", "remaining_time": "0:45:03", "throughput": 10148.08, "total_tokens": 29137088}
{"current_steps": 30350, "total_steps": 58920, "loss": 0.0, "lr": 1.121563564947711e-06, "epoch": 2.5755261371350984, "percentage": 51.51, "elapsed_time": "0:47:51", "remaining_time": "0:45:03", "throughput": 10148.3, "total_tokens": 29141504}
{"current_steps": 30355, "total_steps": 58920, "loss": 0.0, "lr": 1.121269536319726e-06, "epoch": 2.575950441276307, "percentage": 51.52, "elapsed_time": "0:47:51", "remaining_time": "0:45:02", "throughput": 10148.54, "total_tokens": 29146048}
{"current_steps": 30360, "total_steps": 58920, "loss": 0.0, "lr": 1.120975497050777e-06, "epoch": 2.576374745417515, "percentage": 51.53, "elapsed_time": "0:47:52", "remaining_time": "0:45:02", "throughput": 10148.79, "total_tokens": 29150592}
{"current_steps": 30365, "total_steps": 58920, "loss": 0.023, "lr": 1.1206814471666648e-06, "epoch": 2.5767990495587236, "percentage": 51.54, "elapsed_time": "0:47:52", "remaining_time": "0:45:01", "throughput": 10149.09, "total_tokens": 29155328}
{"current_steps": 30370, "total_steps": 58920, "loss": 0.0, "lr": 1.1203873866931915e-06, "epoch": 2.577223353699932, "percentage": 51.54, "elapsed_time": "0:47:53", "remaining_time": "0:45:00", "throughput": 10149.55, "total_tokens": 29160576}
{"current_steps": 30375, "total_steps": 58920, "loss": 0.0018, "lr": 1.1200933156561594e-06, "epoch": 2.5776476578411405, "percentage": 51.55, "elapsed_time": "0:47:53", "remaining_time": "0:45:00", "throughput": 10150.09, "total_tokens": 29166272}
{"current_steps": 30380, "total_steps": 58920, "loss": 0.0084, "lr": 1.1197992340813726e-06, "epoch": 2.578071961982349, "percentage": 51.56, "elapsed_time": "0:47:53", "remaining_time": "0:44:59", "throughput": 10150.38, "total_tokens": 29170944}
{"current_steps": 30385, "total_steps": 58920, "loss": 0.0424, "lr": 1.1195051419946356e-06, "epoch": 2.5784962661235573, "percentage": 51.57, "elapsed_time": "0:47:54", "remaining_time": "0:44:59", "throughput": 10150.65, "total_tokens": 29175552}
{"current_steps": 30390, "total_steps": 58920, "loss": 0.0001, "lr": 1.1192110394217537e-06, "epoch": 2.5789205702647657, "percentage": 51.58, "elapsed_time": "0:47:54", "remaining_time": "0:44:58", "throughput": 10151.13, "total_tokens": 29180992}
{"current_steps": 30395, "total_steps": 58920, "loss": 0.0, "lr": 1.1189169263885338e-06, "epoch": 2.579344874405974, "percentage": 51.59, "elapsed_time": "0:47:55", "remaining_time": "0:44:58", "throughput": 10151.73, "total_tokens": 29186944}
{"current_steps": 30400, "total_steps": 58920, "loss": 0.0481, "lr": 1.1186228029207827e-06, "epoch": 2.5797691785471826, "percentage": 51.6, "elapsed_time": "0:47:55", "remaining_time": "0:44:57", "throughput": 10151.98, "total_tokens": 29191488}
{"current_steps": 30405, "total_steps": 58920, "loss": 0.0599, "lr": 1.118328669044309e-06, "epoch": 2.580193482688391, "percentage": 51.6, "elapsed_time": "0:47:55", "remaining_time": "0:44:57", "throughput": 10152.41, "total_tokens": 29196672}
{"current_steps": 30410, "total_steps": 58920, "loss": 0.0244, "lr": 1.118034524784922e-06, "epoch": 2.5806177868295994, "percentage": 51.61, "elapsed_time": "0:47:56", "remaining_time": "0:44:56", "throughput": 10152.74, "total_tokens": 29201536}
{"current_steps": 30415, "total_steps": 58920, "loss": 0.0001, "lr": 1.1177403701684313e-06, "epoch": 2.581042090970808, "percentage": 51.62, "elapsed_time": "0:47:56", "remaining_time": "0:44:55", "throughput": 10152.93, "total_tokens": 29205888}
{"current_steps": 30420, "total_steps": 58920, "loss": 0.0002, "lr": 1.1174462052206482e-06, "epoch": 2.5814663951120163, "percentage": 51.63, "elapsed_time": "0:47:56", "remaining_time": "0:44:55", "throughput": 10153.14, "total_tokens": 29210304}
{"current_steps": 30425, "total_steps": 58920, "loss": 0.021, "lr": 1.117152029967385e-06, "epoch": 2.5818906992532247, "percentage": 51.64, "elapsed_time": "0:47:57", "remaining_time": "0:44:54", "throughput": 10153.45, "total_tokens": 29215104}
{"current_steps": 30430, "total_steps": 58920, "loss": 0.0037, "lr": 1.1168578444344538e-06, "epoch": 2.582315003394433, "percentage": 51.65, "elapsed_time": "0:47:57", "remaining_time": "0:44:54", "throughput": 10153.58, "total_tokens": 29219264}
{"current_steps": 30435, "total_steps": 58920, "loss": 0.0001, "lr": 1.1165636486476688e-06, "epoch": 2.5827393075356415, "percentage": 51.65, "elapsed_time": "0:47:58", "remaining_time": "0:44:53", "throughput": 10154.04, "total_tokens": 29224640}
{"current_steps": 30440, "total_steps": 58920, "loss": 0.0002, "lr": 1.1162694426328445e-06, "epoch": 2.58316361167685, "percentage": 51.66, "elapsed_time": "0:47:58", "remaining_time": "0:44:53", "throughput": 10154.36, "total_tokens": 29229440}
{"current_steps": 30445, "total_steps": 58920, "loss": 0.0238, "lr": 1.1159752264157963e-06, "epoch": 2.5835879158180584, "percentage": 51.67, "elapsed_time": "0:47:58", "remaining_time": "0:44:52", "throughput": 10154.62, "total_tokens": 29234112}
{"current_steps": 30450, "total_steps": 58920, "loss": 0.0001, "lr": 1.1156810000223406e-06, "epoch": 2.5840122199592668, "percentage": 51.68, "elapsed_time": "0:47:59", "remaining_time": "0:44:52", "throughput": 10154.93, "total_tokens": 29238912}
{"current_steps": 30455, "total_steps": 58920, "loss": 0.0002, "lr": 1.1153867634782953e-06, "epoch": 2.584436524100475, "percentage": 51.69, "elapsed_time": "0:47:59", "remaining_time": "0:44:51", "throughput": 10155.25, "total_tokens": 29243712}
{"current_steps": 30460, "total_steps": 58920, "loss": 0.0015, "lr": 1.1150925168094775e-06, "epoch": 2.5848608282416836, "percentage": 51.7, "elapsed_time": "0:48:00", "remaining_time": "0:44:50", "throughput": 10155.54, "total_tokens": 29248448}
{"current_steps": 30465, "total_steps": 58920, "loss": 0.0001, "lr": 1.1147982600417076e-06, "epoch": 2.585285132382892, "percentage": 51.71, "elapsed_time": "0:48:00", "remaining_time": "0:44:50", "throughput": 10155.89, "total_tokens": 29253376}
{"current_steps": 30470, "total_steps": 58920, "loss": 0.0013, "lr": 1.1145039932008045e-06, "epoch": 2.5857094365241005, "percentage": 51.71, "elapsed_time": "0:48:00", "remaining_time": "0:44:49", "throughput": 10156.21, "total_tokens": 29258176}
{"current_steps": 30475, "total_steps": 58920, "loss": 0.0491, "lr": 1.114209716312589e-06, "epoch": 2.586133740665309, "percentage": 51.72, "elapsed_time": "0:48:01", "remaining_time": "0:44:49", "throughput": 10156.4, "total_tokens": 29262528}
{"current_steps": 30480, "total_steps": 58920, "loss": 0.0001, "lr": 1.1139154294028836e-06, "epoch": 2.5865580448065173, "percentage": 51.73, "elapsed_time": "0:48:01", "remaining_time": "0:44:48", "throughput": 10156.64, "total_tokens": 29267072}
{"current_steps": 30485, "total_steps": 58920, "loss": 0.0644, "lr": 1.1136211324975107e-06, "epoch": 2.5869823489477257, "percentage": 51.74, "elapsed_time": "0:48:01", "remaining_time": "0:44:48", "throughput": 10156.95, "total_tokens": 29271808}
{"current_steps": 30490, "total_steps": 58920, "loss": 0.0001, "lr": 1.1133268256222935e-06, "epoch": 2.587406653088934, "percentage": 51.75, "elapsed_time": "0:48:02", "remaining_time": "0:44:47", "throughput": 10157.29, "total_tokens": 29276672}
{"current_steps": 30495, "total_steps": 58920, "loss": 0.0, "lr": 1.1130325088030566e-06, "epoch": 2.5878309572301426, "percentage": 51.76, "elapsed_time": "0:48:02", "remaining_time": "0:44:47", "throughput": 10157.68, "total_tokens": 29281728}
{"current_steps": 30500, "total_steps": 58920, "loss": 0.0001, "lr": 1.112738182065625e-06, "epoch": 2.588255261371351, "percentage": 51.77, "elapsed_time": "0:48:03", "remaining_time": "0:44:46", "throughput": 10158.02, "total_tokens": 29286592}
{"current_steps": 30505, "total_steps": 58920, "loss": 0.0779, "lr": 1.1124438454358252e-06, "epoch": 2.5886795655125594, "percentage": 51.77, "elapsed_time": "0:48:03", "remaining_time": "0:44:45", "throughput": 10158.25, "total_tokens": 29291072}
{"current_steps": 30510, "total_steps": 58920, "loss": 0.0005, "lr": 1.1121494989394837e-06, "epoch": 2.589103869653768, "percentage": 51.78, "elapsed_time": "0:48:03", "remaining_time": "0:44:45", "throughput": 10158.46, "total_tokens": 29295488}
{"current_steps": 30515, "total_steps": 58920, "loss": 0.0002, "lr": 1.1118551426024287e-06, "epoch": 2.5895281737949762, "percentage": 51.79, "elapsed_time": "0:48:04", "remaining_time": "0:44:44", "throughput": 10158.74, "total_tokens": 29300160}
{"current_steps": 30520, "total_steps": 58920, "loss": 0.0001, "lr": 1.1115607764504886e-06, "epoch": 2.5899524779361847, "percentage": 51.8, "elapsed_time": "0:48:04", "remaining_time": "0:44:44", "throughput": 10160.08, "total_tokens": 29309056}
{"current_steps": 30525, "total_steps": 58920, "loss": 0.0001, "lr": 1.1112664005094934e-06, "epoch": 2.590376782077393, "percentage": 51.81, "elapsed_time": "0:48:05", "remaining_time": "0:44:43", "throughput": 10160.31, "total_tokens": 29313536}
{"current_steps": 30530, "total_steps": 58920, "loss": 0.0445, "lr": 1.1109720148052733e-06, "epoch": 2.5908010862186015, "percentage": 51.82, "elapsed_time": "0:48:05", "remaining_time": "0:44:43", "throughput": 10160.61, "total_tokens": 29318336}
{"current_steps": 30535, "total_steps": 58920, "loss": 0.0004, "lr": 1.1106776193636592e-06, "epoch": 2.59122539035981, "percentage": 51.82, "elapsed_time": "0:48:05", "remaining_time": "0:44:42", "throughput": 10160.92, "total_tokens": 29323072}
{"current_steps": 30540, "total_steps": 58920, "loss": 0.0213, "lr": 1.110383214210484e-06, "epoch": 2.5916496945010183, "percentage": 51.83, "elapsed_time": "0:48:06", "remaining_time": "0:44:42", "throughput": 10161.15, "total_tokens": 29327552}
{"current_steps": 30545, "total_steps": 58920, "loss": 0.0006, "lr": 1.11008879937158e-06, "epoch": 2.5920739986422268, "percentage": 51.84, "elapsed_time": "0:48:06", "remaining_time": "0:44:41", "throughput": 10161.47, "total_tokens": 29332352}
{"current_steps": 30550, "total_steps": 58920, "loss": 0.0002, "lr": 1.1097943748727818e-06, "epoch": 2.592498302783435, "percentage": 51.85, "elapsed_time": "0:48:07", "remaining_time": "0:44:40", "throughput": 10161.78, "total_tokens": 29337152}
{"current_steps": 30555, "total_steps": 58920, "loss": 0.0642, "lr": 1.1094999407399232e-06, "epoch": 2.5929226069246436, "percentage": 51.86, "elapsed_time": "0:48:07", "remaining_time": "0:44:40", "throughput": 10162.12, "total_tokens": 29342080}
{"current_steps": 30560, "total_steps": 58920, "loss": 0.0001, "lr": 1.1092054969988402e-06, "epoch": 2.593346911065852, "percentage": 51.87, "elapsed_time": "0:48:07", "remaining_time": "0:44:39", "throughput": 10162.45, "total_tokens": 29346880}
{"current_steps": 30565, "total_steps": 58920, "loss": 0.0207, "lr": 1.108911043675369e-06, "epoch": 2.5937712152070604, "percentage": 51.88, "elapsed_time": "0:48:08", "remaining_time": "0:44:39", "throughput": 10162.74, "total_tokens": 29351616}
{"current_steps": 30570, "total_steps": 58920, "loss": 0.0212, "lr": 1.108616580795347e-06, "epoch": 2.594195519348269, "percentage": 51.88, "elapsed_time": "0:48:08", "remaining_time": "0:44:38", "throughput": 10163.12, "total_tokens": 29356672}
{"current_steps": 30575, "total_steps": 58920, "loss": 0.0311, "lr": 1.1083221083846127e-06, "epoch": 2.5946198234894773, "percentage": 51.89, "elapsed_time": "0:48:08", "remaining_time": "0:44:38", "throughput": 10163.39, "total_tokens": 29361280}
{"current_steps": 30580, "total_steps": 58920, "loss": 0.0179, "lr": 1.108027626469004e-06, "epoch": 2.5950441276306857, "percentage": 51.9, "elapsed_time": "0:48:09", "remaining_time": "0:44:37", "throughput": 10163.82, "total_tokens": 29366592}
{"current_steps": 30585, "total_steps": 58920, "loss": 0.0004, "lr": 1.107733135074361e-06, "epoch": 2.595468431771894, "percentage": 51.91, "elapsed_time": "0:48:09", "remaining_time": "0:44:37", "throughput": 10164.24, "total_tokens": 29371776}
{"current_steps": 30590, "total_steps": 58920, "loss": 0.0003, "lr": 1.107438634226525e-06, "epoch": 2.5958927359131025, "percentage": 51.92, "elapsed_time": "0:48:10", "remaining_time": "0:44:36", "throughput": 10164.5, "total_tokens": 29376320}
{"current_steps": 30595, "total_steps": 58920, "loss": 0.0003, "lr": 1.107144123951336e-06, "epoch": 2.596317040054311, "percentage": 51.93, "elapsed_time": "0:48:10", "remaining_time": "0:44:36", "throughput": 10164.78, "total_tokens": 29380992}
{"current_steps": 30600, "total_steps": 58920, "loss": 0.0002, "lr": 1.1068496042746374e-06, "epoch": 2.5967413441955194, "percentage": 51.93, "elapsed_time": "0:48:10", "remaining_time": "0:44:35", "throughput": 10164.99, "total_tokens": 29385408}
{"current_steps": 30605, "total_steps": 58920, "loss": 0.0001, "lr": 1.1065550752222717e-06, "epoch": 2.597165648336728, "percentage": 51.94, "elapsed_time": "0:48:11", "remaining_time": "0:44:34", "throughput": 10165.28, "total_tokens": 29390144}
{"current_steps": 30610, "total_steps": 58920, "loss": 0.0, "lr": 1.1062605368200828e-06, "epoch": 2.5975899524779362, "percentage": 51.95, "elapsed_time": "0:48:11", "remaining_time": "0:44:34", "throughput": 10165.64, "total_tokens": 29395072}
{"current_steps": 30615, "total_steps": 58920, "loss": 0.0009, "lr": 1.1059659890939155e-06, "epoch": 2.5980142566191446, "percentage": 51.96, "elapsed_time": "0:48:12", "remaining_time": "0:44:33", "throughput": 10166.09, "total_tokens": 29400320}
{"current_steps": 30620, "total_steps": 58920, "loss": 0.03, "lr": 1.1056714320696153e-06, "epoch": 2.598438560760353, "percentage": 51.97, "elapsed_time": "0:48:12", "remaining_time": "0:44:33", "throughput": 10166.25, "total_tokens": 29404544}
{"current_steps": 30625, "total_steps": 58920, "loss": 0.0001, "lr": 1.1053768657730282e-06, "epoch": 2.5988628649015615, "percentage": 51.98, "elapsed_time": "0:48:12", "remaining_time": "0:44:32", "throughput": 10166.52, "total_tokens": 29409216}
{"current_steps": 30630, "total_steps": 58920, "loss": 0.0464, "lr": 1.1050822902300018e-06, "epoch": 2.59928716904277, "percentage": 51.99, "elapsed_time": "0:48:13", "remaining_time": "0:44:32", "throughput": 10166.79, "total_tokens": 29413888}
{"current_steps": 30635, "total_steps": 58920, "loss": 0.0323, "lr": 1.104787705466384e-06, "epoch": 2.5997114731839783, "percentage": 51.99, "elapsed_time": "0:48:13", "remaining_time": "0:44:31", "throughput": 10167.02, "total_tokens": 29418368}
{"current_steps": 30640, "total_steps": 58920, "loss": 0.0601, "lr": 1.1044931115080231e-06, "epoch": 2.6001357773251867, "percentage": 52.0, "elapsed_time": "0:48:13", "remaining_time": "0:44:30", "throughput": 10167.21, "total_tokens": 29422720}
{"current_steps": 30645, "total_steps": 58920, "loss": 0.0, "lr": 1.104198508380769e-06, "epoch": 2.600560081466395, "percentage": 52.01, "elapsed_time": "0:48:14", "remaining_time": "0:44:30", "throughput": 10167.42, "total_tokens": 29427136}
{"current_steps": 30650, "total_steps": 58920, "loss": 0.0001, "lr": 1.103903896110472e-06, "epoch": 2.6009843856076036, "percentage": 52.02, "elapsed_time": "0:48:14", "remaining_time": "0:44:29", "throughput": 10167.87, "total_tokens": 29432512}
{"current_steps": 30655, "total_steps": 58920, "loss": 0.0001, "lr": 1.1036092747229836e-06, "epoch": 2.601408689748812, "percentage": 52.03, "elapsed_time": "0:48:15", "remaining_time": "0:44:29", "throughput": 10168.13, "total_tokens": 29437120}
{"current_steps": 30660, "total_steps": 58920, "loss": 0.0852, "lr": 1.1033146442441548e-06, "epoch": 2.6018329938900204, "percentage": 52.04, "elapsed_time": "0:48:15", "remaining_time": "0:44:28", "throughput": 10168.37, "total_tokens": 29441664}
{"current_steps": 30665, "total_steps": 58920, "loss": 0.0001, "lr": 1.1030200046998392e-06, "epoch": 2.602257298031229, "percentage": 52.05, "elapsed_time": "0:48:15", "remaining_time": "0:44:28", "throughput": 10168.73, "total_tokens": 29446656}
{"current_steps": 30670, "total_steps": 58920, "loss": 0.0228, "lr": 1.1027253561158903e-06, "epoch": 2.6026816021724373, "percentage": 52.05, "elapsed_time": "0:48:16", "remaining_time": "0:44:27", "throughput": 10169.1, "total_tokens": 29451712}
{"current_steps": 30675, "total_steps": 58920, "loss": 0.0001, "lr": 1.1024306985181624e-06, "epoch": 2.6031059063136457, "percentage": 52.06, "elapsed_time": "0:48:16", "remaining_time": "0:44:27", "throughput": 10169.59, "total_tokens": 29457216}
{"current_steps": 30680, "total_steps": 58920, "loss": 0.0001, "lr": 1.1021360319325104e-06, "epoch": 2.603530210454854, "percentage": 52.07, "elapsed_time": "0:48:16", "remaining_time": "0:44:26", "throughput": 10169.91, "total_tokens": 29462016}
{"current_steps": 30685, "total_steps": 58920, "loss": 0.0383, "lr": 1.1018413563847904e-06, "epoch": 2.6039545145960625, "percentage": 52.08, "elapsed_time": "0:48:17", "remaining_time": "0:44:26", "throughput": 10170.24, "total_tokens": 29466944}
{"current_steps": 30690, "total_steps": 58920, "loss": 0.0001, "lr": 1.1015466719008587e-06, "epoch": 2.604378818737271, "percentage": 52.09, "elapsed_time": "0:48:17", "remaining_time": "0:44:25", "throughput": 10170.66, "total_tokens": 29472192}
{"current_steps": 30695, "total_steps": 58920, "loss": 0.0446, "lr": 1.1012519785065736e-06, "epoch": 2.6048031228784794, "percentage": 52.1, "elapsed_time": "0:48:18", "remaining_time": "0:44:24", "throughput": 10170.9, "total_tokens": 29476672}
{"current_steps": 30700, "total_steps": 58920, "loss": 0.0001, "lr": 1.1009572762277927e-06, "epoch": 2.605227427019688, "percentage": 52.1, "elapsed_time": "0:48:18", "remaining_time": "0:44:24", "throughput": 10171.36, "total_tokens": 29482048}
{"current_steps": 30705, "total_steps": 58920, "loss": 0.0001, "lr": 1.1006625650903754e-06, "epoch": 2.605651731160896, "percentage": 52.11, "elapsed_time": "0:48:18", "remaining_time": "0:44:23", "throughput": 10171.59, "total_tokens": 29486528}
{"current_steps": 30710, "total_steps": 58920, "loss": 0.0001, "lr": 1.1003678451201815e-06, "epoch": 2.6060760353021046, "percentage": 52.12, "elapsed_time": "0:48:19", "remaining_time": "0:44:23", "throughput": 10171.98, "total_tokens": 29491584}
{"current_steps": 30715, "total_steps": 58920, "loss": 0.0297, "lr": 1.1000731163430718e-06, "epoch": 2.606500339443313, "percentage": 52.13, "elapsed_time": "0:48:19", "remaining_time": "0:44:22", "throughput": 10172.39, "total_tokens": 29496768}
{"current_steps": 30720, "total_steps": 58920, "loss": 0.0001, "lr": 1.099778378784907e-06, "epoch": 2.6069246435845215, "percentage": 52.14, "elapsed_time": "0:48:20", "remaining_time": "0:44:22", "throughput": 10172.57, "total_tokens": 29501056}
{"current_steps": 30725, "total_steps": 58920, "loss": 0.0001, "lr": 1.09948363247155e-06, "epoch": 2.60734894772573, "percentage": 52.15, "elapsed_time": "0:48:20", "remaining_time": "0:44:21", "throughput": 10173.16, "total_tokens": 29506944}
{"current_steps": 30730, "total_steps": 58920, "loss": 0.0038, "lr": 1.0991888774288634e-06, "epoch": 2.6077732518669383, "percentage": 52.16, "elapsed_time": "0:48:20", "remaining_time": "0:44:21", "throughput": 10173.5, "total_tokens": 29511872}
{"current_steps": 30735, "total_steps": 58920, "loss": 0.0001, "lr": 1.0988941136827108e-06, "epoch": 2.6081975560081467, "percentage": 52.16, "elapsed_time": "0:48:21", "remaining_time": "0:44:20", "throughput": 10173.6, "total_tokens": 29515904}
{"current_steps": 30740, "total_steps": 58920, "loss": 0.028, "lr": 1.098599341258957e-06, "epoch": 2.608621860149355, "percentage": 52.17, "elapsed_time": "0:48:21", "remaining_time": "0:44:19", "throughput": 10173.94, "total_tokens": 29520832}
{"current_steps": 30745, "total_steps": 58920, "loss": 0.0002, "lr": 1.0983045601834669e-06, "epoch": 2.6090461642905636, "percentage": 52.18, "elapsed_time": "0:48:21", "remaining_time": "0:44:19", "throughput": 10174.22, "total_tokens": 29525504}
{"current_steps": 30750, "total_steps": 58920, "loss": 0.0258, "lr": 1.0980097704821064e-06, "epoch": 2.609470468431772, "percentage": 52.19, "elapsed_time": "0:48:22", "remaining_time": "0:44:18", "throughput": 10174.6, "total_tokens": 29530560}
{"current_steps": 30755, "total_steps": 58920, "loss": 0.0323, "lr": 1.0977149721807424e-06, "epoch": 2.6098947725729804, "percentage": 52.2, "elapsed_time": "0:48:22", "remaining_time": "0:44:18", "throughput": 10174.92, "total_tokens": 29535360}
{"current_steps": 30760, "total_steps": 58920, "loss": 0.0422, "lr": 1.0974201653052426e-06, "epoch": 2.610319076714189, "percentage": 52.21, "elapsed_time": "0:48:23", "remaining_time": "0:44:17", "throughput": 10175.12, "total_tokens": 29539776}
{"current_steps": 30765, "total_steps": 58920, "loss": 0.0224, "lr": 1.097125349881475e-06, "epoch": 2.6107433808553973, "percentage": 52.21, "elapsed_time": "0:48:23", "remaining_time": "0:44:17", "throughput": 10175.43, "total_tokens": 29544576}
{"current_steps": 30770, "total_steps": 58920, "loss": 0.0001, "lr": 1.0968305259353085e-06, "epoch": 2.6111676849966057, "percentage": 52.22, "elapsed_time": "0:48:23", "remaining_time": "0:44:16", "throughput": 10175.74, "total_tokens": 29549376}
{"current_steps": 30775, "total_steps": 58920, "loss": 0.0002, "lr": 1.0965356934926132e-06, "epoch": 2.611591989137814, "percentage": 52.23, "elapsed_time": "0:48:24", "remaining_time": "0:44:16", "throughput": 10176.04, "total_tokens": 29554112}
{"current_steps": 30780, "total_steps": 58920, "loss": 0.0316, "lr": 1.096240852579259e-06, "epoch": 2.6120162932790225, "percentage": 52.24, "elapsed_time": "0:48:24", "remaining_time": "0:44:15", "throughput": 10176.34, "total_tokens": 29558848}
{"current_steps": 30785, "total_steps": 58920, "loss": 0.0001, "lr": 1.0959460032211174e-06, "epoch": 2.612440597420231, "percentage": 52.25, "elapsed_time": "0:48:25", "remaining_time": "0:44:14", "throughput": 10176.51, "total_tokens": 29563136}
{"current_steps": 30790, "total_steps": 58920, "loss": 0.0002, "lr": 1.0956511454440607e-06, "epoch": 2.6128649015614394, "percentage": 52.26, "elapsed_time": "0:48:25", "remaining_time": "0:44:14", "throughput": 10176.82, "total_tokens": 29567872}
{"current_steps": 30795, "total_steps": 58920, "loss": 0.0291, "lr": 1.0953562792739612e-06, "epoch": 2.6132892057026478, "percentage": 52.27, "elapsed_time": "0:48:25", "remaining_time": "0:44:13", "throughput": 10177.0, "total_tokens": 29572160}
{"current_steps": 30800, "total_steps": 58920, "loss": 0.0003, "lr": 1.0950614047366928e-06, "epoch": 2.613713509843856, "percentage": 52.27, "elapsed_time": "0:48:26", "remaining_time": "0:44:13", "throughput": 10177.36, "total_tokens": 29577152}
{"current_steps": 30805, "total_steps": 58920, "loss": 0.0001, "lr": 1.0947665218581292e-06, "epoch": 2.6141378139850646, "percentage": 52.28, "elapsed_time": "0:48:26", "remaining_time": "0:44:12", "throughput": 10177.75, "total_tokens": 29582272}
{"current_steps": 30810, "total_steps": 58920, "loss": 0.0188, "lr": 1.0944716306641453e-06, "epoch": 2.614562118126273, "percentage": 52.29, "elapsed_time": "0:48:26", "remaining_time": "0:44:12", "throughput": 10177.98, "total_tokens": 29586752}
{"current_steps": 30815, "total_steps": 58920, "loss": 0.0003, "lr": 1.0941767311806169e-06, "epoch": 2.6149864222674815, "percentage": 52.3, "elapsed_time": "0:48:27", "remaining_time": "0:44:11", "throughput": 10178.37, "total_tokens": 29591872}
{"current_steps": 30820, "total_steps": 58920, "loss": 0.0448, "lr": 1.0938818234334205e-06, "epoch": 2.61541072640869, "percentage": 52.31, "elapsed_time": "0:48:27", "remaining_time": "0:44:11", "throughput": 10178.48, "total_tokens": 29595968}
{"current_steps": 30825, "total_steps": 58920, "loss": 0.0674, "lr": 1.093586907448433e-06, "epoch": 2.6158350305498983, "percentage": 52.32, "elapsed_time": "0:48:28", "remaining_time": "0:44:10", "throughput": 10178.69, "total_tokens": 29600384}
{"current_steps": 30830, "total_steps": 58920, "loss": 0.0002, "lr": 1.0932919832515322e-06, "epoch": 2.6162593346911067, "percentage": 52.33, "elapsed_time": "0:48:28", "remaining_time": "0:44:09", "throughput": 10178.96, "total_tokens": 29605056}
{"current_steps": 30835, "total_steps": 58920, "loss": 0.0002, "lr": 1.0929970508685968e-06, "epoch": 2.616683638832315, "percentage": 52.33, "elapsed_time": "0:48:28", "remaining_time": "0:44:09", "throughput": 10179.46, "total_tokens": 29610560}
{"current_steps": 30840, "total_steps": 58920, "loss": 0.0003, "lr": 1.0927021103255058e-06, "epoch": 2.6171079429735236, "percentage": 52.34, "elapsed_time": "0:48:29", "remaining_time": "0:44:08", "throughput": 10179.77, "total_tokens": 29615360}
{"current_steps": 30845, "total_steps": 58920, "loss": 0.0394, "lr": 1.0924071616481394e-06, "epoch": 2.617532247114732, "percentage": 52.35, "elapsed_time": "0:48:29", "remaining_time": "0:44:08", "throughput": 10180.06, "total_tokens": 29620096}
{"current_steps": 30850, "total_steps": 58920, "loss": 0.0002, "lr": 1.0921122048623783e-06, "epoch": 2.6179565512559404, "percentage": 52.36, "elapsed_time": "0:48:29", "remaining_time": "0:44:07", "throughput": 10180.3, "total_tokens": 29624640}
{"current_steps": 30855, "total_steps": 58920, "loss": 0.0001, "lr": 1.0918172399941037e-06, "epoch": 2.618380855397149, "percentage": 52.37, "elapsed_time": "0:48:30", "remaining_time": "0:44:07", "throughput": 10180.51, "total_tokens": 29629056}
{"current_steps": 30860, "total_steps": 58920, "loss": 0.0002, "lr": 1.091522267069198e-06, "epoch": 2.6188051595383572, "percentage": 52.38, "elapsed_time": "0:48:30", "remaining_time": "0:44:06", "throughput": 10180.85, "total_tokens": 29633984}
{"current_steps": 30865, "total_steps": 58920, "loss": 0.0002, "lr": 1.0912272861135434e-06, "epoch": 2.6192294636795657, "percentage": 52.38, "elapsed_time": "0:48:31", "remaining_time": "0:44:06", "throughput": 10181.47, "total_tokens": 29639936}
{"current_steps": 30870, "total_steps": 58920, "loss": 0.0002, "lr": 1.090932297153024e-06, "epoch": 2.619653767820774, "percentage": 52.39, "elapsed_time": "0:48:31", "remaining_time": "0:44:05", "throughput": 10181.83, "total_tokens": 29644928}
{"current_steps": 30875, "total_steps": 58920, "loss": 0.0002, "lr": 1.0906373002135239e-06, "epoch": 2.6200780719619825, "percentage": 52.4, "elapsed_time": "0:48:31", "remaining_time": "0:44:05", "throughput": 10182.07, "total_tokens": 29649408}
{"current_steps": 30880, "total_steps": 58920, "loss": 0.043, "lr": 1.0903422953209278e-06, "epoch": 2.620502376103191, "percentage": 52.41, "elapsed_time": "0:48:32", "remaining_time": "0:44:04", "throughput": 10182.3, "total_tokens": 29653888}
{"current_steps": 30885, "total_steps": 58920, "loss": 0.0001, "lr": 1.0900472825011218e-06, "epoch": 2.6209266802443993, "percentage": 52.42, "elapsed_time": "0:48:32", "remaining_time": "0:44:03", "throughput": 10182.5, "total_tokens": 29658240}
{"current_steps": 30890, "total_steps": 58920, "loss": 0.0001, "lr": 1.0897522617799916e-06, "epoch": 2.6213509843856078, "percentage": 52.43, "elapsed_time": "0:48:33", "remaining_time": "0:44:03", "throughput": 10182.77, "total_tokens": 29662912}
{"current_steps": 30895, "total_steps": 58920, "loss": 0.0002, "lr": 1.0894572331834247e-06, "epoch": 2.621775288526816, "percentage": 52.44, "elapsed_time": "0:48:33", "remaining_time": "0:44:02", "throughput": 10183.16, "total_tokens": 29668032}
{"current_steps": 30900, "total_steps": 58920, "loss": 0.0001, "lr": 1.0891621967373083e-06, "epoch": 2.6221995926680246, "percentage": 52.44, "elapsed_time": "0:48:33", "remaining_time": "0:44:02", "throughput": 10183.61, "total_tokens": 29673344}
{"current_steps": 30905, "total_steps": 58920, "loss": 0.0129, "lr": 1.088867152467531e-06, "epoch": 2.622623896809233, "percentage": 52.45, "elapsed_time": "0:48:34", "remaining_time": "0:44:01", "throughput": 10184.0, "total_tokens": 29678464}
{"current_steps": 30910, "total_steps": 58920, "loss": 0.0, "lr": 1.0885721003999821e-06, "epoch": 2.623048200950441, "percentage": 52.46, "elapsed_time": "0:48:34", "remaining_time": "0:44:01", "throughput": 10184.19, "total_tokens": 29682816}
{"current_steps": 30915, "total_steps": 58920, "loss": 0.0305, "lr": 1.0882770405605511e-06, "epoch": 2.62347250509165, "percentage": 52.47, "elapsed_time": "0:48:34", "remaining_time": "0:44:00", "throughput": 10184.47, "total_tokens": 29687552}
{"current_steps": 30920, "total_steps": 58920, "loss": 0.0001, "lr": 1.0879819729751287e-06, "epoch": 2.623896809232858, "percentage": 52.48, "elapsed_time": "0:48:35", "remaining_time": "0:44:00", "throughput": 10184.76, "total_tokens": 29692288}
{"current_steps": 30925, "total_steps": 58920, "loss": 0.0001, "lr": 1.0876868976696058e-06, "epoch": 2.6243211133740667, "percentage": 52.49, "elapsed_time": "0:48:35", "remaining_time": "0:43:59", "throughput": 10184.9, "total_tokens": 29696448}
{"current_steps": 30930, "total_steps": 58920, "loss": 0.0609, "lr": 1.0873918146698742e-06, "epoch": 2.6247454175152747, "percentage": 52.49, "elapsed_time": "0:48:36", "remaining_time": "0:43:58", "throughput": 10185.09, "total_tokens": 29700800}
{"current_steps": 30935, "total_steps": 58920, "loss": 0.0366, "lr": 1.0870967240018261e-06, "epoch": 2.6251697216564835, "percentage": 52.5, "elapsed_time": "0:48:36", "remaining_time": "0:43:58", "throughput": 10185.37, "total_tokens": 29705472}
{"current_steps": 30940, "total_steps": 58920, "loss": 0.0001, "lr": 1.0868016256913553e-06, "epoch": 2.6255940257976915, "percentage": 52.51, "elapsed_time": "0:48:36", "remaining_time": "0:43:57", "throughput": 10185.77, "total_tokens": 29710592}
{"current_steps": 30945, "total_steps": 58920, "loss": 0.0302, "lr": 1.086506519764355e-06, "epoch": 2.6260183299389004, "percentage": 52.52, "elapsed_time": "0:48:37", "remaining_time": "0:43:57", "throughput": 10186.17, "total_tokens": 29715712}
{"current_steps": 30950, "total_steps": 58920, "loss": 0.0807, "lr": 1.08621140624672e-06, "epoch": 2.6264426340801084, "percentage": 52.53, "elapsed_time": "0:48:37", "remaining_time": "0:43:56", "throughput": 10186.49, "total_tokens": 29720576}
{"current_steps": 30955, "total_steps": 58920, "loss": 0.0004, "lr": 1.0859162851643453e-06, "epoch": 2.6268669382213172, "percentage": 52.54, "elapsed_time": "0:48:38", "remaining_time": "0:43:56", "throughput": 10186.75, "total_tokens": 29725184}
{"current_steps": 30960, "total_steps": 58920, "loss": 0.0002, "lr": 1.085621156543127e-06, "epoch": 2.627291242362525, "percentage": 52.55, "elapsed_time": "0:48:38", "remaining_time": "0:43:55", "throughput": 10187.23, "total_tokens": 29730624}
{"current_steps": 30965, "total_steps": 58920, "loss": 0.0001, "lr": 1.0853260204089612e-06, "epoch": 2.627715546503734, "percentage": 52.55, "elapsed_time": "0:48:38", "remaining_time": "0:43:55", "throughput": 10187.75, "total_tokens": 29736192}
{"current_steps": 30970, "total_steps": 58920, "loss": 0.0001, "lr": 1.0850308767877453e-06, "epoch": 2.628139850644942, "percentage": 52.56, "elapsed_time": "0:48:39", "remaining_time": "0:43:54", "throughput": 10187.86, "total_tokens": 29740288}
{"current_steps": 30975, "total_steps": 58920, "loss": 0.0021, "lr": 1.0847357257053767e-06, "epoch": 2.628564154786151, "percentage": 52.57, "elapsed_time": "0:48:39", "remaining_time": "0:43:53", "throughput": 10188.11, "total_tokens": 29744832}
{"current_steps": 30980, "total_steps": 58920, "loss": 0.0397, "lr": 1.0844405671877544e-06, "epoch": 2.628988458927359, "percentage": 52.58, "elapsed_time": "0:48:39", "remaining_time": "0:43:53", "throughput": 10188.35, "total_tokens": 29749376}
{"current_steps": 30985, "total_steps": 58920, "loss": 0.0002, "lr": 1.0841454012607769e-06, "epoch": 2.6294127630685677, "percentage": 52.59, "elapsed_time": "0:48:40", "remaining_time": "0:43:52", "throughput": 10188.52, "total_tokens": 29753664}
{"current_steps": 30990, "total_steps": 58920, "loss": 0.0001, "lr": 1.0838502279503446e-06, "epoch": 2.6298370672097757, "percentage": 52.6, "elapsed_time": "0:48:40", "remaining_time": "0:43:52", "throughput": 10188.8, "total_tokens": 29758336}
{"current_steps": 30995, "total_steps": 58920, "loss": 0.0005, "lr": 1.0835550472823571e-06, "epoch": 2.6302613713509846, "percentage": 52.61, "elapsed_time": "0:48:41", "remaining_time": "0:43:51", "throughput": 10189.04, "total_tokens": 29762880}
{"current_steps": 31000, "total_steps": 58920, "loss": 0.0423, "lr": 1.083259859282716e-06, "epoch": 2.6306856754921926, "percentage": 52.61, "elapsed_time": "0:48:41", "remaining_time": "0:43:51", "throughput": 10189.26, "total_tokens": 29767296}
{"current_steps": 31005, "total_steps": 58920, "loss": 0.0009, "lr": 1.0829646639773228e-06, "epoch": 2.6311099796334014, "percentage": 52.62, "elapsed_time": "0:48:41", "remaining_time": "0:43:50", "throughput": 10189.76, "total_tokens": 29772864}
{"current_steps": 31010, "total_steps": 58920, "loss": 0.0188, "lr": 1.0826694613920804e-06, "epoch": 2.6315342837746094, "percentage": 52.63, "elapsed_time": "0:48:42", "remaining_time": "0:43:50", "throughput": 10190.18, "total_tokens": 29778112}
{"current_steps": 31015, "total_steps": 58920, "loss": 0.0078, "lr": 1.082374251552891e-06, "epoch": 2.6319585879158183, "percentage": 52.64, "elapsed_time": "0:48:42", "remaining_time": "0:43:49", "throughput": 10190.58, "total_tokens": 29783232}
{"current_steps": 31020, "total_steps": 58920, "loss": 0.0002, "lr": 1.0820790344856584e-06, "epoch": 2.6323828920570262, "percentage": 52.65, "elapsed_time": "0:48:43", "remaining_time": "0:43:49", "throughput": 10191.06, "total_tokens": 29788672}
{"current_steps": 31025, "total_steps": 58920, "loss": 0.0478, "lr": 1.0817838102162864e-06, "epoch": 2.632807196198235, "percentage": 52.66, "elapsed_time": "0:48:43", "remaining_time": "0:43:48", "throughput": 10191.22, "total_tokens": 29792896}
{"current_steps": 31030, "total_steps": 58920, "loss": 0.0305, "lr": 1.0814885787706808e-06, "epoch": 2.633231500339443, "percentage": 52.66, "elapsed_time": "0:48:43", "remaining_time": "0:43:47", "throughput": 10191.5, "total_tokens": 29797632}
{"current_steps": 31035, "total_steps": 58920, "loss": 0.0247, "lr": 1.0811933401747466e-06, "epoch": 2.633655804480652, "percentage": 52.67, "elapsed_time": "0:48:44", "remaining_time": "0:43:47", "throughput": 10191.75, "total_tokens": 29802240}
{"current_steps": 31040, "total_steps": 58920, "loss": 0.0041, "lr": 1.0808980944543897e-06, "epoch": 2.63408010862186, "percentage": 52.68, "elapsed_time": "0:48:44", "remaining_time": "0:43:46", "throughput": 10192.01, "total_tokens": 29806848}
{"current_steps": 31045, "total_steps": 58920, "loss": 0.0006, "lr": 1.0806028416355175e-06, "epoch": 2.634504412763069, "percentage": 52.69, "elapsed_time": "0:48:44", "remaining_time": "0:43:46", "throughput": 10192.53, "total_tokens": 29812480}
{"current_steps": 31050, "total_steps": 58920, "loss": 0.0208, "lr": 1.0803075817440368e-06, "epoch": 2.6349287169042768, "percentage": 52.7, "elapsed_time": "0:48:45", "remaining_time": "0:43:45", "throughput": 10192.89, "total_tokens": 29817472}
{"current_steps": 31055, "total_steps": 58920, "loss": 0.0001, "lr": 1.0800123148058555e-06, "epoch": 2.6353530210454856, "percentage": 52.71, "elapsed_time": "0:48:45", "remaining_time": "0:43:45", "throughput": 10193.3, "total_tokens": 29822656}
{"current_steps": 31060, "total_steps": 58920, "loss": 0.0262, "lr": 1.0797170408468828e-06, "epoch": 2.6357773251866936, "percentage": 52.72, "elapsed_time": "0:48:46", "remaining_time": "0:43:44", "throughput": 10193.74, "total_tokens": 29827968}
{"current_steps": 31065, "total_steps": 58920, "loss": 0.0001, "lr": 1.0794217598930275e-06, "epoch": 2.6362016293279025, "percentage": 52.72, "elapsed_time": "0:48:46", "remaining_time": "0:43:44", "throughput": 10194.42, "total_tokens": 29834176}
{"current_steps": 31070, "total_steps": 58920, "loss": 0.0002, "lr": 1.0791264719701993e-06, "epoch": 2.6366259334691104, "percentage": 52.73, "elapsed_time": "0:48:46", "remaining_time": "0:43:43", "throughput": 10194.71, "total_tokens": 29838848}
{"current_steps": 31075, "total_steps": 58920, "loss": 0.0204, "lr": 1.078831177104309e-06, "epoch": 2.6370502376103193, "percentage": 52.74, "elapsed_time": "0:48:47", "remaining_time": "0:43:43", "throughput": 10195.22, "total_tokens": 29844416}
{"current_steps": 31080, "total_steps": 58920, "loss": 0.0006, "lr": 1.0785358753212677e-06, "epoch": 2.6374745417515273, "percentage": 52.75, "elapsed_time": "0:48:47", "remaining_time": "0:43:42", "throughput": 10195.56, "total_tokens": 29849344}
{"current_steps": 31085, "total_steps": 58920, "loss": 0.0774, "lr": 1.0782405666469867e-06, "epoch": 2.637898845892736, "percentage": 52.76, "elapsed_time": "0:48:48", "remaining_time": "0:43:41", "throughput": 10195.97, "total_tokens": 29854592}
{"current_steps": 31090, "total_steps": 58920, "loss": 0.0, "lr": 1.0779452511073786e-06, "epoch": 2.638323150033944, "percentage": 52.77, "elapsed_time": "0:48:48", "remaining_time": "0:43:41", "throughput": 10196.26, "total_tokens": 29859328}
{"current_steps": 31095, "total_steps": 58920, "loss": 0.0002, "lr": 1.077649928728356e-06, "epoch": 2.638747454175153, "percentage": 52.77, "elapsed_time": "0:48:48", "remaining_time": "0:43:40", "throughput": 10196.5, "total_tokens": 29863872}
{"current_steps": 31100, "total_steps": 58920, "loss": 0.0481, "lr": 1.0773545995358326e-06, "epoch": 2.639171758316361, "percentage": 52.78, "elapsed_time": "0:48:49", "remaining_time": "0:43:40", "throughput": 10196.85, "total_tokens": 29868800}
{"current_steps": 31105, "total_steps": 58920, "loss": 0.0317, "lr": 1.0770592635557224e-06, "epoch": 2.63959606245757, "percentage": 52.79, "elapsed_time": "0:48:49", "remaining_time": "0:43:39", "throughput": 10197.13, "total_tokens": 29873536}
{"current_steps": 31110, "total_steps": 58920, "loss": 0.0002, "lr": 1.07676392081394e-06, "epoch": 2.640020366598778, "percentage": 52.8, "elapsed_time": "0:48:49", "remaining_time": "0:43:39", "throughput": 10197.33, "total_tokens": 29877952}
{"current_steps": 31115, "total_steps": 58920, "loss": 0.021, "lr": 1.0764685713364008e-06, "epoch": 2.6404446707399867, "percentage": 52.81, "elapsed_time": "0:48:50", "remaining_time": "0:43:38", "throughput": 10197.56, "total_tokens": 29882432}
{"current_steps": 31120, "total_steps": 58920, "loss": 0.0002, "lr": 1.07617321514902e-06, "epoch": 2.6408689748811947, "percentage": 52.82, "elapsed_time": "0:48:50", "remaining_time": "0:43:38", "throughput": 10197.86, "total_tokens": 29887168}
{"current_steps": 31125, "total_steps": 58920, "loss": 0.0001, "lr": 1.0758778522777153e-06, "epoch": 2.6412932790224035, "percentage": 52.83, "elapsed_time": "0:48:51", "remaining_time": "0:43:37", "throughput": 10198.3, "total_tokens": 29892480}
{"current_steps": 31130, "total_steps": 58920, "loss": 0.0001, "lr": 1.0755824827484026e-06, "epoch": 2.6417175831636115, "percentage": 52.83, "elapsed_time": "0:48:51", "remaining_time": "0:43:36", "throughput": 10198.65, "total_tokens": 29897472}
{"current_steps": 31135, "total_steps": 58920, "loss": 0.0003, "lr": 1.0752871065870003e-06, "epoch": 2.6421418873048204, "percentage": 52.84, "elapsed_time": "0:48:51", "remaining_time": "0:43:36", "throughput": 10198.91, "total_tokens": 29902080}
{"current_steps": 31140, "total_steps": 58920, "loss": 0.0233, "lr": 1.0749917238194263e-06, "epoch": 2.6425661914460283, "percentage": 52.85, "elapsed_time": "0:48:52", "remaining_time": "0:43:35", "throughput": 10199.26, "total_tokens": 29907008}
{"current_steps": 31145, "total_steps": 58920, "loss": 0.0001, "lr": 1.0746963344715986e-06, "epoch": 2.642990495587237, "percentage": 52.86, "elapsed_time": "0:48:52", "remaining_time": "0:43:35", "throughput": 10199.64, "total_tokens": 29912064}
{"current_steps": 31150, "total_steps": 58920, "loss": 0.0487, "lr": 1.0744009385694374e-06, "epoch": 2.643414799728445, "percentage": 52.87, "elapsed_time": "0:48:53", "remaining_time": "0:43:34", "throughput": 10200.07, "total_tokens": 29917312}
{"current_steps": 31155, "total_steps": 58920, "loss": 0.0001, "lr": 1.074105536138863e-06, "epoch": 2.643839103869654, "percentage": 52.88, "elapsed_time": "0:48:53", "remaining_time": "0:43:34", "throughput": 10200.24, "total_tokens": 29921664}
{"current_steps": 31160, "total_steps": 58920, "loss": 0.0238, "lr": 1.073810127205795e-06, "epoch": 2.644263408010862, "percentage": 52.89, "elapsed_time": "0:48:53", "remaining_time": "0:43:33", "throughput": 10200.82, "total_tokens": 29927488}
{"current_steps": 31165, "total_steps": 58920, "loss": 0.0003, "lr": 1.073514711796155e-06, "epoch": 2.644687712152071, "percentage": 52.89, "elapsed_time": "0:48:54", "remaining_time": "0:43:33", "throughput": 10201.12, "total_tokens": 29932288}
{"current_steps": 31170, "total_steps": 58920, "loss": 0.0001, "lr": 1.0732192899358644e-06, "epoch": 2.645112016293279, "percentage": 52.9, "elapsed_time": "0:48:54", "remaining_time": "0:43:32", "throughput": 10201.35, "total_tokens": 29936832}
{"current_steps": 31175, "total_steps": 58920, "loss": 0.0295, "lr": 1.0729238616508453e-06, "epoch": 2.6455363204344873, "percentage": 52.91, "elapsed_time": "0:48:54", "remaining_time": "0:43:32", "throughput": 10201.64, "total_tokens": 29941568}
{"current_steps": 31180, "total_steps": 58920, "loss": 0.0001, "lr": 1.0726284269670208e-06, "epoch": 2.6459606245756957, "percentage": 52.92, "elapsed_time": "0:48:55", "remaining_time": "0:43:31", "throughput": 10201.88, "total_tokens": 29946112}
{"current_steps": 31185, "total_steps": 58920, "loss": 0.0401, "lr": 1.072332985910314e-06, "epoch": 2.646384928716904, "percentage": 52.93, "elapsed_time": "0:48:55", "remaining_time": "0:43:30", "throughput": 10202.27, "total_tokens": 29951232}
{"current_steps": 31190, "total_steps": 58920, "loss": 0.0142, "lr": 1.0720375385066486e-06, "epoch": 2.6468092328581125, "percentage": 52.94, "elapsed_time": "0:48:56", "remaining_time": "0:43:30", "throughput": 10202.43, "total_tokens": 29955520}
{"current_steps": 31195, "total_steps": 58920, "loss": 0.0122, "lr": 1.07174208478195e-06, "epoch": 2.647233536999321, "percentage": 52.94, "elapsed_time": "0:48:56", "remaining_time": "0:43:29", "throughput": 10202.76, "total_tokens": 29960384}
{"current_steps": 31200, "total_steps": 58920, "loss": 0.0267, "lr": 1.0714466247621416e-06, "epoch": 2.6476578411405294, "percentage": 52.95, "elapsed_time": "0:48:56", "remaining_time": "0:43:29", "throughput": 10202.92, "total_tokens": 29964608}
{"current_steps": 31205, "total_steps": 58920, "loss": 0.0001, "lr": 1.0711511584731506e-06, "epoch": 2.648082145281738, "percentage": 52.96, "elapsed_time": "0:48:57", "remaining_time": "0:43:28", "throughput": 10203.22, "total_tokens": 29969408}
{"current_steps": 31210, "total_steps": 58920, "loss": 0.0071, "lr": 1.0708556859409016e-06, "epoch": 2.648506449422946, "percentage": 52.97, "elapsed_time": "0:48:57", "remaining_time": "0:43:28", "throughput": 10203.42, "total_tokens": 29973824}
{"current_steps": 31215, "total_steps": 58920, "loss": 0.0002, "lr": 1.0705602071913224e-06, "epoch": 2.6489307535641546, "percentage": 52.98, "elapsed_time": "0:48:58", "remaining_time": "0:43:27", "throughput": 10203.71, "total_tokens": 29978560}
{"current_steps": 31220, "total_steps": 58920, "loss": 0.0002, "lr": 1.07026472225034e-06, "epoch": 2.649355057705363, "percentage": 52.99, "elapsed_time": "0:48:58", "remaining_time": "0:43:27", "throughput": 10204.0, "total_tokens": 29983296}
{"current_steps": 31225, "total_steps": 58920, "loss": 0.0001, "lr": 1.0699692311438817e-06, "epoch": 2.6497793618465715, "percentage": 53.0, "elapsed_time": "0:48:58", "remaining_time": "0:43:26", "throughput": 10204.28, "total_tokens": 29987968}
{"current_steps": 31230, "total_steps": 58920, "loss": 0.0001, "lr": 1.069673733897876e-06, "epoch": 2.65020366598778, "percentage": 53.0, "elapsed_time": "0:48:59", "remaining_time": "0:43:25", "throughput": 10204.56, "total_tokens": 29992704}
{"current_steps": 31235, "total_steps": 58920, "loss": 0.0001, "lr": 1.0693782305382514e-06, "epoch": 2.6506279701289883, "percentage": 53.01, "elapsed_time": "0:48:59", "remaining_time": "0:43:25", "throughput": 10204.82, "total_tokens": 29997376}
{"current_steps": 31240, "total_steps": 58920, "loss": 0.0001, "lr": 1.0690827210909378e-06, "epoch": 2.6510522742701967, "percentage": 53.02, "elapsed_time": "0:48:59", "remaining_time": "0:43:24", "throughput": 10205.41, "total_tokens": 30003264}
{"current_steps": 31245, "total_steps": 58920, "loss": 0.0001, "lr": 1.0687872055818647e-06, "epoch": 2.651476578411405, "percentage": 53.03, "elapsed_time": "0:49:00", "remaining_time": "0:43:24", "throughput": 10205.81, "total_tokens": 30008448}
{"current_steps": 31250, "total_steps": 58920, "loss": 0.0001, "lr": 1.068491684036963e-06, "epoch": 2.6519008825526136, "percentage": 53.04, "elapsed_time": "0:49:00", "remaining_time": "0:43:23", "throughput": 10206.15, "total_tokens": 30013376}
{"current_steps": 31255, "total_steps": 58920, "loss": 0.0002, "lr": 1.0681961564821632e-06, "epoch": 2.652325186693822, "percentage": 53.05, "elapsed_time": "0:49:01", "remaining_time": "0:43:23", "throughput": 10206.44, "total_tokens": 30018112}
{"current_steps": 31260, "total_steps": 58920, "loss": 0.0001, "lr": 1.0679006229433968e-06, "epoch": 2.6527494908350304, "percentage": 53.05, "elapsed_time": "0:49:01", "remaining_time": "0:43:22", "throughput": 10206.71, "total_tokens": 30022784}
{"current_steps": 31265, "total_steps": 58920, "loss": 0.0387, "lr": 1.067605083446596e-06, "epoch": 2.653173794976239, "percentage": 53.06, "elapsed_time": "0:49:01", "remaining_time": "0:43:22", "throughput": 10206.96, "total_tokens": 30027392}
{"current_steps": 31270, "total_steps": 58920, "loss": 0.0215, "lr": 1.067309538017693e-06, "epoch": 2.6535980991174473, "percentage": 53.07, "elapsed_time": "0:49:02", "remaining_time": "0:43:21", "throughput": 10207.14, "total_tokens": 30031744}
{"current_steps": 31275, "total_steps": 58920, "loss": 0.0269, "lr": 1.0670139866826211e-06, "epoch": 2.6540224032586557, "percentage": 53.08, "elapsed_time": "0:49:02", "remaining_time": "0:43:21", "throughput": 10207.4, "total_tokens": 30036352}
{"current_steps": 31280, "total_steps": 58920, "loss": 0.0001, "lr": 1.066718429467314e-06, "epoch": 2.654446707399864, "percentage": 53.09, "elapsed_time": "0:49:02", "remaining_time": "0:43:20", "throughput": 10207.64, "total_tokens": 30040896}
{"current_steps": 31285, "total_steps": 58920, "loss": 0.0224, "lr": 1.0664228663977055e-06, "epoch": 2.6548710115410725, "percentage": 53.1, "elapsed_time": "0:49:03", "remaining_time": "0:43:19", "throughput": 10208.0, "total_tokens": 30045952}
{"current_steps": 31290, "total_steps": 58920, "loss": 0.0002, "lr": 1.0661272974997305e-06, "epoch": 2.655295315682281, "percentage": 53.11, "elapsed_time": "0:49:03", "remaining_time": "0:43:19", "throughput": 10208.57, "total_tokens": 30051776}
{"current_steps": 31295, "total_steps": 58920, "loss": 0.027, "lr": 1.0658317227993237e-06, "epoch": 2.6557196198234894, "percentage": 53.11, "elapsed_time": "0:49:04", "remaining_time": "0:43:18", "throughput": 10208.87, "total_tokens": 30056576}
{"current_steps": 31300, "total_steps": 58920, "loss": 0.0661, "lr": 1.0655361423224208e-06, "epoch": 2.656143923964698, "percentage": 53.12, "elapsed_time": "0:49:04", "remaining_time": "0:43:18", "throughput": 10209.15, "total_tokens": 30061312}
{"current_steps": 31305, "total_steps": 58920, "loss": 0.0005, "lr": 1.0652405560949582e-06, "epoch": 2.656568228105906, "percentage": 53.13, "elapsed_time": "0:49:04", "remaining_time": "0:43:17", "throughput": 10209.45, "total_tokens": 30066112}
{"current_steps": 31310, "total_steps": 58920, "loss": 0.061, "lr": 1.0649449641428722e-06, "epoch": 2.6569925322471146, "percentage": 53.14, "elapsed_time": "0:49:05", "remaining_time": "0:43:17", "throughput": 10209.79, "total_tokens": 30071040}
{"current_steps": 31315, "total_steps": 58920, "loss": 0.0385, "lr": 1.0646493664921004e-06, "epoch": 2.657416836388323, "percentage": 53.15, "elapsed_time": "0:49:05", "remaining_time": "0:43:16", "throughput": 10210.02, "total_tokens": 30075520}
{"current_steps": 31320, "total_steps": 58920, "loss": 0.0001, "lr": 1.0643537631685797e-06, "epoch": 2.6578411405295315, "percentage": 53.16, "elapsed_time": "0:49:06", "remaining_time": "0:43:16", "throughput": 10210.27, "total_tokens": 30080128}
{"current_steps": 31325, "total_steps": 58920, "loss": 0.0001, "lr": 1.064058154198249e-06, "epoch": 2.65826544467074, "percentage": 53.17, "elapsed_time": "0:49:06", "remaining_time": "0:43:15", "throughput": 10210.62, "total_tokens": 30085056}
{"current_steps": 31330, "total_steps": 58920, "loss": 0.0, "lr": 1.0637625396070461e-06, "epoch": 2.6586897488119483, "percentage": 53.17, "elapsed_time": "0:49:06", "remaining_time": "0:43:15", "throughput": 10210.92, "total_tokens": 30089920}
{"current_steps": 31335, "total_steps": 58920, "loss": 0.0364, "lr": 1.0634669194209108e-06, "epoch": 2.6591140529531567, "percentage": 53.18, "elapsed_time": "0:49:07", "remaining_time": "0:43:14", "throughput": 10211.17, "total_tokens": 30094528}
{"current_steps": 31340, "total_steps": 58920, "loss": 0.0002, "lr": 1.0631712936657825e-06, "epoch": 2.659538357094365, "percentage": 53.19, "elapsed_time": "0:49:07", "remaining_time": "0:43:13", "throughput": 10211.4, "total_tokens": 30099008}
{"current_steps": 31345, "total_steps": 58920, "loss": 0.0003, "lr": 1.0628756623676013e-06, "epoch": 2.6599626612355736, "percentage": 53.2, "elapsed_time": "0:49:07", "remaining_time": "0:43:13", "throughput": 10211.87, "total_tokens": 30104448}
{"current_steps": 31350, "total_steps": 58920, "loss": 0.0481, "lr": 1.062580025552308e-06, "epoch": 2.660386965376782, "percentage": 53.21, "elapsed_time": "0:49:08", "remaining_time": "0:43:12", "throughput": 10212.13, "total_tokens": 30109056}
{"current_steps": 31355, "total_steps": 58920, "loss": 0.0373, "lr": 1.062284383245843e-06, "epoch": 2.6608112695179904, "percentage": 53.22, "elapsed_time": "0:49:08", "remaining_time": "0:43:12", "throughput": 10212.5, "total_tokens": 30114112}
{"current_steps": 31360, "total_steps": 58920, "loss": 0.0002, "lr": 1.0619887354741484e-06, "epoch": 2.661235573659199, "percentage": 53.22, "elapsed_time": "0:49:09", "remaining_time": "0:43:11", "throughput": 10212.76, "total_tokens": 30118784}
{"current_steps": 31365, "total_steps": 58920, "loss": 0.0246, "lr": 1.0616930822631655e-06, "epoch": 2.6616598778004072, "percentage": 53.23, "elapsed_time": "0:49:09", "remaining_time": "0:43:11", "throughput": 10213.18, "total_tokens": 30124032}
{"current_steps": 31370, "total_steps": 58920, "loss": 0.0204, "lr": 1.0613974236388382e-06, "epoch": 2.6620841819416157, "percentage": 53.24, "elapsed_time": "0:49:09", "remaining_time": "0:43:10", "throughput": 10213.45, "total_tokens": 30128704}
{"current_steps": 31375, "total_steps": 58920, "loss": 0.0026, "lr": 1.061101759627108e-06, "epoch": 2.662508486082824, "percentage": 53.25, "elapsed_time": "0:49:10", "remaining_time": "0:43:10", "throughput": 10213.72, "total_tokens": 30133376}
{"current_steps": 31380, "total_steps": 58920, "loss": 0.0409, "lr": 1.0608060902539194e-06, "epoch": 2.6629327902240325, "percentage": 53.26, "elapsed_time": "0:49:10", "remaining_time": "0:43:09", "throughput": 10214.02, "total_tokens": 30138176}
{"current_steps": 31385, "total_steps": 58920, "loss": 0.0329, "lr": 1.0605104155452163e-06, "epoch": 2.663357094365241, "percentage": 53.27, "elapsed_time": "0:49:11", "remaining_time": "0:43:09", "throughput": 10214.22, "total_tokens": 30142592}
{"current_steps": 31390, "total_steps": 58920, "loss": 0.0016, "lr": 1.0602147355269422e-06, "epoch": 2.6637813985064493, "percentage": 53.28, "elapsed_time": "0:49:11", "remaining_time": "0:43:08", "throughput": 10214.5, "total_tokens": 30147328}
{"current_steps": 31395, "total_steps": 58920, "loss": 0.0003, "lr": 1.0599190502250423e-06, "epoch": 2.6642057026476578, "percentage": 53.28, "elapsed_time": "0:49:11", "remaining_time": "0:43:07", "throughput": 10214.74, "total_tokens": 30151872}
{"current_steps": 31400, "total_steps": 58920, "loss": 0.0002, "lr": 1.0596233596654622e-06, "epoch": 2.664630006788866, "percentage": 53.29, "elapsed_time": "0:49:12", "remaining_time": "0:43:07", "throughput": 10214.9, "total_tokens": 30156160}
{"current_steps": 31405, "total_steps": 58920, "loss": 0.0001, "lr": 1.0593276638741478e-06, "epoch": 2.6650543109300746, "percentage": 53.3, "elapsed_time": "0:49:12", "remaining_time": "0:43:06", "throughput": 10215.26, "total_tokens": 30161152}
{"current_steps": 31410, "total_steps": 58920, "loss": 0.0003, "lr": 1.059031962877045e-06, "epoch": 2.665478615071283, "percentage": 53.31, "elapsed_time": "0:49:12", "remaining_time": "0:43:06", "throughput": 10215.69, "total_tokens": 30166464}
{"current_steps": 31415, "total_steps": 58920, "loss": 0.0001, "lr": 1.0587362567001006e-06, "epoch": 2.6659029192124915, "percentage": 53.32, "elapsed_time": "0:49:13", "remaining_time": "0:43:05", "throughput": 10215.83, "total_tokens": 30170688}
{"current_steps": 31420, "total_steps": 58920, "loss": 0.0244, "lr": 1.0584405453692616e-06, "epoch": 2.6663272233537, "percentage": 53.33, "elapsed_time": "0:49:13", "remaining_time": "0:43:05", "throughput": 10216.15, "total_tokens": 30175488}
{"current_steps": 31425, "total_steps": 58920, "loss": 0.0002, "lr": 1.0581448289104758e-06, "epoch": 2.6667515274949083, "percentage": 53.34, "elapsed_time": "0:49:14", "remaining_time": "0:43:04", "throughput": 10216.43, "total_tokens": 30180224}
{"current_steps": 31430, "total_steps": 58920, "loss": 0.0967, "lr": 1.0578491073496914e-06, "epoch": 2.6671758316361167, "percentage": 53.34, "elapsed_time": "0:49:14", "remaining_time": "0:43:04", "throughput": 10216.79, "total_tokens": 30185216}
{"current_steps": 31435, "total_steps": 58920, "loss": 0.0001, "lr": 1.0575533807128565e-06, "epoch": 2.667600135777325, "percentage": 53.35, "elapsed_time": "0:49:14", "remaining_time": "0:43:03", "throughput": 10217.06, "total_tokens": 30189888}
{"current_steps": 31440, "total_steps": 58920, "loss": 0.0002, "lr": 1.05725764902592e-06, "epoch": 2.6680244399185336, "percentage": 53.36, "elapsed_time": "0:49:15", "remaining_time": "0:43:03", "throughput": 10217.46, "total_tokens": 30195072}
{"current_steps": 31445, "total_steps": 58920, "loss": 0.0301, "lr": 1.0569619123148319e-06, "epoch": 2.668448744059742, "percentage": 53.37, "elapsed_time": "0:49:15", "remaining_time": "0:43:02", "throughput": 10217.66, "total_tokens": 30199488}
{"current_steps": 31450, "total_steps": 58920, "loss": 0.045, "lr": 1.0566661706055416e-06, "epoch": 2.6688730482009504, "percentage": 53.38, "elapsed_time": "0:49:16", "remaining_time": "0:43:01", "throughput": 10218.02, "total_tokens": 30204480}
{"current_steps": 31455, "total_steps": 58920, "loss": 0.0001, "lr": 1.0563704239239994e-06, "epoch": 2.669297352342159, "percentage": 53.39, "elapsed_time": "0:49:16", "remaining_time": "0:43:01", "throughput": 10218.35, "total_tokens": 30209408}
{"current_steps": 31460, "total_steps": 58920, "loss": 0.0077, "lr": 1.0560746722961557e-06, "epoch": 2.6697216564833672, "percentage": 53.39, "elapsed_time": "0:49:16", "remaining_time": "0:43:00", "throughput": 10218.51, "total_tokens": 30213696}
{"current_steps": 31465, "total_steps": 58920, "loss": 0.0244, "lr": 1.0557789157479625e-06, "epoch": 2.6701459606245757, "percentage": 53.4, "elapsed_time": "0:49:17", "remaining_time": "0:43:00", "throughput": 10219.23, "total_tokens": 30220224}
{"current_steps": 31470, "total_steps": 58920, "loss": 0.0214, "lr": 1.0554831543053706e-06, "epoch": 2.670570264765784, "percentage": 53.41, "elapsed_time": "0:49:17", "remaining_time": "0:42:59", "throughput": 10219.59, "total_tokens": 30225216}
{"current_steps": 31475, "total_steps": 58920, "loss": 0.0001, "lr": 1.0551873879943324e-06, "epoch": 2.6709945689069925, "percentage": 53.42, "elapsed_time": "0:49:17", "remaining_time": "0:42:59", "throughput": 10219.93, "total_tokens": 30230144}
{"current_steps": 31480, "total_steps": 58920, "loss": 0.0003, "lr": 1.0548916168407998e-06, "epoch": 2.671418873048201, "percentage": 53.43, "elapsed_time": "0:49:18", "remaining_time": "0:42:58", "throughput": 10220.25, "total_tokens": 30235072}
{"current_steps": 31485, "total_steps": 58920, "loss": 0.0001, "lr": 1.0545958408707261e-06, "epoch": 2.6718431771894093, "percentage": 53.44, "elapsed_time": "0:49:18", "remaining_time": "0:42:58", "throughput": 10220.5, "total_tokens": 30239680}
{"current_steps": 31490, "total_steps": 58920, "loss": 0.0003, "lr": 1.0543000601100645e-06, "epoch": 2.6722674813306178, "percentage": 53.45, "elapsed_time": "0:49:19", "remaining_time": "0:42:57", "throughput": 10220.71, "total_tokens": 30244096}
{"current_steps": 31495, "total_steps": 58920, "loss": 0.0, "lr": 1.0540042745847687e-06, "epoch": 2.672691785471826, "percentage": 53.45, "elapsed_time": "0:49:19", "remaining_time": "0:42:57", "throughput": 10221.03, "total_tokens": 30248960}
{"current_steps": 31500, "total_steps": 58920, "loss": 0.0334, "lr": 1.0537084843207928e-06, "epoch": 2.6731160896130346, "percentage": 53.46, "elapsed_time": "0:49:19", "remaining_time": "0:42:56", "throughput": 10221.22, "total_tokens": 30253376}
{"current_steps": 31505, "total_steps": 58920, "loss": 0.0426, "lr": 1.0534126893440914e-06, "epoch": 2.673540393754243, "percentage": 53.47, "elapsed_time": "0:49:20", "remaining_time": "0:42:55", "throughput": 10221.48, "total_tokens": 30258048}
{"current_steps": 31510, "total_steps": 58920, "loss": 0.0377, "lr": 1.0531168896806194e-06, "epoch": 2.6739646978954514, "percentage": 53.48, "elapsed_time": "0:49:20", "remaining_time": "0:42:55", "throughput": 10221.76, "total_tokens": 30262784}
{"current_steps": 31515, "total_steps": 58920, "loss": 0.0003, "lr": 1.052821085356332e-06, "epoch": 2.67438900203666, "percentage": 53.49, "elapsed_time": "0:49:20", "remaining_time": "0:42:54", "throughput": 10222.0, "total_tokens": 30267328}
{"current_steps": 31520, "total_steps": 58920, "loss": 0.0373, "lr": 1.052525276397185e-06, "epoch": 2.6748133061778683, "percentage": 53.5, "elapsed_time": "0:49:21", "remaining_time": "0:42:54", "throughput": 10222.4, "total_tokens": 30272512}
{"current_steps": 31525, "total_steps": 58920, "loss": 0.0008, "lr": 1.0522294628291345e-06, "epoch": 2.6752376103190767, "percentage": 53.5, "elapsed_time": "0:49:21", "remaining_time": "0:42:53", "throughput": 10222.78, "total_tokens": 30277632}
{"current_steps": 31530, "total_steps": 58920, "loss": 0.0005, "lr": 1.0519336446781374e-06, "epoch": 2.675661914460285, "percentage": 53.51, "elapsed_time": "0:49:22", "remaining_time": "0:42:53", "throughput": 10223.15, "total_tokens": 30282688}
{"current_steps": 31535, "total_steps": 58920, "loss": 0.0005, "lr": 1.0516378219701508e-06, "epoch": 2.6760862186014935, "percentage": 53.52, "elapsed_time": "0:49:22", "remaining_time": "0:42:52", "throughput": 10223.55, "total_tokens": 30287872}
{"current_steps": 31540, "total_steps": 58920, "loss": 0.0001, "lr": 1.0513419947311316e-06, "epoch": 2.676510522742702, "percentage": 53.53, "elapsed_time": "0:49:22", "remaining_time": "0:42:52", "throughput": 10223.78, "total_tokens": 30292416}
{"current_steps": 31545, "total_steps": 58920, "loss": 0.0001, "lr": 1.0510461629870373e-06, "epoch": 2.6769348268839104, "percentage": 53.54, "elapsed_time": "0:49:23", "remaining_time": "0:42:51", "throughput": 10224.2, "total_tokens": 30297664}
{"current_steps": 31550, "total_steps": 58920, "loss": 0.0001, "lr": 1.050750326763827e-06, "epoch": 2.677359131025119, "percentage": 53.55, "elapsed_time": "0:49:23", "remaining_time": "0:42:51", "throughput": 10224.55, "total_tokens": 30302656}
{"current_steps": 31555, "total_steps": 58920, "loss": 0.0486, "lr": 1.0504544860874585e-06, "epoch": 2.677783435166327, "percentage": 53.56, "elapsed_time": "0:49:24", "remaining_time": "0:42:50", "throughput": 10224.95, "total_tokens": 30307776}
{"current_steps": 31560, "total_steps": 58920, "loss": 0.0001, "lr": 1.050158640983891e-06, "epoch": 2.6782077393075356, "percentage": 53.56, "elapsed_time": "0:49:24", "remaining_time": "0:42:49", "throughput": 10225.3, "total_tokens": 30312768}
{"current_steps": 31565, "total_steps": 58920, "loss": 0.0202, "lr": 1.0498627914790839e-06, "epoch": 2.678632043448744, "percentage": 53.57, "elapsed_time": "0:49:24", "remaining_time": "0:42:49", "throughput": 10225.57, "total_tokens": 30317440}
{"current_steps": 31570, "total_steps": 58920, "loss": 0.0422, "lr": 1.049566937598997e-06, "epoch": 2.6790563475899525, "percentage": 53.58, "elapsed_time": "0:49:25", "remaining_time": "0:42:48", "throughput": 10225.84, "total_tokens": 30322112}
{"current_steps": 31575, "total_steps": 58920, "loss": 0.0002, "lr": 1.04927107936959e-06, "epoch": 2.679480651731161, "percentage": 53.59, "elapsed_time": "0:49:25", "remaining_time": "0:42:48", "throughput": 10226.09, "total_tokens": 30326720}
{"current_steps": 31580, "total_steps": 58920, "loss": 0.0001, "lr": 1.0489752168168239e-06, "epoch": 2.6799049558723693, "percentage": 53.6, "elapsed_time": "0:49:26", "remaining_time": "0:42:47", "throughput": 10226.4, "total_tokens": 30331584}
{"current_steps": 31585, "total_steps": 58920, "loss": 0.0005, "lr": 1.0486793499666592e-06, "epoch": 2.6803292600135777, "percentage": 53.61, "elapsed_time": "0:49:26", "remaining_time": "0:42:47", "throughput": 10226.65, "total_tokens": 30336192}
{"current_steps": 31590, "total_steps": 58920, "loss": 0.0001, "lr": 1.0483834788450574e-06, "epoch": 2.680753564154786, "percentage": 53.62, "elapsed_time": "0:49:26", "remaining_time": "0:42:46", "throughput": 10226.92, "total_tokens": 30340928}
{"current_steps": 31595, "total_steps": 58920, "loss": 0.0002, "lr": 1.0480876034779803e-06, "epoch": 2.6811778682959946, "percentage": 53.62, "elapsed_time": "0:49:27", "remaining_time": "0:42:46", "throughput": 10227.14, "total_tokens": 30345408}
{"current_steps": 31600, "total_steps": 58920, "loss": 0.0009, "lr": 1.0477917238913894e-06, "epoch": 2.681602172437203, "percentage": 53.63, "elapsed_time": "0:49:27", "remaining_time": "0:42:45", "throughput": 10227.33, "total_tokens": 30349824}
{"current_steps": 31605, "total_steps": 58920, "loss": 0.0001, "lr": 1.047495840111247e-06, "epoch": 2.6820264765784114, "percentage": 53.64, "elapsed_time": "0:49:27", "remaining_time": "0:42:45", "throughput": 10227.54, "total_tokens": 30354304}
{"current_steps": 31610, "total_steps": 58920, "loss": 0.0001, "lr": 1.0471999521635163e-06, "epoch": 2.68245078071962, "percentage": 53.65, "elapsed_time": "0:49:28", "remaining_time": "0:42:44", "throughput": 10227.84, "total_tokens": 30359040}
{"current_steps": 31615, "total_steps": 58920, "loss": 0.0004, "lr": 1.04690406007416e-06, "epoch": 2.6828750848608283, "percentage": 53.66, "elapsed_time": "0:49:28", "remaining_time": "0:42:43", "throughput": 10228.2, "total_tokens": 30364032}
{"current_steps": 31620, "total_steps": 58920, "loss": 0.0292, "lr": 1.0466081638691421e-06, "epoch": 2.6832993890020367, "percentage": 53.67, "elapsed_time": "0:49:29", "remaining_time": "0:42:43", "throughput": 10228.53, "total_tokens": 30368960}
{"current_steps": 31625, "total_steps": 58920, "loss": 0.0001, "lr": 1.0463122635744261e-06, "epoch": 2.683723693143245, "percentage": 53.67, "elapsed_time": "0:49:29", "remaining_time": "0:42:42", "throughput": 10228.91, "total_tokens": 30374016}
{"current_steps": 31630, "total_steps": 58920, "loss": 0.0301, "lr": 1.046016359215976e-06, "epoch": 2.6841479972844535, "percentage": 53.68, "elapsed_time": "0:49:29", "remaining_time": "0:42:42", "throughput": 10229.41, "total_tokens": 30379648}
{"current_steps": 31635, "total_steps": 58920, "loss": 0.0231, "lr": 1.0457204508197569e-06, "epoch": 2.684572301425662, "percentage": 53.69, "elapsed_time": "0:49:30", "remaining_time": "0:42:41", "throughput": 10229.71, "total_tokens": 30384448}
{"current_steps": 31640, "total_steps": 58920, "loss": 0.0002, "lr": 1.0454245384117328e-06, "epoch": 2.6849966055668704, "percentage": 53.7, "elapsed_time": "0:49:30", "remaining_time": "0:42:41", "throughput": 10230.04, "total_tokens": 30389312}
{"current_steps": 31645, "total_steps": 58920, "loss": 0.0001, "lr": 1.0451286220178699e-06, "epoch": 2.685420909708079, "percentage": 53.71, "elapsed_time": "0:49:30", "remaining_time": "0:42:40", "throughput": 10230.32, "total_tokens": 30393984}
{"current_steps": 31650, "total_steps": 58920, "loss": 0.0001, "lr": 1.044832701664133e-06, "epoch": 2.685845213849287, "percentage": 53.72, "elapsed_time": "0:49:31", "remaining_time": "0:42:40", "throughput": 10230.53, "total_tokens": 30398464}
{"current_steps": 31655, "total_steps": 58920, "loss": 0.0387, "lr": 1.0445367773764886e-06, "epoch": 2.6862695179904956, "percentage": 53.73, "elapsed_time": "0:49:31", "remaining_time": "0:42:39", "throughput": 10230.89, "total_tokens": 30403456}
{"current_steps": 31660, "total_steps": 58920, "loss": 0.0467, "lr": 1.0442408491809027e-06, "epoch": 2.686693822131704, "percentage": 53.73, "elapsed_time": "0:49:32", "remaining_time": "0:42:39", "throughput": 10231.09, "total_tokens": 30407872}
{"current_steps": 31665, "total_steps": 58920, "loss": 0.0001, "lr": 1.0439449171033421e-06, "epoch": 2.6871181262729125, "percentage": 53.74, "elapsed_time": "0:49:32", "remaining_time": "0:42:38", "throughput": 10231.34, "total_tokens": 30412480}
{"current_steps": 31670, "total_steps": 58920, "loss": 0.0, "lr": 1.0436489811697735e-06, "epoch": 2.687542430414121, "percentage": 53.75, "elapsed_time": "0:49:32", "remaining_time": "0:42:37", "throughput": 10231.64, "total_tokens": 30417280}
{"current_steps": 31675, "total_steps": 58920, "loss": 0.089, "lr": 1.0433530414061644e-06, "epoch": 2.6879667345553293, "percentage": 53.76, "elapsed_time": "0:49:33", "remaining_time": "0:42:37", "throughput": 10231.78, "total_tokens": 30421504}
{"current_steps": 31680, "total_steps": 58920, "loss": 0.0293, "lr": 1.0430570978384827e-06, "epoch": 2.6883910386965377, "percentage": 53.77, "elapsed_time": "0:49:33", "remaining_time": "0:42:36", "throughput": 10232.1, "total_tokens": 30426368}
{"current_steps": 31685, "total_steps": 58920, "loss": 0.0002, "lr": 1.042761150492696e-06, "epoch": 2.688815342837746, "percentage": 53.78, "elapsed_time": "0:49:34", "remaining_time": "0:42:36", "throughput": 10232.47, "total_tokens": 30431488}
{"current_steps": 31690, "total_steps": 58920, "loss": 0.0001, "lr": 1.0424651993947729e-06, "epoch": 2.6892396469789546, "percentage": 53.78, "elapsed_time": "0:49:34", "remaining_time": "0:42:35", "throughput": 10232.8, "total_tokens": 30436352}
{"current_steps": 31695, "total_steps": 58920, "loss": 0.0006, "lr": 1.0421692445706817e-06, "epoch": 2.689663951120163, "percentage": 53.79, "elapsed_time": "0:49:34", "remaining_time": "0:42:35", "throughput": 10232.93, "total_tokens": 30440512}
{"current_steps": 31700, "total_steps": 58920, "loss": 0.0328, "lr": 1.0418732860463912e-06, "epoch": 2.6900882552613714, "percentage": 53.8, "elapsed_time": "0:49:35", "remaining_time": "0:42:34", "throughput": 10233.09, "total_tokens": 30444800}
{"current_steps": 31705, "total_steps": 58920, "loss": 0.0001, "lr": 1.0415773238478714e-06, "epoch": 2.69051255940258, "percentage": 53.81, "elapsed_time": "0:49:35", "remaining_time": "0:42:34", "throughput": 10233.44, "total_tokens": 30449792}
{"current_steps": 31710, "total_steps": 58920, "loss": 0.0001, "lr": 1.0412813580010914e-06, "epoch": 2.6909368635437882, "percentage": 53.82, "elapsed_time": "0:49:35", "remaining_time": "0:42:33", "throughput": 10233.9, "total_tokens": 30455296}
{"current_steps": 31715, "total_steps": 58920, "loss": 0.021, "lr": 1.0409853885320214e-06, "epoch": 2.6913611676849967, "percentage": 53.83, "elapsed_time": "0:49:36", "remaining_time": "0:42:33", "throughput": 10234.18, "total_tokens": 30460032}
{"current_steps": 31720, "total_steps": 58920, "loss": 0.0001, "lr": 1.040689415466632e-06, "epoch": 2.691785471826205, "percentage": 53.84, "elapsed_time": "0:49:36", "remaining_time": "0:42:32", "throughput": 10234.48, "total_tokens": 30464832}
{"current_steps": 31725, "total_steps": 58920, "loss": 0.0005, "lr": 1.0403934388308929e-06, "epoch": 2.6922097759674135, "percentage": 53.84, "elapsed_time": "0:49:37", "remaining_time": "0:42:31", "throughput": 10234.85, "total_tokens": 30469888}
{"current_steps": 31730, "total_steps": 58920, "loss": 0.0289, "lr": 1.0400974586507749e-06, "epoch": 2.692634080108622, "percentage": 53.85, "elapsed_time": "0:49:37", "remaining_time": "0:42:31", "throughput": 10235.3, "total_tokens": 30475264}
{"current_steps": 31735, "total_steps": 58920, "loss": 0.0285, "lr": 1.0398014749522501e-06, "epoch": 2.6930583842498304, "percentage": 53.86, "elapsed_time": "0:49:37", "remaining_time": "0:42:30", "throughput": 10235.65, "total_tokens": 30480320}
{"current_steps": 31740, "total_steps": 58920, "loss": 0.0001, "lr": 1.0395054877612896e-06, "epoch": 2.6934826883910388, "percentage": 53.87, "elapsed_time": "0:49:38", "remaining_time": "0:42:30", "throughput": 10235.9, "total_tokens": 30484928}
{"current_steps": 31745, "total_steps": 58920, "loss": 0.0001, "lr": 1.0392094971038653e-06, "epoch": 2.693906992532247, "percentage": 53.88, "elapsed_time": "0:49:38", "remaining_time": "0:42:29", "throughput": 10236.1, "total_tokens": 30489344}
{"current_steps": 31750, "total_steps": 58920, "loss": 0.0002, "lr": 1.0389135030059488e-06, "epoch": 2.6943312966734556, "percentage": 53.89, "elapsed_time": "0:49:38", "remaining_time": "0:42:29", "throughput": 10236.43, "total_tokens": 30494272}
{"current_steps": 31755, "total_steps": 58920, "loss": 0.0256, "lr": 1.0386175054935131e-06, "epoch": 2.694755600814664, "percentage": 53.9, "elapsed_time": "0:49:39", "remaining_time": "0:42:28", "throughput": 10236.6, "total_tokens": 30498560}
{"current_steps": 31760, "total_steps": 58920, "loss": 0.033, "lr": 1.0383215045925308e-06, "epoch": 2.6951799049558725, "percentage": 53.9, "elapsed_time": "0:49:39", "remaining_time": "0:42:28", "throughput": 10236.81, "total_tokens": 30503040}
{"current_steps": 31765, "total_steps": 58920, "loss": 0.0192, "lr": 1.038025500328975e-06, "epoch": 2.695604209097081, "percentage": 53.91, "elapsed_time": "0:49:40", "remaining_time": "0:42:27", "throughput": 10237.05, "total_tokens": 30507648}
{"current_steps": 31770, "total_steps": 58920, "loss": 0.0003, "lr": 1.0377294927288186e-06, "epoch": 2.6960285132382893, "percentage": 53.92, "elapsed_time": "0:49:40", "remaining_time": "0:42:27", "throughput": 10237.27, "total_tokens": 30512192}
{"current_steps": 31775, "total_steps": 58920, "loss": 0.0022, "lr": 1.0374334818180354e-06, "epoch": 2.6964528173794977, "percentage": 53.93, "elapsed_time": "0:49:40", "remaining_time": "0:42:26", "throughput": 10237.91, "total_tokens": 30518400}
{"current_steps": 31780, "total_steps": 58920, "loss": 0.0001, "lr": 1.0371374676225996e-06, "epoch": 2.696877121520706, "percentage": 53.94, "elapsed_time": "0:49:41", "remaining_time": "0:42:26", "throughput": 10238.18, "total_tokens": 30523072}
{"current_steps": 31785, "total_steps": 58920, "loss": 0.0329, "lr": 1.0368414501684848e-06, "epoch": 2.6973014256619146, "percentage": 53.95, "elapsed_time": "0:49:41", "remaining_time": "0:42:25", "throughput": 10238.36, "total_tokens": 30527424}
{"current_steps": 31790, "total_steps": 58920, "loss": 0.0001, "lr": 1.0365454294816658e-06, "epoch": 2.697725729803123, "percentage": 53.95, "elapsed_time": "0:49:42", "remaining_time": "0:42:24", "throughput": 10238.72, "total_tokens": 30532480}
{"current_steps": 31795, "total_steps": 58920, "loss": 0.0301, "lr": 1.036249405588117e-06, "epoch": 2.6981500339443314, "percentage": 53.96, "elapsed_time": "0:49:42", "remaining_time": "0:42:24", "throughput": 10238.98, "total_tokens": 30537088}
{"current_steps": 31800, "total_steps": 58920, "loss": 0.0004, "lr": 1.0359533785138142e-06, "epoch": 2.69857433808554, "percentage": 53.97, "elapsed_time": "0:49:42", "remaining_time": "0:42:23", "throughput": 10239.26, "total_tokens": 30541888}
{"current_steps": 31805, "total_steps": 58920, "loss": 0.0244, "lr": 1.0356573482847324e-06, "epoch": 2.6989986422267482, "percentage": 53.98, "elapsed_time": "0:49:43", "remaining_time": "0:42:23", "throughput": 10239.53, "total_tokens": 30546560}
{"current_steps": 31810, "total_steps": 58920, "loss": 0.032, "lr": 1.0353613149268467e-06, "epoch": 2.6994229463679567, "percentage": 53.99, "elapsed_time": "0:49:43", "remaining_time": "0:42:22", "throughput": 10239.95, "total_tokens": 30551808}
{"current_steps": 31815, "total_steps": 58920, "loss": 0.0, "lr": 1.0350652784661335e-06, "epoch": 2.699847250509165, "percentage": 54.0, "elapsed_time": "0:49:43", "remaining_time": "0:42:22", "throughput": 10240.3, "total_tokens": 30556800}
{"current_steps": 31820, "total_steps": 58920, "loss": 0.0001, "lr": 1.0347692389285686e-06, "epoch": 2.7002715546503735, "percentage": 54.01, "elapsed_time": "0:49:44", "remaining_time": "0:42:21", "throughput": 10240.51, "total_tokens": 30561344}
{"current_steps": 31825, "total_steps": 58920, "loss": 0.0272, "lr": 1.0344731963401284e-06, "epoch": 2.700695858791582, "percentage": 54.01, "elapsed_time": "0:49:44", "remaining_time": "0:42:21", "throughput": 10240.78, "total_tokens": 30566016}
{"current_steps": 31830, "total_steps": 58920, "loss": 0.1276, "lr": 1.0341771507267895e-06, "epoch": 2.7011201629327903, "percentage": 54.02, "elapsed_time": "0:49:45", "remaining_time": "0:42:20", "throughput": 10241.23, "total_tokens": 30571456}
{"current_steps": 31835, "total_steps": 58920, "loss": 0.0258, "lr": 1.0338811021145295e-06, "epoch": 2.7015444670739988, "percentage": 54.03, "elapsed_time": "0:49:45", "remaining_time": "0:42:20", "throughput": 10241.86, "total_tokens": 30577664}
{"current_steps": 31840, "total_steps": 58920, "loss": 0.0394, "lr": 1.0335850505293248e-06, "epoch": 2.701968771215207, "percentage": 54.04, "elapsed_time": "0:49:45", "remaining_time": "0:42:19", "throughput": 10242.25, "total_tokens": 30582848}
{"current_steps": 31845, "total_steps": 58920, "loss": 0.0003, "lr": 1.0332889959971536e-06, "epoch": 2.7023930753564156, "percentage": 54.05, "elapsed_time": "0:49:46", "remaining_time": "0:42:19", "throughput": 10242.58, "total_tokens": 30587776}
{"current_steps": 31850, "total_steps": 58920, "loss": 0.0002, "lr": 1.0329929385439928e-06, "epoch": 2.702817379497624, "percentage": 54.06, "elapsed_time": "0:49:46", "remaining_time": "0:42:18", "throughput": 10242.8, "total_tokens": 30592256}
{"current_steps": 31855, "total_steps": 58920, "loss": 0.0002, "lr": 1.0326968781958207e-06, "epoch": 2.7032416836388324, "percentage": 54.06, "elapsed_time": "0:49:47", "remaining_time": "0:42:17", "throughput": 10243.1, "total_tokens": 30597056}
{"current_steps": 31860, "total_steps": 58920, "loss": 0.0005, "lr": 1.032400814978616e-06, "epoch": 2.703665987780041, "percentage": 54.07, "elapsed_time": "0:49:47", "remaining_time": "0:42:17", "throughput": 10243.46, "total_tokens": 30602048}
{"current_steps": 31865, "total_steps": 58920, "loss": 0.0381, "lr": 1.0321047489183564e-06, "epoch": 2.7040902919212493, "percentage": 54.08, "elapsed_time": "0:49:47", "remaining_time": "0:42:16", "throughput": 10243.7, "total_tokens": 30606656}
{"current_steps": 31870, "total_steps": 58920, "loss": 0.0014, "lr": 1.0318086800410211e-06, "epoch": 2.7045145960624577, "percentage": 54.09, "elapsed_time": "0:49:48", "remaining_time": "0:42:16", "throughput": 10244.11, "total_tokens": 30611904}
{"current_steps": 31875, "total_steps": 58920, "loss": 0.0002, "lr": 1.0315126083725888e-06, "epoch": 2.704938900203666, "percentage": 54.1, "elapsed_time": "0:49:48", "remaining_time": "0:42:15", "throughput": 10244.34, "total_tokens": 30616512}
{"current_steps": 31880, "total_steps": 58920, "loss": 0.0001, "lr": 1.031216533939039e-06, "epoch": 2.7053632043448745, "percentage": 54.11, "elapsed_time": "0:49:49", "remaining_time": "0:42:15", "throughput": 10244.77, "total_tokens": 30621824}
{"current_steps": 31885, "total_steps": 58920, "loss": 0.0006, "lr": 1.0309204567663512e-06, "epoch": 2.705787508486083, "percentage": 54.12, "elapsed_time": "0:49:49", "remaining_time": "0:42:14", "throughput": 10245.07, "total_tokens": 30626624}
{"current_steps": 31890, "total_steps": 58920, "loss": 0.0002, "lr": 1.030624376880505e-06, "epoch": 2.7062118126272914, "percentage": 54.12, "elapsed_time": "0:49:49", "remaining_time": "0:42:14", "throughput": 10245.31, "total_tokens": 30631168}
{"current_steps": 31895, "total_steps": 58920, "loss": 0.0001, "lr": 1.0303282943074802e-06, "epoch": 2.7066361167685, "percentage": 54.13, "elapsed_time": "0:49:50", "remaining_time": "0:42:13", "throughput": 10245.65, "total_tokens": 30636160}
{"current_steps": 31900, "total_steps": 58920, "loss": 0.0006, "lr": 1.0300322090732568e-06, "epoch": 2.707060420909708, "percentage": 54.14, "elapsed_time": "0:49:50", "remaining_time": "0:42:13", "throughput": 10245.91, "total_tokens": 30640832}
{"current_steps": 31905, "total_steps": 58920, "loss": 0.0, "lr": 1.029736121203816e-06, "epoch": 2.7074847250509166, "percentage": 54.15, "elapsed_time": "0:49:50", "remaining_time": "0:42:12", "throughput": 10246.12, "total_tokens": 30645312}
{"current_steps": 31910, "total_steps": 58920, "loss": 0.0005, "lr": 1.0294400307251377e-06, "epoch": 2.707909029192125, "percentage": 54.16, "elapsed_time": "0:49:51", "remaining_time": "0:42:11", "throughput": 10246.55, "total_tokens": 30650624}
{"current_steps": 31915, "total_steps": 58920, "loss": 0.0356, "lr": 1.029143937663203e-06, "epoch": 2.7083333333333335, "percentage": 54.17, "elapsed_time": "0:49:51", "remaining_time": "0:42:11", "throughput": 10246.83, "total_tokens": 30655360}
{"current_steps": 31920, "total_steps": 58920, "loss": 0.0002, "lr": 1.0288478420439925e-06, "epoch": 2.708757637474542, "percentage": 54.18, "elapsed_time": "0:49:52", "remaining_time": "0:42:10", "throughput": 10246.93, "total_tokens": 30659456}
{"current_steps": 31925, "total_steps": 58920, "loss": 0.0001, "lr": 1.0285517438934886e-06, "epoch": 2.7091819416157503, "percentage": 54.18, "elapsed_time": "0:49:52", "remaining_time": "0:42:10", "throughput": 10247.27, "total_tokens": 30664384}
{"current_steps": 31930, "total_steps": 58920, "loss": 0.0001, "lr": 1.0282556432376723e-06, "epoch": 2.7096062457569587, "percentage": 54.19, "elapsed_time": "0:49:52", "remaining_time": "0:42:09", "throughput": 10247.47, "total_tokens": 30668864}
{"current_steps": 31935, "total_steps": 58920, "loss": 0.023, "lr": 1.0279595401025252e-06, "epoch": 2.710030549898167, "percentage": 54.2, "elapsed_time": "0:49:53", "remaining_time": "0:42:09", "throughput": 10247.69, "total_tokens": 30673344}
{"current_steps": 31940, "total_steps": 58920, "loss": 0.0001, "lr": 1.0276634345140294e-06, "epoch": 2.7104548540393756, "percentage": 54.21, "elapsed_time": "0:49:53", "remaining_time": "0:42:08", "throughput": 10247.91, "total_tokens": 30677888}
{"current_steps": 31945, "total_steps": 58920, "loss": 0.0446, "lr": 1.027367326498167e-06, "epoch": 2.710879158180584, "percentage": 54.22, "elapsed_time": "0:49:53", "remaining_time": "0:42:08", "throughput": 10248.18, "total_tokens": 30682624}
{"current_steps": 31950, "total_steps": 58920, "loss": 0.0001, "lr": 1.0270712160809203e-06, "epoch": 2.7113034623217924, "percentage": 54.23, "elapsed_time": "0:49:54", "remaining_time": "0:42:07", "throughput": 10248.42, "total_tokens": 30687232}
{"current_steps": 31955, "total_steps": 58920, "loss": 0.0001, "lr": 1.0267751032882725e-06, "epoch": 2.711727766463001, "percentage": 54.23, "elapsed_time": "0:49:54", "remaining_time": "0:42:07", "throughput": 10248.65, "total_tokens": 30691776}
{"current_steps": 31960, "total_steps": 58920, "loss": 0.0376, "lr": 1.026478988146206e-06, "epoch": 2.7121520706042093, "percentage": 54.24, "elapsed_time": "0:49:55", "remaining_time": "0:42:06", "throughput": 10248.97, "total_tokens": 30696640}
{"current_steps": 31965, "total_steps": 58920, "loss": 0.0156, "lr": 1.0261828706807036e-06, "epoch": 2.7125763747454172, "percentage": 54.25, "elapsed_time": "0:49:55", "remaining_time": "0:42:05", "throughput": 10249.24, "total_tokens": 30701376}
{"current_steps": 31970, "total_steps": 58920, "loss": 0.0682, "lr": 1.0258867509177494e-06, "epoch": 2.713000678886626, "percentage": 54.26, "elapsed_time": "0:49:55", "remaining_time": "0:42:05", "throughput": 10249.46, "total_tokens": 30705856}
{"current_steps": 31975, "total_steps": 58920, "loss": 0.0325, "lr": 1.0255906288833258e-06, "epoch": 2.713424983027834, "percentage": 54.27, "elapsed_time": "0:49:56", "remaining_time": "0:42:04", "throughput": 10249.8, "total_tokens": 30710784}
{"current_steps": 31980, "total_steps": 58920, "loss": 0.0162, "lr": 1.0252945046034169e-06, "epoch": 2.713849287169043, "percentage": 54.28, "elapsed_time": "0:49:56", "remaining_time": "0:42:04", "throughput": 10250.03, "total_tokens": 30715328}
{"current_steps": 31985, "total_steps": 58920, "loss": 0.0002, "lr": 1.0249983781040067e-06, "epoch": 2.714273591310251, "percentage": 54.29, "elapsed_time": "0:49:57", "remaining_time": "0:42:03", "throughput": 10251.09, "total_tokens": 30723456}
{"current_steps": 31990, "total_steps": 58920, "loss": 0.0002, "lr": 1.0247022494110794e-06, "epoch": 2.71469789545146, "percentage": 54.29, "elapsed_time": "0:49:57", "remaining_time": "0:42:03", "throughput": 10251.3, "total_tokens": 30727872}
{"current_steps": 31995, "total_steps": 58920, "loss": 0.0006, "lr": 1.0244061185506183e-06, "epoch": 2.7151221995926678, "percentage": 54.3, "elapsed_time": "0:49:57", "remaining_time": "0:42:02", "throughput": 10251.51, "total_tokens": 30732352}
{"current_steps": 32000, "total_steps": 58920, "loss": 0.0345, "lr": 1.0241099855486088e-06, "epoch": 2.7155465037338766, "percentage": 54.31, "elapsed_time": "0:49:58", "remaining_time": "0:42:02", "throughput": 10251.78, "total_tokens": 30737088}
{"current_steps": 32005, "total_steps": 58920, "loss": 0.0002, "lr": 1.023813850431035e-06, "epoch": 2.7159708078750846, "percentage": 54.32, "elapsed_time": "0:49:58", "remaining_time": "0:42:01", "throughput": 10251.97, "total_tokens": 30741504}
{"current_steps": 32010, "total_steps": 58920, "loss": 0.0001, "lr": 1.0235177132238818e-06, "epoch": 2.7163951120162935, "percentage": 54.33, "elapsed_time": "0:49:58", "remaining_time": "0:42:01", "throughput": 10252.14, "total_tokens": 30745856}
{"current_steps": 32015, "total_steps": 58920, "loss": 0.0002, "lr": 1.0232215739531342e-06, "epoch": 2.7168194161575014, "percentage": 54.34, "elapsed_time": "0:49:59", "remaining_time": "0:42:00", "throughput": 10252.87, "total_tokens": 30752384}
{"current_steps": 32020, "total_steps": 58920, "loss": 0.0001, "lr": 1.0229254326447773e-06, "epoch": 2.7172437202987103, "percentage": 54.34, "elapsed_time": "0:49:59", "remaining_time": "0:42:00", "throughput": 10253.02, "total_tokens": 30756672}
{"current_steps": 32025, "total_steps": 58920, "loss": 0.0013, "lr": 1.0226292893247965e-06, "epoch": 2.7176680244399183, "percentage": 54.35, "elapsed_time": "0:50:00", "remaining_time": "0:41:59", "throughput": 10253.24, "total_tokens": 30761216}
{"current_steps": 32030, "total_steps": 58920, "loss": 0.0002, "lr": 1.0223331440191773e-06, "epoch": 2.718092328581127, "percentage": 54.36, "elapsed_time": "0:50:00", "remaining_time": "0:41:59", "throughput": 10253.46, "total_tokens": 30765760}
{"current_steps": 32035, "total_steps": 58920, "loss": 0.0001, "lr": 1.0220369967539053e-06, "epoch": 2.718516632722335, "percentage": 54.37, "elapsed_time": "0:50:00", "remaining_time": "0:41:58", "throughput": 10253.85, "total_tokens": 30770944}
{"current_steps": 32040, "total_steps": 58920, "loss": 0.0001, "lr": 1.021740847554966e-06, "epoch": 2.718940936863544, "percentage": 54.38, "elapsed_time": "0:50:01", "remaining_time": "0:41:57", "throughput": 10254.1, "total_tokens": 30775552}
{"current_steps": 32045, "total_steps": 58920, "loss": 0.0692, "lr": 1.0214446964483462e-06, "epoch": 2.719365241004752, "percentage": 54.39, "elapsed_time": "0:50:01", "remaining_time": "0:41:57", "throughput": 10254.41, "total_tokens": 30780416}
{"current_steps": 32050, "total_steps": 58920, "loss": 0.083, "lr": 1.0211485434600317e-06, "epoch": 2.719789545145961, "percentage": 54.4, "elapsed_time": "0:50:02", "remaining_time": "0:41:56", "throughput": 10254.58, "total_tokens": 30784704}
{"current_steps": 32055, "total_steps": 58920, "loss": 0.0547, "lr": 1.0208523886160093e-06, "epoch": 2.720213849287169, "percentage": 54.4, "elapsed_time": "0:50:02", "remaining_time": "0:41:56", "throughput": 10254.89, "total_tokens": 30789504}
{"current_steps": 32060, "total_steps": 58920, "loss": 0.0218, "lr": 1.0205562319422646e-06, "epoch": 2.7206381534283777, "percentage": 54.41, "elapsed_time": "0:50:02", "remaining_time": "0:41:55", "throughput": 10255.25, "total_tokens": 30794560}
{"current_steps": 32065, "total_steps": 58920, "loss": 0.0003, "lr": 1.0202600734647849e-06, "epoch": 2.7210624575695856, "percentage": 54.42, "elapsed_time": "0:50:03", "remaining_time": "0:41:55", "throughput": 10255.58, "total_tokens": 30799552}
{"current_steps": 32070, "total_steps": 58920, "loss": 0.0004, "lr": 1.0199639132095566e-06, "epoch": 2.7214867617107945, "percentage": 54.43, "elapsed_time": "0:50:03", "remaining_time": "0:41:54", "throughput": 10255.9, "total_tokens": 30804416}
{"current_steps": 32075, "total_steps": 58920, "loss": 0.0002, "lr": 1.0196677512025673e-06, "epoch": 2.7219110658520025, "percentage": 54.44, "elapsed_time": "0:50:03", "remaining_time": "0:41:54", "throughput": 10256.21, "total_tokens": 30809344}
{"current_steps": 32080, "total_steps": 58920, "loss": 0.0003, "lr": 1.0193715874698037e-06, "epoch": 2.7223353699932114, "percentage": 54.45, "elapsed_time": "0:50:04", "remaining_time": "0:41:53", "throughput": 10256.47, "total_tokens": 30814016}
{"current_steps": 32085, "total_steps": 58920, "loss": 0.0002, "lr": 1.0190754220372533e-06, "epoch": 2.7227596741344193, "percentage": 54.46, "elapsed_time": "0:50:04", "remaining_time": "0:41:53", "throughput": 10256.77, "total_tokens": 30818816}
{"current_steps": 32090, "total_steps": 58920, "loss": 0.0002, "lr": 1.0187792549309036e-06, "epoch": 2.723183978275628, "percentage": 54.46, "elapsed_time": "0:50:05", "remaining_time": "0:41:52", "throughput": 10257.0, "total_tokens": 30823360}
{"current_steps": 32095, "total_steps": 58920, "loss": 0.0199, "lr": 1.018483086176742e-06, "epoch": 2.723608282416836, "percentage": 54.47, "elapsed_time": "0:50:05", "remaining_time": "0:41:51", "throughput": 10257.37, "total_tokens": 30828416}
{"current_steps": 32100, "total_steps": 58920, "loss": 0.0001, "lr": 1.0181869158007563e-06, "epoch": 2.724032586558045, "percentage": 54.48, "elapsed_time": "0:50:05", "remaining_time": "0:41:51", "throughput": 10257.69, "total_tokens": 30833280}
{"current_steps": 32105, "total_steps": 58920, "loss": 0.0354, "lr": 1.0178907438289344e-06, "epoch": 2.724456890699253, "percentage": 54.49, "elapsed_time": "0:50:06", "remaining_time": "0:41:50", "throughput": 10258.0, "total_tokens": 30838144}
{"current_steps": 32110, "total_steps": 58920, "loss": 0.0002, "lr": 1.0175945702872645e-06, "epoch": 2.724881194840462, "percentage": 54.5, "elapsed_time": "0:50:06", "remaining_time": "0:41:50", "throughput": 10258.32, "total_tokens": 30843072}
{"current_steps": 32115, "total_steps": 58920, "loss": 0.0102, "lr": 1.0172983952017342e-06, "epoch": 2.72530549898167, "percentage": 54.51, "elapsed_time": "0:50:07", "remaining_time": "0:41:49", "throughput": 10258.61, "total_tokens": 30847872}
{"current_steps": 32120, "total_steps": 58920, "loss": 0.0001, "lr": 1.0170022185983324e-06, "epoch": 2.7257298031228787, "percentage": 54.51, "elapsed_time": "0:50:07", "remaining_time": "0:41:49", "throughput": 10258.9, "total_tokens": 30852672}
{"current_steps": 32125, "total_steps": 58920, "loss": 0.0001, "lr": 1.0167060405030472e-06, "epoch": 2.7261541072640867, "percentage": 54.52, "elapsed_time": "0:50:07", "remaining_time": "0:41:48", "throughput": 10259.12, "total_tokens": 30857216}
{"current_steps": 32130, "total_steps": 58920, "loss": 0.0239, "lr": 1.0164098609418675e-06, "epoch": 2.7265784114052956, "percentage": 54.53, "elapsed_time": "0:50:08", "remaining_time": "0:41:48", "throughput": 10259.28, "total_tokens": 30861504}
{"current_steps": 32135, "total_steps": 58920, "loss": 0.0001, "lr": 1.0161136799407814e-06, "epoch": 2.7270027155465035, "percentage": 54.54, "elapsed_time": "0:50:08", "remaining_time": "0:41:47", "throughput": 10259.58, "total_tokens": 30866368}
{"current_steps": 32140, "total_steps": 58920, "loss": 0.0542, "lr": 1.0158174975257785e-06, "epoch": 2.7274270196877124, "percentage": 54.55, "elapsed_time": "0:50:08", "remaining_time": "0:41:47", "throughput": 10259.95, "total_tokens": 30871488}
{"current_steps": 32145, "total_steps": 58920, "loss": 0.0001, "lr": 1.015521313722847e-06, "epoch": 2.7278513238289204, "percentage": 54.56, "elapsed_time": "0:50:09", "remaining_time": "0:41:46", "throughput": 10260.25, "total_tokens": 30876288}
{"current_steps": 32150, "total_steps": 58920, "loss": 0.0002, "lr": 1.0152251285579763e-06, "epoch": 2.7282756279701292, "percentage": 54.57, "elapsed_time": "0:50:09", "remaining_time": "0:41:46", "throughput": 10260.51, "total_tokens": 30880960}
{"current_steps": 32155, "total_steps": 58920, "loss": 0.0013, "lr": 1.0149289420571556e-06, "epoch": 2.728699932111337, "percentage": 54.57, "elapsed_time": "0:50:10", "remaining_time": "0:41:45", "throughput": 10260.85, "total_tokens": 30885952}
{"current_steps": 32160, "total_steps": 58920, "loss": 0.0002, "lr": 1.014632754246374e-06, "epoch": 2.729124236252546, "percentage": 54.58, "elapsed_time": "0:50:10", "remaining_time": "0:41:44", "throughput": 10261.14, "total_tokens": 30890688}
{"current_steps": 32165, "total_steps": 58920, "loss": 0.0001, "lr": 1.0143365651516212e-06, "epoch": 2.729548540393754, "percentage": 54.59, "elapsed_time": "0:50:10", "remaining_time": "0:41:44", "throughput": 10261.45, "total_tokens": 30895616}
{"current_steps": 32170, "total_steps": 58920, "loss": 0.0, "lr": 1.0140403747988864e-06, "epoch": 2.729972844534963, "percentage": 54.6, "elapsed_time": "0:50:11", "remaining_time": "0:41:43", "throughput": 10261.88, "total_tokens": 30900992}
{"current_steps": 32175, "total_steps": 58920, "loss": 0.0515, "lr": 1.0137441832141596e-06, "epoch": 2.730397148676171, "percentage": 54.61, "elapsed_time": "0:50:11", "remaining_time": "0:41:43", "throughput": 10262.16, "total_tokens": 30905792}
{"current_steps": 32180, "total_steps": 58920, "loss": 0.0005, "lr": 1.0134479904234306e-06, "epoch": 2.7308214528173798, "percentage": 54.62, "elapsed_time": "0:50:12", "remaining_time": "0:41:42", "throughput": 10262.43, "total_tokens": 30910592}
{"current_steps": 32185, "total_steps": 58920, "loss": 0.0346, "lr": 1.0131517964526887e-06, "epoch": 2.7312457569585877, "percentage": 54.62, "elapsed_time": "0:50:12", "remaining_time": "0:41:42", "throughput": 10262.65, "total_tokens": 30915072}
{"current_steps": 32190, "total_steps": 58920, "loss": 0.0001, "lr": 1.0128556013279238e-06, "epoch": 2.7316700610997966, "percentage": 54.63, "elapsed_time": "0:50:12", "remaining_time": "0:41:41", "throughput": 10262.86, "total_tokens": 30919552}
{"current_steps": 32195, "total_steps": 58920, "loss": 0.0508, "lr": 1.0125594050751264e-06, "epoch": 2.7320943652410046, "percentage": 54.64, "elapsed_time": "0:50:13", "remaining_time": "0:41:41", "throughput": 10263.11, "total_tokens": 30924160}
{"current_steps": 32200, "total_steps": 58920, "loss": 0.0001, "lr": 1.0122632077202868e-06, "epoch": 2.7325186693822134, "percentage": 54.65, "elapsed_time": "0:50:13", "remaining_time": "0:41:40", "throughput": 10263.27, "total_tokens": 30928448}
{"current_steps": 32205, "total_steps": 58920, "loss": 0.0001, "lr": 1.011967009289395e-06, "epoch": 2.7329429735234214, "percentage": 54.66, "elapsed_time": "0:50:13", "remaining_time": "0:41:40", "throughput": 10263.7, "total_tokens": 30933824}
{"current_steps": 32210, "total_steps": 58920, "loss": 0.036, "lr": 1.0116708098084414e-06, "epoch": 2.7333672776646303, "percentage": 54.67, "elapsed_time": "0:50:14", "remaining_time": "0:41:39", "throughput": 10264.04, "total_tokens": 30938816}
{"current_steps": 32215, "total_steps": 58920, "loss": 0.017, "lr": 1.0113746093034164e-06, "epoch": 2.7337915818058383, "percentage": 54.68, "elapsed_time": "0:50:14", "remaining_time": "0:41:39", "throughput": 10264.25, "total_tokens": 30943296}
{"current_steps": 32220, "total_steps": 58920, "loss": 0.0001, "lr": 1.0110784078003103e-06, "epoch": 2.734215885947047, "percentage": 54.68, "elapsed_time": "0:50:15", "remaining_time": "0:41:38", "throughput": 10264.56, "total_tokens": 30948224}
{"current_steps": 32225, "total_steps": 58920, "loss": 0.0001, "lr": 1.010782205325114e-06, "epoch": 2.734640190088255, "percentage": 54.69, "elapsed_time": "0:50:15", "remaining_time": "0:41:37", "throughput": 10265.1, "total_tokens": 30953984}
{"current_steps": 32230, "total_steps": 58920, "loss": 0.0003, "lr": 1.0104860019038179e-06, "epoch": 2.7350644942294635, "percentage": 54.7, "elapsed_time": "0:50:15", "remaining_time": "0:41:37", "throughput": 10265.37, "total_tokens": 30958720}
{"current_steps": 32235, "total_steps": 58920, "loss": 0.0001, "lr": 1.0101897975624134e-06, "epoch": 2.735488798370672, "percentage": 54.71, "elapsed_time": "0:50:16", "remaining_time": "0:41:36", "throughput": 10265.72, "total_tokens": 30963712}
{"current_steps": 32240, "total_steps": 58920, "loss": 0.0002, "lr": 1.0098935923268907e-06, "epoch": 2.7359131025118804, "percentage": 54.72, "elapsed_time": "0:50:16", "remaining_time": "0:41:36", "throughput": 10265.95, "total_tokens": 30968320}
{"current_steps": 32245, "total_steps": 58920, "loss": 0.0001, "lr": 1.009597386223241e-06, "epoch": 2.7363374066530888, "percentage": 54.73, "elapsed_time": "0:50:16", "remaining_time": "0:41:35", "throughput": 10266.19, "total_tokens": 30972928}
{"current_steps": 32250, "total_steps": 58920, "loss": 0.0001, "lr": 1.0093011792774555e-06, "epoch": 2.736761710794297, "percentage": 54.74, "elapsed_time": "0:50:17", "remaining_time": "0:41:35", "throughput": 10266.44, "total_tokens": 30977600}
{"current_steps": 32255, "total_steps": 58920, "loss": 0.0001, "lr": 1.0090049715155247e-06, "epoch": 2.7371860149355056, "percentage": 54.74, "elapsed_time": "0:50:17", "remaining_time": "0:41:34", "throughput": 10266.78, "total_tokens": 30982592}
{"current_steps": 32260, "total_steps": 58920, "loss": 0.0557, "lr": 1.0087087629634403e-06, "epoch": 2.737610319076714, "percentage": 54.75, "elapsed_time": "0:50:18", "remaining_time": "0:41:34", "throughput": 10267.15, "total_tokens": 30987712}
{"current_steps": 32265, "total_steps": 58920, "loss": 0.0001, "lr": 1.008412553647194e-06, "epoch": 2.7380346232179225, "percentage": 54.76, "elapsed_time": "0:50:18", "remaining_time": "0:41:33", "throughput": 10267.39, "total_tokens": 30992320}
{"current_steps": 32270, "total_steps": 58920, "loss": 0.0328, "lr": 1.0081163435927757e-06, "epoch": 2.738458927359131, "percentage": 54.77, "elapsed_time": "0:50:18", "remaining_time": "0:41:33", "throughput": 10267.66, "total_tokens": 30997056}
{"current_steps": 32275, "total_steps": 58920, "loss": 0.0001, "lr": 1.007820132826178e-06, "epoch": 2.7388832315003393, "percentage": 54.78, "elapsed_time": "0:50:19", "remaining_time": "0:41:32", "throughput": 10268.4, "total_tokens": 31003648}
{"current_steps": 32280, "total_steps": 58920, "loss": 0.0001, "lr": 1.0075239213733918e-06, "epoch": 2.7393075356415477, "percentage": 54.79, "elapsed_time": "0:50:19", "remaining_time": "0:41:32", "throughput": 10268.69, "total_tokens": 31008448}
{"current_steps": 32285, "total_steps": 58920, "loss": 0.0003, "lr": 1.0072277092604083e-06, "epoch": 2.739731839782756, "percentage": 54.79, "elapsed_time": "0:50:20", "remaining_time": "0:41:31", "throughput": 10269.03, "total_tokens": 31013504}
{"current_steps": 32290, "total_steps": 58920, "loss": 0.0001, "lr": 1.0069314965132195e-06, "epoch": 2.7401561439239646, "percentage": 54.8, "elapsed_time": "0:50:20", "remaining_time": "0:41:31", "throughput": 10269.35, "total_tokens": 31018496}
{"current_steps": 32295, "total_steps": 58920, "loss": 0.0249, "lr": 1.0066352831578173e-06, "epoch": 2.740580448065173, "percentage": 54.81, "elapsed_time": "0:50:20", "remaining_time": "0:41:30", "throughput": 10269.61, "total_tokens": 31023232}
{"current_steps": 32300, "total_steps": 58920, "loss": 0.0001, "lr": 1.0063390692201927e-06, "epoch": 2.7410047522063814, "percentage": 54.82, "elapsed_time": "0:50:21", "remaining_time": "0:41:29", "throughput": 10269.75, "total_tokens": 31027456}
{"current_steps": 32305, "total_steps": 58920, "loss": 0.0001, "lr": 1.006042854726338e-06, "epoch": 2.74142905634759, "percentage": 54.83, "elapsed_time": "0:50:21", "remaining_time": "0:41:29", "throughput": 10270.04, "total_tokens": 31032256}
{"current_steps": 32310, "total_steps": 58920, "loss": 0.0388, "lr": 1.0057466397022444e-06, "epoch": 2.7418533604887982, "percentage": 54.84, "elapsed_time": "0:50:22", "remaining_time": "0:41:28", "throughput": 10270.34, "total_tokens": 31037120}
{"current_steps": 32315, "total_steps": 58920, "loss": 0.0001, "lr": 1.0054504241739036e-06, "epoch": 2.7422776646300067, "percentage": 54.85, "elapsed_time": "0:50:22", "remaining_time": "0:41:28", "throughput": 10270.63, "total_tokens": 31041984}
{"current_steps": 32320, "total_steps": 58920, "loss": 0.0001, "lr": 1.0051542081673081e-06, "epoch": 2.742701968771215, "percentage": 54.85, "elapsed_time": "0:50:22", "remaining_time": "0:41:27", "throughput": 10270.9, "total_tokens": 31046720}
{"current_steps": 32325, "total_steps": 58920, "loss": 0.0058, "lr": 1.0048579917084493e-06, "epoch": 2.7431262729124235, "percentage": 54.86, "elapsed_time": "0:50:23", "remaining_time": "0:41:27", "throughput": 10271.22, "total_tokens": 31051712}
{"current_steps": 32330, "total_steps": 58920, "loss": 0.0003, "lr": 1.0045617748233195e-06, "epoch": 2.743550577053632, "percentage": 54.87, "elapsed_time": "0:50:23", "remaining_time": "0:41:26", "throughput": 10271.45, "total_tokens": 31056320}
{"current_steps": 32335, "total_steps": 58920, "loss": 0.0001, "lr": 1.0042655575379101e-06, "epoch": 2.7439748811948403, "percentage": 54.88, "elapsed_time": "0:50:23", "remaining_time": "0:41:26", "throughput": 10271.65, "total_tokens": 31060800}
{"current_steps": 32340, "total_steps": 58920, "loss": 0.0, "lr": 1.0039693398782136e-06, "epoch": 2.7443991853360488, "percentage": 54.89, "elapsed_time": "0:50:24", "remaining_time": "0:41:25", "throughput": 10271.88, "total_tokens": 31065344}
{"current_steps": 32345, "total_steps": 58920, "loss": 0.0266, "lr": 1.003673121870222e-06, "epoch": 2.744823489477257, "percentage": 54.9, "elapsed_time": "0:50:24", "remaining_time": "0:41:25", "throughput": 10272.48, "total_tokens": 31071424}
{"current_steps": 32350, "total_steps": 58920, "loss": 0.0001, "lr": 1.0033769035399271e-06, "epoch": 2.7452477936184656, "percentage": 54.9, "elapsed_time": "0:50:25", "remaining_time": "0:41:24", "throughput": 10272.68, "total_tokens": 31075904}
{"current_steps": 32355, "total_steps": 58920, "loss": 0.0001, "lr": 1.003080684913321e-06, "epoch": 2.745672097759674, "percentage": 54.91, "elapsed_time": "0:50:25", "remaining_time": "0:41:24", "throughput": 10272.93, "total_tokens": 31080576}
{"current_steps": 32360, "total_steps": 58920, "loss": 0.0, "lr": 1.002784466016396e-06, "epoch": 2.7460964019008824, "percentage": 54.92, "elapsed_time": "0:50:25", "remaining_time": "0:41:23", "throughput": 10273.32, "total_tokens": 31085824}
{"current_steps": 32365, "total_steps": 58920, "loss": 0.039, "lr": 1.0024882468751441e-06, "epoch": 2.746520706042091, "percentage": 54.93, "elapsed_time": "0:50:26", "remaining_time": "0:41:23", "throughput": 10273.63, "total_tokens": 31090688}
{"current_steps": 32370, "total_steps": 58920, "loss": 0.0001, "lr": 1.0021920275155575e-06, "epoch": 2.7469450101832993, "percentage": 54.94, "elapsed_time": "0:50:26", "remaining_time": "0:41:22", "throughput": 10273.94, "total_tokens": 31095616}
{"current_steps": 32375, "total_steps": 58920, "loss": 0.0001, "lr": 1.0018958079636283e-06, "epoch": 2.7473693143245077, "percentage": 54.95, "elapsed_time": "0:50:27", "remaining_time": "0:41:21", "throughput": 10274.18, "total_tokens": 31100224}
{"current_steps": 32380, "total_steps": 58920, "loss": 0.0001, "lr": 1.0015995882453489e-06, "epoch": 2.747793618465716, "percentage": 54.96, "elapsed_time": "0:50:27", "remaining_time": "0:41:21", "throughput": 10274.41, "total_tokens": 31104768}
{"current_steps": 32385, "total_steps": 58920, "loss": 0.0001, "lr": 1.0013033683867116e-06, "epoch": 2.7482179226069245, "percentage": 54.96, "elapsed_time": "0:50:27", "remaining_time": "0:41:20", "throughput": 10274.54, "total_tokens": 31108992}
{"current_steps": 32390, "total_steps": 58920, "loss": 0.0375, "lr": 1.0010071484137086e-06, "epoch": 2.748642226748133, "percentage": 54.97, "elapsed_time": "0:50:28", "remaining_time": "0:41:20", "throughput": 10274.87, "total_tokens": 31113984}
{"current_steps": 32395, "total_steps": 58920, "loss": 0.0179, "lr": 1.0007109283523317e-06, "epoch": 2.7490665308893414, "percentage": 54.98, "elapsed_time": "0:50:28", "remaining_time": "0:41:19", "throughput": 10275.17, "total_tokens": 31118848}
{"current_steps": 32400, "total_steps": 58920, "loss": 0.0002, "lr": 1.0004147082285733e-06, "epoch": 2.74949083503055, "percentage": 54.99, "elapsed_time": "0:50:28", "remaining_time": "0:41:19", "throughput": 10275.67, "total_tokens": 31124544}
{"current_steps": 32405, "total_steps": 58920, "loss": 0.0001, "lr": 1.0001184880684258e-06, "epoch": 2.7499151391717582, "percentage": 55.0, "elapsed_time": "0:50:29", "remaining_time": "0:41:18", "throughput": 10276.06, "total_tokens": 31129664}
{"current_steps": 32406, "total_steps": 58920, "eval_loss": 0.1111646443605423, "epoch": 2.75, "percentage": 55.0, "elapsed_time": "0:50:45", "remaining_time": "0:41:32", "throughput": 10220.81, "total_tokens": 31130432}
{"current_steps": 32410, "total_steps": 58920, "loss": 0.0001, "lr": 9.998222678978815e-07, "epoch": 2.7503394433129666, "percentage": 55.01, "elapsed_time": "0:51:22", "remaining_time": "0:42:01", "throughput": 10099.2, "total_tokens": 31133888}
{"current_steps": 32415, "total_steps": 58920, "loss": 0.0341, "lr": 9.995260477429322e-07, "epoch": 2.750763747454175, "percentage": 55.02, "elapsed_time": "0:51:23", "remaining_time": "0:42:01", "throughput": 10099.42, "total_tokens": 31138368}
{"current_steps": 32420, "total_steps": 58920, "loss": 0.0, "lr": 9.99229827629571e-07, "epoch": 2.7511880515953835, "percentage": 55.02, "elapsed_time": "0:51:23", "remaining_time": "0:42:00", "throughput": 10099.72, "total_tokens": 31143168}
{"current_steps": 32425, "total_steps": 58920, "loss": 0.0002, "lr": 9.989336075837892e-07, "epoch": 2.751612355736592, "percentage": 55.03, "elapsed_time": "0:51:23", "remaining_time": "0:41:59", "throughput": 10100.14, "total_tokens": 31148416}
{"current_steps": 32430, "total_steps": 58920, "loss": 0.0002, "lr": 9.986373876315798e-07, "epoch": 2.7520366598778003, "percentage": 55.04, "elapsed_time": "0:51:24", "remaining_time": "0:41:59", "throughput": 10100.43, "total_tokens": 31153088}
{"current_steps": 32435, "total_steps": 58920, "loss": 0.0002, "lr": 9.983411677989346e-07, "epoch": 2.7524609640190087, "percentage": 55.05, "elapsed_time": "0:51:24", "remaining_time": "0:41:58", "throughput": 10100.64, "total_tokens": 31157568}
{"current_steps": 32440, "total_steps": 58920, "loss": 0.0732, "lr": 9.980449481118458e-07, "epoch": 2.752885268160217, "percentage": 55.06, "elapsed_time": "0:51:25", "remaining_time": "0:41:58", "throughput": 10100.99, "total_tokens": 31162560}
{"current_steps": 32445, "total_steps": 58920, "loss": 0.0001, "lr": 9.977487285963058e-07, "epoch": 2.7533095723014256, "percentage": 55.07, "elapsed_time": "0:51:25", "remaining_time": "0:41:57", "throughput": 10101.36, "total_tokens": 31167616}
{"current_steps": 32450, "total_steps": 58920, "loss": 0.0003, "lr": 9.97452509278307e-07, "epoch": 2.753733876442634, "percentage": 55.07, "elapsed_time": "0:51:25", "remaining_time": "0:41:57", "throughput": 10101.81, "total_tokens": 31172992}
{"current_steps": 32455, "total_steps": 58920, "loss": 0.0, "lr": 9.971562901838413e-07, "epoch": 2.7541581805838424, "percentage": 55.08, "elapsed_time": "0:51:26", "remaining_time": "0:41:56", "throughput": 10102.36, "total_tokens": 31178880}
{"current_steps": 32460, "total_steps": 58920, "loss": 0.0673, "lr": 9.968600713389007e-07, "epoch": 2.754582484725051, "percentage": 55.09, "elapsed_time": "0:51:26", "remaining_time": "0:41:56", "throughput": 10102.7, "total_tokens": 31183808}
{"current_steps": 32465, "total_steps": 58920, "loss": 0.0, "lr": 9.965638527694774e-07, "epoch": 2.7550067888662593, "percentage": 55.1, "elapsed_time": "0:51:27", "remaining_time": "0:41:55", "throughput": 10103.0, "total_tokens": 31188544}
{"current_steps": 32470, "total_steps": 58920, "loss": 0.0223, "lr": 9.962676345015636e-07, "epoch": 2.7554310930074677, "percentage": 55.11, "elapsed_time": "0:51:27", "remaining_time": "0:41:55", "throughput": 10103.34, "total_tokens": 31193536}
{"current_steps": 32475, "total_steps": 58920, "loss": 0.0, "lr": 9.959714165611516e-07, "epoch": 2.755855397148676, "percentage": 55.12, "elapsed_time": "0:51:27", "remaining_time": "0:41:54", "throughput": 10103.59, "total_tokens": 31198080}
{"current_steps": 32480, "total_steps": 58920, "loss": 0.0, "lr": 9.95675198974233e-07, "epoch": 2.7562797012898845, "percentage": 55.13, "elapsed_time": "0:51:28", "remaining_time": "0:41:53", "throughput": 10103.75, "total_tokens": 31202304}
{"current_steps": 32485, "total_steps": 58920, "loss": 0.0001, "lr": 9.953789817668006e-07, "epoch": 2.756704005431093, "percentage": 55.13, "elapsed_time": "0:51:28", "remaining_time": "0:41:53", "throughput": 10104.07, "total_tokens": 31207168}
{"current_steps": 32490, "total_steps": 58920, "loss": 0.0001, "lr": 9.950827649648452e-07, "epoch": 2.7571283095723014, "percentage": 55.14, "elapsed_time": "0:51:28", "remaining_time": "0:41:52", "throughput": 10104.18, "total_tokens": 31211264}
{"current_steps": 32495, "total_steps": 58920, "loss": 0.0374, "lr": 9.947865485943602e-07, "epoch": 2.75755261371351, "percentage": 55.15, "elapsed_time": "0:51:29", "remaining_time": "0:41:52", "throughput": 10104.51, "total_tokens": 31216192}
{"current_steps": 32500, "total_steps": 58920, "loss": 0.0195, "lr": 9.94490332681336e-07, "epoch": 2.757976917854718, "percentage": 55.16, "elapsed_time": "0:51:29", "remaining_time": "0:41:51", "throughput": 10104.86, "total_tokens": 31221184}
{"current_steps": 32505, "total_steps": 58920, "loss": 0.0002, "lr": 9.941941172517654e-07, "epoch": 2.7584012219959266, "percentage": 55.17, "elapsed_time": "0:51:30", "remaining_time": "0:41:51", "throughput": 10105.13, "total_tokens": 31225856}
{"current_steps": 32510, "total_steps": 58920, "loss": 0.0002, "lr": 9.938979023316404e-07, "epoch": 2.758825526137135, "percentage": 55.18, "elapsed_time": "0:51:30", "remaining_time": "0:41:50", "throughput": 10105.45, "total_tokens": 31230720}
{"current_steps": 32515, "total_steps": 58920, "loss": 0.0001, "lr": 9.93601687946952e-07, "epoch": 2.7592498302783435, "percentage": 55.18, "elapsed_time": "0:51:30", "remaining_time": "0:41:50", "throughput": 10105.75, "total_tokens": 31235520}
{"current_steps": 32520, "total_steps": 58920, "loss": 0.0352, "lr": 9.93305474123693e-07, "epoch": 2.759674134419552, "percentage": 55.19, "elapsed_time": "0:51:31", "remaining_time": "0:41:49", "throughput": 10105.92, "total_tokens": 31239808}
{"current_steps": 32525, "total_steps": 58920, "loss": 0.0231, "lr": 9.930092608878536e-07, "epoch": 2.7600984385607603, "percentage": 55.2, "elapsed_time": "0:51:31", "remaining_time": "0:41:48", "throughput": 10106.26, "total_tokens": 31244736}
{"current_steps": 32530, "total_steps": 58920, "loss": 0.0, "lr": 9.927130482654268e-07, "epoch": 2.7605227427019687, "percentage": 55.21, "elapsed_time": "0:51:32", "remaining_time": "0:41:48", "throughput": 10106.5, "total_tokens": 31249344}
{"current_steps": 32535, "total_steps": 58920, "loss": 0.0002, "lr": 9.924168362824039e-07, "epoch": 2.760947046843177, "percentage": 55.22, "elapsed_time": "0:51:32", "remaining_time": "0:41:47", "throughput": 10106.7, "total_tokens": 31253760}
{"current_steps": 32540, "total_steps": 58920, "loss": 0.0322, "lr": 9.921206249647759e-07, "epoch": 2.7613713509843856, "percentage": 55.23, "elapsed_time": "0:51:32", "remaining_time": "0:41:47", "throughput": 10107.03, "total_tokens": 31258688}
{"current_steps": 32545, "total_steps": 58920, "loss": 0.0001, "lr": 9.918244143385347e-07, "epoch": 2.761795655125594, "percentage": 55.24, "elapsed_time": "0:51:33", "remaining_time": "0:41:46", "throughput": 10107.42, "total_tokens": 31263872}
{"current_steps": 32550, "total_steps": 58920, "loss": 0.0001, "lr": 9.915282044296714e-07, "epoch": 2.7622199592668024, "percentage": 55.24, "elapsed_time": "0:51:33", "remaining_time": "0:41:46", "throughput": 10107.79, "total_tokens": 31268864}
{"current_steps": 32555, "total_steps": 58920, "loss": 0.0022, "lr": 9.91231995264178e-07, "epoch": 2.762644263408011, "percentage": 55.25, "elapsed_time": "0:51:33", "remaining_time": "0:41:45", "throughput": 10108.04, "total_tokens": 31273472}
{"current_steps": 32560, "total_steps": 58920, "loss": 0.0101, "lr": 9.90935786868045e-07, "epoch": 2.7630685675492193, "percentage": 55.26, "elapsed_time": "0:51:34", "remaining_time": "0:41:45", "throughput": 10108.28, "total_tokens": 31278016}
{"current_steps": 32565, "total_steps": 58920, "loss": 0.0001, "lr": 9.906395792672643e-07, "epoch": 2.7634928716904277, "percentage": 55.27, "elapsed_time": "0:51:34", "remaining_time": "0:41:44", "throughput": 10108.6, "total_tokens": 31282880}
{"current_steps": 32570, "total_steps": 58920, "loss": 0.0376, "lr": 9.903433724878262e-07, "epoch": 2.763917175831636, "percentage": 55.28, "elapsed_time": "0:51:35", "remaining_time": "0:41:43", "throughput": 10108.95, "total_tokens": 31287936}
{"current_steps": 32575, "total_steps": 58920, "loss": 0.0001, "lr": 9.90047166555723e-07, "epoch": 2.7643414799728445, "percentage": 55.29, "elapsed_time": "0:51:35", "remaining_time": "0:41:43", "throughput": 10109.1, "total_tokens": 31292160}
{"current_steps": 32580, "total_steps": 58920, "loss": 0.0001, "lr": 9.897509614969448e-07, "epoch": 2.764765784114053, "percentage": 55.3, "elapsed_time": "0:51:35", "remaining_time": "0:41:42", "throughput": 10109.33, "total_tokens": 31296704}
{"current_steps": 32585, "total_steps": 58920, "loss": 0.0001, "lr": 9.894547573374824e-07, "epoch": 2.7651900882552614, "percentage": 55.3, "elapsed_time": "0:51:36", "remaining_time": "0:41:42", "throughput": 10109.61, "total_tokens": 31301440}
{"current_steps": 32590, "total_steps": 58920, "loss": 0.0003, "lr": 9.891585541033272e-07, "epoch": 2.76561439239647, "percentage": 55.31, "elapsed_time": "0:51:36", "remaining_time": "0:41:41", "throughput": 10110.05, "total_tokens": 31306816}
{"current_steps": 32595, "total_steps": 58920, "loss": 0.0, "lr": 9.888623518204694e-07, "epoch": 2.766038696537678, "percentage": 55.32, "elapsed_time": "0:51:36", "remaining_time": "0:41:41", "throughput": 10110.46, "total_tokens": 31312064}
{"current_steps": 32600, "total_steps": 58920, "loss": 0.0001, "lr": 9.885661505149007e-07, "epoch": 2.7664630006788866, "percentage": 55.33, "elapsed_time": "0:51:37", "remaining_time": "0:41:40", "throughput": 10110.74, "total_tokens": 31316800}
{"current_steps": 32605, "total_steps": 58920, "loss": 0.0, "lr": 9.882699502126103e-07, "epoch": 2.766887304820095, "percentage": 55.34, "elapsed_time": "0:51:37", "remaining_time": "0:41:40", "throughput": 10111.12, "total_tokens": 31321920}
{"current_steps": 32610, "total_steps": 58920, "loss": 0.0001, "lr": 9.879737509395901e-07, "epoch": 2.7673116089613035, "percentage": 55.35, "elapsed_time": "0:51:38", "remaining_time": "0:41:39", "throughput": 10111.41, "total_tokens": 31326656}
{"current_steps": 32615, "total_steps": 58920, "loss": 0.0, "lr": 9.876775527218292e-07, "epoch": 2.767735913102512, "percentage": 55.35, "elapsed_time": "0:51:38", "remaining_time": "0:41:39", "throughput": 10111.67, "total_tokens": 31331328}
{"current_steps": 32620, "total_steps": 58920, "loss": 0.0, "lr": 9.873813555853187e-07, "epoch": 2.7681602172437203, "percentage": 55.36, "elapsed_time": "0:51:38", "remaining_time": "0:41:38", "throughput": 10112.02, "total_tokens": 31336320}
{"current_steps": 32625, "total_steps": 58920, "loss": 0.0285, "lr": 9.87085159556049e-07, "epoch": 2.7685845213849287, "percentage": 55.37, "elapsed_time": "0:51:39", "remaining_time": "0:41:37", "throughput": 10112.26, "total_tokens": 31340864}
{"current_steps": 32630, "total_steps": 58920, "loss": 0.0014, "lr": 9.867889646600098e-07, "epoch": 2.769008825526137, "percentage": 55.38, "elapsed_time": "0:51:39", "remaining_time": "0:41:37", "throughput": 10112.48, "total_tokens": 31345344}
{"current_steps": 32635, "total_steps": 58920, "loss": 0.0431, "lr": 9.864927709231912e-07, "epoch": 2.7694331296673456, "percentage": 55.39, "elapsed_time": "0:51:40", "remaining_time": "0:41:36", "throughput": 10112.78, "total_tokens": 31350144}
{"current_steps": 32640, "total_steps": 58920, "loss": 0.041, "lr": 9.86196578371583e-07, "epoch": 2.769857433808554, "percentage": 55.4, "elapsed_time": "0:51:40", "remaining_time": "0:41:36", "throughput": 10112.89, "total_tokens": 31354304}
{"current_steps": 32645, "total_steps": 58920, "loss": 0.0, "lr": 9.859003870311757e-07, "epoch": 2.7702817379497624, "percentage": 55.41, "elapsed_time": "0:51:40", "remaining_time": "0:41:35", "throughput": 10113.28, "total_tokens": 31359424}
{"current_steps": 32650, "total_steps": 58920, "loss": 0.0, "lr": 9.85604196927958e-07, "epoch": 2.770706042090971, "percentage": 55.41, "elapsed_time": "0:51:41", "remaining_time": "0:41:35", "throughput": 10113.64, "total_tokens": 31364480}
{"current_steps": 32655, "total_steps": 58920, "loss": 0.0, "lr": 9.853080080879203e-07, "epoch": 2.7711303462321792, "percentage": 55.42, "elapsed_time": "0:51:41", "remaining_time": "0:41:34", "throughput": 10113.98, "total_tokens": 31369408}
{"current_steps": 32660, "total_steps": 58920, "loss": 0.0001, "lr": 9.85011820537052e-07, "epoch": 2.7715546503733877, "percentage": 55.43, "elapsed_time": "0:51:41", "remaining_time": "0:41:34", "throughput": 10114.23, "total_tokens": 31374016}
{"current_steps": 32665, "total_steps": 58920, "loss": 0.0, "lr": 9.84715634301342e-07, "epoch": 2.771978954514596, "percentage": 55.44, "elapsed_time": "0:51:42", "remaining_time": "0:41:33", "throughput": 10114.45, "total_tokens": 31378496}
{"current_steps": 32670, "total_steps": 58920, "loss": 0.0, "lr": 9.844194494067801e-07, "epoch": 2.7724032586558045, "percentage": 55.45, "elapsed_time": "0:51:42", "remaining_time": "0:41:33", "throughput": 10114.81, "total_tokens": 31383552}
{"current_steps": 32675, "total_steps": 58920, "loss": 0.0002, "lr": 9.841232658793551e-07, "epoch": 2.772827562797013, "percentage": 55.46, "elapsed_time": "0:51:43", "remaining_time": "0:41:32", "throughput": 10115.09, "total_tokens": 31388288}
{"current_steps": 32680, "total_steps": 58920, "loss": 0.0, "lr": 9.838270837450562e-07, "epoch": 2.7732518669382213, "percentage": 55.47, "elapsed_time": "0:51:43", "remaining_time": "0:41:31", "throughput": 10115.3, "total_tokens": 31392768}
{"current_steps": 32685, "total_steps": 58920, "loss": 0.0, "lr": 9.835309030298723e-07, "epoch": 2.7736761710794298, "percentage": 55.47, "elapsed_time": "0:51:43", "remaining_time": "0:41:31", "throughput": 10115.51, "total_tokens": 31397184}
{"current_steps": 32690, "total_steps": 58920, "loss": 0.0001, "lr": 9.832347237597926e-07, "epoch": 2.774100475220638, "percentage": 55.48, "elapsed_time": "0:51:44", "remaining_time": "0:41:30", "throughput": 10115.65, "total_tokens": 31401408}
{"current_steps": 32695, "total_steps": 58920, "loss": 0.0298, "lr": 9.829385459608048e-07, "epoch": 2.7745247793618466, "percentage": 55.49, "elapsed_time": "0:51:44", "remaining_time": "0:41:30", "throughput": 10116.2, "total_tokens": 31407360}
{"current_steps": 32700, "total_steps": 58920, "loss": 0.0494, "lr": 9.826423696588984e-07, "epoch": 2.774949083503055, "percentage": 55.5, "elapsed_time": "0:51:45", "remaining_time": "0:41:29", "throughput": 10116.47, "total_tokens": 31412096}
{"current_steps": 32705, "total_steps": 58920, "loss": 0.0514, "lr": 9.823461948800613e-07, "epoch": 2.7753733876442634, "percentage": 55.51, "elapsed_time": "0:51:45", "remaining_time": "0:41:29", "throughput": 10116.72, "total_tokens": 31416704}
{"current_steps": 32710, "total_steps": 58920, "loss": 0.0001, "lr": 9.820500216502818e-07, "epoch": 2.775797691785472, "percentage": 55.52, "elapsed_time": "0:51:45", "remaining_time": "0:41:28", "throughput": 10116.91, "total_tokens": 31421120}
{"current_steps": 32715, "total_steps": 58920, "loss": 0.0001, "lr": 9.817538499955482e-07, "epoch": 2.7762219959266803, "percentage": 55.52, "elapsed_time": "0:51:46", "remaining_time": "0:41:28", "throughput": 10117.07, "total_tokens": 31425408}
{"current_steps": 32720, "total_steps": 58920, "loss": 0.0001, "lr": 9.81457679941848e-07, "epoch": 2.7766463000678887, "percentage": 55.53, "elapsed_time": "0:51:46", "remaining_time": "0:41:27", "throughput": 10117.32, "total_tokens": 31430016}
{"current_steps": 32725, "total_steps": 58920, "loss": 0.0003, "lr": 9.8116151151517e-07, "epoch": 2.777070604209097, "percentage": 55.54, "elapsed_time": "0:51:46", "remaining_time": "0:41:26", "throughput": 10117.61, "total_tokens": 31434752}
{"current_steps": 32730, "total_steps": 58920, "loss": 0.0001, "lr": 9.80865344741501e-07, "epoch": 2.7774949083503055, "percentage": 55.55, "elapsed_time": "0:51:47", "remaining_time": "0:41:26", "throughput": 10117.93, "total_tokens": 31439616}
{"current_steps": 32735, "total_steps": 58920, "loss": 0.0001, "lr": 9.805691796468292e-07, "epoch": 2.777919212491514, "percentage": 55.56, "elapsed_time": "0:51:47", "remaining_time": "0:41:25", "throughput": 10118.44, "total_tokens": 31445376}
{"current_steps": 32740, "total_steps": 58920, "loss": 0.0001, "lr": 9.802730162571411e-07, "epoch": 2.7783435166327224, "percentage": 55.57, "elapsed_time": "0:51:48", "remaining_time": "0:41:25", "throughput": 10118.65, "total_tokens": 31449856}
{"current_steps": 32745, "total_steps": 58920, "loss": 0.0003, "lr": 9.799768545984252e-07, "epoch": 2.778767820773931, "percentage": 55.58, "elapsed_time": "0:51:48", "remaining_time": "0:41:24", "throughput": 10118.86, "total_tokens": 31454336}
{"current_steps": 32750, "total_steps": 58920, "loss": 0.0, "lr": 9.79680694696668e-07, "epoch": 2.7791921249151392, "percentage": 55.58, "elapsed_time": "0:51:48", "remaining_time": "0:41:24", "throughput": 10119.13, "total_tokens": 31459072}
{"current_steps": 32755, "total_steps": 58920, "loss": 0.0, "lr": 9.793845365778562e-07, "epoch": 2.7796164290563476, "percentage": 55.59, "elapsed_time": "0:51:49", "remaining_time": "0:41:23", "throughput": 10119.5, "total_tokens": 31464192}
{"current_steps": 32760, "total_steps": 58920, "loss": 0.0, "lr": 9.790883802679772e-07, "epoch": 2.780040733197556, "percentage": 55.6, "elapsed_time": "0:51:49", "remaining_time": "0:41:23", "throughput": 10119.93, "total_tokens": 31469504}
{"current_steps": 32765, "total_steps": 58920, "loss": 0.0131, "lr": 9.78792225793017e-07, "epoch": 2.7804650373387645, "percentage": 55.61, "elapsed_time": "0:51:50", "remaining_time": "0:41:22", "throughput": 10120.29, "total_tokens": 31474560}
{"current_steps": 32770, "total_steps": 58920, "loss": 0.0003, "lr": 9.784960731789625e-07, "epoch": 2.780889341479973, "percentage": 55.62, "elapsed_time": "0:51:50", "remaining_time": "0:41:22", "throughput": 10120.41, "total_tokens": 31478720}
{"current_steps": 32775, "total_steps": 58920, "loss": 0.0001, "lr": 9.781999224518e-07, "epoch": 2.7813136456211813, "percentage": 55.63, "elapsed_time": "0:51:50", "remaining_time": "0:41:21", "throughput": 10120.75, "total_tokens": 31483776}
{"current_steps": 32780, "total_steps": 58920, "loss": 0.0, "lr": 9.779037736375156e-07, "epoch": 2.7817379497623897, "percentage": 55.63, "elapsed_time": "0:51:51", "remaining_time": "0:41:20", "throughput": 10120.96, "total_tokens": 31488256}
{"current_steps": 32785, "total_steps": 58920, "loss": 0.0442, "lr": 9.776076267620953e-07, "epoch": 2.782162253903598, "percentage": 55.64, "elapsed_time": "0:51:51", "remaining_time": "0:41:20", "throughput": 10121.2, "total_tokens": 31492864}
{"current_steps": 32790, "total_steps": 58920, "loss": 0.0001, "lr": 9.773114818515247e-07, "epoch": 2.7825865580448066, "percentage": 55.65, "elapsed_time": "0:51:51", "remaining_time": "0:41:19", "throughput": 10121.53, "total_tokens": 31497856}
{"current_steps": 32795, "total_steps": 58920, "loss": 0.0044, "lr": 9.770153389317901e-07, "epoch": 2.783010862186015, "percentage": 55.66, "elapsed_time": "0:51:52", "remaining_time": "0:41:19", "throughput": 10121.7, "total_tokens": 31502208}
{"current_steps": 32800, "total_steps": 58920, "loss": 0.0001, "lr": 9.76719198028876e-07, "epoch": 2.7834351663272234, "percentage": 55.67, "elapsed_time": "0:51:52", "remaining_time": "0:41:18", "throughput": 10121.93, "total_tokens": 31506816}
{"current_steps": 32805, "total_steps": 58920, "loss": 0.0, "lr": 9.764230591687685e-07, "epoch": 2.783859470468432, "percentage": 55.68, "elapsed_time": "0:51:53", "remaining_time": "0:41:18", "throughput": 10122.26, "total_tokens": 31511744}
{"current_steps": 32810, "total_steps": 58920, "loss": 0.0, "lr": 9.761269223774522e-07, "epoch": 2.7842837746096403, "percentage": 55.69, "elapsed_time": "0:51:53", "remaining_time": "0:41:17", "throughput": 10122.51, "total_tokens": 31516416}
{"current_steps": 32815, "total_steps": 58920, "loss": 0.0287, "lr": 9.758307876809127e-07, "epoch": 2.7847080787508487, "percentage": 55.69, "elapsed_time": "0:51:53", "remaining_time": "0:41:17", "throughput": 10122.8, "total_tokens": 31521280}
{"current_steps": 32820, "total_steps": 58920, "loss": 0.0, "lr": 9.755346551051338e-07, "epoch": 2.785132382892057, "percentage": 55.7, "elapsed_time": "0:51:54", "remaining_time": "0:41:16", "throughput": 10123.0, "total_tokens": 31525696}
{"current_steps": 32825, "total_steps": 58920, "loss": 0.0001, "lr": 9.752385246761013e-07, "epoch": 2.7855566870332655, "percentage": 55.71, "elapsed_time": "0:51:54", "remaining_time": "0:41:16", "throughput": 10123.33, "total_tokens": 31530752}
{"current_steps": 32830, "total_steps": 58920, "loss": 0.0001, "lr": 9.749423964197985e-07, "epoch": 2.785980991174474, "percentage": 55.72, "elapsed_time": "0:51:55", "remaining_time": "0:41:15", "throughput": 10123.67, "total_tokens": 31535744}
{"current_steps": 32835, "total_steps": 58920, "loss": 0.0, "lr": 9.746462703622094e-07, "epoch": 2.7864052953156824, "percentage": 55.73, "elapsed_time": "0:51:55", "remaining_time": "0:41:14", "throughput": 10123.93, "total_tokens": 31540416}
{"current_steps": 32840, "total_steps": 58920, "loss": 0.0, "lr": 9.743501465293193e-07, "epoch": 2.786829599456891, "percentage": 55.74, "elapsed_time": "0:51:55", "remaining_time": "0:41:14", "throughput": 10124.28, "total_tokens": 31545536}
{"current_steps": 32845, "total_steps": 58920, "loss": 0.0, "lr": 9.740540249471107e-07, "epoch": 2.787253903598099, "percentage": 55.75, "elapsed_time": "0:51:56", "remaining_time": "0:41:13", "throughput": 10124.57, "total_tokens": 31550400}
{"current_steps": 32850, "total_steps": 58920, "loss": 0.0, "lr": 9.737579056415681e-07, "epoch": 2.7876782077393076, "percentage": 55.75, "elapsed_time": "0:51:56", "remaining_time": "0:41:13", "throughput": 10124.88, "total_tokens": 31555264}
{"current_steps": 32855, "total_steps": 58920, "loss": 0.0379, "lr": 9.734617886386744e-07, "epoch": 2.788102511880516, "percentage": 55.76, "elapsed_time": "0:51:57", "remaining_time": "0:41:12", "throughput": 10125.24, "total_tokens": 31560384}
{"current_steps": 32860, "total_steps": 58920, "loss": 0.0, "lr": 9.73165673964413e-07, "epoch": 2.7885268160217245, "percentage": 55.77, "elapsed_time": "0:51:57", "remaining_time": "0:41:12", "throughput": 10125.49, "total_tokens": 31564992}
{"current_steps": 32865, "total_steps": 58920, "loss": 0.0488, "lr": 9.728695616447666e-07, "epoch": 2.788951120162933, "percentage": 55.78, "elapsed_time": "0:51:57", "remaining_time": "0:41:11", "throughput": 10125.86, "total_tokens": 31570176}
{"current_steps": 32870, "total_steps": 58920, "loss": 0.0001, "lr": 9.725734517057184e-07, "epoch": 2.7893754243041413, "percentage": 55.79, "elapsed_time": "0:51:58", "remaining_time": "0:41:11", "throughput": 10126.18, "total_tokens": 31575168}
{"current_steps": 32875, "total_steps": 58920, "loss": 0.0279, "lr": 9.72277344173251e-07, "epoch": 2.7897997284453497, "percentage": 55.8, "elapsed_time": "0:51:58", "remaining_time": "0:41:10", "throughput": 10126.45, "total_tokens": 31579968}
{"current_steps": 32880, "total_steps": 58920, "loss": 0.0002, "lr": 9.719812390733463e-07, "epoch": 2.790224032586558, "percentage": 55.8, "elapsed_time": "0:51:58", "remaining_time": "0:41:10", "throughput": 10126.66, "total_tokens": 31584512}
{"current_steps": 32885, "total_steps": 58920, "loss": 0.0001, "lr": 9.716851364319868e-07, "epoch": 2.7906483367277666, "percentage": 55.81, "elapsed_time": "0:51:59", "remaining_time": "0:41:09", "throughput": 10126.87, "total_tokens": 31588992}
{"current_steps": 32890, "total_steps": 58920, "loss": 0.0001, "lr": 9.71389036275154e-07, "epoch": 2.791072640868975, "percentage": 55.82, "elapsed_time": "0:51:59", "remaining_time": "0:41:09", "throughput": 10127.17, "total_tokens": 31593920}
{"current_steps": 32895, "total_steps": 58920, "loss": 0.0001, "lr": 9.710929386288304e-07, "epoch": 2.7914969450101834, "percentage": 55.83, "elapsed_time": "0:52:00", "remaining_time": "0:41:08", "throughput": 10127.45, "total_tokens": 31598720}
{"current_steps": 32900, "total_steps": 58920, "loss": 0.0004, "lr": 9.707968435189965e-07, "epoch": 2.791921249151392, "percentage": 55.84, "elapsed_time": "0:52:00", "remaining_time": "0:41:07", "throughput": 10127.8, "total_tokens": 31603776}
{"current_steps": 32905, "total_steps": 58920, "loss": 0.0, "lr": 9.70500750971635e-07, "epoch": 2.7923455532926003, "percentage": 55.85, "elapsed_time": "0:52:00", "remaining_time": "0:41:07", "throughput": 10128.19, "total_tokens": 31609024}
{"current_steps": 32910, "total_steps": 58920, "loss": 0.0, "lr": 9.702046610127257e-07, "epoch": 2.7927698574338087, "percentage": 55.86, "elapsed_time": "0:52:01", "remaining_time": "0:41:06", "throughput": 10128.48, "total_tokens": 31613888}
{"current_steps": 32915, "total_steps": 58920, "loss": 0.0172, "lr": 9.699085736682496e-07, "epoch": 2.793194161575017, "percentage": 55.86, "elapsed_time": "0:52:01", "remaining_time": "0:41:06", "throughput": 10128.67, "total_tokens": 31618368}
{"current_steps": 32920, "total_steps": 58920, "loss": 0.0, "lr": 9.69612488964188e-07, "epoch": 2.7936184657162255, "percentage": 55.87, "elapsed_time": "0:52:02", "remaining_time": "0:41:05", "throughput": 10129.0, "total_tokens": 31623360}
{"current_steps": 32925, "total_steps": 58920, "loss": 0.0773, "lr": 9.693164069265202e-07, "epoch": 2.794042769857434, "percentage": 55.88, "elapsed_time": "0:52:02", "remaining_time": "0:41:05", "throughput": 10129.35, "total_tokens": 31628480}
{"current_steps": 32930, "total_steps": 58920, "loss": 0.0, "lr": 9.690203275812271e-07, "epoch": 2.7944670739986424, "percentage": 55.89, "elapsed_time": "0:52:02", "remaining_time": "0:41:04", "throughput": 10129.59, "total_tokens": 31633152}
{"current_steps": 32935, "total_steps": 58920, "loss": 0.0164, "lr": 9.687242509542883e-07, "epoch": 2.794891378139851, "percentage": 55.9, "elapsed_time": "0:52:03", "remaining_time": "0:41:04", "throughput": 10129.96, "total_tokens": 31638336}
{"current_steps": 32940, "total_steps": 58920, "loss": 0.0, "lr": 9.68428177071684e-07, "epoch": 2.795315682281059, "percentage": 55.91, "elapsed_time": "0:52:03", "remaining_time": "0:41:03", "throughput": 10130.17, "total_tokens": 31642880}
{"current_steps": 32945, "total_steps": 58920, "loss": 0.0301, "lr": 9.681321059593927e-07, "epoch": 2.7957399864222676, "percentage": 55.91, "elapsed_time": "0:52:04", "remaining_time": "0:41:03", "throughput": 10130.51, "total_tokens": 31647936}
{"current_steps": 32950, "total_steps": 58920, "loss": 0.0001, "lr": 9.678360376433944e-07, "epoch": 2.796164290563476, "percentage": 55.92, "elapsed_time": "0:52:04", "remaining_time": "0:41:02", "throughput": 10130.84, "total_tokens": 31652928}
{"current_steps": 32955, "total_steps": 58920, "loss": 0.0, "lr": 9.675399721496678e-07, "epoch": 2.7965885947046845, "percentage": 55.93, "elapsed_time": "0:52:04", "remaining_time": "0:41:02", "throughput": 10131.09, "total_tokens": 31657664}
{"current_steps": 32960, "total_steps": 58920, "loss": 0.0191, "lr": 9.672439095041908e-07, "epoch": 2.797012898845893, "percentage": 55.94, "elapsed_time": "0:52:05", "remaining_time": "0:41:01", "throughput": 10131.22, "total_tokens": 31661888}
{"current_steps": 32965, "total_steps": 58920, "loss": 0.0001, "lr": 9.669478497329432e-07, "epoch": 2.7974372029871013, "percentage": 55.95, "elapsed_time": "0:52:05", "remaining_time": "0:41:00", "throughput": 10131.48, "total_tokens": 31666624}
{"current_steps": 32970, "total_steps": 58920, "loss": 0.004, "lr": 9.666517928619018e-07, "epoch": 2.7978615071283097, "percentage": 55.96, "elapsed_time": "0:52:05", "remaining_time": "0:41:00", "throughput": 10131.78, "total_tokens": 31671488}
{"current_steps": 32975, "total_steps": 58920, "loss": 0.0406, "lr": 9.663557389170457e-07, "epoch": 2.798285811269518, "percentage": 55.97, "elapsed_time": "0:52:06", "remaining_time": "0:40:59", "throughput": 10132.0, "total_tokens": 31676032}
{"current_steps": 32980, "total_steps": 58920, "loss": 0.003, "lr": 9.660596879243515e-07, "epoch": 2.7987101154107266, "percentage": 55.97, "elapsed_time": "0:52:06", "remaining_time": "0:40:59", "throughput": 10132.12, "total_tokens": 31680192}
{"current_steps": 32985, "total_steps": 58920, "loss": 0.0001, "lr": 9.657636399097977e-07, "epoch": 2.799134419551935, "percentage": 55.98, "elapsed_time": "0:52:07", "remaining_time": "0:40:58", "throughput": 10132.46, "total_tokens": 31685184}
{"current_steps": 32990, "total_steps": 58920, "loss": 0.0001, "lr": 9.654675948993604e-07, "epoch": 2.7995587236931434, "percentage": 55.99, "elapsed_time": "0:52:07", "remaining_time": "0:40:58", "throughput": 10132.83, "total_tokens": 31690368}
{"current_steps": 32995, "total_steps": 58920, "loss": 0.0, "lr": 9.651715529190172e-07, "epoch": 2.799983027834352, "percentage": 56.0, "elapsed_time": "0:52:07", "remaining_time": "0:40:57", "throughput": 10133.05, "total_tokens": 31694912}
{"current_steps": 33000, "total_steps": 58920, "loss": 0.0493, "lr": 9.648755139947448e-07, "epoch": 2.8004073319755602, "percentage": 56.01, "elapsed_time": "0:52:08", "remaining_time": "0:40:57", "throughput": 10133.4, "total_tokens": 31699968}
{"current_steps": 33005, "total_steps": 58920, "loss": 0.0441, "lr": 9.645794781525188e-07, "epoch": 2.8008316361167687, "percentage": 56.02, "elapsed_time": "0:52:08", "remaining_time": "0:40:56", "throughput": 10133.73, "total_tokens": 31704960}
{"current_steps": 33010, "total_steps": 58920, "loss": 0.019, "lr": 9.64283445418316e-07, "epoch": 2.801255940257977, "percentage": 56.03, "elapsed_time": "0:52:09", "remaining_time": "0:40:56", "throughput": 10134.14, "total_tokens": 31710272}
{"current_steps": 33015, "total_steps": 58920, "loss": 0.0001, "lr": 9.639874158181114e-07, "epoch": 2.8016802443991855, "percentage": 56.03, "elapsed_time": "0:52:09", "remaining_time": "0:40:55", "throughput": 10134.29, "total_tokens": 31714560}
{"current_steps": 33020, "total_steps": 58920, "loss": 0.0359, "lr": 9.636913893778815e-07, "epoch": 2.8021045485403935, "percentage": 56.04, "elapsed_time": "0:52:09", "remaining_time": "0:40:54", "throughput": 10134.53, "total_tokens": 31719168}
{"current_steps": 33025, "total_steps": 58920, "loss": 0.0075, "lr": 9.633953661236008e-07, "epoch": 2.8025288526816023, "percentage": 56.05, "elapsed_time": "0:52:10", "remaining_time": "0:40:54", "throughput": 10134.82, "total_tokens": 31723904}
{"current_steps": 33030, "total_steps": 58920, "loss": 0.0541, "lr": 9.63099346081245e-07, "epoch": 2.8029531568228103, "percentage": 56.06, "elapsed_time": "0:52:10", "remaining_time": "0:40:53", "throughput": 10135.08, "total_tokens": 31728576}
{"current_steps": 33035, "total_steps": 58920, "loss": 0.0001, "lr": 9.628033292767882e-07, "epoch": 2.803377460964019, "percentage": 56.07, "elapsed_time": "0:52:10", "remaining_time": "0:40:53", "throughput": 10135.35, "total_tokens": 31733248}
{"current_steps": 33040, "total_steps": 58920, "loss": 0.0003, "lr": 9.625073157362047e-07, "epoch": 2.803801765105227, "percentage": 56.08, "elapsed_time": "0:52:11", "remaining_time": "0:40:52", "throughput": 10135.65, "total_tokens": 31738048}
{"current_steps": 33045, "total_steps": 58920, "loss": 0.0001, "lr": 9.62211305485469e-07, "epoch": 2.804226069246436, "percentage": 56.08, "elapsed_time": "0:52:11", "remaining_time": "0:40:52", "throughput": 10135.99, "total_tokens": 31743040}
{"current_steps": 33050, "total_steps": 58920, "loss": 0.0196, "lr": 9.619152985505545e-07, "epoch": 2.804650373387644, "percentage": 56.09, "elapsed_time": "0:52:12", "remaining_time": "0:40:51", "throughput": 10136.2, "total_tokens": 31747520}
{"current_steps": 33055, "total_steps": 58920, "loss": 0.0008, "lr": 9.616192949574356e-07, "epoch": 2.805074677528853, "percentage": 56.1, "elapsed_time": "0:52:12", "remaining_time": "0:40:51", "throughput": 10136.43, "total_tokens": 31752064}
{"current_steps": 33060, "total_steps": 58920, "loss": 0.0001, "lr": 9.613232947320847e-07, "epoch": 2.805498981670061, "percentage": 56.11, "elapsed_time": "0:52:12", "remaining_time": "0:40:50", "throughput": 10136.75, "total_tokens": 31757056}
{"current_steps": 33065, "total_steps": 58920, "loss": 0.0001, "lr": 9.610272979004752e-07, "epoch": 2.8059232858112697, "percentage": 56.12, "elapsed_time": "0:52:13", "remaining_time": "0:40:50", "throughput": 10136.99, "total_tokens": 31761600}
{"current_steps": 33070, "total_steps": 58920, "loss": 0.0001, "lr": 9.607313044885794e-07, "epoch": 2.8063475899524777, "percentage": 56.13, "elapsed_time": "0:52:13", "remaining_time": "0:40:49", "throughput": 10137.43, "total_tokens": 31766976}
{"current_steps": 33075, "total_steps": 58920, "loss": 0.0246, "lr": 9.604353145223702e-07, "epoch": 2.8067718940936865, "percentage": 56.14, "elapsed_time": "0:52:14", "remaining_time": "0:40:48", "throughput": 10137.75, "total_tokens": 31771840}
{"current_steps": 33080, "total_steps": 58920, "loss": 0.0001, "lr": 9.60139328027819e-07, "epoch": 2.8071961982348945, "percentage": 56.14, "elapsed_time": "0:52:14", "remaining_time": "0:40:48", "throughput": 10138.06, "total_tokens": 31776704}
{"current_steps": 33085, "total_steps": 58920, "loss": 0.0232, "lr": 9.598433450308978e-07, "epoch": 2.8076205023761034, "percentage": 56.15, "elapsed_time": "0:52:14", "remaining_time": "0:40:47", "throughput": 10138.43, "total_tokens": 31781824}
{"current_steps": 33090, "total_steps": 58920, "loss": 0.0001, "lr": 9.595473655575783e-07, "epoch": 2.8080448065173114, "percentage": 56.16, "elapsed_time": "0:52:15", "remaining_time": "0:40:47", "throughput": 10138.61, "total_tokens": 31786176}
{"current_steps": 33095, "total_steps": 58920, "loss": 0.0718, "lr": 9.592513896338312e-07, "epoch": 2.8084691106585202, "percentage": 56.17, "elapsed_time": "0:52:15", "remaining_time": "0:40:46", "throughput": 10138.89, "total_tokens": 31790912}
{"current_steps": 33100, "total_steps": 58920, "loss": 0.0572, "lr": 9.58955417285628e-07, "epoch": 2.808893414799728, "percentage": 56.18, "elapsed_time": "0:52:15", "remaining_time": "0:40:46", "throughput": 10139.21, "total_tokens": 31795840}
{"current_steps": 33105, "total_steps": 58920, "loss": 0.0002, "lr": 9.586594485389382e-07, "epoch": 2.809317718940937, "percentage": 56.19, "elapsed_time": "0:52:16", "remaining_time": "0:40:45", "throughput": 10139.45, "total_tokens": 31800384}
{"current_steps": 33110, "total_steps": 58920, "loss": 0.0231, "lr": 9.583634834197326e-07, "epoch": 2.809742023082145, "percentage": 56.19, "elapsed_time": "0:52:16", "remaining_time": "0:40:45", "throughput": 10139.79, "total_tokens": 31805376}
{"current_steps": 33115, "total_steps": 58920, "loss": 0.0003, "lr": 9.58067521953981e-07, "epoch": 2.810166327223354, "percentage": 56.2, "elapsed_time": "0:52:17", "remaining_time": "0:40:44", "throughput": 10140.04, "total_tokens": 31809984}
{"current_steps": 33120, "total_steps": 58920, "loss": 0.0002, "lr": 9.577715641676532e-07, "epoch": 2.810590631364562, "percentage": 56.21, "elapsed_time": "0:52:17", "remaining_time": "0:40:44", "throughput": 10140.42, "total_tokens": 31815168}
{"current_steps": 33125, "total_steps": 58920, "loss": 0.023, "lr": 9.574756100867184e-07, "epoch": 2.8110149355057708, "percentage": 56.22, "elapsed_time": "0:52:17", "remaining_time": "0:40:43", "throughput": 10140.77, "total_tokens": 31820096}
{"current_steps": 33130, "total_steps": 58920, "loss": 0.0187, "lr": 9.571796597371447e-07, "epoch": 2.8114392396469787, "percentage": 56.23, "elapsed_time": "0:52:18", "remaining_time": "0:40:42", "throughput": 10141.07, "total_tokens": 31824960}
{"current_steps": 33135, "total_steps": 58920, "loss": 0.0002, "lr": 9.568837131449017e-07, "epoch": 2.8118635437881876, "percentage": 56.24, "elapsed_time": "0:52:18", "remaining_time": "0:40:42", "throughput": 10141.25, "total_tokens": 31829312}
{"current_steps": 33140, "total_steps": 58920, "loss": 0.0003, "lr": 9.565877703359567e-07, "epoch": 2.8122878479293956, "percentage": 56.25, "elapsed_time": "0:52:18", "remaining_time": "0:40:41", "throughput": 10141.66, "total_tokens": 31834624}
{"current_steps": 33145, "total_steps": 58920, "loss": 0.0001, "lr": 9.562918313362786e-07, "epoch": 2.8127121520706044, "percentage": 56.25, "elapsed_time": "0:52:19", "remaining_time": "0:40:41", "throughput": 10141.97, "total_tokens": 31839488}
{"current_steps": 33150, "total_steps": 58920, "loss": 0.0, "lr": 9.559958961718342e-07, "epoch": 2.8131364562118124, "percentage": 56.26, "elapsed_time": "0:52:19", "remaining_time": "0:40:40", "throughput": 10142.39, "total_tokens": 31844800}
{"current_steps": 33155, "total_steps": 58920, "loss": 0.0173, "lr": 9.556999648685913e-07, "epoch": 2.8135607603530213, "percentage": 56.27, "elapsed_time": "0:52:20", "remaining_time": "0:40:40", "throughput": 10142.6, "total_tokens": 31849280}
{"current_steps": 33160, "total_steps": 58920, "loss": 0.0562, "lr": 9.554040374525167e-07, "epoch": 2.8139850644942292, "percentage": 56.28, "elapsed_time": "0:52:20", "remaining_time": "0:40:39", "throughput": 10143.0, "total_tokens": 31854528}
{"current_steps": 33165, "total_steps": 58920, "loss": 0.0306, "lr": 9.55108113949576e-07, "epoch": 2.814409368635438, "percentage": 56.29, "elapsed_time": "0:52:20", "remaining_time": "0:40:39", "throughput": 10143.24, "total_tokens": 31859072}
{"current_steps": 33170, "total_steps": 58920, "loss": 0.0001, "lr": 9.548121943857368e-07, "epoch": 2.814833672776646, "percentage": 56.3, "elapsed_time": "0:52:21", "remaining_time": "0:40:38", "throughput": 10143.45, "total_tokens": 31863552}
{"current_steps": 33175, "total_steps": 58920, "loss": 0.0278, "lr": 9.545162787869642e-07, "epoch": 2.815257976917855, "percentage": 56.31, "elapsed_time": "0:52:21", "remaining_time": "0:40:38", "throughput": 10144.49, "total_tokens": 31871680}
{"current_steps": 33180, "total_steps": 58920, "loss": 0.0001, "lr": 9.542203671792241e-07, "epoch": 2.815682281059063, "percentage": 56.31, "elapsed_time": "0:52:22", "remaining_time": "0:40:37", "throughput": 10145.16, "total_tokens": 31878016}
{"current_steps": 33185, "total_steps": 58920, "loss": 0.0001, "lr": 9.539244595884814e-07, "epoch": 2.816106585200272, "percentage": 56.32, "elapsed_time": "0:52:22", "remaining_time": "0:40:37", "throughput": 10145.31, "total_tokens": 31882240}
{"current_steps": 33190, "total_steps": 58920, "loss": 0.044, "lr": 9.536285560407011e-07, "epoch": 2.8165308893414798, "percentage": 56.33, "elapsed_time": "0:52:22", "remaining_time": "0:40:36", "throughput": 10145.52, "total_tokens": 31886720}
{"current_steps": 33195, "total_steps": 58920, "loss": 0.0056, "lr": 9.533326565618474e-07, "epoch": 2.8169551934826886, "percentage": 56.34, "elapsed_time": "0:52:23", "remaining_time": "0:40:35", "throughput": 10145.76, "total_tokens": 31891264}
{"current_steps": 33200, "total_steps": 58920, "loss": 0.0002, "lr": 9.530367611778849e-07, "epoch": 2.8173794976238966, "percentage": 56.35, "elapsed_time": "0:52:23", "remaining_time": "0:40:35", "throughput": 10146.0, "total_tokens": 31895808}
{"current_steps": 33205, "total_steps": 58920, "loss": 0.0465, "lr": 9.527408699147769e-07, "epoch": 2.8178038017651055, "percentage": 56.36, "elapsed_time": "0:52:24", "remaining_time": "0:40:34", "throughput": 10146.18, "total_tokens": 31900160}
{"current_steps": 33210, "total_steps": 58920, "loss": 0.0001, "lr": 9.524449827984866e-07, "epoch": 2.8182281059063135, "percentage": 56.36, "elapsed_time": "0:52:24", "remaining_time": "0:40:34", "throughput": 10146.28, "total_tokens": 31904192}
{"current_steps": 33215, "total_steps": 58920, "loss": 0.0196, "lr": 9.52149099854978e-07, "epoch": 2.8186524100475223, "percentage": 56.37, "elapsed_time": "0:52:24", "remaining_time": "0:40:33", "throughput": 10146.91, "total_tokens": 31910400}
{"current_steps": 33220, "total_steps": 58920, "loss": 0.0159, "lr": 9.518532211102125e-07, "epoch": 2.8190767141887303, "percentage": 56.38, "elapsed_time": "0:52:25", "remaining_time": "0:40:33", "throughput": 10147.28, "total_tokens": 31915456}
{"current_steps": 33225, "total_steps": 58920, "loss": 0.0001, "lr": 9.515573465901536e-07, "epoch": 2.819501018329939, "percentage": 56.39, "elapsed_time": "0:52:25", "remaining_time": "0:40:32", "throughput": 10147.77, "total_tokens": 31921088}
{"current_steps": 33230, "total_steps": 58920, "loss": 0.0514, "lr": 9.512614763207621e-07, "epoch": 2.819925322471147, "percentage": 56.4, "elapsed_time": "0:52:26", "remaining_time": "0:40:32", "throughput": 10148.08, "total_tokens": 31925888}
{"current_steps": 33235, "total_steps": 58920, "loss": 0.0001, "lr": 9.509656103280002e-07, "epoch": 2.820349626612356, "percentage": 56.41, "elapsed_time": "0:52:26", "remaining_time": "0:40:31", "throughput": 10148.28, "total_tokens": 31930304}
{"current_steps": 33240, "total_steps": 58920, "loss": 0.0153, "lr": 9.506697486378288e-07, "epoch": 2.820773930753564, "percentage": 56.42, "elapsed_time": "0:52:26", "remaining_time": "0:40:31", "throughput": 10148.49, "total_tokens": 31934720}
{"current_steps": 33245, "total_steps": 58920, "loss": 0.0782, "lr": 9.503738912762094e-07, "epoch": 2.821198234894773, "percentage": 56.42, "elapsed_time": "0:52:27", "remaining_time": "0:40:30", "throughput": 10148.74, "total_tokens": 31939392}
{"current_steps": 33250, "total_steps": 58920, "loss": 0.0304, "lr": 9.500780382691018e-07, "epoch": 2.821622539035981, "percentage": 56.43, "elapsed_time": "0:52:27", "remaining_time": "0:40:29", "throughput": 10148.92, "total_tokens": 31943744}
{"current_steps": 33255, "total_steps": 58920, "loss": 0.0003, "lr": 9.497821896424657e-07, "epoch": 2.8220468431771897, "percentage": 56.44, "elapsed_time": "0:52:27", "remaining_time": "0:40:29", "throughput": 10149.29, "total_tokens": 31948928}
{"current_steps": 33260, "total_steps": 58920, "loss": 0.0002, "lr": 9.494863454222614e-07, "epoch": 2.8224711473183977, "percentage": 56.45, "elapsed_time": "0:52:28", "remaining_time": "0:40:28", "throughput": 10149.68, "total_tokens": 31954112}
{"current_steps": 33265, "total_steps": 58920, "loss": 0.0172, "lr": 9.491905056344478e-07, "epoch": 2.8228954514596065, "percentage": 56.46, "elapsed_time": "0:52:28", "remaining_time": "0:40:28", "throughput": 10150.15, "total_tokens": 31959680}
{"current_steps": 33270, "total_steps": 58920, "loss": 0.038, "lr": 9.488946703049839e-07, "epoch": 2.8233197556008145, "percentage": 56.47, "elapsed_time": "0:52:29", "remaining_time": "0:40:27", "throughput": 10150.57, "total_tokens": 31964992}
{"current_steps": 33275, "total_steps": 58920, "loss": 0.0001, "lr": 9.48598839459828e-07, "epoch": 2.823744059742023, "percentage": 56.47, "elapsed_time": "0:52:29", "remaining_time": "0:40:27", "throughput": 10150.81, "total_tokens": 31969600}
{"current_steps": 33280, "total_steps": 58920, "loss": 0.0001, "lr": 9.483030131249387e-07, "epoch": 2.8241683638832313, "percentage": 56.48, "elapsed_time": "0:52:29", "remaining_time": "0:40:26", "throughput": 10151.13, "total_tokens": 31974464}
{"current_steps": 33285, "total_steps": 58920, "loss": 0.0273, "lr": 9.480071913262731e-07, "epoch": 2.8245926680244398, "percentage": 56.49, "elapsed_time": "0:52:30", "remaining_time": "0:40:26", "throughput": 10151.35, "total_tokens": 31979008}
{"current_steps": 33290, "total_steps": 58920, "loss": 0.0001, "lr": 9.47711374089789e-07, "epoch": 2.825016972165648, "percentage": 56.5, "elapsed_time": "0:52:30", "remaining_time": "0:40:25", "throughput": 10151.65, "total_tokens": 31983872}
{"current_steps": 33295, "total_steps": 58920, "loss": 0.0178, "lr": 9.474155614414429e-07, "epoch": 2.8254412763068566, "percentage": 56.51, "elapsed_time": "0:52:30", "remaining_time": "0:40:25", "throughput": 10152.01, "total_tokens": 31988928}
{"current_steps": 33300, "total_steps": 58920, "loss": 0.02, "lr": 9.471197534071911e-07, "epoch": 2.825865580448065, "percentage": 56.52, "elapsed_time": "0:52:31", "remaining_time": "0:40:24", "throughput": 10152.26, "total_tokens": 31993600}
{"current_steps": 33305, "total_steps": 58920, "loss": 0.0001, "lr": 9.468239500129906e-07, "epoch": 2.8262898845892734, "percentage": 56.53, "elapsed_time": "0:52:31", "remaining_time": "0:40:24", "throughput": 10152.53, "total_tokens": 31998272}
{"current_steps": 33310, "total_steps": 58920, "loss": 0.0374, "lr": 9.46528151284796e-07, "epoch": 2.826714188730482, "percentage": 56.53, "elapsed_time": "0:52:32", "remaining_time": "0:40:23", "throughput": 10152.81, "total_tokens": 32003008}
{"current_steps": 33315, "total_steps": 58920, "loss": 0.0001, "lr": 9.462323572485634e-07, "epoch": 2.8271384928716903, "percentage": 56.54, "elapsed_time": "0:52:32", "remaining_time": "0:40:22", "throughput": 10153.03, "total_tokens": 32007552}
{"current_steps": 33320, "total_steps": 58920, "loss": 0.0003, "lr": 9.45936567930247e-07, "epoch": 2.8275627970128987, "percentage": 56.55, "elapsed_time": "0:52:32", "remaining_time": "0:40:22", "throughput": 10153.27, "total_tokens": 32012160}
{"current_steps": 33325, "total_steps": 58920, "loss": 0.0427, "lr": 9.456407833558018e-07, "epoch": 2.827987101154107, "percentage": 56.56, "elapsed_time": "0:52:33", "remaining_time": "0:40:21", "throughput": 10153.61, "total_tokens": 32017152}
{"current_steps": 33330, "total_steps": 58920, "loss": 0.0326, "lr": 9.453450035511819e-07, "epoch": 2.8284114052953155, "percentage": 56.57, "elapsed_time": "0:52:33", "remaining_time": "0:40:21", "throughput": 10153.89, "total_tokens": 32021824}
{"current_steps": 33335, "total_steps": 58920, "loss": 0.0003, "lr": 9.4504922854234e-07, "epoch": 2.828835709436524, "percentage": 56.58, "elapsed_time": "0:52:34", "remaining_time": "0:40:20", "throughput": 10154.27, "total_tokens": 32027008}
{"current_steps": 33340, "total_steps": 58920, "loss": 0.0002, "lr": 9.447534583552304e-07, "epoch": 2.8292600135777324, "percentage": 56.59, "elapsed_time": "0:52:34", "remaining_time": "0:40:20", "throughput": 10154.54, "total_tokens": 32031680}
{"current_steps": 33345, "total_steps": 58920, "loss": 0.0001, "lr": 9.444576930158049e-07, "epoch": 2.829684317718941, "percentage": 56.59, "elapsed_time": "0:52:34", "remaining_time": "0:40:19", "throughput": 10154.9, "total_tokens": 32036736}
{"current_steps": 33350, "total_steps": 58920, "loss": 0.0001, "lr": 9.441619325500168e-07, "epoch": 2.830108621860149, "percentage": 56.6, "elapsed_time": "0:52:35", "remaining_time": "0:40:19", "throughput": 10155.11, "total_tokens": 32041216}
{"current_steps": 33355, "total_steps": 58920, "loss": 0.0001, "lr": 9.43866176983817e-07, "epoch": 2.8305329260013576, "percentage": 56.61, "elapsed_time": "0:52:35", "remaining_time": "0:40:18", "throughput": 10155.48, "total_tokens": 32046400}
{"current_steps": 33360, "total_steps": 58920, "loss": 0.0284, "lr": 9.435704263431578e-07, "epoch": 2.830957230142566, "percentage": 56.62, "elapsed_time": "0:52:35", "remaining_time": "0:40:18", "throughput": 10155.77, "total_tokens": 32051200}
{"current_steps": 33365, "total_steps": 58920, "loss": 0.0191, "lr": 9.432746806539897e-07, "epoch": 2.8313815342837745, "percentage": 56.63, "elapsed_time": "0:52:36", "remaining_time": "0:40:17", "throughput": 10156.41, "total_tokens": 32057408}
{"current_steps": 33370, "total_steps": 58920, "loss": 0.0799, "lr": 9.429789399422639e-07, "epoch": 2.831805838424983, "percentage": 56.64, "elapsed_time": "0:52:36", "remaining_time": "0:40:16", "throughput": 10156.74, "total_tokens": 32062336}
{"current_steps": 33375, "total_steps": 58920, "loss": 0.0015, "lr": 9.426832042339303e-07, "epoch": 2.8322301425661913, "percentage": 56.64, "elapsed_time": "0:52:37", "remaining_time": "0:40:16", "throughput": 10157.11, "total_tokens": 32067456}
{"current_steps": 33380, "total_steps": 58920, "loss": 0.0001, "lr": 9.423874735549382e-07, "epoch": 2.8326544467073997, "percentage": 56.65, "elapsed_time": "0:52:37", "remaining_time": "0:40:15", "throughput": 10157.34, "total_tokens": 32072000}
{"current_steps": 33385, "total_steps": 58920, "loss": 0.0001, "lr": 9.420917479312374e-07, "epoch": 2.833078750848608, "percentage": 56.66, "elapsed_time": "0:52:37", "remaining_time": "0:40:15", "throughput": 10157.74, "total_tokens": 32077248}
{"current_steps": 33390, "total_steps": 58920, "loss": 0.0013, "lr": 9.417960273887766e-07, "epoch": 2.8335030549898166, "percentage": 56.67, "elapsed_time": "0:52:38", "remaining_time": "0:40:14", "throughput": 10157.94, "total_tokens": 32081664}
{"current_steps": 33395, "total_steps": 58920, "loss": 0.0273, "lr": 9.415003119535046e-07, "epoch": 2.833927359131025, "percentage": 56.68, "elapsed_time": "0:52:38", "remaining_time": "0:40:14", "throughput": 10158.33, "total_tokens": 32086848}
{"current_steps": 33400, "total_steps": 58920, "loss": 0.0003, "lr": 9.412046016513686e-07, "epoch": 2.8343516632722334, "percentage": 56.69, "elapsed_time": "0:52:39", "remaining_time": "0:40:13", "throughput": 10158.54, "total_tokens": 32091328}
{"current_steps": 33405, "total_steps": 58920, "loss": 0.0001, "lr": 9.409088965083169e-07, "epoch": 2.834775967413442, "percentage": 56.7, "elapsed_time": "0:52:39", "remaining_time": "0:40:13", "throughput": 10157.92, "total_tokens": 32095808}
{"current_steps": 33410, "total_steps": 58920, "loss": 0.0002, "lr": 9.406131965502958e-07, "epoch": 2.8352002715546503, "percentage": 56.7, "elapsed_time": "0:52:40", "remaining_time": "0:40:12", "throughput": 10158.18, "total_tokens": 32100544}
{"current_steps": 33415, "total_steps": 58920, "loss": 0.017, "lr": 9.403175018032528e-07, "epoch": 2.8356245756958587, "percentage": 56.71, "elapsed_time": "0:52:40", "remaining_time": "0:40:12", "throughput": 10158.45, "total_tokens": 32105280}
{"current_steps": 33420, "total_steps": 58920, "loss": 0.0001, "lr": 9.400218122931331e-07, "epoch": 2.836048879837067, "percentage": 56.72, "elapsed_time": "0:52:40", "remaining_time": "0:40:11", "throughput": 10158.71, "total_tokens": 32109952}
{"current_steps": 33425, "total_steps": 58920, "loss": 0.0238, "lr": 9.397261280458828e-07, "epoch": 2.8364731839782755, "percentage": 56.73, "elapsed_time": "0:52:41", "remaining_time": "0:40:11", "throughput": 10158.98, "total_tokens": 32114688}
{"current_steps": 33430, "total_steps": 58920, "loss": 0.0001, "lr": 9.394304490874476e-07, "epoch": 2.836897488119484, "percentage": 56.74, "elapsed_time": "0:52:41", "remaining_time": "0:40:10", "throughput": 10159.19, "total_tokens": 32119168}
{"current_steps": 33435, "total_steps": 58920, "loss": 0.0456, "lr": 9.391347754437711e-07, "epoch": 2.8373217922606924, "percentage": 56.75, "elapsed_time": "0:52:41", "remaining_time": "0:40:10", "throughput": 10159.53, "total_tokens": 32124160}
{"current_steps": 33440, "total_steps": 58920, "loss": 0.0932, "lr": 9.388391071407991e-07, "epoch": 2.837746096401901, "percentage": 56.75, "elapsed_time": "0:52:42", "remaining_time": "0:40:09", "throughput": 10159.87, "total_tokens": 32129152}
{"current_steps": 33445, "total_steps": 58920, "loss": 0.0005, "lr": 9.38543444204474e-07, "epoch": 2.838170400543109, "percentage": 56.76, "elapsed_time": "0:52:42", "remaining_time": "0:40:09", "throughput": 10160.12, "total_tokens": 32133824}
{"current_steps": 33450, "total_steps": 58920, "loss": 0.0178, "lr": 9.382477866607399e-07, "epoch": 2.8385947046843176, "percentage": 56.77, "elapsed_time": "0:52:43", "remaining_time": "0:40:08", "throughput": 10160.57, "total_tokens": 32139328}
{"current_steps": 33455, "total_steps": 58920, "loss": 0.0009, "lr": 9.379521345355399e-07, "epoch": 2.839019008825526, "percentage": 56.78, "elapsed_time": "0:52:43", "remaining_time": "0:40:07", "throughput": 10160.88, "total_tokens": 32144192}
{"current_steps": 33460, "total_steps": 58920, "loss": 0.0002, "lr": 9.376564878548157e-07, "epoch": 2.8394433129667345, "percentage": 56.79, "elapsed_time": "0:52:43", "remaining_time": "0:40:07", "throughput": 10161.16, "total_tokens": 32148992}
{"current_steps": 33465, "total_steps": 58920, "loss": 0.0006, "lr": 9.3736084664451e-07, "epoch": 2.839867617107943, "percentage": 56.8, "elapsed_time": "0:52:44", "remaining_time": "0:40:06", "throughput": 10161.46, "total_tokens": 32153792}
{"current_steps": 33470, "total_steps": 58920, "loss": 0.0002, "lr": 9.370652109305633e-07, "epoch": 2.8402919212491513, "percentage": 56.81, "elapsed_time": "0:52:44", "remaining_time": "0:40:06", "throughput": 10161.66, "total_tokens": 32158208}
{"current_steps": 33475, "total_steps": 58920, "loss": 0.0002, "lr": 9.367695807389174e-07, "epoch": 2.8407162253903597, "percentage": 56.81, "elapsed_time": "0:52:45", "remaining_time": "0:40:05", "throughput": 10161.97, "total_tokens": 32163072}
{"current_steps": 33480, "total_steps": 58920, "loss": 0.0001, "lr": 9.364739560955126e-07, "epoch": 2.841140529531568, "percentage": 56.82, "elapsed_time": "0:52:45", "remaining_time": "0:40:05", "throughput": 10162.36, "total_tokens": 32168320}
{"current_steps": 33485, "total_steps": 58920, "loss": 0.0029, "lr": 9.361783370262886e-07, "epoch": 2.8415648336727766, "percentage": 56.83, "elapsed_time": "0:52:45", "remaining_time": "0:40:04", "throughput": 10162.69, "total_tokens": 32173312}
{"current_steps": 33490, "total_steps": 58920, "loss": 0.0073, "lr": 9.35882723557185e-07, "epoch": 2.841989137813985, "percentage": 56.84, "elapsed_time": "0:52:46", "remaining_time": "0:40:04", "throughput": 10162.98, "total_tokens": 32178176}
{"current_steps": 33495, "total_steps": 58920, "loss": 0.0001, "lr": 9.355871157141414e-07, "epoch": 2.8424134419551934, "percentage": 56.85, "elapsed_time": "0:52:46", "remaining_time": "0:40:03", "throughput": 10163.17, "total_tokens": 32182592}
{"current_steps": 33500, "total_steps": 58920, "loss": 0.0001, "lr": 9.352915135230958e-07, "epoch": 2.842837746096402, "percentage": 56.86, "elapsed_time": "0:52:46", "remaining_time": "0:40:03", "throughput": 10163.37, "total_tokens": 32187008}
{"current_steps": 33505, "total_steps": 58920, "loss": 0.0049, "lr": 9.349959170099857e-07, "epoch": 2.8432620502376103, "percentage": 56.87, "elapsed_time": "0:52:47", "remaining_time": "0:40:02", "throughput": 10163.66, "total_tokens": 32191872}
{"current_steps": 33510, "total_steps": 58920, "loss": 0.0, "lr": 9.347003262007496e-07, "epoch": 2.8436863543788187, "percentage": 56.87, "elapsed_time": "0:52:47", "remaining_time": "0:40:02", "throughput": 10163.94, "total_tokens": 32196608}
{"current_steps": 33515, "total_steps": 58920, "loss": 0.0749, "lr": 9.344047411213238e-07, "epoch": 2.844110658520027, "percentage": 56.88, "elapsed_time": "0:52:48", "remaining_time": "0:40:01", "throughput": 10164.14, "total_tokens": 32201024}
{"current_steps": 33520, "total_steps": 58920, "loss": 0.0028, "lr": 9.341091617976455e-07, "epoch": 2.8445349626612355, "percentage": 56.89, "elapsed_time": "0:52:48", "remaining_time": "0:40:00", "throughput": 10164.38, "total_tokens": 32205632}
{"current_steps": 33525, "total_steps": 58920, "loss": 0.0155, "lr": 9.3381358825565e-07, "epoch": 2.844959266802444, "percentage": 56.9, "elapsed_time": "0:52:48", "remaining_time": "0:40:00", "throughput": 10164.77, "total_tokens": 32210816}
{"current_steps": 33530, "total_steps": 58920, "loss": 0.0001, "lr": 9.335180205212736e-07, "epoch": 2.8453835709436524, "percentage": 56.91, "elapsed_time": "0:52:49", "remaining_time": "0:39:59", "throughput": 10165.06, "total_tokens": 32215680}
{"current_steps": 33535, "total_steps": 58920, "loss": 0.0224, "lr": 9.332224586204503e-07, "epoch": 2.8458078750848608, "percentage": 56.92, "elapsed_time": "0:52:49", "remaining_time": "0:39:59", "throughput": 10165.24, "total_tokens": 32220032}
{"current_steps": 33540, "total_steps": 58920, "loss": 0.0219, "lr": 9.329269025791155e-07, "epoch": 2.846232179226069, "percentage": 56.92, "elapsed_time": "0:52:50", "remaining_time": "0:39:58", "throughput": 10165.47, "total_tokens": 32224576}
{"current_steps": 33545, "total_steps": 58920, "loss": 0.0027, "lr": 9.326313524232032e-07, "epoch": 2.8466564833672776, "percentage": 56.93, "elapsed_time": "0:52:50", "remaining_time": "0:39:58", "throughput": 10165.68, "total_tokens": 32229120}
{"current_steps": 33550, "total_steps": 58920, "loss": 0.0001, "lr": 9.323358081786458e-07, "epoch": 2.847080787508486, "percentage": 56.94, "elapsed_time": "0:52:50", "remaining_time": "0:39:57", "throughput": 10165.93, "total_tokens": 32233792}
{"current_steps": 33555, "total_steps": 58920, "loss": 0.0002, "lr": 9.320402698713775e-07, "epoch": 2.8475050916496945, "percentage": 56.95, "elapsed_time": "0:52:51", "remaining_time": "0:39:57", "throughput": 10166.21, "total_tokens": 32238592}
{"current_steps": 33560, "total_steps": 58920, "loss": 0.0001, "lr": 9.317447375273297e-07, "epoch": 2.847929395790903, "percentage": 56.96, "elapsed_time": "0:52:51", "remaining_time": "0:39:56", "throughput": 10166.7, "total_tokens": 32244224}
{"current_steps": 33565, "total_steps": 58920, "loss": 0.0001, "lr": 9.314492111724351e-07, "epoch": 2.8483536999321113, "percentage": 56.97, "elapsed_time": "0:52:51", "remaining_time": "0:39:56", "throughput": 10166.9, "total_tokens": 32248704}
{"current_steps": 33570, "total_steps": 58920, "loss": 0.0001, "lr": 9.311536908326244e-07, "epoch": 2.8487780040733197, "percentage": 56.98, "elapsed_time": "0:52:52", "remaining_time": "0:39:55", "throughput": 10167.24, "total_tokens": 32253696}
{"current_steps": 33575, "total_steps": 58920, "loss": 0.0001, "lr": 9.308581765338289e-07, "epoch": 2.849202308214528, "percentage": 56.98, "elapsed_time": "0:52:52", "remaining_time": "0:39:54", "throughput": 10167.55, "total_tokens": 32258560}
{"current_steps": 33580, "total_steps": 58920, "loss": 0.0525, "lr": 9.30562668301979e-07, "epoch": 2.8496266123557366, "percentage": 56.99, "elapsed_time": "0:52:53", "remaining_time": "0:39:54", "throughput": 10168.0, "total_tokens": 32264064}
{"current_steps": 33585, "total_steps": 58920, "loss": 0.0001, "lr": 9.302671661630038e-07, "epoch": 2.850050916496945, "percentage": 57.0, "elapsed_time": "0:52:53", "remaining_time": "0:39:53", "throughput": 10168.31, "total_tokens": 32268928}
{"current_steps": 33590, "total_steps": 58920, "loss": 0.0001, "lr": 9.299716701428335e-07, "epoch": 2.8504752206381534, "percentage": 57.01, "elapsed_time": "0:52:53", "remaining_time": "0:39:53", "throughput": 10168.65, "total_tokens": 32273920}
{"current_steps": 33595, "total_steps": 58920, "loss": 0.0458, "lr": 9.296761802673958e-07, "epoch": 2.850899524779362, "percentage": 57.02, "elapsed_time": "0:52:54", "remaining_time": "0:39:52", "throughput": 10168.82, "total_tokens": 32278272}
{"current_steps": 33600, "total_steps": 58920, "loss": 0.0305, "lr": 9.293806965626196e-07, "epoch": 2.8513238289205702, "percentage": 57.03, "elapsed_time": "0:52:54", "remaining_time": "0:39:52", "throughput": 10169.33, "total_tokens": 32284096}
{"current_steps": 33605, "total_steps": 58920, "loss": 0.0, "lr": 9.290852190544322e-07, "epoch": 2.8517481330617787, "percentage": 57.03, "elapsed_time": "0:52:55", "remaining_time": "0:39:51", "throughput": 10169.56, "total_tokens": 32288704}
{"current_steps": 33610, "total_steps": 58920, "loss": 0.0159, "lr": 9.287897477687611e-07, "epoch": 2.852172437202987, "percentage": 57.04, "elapsed_time": "0:52:55", "remaining_time": "0:39:51", "throughput": 10169.8, "total_tokens": 32293312}
{"current_steps": 33615, "total_steps": 58920, "loss": 0.0287, "lr": 9.284942827315322e-07, "epoch": 2.8525967413441955, "percentage": 57.05, "elapsed_time": "0:52:55", "remaining_time": "0:39:50", "throughput": 10170.09, "total_tokens": 32298112}
{"current_steps": 33620, "total_steps": 58920, "loss": 0.0003, "lr": 9.281988239686722e-07, "epoch": 2.853021045485404, "percentage": 57.06, "elapsed_time": "0:52:56", "remaining_time": "0:39:50", "throughput": 10170.36, "total_tokens": 32302848}
{"current_steps": 33625, "total_steps": 58920, "loss": 0.0205, "lr": 9.27903371506106e-07, "epoch": 2.8534453496266123, "percentage": 57.07, "elapsed_time": "0:52:56", "remaining_time": "0:39:49", "throughput": 10170.66, "total_tokens": 32307712}
{"current_steps": 33630, "total_steps": 58920, "loss": 0.0001, "lr": 9.276079253697585e-07, "epoch": 2.8538696537678208, "percentage": 57.08, "elapsed_time": "0:52:56", "remaining_time": "0:39:49", "throughput": 10170.83, "total_tokens": 32312064}
{"current_steps": 33635, "total_steps": 58920, "loss": 0.0187, "lr": 9.273124855855543e-07, "epoch": 2.854293957909029, "percentage": 57.09, "elapsed_time": "0:52:57", "remaining_time": "0:39:48", "throughput": 10170.99, "total_tokens": 32316416}
{"current_steps": 33640, "total_steps": 58920, "loss": 0.0001, "lr": 9.270170521794168e-07, "epoch": 2.8547182620502376, "percentage": 57.09, "elapsed_time": "0:52:57", "remaining_time": "0:39:47", "throughput": 10171.33, "total_tokens": 32321408}
{"current_steps": 33645, "total_steps": 58920, "loss": 0.0001, "lr": 9.2672162517727e-07, "epoch": 2.855142566191446, "percentage": 57.1, "elapsed_time": "0:52:58", "remaining_time": "0:39:47", "throughput": 10171.66, "total_tokens": 32326400}
{"current_steps": 33650, "total_steps": 58920, "loss": 0.0004, "lr": 9.264262046050354e-07, "epoch": 2.8555668703326544, "percentage": 57.11, "elapsed_time": "0:52:58", "remaining_time": "0:39:46", "throughput": 10172.01, "total_tokens": 32331456}
{"current_steps": 33655, "total_steps": 58920, "loss": 0.0217, "lr": 9.261307904886363e-07, "epoch": 2.855991174473863, "percentage": 57.12, "elapsed_time": "0:52:58", "remaining_time": "0:39:46", "throughput": 10172.28, "total_tokens": 32336256}
{"current_steps": 33660, "total_steps": 58920, "loss": 0.0009, "lr": 9.258353828539931e-07, "epoch": 2.8564154786150713, "percentage": 57.13, "elapsed_time": "0:52:59", "remaining_time": "0:39:45", "throughput": 10172.53, "total_tokens": 32340928}
{"current_steps": 33665, "total_steps": 58920, "loss": 0.0664, "lr": 9.255399817270275e-07, "epoch": 2.8568397827562797, "percentage": 57.14, "elapsed_time": "0:52:59", "remaining_time": "0:39:45", "throughput": 10172.85, "total_tokens": 32345920}
{"current_steps": 33670, "total_steps": 58920, "loss": 0.0308, "lr": 9.252445871336599e-07, "epoch": 2.857264086897488, "percentage": 57.15, "elapsed_time": "0:53:00", "remaining_time": "0:39:44", "throughput": 10173.08, "total_tokens": 32350464}
{"current_steps": 33675, "total_steps": 58920, "loss": 0.0192, "lr": 9.249491990998095e-07, "epoch": 2.8576883910386965, "percentage": 57.15, "elapsed_time": "0:53:00", "remaining_time": "0:39:44", "throughput": 10173.44, "total_tokens": 32355520}
{"current_steps": 33680, "total_steps": 58920, "loss": 0.0011, "lr": 9.246538176513963e-07, "epoch": 2.858112695179905, "percentage": 57.16, "elapsed_time": "0:53:00", "remaining_time": "0:39:43", "throughput": 10173.66, "total_tokens": 32360064}
{"current_steps": 33685, "total_steps": 58920, "loss": 0.0001, "lr": 9.243584428143381e-07, "epoch": 2.8585369993211134, "percentage": 57.17, "elapsed_time": "0:53:01", "remaining_time": "0:39:43", "throughput": 10173.98, "total_tokens": 32364992}
{"current_steps": 33690, "total_steps": 58920, "loss": 0.0423, "lr": 9.240630746145537e-07, "epoch": 2.858961303462322, "percentage": 57.18, "elapsed_time": "0:53:01", "remaining_time": "0:39:42", "throughput": 10174.29, "total_tokens": 32369856}
{"current_steps": 33695, "total_steps": 58920, "loss": 0.0326, "lr": 9.237677130779604e-07, "epoch": 2.85938560760353, "percentage": 57.19, "elapsed_time": "0:53:01", "remaining_time": "0:39:42", "throughput": 10174.51, "total_tokens": 32374400}
{"current_steps": 33700, "total_steps": 58920, "loss": 0.0082, "lr": 9.234723582304748e-07, "epoch": 2.8598099117447386, "percentage": 57.2, "elapsed_time": "0:53:02", "remaining_time": "0:39:41", "throughput": 10174.7, "total_tokens": 32378816}
{"current_steps": 33705, "total_steps": 58920, "loss": 0.0212, "lr": 9.231770100980139e-07, "epoch": 2.860234215885947, "percentage": 57.2, "elapsed_time": "0:53:02", "remaining_time": "0:39:40", "throughput": 10174.91, "total_tokens": 32383296}
{"current_steps": 33710, "total_steps": 58920, "loss": 0.0262, "lr": 9.228816687064926e-07, "epoch": 2.8606585200271555, "percentage": 57.21, "elapsed_time": "0:53:03", "remaining_time": "0:39:40", "throughput": 10175.18, "total_tokens": 32388032}
{"current_steps": 33715, "total_steps": 58920, "loss": 0.0003, "lr": 9.225863340818267e-07, "epoch": 2.861082824168364, "percentage": 57.22, "elapsed_time": "0:53:03", "remaining_time": "0:39:39", "throughput": 10175.47, "total_tokens": 32392896}
{"current_steps": 33720, "total_steps": 58920, "loss": 0.0, "lr": 9.222910062499301e-07, "epoch": 2.8615071283095723, "percentage": 57.23, "elapsed_time": "0:53:03", "remaining_time": "0:39:39", "throughput": 10175.78, "total_tokens": 32397760}
{"current_steps": 33725, "total_steps": 58920, "loss": 0.0281, "lr": 9.219956852367175e-07, "epoch": 2.8619314324507807, "percentage": 57.24, "elapsed_time": "0:53:04", "remaining_time": "0:39:38", "throughput": 10176.1, "total_tokens": 32402688}
{"current_steps": 33730, "total_steps": 58920, "loss": 0.0001, "lr": 9.217003710681015e-07, "epoch": 2.862355736591989, "percentage": 57.25, "elapsed_time": "0:53:04", "remaining_time": "0:39:38", "throughput": 10176.31, "total_tokens": 32407168}
{"current_steps": 33735, "total_steps": 58920, "loss": 0.0, "lr": 9.214050637699958e-07, "epoch": 2.8627800407331976, "percentage": 57.26, "elapsed_time": "0:53:04", "remaining_time": "0:39:37", "throughput": 10176.67, "total_tokens": 32412288}
{"current_steps": 33740, "total_steps": 58920, "loss": 0.0049, "lr": 9.211097633683113e-07, "epoch": 2.863204344874406, "percentage": 57.26, "elapsed_time": "0:53:05", "remaining_time": "0:39:37", "throughput": 10177.05, "total_tokens": 32417536}
{"current_steps": 33745, "total_steps": 58920, "loss": 0.0515, "lr": 9.20814469888961e-07, "epoch": 2.8636286490156144, "percentage": 57.27, "elapsed_time": "0:53:05", "remaining_time": "0:39:36", "throughput": 10177.23, "total_tokens": 32421952}
{"current_steps": 33750, "total_steps": 58920, "loss": 0.0001, "lr": 9.205191833578546e-07, "epoch": 2.864052953156823, "percentage": 57.28, "elapsed_time": "0:53:06", "remaining_time": "0:39:36", "throughput": 10177.61, "total_tokens": 32427136}
{"current_steps": 33755, "total_steps": 58920, "loss": 0.0497, "lr": 9.202239038009028e-07, "epoch": 2.8644772572980313, "percentage": 57.29, "elapsed_time": "0:53:06", "remaining_time": "0:39:35", "throughput": 10178.07, "total_tokens": 32432704}
{"current_steps": 33760, "total_steps": 58920, "loss": 0.0001, "lr": 9.199286312440159e-07, "epoch": 2.8649015614392397, "percentage": 57.3, "elapsed_time": "0:53:06", "remaining_time": "0:39:35", "throughput": 10178.3, "total_tokens": 32437312}
{"current_steps": 33765, "total_steps": 58920, "loss": 0.0411, "lr": 9.196333657131019e-07, "epoch": 2.865325865580448, "percentage": 57.31, "elapsed_time": "0:53:07", "remaining_time": "0:39:34", "throughput": 10178.44, "total_tokens": 32441536}
{"current_steps": 33770, "total_steps": 58920, "loss": 0.0002, "lr": 9.193381072340704e-07, "epoch": 2.8657501697216565, "percentage": 57.32, "elapsed_time": "0:53:07", "remaining_time": "0:39:33", "throughput": 10178.58, "total_tokens": 32445760}
{"current_steps": 33775, "total_steps": 58920, "loss": 0.0, "lr": 9.190428558328283e-07, "epoch": 2.866174473862865, "percentage": 57.32, "elapsed_time": "0:53:08", "remaining_time": "0:39:33", "throughput": 10178.88, "total_tokens": 32450560}
{"current_steps": 33780, "total_steps": 58920, "loss": 0.0174, "lr": 9.187476115352839e-07, "epoch": 2.8665987780040734, "percentage": 57.33, "elapsed_time": "0:53:08", "remaining_time": "0:39:32", "throughput": 10179.18, "total_tokens": 32455424}
{"current_steps": 33785, "total_steps": 58920, "loss": 0.0065, "lr": 9.184523743673427e-07, "epoch": 2.867023082145282, "percentage": 57.34, "elapsed_time": "0:53:08", "remaining_time": "0:39:32", "throughput": 10179.48, "total_tokens": 32460288}
{"current_steps": 33790, "total_steps": 58920, "loss": 0.0002, "lr": 9.181571443549114e-07, "epoch": 2.86744738628649, "percentage": 57.35, "elapsed_time": "0:53:09", "remaining_time": "0:39:31", "throughput": 10179.72, "total_tokens": 32464896}
{"current_steps": 33795, "total_steps": 58920, "loss": 0.0381, "lr": 9.178619215238955e-07, "epoch": 2.8678716904276986, "percentage": 57.36, "elapsed_time": "0:53:09", "remaining_time": "0:39:31", "throughput": 10179.93, "total_tokens": 32469440}
{"current_steps": 33800, "total_steps": 58920, "loss": 0.0, "lr": 9.175667059001989e-07, "epoch": 2.868295994568907, "percentage": 57.37, "elapsed_time": "0:53:09", "remaining_time": "0:39:30", "throughput": 10180.16, "total_tokens": 32474048}
{"current_steps": 33805, "total_steps": 58920, "loss": 0.0001, "lr": 9.172714975097267e-07, "epoch": 2.8687202987101155, "percentage": 57.37, "elapsed_time": "0:53:10", "remaining_time": "0:39:30", "throughput": 10180.63, "total_tokens": 32479680}
{"current_steps": 33810, "total_steps": 58920, "loss": 0.0, "lr": 9.169762963783814e-07, "epoch": 2.869144602851324, "percentage": 57.38, "elapsed_time": "0:53:10", "remaining_time": "0:39:29", "throughput": 10180.88, "total_tokens": 32484288}
{"current_steps": 33815, "total_steps": 58920, "loss": 0.0001, "lr": 9.166811025320666e-07, "epoch": 2.8695689069925323, "percentage": 57.39, "elapsed_time": "0:53:11", "remaining_time": "0:39:29", "throughput": 10181.16, "total_tokens": 32489088}
{"current_steps": 33820, "total_steps": 58920, "loss": 0.0466, "lr": 9.163859159966842e-07, "epoch": 2.8699932111337407, "percentage": 57.4, "elapsed_time": "0:53:11", "remaining_time": "0:39:28", "throughput": 10181.36, "total_tokens": 32493568}
{"current_steps": 33825, "total_steps": 58920, "loss": 0.0389, "lr": 9.16090736798136e-07, "epoch": 2.870417515274949, "percentage": 57.41, "elapsed_time": "0:53:11", "remaining_time": "0:39:28", "throughput": 10181.76, "total_tokens": 32498880}
{"current_steps": 33830, "total_steps": 58920, "loss": 0.028, "lr": 9.157955649623227e-07, "epoch": 2.8708418194161576, "percentage": 57.42, "elapsed_time": "0:53:12", "remaining_time": "0:39:27", "throughput": 10182.07, "total_tokens": 32503808}
{"current_steps": 33835, "total_steps": 58920, "loss": 0.0255, "lr": 9.155004005151441e-07, "epoch": 2.871266123557366, "percentage": 57.43, "elapsed_time": "0:53:12", "remaining_time": "0:39:27", "throughput": 10182.35, "total_tokens": 32508608}
{"current_steps": 33840, "total_steps": 58920, "loss": 0.0627, "lr": 9.152052434825006e-07, "epoch": 2.8716904276985744, "percentage": 57.43, "elapsed_time": "0:53:13", "remaining_time": "0:39:26", "throughput": 10182.68, "total_tokens": 32513600}
{"current_steps": 33845, "total_steps": 58920, "loss": 0.0011, "lr": 9.149100938902908e-07, "epoch": 2.872114731839783, "percentage": 57.44, "elapsed_time": "0:53:13", "remaining_time": "0:39:25", "throughput": 10182.93, "total_tokens": 32518272}
{"current_steps": 33850, "total_steps": 58920, "loss": 0.0318, "lr": 9.146149517644131e-07, "epoch": 2.8725390359809913, "percentage": 57.45, "elapsed_time": "0:53:13", "remaining_time": "0:39:25", "throughput": 10183.17, "total_tokens": 32522880}
{"current_steps": 33855, "total_steps": 58920, "loss": 0.0441, "lr": 9.143198171307648e-07, "epoch": 2.8729633401221997, "percentage": 57.46, "elapsed_time": "0:53:14", "remaining_time": "0:39:24", "throughput": 10183.38, "total_tokens": 32527424}
{"current_steps": 33860, "total_steps": 58920, "loss": 0.0001, "lr": 9.140246900152437e-07, "epoch": 2.873387644263408, "percentage": 57.47, "elapsed_time": "0:53:14", "remaining_time": "0:39:24", "throughput": 10183.86, "total_tokens": 32533056}
{"current_steps": 33865, "total_steps": 58920, "loss": 0.0258, "lr": 9.13729570443745e-07, "epoch": 2.8738119484046165, "percentage": 57.48, "elapsed_time": "0:53:14", "remaining_time": "0:39:23", "throughput": 10184.1, "total_tokens": 32537664}
{"current_steps": 33870, "total_steps": 58920, "loss": 0.011, "lr": 9.134344584421656e-07, "epoch": 2.874236252545825, "percentage": 57.48, "elapsed_time": "0:53:15", "remaining_time": "0:39:23", "throughput": 10184.39, "total_tokens": 32542464}
{"current_steps": 33875, "total_steps": 58920, "loss": 0.0005, "lr": 9.131393540363998e-07, "epoch": 2.8746605566870334, "percentage": 57.49, "elapsed_time": "0:53:15", "remaining_time": "0:39:22", "throughput": 10184.64, "total_tokens": 32547136}
{"current_steps": 33880, "total_steps": 58920, "loss": 0.0001, "lr": 9.128442572523417e-07, "epoch": 2.8750848608282418, "percentage": 57.5, "elapsed_time": "0:53:16", "remaining_time": "0:39:22", "throughput": 10184.9, "total_tokens": 32551872}
{"current_steps": 33885, "total_steps": 58920, "loss": 0.0, "lr": 9.125491681158859e-07, "epoch": 2.87550916496945, "percentage": 57.51, "elapsed_time": "0:53:16", "remaining_time": "0:39:21", "throughput": 10185.1, "total_tokens": 32556352}
{"current_steps": 33890, "total_steps": 58920, "loss": 0.0001, "lr": 9.122540866529244e-07, "epoch": 2.8759334691106586, "percentage": 57.52, "elapsed_time": "0:53:16", "remaining_time": "0:39:21", "throughput": 10185.34, "total_tokens": 32561024}
{"current_steps": 33895, "total_steps": 58920, "loss": 0.0, "lr": 9.119590128893504e-07, "epoch": 2.876357773251867, "percentage": 57.53, "elapsed_time": "0:53:17", "remaining_time": "0:39:20", "throughput": 10185.5, "total_tokens": 32565312}
{"current_steps": 33900, "total_steps": 58920, "loss": 0.0002, "lr": 9.116639468510547e-07, "epoch": 2.8767820773930755, "percentage": 57.54, "elapsed_time": "0:53:17", "remaining_time": "0:39:20", "throughput": 10185.87, "total_tokens": 32570432}
{"current_steps": 33905, "total_steps": 58920, "loss": 0.0455, "lr": 9.11368888563929e-07, "epoch": 2.877206381534284, "percentage": 57.54, "elapsed_time": "0:53:17", "remaining_time": "0:39:19", "throughput": 10186.12, "total_tokens": 32575104}
{"current_steps": 33910, "total_steps": 58920, "loss": 0.0001, "lr": 9.110738380538633e-07, "epoch": 2.8776306856754923, "percentage": 57.55, "elapsed_time": "0:53:18", "remaining_time": "0:39:18", "throughput": 10186.44, "total_tokens": 32580096}
{"current_steps": 33915, "total_steps": 58920, "loss": 0.0003, "lr": 9.107787953467472e-07, "epoch": 2.8780549898167007, "percentage": 57.56, "elapsed_time": "0:53:18", "remaining_time": "0:39:18", "throughput": 10186.67, "total_tokens": 32584704}
{"current_steps": 33920, "total_steps": 58920, "loss": 0.0001, "lr": 9.104837604684699e-07, "epoch": 2.878479293957909, "percentage": 57.57, "elapsed_time": "0:53:19", "remaining_time": "0:39:17", "throughput": 10187.04, "total_tokens": 32589888}
{"current_steps": 33925, "total_steps": 58920, "loss": 0.0005, "lr": 9.10188733444919e-07, "epoch": 2.8789035980991176, "percentage": 57.58, "elapsed_time": "0:53:19", "remaining_time": "0:39:17", "throughput": 10187.34, "total_tokens": 32594752}
{"current_steps": 33930, "total_steps": 58920, "loss": 0.0294, "lr": 9.098937143019829e-07, "epoch": 2.879327902240326, "percentage": 57.59, "elapsed_time": "0:53:19", "remaining_time": "0:39:16", "throughput": 10187.53, "total_tokens": 32599232}
{"current_steps": 33935, "total_steps": 58920, "loss": 0.0001, "lr": 9.095987030655476e-07, "epoch": 2.8797522063815344, "percentage": 57.6, "elapsed_time": "0:53:20", "remaining_time": "0:39:16", "throughput": 10187.85, "total_tokens": 32604160}
{"current_steps": 33940, "total_steps": 58920, "loss": 0.0001, "lr": 9.093036997615e-07, "epoch": 2.880176510522743, "percentage": 57.6, "elapsed_time": "0:53:20", "remaining_time": "0:39:15", "throughput": 10188.24, "total_tokens": 32609408}
{"current_steps": 33945, "total_steps": 58920, "loss": 0.0001, "lr": 9.090087044157251e-07, "epoch": 2.8806008146639512, "percentage": 57.61, "elapsed_time": "0:53:21", "remaining_time": "0:39:15", "throughput": 10188.73, "total_tokens": 32615104}
{"current_steps": 33950, "total_steps": 58920, "loss": 0.0001, "lr": 9.087137170541082e-07, "epoch": 2.8810251188051597, "percentage": 57.62, "elapsed_time": "0:53:21", "remaining_time": "0:39:14", "throughput": 10189.08, "total_tokens": 32620224}
{"current_steps": 33955, "total_steps": 58920, "loss": 0.037, "lr": 9.084187377025332e-07, "epoch": 2.881449422946368, "percentage": 57.63, "elapsed_time": "0:53:21", "remaining_time": "0:39:14", "throughput": 10189.5, "total_tokens": 32625536}
{"current_steps": 33960, "total_steps": 58920, "loss": 0.0, "lr": 9.081237663868827e-07, "epoch": 2.8818737270875765, "percentage": 57.64, "elapsed_time": "0:53:22", "remaining_time": "0:39:13", "throughput": 10189.64, "total_tokens": 32629760}
{"current_steps": 33965, "total_steps": 58920, "loss": 0.0, "lr": 9.078288031330402e-07, "epoch": 2.882298031228785, "percentage": 57.65, "elapsed_time": "0:53:22", "remaining_time": "0:39:13", "throughput": 10189.94, "total_tokens": 32634624}
{"current_steps": 33970, "total_steps": 58920, "loss": 0.0359, "lr": 9.075338479668873e-07, "epoch": 2.8827223353699933, "percentage": 57.65, "elapsed_time": "0:53:23", "remaining_time": "0:39:12", "throughput": 10190.13, "total_tokens": 32639104}
{"current_steps": 33975, "total_steps": 58920, "loss": 0.0001, "lr": 9.072389009143057e-07, "epoch": 2.8831466395112018, "percentage": 57.66, "elapsed_time": "0:53:23", "remaining_time": "0:39:11", "throughput": 10190.41, "total_tokens": 32643904}
{"current_steps": 33980, "total_steps": 58920, "loss": 0.0115, "lr": 9.069439620011754e-07, "epoch": 2.88357094365241, "percentage": 57.67, "elapsed_time": "0:53:23", "remaining_time": "0:39:11", "throughput": 10190.58, "total_tokens": 32648256}
{"current_steps": 33985, "total_steps": 58920, "loss": 0.0001, "lr": 9.066490312533769e-07, "epoch": 2.8839952477936186, "percentage": 57.68, "elapsed_time": "0:53:24", "remaining_time": "0:39:10", "throughput": 10190.9, "total_tokens": 32653248}
{"current_steps": 33990, "total_steps": 58920, "loss": 0.0011, "lr": 9.063541086967883e-07, "epoch": 2.884419551934827, "percentage": 57.69, "elapsed_time": "0:53:24", "remaining_time": "0:39:10", "throughput": 10191.08, "total_tokens": 32657664}
{"current_steps": 33995, "total_steps": 58920, "loss": 0.0157, "lr": 9.06059194357289e-07, "epoch": 2.8848438560760354, "percentage": 57.7, "elapsed_time": "0:53:24", "remaining_time": "0:39:09", "throughput": 10191.36, "total_tokens": 32662464}
{"current_steps": 34000, "total_steps": 58920, "loss": 0.019, "lr": 9.05764288260756e-07, "epoch": 2.885268160217244, "percentage": 57.71, "elapsed_time": "0:53:25", "remaining_time": "0:39:09", "throughput": 10191.56, "total_tokens": 32666944}
{"current_steps": 34005, "total_steps": 58920, "loss": 0.0001, "lr": 9.054693904330662e-07, "epoch": 2.8856924643584523, "percentage": 57.71, "elapsed_time": "0:53:25", "remaining_time": "0:39:08", "throughput": 10192.01, "total_tokens": 32672384}
{"current_steps": 34010, "total_steps": 58920, "loss": 0.0001, "lr": 9.051745009000968e-07, "epoch": 2.8861167684996607, "percentage": 57.72, "elapsed_time": "0:53:26", "remaining_time": "0:39:08", "throughput": 10192.46, "total_tokens": 32677888}
{"current_steps": 34015, "total_steps": 58920, "loss": 0.0, "lr": 9.048796196877219e-07, "epoch": 2.886541072640869, "percentage": 57.73, "elapsed_time": "0:53:26", "remaining_time": "0:39:07", "throughput": 10192.74, "total_tokens": 32682688}
{"current_steps": 34020, "total_steps": 58920, "loss": 0.0051, "lr": 9.045847468218174e-07, "epoch": 2.8869653767820775, "percentage": 57.74, "elapsed_time": "0:53:26", "remaining_time": "0:39:07", "throughput": 10193.18, "total_tokens": 32688192}
{"current_steps": 34025, "total_steps": 58920, "loss": 0.0298, "lr": 9.042898823282564e-07, "epoch": 2.887389680923286, "percentage": 57.75, "elapsed_time": "0:53:27", "remaining_time": "0:39:06", "throughput": 10193.41, "total_tokens": 32692800}
{"current_steps": 34030, "total_steps": 58920, "loss": 0.0001, "lr": 9.039950262329129e-07, "epoch": 2.8878139850644944, "percentage": 57.76, "elapsed_time": "0:53:27", "remaining_time": "0:39:06", "throughput": 10193.62, "total_tokens": 32697280}
{"current_steps": 34035, "total_steps": 58920, "loss": 0.0001, "lr": 9.037001785616591e-07, "epoch": 2.888238289205703, "percentage": 57.76, "elapsed_time": "0:53:28", "remaining_time": "0:39:05", "throughput": 10193.96, "total_tokens": 32702336}
{"current_steps": 34040, "total_steps": 58920, "loss": 0.0153, "lr": 9.034053393403674e-07, "epoch": 2.8886625933469112, "percentage": 57.77, "elapsed_time": "0:53:28", "remaining_time": "0:39:05", "throughput": 10194.34, "total_tokens": 32707520}
{"current_steps": 34045, "total_steps": 58920, "loss": 0.0222, "lr": 9.031105085949083e-07, "epoch": 2.8890868974881196, "percentage": 57.78, "elapsed_time": "0:53:28", "remaining_time": "0:39:04", "throughput": 10194.64, "total_tokens": 32712384}
{"current_steps": 34050, "total_steps": 58920, "loss": 0.0001, "lr": 9.028156863511518e-07, "epoch": 2.889511201629328, "percentage": 57.79, "elapsed_time": "0:53:29", "remaining_time": "0:39:03", "throughput": 10194.98, "total_tokens": 32717440}
{"current_steps": 34055, "total_steps": 58920, "loss": 0.0306, "lr": 9.025208726349682e-07, "epoch": 2.8899355057705365, "percentage": 57.8, "elapsed_time": "0:53:29", "remaining_time": "0:39:03", "throughput": 10195.09, "total_tokens": 32721536}
{"current_steps": 34060, "total_steps": 58920, "loss": 0.0001, "lr": 9.022260674722262e-07, "epoch": 2.890359809911745, "percentage": 57.81, "elapsed_time": "0:53:29", "remaining_time": "0:39:02", "throughput": 10195.29, "total_tokens": 32726080}
{"current_steps": 34065, "total_steps": 58920, "loss": 0.1092, "lr": 9.019312708887936e-07, "epoch": 2.890784114052953, "percentage": 57.82, "elapsed_time": "0:53:30", "remaining_time": "0:39:02", "throughput": 10195.5, "total_tokens": 32730560}
{"current_steps": 34070, "total_steps": 58920, "loss": 0.0002, "lr": 9.016364829105377e-07, "epoch": 2.8912084181941617, "percentage": 57.82, "elapsed_time": "0:53:30", "remaining_time": "0:39:01", "throughput": 10195.74, "total_tokens": 32735168}
{"current_steps": 34075, "total_steps": 58920, "loss": 0.0001, "lr": 9.013417035633259e-07, "epoch": 2.8916327223353697, "percentage": 57.83, "elapsed_time": "0:53:31", "remaining_time": "0:39:01", "throughput": 10195.88, "total_tokens": 32739456}
{"current_steps": 34080, "total_steps": 58920, "loss": 0.001, "lr": 9.010469328730232e-07, "epoch": 2.8920570264765786, "percentage": 57.84, "elapsed_time": "0:53:31", "remaining_time": "0:39:00", "throughput": 10196.29, "total_tokens": 32744832}
{"current_steps": 34085, "total_steps": 58920, "loss": 0.0274, "lr": 9.007521708654945e-07, "epoch": 2.8924813306177866, "percentage": 57.85, "elapsed_time": "0:53:31", "remaining_time": "0:39:00", "throughput": 10196.53, "total_tokens": 32749440}
{"current_steps": 34090, "total_steps": 58920, "loss": 0.0001, "lr": 9.004574175666048e-07, "epoch": 2.8929056347589954, "percentage": 57.86, "elapsed_time": "0:53:32", "remaining_time": "0:38:59", "throughput": 10196.78, "total_tokens": 32754112}
{"current_steps": 34095, "total_steps": 58920, "loss": 0.0001, "lr": 9.001626730022169e-07, "epoch": 2.8933299389002034, "percentage": 57.87, "elapsed_time": "0:53:32", "remaining_time": "0:38:59", "throughput": 10196.96, "total_tokens": 32758528}
{"current_steps": 34100, "total_steps": 58920, "loss": 0.0194, "lr": 8.998679371981945e-07, "epoch": 2.8937542430414123, "percentage": 57.88, "elapsed_time": "0:53:32", "remaining_time": "0:38:58", "throughput": 10197.24, "total_tokens": 32763392}
{"current_steps": 34105, "total_steps": 58920, "loss": 0.0005, "lr": 8.995732101803987e-07, "epoch": 2.8941785471826202, "percentage": 57.88, "elapsed_time": "0:53:33", "remaining_time": "0:38:58", "throughput": 10197.47, "total_tokens": 32768000}
{"current_steps": 34110, "total_steps": 58920, "loss": 0.0001, "lr": 8.992784919746915e-07, "epoch": 2.894602851323829, "percentage": 57.89, "elapsed_time": "0:53:33", "remaining_time": "0:38:57", "throughput": 10197.68, "total_tokens": 32772544}
{"current_steps": 34115, "total_steps": 58920, "loss": 0.0001, "lr": 8.989837826069326e-07, "epoch": 2.895027155465037, "percentage": 57.9, "elapsed_time": "0:53:34", "remaining_time": "0:38:56", "throughput": 10198.09, "total_tokens": 32777856}
{"current_steps": 34120, "total_steps": 58920, "loss": 0.0002, "lr": 8.986890821029822e-07, "epoch": 2.895451459606246, "percentage": 57.91, "elapsed_time": "0:53:34", "remaining_time": "0:38:56", "throughput": 10198.34, "total_tokens": 32782528}
{"current_steps": 34125, "total_steps": 58920, "loss": 0.0982, "lr": 8.983943904886994e-07, "epoch": 2.895875763747454, "percentage": 57.92, "elapsed_time": "0:53:34", "remaining_time": "0:38:55", "throughput": 10198.6, "total_tokens": 32787264}
{"current_steps": 34130, "total_steps": 58920, "loss": 0.0001, "lr": 8.980997077899414e-07, "epoch": 2.896300067888663, "percentage": 57.93, "elapsed_time": "0:53:35", "remaining_time": "0:38:55", "throughput": 10198.9, "total_tokens": 32792192}
{"current_steps": 34135, "total_steps": 58920, "loss": 0.0002, "lr": 8.978050340325667e-07, "epoch": 2.8967243720298708, "percentage": 57.93, "elapsed_time": "0:53:35", "remaining_time": "0:38:54", "throughput": 10199.26, "total_tokens": 32797376}
{"current_steps": 34140, "total_steps": 58920, "loss": 0.0002, "lr": 8.975103692424307e-07, "epoch": 2.8971486761710796, "percentage": 57.94, "elapsed_time": "0:53:36", "remaining_time": "0:38:54", "throughput": 10199.52, "total_tokens": 32802112}
{"current_steps": 34145, "total_steps": 58920, "loss": 0.0001, "lr": 8.972157134453904e-07, "epoch": 2.8975729803122876, "percentage": 57.95, "elapsed_time": "0:53:36", "remaining_time": "0:38:53", "throughput": 10199.81, "total_tokens": 32806976}
{"current_steps": 34150, "total_steps": 58920, "loss": 0.0002, "lr": 8.969210666672995e-07, "epoch": 2.8979972844534965, "percentage": 57.96, "elapsed_time": "0:53:36", "remaining_time": "0:38:53", "throughput": 10199.99, "total_tokens": 32811392}
{"current_steps": 34155, "total_steps": 58920, "loss": 0.0183, "lr": 8.966264289340132e-07, "epoch": 2.8984215885947044, "percentage": 57.97, "elapsed_time": "0:53:37", "remaining_time": "0:38:52", "throughput": 10200.36, "total_tokens": 32816576}
{"current_steps": 34160, "total_steps": 58920, "loss": 0.0251, "lr": 8.963318002713842e-07, "epoch": 2.8988458927359133, "percentage": 57.98, "elapsed_time": "0:53:37", "remaining_time": "0:38:52", "throughput": 10200.65, "total_tokens": 32821440}
{"current_steps": 34165, "total_steps": 58920, "loss": 0.0295, "lr": 8.960371807052661e-07, "epoch": 2.8992701968771213, "percentage": 57.99, "elapsed_time": "0:53:37", "remaining_time": "0:38:51", "throughput": 10200.97, "total_tokens": 32826368}
{"current_steps": 34170, "total_steps": 58920, "loss": 0.0768, "lr": 8.957425702615098e-07, "epoch": 2.89969450101833, "percentage": 57.99, "elapsed_time": "0:53:38", "remaining_time": "0:38:51", "throughput": 10201.28, "total_tokens": 32831296}
{"current_steps": 34175, "total_steps": 58920, "loss": 0.0001, "lr": 8.954479689659662e-07, "epoch": 2.900118805159538, "percentage": 58.0, "elapsed_time": "0:53:38", "remaining_time": "0:38:50", "throughput": 10201.52, "total_tokens": 32835968}
{"current_steps": 34180, "total_steps": 58920, "loss": 0.0, "lr": 8.95153376844486e-07, "epoch": 2.900543109300747, "percentage": 58.01, "elapsed_time": "0:53:39", "remaining_time": "0:38:50", "throughput": 10201.69, "total_tokens": 32840320}
{"current_steps": 34185, "total_steps": 58920, "loss": 0.0001, "lr": 8.948587939229182e-07, "epoch": 2.900967413441955, "percentage": 58.02, "elapsed_time": "0:53:39", "remaining_time": "0:38:49", "throughput": 10201.98, "total_tokens": 32845120}
{"current_steps": 34190, "total_steps": 58920, "loss": 0.0001, "lr": 8.945642202271122e-07, "epoch": 2.901391717583164, "percentage": 58.03, "elapsed_time": "0:53:39", "remaining_time": "0:38:48", "throughput": 10202.14, "total_tokens": 32849408}
{"current_steps": 34195, "total_steps": 58920, "loss": 0.0002, "lr": 8.942696557829146e-07, "epoch": 2.901816021724372, "percentage": 58.04, "elapsed_time": "0:53:40", "remaining_time": "0:38:48", "throughput": 10202.36, "total_tokens": 32854016}
{"current_steps": 34200, "total_steps": 58920, "loss": 0.0288, "lr": 8.939751006161735e-07, "epoch": 2.9022403258655807, "percentage": 58.04, "elapsed_time": "0:53:40", "remaining_time": "0:38:47", "throughput": 10202.56, "total_tokens": 32858560}
{"current_steps": 34205, "total_steps": 58920, "loss": 0.0631, "lr": 8.93680554752734e-07, "epoch": 2.9026646300067886, "percentage": 58.05, "elapsed_time": "0:53:41", "remaining_time": "0:38:47", "throughput": 10202.98, "total_tokens": 32863936}
{"current_steps": 34210, "total_steps": 58920, "loss": 0.0001, "lr": 8.933860182184425e-07, "epoch": 2.9030889341479975, "percentage": 58.06, "elapsed_time": "0:53:41", "remaining_time": "0:38:46", "throughput": 10203.24, "total_tokens": 32868672}
{"current_steps": 34215, "total_steps": 58920, "loss": 0.0001, "lr": 8.930914910391427e-07, "epoch": 2.9035132382892055, "percentage": 58.07, "elapsed_time": "0:53:41", "remaining_time": "0:38:46", "throughput": 10203.49, "total_tokens": 32873344}
{"current_steps": 34220, "total_steps": 58920, "loss": 0.0263, "lr": 8.927969732406784e-07, "epoch": 2.9039375424304144, "percentage": 58.08, "elapsed_time": "0:53:42", "remaining_time": "0:38:45", "throughput": 10203.77, "total_tokens": 32878144}
{"current_steps": 34225, "total_steps": 58920, "loss": 0.0, "lr": 8.92502464848893e-07, "epoch": 2.9043618465716223, "percentage": 58.09, "elapsed_time": "0:53:42", "remaining_time": "0:38:45", "throughput": 10203.91, "total_tokens": 32882368}
{"current_steps": 34230, "total_steps": 58920, "loss": 0.0546, "lr": 8.922079658896278e-07, "epoch": 2.904786150712831, "percentage": 58.1, "elapsed_time": "0:53:42", "remaining_time": "0:38:44", "throughput": 10204.15, "total_tokens": 32887040}
{"current_steps": 34235, "total_steps": 58920, "loss": 0.0001, "lr": 8.919134763887249e-07, "epoch": 2.905210454854039, "percentage": 58.1, "elapsed_time": "0:53:43", "remaining_time": "0:38:44", "throughput": 10204.35, "total_tokens": 32891520}
{"current_steps": 34240, "total_steps": 58920, "loss": 0.0303, "lr": 8.916189963720237e-07, "epoch": 2.905634758995248, "percentage": 58.11, "elapsed_time": "0:53:43", "remaining_time": "0:38:43", "throughput": 10204.72, "total_tokens": 32896704}
{"current_steps": 34245, "total_steps": 58920, "loss": 0.0245, "lr": 8.913245258653644e-07, "epoch": 2.906059063136456, "percentage": 58.12, "elapsed_time": "0:53:44", "remaining_time": "0:38:43", "throughput": 10205.1, "total_tokens": 32901952}
{"current_steps": 34250, "total_steps": 58920, "loss": 0.0007, "lr": 8.91030064894586e-07, "epoch": 2.906483367277665, "percentage": 58.13, "elapsed_time": "0:53:44", "remaining_time": "0:38:42", "throughput": 10205.37, "total_tokens": 32906752}
{"current_steps": 34255, "total_steps": 58920, "loss": 0.0003, "lr": 8.907356134855254e-07, "epoch": 2.906907671418873, "percentage": 58.14, "elapsed_time": "0:53:44", "remaining_time": "0:38:42", "throughput": 10205.73, "total_tokens": 32911872}
{"current_steps": 34260, "total_steps": 58920, "loss": 0.0001, "lr": 8.904411716640206e-07, "epoch": 2.9073319755600817, "percentage": 58.15, "elapsed_time": "0:53:45", "remaining_time": "0:38:41", "throughput": 10205.91, "total_tokens": 32916288}
{"current_steps": 34265, "total_steps": 58920, "loss": 0.0004, "lr": 8.901467394559071e-07, "epoch": 2.9077562797012897, "percentage": 58.16, "elapsed_time": "0:53:45", "remaining_time": "0:38:40", "throughput": 10206.21, "total_tokens": 32921216}
{"current_steps": 34270, "total_steps": 58920, "loss": 0.0, "lr": 8.89852316887021e-07, "epoch": 2.9081805838424986, "percentage": 58.16, "elapsed_time": "0:53:45", "remaining_time": "0:38:40", "throughput": 10206.58, "total_tokens": 32926400}
{"current_steps": 34275, "total_steps": 58920, "loss": 0.0, "lr": 8.895579039831959e-07, "epoch": 2.9086048879837065, "percentage": 58.17, "elapsed_time": "0:53:46", "remaining_time": "0:38:39", "throughput": 10206.84, "total_tokens": 32931136}
{"current_steps": 34280, "total_steps": 58920, "loss": 0.0001, "lr": 8.892635007702663e-07, "epoch": 2.9090291921249154, "percentage": 58.18, "elapsed_time": "0:53:46", "remaining_time": "0:38:39", "throughput": 10207.16, "total_tokens": 32936064}
{"current_steps": 34285, "total_steps": 58920, "loss": 0.0334, "lr": 8.889691072740645e-07, "epoch": 2.9094534962661234, "percentage": 58.19, "elapsed_time": "0:53:47", "remaining_time": "0:38:38", "throughput": 10207.36, "total_tokens": 32940544}
{"current_steps": 34290, "total_steps": 58920, "loss": 0.0325, "lr": 8.88674723520423e-07, "epoch": 2.9098778004073322, "percentage": 58.2, "elapsed_time": "0:53:47", "remaining_time": "0:38:38", "throughput": 10207.55, "total_tokens": 32944960}
{"current_steps": 34295, "total_steps": 58920, "loss": 0.0226, "lr": 8.883803495351726e-07, "epoch": 2.91030210454854, "percentage": 58.21, "elapsed_time": "0:53:47", "remaining_time": "0:38:37", "throughput": 10207.76, "total_tokens": 32949504}
{"current_steps": 34300, "total_steps": 58920, "loss": 0.0017, "lr": 8.880859853441431e-07, "epoch": 2.910726408689749, "percentage": 58.21, "elapsed_time": "0:53:48", "remaining_time": "0:38:37", "throughput": 10207.92, "total_tokens": 32953856}
{"current_steps": 34305, "total_steps": 58920, "loss": 0.0, "lr": 8.877916309731645e-07, "epoch": 2.911150712830957, "percentage": 58.22, "elapsed_time": "0:53:48", "remaining_time": "0:38:36", "throughput": 10208.18, "total_tokens": 32958592}
{"current_steps": 34310, "total_steps": 58920, "loss": 0.0001, "lr": 8.874972864480649e-07, "epoch": 2.911575016972166, "percentage": 58.23, "elapsed_time": "0:53:49", "remaining_time": "0:38:36", "throughput": 10208.46, "total_tokens": 32963392}
{"current_steps": 34315, "total_steps": 58920, "loss": 0.006, "lr": 8.872029517946728e-07, "epoch": 2.911999321113374, "percentage": 58.24, "elapsed_time": "0:53:49", "remaining_time": "0:38:35", "throughput": 10208.85, "total_tokens": 32968640}
{"current_steps": 34320, "total_steps": 58920, "loss": 0.0001, "lr": 8.86908627038814e-07, "epoch": 2.9124236252545828, "percentage": 58.25, "elapsed_time": "0:53:49", "remaining_time": "0:38:35", "throughput": 10209.09, "total_tokens": 32973312}
{"current_steps": 34325, "total_steps": 58920, "loss": 0.0048, "lr": 8.866143122063153e-07, "epoch": 2.9128479293957907, "percentage": 58.26, "elapsed_time": "0:53:50", "remaining_time": "0:38:34", "throughput": 10209.39, "total_tokens": 32978176}
{"current_steps": 34330, "total_steps": 58920, "loss": 0.0001, "lr": 8.863200073230007e-07, "epoch": 2.913272233536999, "percentage": 58.27, "elapsed_time": "0:53:50", "remaining_time": "0:38:34", "throughput": 10209.64, "total_tokens": 32982912}
{"current_steps": 34335, "total_steps": 58920, "loss": 0.0001, "lr": 8.860257124146956e-07, "epoch": 2.9136965376782076, "percentage": 58.27, "elapsed_time": "0:53:50", "remaining_time": "0:38:33", "throughput": 10209.86, "total_tokens": 32987520}
{"current_steps": 34340, "total_steps": 58920, "loss": 0.066, "lr": 8.857314275072225e-07, "epoch": 2.914120841819416, "percentage": 58.28, "elapsed_time": "0:53:51", "remaining_time": "0:38:32", "throughput": 10210.2, "total_tokens": 32992576}
{"current_steps": 34345, "total_steps": 58920, "loss": 0.0329, "lr": 8.854371526264039e-07, "epoch": 2.9145451459606244, "percentage": 58.29, "elapsed_time": "0:53:51", "remaining_time": "0:38:32", "throughput": 10210.34, "total_tokens": 32996800}
{"current_steps": 34350, "total_steps": 58920, "loss": 0.0191, "lr": 8.851428877980618e-07, "epoch": 2.914969450101833, "percentage": 58.3, "elapsed_time": "0:53:52", "remaining_time": "0:38:31", "throughput": 10210.55, "total_tokens": 33001280}
{"current_steps": 34355, "total_steps": 58920, "loss": 0.0006, "lr": 8.848486330480163e-07, "epoch": 2.9153937542430413, "percentage": 58.31, "elapsed_time": "0:53:52", "remaining_time": "0:38:31", "throughput": 10210.82, "total_tokens": 33006080}
{"current_steps": 34360, "total_steps": 58920, "loss": 0.0, "lr": 8.845543884020878e-07, "epoch": 2.9158180583842497, "percentage": 58.32, "elapsed_time": "0:53:52", "remaining_time": "0:38:30", "throughput": 10210.98, "total_tokens": 33010368}
{"current_steps": 34365, "total_steps": 58920, "loss": 0.0002, "lr": 8.842601538860946e-07, "epoch": 2.916242362525458, "percentage": 58.32, "elapsed_time": "0:53:53", "remaining_time": "0:38:30", "throughput": 10211.23, "total_tokens": 33015040}
{"current_steps": 34370, "total_steps": 58920, "loss": 0.0, "lr": 8.839659295258552e-07, "epoch": 2.9166666666666665, "percentage": 58.33, "elapsed_time": "0:53:53", "remaining_time": "0:38:29", "throughput": 10211.52, "total_tokens": 33019840}
{"current_steps": 34375, "total_steps": 58920, "loss": 0.0001, "lr": 8.836717153471868e-07, "epoch": 2.917090970807875, "percentage": 58.34, "elapsed_time": "0:53:53", "remaining_time": "0:38:29", "throughput": 10211.69, "total_tokens": 33024192}
{"current_steps": 34380, "total_steps": 58920, "loss": 0.0366, "lr": 8.83377511375905e-07, "epoch": 2.9175152749490834, "percentage": 58.35, "elapsed_time": "0:53:54", "remaining_time": "0:38:28", "throughput": 10211.97, "total_tokens": 33028992}
{"current_steps": 34385, "total_steps": 58920, "loss": 0.0307, "lr": 8.830833176378259e-07, "epoch": 2.917939579090292, "percentage": 58.36, "elapsed_time": "0:53:54", "remaining_time": "0:38:28", "throughput": 10212.18, "total_tokens": 33033536}
{"current_steps": 34390, "total_steps": 58920, "loss": 0.0001, "lr": 8.82789134158763e-07, "epoch": 2.9183638832315, "percentage": 58.37, "elapsed_time": "0:53:55", "remaining_time": "0:38:27", "throughput": 10212.42, "total_tokens": 33038144}
{"current_steps": 34395, "total_steps": 58920, "loss": 0.0005, "lr": 8.824949609645307e-07, "epoch": 2.9187881873727086, "percentage": 58.38, "elapsed_time": "0:53:55", "remaining_time": "0:38:27", "throughput": 10212.62, "total_tokens": 33042624}
{"current_steps": 34400, "total_steps": 58920, "loss": 0.0001, "lr": 8.822007980809412e-07, "epoch": 2.919212491513917, "percentage": 58.38, "elapsed_time": "0:53:55", "remaining_time": "0:38:26", "throughput": 10212.78, "total_tokens": 33046976}
{"current_steps": 34405, "total_steps": 58920, "loss": 0.0001, "lr": 8.819066455338066e-07, "epoch": 2.9196367956551255, "percentage": 58.39, "elapsed_time": "0:53:56", "remaining_time": "0:38:25", "throughput": 10213.09, "total_tokens": 33051904}
{"current_steps": 34410, "total_steps": 58920, "loss": 0.0304, "lr": 8.816125033489371e-07, "epoch": 2.920061099796334, "percentage": 58.4, "elapsed_time": "0:53:56", "remaining_time": "0:38:25", "throughput": 10213.28, "total_tokens": 33056320}
{"current_steps": 34415, "total_steps": 58920, "loss": 0.0004, "lr": 8.813183715521434e-07, "epoch": 2.9204854039375423, "percentage": 58.41, "elapsed_time": "0:53:56", "remaining_time": "0:38:24", "throughput": 10213.54, "total_tokens": 33061056}
{"current_steps": 34420, "total_steps": 58920, "loss": 0.0278, "lr": 8.810242501692342e-07, "epoch": 2.9209097080787507, "percentage": 58.42, "elapsed_time": "0:53:57", "remaining_time": "0:38:24", "throughput": 10213.71, "total_tokens": 33065408}
{"current_steps": 34425, "total_steps": 58920, "loss": 0.0001, "lr": 8.80730139226017e-07, "epoch": 2.921334012219959, "percentage": 58.43, "elapsed_time": "0:53:57", "remaining_time": "0:38:23", "throughput": 10214.05, "total_tokens": 33070400}
{"current_steps": 34430, "total_steps": 58920, "loss": 0.0002, "lr": 8.804360387482997e-07, "epoch": 2.9217583163611676, "percentage": 58.44, "elapsed_time": "0:53:58", "remaining_time": "0:38:23", "throughput": 10214.23, "total_tokens": 33074880}
{"current_steps": 34435, "total_steps": 58920, "loss": 0.0452, "lr": 8.801419487618881e-07, "epoch": 2.922182620502376, "percentage": 58.44, "elapsed_time": "0:53:58", "remaining_time": "0:38:22", "throughput": 10214.64, "total_tokens": 33080256}
{"current_steps": 34440, "total_steps": 58920, "loss": 0.0016, "lr": 8.798478692925882e-07, "epoch": 2.9226069246435844, "percentage": 58.45, "elapsed_time": "0:53:58", "remaining_time": "0:38:22", "throughput": 10214.85, "total_tokens": 33084800}
{"current_steps": 34445, "total_steps": 58920, "loss": 0.0004, "lr": 8.795538003662034e-07, "epoch": 2.923031228784793, "percentage": 58.46, "elapsed_time": "0:53:59", "remaining_time": "0:38:21", "throughput": 10215.05, "total_tokens": 33089280}
{"current_steps": 34450, "total_steps": 58920, "loss": 0.0, "lr": 8.792597420085384e-07, "epoch": 2.9234555329260012, "percentage": 58.47, "elapsed_time": "0:53:59", "remaining_time": "0:38:21", "throughput": 10215.34, "total_tokens": 33094144}
{"current_steps": 34455, "total_steps": 58920, "loss": 0.0003, "lr": 8.789656942453945e-07, "epoch": 2.9238798370672097, "percentage": 58.48, "elapsed_time": "0:54:00", "remaining_time": "0:38:20", "throughput": 10215.6, "total_tokens": 33098880}
{"current_steps": 34460, "total_steps": 58920, "loss": 0.0002, "lr": 8.786716571025741e-07, "epoch": 2.924304141208418, "percentage": 58.49, "elapsed_time": "0:54:00", "remaining_time": "0:38:20", "throughput": 10215.8, "total_tokens": 33103360}
{"current_steps": 34465, "total_steps": 58920, "loss": 0.0355, "lr": 8.783776306058781e-07, "epoch": 2.9247284453496265, "percentage": 58.49, "elapsed_time": "0:54:00", "remaining_time": "0:38:19", "throughput": 10216.06, "total_tokens": 33108096}
{"current_steps": 34470, "total_steps": 58920, "loss": 0.0001, "lr": 8.780836147811055e-07, "epoch": 2.925152749490835, "percentage": 58.5, "elapsed_time": "0:54:01", "remaining_time": "0:38:19", "throughput": 10216.38, "total_tokens": 33113024}
{"current_steps": 34475, "total_steps": 58920, "loss": 0.0161, "lr": 8.77789609654056e-07, "epoch": 2.9255770536320433, "percentage": 58.51, "elapsed_time": "0:54:01", "remaining_time": "0:38:18", "throughput": 10216.56, "total_tokens": 33117440}
{"current_steps": 34480, "total_steps": 58920, "loss": 0.0, "lr": 8.774956152505262e-07, "epoch": 2.9260013577732518, "percentage": 58.52, "elapsed_time": "0:54:01", "remaining_time": "0:38:17", "throughput": 10216.79, "total_tokens": 33122112}
{"current_steps": 34485, "total_steps": 58920, "loss": 0.0, "lr": 8.772016315963146e-07, "epoch": 2.92642566191446, "percentage": 58.53, "elapsed_time": "0:54:02", "remaining_time": "0:38:17", "throughput": 10217.07, "total_tokens": 33126912}
{"current_steps": 34490, "total_steps": 58920, "loss": 0.0001, "lr": 8.769076587172161e-07, "epoch": 2.9268499660556686, "percentage": 58.54, "elapsed_time": "0:54:02", "remaining_time": "0:38:16", "throughput": 10217.43, "total_tokens": 33132096}
{"current_steps": 34495, "total_steps": 58920, "loss": 0.0003, "lr": 8.766136966390261e-07, "epoch": 2.927274270196877, "percentage": 58.55, "elapsed_time": "0:54:03", "remaining_time": "0:38:16", "throughput": 10217.72, "total_tokens": 33136960}
{"current_steps": 34500, "total_steps": 58920, "loss": 0.0594, "lr": 8.763197453875392e-07, "epoch": 2.9276985743380854, "percentage": 58.55, "elapsed_time": "0:54:03", "remaining_time": "0:38:15", "throughput": 10217.81, "total_tokens": 33140992}
{"current_steps": 34505, "total_steps": 58920, "loss": 0.0001, "lr": 8.760258049885476e-07, "epoch": 2.928122878479294, "percentage": 58.56, "elapsed_time": "0:54:03", "remaining_time": "0:38:15", "throughput": 10218.15, "total_tokens": 33146048}
{"current_steps": 34510, "total_steps": 58920, "loss": 0.0407, "lr": 8.757318754678443e-07, "epoch": 2.9285471826205023, "percentage": 58.57, "elapsed_time": "0:54:04", "remaining_time": "0:38:14", "throughput": 10218.5, "total_tokens": 33151168}
{"current_steps": 34515, "total_steps": 58920, "loss": 0.0, "lr": 8.754379568512199e-07, "epoch": 2.9289714867617107, "percentage": 58.58, "elapsed_time": "0:54:04", "remaining_time": "0:38:14", "throughput": 10218.71, "total_tokens": 33155712}
{"current_steps": 34520, "total_steps": 58920, "loss": 0.0252, "lr": 8.751440491644654e-07, "epoch": 2.929395790902919, "percentage": 58.59, "elapsed_time": "0:54:04", "remaining_time": "0:38:13", "throughput": 10219.02, "total_tokens": 33160640}
{"current_steps": 34525, "total_steps": 58920, "loss": 0.0226, "lr": 8.748501524333694e-07, "epoch": 2.9298200950441275, "percentage": 58.6, "elapsed_time": "0:54:05", "remaining_time": "0:38:13", "throughput": 10219.17, "total_tokens": 33164928}
{"current_steps": 34530, "total_steps": 58920, "loss": 0.0857, "lr": 8.745562666837212e-07, "epoch": 2.930244399185336, "percentage": 58.6, "elapsed_time": "0:54:05", "remaining_time": "0:38:12", "throughput": 10219.36, "total_tokens": 33169408}
{"current_steps": 34535, "total_steps": 58920, "loss": 0.0, "lr": 8.742623919413073e-07, "epoch": 2.9306687033265444, "percentage": 58.61, "elapsed_time": "0:54:06", "remaining_time": "0:38:12", "throughput": 10219.7, "total_tokens": 33174464}
{"current_steps": 34540, "total_steps": 58920, "loss": 0.0011, "lr": 8.739685282319148e-07, "epoch": 2.931093007467753, "percentage": 58.62, "elapsed_time": "0:54:06", "remaining_time": "0:38:11", "throughput": 10220.02, "total_tokens": 33179392}
{"current_steps": 34545, "total_steps": 58920, "loss": 0.0015, "lr": 8.736746755813288e-07, "epoch": 2.9315173116089612, "percentage": 58.63, "elapsed_time": "0:54:06", "remaining_time": "0:38:11", "throughput": 10220.36, "total_tokens": 33184448}
{"current_steps": 34550, "total_steps": 58920, "loss": 0.0001, "lr": 8.73380834015334e-07, "epoch": 2.9319416157501696, "percentage": 58.64, "elapsed_time": "0:54:07", "remaining_time": "0:38:10", "throughput": 10220.53, "total_tokens": 33188800}
{"current_steps": 34555, "total_steps": 58920, "loss": 0.0251, "lr": 8.730870035597137e-07, "epoch": 2.932365919891378, "percentage": 58.65, "elapsed_time": "0:54:07", "remaining_time": "0:38:09", "throughput": 10220.76, "total_tokens": 33193472}
{"current_steps": 34560, "total_steps": 58920, "loss": 0.0003, "lr": 8.727931842402504e-07, "epoch": 2.9327902240325865, "percentage": 58.66, "elapsed_time": "0:54:08", "remaining_time": "0:38:09", "throughput": 10221.02, "total_tokens": 33198208}
{"current_steps": 34565, "total_steps": 58920, "loss": 0.02, "lr": 8.724993760827264e-07, "epoch": 2.933214528173795, "percentage": 58.66, "elapsed_time": "0:54:08", "remaining_time": "0:38:08", "throughput": 10221.15, "total_tokens": 33202432}
{"current_steps": 34570, "total_steps": 58920, "loss": 0.0003, "lr": 8.722055791129215e-07, "epoch": 2.9336388323150033, "percentage": 58.67, "elapsed_time": "0:54:08", "remaining_time": "0:38:08", "throughput": 10221.42, "total_tokens": 33207232}
{"current_steps": 34575, "total_steps": 58920, "loss": 0.016, "lr": 8.719117933566159e-07, "epoch": 2.9340631364562118, "percentage": 58.68, "elapsed_time": "0:54:09", "remaining_time": "0:38:07", "throughput": 10221.55, "total_tokens": 33211456}
{"current_steps": 34580, "total_steps": 58920, "loss": 0.0058, "lr": 8.716180188395875e-07, "epoch": 2.93448744059742, "percentage": 58.69, "elapsed_time": "0:54:09", "remaining_time": "0:38:07", "throughput": 10221.98, "total_tokens": 33216896}
{"current_steps": 34585, "total_steps": 58920, "loss": 0.0003, "lr": 8.713242555876148e-07, "epoch": 2.9349117447386286, "percentage": 58.7, "elapsed_time": "0:54:09", "remaining_time": "0:38:06", "throughput": 10222.17, "total_tokens": 33221376}
{"current_steps": 34590, "total_steps": 58920, "loss": 0.0, "lr": 8.710305036264743e-07, "epoch": 2.935336048879837, "percentage": 58.71, "elapsed_time": "0:54:10", "remaining_time": "0:38:06", "throughput": 10222.58, "total_tokens": 33226752}
{"current_steps": 34595, "total_steps": 58920, "loss": 0.0005, "lr": 8.707367629819409e-07, "epoch": 2.9357603530210454, "percentage": 58.72, "elapsed_time": "0:54:10", "remaining_time": "0:38:05", "throughput": 10222.98, "total_tokens": 33232064}
{"current_steps": 34600, "total_steps": 58920, "loss": 0.0001, "lr": 8.704430336797903e-07, "epoch": 2.936184657162254, "percentage": 58.72, "elapsed_time": "0:54:11", "remaining_time": "0:38:05", "throughput": 10223.13, "total_tokens": 33236352}
{"current_steps": 34605, "total_steps": 58920, "loss": 0.0521, "lr": 8.701493157457955e-07, "epoch": 2.9366089613034623, "percentage": 58.73, "elapsed_time": "0:54:11", "remaining_time": "0:38:04", "throughput": 10223.28, "total_tokens": 33240640}
{"current_steps": 34610, "total_steps": 58920, "loss": 0.0107, "lr": 8.698556092057294e-07, "epoch": 2.9370332654446707, "percentage": 58.74, "elapsed_time": "0:54:11", "remaining_time": "0:38:04", "throughput": 10223.46, "total_tokens": 33245056}
{"current_steps": 34615, "total_steps": 58920, "loss": 0.0, "lr": 8.695619140853638e-07, "epoch": 2.937457569585879, "percentage": 58.75, "elapsed_time": "0:54:12", "remaining_time": "0:38:03", "throughput": 10223.86, "total_tokens": 33250432}
{"current_steps": 34620, "total_steps": 58920, "loss": 0.0, "lr": 8.692682304104692e-07, "epoch": 2.9378818737270875, "percentage": 58.76, "elapsed_time": "0:54:12", "remaining_time": "0:38:03", "throughput": 10224.23, "total_tokens": 33255616}
{"current_steps": 34625, "total_steps": 58920, "loss": 0.0271, "lr": 8.689745582068158e-07, "epoch": 2.938306177868296, "percentage": 58.77, "elapsed_time": "0:54:13", "remaining_time": "0:38:02", "throughput": 10224.47, "total_tokens": 33260288}
{"current_steps": 34630, "total_steps": 58920, "loss": 0.0012, "lr": 8.686808975001713e-07, "epoch": 2.9387304820095044, "percentage": 58.77, "elapsed_time": "0:54:13", "remaining_time": "0:38:01", "throughput": 10224.6, "total_tokens": 33264512}
{"current_steps": 34635, "total_steps": 58920, "loss": 0.0, "lr": 8.683872483163043e-07, "epoch": 2.939154786150713, "percentage": 58.78, "elapsed_time": "0:54:13", "remaining_time": "0:38:01", "throughput": 10224.73, "total_tokens": 33268736}
{"current_steps": 34640, "total_steps": 58920, "loss": 0.0001, "lr": 8.680936106809806e-07, "epoch": 2.939579090291921, "percentage": 58.79, "elapsed_time": "0:54:14", "remaining_time": "0:38:00", "throughput": 10225.08, "total_tokens": 33273856}
{"current_steps": 34645, "total_steps": 58920, "loss": 0.0, "lr": 8.677999846199666e-07, "epoch": 2.9400033944331296, "percentage": 58.8, "elapsed_time": "0:54:14", "remaining_time": "0:38:00", "throughput": 10225.23, "total_tokens": 33278144}
{"current_steps": 34650, "total_steps": 58920, "loss": 0.0001, "lr": 8.675063701590265e-07, "epoch": 2.940427698574338, "percentage": 58.81, "elapsed_time": "0:54:14", "remaining_time": "0:37:59", "throughput": 10225.41, "total_tokens": 33282560}
{"current_steps": 34655, "total_steps": 58920, "loss": 0.0001, "lr": 8.672127673239244e-07, "epoch": 2.9408520027155465, "percentage": 58.82, "elapsed_time": "0:54:15", "remaining_time": "0:37:59", "throughput": 10225.6, "total_tokens": 33287040}
{"current_steps": 34660, "total_steps": 58920, "loss": 0.0004, "lr": 8.669191761404222e-07, "epoch": 2.941276306856755, "percentage": 58.83, "elapsed_time": "0:54:15", "remaining_time": "0:37:58", "throughput": 10226.01, "total_tokens": 33292480}
{"current_steps": 34665, "total_steps": 58920, "loss": 0.0224, "lr": 8.666255966342822e-07, "epoch": 2.9417006109979633, "percentage": 58.83, "elapsed_time": "0:54:16", "remaining_time": "0:37:58", "throughput": 10226.31, "total_tokens": 33297408}
{"current_steps": 34670, "total_steps": 58920, "loss": 0.0002, "lr": 8.663320288312644e-07, "epoch": 2.9421249151391717, "percentage": 58.84, "elapsed_time": "0:54:16", "remaining_time": "0:37:57", "throughput": 10226.5, "total_tokens": 33301888}
{"current_steps": 34675, "total_steps": 58920, "loss": 0.0, "lr": 8.660384727571281e-07, "epoch": 2.94254921928038, "percentage": 58.85, "elapsed_time": "0:54:16", "remaining_time": "0:37:57", "throughput": 10226.75, "total_tokens": 33306560}
{"current_steps": 34680, "total_steps": 58920, "loss": 0.0383, "lr": 8.657449284376325e-07, "epoch": 2.9429735234215886, "percentage": 58.86, "elapsed_time": "0:54:17", "remaining_time": "0:37:56", "throughput": 10227.06, "total_tokens": 33311552}
{"current_steps": 34685, "total_steps": 58920, "loss": 0.0117, "lr": 8.654513958985346e-07, "epoch": 2.943397827562797, "percentage": 58.87, "elapsed_time": "0:54:17", "remaining_time": "0:37:56", "throughput": 10227.37, "total_tokens": 33316480}
{"current_steps": 34690, "total_steps": 58920, "loss": 0.0, "lr": 8.651578751655911e-07, "epoch": 2.9438221317040054, "percentage": 58.88, "elapsed_time": "0:54:17", "remaining_time": "0:37:55", "throughput": 10227.48, "total_tokens": 33320640}
{"current_steps": 34695, "total_steps": 58920, "loss": 0.0001, "lr": 8.648643662645569e-07, "epoch": 2.944246435845214, "percentage": 58.88, "elapsed_time": "0:54:18", "remaining_time": "0:37:55", "throughput": 10227.68, "total_tokens": 33325120}
{"current_steps": 34700, "total_steps": 58920, "loss": 0.1064, "lr": 8.645708692211869e-07, "epoch": 2.9446707399864223, "percentage": 58.89, "elapsed_time": "0:54:18", "remaining_time": "0:37:54", "throughput": 10227.97, "total_tokens": 33329984}
{"current_steps": 34705, "total_steps": 58920, "loss": 0.0605, "lr": 8.64277384061234e-07, "epoch": 2.9450950441276307, "percentage": 58.9, "elapsed_time": "0:54:19", "remaining_time": "0:37:53", "throughput": 10228.2, "total_tokens": 33334592}
{"current_steps": 34710, "total_steps": 58920, "loss": 0.0, "lr": 8.639839108104506e-07, "epoch": 2.945519348268839, "percentage": 58.91, "elapsed_time": "0:54:19", "remaining_time": "0:37:53", "throughput": 10228.5, "total_tokens": 33339520}
{"current_steps": 34715, "total_steps": 58920, "loss": 0.0001, "lr": 8.636904494945882e-07, "epoch": 2.9459436524100475, "percentage": 58.92, "elapsed_time": "0:54:19", "remaining_time": "0:37:52", "throughput": 10228.77, "total_tokens": 33344256}
{"current_steps": 34720, "total_steps": 58920, "loss": 0.0002, "lr": 8.633970001393964e-07, "epoch": 2.946367956551256, "percentage": 58.93, "elapsed_time": "0:54:20", "remaining_time": "0:37:52", "throughput": 10229.06, "total_tokens": 33349120}
{"current_steps": 34725, "total_steps": 58920, "loss": 0.0001, "lr": 8.631035627706251e-07, "epoch": 2.9467922606924644, "percentage": 58.94, "elapsed_time": "0:54:20", "remaining_time": "0:37:51", "throughput": 10229.44, "total_tokens": 33354368}
{"current_steps": 34730, "total_steps": 58920, "loss": 0.0, "lr": 8.628101374140213e-07, "epoch": 2.947216564833673, "percentage": 58.94, "elapsed_time": "0:54:21", "remaining_time": "0:37:51", "throughput": 10229.75, "total_tokens": 33359360}
{"current_steps": 34735, "total_steps": 58920, "loss": 0.0196, "lr": 8.625167240953329e-07, "epoch": 2.947640868974881, "percentage": 58.95, "elapsed_time": "0:54:21", "remaining_time": "0:37:50", "throughput": 10230.12, "total_tokens": 33364544}
{"current_steps": 34740, "total_steps": 58920, "loss": 0.0278, "lr": 8.622233228403054e-07, "epoch": 2.9480651731160896, "percentage": 58.96, "elapsed_time": "0:54:21", "remaining_time": "0:37:50", "throughput": 10230.32, "total_tokens": 33369024}
{"current_steps": 34745, "total_steps": 58920, "loss": 0.0, "lr": 8.619299336746844e-07, "epoch": 2.948489477257298, "percentage": 58.97, "elapsed_time": "0:54:22", "remaining_time": "0:37:49", "throughput": 10230.56, "total_tokens": 33373696}
{"current_steps": 34750, "total_steps": 58920, "loss": 0.0001, "lr": 8.616365566242131e-07, "epoch": 2.9489137813985065, "percentage": 58.98, "elapsed_time": "0:54:22", "remaining_time": "0:37:49", "throughput": 10230.8, "total_tokens": 33378304}
{"current_steps": 34755, "total_steps": 58920, "loss": 0.0, "lr": 8.613431917146339e-07, "epoch": 2.949338085539715, "percentage": 58.99, "elapsed_time": "0:54:22", "remaining_time": "0:37:48", "throughput": 10231.0, "total_tokens": 33382784}
{"current_steps": 34760, "total_steps": 58920, "loss": 0.0916, "lr": 8.610498389716893e-07, "epoch": 2.9497623896809233, "percentage": 59.0, "elapsed_time": "0:54:23", "remaining_time": "0:37:48", "throughput": 10231.27, "total_tokens": 33387584}
{"current_steps": 34765, "total_steps": 58920, "loss": 0.0008, "lr": 8.607564984211197e-07, "epoch": 2.9501866938221317, "percentage": 59.0, "elapsed_time": "0:54:23", "remaining_time": "0:37:47", "throughput": 10231.6, "total_tokens": 33392640}
{"current_steps": 34770, "total_steps": 58920, "loss": 0.0001, "lr": 8.604631700886645e-07, "epoch": 2.95061099796334, "percentage": 59.01, "elapsed_time": "0:54:24", "remaining_time": "0:37:47", "throughput": 10231.83, "total_tokens": 33397248}
{"current_steps": 34775, "total_steps": 58920, "loss": 0.0001, "lr": 8.601698540000622e-07, "epoch": 2.9510353021045486, "percentage": 59.02, "elapsed_time": "0:54:24", "remaining_time": "0:37:46", "throughput": 10231.93, "total_tokens": 33401344}
{"current_steps": 34780, "total_steps": 58920, "loss": 0.0004, "lr": 8.598765501810508e-07, "epoch": 2.951459606245757, "percentage": 59.03, "elapsed_time": "0:54:24", "remaining_time": "0:37:46", "throughput": 10232.31, "total_tokens": 33406656}
{"current_steps": 34785, "total_steps": 58920, "loss": 0.0002, "lr": 8.595832586573658e-07, "epoch": 2.9518839103869654, "percentage": 59.04, "elapsed_time": "0:54:25", "remaining_time": "0:37:45", "throughput": 10232.63, "total_tokens": 33411648}
{"current_steps": 34790, "total_steps": 58920, "loss": 0.0137, "lr": 8.592899794547432e-07, "epoch": 2.952308214528174, "percentage": 59.05, "elapsed_time": "0:54:25", "remaining_time": "0:37:44", "throughput": 10233.06, "total_tokens": 33417152}
{"current_steps": 34795, "total_steps": 58920, "loss": 0.0481, "lr": 8.589967125989169e-07, "epoch": 2.9527325186693822, "percentage": 59.05, "elapsed_time": "0:54:25", "remaining_time": "0:37:44", "throughput": 10233.39, "total_tokens": 33422208}
{"current_steps": 34800, "total_steps": 58920, "loss": 0.0001, "lr": 8.587034581156196e-07, "epoch": 2.9531568228105907, "percentage": 59.06, "elapsed_time": "0:54:26", "remaining_time": "0:37:43", "throughput": 10233.65, "total_tokens": 33426944}
{"current_steps": 34805, "total_steps": 58920, "loss": 0.0001, "lr": 8.58410216030584e-07, "epoch": 2.953581126951799, "percentage": 59.07, "elapsed_time": "0:54:26", "remaining_time": "0:37:43", "throughput": 10233.9, "total_tokens": 33431616}
{"current_steps": 34810, "total_steps": 58920, "loss": 0.0901, "lr": 8.581169863695404e-07, "epoch": 2.9540054310930075, "percentage": 59.08, "elapsed_time": "0:54:27", "remaining_time": "0:37:42", "throughput": 10234.25, "total_tokens": 33436736}
{"current_steps": 34815, "total_steps": 58920, "loss": 0.0273, "lr": 8.578237691582195e-07, "epoch": 2.954429735234216, "percentage": 59.09, "elapsed_time": "0:54:27", "remaining_time": "0:37:42", "throughput": 10234.53, "total_tokens": 33441600}
{"current_steps": 34820, "total_steps": 58920, "loss": 0.0002, "lr": 8.57530564422349e-07, "epoch": 2.9548540393754243, "percentage": 59.1, "elapsed_time": "0:54:27", "remaining_time": "0:37:41", "throughput": 10234.84, "total_tokens": 33446528}
{"current_steps": 34825, "total_steps": 58920, "loss": 0.0117, "lr": 8.572373721876574e-07, "epoch": 2.9552783435166328, "percentage": 59.11, "elapsed_time": "0:54:28", "remaining_time": "0:37:41", "throughput": 10235.11, "total_tokens": 33451328}
{"current_steps": 34830, "total_steps": 58920, "loss": 0.0001, "lr": 8.569441924798709e-07, "epoch": 2.955702647657841, "percentage": 59.11, "elapsed_time": "0:54:28", "remaining_time": "0:37:40", "throughput": 10235.3, "total_tokens": 33455744}
{"current_steps": 34835, "total_steps": 58920, "loss": 0.0001, "lr": 8.566510253247151e-07, "epoch": 2.9561269517990496, "percentage": 59.12, "elapsed_time": "0:54:29", "remaining_time": "0:37:40", "throughput": 10235.57, "total_tokens": 33460544}
{"current_steps": 34840, "total_steps": 58920, "loss": 0.0001, "lr": 8.563578707479142e-07, "epoch": 2.956551255940258, "percentage": 59.13, "elapsed_time": "0:54:29", "remaining_time": "0:37:39", "throughput": 10235.77, "total_tokens": 33465024}
{"current_steps": 34845, "total_steps": 58920, "loss": 0.0401, "lr": 8.560647287751913e-07, "epoch": 2.9569755600814664, "percentage": 59.14, "elapsed_time": "0:54:29", "remaining_time": "0:37:39", "throughput": 10236.13, "total_tokens": 33470208}
{"current_steps": 34850, "total_steps": 58920, "loss": 0.0001, "lr": 8.557715994322692e-07, "epoch": 2.957399864222675, "percentage": 59.15, "elapsed_time": "0:54:30", "remaining_time": "0:37:38", "throughput": 10236.4, "total_tokens": 33475008}
{"current_steps": 34855, "total_steps": 58920, "loss": 0.03, "lr": 8.55478482744868e-07, "epoch": 2.9578241683638833, "percentage": 59.16, "elapsed_time": "0:54:30", "remaining_time": "0:37:38", "throughput": 10236.66, "total_tokens": 33479744}
{"current_steps": 34860, "total_steps": 58920, "loss": 0.0002, "lr": 8.551853787387084e-07, "epoch": 2.9582484725050917, "percentage": 59.16, "elapsed_time": "0:54:30", "remaining_time": "0:37:37", "throughput": 10236.84, "total_tokens": 33484160}
{"current_steps": 34865, "total_steps": 58920, "loss": 0.0001, "lr": 8.548922874395088e-07, "epoch": 2.9586727766463, "percentage": 59.17, "elapsed_time": "0:54:31", "remaining_time": "0:37:37", "throughput": 10237.09, "total_tokens": 33488832}
{"current_steps": 34870, "total_steps": 58920, "loss": 0.0002, "lr": 8.545992088729875e-07, "epoch": 2.9590970807875085, "percentage": 59.18, "elapsed_time": "0:54:31", "remaining_time": "0:37:36", "throughput": 10237.38, "total_tokens": 33493696}
{"current_steps": 34875, "total_steps": 58920, "loss": 0.0, "lr": 8.543061430648607e-07, "epoch": 2.959521384928717, "percentage": 59.19, "elapsed_time": "0:54:32", "remaining_time": "0:37:35", "throughput": 10237.63, "total_tokens": 33498368}
{"current_steps": 34880, "total_steps": 58920, "loss": 0.0001, "lr": 8.540130900408433e-07, "epoch": 2.9599456890699254, "percentage": 59.2, "elapsed_time": "0:54:32", "remaining_time": "0:37:35", "throughput": 10237.78, "total_tokens": 33502656}
{"current_steps": 34885, "total_steps": 58920, "loss": 0.0001, "lr": 8.537200498266503e-07, "epoch": 2.960369993211134, "percentage": 59.21, "elapsed_time": "0:54:32", "remaining_time": "0:37:34", "throughput": 10238.03, "total_tokens": 33507392}
{"current_steps": 34890, "total_steps": 58920, "loss": 0.0, "lr": 8.534270224479947e-07, "epoch": 2.9607942973523422, "percentage": 59.22, "elapsed_time": "0:54:33", "remaining_time": "0:37:34", "throughput": 10238.34, "total_tokens": 33512384}
{"current_steps": 34895, "total_steps": 58920, "loss": 0.0001, "lr": 8.531340079305891e-07, "epoch": 2.9612186014935507, "percentage": 59.22, "elapsed_time": "0:54:33", "remaining_time": "0:37:33", "throughput": 10238.46, "total_tokens": 33516544}
{"current_steps": 34900, "total_steps": 58920, "loss": 0.0001, "lr": 8.528410063001437e-07, "epoch": 2.961642905634759, "percentage": 59.23, "elapsed_time": "0:54:33", "remaining_time": "0:37:33", "throughput": 10238.72, "total_tokens": 33521280}
{"current_steps": 34905, "total_steps": 58920, "loss": 0.0003, "lr": 8.525480175823689e-07, "epoch": 2.9620672097759675, "percentage": 59.24, "elapsed_time": "0:54:34", "remaining_time": "0:37:32", "throughput": 10238.94, "total_tokens": 33525888}
{"current_steps": 34910, "total_steps": 58920, "loss": 0.0, "lr": 8.522550418029729e-07, "epoch": 2.962491513917176, "percentage": 59.25, "elapsed_time": "0:54:34", "remaining_time": "0:37:32", "throughput": 10239.17, "total_tokens": 33530496}
{"current_steps": 34915, "total_steps": 58920, "loss": 0.0001, "lr": 8.51962078987664e-07, "epoch": 2.9629158180583843, "percentage": 59.26, "elapsed_time": "0:54:35", "remaining_time": "0:37:31", "throughput": 10239.36, "total_tokens": 33534976}
{"current_steps": 34920, "total_steps": 58920, "loss": 0.0001, "lr": 8.516691291621478e-07, "epoch": 2.9633401221995928, "percentage": 59.27, "elapsed_time": "0:54:35", "remaining_time": "0:37:31", "throughput": 10239.62, "total_tokens": 33539712}
{"current_steps": 34925, "total_steps": 58920, "loss": 0.0138, "lr": 8.513761923521299e-07, "epoch": 2.963764426340801, "percentage": 59.28, "elapsed_time": "0:54:35", "remaining_time": "0:37:30", "throughput": 10239.85, "total_tokens": 33544320}
{"current_steps": 34930, "total_steps": 58920, "loss": 0.0, "lr": 8.510832685833149e-07, "epoch": 2.9641887304820096, "percentage": 59.28, "elapsed_time": "0:54:36", "remaining_time": "0:37:30", "throughput": 10239.98, "total_tokens": 33548544}
{"current_steps": 34935, "total_steps": 58920, "loss": 0.0, "lr": 8.50790357881405e-07, "epoch": 2.964613034623218, "percentage": 59.29, "elapsed_time": "0:54:36", "remaining_time": "0:37:29", "throughput": 10240.15, "total_tokens": 33552960}
{"current_steps": 34940, "total_steps": 58920, "loss": 0.0, "lr": 8.504974602721029e-07, "epoch": 2.9650373387644264, "percentage": 59.3, "elapsed_time": "0:54:36", "remaining_time": "0:37:29", "throughput": 10240.4, "total_tokens": 33557696}
{"current_steps": 34945, "total_steps": 58920, "loss": 0.0237, "lr": 8.502045757811085e-07, "epoch": 2.965461642905635, "percentage": 59.31, "elapsed_time": "0:54:37", "remaining_time": "0:37:28", "throughput": 10240.61, "total_tokens": 33562240}
{"current_steps": 34950, "total_steps": 58920, "loss": 0.0, "lr": 8.49911704434122e-07, "epoch": 2.9658859470468433, "percentage": 59.32, "elapsed_time": "0:54:37", "remaining_time": "0:37:28", "throughput": 10241.15, "total_tokens": 33568256}
{"current_steps": 34955, "total_steps": 58920, "loss": 0.0263, "lr": 8.496188462568412e-07, "epoch": 2.9663102511880517, "percentage": 59.33, "elapsed_time": "0:54:38", "remaining_time": "0:37:27", "throughput": 10241.53, "total_tokens": 33573504}
{"current_steps": 34960, "total_steps": 58920, "loss": 0.0, "lr": 8.493260012749641e-07, "epoch": 2.96673455532926, "percentage": 59.33, "elapsed_time": "0:54:38", "remaining_time": "0:37:26", "throughput": 10241.74, "total_tokens": 33578048}
{"current_steps": 34965, "total_steps": 58920, "loss": 0.0442, "lr": 8.490331695141865e-07, "epoch": 2.9671588594704685, "percentage": 59.34, "elapsed_time": "0:54:38", "remaining_time": "0:37:26", "throughput": 10241.96, "total_tokens": 33582592}
{"current_steps": 34970, "total_steps": 58920, "loss": 0.0295, "lr": 8.487403510002027e-07, "epoch": 2.967583163611677, "percentage": 59.35, "elapsed_time": "0:54:39", "remaining_time": "0:37:25", "throughput": 10242.24, "total_tokens": 33587456}
{"current_steps": 34975, "total_steps": 58920, "loss": 0.0, "lr": 8.484475457587072e-07, "epoch": 2.9680074677528854, "percentage": 59.36, "elapsed_time": "0:54:39", "remaining_time": "0:37:25", "throughput": 10242.5, "total_tokens": 33592256}
{"current_steps": 34980, "total_steps": 58920, "loss": 0.0, "lr": 8.481547538153925e-07, "epoch": 2.968431771894094, "percentage": 59.37, "elapsed_time": "0:54:40", "remaining_time": "0:37:24", "throughput": 10242.7, "total_tokens": 33596736}
{"current_steps": 34985, "total_steps": 58920, "loss": 0.0001, "lr": 8.478619751959497e-07, "epoch": 2.968856076035302, "percentage": 59.38, "elapsed_time": "0:54:40", "remaining_time": "0:37:24", "throughput": 10242.95, "total_tokens": 33601472}
{"current_steps": 34990, "total_steps": 58920, "loss": 0.0001, "lr": 8.475692099260693e-07, "epoch": 2.9692803801765106, "percentage": 59.39, "elapsed_time": "0:54:40", "remaining_time": "0:37:23", "throughput": 10243.2, "total_tokens": 33606208}
{"current_steps": 34995, "total_steps": 58920, "loss": 0.0546, "lr": 8.472764580314407e-07, "epoch": 2.969704684317719, "percentage": 59.39, "elapsed_time": "0:54:41", "remaining_time": "0:37:23", "throughput": 10243.47, "total_tokens": 33611008}
{"current_steps": 35000, "total_steps": 58920, "loss": 0.0313, "lr": 8.469837195377515e-07, "epoch": 2.9701289884589275, "percentage": 59.4, "elapsed_time": "0:54:41", "remaining_time": "0:37:22", "throughput": 10243.75, "total_tokens": 33615872}
{"current_steps": 35005, "total_steps": 58920, "loss": 0.0001, "lr": 8.466909944706881e-07, "epoch": 2.970553292600136, "percentage": 59.41, "elapsed_time": "0:54:41", "remaining_time": "0:37:22", "throughput": 10244.05, "total_tokens": 33620800}
{"current_steps": 35010, "total_steps": 58920, "loss": 0.0001, "lr": 8.463982828559364e-07, "epoch": 2.9709775967413443, "percentage": 59.42, "elapsed_time": "0:54:42", "remaining_time": "0:37:21", "throughput": 10244.29, "total_tokens": 33625472}
{"current_steps": 35015, "total_steps": 58920, "loss": 0.0001, "lr": 8.461055847191808e-07, "epoch": 2.9714019008825527, "percentage": 59.43, "elapsed_time": "0:54:42", "remaining_time": "0:37:21", "throughput": 10244.57, "total_tokens": 33630336}
{"current_steps": 35020, "total_steps": 58920, "loss": 0.0238, "lr": 8.458129000861048e-07, "epoch": 2.971826205023761, "percentage": 59.44, "elapsed_time": "0:54:43", "remaining_time": "0:37:20", "throughput": 10244.79, "total_tokens": 33634944}
{"current_steps": 35025, "total_steps": 58920, "loss": 0.0279, "lr": 8.455202289823899e-07, "epoch": 2.9722505091649696, "percentage": 59.45, "elapsed_time": "0:54:43", "remaining_time": "0:37:20", "throughput": 10245.04, "total_tokens": 33639616}
{"current_steps": 35030, "total_steps": 58920, "loss": 0.0403, "lr": 8.452275714337173e-07, "epoch": 2.972674813306178, "percentage": 59.45, "elapsed_time": "0:54:43", "remaining_time": "0:37:19", "throughput": 10245.24, "total_tokens": 33644096}
{"current_steps": 35035, "total_steps": 58920, "loss": 0.0, "lr": 8.449349274657664e-07, "epoch": 2.9730991174473864, "percentage": 59.46, "elapsed_time": "0:54:44", "remaining_time": "0:37:19", "throughput": 10245.38, "total_tokens": 33648384}
{"current_steps": 35040, "total_steps": 58920, "loss": 0.0001, "lr": 8.446422971042158e-07, "epoch": 2.973523421588595, "percentage": 59.47, "elapsed_time": "0:54:44", "remaining_time": "0:37:18", "throughput": 10245.66, "total_tokens": 33653248}
{"current_steps": 35045, "total_steps": 58920, "loss": 0.0238, "lr": 8.443496803747429e-07, "epoch": 2.9739477257298033, "percentage": 59.48, "elapsed_time": "0:54:45", "remaining_time": "0:37:17", "throughput": 10246.05, "total_tokens": 33658560}
{"current_steps": 35050, "total_steps": 58920, "loss": 0.0467, "lr": 8.440570773030231e-07, "epoch": 2.9743720298710117, "percentage": 59.49, "elapsed_time": "0:54:45", "remaining_time": "0:37:17", "throughput": 10246.29, "total_tokens": 33663232}
{"current_steps": 35055, "total_steps": 58920, "loss": 0.0002, "lr": 8.437644879147323e-07, "epoch": 2.97479633401222, "percentage": 59.5, "elapsed_time": "0:54:45", "remaining_time": "0:37:16", "throughput": 10246.53, "total_tokens": 33667904}
{"current_steps": 35060, "total_steps": 58920, "loss": 0.0001, "lr": 8.434719122355432e-07, "epoch": 2.9752206381534285, "percentage": 59.5, "elapsed_time": "0:54:46", "remaining_time": "0:37:16", "throughput": 10246.74, "total_tokens": 33672448}
{"current_steps": 35065, "total_steps": 58920, "loss": 0.031, "lr": 8.43179350291129e-07, "epoch": 2.975644942294637, "percentage": 59.51, "elapsed_time": "0:54:46", "remaining_time": "0:37:15", "throughput": 10246.91, "total_tokens": 33676800}
{"current_steps": 35070, "total_steps": 58920, "loss": 0.0001, "lr": 8.428868021071601e-07, "epoch": 2.9760692464358454, "percentage": 59.52, "elapsed_time": "0:54:46", "remaining_time": "0:37:15", "throughput": 10247.18, "total_tokens": 33681600}
{"current_steps": 35075, "total_steps": 58920, "loss": 0.0001, "lr": 8.425942677093075e-07, "epoch": 2.976493550577054, "percentage": 59.53, "elapsed_time": "0:54:47", "remaining_time": "0:37:14", "throughput": 10247.49, "total_tokens": 33686592}
{"current_steps": 35080, "total_steps": 58920, "loss": 0.0, "lr": 8.423017471232391e-07, "epoch": 2.976917854718262, "percentage": 59.54, "elapsed_time": "0:54:47", "remaining_time": "0:37:14", "throughput": 10247.68, "total_tokens": 33691072}
{"current_steps": 35085, "total_steps": 58920, "loss": 0.0001, "lr": 8.420092403746236e-07, "epoch": 2.9773421588594706, "percentage": 59.55, "elapsed_time": "0:54:48", "remaining_time": "0:37:13", "throughput": 10247.84, "total_tokens": 33695424}
{"current_steps": 35090, "total_steps": 58920, "loss": 0.0001, "lr": 8.417167474891269e-07, "epoch": 2.977766463000679, "percentage": 59.56, "elapsed_time": "0:54:48", "remaining_time": "0:37:13", "throughput": 10248.14, "total_tokens": 33700352}
{"current_steps": 35095, "total_steps": 58920, "loss": 0.0002, "lr": 8.414242684924135e-07, "epoch": 2.9781907671418875, "percentage": 59.56, "elapsed_time": "0:54:48", "remaining_time": "0:37:12", "throughput": 10248.34, "total_tokens": 33704832}
{"current_steps": 35100, "total_steps": 58920, "loss": 0.0002, "lr": 8.411318034101484e-07, "epoch": 2.978615071283096, "percentage": 59.57, "elapsed_time": "0:54:49", "remaining_time": "0:37:12", "throughput": 10248.55, "total_tokens": 33709376}
{"current_steps": 35105, "total_steps": 58920, "loss": 0.0001, "lr": 8.408393522679937e-07, "epoch": 2.9790393754243043, "percentage": 59.58, "elapsed_time": "0:54:49", "remaining_time": "0:37:11", "throughput": 10248.81, "total_tokens": 33714112}
{"current_steps": 35110, "total_steps": 58920, "loss": 0.0867, "lr": 8.405469150916117e-07, "epoch": 2.9794636795655127, "percentage": 59.59, "elapsed_time": "0:54:49", "remaining_time": "0:37:11", "throughput": 10249.07, "total_tokens": 33718912}
{"current_steps": 35115, "total_steps": 58920, "loss": 0.0281, "lr": 8.402544919066616e-07, "epoch": 2.979887983706721, "percentage": 59.6, "elapsed_time": "0:54:50", "remaining_time": "0:37:10", "throughput": 10249.4, "total_tokens": 33723968}
{"current_steps": 35120, "total_steps": 58920, "loss": 0.0001, "lr": 8.399620827388036e-07, "epoch": 2.980312287847929, "percentage": 59.61, "elapsed_time": "0:54:50", "remaining_time": "0:37:10", "throughput": 10249.68, "total_tokens": 33728832}
{"current_steps": 35125, "total_steps": 58920, "loss": 0.039, "lr": 8.396696876136946e-07, "epoch": 2.980736591989138, "percentage": 59.61, "elapsed_time": "0:54:51", "remaining_time": "0:37:09", "throughput": 10250.12, "total_tokens": 33734336}
{"current_steps": 35130, "total_steps": 58920, "loss": 0.0937, "lr": 8.39377306556992e-07, "epoch": 2.981160896130346, "percentage": 59.62, "elapsed_time": "0:54:51", "remaining_time": "0:37:09", "throughput": 10250.48, "total_tokens": 33739520}
{"current_steps": 35135, "total_steps": 58920, "loss": 0.0001, "lr": 8.390849395943507e-07, "epoch": 2.981585200271555, "percentage": 59.63, "elapsed_time": "0:54:51", "remaining_time": "0:37:08", "throughput": 10250.71, "total_tokens": 33744192}
{"current_steps": 35140, "total_steps": 58920, "loss": 0.0253, "lr": 8.387925867514248e-07, "epoch": 2.982009504412763, "percentage": 59.64, "elapsed_time": "0:54:52", "remaining_time": "0:37:07", "throughput": 10250.9, "total_tokens": 33748672}
{"current_steps": 35145, "total_steps": 58920, "loss": 0.0037, "lr": 8.385002480538676e-07, "epoch": 2.9824338085539717, "percentage": 59.65, "elapsed_time": "0:54:52", "remaining_time": "0:37:07", "throughput": 10251.16, "total_tokens": 33753472}
{"current_steps": 35150, "total_steps": 58920, "loss": 0.0004, "lr": 8.382079235273302e-07, "epoch": 2.9828581126951796, "percentage": 59.66, "elapsed_time": "0:54:53", "remaining_time": "0:37:06", "throughput": 10251.42, "total_tokens": 33758144}
{"current_steps": 35155, "total_steps": 58920, "loss": 0.0003, "lr": 8.37915613197464e-07, "epoch": 2.9832824168363885, "percentage": 59.67, "elapsed_time": "0:54:53", "remaining_time": "0:37:06", "throughput": 10251.7, "total_tokens": 33763008}
{"current_steps": 35160, "total_steps": 58920, "loss": 0.0001, "lr": 8.376233170899168e-07, "epoch": 2.9837067209775965, "percentage": 59.67, "elapsed_time": "0:54:53", "remaining_time": "0:37:05", "throughput": 10252.01, "total_tokens": 33768000}
{"current_steps": 35165, "total_steps": 58920, "loss": 0.0001, "lr": 8.373310352303376e-07, "epoch": 2.9841310251188053, "percentage": 59.68, "elapsed_time": "0:54:54", "remaining_time": "0:37:05", "throughput": 10252.28, "total_tokens": 33772800}
{"current_steps": 35170, "total_steps": 58920, "loss": 0.0001, "lr": 8.370387676443731e-07, "epoch": 2.9845553292600133, "percentage": 59.69, "elapsed_time": "0:54:54", "remaining_time": "0:37:04", "throughput": 10252.56, "total_tokens": 33777664}
{"current_steps": 35175, "total_steps": 58920, "loss": 0.0017, "lr": 8.367465143576677e-07, "epoch": 2.984979633401222, "percentage": 59.7, "elapsed_time": "0:54:54", "remaining_time": "0:37:04", "throughput": 10252.88, "total_tokens": 33782656}
{"current_steps": 35180, "total_steps": 58920, "loss": 0.0, "lr": 8.364542753958669e-07, "epoch": 2.98540393754243, "percentage": 59.71, "elapsed_time": "0:54:55", "remaining_time": "0:37:03", "throughput": 10253.07, "total_tokens": 33787136}
{"current_steps": 35185, "total_steps": 58920, "loss": 0.0001, "lr": 8.361620507846124e-07, "epoch": 2.985828241683639, "percentage": 59.72, "elapsed_time": "0:54:55", "remaining_time": "0:37:03", "throughput": 10253.28, "total_tokens": 33791680}
{"current_steps": 35190, "total_steps": 58920, "loss": 0.0, "lr": 8.358698405495466e-07, "epoch": 2.986252545824847, "percentage": 59.73, "elapsed_time": "0:54:56", "remaining_time": "0:37:02", "throughput": 10253.51, "total_tokens": 33796288}
{"current_steps": 35195, "total_steps": 58920, "loss": 0.0001, "lr": 8.355776447163097e-07, "epoch": 2.986676849966056, "percentage": 59.73, "elapsed_time": "0:54:56", "remaining_time": "0:37:02", "throughput": 10253.72, "total_tokens": 33800896}
{"current_steps": 35200, "total_steps": 58920, "loss": 0.0095, "lr": 8.35285463310541e-07, "epoch": 2.987101154107264, "percentage": 59.74, "elapsed_time": "0:54:56", "remaining_time": "0:37:01", "throughput": 10253.92, "total_tokens": 33805440}
{"current_steps": 35205, "total_steps": 58920, "loss": 0.0001, "lr": 8.349932963578778e-07, "epoch": 2.9875254582484727, "percentage": 59.75, "elapsed_time": "0:54:57", "remaining_time": "0:37:01", "throughput": 10254.36, "total_tokens": 33811008}
{"current_steps": 35210, "total_steps": 58920, "loss": 0.0001, "lr": 8.347011438839575e-07, "epoch": 2.9879497623896807, "percentage": 59.76, "elapsed_time": "0:54:57", "remaining_time": "0:37:00", "throughput": 10254.52, "total_tokens": 33815360}
{"current_steps": 35215, "total_steps": 58920, "loss": 0.0, "lr": 8.344090059144151e-07, "epoch": 2.9883740665308896, "percentage": 59.77, "elapsed_time": "0:54:57", "remaining_time": "0:37:00", "throughput": 10254.78, "total_tokens": 33820160}
{"current_steps": 35220, "total_steps": 58920, "loss": 0.0476, "lr": 8.341168824748841e-07, "epoch": 2.9887983706720975, "percentage": 59.78, "elapsed_time": "0:54:58", "remaining_time": "0:36:59", "throughput": 10255.0, "total_tokens": 33824704}
{"current_steps": 35225, "total_steps": 58920, "loss": 0.0002, "lr": 8.33824773590998e-07, "epoch": 2.9892226748133064, "percentage": 59.78, "elapsed_time": "0:54:58", "remaining_time": "0:36:58", "throughput": 10255.15, "total_tokens": 33829056}
{"current_steps": 35230, "total_steps": 58920, "loss": 0.0001, "lr": 8.335326792883879e-07, "epoch": 2.9896469789545144, "percentage": 59.79, "elapsed_time": "0:54:59", "remaining_time": "0:36:58", "throughput": 10255.56, "total_tokens": 33834496}
{"current_steps": 35235, "total_steps": 58920, "loss": 0.0002, "lr": 8.332405995926844e-07, "epoch": 2.9900712830957232, "percentage": 59.8, "elapsed_time": "0:54:59", "remaining_time": "0:36:57", "throughput": 10255.92, "total_tokens": 33839744}
{"current_steps": 35240, "total_steps": 58920, "loss": 0.0001, "lr": 8.32948534529516e-07, "epoch": 2.990495587236931, "percentage": 59.81, "elapsed_time": "0:54:59", "remaining_time": "0:36:57", "throughput": 10256.08, "total_tokens": 33844160}
{"current_steps": 35245, "total_steps": 58920, "loss": 0.0001, "lr": 8.326564841245109e-07, "epoch": 2.99091989137814, "percentage": 59.82, "elapsed_time": "0:55:00", "remaining_time": "0:36:56", "throughput": 10256.18, "total_tokens": 33848256}
{"current_steps": 35250, "total_steps": 58920, "loss": 0.0, "lr": 8.323644484032946e-07, "epoch": 2.991344195519348, "percentage": 59.83, "elapsed_time": "0:55:00", "remaining_time": "0:36:56", "throughput": 10256.4, "total_tokens": 33852864}
{"current_steps": 35255, "total_steps": 58920, "loss": 0.0238, "lr": 8.32072427391493e-07, "epoch": 2.991768499660557, "percentage": 59.84, "elapsed_time": "0:55:01", "remaining_time": "0:36:55", "throughput": 10256.71, "total_tokens": 33857856}
{"current_steps": 35260, "total_steps": 58920, "loss": 0.0369, "lr": 8.317804211147297e-07, "epoch": 2.992192803801765, "percentage": 59.84, "elapsed_time": "0:55:01", "remaining_time": "0:36:55", "throughput": 10256.93, "total_tokens": 33862464}
{"current_steps": 35265, "total_steps": 58920, "loss": 0.0, "lr": 8.314884295986268e-07, "epoch": 2.9926171079429738, "percentage": 59.85, "elapsed_time": "0:55:01", "remaining_time": "0:36:54", "throughput": 10257.17, "total_tokens": 33867136}
{"current_steps": 35270, "total_steps": 58920, "loss": 0.0121, "lr": 8.311964528688063e-07, "epoch": 2.9930414120841817, "percentage": 59.86, "elapsed_time": "0:55:02", "remaining_time": "0:36:54", "throughput": 10257.47, "total_tokens": 33872064}
{"current_steps": 35275, "total_steps": 58920, "loss": 0.0, "lr": 8.309044909508869e-07, "epoch": 2.9934657162253906, "percentage": 59.87, "elapsed_time": "0:55:02", "remaining_time": "0:36:53", "throughput": 10257.73, "total_tokens": 33876864}
{"current_steps": 35280, "total_steps": 58920, "loss": 0.0, "lr": 8.306125438704885e-07, "epoch": 2.9938900203665986, "percentage": 59.88, "elapsed_time": "0:55:02", "remaining_time": "0:36:53", "throughput": 10258.04, "total_tokens": 33881792}
{"current_steps": 35285, "total_steps": 58920, "loss": 0.0, "lr": 8.303206116532273e-07, "epoch": 2.9943143245078074, "percentage": 59.89, "elapsed_time": "0:55:03", "remaining_time": "0:36:52", "throughput": 10258.25, "total_tokens": 33886336}
{"current_steps": 35290, "total_steps": 58920, "loss": 0.0001, "lr": 8.300286943247201e-07, "epoch": 2.9947386286490154, "percentage": 59.89, "elapsed_time": "0:55:03", "remaining_time": "0:36:52", "throughput": 10258.55, "total_tokens": 33891200}
{"current_steps": 35295, "total_steps": 58920, "loss": 0.0007, "lr": 8.297367919105815e-07, "epoch": 2.9951629327902243, "percentage": 59.9, "elapsed_time": "0:55:04", "remaining_time": "0:36:51", "throughput": 10258.79, "total_tokens": 33895872}
{"current_steps": 35300, "total_steps": 58920, "loss": 0.0383, "lr": 8.294449044364242e-07, "epoch": 2.9955872369314323, "percentage": 59.91, "elapsed_time": "0:55:04", "remaining_time": "0:36:51", "throughput": 10258.93, "total_tokens": 33900160}
{"current_steps": 35305, "total_steps": 58920, "loss": 0.0001, "lr": 8.291530319278612e-07, "epoch": 2.996011541072641, "percentage": 59.92, "elapsed_time": "0:55:04", "remaining_time": "0:36:50", "throughput": 10259.18, "total_tokens": 33904896}
{"current_steps": 35310, "total_steps": 58920, "loss": 0.0001, "lr": 8.288611744105025e-07, "epoch": 2.996435845213849, "percentage": 59.93, "elapsed_time": "0:55:05", "remaining_time": "0:36:50", "throughput": 10259.37, "total_tokens": 33909376}
{"current_steps": 35315, "total_steps": 58920, "loss": 0.0001, "lr": 8.285693319099579e-07, "epoch": 2.996860149355058, "percentage": 59.94, "elapsed_time": "0:55:05", "remaining_time": "0:36:49", "throughput": 10259.59, "total_tokens": 33913984}
{"current_steps": 35320, "total_steps": 58920, "loss": 0.0432, "lr": 8.282775044518353e-07, "epoch": 2.997284453496266, "percentage": 59.95, "elapsed_time": "0:55:05", "remaining_time": "0:36:48", "throughput": 10259.82, "total_tokens": 33918592}
{"current_steps": 35325, "total_steps": 58920, "loss": 0.0001, "lr": 8.279856920617422e-07, "epoch": 2.997708757637475, "percentage": 59.95, "elapsed_time": "0:55:06", "remaining_time": "0:36:48", "throughput": 10259.93, "total_tokens": 33922752}
{"current_steps": 35330, "total_steps": 58920, "loss": 0.0002, "lr": 8.276938947652831e-07, "epoch": 2.9981330617786828, "percentage": 59.96, "elapsed_time": "0:55:06", "remaining_time": "0:36:47", "throughput": 10260.16, "total_tokens": 33927424}
{"current_steps": 35335, "total_steps": 58920, "loss": 0.0001, "lr": 8.274021125880629e-07, "epoch": 2.9985573659198916, "percentage": 59.97, "elapsed_time": "0:55:07", "remaining_time": "0:36:47", "throughput": 10260.37, "total_tokens": 33931968}
{"current_steps": 35340, "total_steps": 58920, "loss": 0.0001, "lr": 8.271103455556844e-07, "epoch": 2.9989816700610996, "percentage": 59.98, "elapsed_time": "0:55:07", "remaining_time": "0:36:46", "throughput": 10260.61, "total_tokens": 33936640}
{"current_steps": 35345, "total_steps": 58920, "loss": 0.0005, "lr": 8.268185936937483e-07, "epoch": 2.9994059742023085, "percentage": 59.99, "elapsed_time": "0:55:07", "remaining_time": "0:36:46", "throughput": 10260.8, "total_tokens": 33941120}
{"current_steps": 35350, "total_steps": 58920, "loss": 0.023, "lr": 8.265268570278555e-07, "epoch": 2.9998302783435165, "percentage": 60.0, "elapsed_time": "0:55:08", "remaining_time": "0:36:45", "throughput": 10261.06, "total_tokens": 33945856}
{"current_steps": 35352, "total_steps": 58920, "eval_loss": 0.1149335578083992, "epoch": 3.0, "percentage": 60.0, "elapsed_time": "0:55:24", "remaining_time": "0:36:56", "throughput": 10210.24, "total_tokens": 33947392}
{"current_steps": 35355, "total_steps": 58920, "loss": 0.0, "lr": 8.262351355836045e-07, "epoch": 3.000254582484725, "percentage": 60.01, "elapsed_time": "0:56:03", "remaining_time": "0:37:21", "throughput": 10094.96, "total_tokens": 33949760}
{"current_steps": 35360, "total_steps": 58920, "loss": 0.0001, "lr": 8.259434293865935e-07, "epoch": 3.0006788866259333, "percentage": 60.01, "elapsed_time": "0:56:03", "remaining_time": "0:37:21", "throughput": 10095.15, "total_tokens": 33954240}
{"current_steps": 35365, "total_steps": 58920, "loss": 0.0, "lr": 8.256517384624176e-07, "epoch": 3.0011031907671417, "percentage": 60.02, "elapsed_time": "0:56:03", "remaining_time": "0:37:20", "throughput": 10095.45, "total_tokens": 33959232}
{"current_steps": 35370, "total_steps": 58920, "loss": 0.0001, "lr": 8.253600628366726e-07, "epoch": 3.00152749490835, "percentage": 60.03, "elapsed_time": "0:56:04", "remaining_time": "0:37:19", "throughput": 10095.65, "total_tokens": 33963712}
{"current_steps": 35375, "total_steps": 58920, "loss": 0.0, "lr": 8.250684025349513e-07, "epoch": 3.0019517990495586, "percentage": 60.04, "elapsed_time": "0:56:04", "remaining_time": "0:37:19", "throughput": 10095.91, "total_tokens": 33968448}
{"current_steps": 35380, "total_steps": 58920, "loss": 0.0, "lr": 8.24776757582846e-07, "epoch": 3.002376103190767, "percentage": 60.05, "elapsed_time": "0:56:04", "remaining_time": "0:37:18", "throughput": 10096.25, "total_tokens": 33973504}
{"current_steps": 35385, "total_steps": 58920, "loss": 0.0001, "lr": 8.24485128005948e-07, "epoch": 3.0028004073319754, "percentage": 60.06, "elapsed_time": "0:56:05", "remaining_time": "0:37:18", "throughput": 10096.36, "total_tokens": 33977664}
{"current_steps": 35390, "total_steps": 58920, "loss": 0.0112, "lr": 8.24193513829846e-07, "epoch": 3.003224711473184, "percentage": 60.06, "elapsed_time": "0:56:05", "remaining_time": "0:37:17", "throughput": 10096.71, "total_tokens": 33982784}
{"current_steps": 35395, "total_steps": 58920, "loss": 0.0, "lr": 8.239019150801285e-07, "epoch": 3.0036490156143922, "percentage": 60.07, "elapsed_time": "0:56:06", "remaining_time": "0:37:17", "throughput": 10096.97, "total_tokens": 33987520}
{"current_steps": 35400, "total_steps": 58920, "loss": 0.0365, "lr": 8.236103317823819e-07, "epoch": 3.0040733197556007, "percentage": 60.08, "elapsed_time": "0:56:06", "remaining_time": "0:37:16", "throughput": 10097.24, "total_tokens": 33992256}
{"current_steps": 35405, "total_steps": 58920, "loss": 0.0, "lr": 8.233187639621924e-07, "epoch": 3.004497623896809, "percentage": 60.09, "elapsed_time": "0:56:06", "remaining_time": "0:37:16", "throughput": 10097.65, "total_tokens": 33997632}
{"current_steps": 35410, "total_steps": 58920, "loss": 0.0, "lr": 8.230272116451429e-07, "epoch": 3.0049219280380175, "percentage": 60.1, "elapsed_time": "0:56:07", "remaining_time": "0:37:15", "throughput": 10097.89, "total_tokens": 34002240}
{"current_steps": 35415, "total_steps": 58920, "loss": 0.0484, "lr": 8.227356748568168e-07, "epoch": 3.005346232179226, "percentage": 60.11, "elapsed_time": "0:56:07", "remaining_time": "0:37:15", "throughput": 10098.06, "total_tokens": 34006592}
{"current_steps": 35420, "total_steps": 58920, "loss": 0.0, "lr": 8.224441536227955e-07, "epoch": 3.0057705363204343, "percentage": 60.12, "elapsed_time": "0:56:08", "remaining_time": "0:37:14", "throughput": 10098.49, "total_tokens": 34012096}
{"current_steps": 35425, "total_steps": 58920, "loss": 0.0, "lr": 8.221526479686582e-07, "epoch": 3.0061948404616428, "percentage": 60.12, "elapsed_time": "0:56:08", "remaining_time": "0:37:14", "throughput": 10098.77, "total_tokens": 34016896}
{"current_steps": 35430, "total_steps": 58920, "loss": 0.0001, "lr": 8.218611579199843e-07, "epoch": 3.006619144602851, "percentage": 60.13, "elapsed_time": "0:56:08", "remaining_time": "0:37:13", "throughput": 10098.98, "total_tokens": 34021376}
{"current_steps": 35435, "total_steps": 58920, "loss": 0.0001, "lr": 8.215696835023504e-07, "epoch": 3.0070434487440596, "percentage": 60.14, "elapsed_time": "0:56:09", "remaining_time": "0:37:12", "throughput": 10099.14, "total_tokens": 34025728}
{"current_steps": 35440, "total_steps": 58920, "loss": 0.0, "lr": 8.212782247413325e-07, "epoch": 3.007467752885268, "percentage": 60.15, "elapsed_time": "0:56:09", "remaining_time": "0:37:12", "throughput": 10099.82, "total_tokens": 34032320}
{"current_steps": 35445, "total_steps": 58920, "loss": 0.0, "lr": 8.209867816625051e-07, "epoch": 3.0078920570264764, "percentage": 60.16, "elapsed_time": "0:56:09", "remaining_time": "0:37:11", "throughput": 10100.02, "total_tokens": 34036800}
{"current_steps": 35450, "total_steps": 58920, "loss": 0.0, "lr": 8.206953542914416e-07, "epoch": 3.008316361167685, "percentage": 60.17, "elapsed_time": "0:56:10", "remaining_time": "0:37:11", "throughput": 10100.14, "total_tokens": 34040960}
{"current_steps": 35455, "total_steps": 58920, "loss": 0.0001, "lr": 8.20403942653713e-07, "epoch": 3.0087406653088933, "percentage": 60.17, "elapsed_time": "0:56:10", "remaining_time": "0:37:10", "throughput": 10100.38, "total_tokens": 34045632}
{"current_steps": 35460, "total_steps": 58920, "loss": 0.0, "lr": 8.201125467748904e-07, "epoch": 3.0091649694501017, "percentage": 60.18, "elapsed_time": "0:56:11", "remaining_time": "0:37:10", "throughput": 10100.53, "total_tokens": 34049920}
{"current_steps": 35465, "total_steps": 58920, "loss": 0.0, "lr": 8.198211666805421e-07, "epoch": 3.00958927359131, "percentage": 60.19, "elapsed_time": "0:56:11", "remaining_time": "0:37:09", "throughput": 10100.76, "total_tokens": 34054528}
{"current_steps": 35470, "total_steps": 58920, "loss": 0.0001, "lr": 8.19529802396236e-07, "epoch": 3.0100135777325185, "percentage": 60.2, "elapsed_time": "0:56:11", "remaining_time": "0:37:09", "throughput": 10101.07, "total_tokens": 34059520}
{"current_steps": 35475, "total_steps": 58920, "loss": 0.0, "lr": 8.192384539475381e-07, "epoch": 3.010437881873727, "percentage": 60.21, "elapsed_time": "0:56:12", "remaining_time": "0:37:08", "throughput": 10101.29, "total_tokens": 34064064}
{"current_steps": 35480, "total_steps": 58920, "loss": 0.0, "lr": 8.18947121360013e-07, "epoch": 3.0108621860149354, "percentage": 60.22, "elapsed_time": "0:56:12", "remaining_time": "0:37:08", "throughput": 10101.5, "total_tokens": 34068608}
{"current_steps": 35485, "total_steps": 58920, "loss": 0.0, "lr": 8.186558046592246e-07, "epoch": 3.011286490156144, "percentage": 60.23, "elapsed_time": "0:56:13", "remaining_time": "0:37:07", "throughput": 10101.68, "total_tokens": 34073024}
{"current_steps": 35490, "total_steps": 58920, "loss": 0.0, "lr": 8.183645038707344e-07, "epoch": 3.0117107942973522, "percentage": 60.23, "elapsed_time": "0:56:13", "remaining_time": "0:37:07", "throughput": 10102.0, "total_tokens": 34078080}
{"current_steps": 35495, "total_steps": 58920, "loss": 0.0, "lr": 8.180732190201036e-07, "epoch": 3.0121350984385606, "percentage": 60.24, "elapsed_time": "0:56:13", "remaining_time": "0:37:06", "throughput": 10102.26, "total_tokens": 34082816}
{"current_steps": 35500, "total_steps": 58920, "loss": 0.0, "lr": 8.177819501328905e-07, "epoch": 3.012559402579769, "percentage": 60.25, "elapsed_time": "0:56:14", "remaining_time": "0:37:05", "throughput": 10102.47, "total_tokens": 34087360}
{"current_steps": 35505, "total_steps": 58920, "loss": 0.0001, "lr": 8.174906972346536e-07, "epoch": 3.0129837067209775, "percentage": 60.26, "elapsed_time": "0:56:14", "remaining_time": "0:37:05", "throughput": 10102.62, "total_tokens": 34091648}
{"current_steps": 35510, "total_steps": 58920, "loss": 0.0, "lr": 8.171994603509492e-07, "epoch": 3.013408010862186, "percentage": 60.27, "elapsed_time": "0:56:14", "remaining_time": "0:37:04", "throughput": 10102.91, "total_tokens": 34096512}
{"current_steps": 35515, "total_steps": 58920, "loss": 0.0, "lr": 8.169082395073319e-07, "epoch": 3.0138323150033943, "percentage": 60.28, "elapsed_time": "0:56:15", "remaining_time": "0:37:04", "throughput": 10103.16, "total_tokens": 34101184}
{"current_steps": 35520, "total_steps": 58920, "loss": 0.0, "lr": 8.166170347293558e-07, "epoch": 3.0142566191446027, "percentage": 60.29, "elapsed_time": "0:56:15", "remaining_time": "0:37:03", "throughput": 10103.33, "total_tokens": 34105600}
{"current_steps": 35525, "total_steps": 58920, "loss": 0.0, "lr": 8.163258460425724e-07, "epoch": 3.014680923285811, "percentage": 60.29, "elapsed_time": "0:56:16", "remaining_time": "0:37:03", "throughput": 10103.66, "total_tokens": 34110656}
{"current_steps": 35530, "total_steps": 58920, "loss": 0.0001, "lr": 8.160346734725332e-07, "epoch": 3.0151052274270196, "percentage": 60.3, "elapsed_time": "0:56:16", "remaining_time": "0:37:02", "throughput": 10103.91, "total_tokens": 34115392}
{"current_steps": 35535, "total_steps": 58920, "loss": 0.0, "lr": 8.157435170447868e-07, "epoch": 3.015529531568228, "percentage": 60.31, "elapsed_time": "0:56:16", "remaining_time": "0:37:02", "throughput": 10104.4, "total_tokens": 34121152}
{"current_steps": 35540, "total_steps": 58920, "loss": 0.0, "lr": 8.154523767848821e-07, "epoch": 3.0159538357094364, "percentage": 60.32, "elapsed_time": "0:56:17", "remaining_time": "0:37:01", "throughput": 10104.56, "total_tokens": 34125504}
{"current_steps": 35545, "total_steps": 58920, "loss": 0.0, "lr": 8.15161252718365e-07, "epoch": 3.016378139850645, "percentage": 60.33, "elapsed_time": "0:56:17", "remaining_time": "0:37:01", "throughput": 10104.88, "total_tokens": 34130496}
{"current_steps": 35550, "total_steps": 58920, "loss": 0.0, "lr": 8.148701448707801e-07, "epoch": 3.0168024439918533, "percentage": 60.34, "elapsed_time": "0:56:18", "remaining_time": "0:37:00", "throughput": 10105.12, "total_tokens": 34135104}
{"current_steps": 35555, "total_steps": 58920, "loss": 0.0001, "lr": 8.145790532676721e-07, "epoch": 3.0172267481330617, "percentage": 60.34, "elapsed_time": "0:56:18", "remaining_time": "0:37:00", "throughput": 10105.39, "total_tokens": 34139904}
{"current_steps": 35560, "total_steps": 58920, "loss": 0.0, "lr": 8.142879779345823e-07, "epoch": 3.01765105227427, "percentage": 60.35, "elapsed_time": "0:56:18", "remaining_time": "0:36:59", "throughput": 10105.63, "total_tokens": 34144512}
{"current_steps": 35565, "total_steps": 58920, "loss": 0.0, "lr": 8.13996918897052e-07, "epoch": 3.0180753564154785, "percentage": 60.36, "elapsed_time": "0:56:19", "remaining_time": "0:36:59", "throughput": 10105.85, "total_tokens": 34149056}
{"current_steps": 35570, "total_steps": 58920, "loss": 0.0, "lr": 8.137058761806203e-07, "epoch": 3.018499660556687, "percentage": 60.37, "elapsed_time": "0:56:19", "remaining_time": "0:36:58", "throughput": 10106.1, "total_tokens": 34153728}
{"current_steps": 35575, "total_steps": 58920, "loss": 0.0, "lr": 8.13414849810826e-07, "epoch": 3.0189239646978954, "percentage": 60.38, "elapsed_time": "0:56:19", "remaining_time": "0:36:57", "throughput": 10106.27, "total_tokens": 34158080}
{"current_steps": 35580, "total_steps": 58920, "loss": 0.0, "lr": 8.131238398132044e-07, "epoch": 3.019348268839104, "percentage": 60.39, "elapsed_time": "0:56:20", "remaining_time": "0:36:57", "throughput": 10106.42, "total_tokens": 34162368}
{"current_steps": 35585, "total_steps": 58920, "loss": 0.0, "lr": 8.128328462132916e-07, "epoch": 3.019772572980312, "percentage": 60.4, "elapsed_time": "0:56:20", "remaining_time": "0:36:56", "throughput": 10106.91, "total_tokens": 34168192}
{"current_steps": 35590, "total_steps": 58920, "loss": 0.0001, "lr": 8.125418690366206e-07, "epoch": 3.0201968771215206, "percentage": 60.4, "elapsed_time": "0:56:21", "remaining_time": "0:36:56", "throughput": 10107.21, "total_tokens": 34173056}
{"current_steps": 35595, "total_steps": 58920, "loss": 0.0, "lr": 8.122509083087234e-07, "epoch": 3.020621181262729, "percentage": 60.41, "elapsed_time": "0:56:21", "remaining_time": "0:36:55", "throughput": 10107.41, "total_tokens": 34177536}
{"current_steps": 35600, "total_steps": 58920, "loss": 0.0, "lr": 8.119599640551316e-07, "epoch": 3.0210454854039375, "percentage": 60.42, "elapsed_time": "0:56:21", "remaining_time": "0:36:55", "throughput": 10107.78, "total_tokens": 34182784}
{"current_steps": 35605, "total_steps": 58920, "loss": 0.0001, "lr": 8.116690363013738e-07, "epoch": 3.021469789545146, "percentage": 60.43, "elapsed_time": "0:56:22", "remaining_time": "0:36:54", "throughput": 10108.0, "total_tokens": 34187328}
{"current_steps": 35610, "total_steps": 58920, "loss": 0.0, "lr": 8.113781250729784e-07, "epoch": 3.0218940936863543, "percentage": 60.44, "elapsed_time": "0:56:22", "remaining_time": "0:36:54", "throughput": 10108.23, "total_tokens": 34192000}
{"current_steps": 35615, "total_steps": 58920, "loss": 0.0, "lr": 8.11087230395471e-07, "epoch": 3.0223183978275627, "percentage": 60.45, "elapsed_time": "0:56:22", "remaining_time": "0:36:53", "throughput": 10108.57, "total_tokens": 34197056}
{"current_steps": 35620, "total_steps": 58920, "loss": 0.0, "lr": 8.107963522943777e-07, "epoch": 3.022742701968771, "percentage": 60.45, "elapsed_time": "0:56:23", "remaining_time": "0:36:53", "throughput": 10108.66, "total_tokens": 34201152}
{"current_steps": 35625, "total_steps": 58920, "loss": 0.0, "lr": 8.105054907952208e-07, "epoch": 3.0231670061099796, "percentage": 60.46, "elapsed_time": "0:56:23", "remaining_time": "0:36:52", "throughput": 10108.95, "total_tokens": 34206016}
{"current_steps": 35630, "total_steps": 58920, "loss": 0.0, "lr": 8.102146459235231e-07, "epoch": 3.023591310251188, "percentage": 60.47, "elapsed_time": "0:56:24", "remaining_time": "0:36:52", "throughput": 10109.18, "total_tokens": 34210624}
{"current_steps": 35635, "total_steps": 58920, "loss": 0.0, "lr": 8.099238177048054e-07, "epoch": 3.0240156143923964, "percentage": 60.48, "elapsed_time": "0:56:24", "remaining_time": "0:36:51", "throughput": 10109.52, "total_tokens": 34215744}
{"current_steps": 35640, "total_steps": 58920, "loss": 0.0, "lr": 8.096330061645857e-07, "epoch": 3.024439918533605, "percentage": 60.49, "elapsed_time": "0:56:24", "remaining_time": "0:36:51", "throughput": 10109.75, "total_tokens": 34220416}
{"current_steps": 35645, "total_steps": 58920, "loss": 0.0, "lr": 8.09342211328383e-07, "epoch": 3.0248642226748133, "percentage": 60.5, "elapsed_time": "0:56:25", "remaining_time": "0:36:50", "throughput": 10110.01, "total_tokens": 34225216}
{"current_steps": 35650, "total_steps": 58920, "loss": 0.0003, "lr": 8.090514332217125e-07, "epoch": 3.0252885268160217, "percentage": 60.51, "elapsed_time": "0:56:25", "remaining_time": "0:36:49", "throughput": 10110.25, "total_tokens": 34229888}
{"current_steps": 35655, "total_steps": 58920, "loss": 0.0, "lr": 8.087606718700894e-07, "epoch": 3.02571283095723, "percentage": 60.51, "elapsed_time": "0:56:26", "remaining_time": "0:36:49", "throughput": 10110.73, "total_tokens": 34235648}
{"current_steps": 35660, "total_steps": 58920, "loss": 0.0, "lr": 8.084699272990267e-07, "epoch": 3.0261371350984385, "percentage": 60.52, "elapsed_time": "0:56:26", "remaining_time": "0:36:48", "throughput": 10110.91, "total_tokens": 34240064}
{"current_steps": 35665, "total_steps": 58920, "loss": 0.0, "lr": 8.081791995340369e-07, "epoch": 3.026561439239647, "percentage": 60.53, "elapsed_time": "0:56:26", "remaining_time": "0:36:48", "throughput": 10111.17, "total_tokens": 34244800}
{"current_steps": 35670, "total_steps": 58920, "loss": 0.0, "lr": 8.078884886006298e-07, "epoch": 3.0269857433808554, "percentage": 60.54, "elapsed_time": "0:56:27", "remaining_time": "0:36:47", "throughput": 10111.32, "total_tokens": 34249088}
{"current_steps": 35675, "total_steps": 58920, "loss": 0.0, "lr": 8.075977945243137e-07, "epoch": 3.0274100475220638, "percentage": 60.55, "elapsed_time": "0:56:27", "remaining_time": "0:36:47", "throughput": 10111.63, "total_tokens": 34254080}
{"current_steps": 35680, "total_steps": 58920, "loss": 0.0, "lr": 8.073071173305965e-07, "epoch": 3.027834351663272, "percentage": 60.56, "elapsed_time": "0:56:28", "remaining_time": "0:36:46", "throughput": 10112.38, "total_tokens": 34261056}
{"current_steps": 35685, "total_steps": 58920, "loss": 0.0, "lr": 8.070164570449843e-07, "epoch": 3.0282586558044806, "percentage": 60.57, "elapsed_time": "0:56:28", "remaining_time": "0:36:46", "throughput": 10112.7, "total_tokens": 34266048}
{"current_steps": 35690, "total_steps": 58920, "loss": 0.0, "lr": 8.067258136929811e-07, "epoch": 3.028682959945689, "percentage": 60.57, "elapsed_time": "0:56:28", "remaining_time": "0:36:45", "throughput": 10112.9, "total_tokens": 34270528}
{"current_steps": 35695, "total_steps": 58920, "loss": 0.0124, "lr": 8.064351873000898e-07, "epoch": 3.0291072640868975, "percentage": 60.58, "elapsed_time": "0:56:29", "remaining_time": "0:36:45", "throughput": 10113.24, "total_tokens": 34275712}
{"current_steps": 35700, "total_steps": 58920, "loss": 0.0, "lr": 8.061445778918123e-07, "epoch": 3.029531568228106, "percentage": 60.59, "elapsed_time": "0:56:29", "remaining_time": "0:36:44", "throughput": 10113.5, "total_tokens": 34280448}
{"current_steps": 35705, "total_steps": 58920, "loss": 0.0, "lr": 8.058539854936478e-07, "epoch": 3.0299558723693143, "percentage": 60.6, "elapsed_time": "0:56:29", "remaining_time": "0:36:44", "throughput": 10113.91, "total_tokens": 34285888}
{"current_steps": 35710, "total_steps": 58920, "loss": 0.0, "lr": 8.055634101310955e-07, "epoch": 3.0303801765105227, "percentage": 60.61, "elapsed_time": "0:56:30", "remaining_time": "0:36:43", "throughput": 10114.1, "total_tokens": 34290368}
{"current_steps": 35715, "total_steps": 58920, "loss": 0.0, "lr": 8.052728518296518e-07, "epoch": 3.030804480651731, "percentage": 60.62, "elapsed_time": "0:56:30", "remaining_time": "0:36:43", "throughput": 10114.29, "total_tokens": 34294848}
{"current_steps": 35720, "total_steps": 58920, "loss": 0.0257, "lr": 8.04982310614812e-07, "epoch": 3.0312287847929396, "percentage": 60.62, "elapsed_time": "0:56:31", "remaining_time": "0:36:42", "throughput": 10114.55, "total_tokens": 34299648}
{"current_steps": 35725, "total_steps": 58920, "loss": 0.0, "lr": 8.046917865120709e-07, "epoch": 3.031653088934148, "percentage": 60.63, "elapsed_time": "0:56:31", "remaining_time": "0:36:41", "throughput": 10114.79, "total_tokens": 34304448}
{"current_steps": 35730, "total_steps": 58920, "loss": 0.0, "lr": 8.044012795469197e-07, "epoch": 3.0320773930753564, "percentage": 60.64, "elapsed_time": "0:56:31", "remaining_time": "0:36:41", "throughput": 10115.12, "total_tokens": 34309632}
{"current_steps": 35735, "total_steps": 58920, "loss": 0.0, "lr": 8.041107897448507e-07, "epoch": 3.032501697216565, "percentage": 60.65, "elapsed_time": "0:56:32", "remaining_time": "0:36:40", "throughput": 10115.38, "total_tokens": 34314432}
{"current_steps": 35740, "total_steps": 58920, "loss": 0.0, "lr": 8.038203171313521e-07, "epoch": 3.0329260013577732, "percentage": 60.66, "elapsed_time": "0:56:32", "remaining_time": "0:36:40", "throughput": 10115.65, "total_tokens": 34319360}
{"current_steps": 35745, "total_steps": 58920, "loss": 0.0, "lr": 8.035298617319126e-07, "epoch": 3.0333503054989817, "percentage": 60.67, "elapsed_time": "0:56:33", "remaining_time": "0:36:39", "throughput": 10116.01, "total_tokens": 34324608}
{"current_steps": 35750, "total_steps": 58920, "loss": 0.0001, "lr": 8.032394235720184e-07, "epoch": 3.03377460964019, "percentage": 60.68, "elapsed_time": "0:56:33", "remaining_time": "0:36:39", "throughput": 10116.21, "total_tokens": 34329088}
{"current_steps": 35755, "total_steps": 58920, "loss": 0.0, "lr": 8.029490026771543e-07, "epoch": 3.0341989137813985, "percentage": 60.68, "elapsed_time": "0:56:33", "remaining_time": "0:36:38", "throughput": 10116.51, "total_tokens": 34334080}
{"current_steps": 35760, "total_steps": 58920, "loss": 0.0, "lr": 8.026585990728041e-07, "epoch": 3.034623217922607, "percentage": 60.69, "elapsed_time": "0:56:34", "remaining_time": "0:36:38", "throughput": 10116.75, "total_tokens": 34338752}
{"current_steps": 35765, "total_steps": 58920, "loss": 0.0, "lr": 8.023682127844488e-07, "epoch": 3.0350475220638153, "percentage": 60.7, "elapsed_time": "0:56:34", "remaining_time": "0:36:37", "throughput": 10116.91, "total_tokens": 34343104}
{"current_steps": 35770, "total_steps": 58920, "loss": 0.0, "lr": 8.020778438375697e-07, "epoch": 3.0354718262050238, "percentage": 60.71, "elapsed_time": "0:56:35", "remaining_time": "0:36:37", "throughput": 10117.16, "total_tokens": 34347840}
{"current_steps": 35775, "total_steps": 58920, "loss": 0.0001, "lr": 8.017874922576448e-07, "epoch": 3.035896130346232, "percentage": 60.72, "elapsed_time": "0:56:35", "remaining_time": "0:36:36", "throughput": 10117.36, "total_tokens": 34352384}
{"current_steps": 35780, "total_steps": 58920, "loss": 0.0, "lr": 8.01497158070152e-07, "epoch": 3.0363204344874406, "percentage": 60.73, "elapsed_time": "0:56:35", "remaining_time": "0:36:36", "throughput": 10117.52, "total_tokens": 34356736}
{"current_steps": 35785, "total_steps": 58920, "loss": 0.0, "lr": 8.012068413005668e-07, "epoch": 3.036744738628649, "percentage": 60.73, "elapsed_time": "0:56:36", "remaining_time": "0:36:35", "throughput": 10117.75, "total_tokens": 34361472}
{"current_steps": 35790, "total_steps": 58920, "loss": 0.0, "lr": 8.009165419743639e-07, "epoch": 3.0371690427698574, "percentage": 60.74, "elapsed_time": "0:56:36", "remaining_time": "0:36:35", "throughput": 10117.97, "total_tokens": 34366080}
{"current_steps": 35795, "total_steps": 58920, "loss": 0.0, "lr": 8.006262601170156e-07, "epoch": 3.037593346911066, "percentage": 60.75, "elapsed_time": "0:56:36", "remaining_time": "0:36:34", "throughput": 10118.2, "total_tokens": 34370816}
{"current_steps": 35800, "total_steps": 58920, "loss": 0.0, "lr": 8.003359957539928e-07, "epoch": 3.0380176510522743, "percentage": 60.76, "elapsed_time": "0:56:37", "remaining_time": "0:36:34", "throughput": 10118.48, "total_tokens": 34375680}
{"current_steps": 35805, "total_steps": 58920, "loss": 0.0, "lr": 8.000457489107657e-07, "epoch": 3.0384419551934827, "percentage": 60.77, "elapsed_time": "0:56:37", "remaining_time": "0:36:33", "throughput": 10118.78, "total_tokens": 34380608}
{"current_steps": 35810, "total_steps": 58920, "loss": 0.0322, "lr": 7.997555196128018e-07, "epoch": 3.038866259334691, "percentage": 60.78, "elapsed_time": "0:56:38", "remaining_time": "0:36:32", "throughput": 10118.95, "total_tokens": 34385024}
{"current_steps": 35815, "total_steps": 58920, "loss": 0.0, "lr": 7.994653078855688e-07, "epoch": 3.0392905634758995, "percentage": 60.79, "elapsed_time": "0:56:38", "remaining_time": "0:36:32", "throughput": 10119.17, "total_tokens": 34389632}
{"current_steps": 35820, "total_steps": 58920, "loss": 0.0, "lr": 7.991751137545304e-07, "epoch": 3.039714867617108, "percentage": 60.79, "elapsed_time": "0:56:38", "remaining_time": "0:36:31", "throughput": 10119.51, "total_tokens": 34394752}
{"current_steps": 35825, "total_steps": 58920, "loss": 0.0, "lr": 7.988849372451511e-07, "epoch": 3.0401391717583164, "percentage": 60.8, "elapsed_time": "0:56:39", "remaining_time": "0:36:31", "throughput": 10119.78, "total_tokens": 34399552}
{"current_steps": 35830, "total_steps": 58920, "loss": 0.0, "lr": 7.98594778382892e-07, "epoch": 3.040563475899525, "percentage": 60.81, "elapsed_time": "0:56:39", "remaining_time": "0:36:30", "throughput": 10120.14, "total_tokens": 34404800}
{"current_steps": 35835, "total_steps": 58920, "loss": 0.0, "lr": 7.983046371932145e-07, "epoch": 3.0409877800407332, "percentage": 60.82, "elapsed_time": "0:56:40", "remaining_time": "0:36:30", "throughput": 10120.34, "total_tokens": 34409344}
{"current_steps": 35840, "total_steps": 58920, "loss": 0.0, "lr": 7.980145137015766e-07, "epoch": 3.0414120841819416, "percentage": 60.83, "elapsed_time": "0:56:40", "remaining_time": "0:36:29", "throughput": 10120.49, "total_tokens": 34413696}
{"current_steps": 35845, "total_steps": 58920, "loss": 0.0, "lr": 7.977244079334355e-07, "epoch": 3.04183638832315, "percentage": 60.84, "elapsed_time": "0:56:40", "remaining_time": "0:36:29", "throughput": 10120.8, "total_tokens": 34418688}
{"current_steps": 35850, "total_steps": 58920, "loss": 0.0, "lr": 7.974343199142478e-07, "epoch": 3.0422606924643585, "percentage": 60.85, "elapsed_time": "0:56:41", "remaining_time": "0:36:28", "throughput": 10120.94, "total_tokens": 34422976}
{"current_steps": 35855, "total_steps": 58920, "loss": 0.0299, "lr": 7.971442496694668e-07, "epoch": 3.042684996605567, "percentage": 60.85, "elapsed_time": "0:56:41", "remaining_time": "0:36:28", "throughput": 10121.08, "total_tokens": 34427264}
{"current_steps": 35860, "total_steps": 58920, "loss": 0.0, "lr": 7.968541972245458e-07, "epoch": 3.0431093007467753, "percentage": 60.86, "elapsed_time": "0:56:41", "remaining_time": "0:36:27", "throughput": 10121.37, "total_tokens": 34432192}
{"current_steps": 35865, "total_steps": 58920, "loss": 0.0, "lr": 7.965641626049353e-07, "epoch": 3.0435336048879837, "percentage": 60.87, "elapsed_time": "0:56:42", "remaining_time": "0:36:27", "throughput": 10121.69, "total_tokens": 34437184}
{"current_steps": 35870, "total_steps": 58920, "loss": 0.0, "lr": 7.962741458360851e-07, "epoch": 3.043957909029192, "percentage": 60.88, "elapsed_time": "0:56:42", "remaining_time": "0:36:26", "throughput": 10121.95, "total_tokens": 34441920}
{"current_steps": 35875, "total_steps": 58920, "loss": 0.0, "lr": 7.959841469434428e-07, "epoch": 3.0443822131704006, "percentage": 60.89, "elapsed_time": "0:56:43", "remaining_time": "0:36:26", "throughput": 10122.18, "total_tokens": 34446528}
{"current_steps": 35880, "total_steps": 58920, "loss": 0.052, "lr": 7.956941659524555e-07, "epoch": 3.044806517311609, "percentage": 60.9, "elapsed_time": "0:56:43", "remaining_time": "0:36:25", "throughput": 10122.33, "total_tokens": 34450880}
{"current_steps": 35885, "total_steps": 58920, "loss": 0.0001, "lr": 7.954042028885675e-07, "epoch": 3.0452308214528174, "percentage": 60.9, "elapsed_time": "0:56:43", "remaining_time": "0:36:24", "throughput": 10122.6, "total_tokens": 34455744}
{"current_steps": 35890, "total_steps": 58920, "loss": 0.0021, "lr": 7.951142577772216e-07, "epoch": 3.045655125594026, "percentage": 60.91, "elapsed_time": "0:56:44", "remaining_time": "0:36:24", "throughput": 10123.09, "total_tokens": 34461632}
{"current_steps": 35895, "total_steps": 58920, "loss": 0.0, "lr": 7.9482433064386e-07, "epoch": 3.0460794297352343, "percentage": 60.92, "elapsed_time": "0:56:44", "remaining_time": "0:36:23", "throughput": 10123.35, "total_tokens": 34466432}
{"current_steps": 35900, "total_steps": 58920, "loss": 0.0, "lr": 7.945344215139227e-07, "epoch": 3.0465037338764427, "percentage": 60.93, "elapsed_time": "0:56:45", "remaining_time": "0:36:23", "throughput": 10123.56, "total_tokens": 34471040}
{"current_steps": 35905, "total_steps": 58920, "loss": 0.0, "lr": 7.94244530412848e-07, "epoch": 3.046928038017651, "percentage": 60.94, "elapsed_time": "0:56:45", "remaining_time": "0:36:22", "throughput": 10123.94, "total_tokens": 34476352}
{"current_steps": 35910, "total_steps": 58920, "loss": 0.0001, "lr": 7.939546573660727e-07, "epoch": 3.0473523421588595, "percentage": 60.95, "elapsed_time": "0:56:45", "remaining_time": "0:36:22", "throughput": 10124.21, "total_tokens": 34481152}
{"current_steps": 35915, "total_steps": 58920, "loss": 0.0, "lr": 7.936648023990327e-07, "epoch": 3.047776646300068, "percentage": 60.96, "elapsed_time": "0:56:46", "remaining_time": "0:36:21", "throughput": 10124.5, "total_tokens": 34486080}
{"current_steps": 35920, "total_steps": 58920, "loss": 0.0, "lr": 7.933749655371613e-07, "epoch": 3.0482009504412764, "percentage": 60.96, "elapsed_time": "0:56:46", "remaining_time": "0:36:21", "throughput": 10124.9, "total_tokens": 34491520}
{"current_steps": 35925, "total_steps": 58920, "loss": 0.0, "lr": 7.930851468058902e-07, "epoch": 3.048625254582485, "percentage": 60.97, "elapsed_time": "0:56:46", "remaining_time": "0:36:20", "throughput": 10125.15, "total_tokens": 34496320}
{"current_steps": 35930, "total_steps": 58920, "loss": 0.0, "lr": 7.927953462306507e-07, "epoch": 3.049049558723693, "percentage": 60.98, "elapsed_time": "0:56:47", "remaining_time": "0:36:20", "throughput": 10125.38, "total_tokens": 34500992}
{"current_steps": 35935, "total_steps": 58920, "loss": 0.0, "lr": 7.925055638368712e-07, "epoch": 3.0494738628649016, "percentage": 60.99, "elapsed_time": "0:56:47", "remaining_time": "0:36:19", "throughput": 10125.71, "total_tokens": 34506048}
{"current_steps": 35940, "total_steps": 58920, "loss": 0.0, "lr": 7.922157996499798e-07, "epoch": 3.04989816700611, "percentage": 61.0, "elapsed_time": "0:56:48", "remaining_time": "0:36:19", "throughput": 10126.05, "total_tokens": 34511168}
{"current_steps": 35945, "total_steps": 58920, "loss": 0.0, "lr": 7.919260536954013e-07, "epoch": 3.0503224711473185, "percentage": 61.01, "elapsed_time": "0:56:48", "remaining_time": "0:36:18", "throughput": 10126.24, "total_tokens": 34515648}
{"current_steps": 35950, "total_steps": 58920, "loss": 0.0, "lr": 7.916363259985608e-07, "epoch": 3.050746775288527, "percentage": 61.01, "elapsed_time": "0:56:48", "remaining_time": "0:36:18", "throughput": 10126.52, "total_tokens": 34520512}
{"current_steps": 35955, "total_steps": 58920, "loss": 0.0, "lr": 7.913466165848799e-07, "epoch": 3.0511710794297353, "percentage": 61.02, "elapsed_time": "0:56:49", "remaining_time": "0:36:17", "throughput": 10126.7, "total_tokens": 34524928}
{"current_steps": 35960, "total_steps": 58920, "loss": 0.0, "lr": 7.910569254797803e-07, "epoch": 3.0515953835709437, "percentage": 61.03, "elapsed_time": "0:56:49", "remaining_time": "0:36:17", "throughput": 10127.0, "total_tokens": 34529920}
{"current_steps": 35965, "total_steps": 58920, "loss": 0.0, "lr": 7.907672527086812e-07, "epoch": 3.052019687712152, "percentage": 61.04, "elapsed_time": "0:56:50", "remaining_time": "0:36:16", "throughput": 10127.4, "total_tokens": 34535296}
{"current_steps": 35970, "total_steps": 58920, "loss": 0.0493, "lr": 7.904775982970001e-07, "epoch": 3.0524439918533606, "percentage": 61.05, "elapsed_time": "0:56:50", "remaining_time": "0:36:15", "throughput": 10127.7, "total_tokens": 34540160}
{"current_steps": 35975, "total_steps": 58920, "loss": 0.0, "lr": 7.901879622701535e-07, "epoch": 3.052868295994569, "percentage": 61.06, "elapsed_time": "0:56:50", "remaining_time": "0:36:15", "throughput": 10127.91, "total_tokens": 34544704}
{"current_steps": 35980, "total_steps": 58920, "loss": 0.0, "lr": 7.898983446535553e-07, "epoch": 3.0532926001357774, "percentage": 61.07, "elapsed_time": "0:56:51", "remaining_time": "0:36:14", "throughput": 10128.07, "total_tokens": 34549056}
{"current_steps": 35985, "total_steps": 58920, "loss": 0.0, "lr": 7.896087454726193e-07, "epoch": 3.053716904276986, "percentage": 61.07, "elapsed_time": "0:56:51", "remaining_time": "0:36:14", "throughput": 10128.39, "total_tokens": 34554048}
{"current_steps": 35990, "total_steps": 58920, "loss": 0.0288, "lr": 7.893191647527557e-07, "epoch": 3.0541412084181943, "percentage": 61.08, "elapsed_time": "0:56:51", "remaining_time": "0:36:13", "throughput": 10128.57, "total_tokens": 34558464}
{"current_steps": 35995, "total_steps": 58920, "loss": 0.0001, "lr": 7.89029602519375e-07, "epoch": 3.0545655125594027, "percentage": 61.09, "elapsed_time": "0:56:52", "remaining_time": "0:36:13", "throughput": 10128.79, "total_tokens": 34563072}
{"current_steps": 36000, "total_steps": 58920, "loss": 0.0001, "lr": 7.887400587978847e-07, "epoch": 3.054989816700611, "percentage": 61.1, "elapsed_time": "0:56:52", "remaining_time": "0:36:12", "throughput": 10128.97, "total_tokens": 34567424}
{"current_steps": 36005, "total_steps": 58920, "loss": 0.0007, "lr": 7.884505336136921e-07, "epoch": 3.0554141208418195, "percentage": 61.11, "elapsed_time": "0:56:53", "remaining_time": "0:36:12", "throughput": 10129.16, "total_tokens": 34571904}
{"current_steps": 36010, "total_steps": 58920, "loss": 0.0, "lr": 7.881610269922013e-07, "epoch": 3.055838424983028, "percentage": 61.12, "elapsed_time": "0:56:53", "remaining_time": "0:36:11", "throughput": 10129.38, "total_tokens": 34576512}
{"current_steps": 36015, "total_steps": 58920, "loss": 0.0, "lr": 7.87871538958815e-07, "epoch": 3.0562627291242364, "percentage": 61.13, "elapsed_time": "0:56:53", "remaining_time": "0:36:11", "throughput": 10129.55, "total_tokens": 34580864}
{"current_steps": 36020, "total_steps": 58920, "loss": 0.0, "lr": 7.875820695389356e-07, "epoch": 3.0566870332654448, "percentage": 61.13, "elapsed_time": "0:56:54", "remaining_time": "0:36:10", "throughput": 10129.7, "total_tokens": 34585152}
{"current_steps": 36025, "total_steps": 58920, "loss": 0.0, "lr": 7.872926187579625e-07, "epoch": 3.057111337406653, "percentage": 61.14, "elapsed_time": "0:56:54", "remaining_time": "0:36:10", "throughput": 10130.06, "total_tokens": 34590336}
{"current_steps": 36030, "total_steps": 58920, "loss": 0.0, "lr": 7.870031866412944e-07, "epoch": 3.0575356415478616, "percentage": 61.15, "elapsed_time": "0:56:54", "remaining_time": "0:36:09", "throughput": 10130.17, "total_tokens": 34594432}
{"current_steps": 36035, "total_steps": 58920, "loss": 0.0001, "lr": 7.867137732143273e-07, "epoch": 3.05795994568907, "percentage": 61.16, "elapsed_time": "0:56:55", "remaining_time": "0:36:09", "throughput": 10130.46, "total_tokens": 34599296}
{"current_steps": 36040, "total_steps": 58920, "loss": 0.0001, "lr": 7.864243785024569e-07, "epoch": 3.0583842498302785, "percentage": 61.17, "elapsed_time": "0:56:55", "remaining_time": "0:36:08", "throughput": 10130.74, "total_tokens": 34604160}
{"current_steps": 36045, "total_steps": 58920, "loss": 0.0, "lr": 7.861350025310758e-07, "epoch": 3.058808553971487, "percentage": 61.18, "elapsed_time": "0:56:56", "remaining_time": "0:36:07", "throughput": 10131.03, "total_tokens": 34609024}
{"current_steps": 36050, "total_steps": 58920, "loss": 0.0, "lr": 7.858456453255766e-07, "epoch": 3.0592328581126953, "percentage": 61.18, "elapsed_time": "0:56:56", "remaining_time": "0:36:07", "throughput": 10131.35, "total_tokens": 34614080}
{"current_steps": 36055, "total_steps": 58920, "loss": 0.0, "lr": 7.855563069113484e-07, "epoch": 3.0596571622539037, "percentage": 61.19, "elapsed_time": "0:56:56", "remaining_time": "0:36:06", "throughput": 10131.53, "total_tokens": 34618496}
{"current_steps": 36060, "total_steps": 58920, "loss": 0.0, "lr": 7.8526698731378e-07, "epoch": 3.060081466395112, "percentage": 61.2, "elapsed_time": "0:56:57", "remaining_time": "0:36:06", "throughput": 10131.73, "total_tokens": 34622976}
{"current_steps": 36065, "total_steps": 58920, "loss": 0.0152, "lr": 7.849776865582585e-07, "epoch": 3.0605057705363206, "percentage": 61.21, "elapsed_time": "0:56:57", "remaining_time": "0:36:05", "throughput": 10131.99, "total_tokens": 34627712}
{"current_steps": 36070, "total_steps": 58920, "loss": 0.0, "lr": 7.846884046701683e-07, "epoch": 3.060930074677529, "percentage": 61.22, "elapsed_time": "0:56:58", "remaining_time": "0:36:05", "throughput": 10132.63, "total_tokens": 34634176}
{"current_steps": 36075, "total_steps": 58920, "loss": 0.0, "lr": 7.843991416748935e-07, "epoch": 3.0613543788187374, "percentage": 61.23, "elapsed_time": "0:56:58", "remaining_time": "0:36:04", "throughput": 10132.97, "total_tokens": 34639296}
{"current_steps": 36080, "total_steps": 58920, "loss": 0.0098, "lr": 7.841098975978154e-07, "epoch": 3.061778682959946, "percentage": 61.24, "elapsed_time": "0:56:58", "remaining_time": "0:36:04", "throughput": 10133.13, "total_tokens": 34643648}
{"current_steps": 36085, "total_steps": 58920, "loss": 0.0, "lr": 7.838206724643143e-07, "epoch": 3.0622029871011542, "percentage": 61.24, "elapsed_time": "0:56:59", "remaining_time": "0:36:03", "throughput": 10133.48, "total_tokens": 34648768}
{"current_steps": 36090, "total_steps": 58920, "loss": 0.0, "lr": 7.83531466299769e-07, "epoch": 3.0626272912423627, "percentage": 61.25, "elapsed_time": "0:56:59", "remaining_time": "0:36:03", "throughput": 10133.78, "total_tokens": 34653696}
{"current_steps": 36095, "total_steps": 58920, "loss": 0.0, "lr": 7.832422791295555e-07, "epoch": 3.063051595383571, "percentage": 61.26, "elapsed_time": "0:57:00", "remaining_time": "0:36:02", "throughput": 10134.05, "total_tokens": 34658496}
{"current_steps": 36100, "total_steps": 58920, "loss": 0.0, "lr": 7.829531109790499e-07, "epoch": 3.0634758995247795, "percentage": 61.27, "elapsed_time": "0:57:00", "remaining_time": "0:36:02", "throughput": 10134.32, "total_tokens": 34663296}
{"current_steps": 36105, "total_steps": 58920, "loss": 0.0, "lr": 7.826639618736247e-07, "epoch": 3.063900203665988, "percentage": 61.28, "elapsed_time": "0:57:00", "remaining_time": "0:36:01", "throughput": 10134.52, "total_tokens": 34667776}
{"current_steps": 36110, "total_steps": 58920, "loss": 0.0, "lr": 7.823748318386524e-07, "epoch": 3.0643245078071963, "percentage": 61.29, "elapsed_time": "0:57:01", "remaining_time": "0:36:01", "throughput": 10134.7, "total_tokens": 34672192}
{"current_steps": 36115, "total_steps": 58920, "loss": 0.0, "lr": 7.820857208995029e-07, "epoch": 3.0647488119484048, "percentage": 61.29, "elapsed_time": "0:57:01", "remaining_time": "0:36:00", "throughput": 10134.98, "total_tokens": 34677056}
{"current_steps": 36120, "total_steps": 58920, "loss": 0.0, "lr": 7.817966290815445e-07, "epoch": 3.065173116089613, "percentage": 61.3, "elapsed_time": "0:57:01", "remaining_time": "0:36:00", "throughput": 10135.21, "total_tokens": 34681664}
{"current_steps": 36125, "total_steps": 58920, "loss": 0.0, "lr": 7.81507556410144e-07, "epoch": 3.0655974202308216, "percentage": 61.31, "elapsed_time": "0:57:02", "remaining_time": "0:35:59", "throughput": 10135.47, "total_tokens": 34686400}
{"current_steps": 36130, "total_steps": 58920, "loss": 0.0, "lr": 7.812185029106668e-07, "epoch": 3.06602172437203, "percentage": 61.32, "elapsed_time": "0:57:02", "remaining_time": "0:35:58", "throughput": 10135.68, "total_tokens": 34690944}
{"current_steps": 36135, "total_steps": 58920, "loss": 0.0, "lr": 7.809294686084761e-07, "epoch": 3.0664460285132384, "percentage": 61.33, "elapsed_time": "0:57:03", "remaining_time": "0:35:58", "throughput": 10135.93, "total_tokens": 34695680}
{"current_steps": 36140, "total_steps": 58920, "loss": 0.0, "lr": 7.806404535289334e-07, "epoch": 3.066870332654447, "percentage": 61.34, "elapsed_time": "0:57:03", "remaining_time": "0:35:57", "throughput": 10136.22, "total_tokens": 34700608}
{"current_steps": 36145, "total_steps": 58920, "loss": 0.0, "lr": 7.803514576973989e-07, "epoch": 3.0672946367956553, "percentage": 61.35, "elapsed_time": "0:57:03", "remaining_time": "0:35:57", "throughput": 10136.42, "total_tokens": 34705088}
{"current_steps": 36150, "total_steps": 58920, "loss": 0.0, "lr": 7.800624811392309e-07, "epoch": 3.0677189409368637, "percentage": 61.35, "elapsed_time": "0:57:04", "remaining_time": "0:35:56", "throughput": 10136.69, "total_tokens": 34709888}
{"current_steps": 36155, "total_steps": 58920, "loss": 0.0, "lr": 7.797735238797864e-07, "epoch": 3.068143245078072, "percentage": 61.36, "elapsed_time": "0:57:04", "remaining_time": "0:35:56", "throughput": 10136.91, "total_tokens": 34714432}
{"current_steps": 36160, "total_steps": 58920, "loss": 0.0, "lr": 7.794845859444196e-07, "epoch": 3.0685675492192805, "percentage": 61.37, "elapsed_time": "0:57:04", "remaining_time": "0:35:55", "throughput": 10137.24, "total_tokens": 34719488}
{"current_steps": 36165, "total_steps": 58920, "loss": 0.0, "lr": 7.791956673584847e-07, "epoch": 3.068991853360489, "percentage": 61.38, "elapsed_time": "0:57:05", "remaining_time": "0:35:55", "throughput": 10137.58, "total_tokens": 34724608}
{"current_steps": 36170, "total_steps": 58920, "loss": 0.0, "lr": 7.789067681473323e-07, "epoch": 3.0694161575016974, "percentage": 61.39, "elapsed_time": "0:57:05", "remaining_time": "0:35:54", "throughput": 10137.71, "total_tokens": 34728768}
{"current_steps": 36175, "total_steps": 58920, "loss": 0.0, "lr": 7.78617888336313e-07, "epoch": 3.069840461642906, "percentage": 61.4, "elapsed_time": "0:57:06", "remaining_time": "0:35:54", "throughput": 10138.12, "total_tokens": 34734208}
{"current_steps": 36180, "total_steps": 58920, "loss": 0.0, "lr": 7.78329027950775e-07, "epoch": 3.0702647657841142, "percentage": 61.41, "elapsed_time": "0:57:06", "remaining_time": "0:35:53", "throughput": 10138.47, "total_tokens": 34739328}
{"current_steps": 36185, "total_steps": 58920, "loss": 0.0, "lr": 7.780401870160639e-07, "epoch": 3.0706890699253226, "percentage": 61.41, "elapsed_time": "0:57:06", "remaining_time": "0:35:53", "throughput": 10138.72, "total_tokens": 34744064}
{"current_steps": 36190, "total_steps": 58920, "loss": 0.0, "lr": 7.777513655575254e-07, "epoch": 3.071113374066531, "percentage": 61.42, "elapsed_time": "0:57:07", "remaining_time": "0:35:52", "throughput": 10139.03, "total_tokens": 34749056}
{"current_steps": 36195, "total_steps": 58920, "loss": 0.0, "lr": 7.774625636005019e-07, "epoch": 3.0715376782077395, "percentage": 61.43, "elapsed_time": "0:57:07", "remaining_time": "0:35:52", "throughput": 10139.36, "total_tokens": 34754112}
{"current_steps": 36200, "total_steps": 58920, "loss": 0.0, "lr": 7.771737811703353e-07, "epoch": 3.071961982348948, "percentage": 61.44, "elapsed_time": "0:57:08", "remaining_time": "0:35:51", "throughput": 10139.68, "total_tokens": 34759104}
{"current_steps": 36205, "total_steps": 58920, "loss": 0.0, "lr": 7.768850182923644e-07, "epoch": 3.0723862864901563, "percentage": 61.45, "elapsed_time": "0:57:08", "remaining_time": "0:35:50", "throughput": 10139.88, "total_tokens": 34763584}
{"current_steps": 36210, "total_steps": 58920, "loss": 0.0, "lr": 7.765962749919279e-07, "epoch": 3.0728105906313647, "percentage": 61.46, "elapsed_time": "0:57:08", "remaining_time": "0:35:50", "throughput": 10140.12, "total_tokens": 34768256}
{"current_steps": 36215, "total_steps": 58920, "loss": 0.0, "lr": 7.763075512943618e-07, "epoch": 3.073234894772573, "percentage": 61.46, "elapsed_time": "0:57:09", "remaining_time": "0:35:49", "throughput": 10140.44, "total_tokens": 34773312}
{"current_steps": 36220, "total_steps": 58920, "loss": 0.0, "lr": 7.760188472250002e-07, "epoch": 3.0736591989137816, "percentage": 61.47, "elapsed_time": "0:57:09", "remaining_time": "0:35:49", "throughput": 10140.73, "total_tokens": 34778176}
{"current_steps": 36225, "total_steps": 58920, "loss": 0.0001, "lr": 7.757301628091763e-07, "epoch": 3.07408350305499, "percentage": 61.48, "elapsed_time": "0:57:09", "remaining_time": "0:35:48", "throughput": 10140.94, "total_tokens": 34782720}
{"current_steps": 36230, "total_steps": 58920, "loss": 0.0001, "lr": 7.754414980722205e-07, "epoch": 3.0745078071961984, "percentage": 61.49, "elapsed_time": "0:57:10", "remaining_time": "0:35:48", "throughput": 10141.16, "total_tokens": 34787264}
{"current_steps": 36235, "total_steps": 58920, "loss": 0.0, "lr": 7.751528530394626e-07, "epoch": 3.074932111337407, "percentage": 61.5, "elapsed_time": "0:57:10", "remaining_time": "0:35:47", "throughput": 10141.36, "total_tokens": 34791744}
{"current_steps": 36240, "total_steps": 58920, "loss": 0.0002, "lr": 7.7486422773623e-07, "epoch": 3.0753564154786153, "percentage": 61.51, "elapsed_time": "0:57:11", "remaining_time": "0:35:47", "throughput": 10141.54, "total_tokens": 34796160}
{"current_steps": 36245, "total_steps": 58920, "loss": 0.0, "lr": 7.74575622187849e-07, "epoch": 3.0757807196198237, "percentage": 61.52, "elapsed_time": "0:57:11", "remaining_time": "0:35:46", "throughput": 10141.81, "total_tokens": 34800960}
{"current_steps": 36250, "total_steps": 58920, "loss": 0.0, "lr": 7.742870364196428e-07, "epoch": 3.076205023761032, "percentage": 61.52, "elapsed_time": "0:57:11", "remaining_time": "0:35:46", "throughput": 10142.12, "total_tokens": 34805888}
{"current_steps": 36255, "total_steps": 58920, "loss": 0.0, "lr": 7.739984704569345e-07, "epoch": 3.0766293279022405, "percentage": 61.53, "elapsed_time": "0:57:12", "remaining_time": "0:35:45", "throughput": 10142.38, "total_tokens": 34810624}
{"current_steps": 36260, "total_steps": 58920, "loss": 0.0, "lr": 7.737099243250444e-07, "epoch": 3.077053632043449, "percentage": 61.54, "elapsed_time": "0:57:12", "remaining_time": "0:35:45", "throughput": 10142.63, "total_tokens": 34815360}
{"current_steps": 36265, "total_steps": 58920, "loss": 0.0, "lr": 7.734213980492914e-07, "epoch": 3.0774779361846574, "percentage": 61.55, "elapsed_time": "0:57:12", "remaining_time": "0:35:44", "throughput": 10142.82, "total_tokens": 34819776}
{"current_steps": 36270, "total_steps": 58920, "loss": 0.0, "lr": 7.731328916549926e-07, "epoch": 3.077902240325866, "percentage": 61.56, "elapsed_time": "0:57:13", "remaining_time": "0:35:44", "throughput": 10143.14, "total_tokens": 34824832}
{"current_steps": 36275, "total_steps": 58920, "loss": 0.0, "lr": 7.728444051674633e-07, "epoch": 3.078326544467074, "percentage": 61.57, "elapsed_time": "0:57:13", "remaining_time": "0:35:43", "throughput": 10143.51, "total_tokens": 34830144}
{"current_steps": 36280, "total_steps": 58920, "loss": 0.0, "lr": 7.725559386120177e-07, "epoch": 3.0787508486082826, "percentage": 61.58, "elapsed_time": "0:57:14", "remaining_time": "0:35:43", "throughput": 10143.75, "total_tokens": 34834816}
{"current_steps": 36285, "total_steps": 58920, "loss": 0.0, "lr": 7.722674920139669e-07, "epoch": 3.0791751527494906, "percentage": 61.58, "elapsed_time": "0:57:14", "remaining_time": "0:35:42", "throughput": 10144.16, "total_tokens": 34840256}
{"current_steps": 36290, "total_steps": 58920, "loss": 0.0, "lr": 7.719790653986218e-07, "epoch": 3.0795994568906995, "percentage": 61.59, "elapsed_time": "0:57:14", "remaining_time": "0:35:41", "throughput": 10144.34, "total_tokens": 34844672}
{"current_steps": 36295, "total_steps": 58920, "loss": 0.0, "lr": 7.716906587912902e-07, "epoch": 3.0800237610319074, "percentage": 61.6, "elapsed_time": "0:57:15", "remaining_time": "0:35:41", "throughput": 10144.51, "total_tokens": 34849024}
{"current_steps": 36300, "total_steps": 58920, "loss": 0.0, "lr": 7.71402272217279e-07, "epoch": 3.0804480651731163, "percentage": 61.61, "elapsed_time": "0:57:15", "remaining_time": "0:35:40", "throughput": 10144.88, "total_tokens": 34854272}
{"current_steps": 36305, "total_steps": 58920, "loss": 0.0, "lr": 7.711139057018934e-07, "epoch": 3.0808723693143243, "percentage": 61.62, "elapsed_time": "0:57:16", "remaining_time": "0:35:40", "throughput": 10145.33, "total_tokens": 34859904}
{"current_steps": 36310, "total_steps": 58920, "loss": 0.0, "lr": 7.708255592704357e-07, "epoch": 3.081296673455533, "percentage": 61.63, "elapsed_time": "0:57:16", "remaining_time": "0:35:39", "throughput": 10145.58, "total_tokens": 34864704}
{"current_steps": 36315, "total_steps": 58920, "loss": 0.0, "lr": 7.705372329482082e-07, "epoch": 3.081720977596741, "percentage": 61.63, "elapsed_time": "0:57:16", "remaining_time": "0:35:39", "throughput": 10145.79, "total_tokens": 34869248}
{"current_steps": 36320, "total_steps": 58920, "loss": 0.0, "lr": 7.702489267605096e-07, "epoch": 3.0821452817379495, "percentage": 61.64, "elapsed_time": "0:57:17", "remaining_time": "0:35:38", "throughput": 10145.96, "total_tokens": 34873600}
{"current_steps": 36325, "total_steps": 58920, "loss": 0.0, "lr": 7.699606407326384e-07, "epoch": 3.082569585879158, "percentage": 61.65, "elapsed_time": "0:57:17", "remaining_time": "0:35:38", "throughput": 10146.23, "total_tokens": 34878464}
{"current_steps": 36330, "total_steps": 58920, "loss": 0.0, "lr": 7.696723748898903e-07, "epoch": 3.0829938900203664, "percentage": 61.66, "elapsed_time": "0:57:17", "remaining_time": "0:35:37", "throughput": 10146.44, "total_tokens": 34883008}
{"current_steps": 36335, "total_steps": 58920, "loss": 0.0, "lr": 7.693841292575598e-07, "epoch": 3.083418194161575, "percentage": 61.67, "elapsed_time": "0:57:18", "remaining_time": "0:35:37", "throughput": 10146.71, "total_tokens": 34887872}
{"current_steps": 36340, "total_steps": 58920, "loss": 0.0, "lr": 7.690959038609396e-07, "epoch": 3.0838424983027832, "percentage": 61.68, "elapsed_time": "0:57:18", "remaining_time": "0:35:36", "throughput": 10146.96, "total_tokens": 34892608}
{"current_steps": 36345, "total_steps": 58920, "loss": 0.0, "lr": 7.688076987253196e-07, "epoch": 3.0842668024439917, "percentage": 61.69, "elapsed_time": "0:57:19", "remaining_time": "0:35:36", "throughput": 10147.22, "total_tokens": 34897408}
{"current_steps": 36350, "total_steps": 58920, "loss": 0.0244, "lr": 7.685195138759899e-07, "epoch": 3.0846911065852, "percentage": 61.69, "elapsed_time": "0:57:19", "remaining_time": "0:35:35", "throughput": 10147.42, "total_tokens": 34901888}
{"current_steps": 36355, "total_steps": 58920, "loss": 0.0, "lr": 7.682313493382366e-07, "epoch": 3.0851154107264085, "percentage": 61.7, "elapsed_time": "0:57:19", "remaining_time": "0:35:35", "throughput": 10147.59, "total_tokens": 34906304}
{"current_steps": 36360, "total_steps": 58920, "loss": 0.0, "lr": 7.679432051373458e-07, "epoch": 3.085539714867617, "percentage": 61.71, "elapsed_time": "0:57:20", "remaining_time": "0:35:34", "throughput": 10148.02, "total_tokens": 34911872}
{"current_steps": 36365, "total_steps": 58920, "loss": 0.0, "lr": 7.676550812986007e-07, "epoch": 3.0859640190088253, "percentage": 61.72, "elapsed_time": "0:57:20", "remaining_time": "0:35:34", "throughput": 10148.13, "total_tokens": 34916032}
{"current_steps": 36370, "total_steps": 58920, "loss": 0.0, "lr": 7.673669778472838e-07, "epoch": 3.0863883231500338, "percentage": 61.73, "elapsed_time": "0:57:21", "remaining_time": "0:35:33", "throughput": 10148.43, "total_tokens": 34920960}
{"current_steps": 36375, "total_steps": 58920, "loss": 0.0, "lr": 7.670788948086741e-07, "epoch": 3.086812627291242, "percentage": 61.74, "elapsed_time": "0:57:21", "remaining_time": "0:35:32", "throughput": 10148.78, "total_tokens": 34926144}
{"current_steps": 36380, "total_steps": 58920, "loss": 0.0, "lr": 7.66790832208051e-07, "epoch": 3.0872369314324506, "percentage": 61.74, "elapsed_time": "0:57:21", "remaining_time": "0:35:32", "throughput": 10148.95, "total_tokens": 34930560}
{"current_steps": 36385, "total_steps": 58920, "loss": 0.0, "lr": 7.6650279007069e-07, "epoch": 3.087661235573659, "percentage": 61.75, "elapsed_time": "0:57:22", "remaining_time": "0:35:31", "throughput": 10149.08, "total_tokens": 34934784}
{"current_steps": 36390, "total_steps": 58920, "loss": 0.0, "lr": 7.662147684218662e-07, "epoch": 3.0880855397148674, "percentage": 61.76, "elapsed_time": "0:57:22", "remaining_time": "0:35:31", "throughput": 10149.3, "total_tokens": 34939392}
{"current_steps": 36395, "total_steps": 58920, "loss": 0.0, "lr": 7.659267672868525e-07, "epoch": 3.088509843856076, "percentage": 61.77, "elapsed_time": "0:57:22", "remaining_time": "0:35:30", "throughput": 10149.65, "total_tokens": 34944576}
{"current_steps": 36400, "total_steps": 58920, "loss": 0.0005, "lr": 7.656387866909197e-07, "epoch": 3.0889341479972843, "percentage": 61.78, "elapsed_time": "0:57:23", "remaining_time": "0:35:30", "throughput": 10150.05, "total_tokens": 34950016}
{"current_steps": 36405, "total_steps": 58920, "loss": 0.0, "lr": 7.653508266593376e-07, "epoch": 3.0893584521384927, "percentage": 61.79, "elapsed_time": "0:57:23", "remaining_time": "0:35:29", "throughput": 10150.34, "total_tokens": 34954880}
{"current_steps": 36410, "total_steps": 58920, "loss": 0.0, "lr": 7.650628872173727e-07, "epoch": 3.089782756279701, "percentage": 61.8, "elapsed_time": "0:57:24", "remaining_time": "0:35:29", "throughput": 10150.54, "total_tokens": 34959360}
{"current_steps": 36415, "total_steps": 58920, "loss": 0.0, "lr": 7.647749683902917e-07, "epoch": 3.0902070604209095, "percentage": 61.8, "elapsed_time": "0:57:24", "remaining_time": "0:35:28", "throughput": 10150.85, "total_tokens": 34964352}
{"current_steps": 36420, "total_steps": 58920, "loss": 0.0, "lr": 7.644870702033575e-07, "epoch": 3.090631364562118, "percentage": 61.81, "elapsed_time": "0:57:24", "remaining_time": "0:35:28", "throughput": 10151.09, "total_tokens": 34969024}
{"current_steps": 36425, "total_steps": 58920, "loss": 0.0059, "lr": 7.641991926818329e-07, "epoch": 3.0910556687033264, "percentage": 61.82, "elapsed_time": "0:57:25", "remaining_time": "0:35:27", "throughput": 10151.42, "total_tokens": 34974144}
{"current_steps": 36430, "total_steps": 58920, "loss": 0.0361, "lr": 7.639113358509779e-07, "epoch": 3.091479972844535, "percentage": 61.83, "elapsed_time": "0:57:25", "remaining_time": "0:35:27", "throughput": 10151.72, "total_tokens": 34979008}
{"current_steps": 36435, "total_steps": 58920, "loss": 0.0, "lr": 7.636234997360503e-07, "epoch": 3.091904276985743, "percentage": 61.84, "elapsed_time": "0:57:26", "remaining_time": "0:35:26", "throughput": 10152.05, "total_tokens": 34984064}
{"current_steps": 36440, "total_steps": 58920, "loss": 0.0, "lr": 7.633356843623077e-07, "epoch": 3.0923285811269516, "percentage": 61.85, "elapsed_time": "0:57:26", "remaining_time": "0:35:26", "throughput": 10152.35, "total_tokens": 34989056}
{"current_steps": 36445, "total_steps": 58920, "loss": 0.0, "lr": 7.630478897550038e-07, "epoch": 3.09275288526816, "percentage": 61.86, "elapsed_time": "0:57:26", "remaining_time": "0:35:25", "throughput": 10152.65, "total_tokens": 34993984}
{"current_steps": 36450, "total_steps": 58920, "loss": 0.0, "lr": 7.627601159393923e-07, "epoch": 3.0931771894093685, "percentage": 61.86, "elapsed_time": "0:57:27", "remaining_time": "0:35:25", "throughput": 10152.93, "total_tokens": 34998848}
{"current_steps": 36455, "total_steps": 58920, "loss": 0.0, "lr": 7.624723629407239e-07, "epoch": 3.093601493550577, "percentage": 61.87, "elapsed_time": "0:57:27", "remaining_time": "0:35:24", "throughput": 10153.13, "total_tokens": 35003328}
{"current_steps": 36460, "total_steps": 58920, "loss": 0.0, "lr": 7.621846307842486e-07, "epoch": 3.0940257976917853, "percentage": 61.88, "elapsed_time": "0:57:27", "remaining_time": "0:35:23", "throughput": 10153.36, "total_tokens": 35007936}
{"current_steps": 36465, "total_steps": 58920, "loss": 0.0, "lr": 7.618969194952132e-07, "epoch": 3.0944501018329937, "percentage": 61.89, "elapsed_time": "0:57:28", "remaining_time": "0:35:23", "throughput": 10153.67, "total_tokens": 35012928}
{"current_steps": 36470, "total_steps": 58920, "loss": 0.0, "lr": 7.616092290988629e-07, "epoch": 3.094874405974202, "percentage": 61.9, "elapsed_time": "0:57:28", "remaining_time": "0:35:22", "throughput": 10153.96, "total_tokens": 35017856}
{"current_steps": 36475, "total_steps": 58920, "loss": 0.0, "lr": 7.613215596204424e-07, "epoch": 3.0952987101154106, "percentage": 61.91, "elapsed_time": "0:57:29", "remaining_time": "0:35:22", "throughput": 10154.28, "total_tokens": 35022912}
{"current_steps": 36480, "total_steps": 58920, "loss": 0.0, "lr": 7.610339110851933e-07, "epoch": 3.095723014256619, "percentage": 61.91, "elapsed_time": "0:57:29", "remaining_time": "0:35:21", "throughput": 10154.47, "total_tokens": 35027392}
{"current_steps": 36485, "total_steps": 58920, "loss": 0.0, "lr": 7.607462835183557e-07, "epoch": 3.0961473183978274, "percentage": 61.92, "elapsed_time": "0:57:29", "remaining_time": "0:35:21", "throughput": 10154.6, "total_tokens": 35031552}
{"current_steps": 36490, "total_steps": 58920, "loss": 0.0, "lr": 7.604586769451676e-07, "epoch": 3.096571622539036, "percentage": 61.93, "elapsed_time": "0:57:30", "remaining_time": "0:35:20", "throughput": 10155.07, "total_tokens": 35037312}
{"current_steps": 36495, "total_steps": 58920, "loss": 0.0, "lr": 7.601710913908663e-07, "epoch": 3.0969959266802443, "percentage": 61.94, "elapsed_time": "0:57:30", "remaining_time": "0:35:20", "throughput": 10155.33, "total_tokens": 35042048}
{"current_steps": 36500, "total_steps": 58920, "loss": 0.0211, "lr": 7.598835268806853e-07, "epoch": 3.0974202308214527, "percentage": 61.95, "elapsed_time": "0:57:30", "remaining_time": "0:35:19", "throughput": 10155.56, "total_tokens": 35046720}
{"current_steps": 36505, "total_steps": 58920, "loss": 0.0, "lr": 7.595959834398584e-07, "epoch": 3.097844534962661, "percentage": 61.96, "elapsed_time": "0:57:31", "remaining_time": "0:35:19", "throughput": 10155.8, "total_tokens": 35051392}
{"current_steps": 36510, "total_steps": 58920, "loss": 0.0, "lr": 7.593084610936156e-07, "epoch": 3.0982688391038695, "percentage": 61.97, "elapsed_time": "0:57:31", "remaining_time": "0:35:18", "throughput": 10155.94, "total_tokens": 35055616}
{"current_steps": 36515, "total_steps": 58920, "loss": 0.0, "lr": 7.590209598671863e-07, "epoch": 3.098693143245078, "percentage": 61.97, "elapsed_time": "0:57:32", "remaining_time": "0:35:18", "throughput": 10156.19, "total_tokens": 35060352}
{"current_steps": 36520, "total_steps": 58920, "loss": 0.0002, "lr": 7.58733479785798e-07, "epoch": 3.0991174473862864, "percentage": 61.98, "elapsed_time": "0:57:32", "remaining_time": "0:35:17", "throughput": 10156.38, "total_tokens": 35064832}
{"current_steps": 36525, "total_steps": 58920, "loss": 0.0, "lr": 7.584460208746754e-07, "epoch": 3.099541751527495, "percentage": 61.99, "elapsed_time": "0:57:32", "remaining_time": "0:35:17", "throughput": 10156.54, "total_tokens": 35069184}
{"current_steps": 36530, "total_steps": 58920, "loss": 0.0, "lr": 7.581585831590429e-07, "epoch": 3.099966055668703, "percentage": 62.0, "elapsed_time": "0:57:33", "remaining_time": "0:35:16", "throughput": 10156.82, "total_tokens": 35074048}
{"current_steps": 36535, "total_steps": 58920, "loss": 0.0, "lr": 7.578711666641209e-07, "epoch": 3.1003903598099116, "percentage": 62.01, "elapsed_time": "0:57:33", "remaining_time": "0:35:16", "throughput": 10157.15, "total_tokens": 35079104}
{"current_steps": 36540, "total_steps": 58920, "loss": 0.0, "lr": 7.575837714151302e-07, "epoch": 3.10081466395112, "percentage": 62.02, "elapsed_time": "0:57:34", "remaining_time": "0:35:15", "throughput": 10157.52, "total_tokens": 35084416}
{"current_steps": 36545, "total_steps": 58920, "loss": 0.0357, "lr": 7.572963974372884e-07, "epoch": 3.1012389680923285, "percentage": 62.02, "elapsed_time": "0:57:34", "remaining_time": "0:35:14", "throughput": 10157.74, "total_tokens": 35089024}
{"current_steps": 36550, "total_steps": 58920, "loss": 0.0, "lr": 7.570090447558112e-07, "epoch": 3.101663272233537, "percentage": 62.03, "elapsed_time": "0:57:34", "remaining_time": "0:35:14", "throughput": 10157.92, "total_tokens": 35093440}
{"current_steps": 36555, "total_steps": 58920, "loss": 0.0003, "lr": 7.567217133959133e-07, "epoch": 3.1020875763747453, "percentage": 62.04, "elapsed_time": "0:57:35", "remaining_time": "0:35:13", "throughput": 10158.13, "total_tokens": 35097984}
{"current_steps": 36560, "total_steps": 58920, "loss": 0.0, "lr": 7.564344033828063e-07, "epoch": 3.1025118805159537, "percentage": 62.05, "elapsed_time": "0:57:35", "remaining_time": "0:35:13", "throughput": 10158.38, "total_tokens": 35102720}
{"current_steps": 36565, "total_steps": 58920, "loss": 0.0, "lr": 7.561471147417014e-07, "epoch": 3.102936184657162, "percentage": 62.06, "elapsed_time": "0:57:35", "remaining_time": "0:35:12", "throughput": 10158.96, "total_tokens": 35108928}
{"current_steps": 36570, "total_steps": 58920, "loss": 0.0, "lr": 7.558598474978064e-07, "epoch": 3.1033604887983706, "percentage": 62.07, "elapsed_time": "0:57:36", "remaining_time": "0:35:12", "throughput": 10159.24, "total_tokens": 35113792}
{"current_steps": 36575, "total_steps": 58920, "loss": 0.0, "lr": 7.555726016763285e-07, "epoch": 3.103784792939579, "percentage": 62.08, "elapsed_time": "0:57:36", "remaining_time": "0:35:11", "throughput": 10159.53, "total_tokens": 35118656}
{"current_steps": 36580, "total_steps": 58920, "loss": 0.0, "lr": 7.552853773024721e-07, "epoch": 3.1042090970807874, "percentage": 62.08, "elapsed_time": "0:57:37", "remaining_time": "0:35:11", "throughput": 10159.78, "total_tokens": 35123456}
{"current_steps": 36585, "total_steps": 58920, "loss": 0.0, "lr": 7.549981744014408e-07, "epoch": 3.104633401221996, "percentage": 62.09, "elapsed_time": "0:57:37", "remaining_time": "0:35:10", "throughput": 10159.99, "total_tokens": 35128000}
{"current_steps": 36590, "total_steps": 58920, "loss": 0.0, "lr": 7.54710992998435e-07, "epoch": 3.1050577053632042, "percentage": 62.1, "elapsed_time": "0:57:37", "remaining_time": "0:35:10", "throughput": 10160.28, "total_tokens": 35132928}
{"current_steps": 36595, "total_steps": 58920, "loss": 0.0, "lr": 7.544238331186535e-07, "epoch": 3.1054820095044127, "percentage": 62.11, "elapsed_time": "0:57:38", "remaining_time": "0:35:09", "throughput": 10160.67, "total_tokens": 35138304}
{"current_steps": 36600, "total_steps": 58920, "loss": 0.0, "lr": 7.541366947872944e-07, "epoch": 3.105906313645621, "percentage": 62.12, "elapsed_time": "0:57:38", "remaining_time": "0:35:09", "throughput": 10160.85, "total_tokens": 35142720}
{"current_steps": 36605, "total_steps": 58920, "loss": 0.0034, "lr": 7.538495780295522e-07, "epoch": 3.1063306177868295, "percentage": 62.13, "elapsed_time": "0:57:39", "remaining_time": "0:35:08", "throughput": 10161.05, "total_tokens": 35147200}
{"current_steps": 36610, "total_steps": 58920, "loss": 0.0, "lr": 7.535624828706214e-07, "epoch": 3.106754921928038, "percentage": 62.14, "elapsed_time": "0:57:39", "remaining_time": "0:35:08", "throughput": 10161.33, "total_tokens": 35152128}
{"current_steps": 36615, "total_steps": 58920, "loss": 0.0, "lr": 7.532754093356925e-07, "epoch": 3.1071792260692463, "percentage": 62.14, "elapsed_time": "0:57:39", "remaining_time": "0:35:07", "throughput": 10161.66, "total_tokens": 35157184}
{"current_steps": 36620, "total_steps": 58920, "loss": 0.0, "lr": 7.52988357449956e-07, "epoch": 3.1076035302104548, "percentage": 62.15, "elapsed_time": "0:57:40", "remaining_time": "0:35:07", "throughput": 10161.99, "total_tokens": 35162304}
{"current_steps": 36625, "total_steps": 58920, "loss": 0.0, "lr": 7.527013272385989e-07, "epoch": 3.108027834351663, "percentage": 62.16, "elapsed_time": "0:57:40", "remaining_time": "0:35:06", "throughput": 10162.29, "total_tokens": 35167232}
{"current_steps": 36630, "total_steps": 58920, "loss": 0.0, "lr": 7.524143187268079e-07, "epoch": 3.1084521384928716, "percentage": 62.17, "elapsed_time": "0:57:40", "remaining_time": "0:35:06", "throughput": 10162.7, "total_tokens": 35172608}
{"current_steps": 36635, "total_steps": 58920, "loss": 0.0, "lr": 7.521273319397663e-07, "epoch": 3.10887644263408, "percentage": 62.18, "elapsed_time": "0:57:41", "remaining_time": "0:35:05", "throughput": 10162.96, "total_tokens": 35177344}
{"current_steps": 36640, "total_steps": 58920, "loss": 0.0, "lr": 7.518403669026563e-07, "epoch": 3.1093007467752884, "percentage": 62.19, "elapsed_time": "0:57:41", "remaining_time": "0:35:04", "throughput": 10163.24, "total_tokens": 35182208}
{"current_steps": 36645, "total_steps": 58920, "loss": 0.0, "lr": 7.515534236406584e-07, "epoch": 3.109725050916497, "percentage": 62.19, "elapsed_time": "0:57:42", "remaining_time": "0:35:04", "throughput": 10163.43, "total_tokens": 35186688}
{"current_steps": 36650, "total_steps": 58920, "loss": 0.0, "lr": 7.512665021789502e-07, "epoch": 3.1101493550577053, "percentage": 62.2, "elapsed_time": "0:57:42", "remaining_time": "0:35:03", "throughput": 10163.85, "total_tokens": 35192192}
{"current_steps": 36655, "total_steps": 58920, "loss": 0.0, "lr": 7.509796025427087e-07, "epoch": 3.1105736591989137, "percentage": 62.21, "elapsed_time": "0:57:42", "remaining_time": "0:35:03", "throughput": 10164.07, "total_tokens": 35196800}
{"current_steps": 36660, "total_steps": 58920, "loss": 0.0281, "lr": 7.506927247571077e-07, "epoch": 3.110997963340122, "percentage": 62.22, "elapsed_time": "0:57:43", "remaining_time": "0:35:02", "throughput": 10164.31, "total_tokens": 35201472}
{"current_steps": 36665, "total_steps": 58920, "loss": 0.0, "lr": 7.504058688473201e-07, "epoch": 3.1114222674813306, "percentage": 62.23, "elapsed_time": "0:57:43", "remaining_time": "0:35:02", "throughput": 10164.59, "total_tokens": 35206336}
{"current_steps": 36670, "total_steps": 58920, "loss": 0.03, "lr": 7.501190348385163e-07, "epoch": 3.111846571622539, "percentage": 62.24, "elapsed_time": "0:57:44", "remaining_time": "0:35:01", "throughput": 10164.82, "total_tokens": 35211008}
{"current_steps": 36675, "total_steps": 58920, "loss": 0.0, "lr": 7.498322227558653e-07, "epoch": 3.1122708757637474, "percentage": 62.25, "elapsed_time": "0:57:44", "remaining_time": "0:35:01", "throughput": 10165.0, "total_tokens": 35215424}
{"current_steps": 36680, "total_steps": 58920, "loss": 0.0, "lr": 7.495454326245335e-07, "epoch": 3.112695179904956, "percentage": 62.25, "elapsed_time": "0:57:44", "remaining_time": "0:35:00", "throughput": 10165.36, "total_tokens": 35220672}
{"current_steps": 36685, "total_steps": 58920, "loss": 0.0, "lr": 7.492586644696854e-07, "epoch": 3.1131194840461642, "percentage": 62.26, "elapsed_time": "0:57:45", "remaining_time": "0:35:00", "throughput": 10165.54, "total_tokens": 35225088}
{"current_steps": 36690, "total_steps": 58920, "loss": 0.0, "lr": 7.489719183164846e-07, "epoch": 3.1135437881873727, "percentage": 62.27, "elapsed_time": "0:57:45", "remaining_time": "0:34:59", "throughput": 10165.74, "total_tokens": 35229632}
{"current_steps": 36695, "total_steps": 58920, "loss": 0.0, "lr": 7.486851941900911e-07, "epoch": 3.113968092328581, "percentage": 62.28, "elapsed_time": "0:57:45", "remaining_time": "0:34:59", "throughput": 10166.1, "total_tokens": 35234816}
{"current_steps": 36700, "total_steps": 58920, "loss": 0.0, "lr": 7.483984921156647e-07, "epoch": 3.1143923964697895, "percentage": 62.29, "elapsed_time": "0:57:46", "remaining_time": "0:34:58", "throughput": 10166.38, "total_tokens": 35239680}
{"current_steps": 36705, "total_steps": 58920, "loss": 0.0, "lr": 7.48111812118362e-07, "epoch": 3.114816700610998, "percentage": 62.3, "elapsed_time": "0:57:46", "remaining_time": "0:34:58", "throughput": 10166.77, "total_tokens": 35245120}
{"current_steps": 36710, "total_steps": 58920, "loss": 0.0716, "lr": 7.478251542233389e-07, "epoch": 3.1152410047522063, "percentage": 62.3, "elapsed_time": "0:57:47", "remaining_time": "0:34:57", "throughput": 10167.08, "total_tokens": 35250112}
{"current_steps": 36715, "total_steps": 58920, "loss": 0.0, "lr": 7.475385184557479e-07, "epoch": 3.1156653088934148, "percentage": 62.31, "elapsed_time": "0:57:47", "remaining_time": "0:34:57", "throughput": 10167.27, "total_tokens": 35254656}
{"current_steps": 36720, "total_steps": 58920, "loss": 0.0, "lr": 7.4725190484074e-07, "epoch": 3.116089613034623, "percentage": 62.32, "elapsed_time": "0:57:47", "remaining_time": "0:34:56", "throughput": 10167.71, "total_tokens": 35260224}
{"current_steps": 36725, "total_steps": 58920, "loss": 0.0, "lr": 7.469653134034653e-07, "epoch": 3.1165139171758316, "percentage": 62.33, "elapsed_time": "0:57:48", "remaining_time": "0:34:56", "throughput": 10168.03, "total_tokens": 35265280}
{"current_steps": 36730, "total_steps": 58920, "loss": 0.0, "lr": 7.466787441690703e-07, "epoch": 3.11693822131704, "percentage": 62.34, "elapsed_time": "0:57:48", "remaining_time": "0:34:55", "throughput": 10168.34, "total_tokens": 35270336}
{"current_steps": 36735, "total_steps": 58920, "loss": 0.0, "lr": 7.463921971627014e-07, "epoch": 3.1173625254582484, "percentage": 62.35, "elapsed_time": "0:57:49", "remaining_time": "0:34:55", "throughput": 10168.57, "total_tokens": 35275008}
{"current_steps": 36740, "total_steps": 58920, "loss": 0.021, "lr": 7.461056724095012e-07, "epoch": 3.117786829599457, "percentage": 62.36, "elapsed_time": "0:57:49", "remaining_time": "0:34:54", "throughput": 10168.8, "total_tokens": 35279680}
{"current_steps": 36745, "total_steps": 58920, "loss": 0.0, "lr": 7.458191699346119e-07, "epoch": 3.1182111337406653, "percentage": 62.36, "elapsed_time": "0:57:49", "remaining_time": "0:34:53", "throughput": 10169.08, "total_tokens": 35284544}
{"current_steps": 36750, "total_steps": 58920, "loss": 0.0, "lr": 7.455326897631722e-07, "epoch": 3.1186354378818737, "percentage": 62.37, "elapsed_time": "0:57:50", "remaining_time": "0:34:53", "throughput": 10169.36, "total_tokens": 35289408}
{"current_steps": 36755, "total_steps": 58920, "loss": 0.0, "lr": 7.452462319203207e-07, "epoch": 3.119059742023082, "percentage": 62.38, "elapsed_time": "0:57:50", "remaining_time": "0:34:52", "throughput": 10169.78, "total_tokens": 35294912}
{"current_steps": 36760, "total_steps": 58920, "loss": 0.0, "lr": 7.449597964311925e-07, "epoch": 3.1194840461642905, "percentage": 62.39, "elapsed_time": "0:57:50", "remaining_time": "0:34:52", "throughput": 10169.98, "total_tokens": 35299456}
{"current_steps": 36765, "total_steps": 58920, "loss": 0.0, "lr": 7.446733833209211e-07, "epoch": 3.119908350305499, "percentage": 62.4, "elapsed_time": "0:57:51", "remaining_time": "0:34:51", "throughput": 10170.22, "total_tokens": 35304128}
{"current_steps": 36770, "total_steps": 58920, "loss": 0.0, "lr": 7.443869926146389e-07, "epoch": 3.1203326544467074, "percentage": 62.41, "elapsed_time": "0:57:51", "remaining_time": "0:34:51", "throughput": 10170.6, "total_tokens": 35309504}
{"current_steps": 36775, "total_steps": 58920, "loss": 0.0, "lr": 7.441006243374747e-07, "epoch": 3.120756958587916, "percentage": 62.42, "elapsed_time": "0:57:52", "remaining_time": "0:34:50", "throughput": 10170.77, "total_tokens": 35313920}
{"current_steps": 36780, "total_steps": 58920, "loss": 0.0, "lr": 7.438142785145572e-07, "epoch": 3.121181262729124, "percentage": 62.42, "elapsed_time": "0:57:52", "remaining_time": "0:34:50", "throughput": 10170.89, "total_tokens": 35318080}
{"current_steps": 36785, "total_steps": 58920, "loss": 0.0, "lr": 7.435279551710114e-07, "epoch": 3.1216055668703326, "percentage": 62.43, "elapsed_time": "0:57:52", "remaining_time": "0:34:49", "throughput": 10171.1, "total_tokens": 35322624}
{"current_steps": 36790, "total_steps": 58920, "loss": 0.0554, "lr": 7.432416543319617e-07, "epoch": 3.122029871011541, "percentage": 62.44, "elapsed_time": "0:57:53", "remaining_time": "0:34:49", "throughput": 10171.49, "total_tokens": 35327936}
{"current_steps": 36795, "total_steps": 58920, "loss": 0.0, "lr": 7.429553760225297e-07, "epoch": 3.1224541751527495, "percentage": 62.45, "elapsed_time": "0:57:53", "remaining_time": "0:34:48", "throughput": 10171.78, "total_tokens": 35332864}
{"current_steps": 36800, "total_steps": 58920, "loss": 0.0, "lr": 7.42669120267836e-07, "epoch": 3.122878479293958, "percentage": 62.46, "elapsed_time": "0:57:53", "remaining_time": "0:34:48", "throughput": 10172.03, "total_tokens": 35337600}
{"current_steps": 36805, "total_steps": 58920, "loss": 0.0364, "lr": 7.423828870929976e-07, "epoch": 3.1233027834351663, "percentage": 62.47, "elapsed_time": "0:57:54", "remaining_time": "0:34:47", "throughput": 10172.18, "total_tokens": 35341888}
{"current_steps": 36810, "total_steps": 58920, "loss": 0.0002, "lr": 7.420966765231305e-07, "epoch": 3.1237270875763747, "percentage": 62.47, "elapsed_time": "0:57:54", "remaining_time": "0:34:47", "throughput": 10172.43, "total_tokens": 35346624}
{"current_steps": 36815, "total_steps": 58920, "loss": 0.0, "lr": 7.418104885833489e-07, "epoch": 3.124151391717583, "percentage": 62.48, "elapsed_time": "0:57:55", "remaining_time": "0:34:46", "throughput": 10172.86, "total_tokens": 35352256}
{"current_steps": 36820, "total_steps": 58920, "loss": 0.0, "lr": 7.415243232987649e-07, "epoch": 3.1245756958587916, "percentage": 62.49, "elapsed_time": "0:57:55", "remaining_time": "0:34:46", "throughput": 10173.16, "total_tokens": 35357184}
{"current_steps": 36825, "total_steps": 58920, "loss": 0.0, "lr": 7.412381806944881e-07, "epoch": 3.125, "percentage": 62.5, "elapsed_time": "0:57:55", "remaining_time": "0:34:45", "throughput": 10173.4, "total_tokens": 35361856}
{"current_steps": 36830, "total_steps": 58920, "loss": 0.0, "lr": 7.409520607956268e-07, "epoch": 3.1254243041412084, "percentage": 62.51, "elapsed_time": "0:57:56", "remaining_time": "0:34:45", "throughput": 10173.77, "total_tokens": 35367104}
{"current_steps": 36835, "total_steps": 58920, "loss": 0.0, "lr": 7.40665963627287e-07, "epoch": 3.125848608282417, "percentage": 62.52, "elapsed_time": "0:57:56", "remaining_time": "0:34:44", "throughput": 10173.98, "total_tokens": 35371712}
{"current_steps": 36840, "total_steps": 58920, "loss": 0.0, "lr": 7.403798892145728e-07, "epoch": 3.1262729124236253, "percentage": 62.53, "elapsed_time": "0:57:57", "remaining_time": "0:34:43", "throughput": 10174.19, "total_tokens": 35376256}
{"current_steps": 36845, "total_steps": 58920, "loss": 0.0, "lr": 7.400938375825853e-07, "epoch": 3.1266972165648337, "percentage": 62.53, "elapsed_time": "0:57:57", "remaining_time": "0:34:43", "throughput": 10174.43, "total_tokens": 35380928}
{"current_steps": 36850, "total_steps": 58920, "loss": 0.0001, "lr": 7.398078087564257e-07, "epoch": 3.127121520706042, "percentage": 62.54, "elapsed_time": "0:57:57", "remaining_time": "0:34:42", "throughput": 10174.67, "total_tokens": 35385664}
{"current_steps": 36855, "total_steps": 58920, "loss": 0.0, "lr": 7.395218027611909e-07, "epoch": 3.1275458248472505, "percentage": 62.55, "elapsed_time": "0:57:58", "remaining_time": "0:34:42", "throughput": 10174.84, "total_tokens": 35390080}
{"current_steps": 36860, "total_steps": 58920, "loss": 0.0002, "lr": 7.392358196219782e-07, "epoch": 3.127970128988459, "percentage": 62.56, "elapsed_time": "0:57:58", "remaining_time": "0:34:41", "throughput": 10175.03, "total_tokens": 35394560}
{"current_steps": 36865, "total_steps": 58920, "loss": 0.0, "lr": 7.389498593638802e-07, "epoch": 3.1283944331296674, "percentage": 62.57, "elapsed_time": "0:57:58", "remaining_time": "0:34:41", "throughput": 10175.26, "total_tokens": 35399168}
{"current_steps": 36870, "total_steps": 58920, "loss": 0.0, "lr": 7.3866392201199e-07, "epoch": 3.128818737270876, "percentage": 62.58, "elapsed_time": "0:57:59", "remaining_time": "0:34:40", "throughput": 10175.53, "total_tokens": 35404032}
{"current_steps": 36875, "total_steps": 58920, "loss": 0.0, "lr": 7.383780075913967e-07, "epoch": 3.129243041412084, "percentage": 62.58, "elapsed_time": "0:57:59", "remaining_time": "0:34:40", "throughput": 10175.83, "total_tokens": 35409024}
{"current_steps": 36880, "total_steps": 58920, "loss": 0.0065, "lr": 7.380921161271889e-07, "epoch": 3.1296673455532926, "percentage": 62.59, "elapsed_time": "0:58:00", "remaining_time": "0:34:39", "throughput": 10176.02, "total_tokens": 35413504}
{"current_steps": 36885, "total_steps": 58920, "loss": 0.0, "lr": 7.378062476444525e-07, "epoch": 3.130091649694501, "percentage": 62.6, "elapsed_time": "0:58:00", "remaining_time": "0:34:39", "throughput": 10176.28, "total_tokens": 35418304}
{"current_steps": 36890, "total_steps": 58920, "loss": 0.0, "lr": 7.375204021682706e-07, "epoch": 3.1305159538357095, "percentage": 62.61, "elapsed_time": "0:58:00", "remaining_time": "0:34:38", "throughput": 10176.54, "total_tokens": 35423040}
{"current_steps": 36895, "total_steps": 58920, "loss": 0.0, "lr": 7.372345797237264e-07, "epoch": 3.130940257976918, "percentage": 62.62, "elapsed_time": "0:58:01", "remaining_time": "0:34:38", "throughput": 10176.74, "total_tokens": 35427584}
{"current_steps": 36900, "total_steps": 58920, "loss": 0.0, "lr": 7.369487803358986e-07, "epoch": 3.1313645621181263, "percentage": 62.63, "elapsed_time": "0:58:01", "remaining_time": "0:34:37", "throughput": 10176.91, "total_tokens": 35432000}
{"current_steps": 36905, "total_steps": 58920, "loss": 0.0, "lr": 7.36663004029866e-07, "epoch": 3.1317888662593347, "percentage": 62.64, "elapsed_time": "0:58:01", "remaining_time": "0:34:37", "throughput": 10177.15, "total_tokens": 35436736}
{"current_steps": 36910, "total_steps": 58920, "loss": 0.0, "lr": 7.363772508307035e-07, "epoch": 3.132213170400543, "percentage": 62.64, "elapsed_time": "0:58:02", "remaining_time": "0:34:36", "throughput": 10177.35, "total_tokens": 35441280}
{"current_steps": 36915, "total_steps": 58920, "loss": 0.0, "lr": 7.360915207634858e-07, "epoch": 3.1326374745417516, "percentage": 62.65, "elapsed_time": "0:58:02", "remaining_time": "0:34:36", "throughput": 10177.59, "total_tokens": 35445952}
{"current_steps": 36920, "total_steps": 58920, "loss": 0.0, "lr": 7.358058138532841e-07, "epoch": 3.13306177868296, "percentage": 62.66, "elapsed_time": "0:58:03", "remaining_time": "0:34:35", "throughput": 10177.83, "total_tokens": 35450624}
{"current_steps": 36925, "total_steps": 58920, "loss": 0.0, "lr": 7.355201301251688e-07, "epoch": 3.1334860828241684, "percentage": 62.67, "elapsed_time": "0:58:03", "remaining_time": "0:34:35", "throughput": 10178.1, "total_tokens": 35455552}
{"current_steps": 36930, "total_steps": 58920, "loss": 0.0, "lr": 7.35234469604207e-07, "epoch": 3.133910386965377, "percentage": 62.68, "elapsed_time": "0:58:03", "remaining_time": "0:34:34", "throughput": 10178.35, "total_tokens": 35460288}
{"current_steps": 36935, "total_steps": 58920, "loss": 0.0, "lr": 7.349488323154642e-07, "epoch": 3.1343346911065852, "percentage": 62.69, "elapsed_time": "0:58:04", "remaining_time": "0:34:33", "throughput": 10178.52, "total_tokens": 35464704}
{"current_steps": 36940, "total_steps": 58920, "loss": 0.0007, "lr": 7.346632182840048e-07, "epoch": 3.1347589952477937, "percentage": 62.7, "elapsed_time": "0:58:04", "remaining_time": "0:34:33", "throughput": 10178.72, "total_tokens": 35469248}
{"current_steps": 36945, "total_steps": 58920, "loss": 0.0, "lr": 7.343776275348896e-07, "epoch": 3.135183299389002, "percentage": 62.7, "elapsed_time": "0:58:05", "remaining_time": "0:34:32", "throughput": 10179.08, "total_tokens": 35474560}
{"current_steps": 36950, "total_steps": 58920, "loss": 0.0001, "lr": 7.34092060093179e-07, "epoch": 3.1356076035302105, "percentage": 62.71, "elapsed_time": "0:58:05", "remaining_time": "0:34:32", "throughput": 10179.42, "total_tokens": 35479744}
{"current_steps": 36955, "total_steps": 58920, "loss": 0.0, "lr": 7.338065159839298e-07, "epoch": 3.136031907671419, "percentage": 62.72, "elapsed_time": "0:58:05", "remaining_time": "0:34:31", "throughput": 10179.65, "total_tokens": 35484416}
{"current_steps": 36960, "total_steps": 58920, "loss": 0.0, "lr": 7.33520995232198e-07, "epoch": 3.1364562118126273, "percentage": 62.73, "elapsed_time": "0:58:06", "remaining_time": "0:34:31", "throughput": 10179.98, "total_tokens": 35489536}
{"current_steps": 36965, "total_steps": 58920, "loss": 0.0, "lr": 7.332354978630364e-07, "epoch": 3.1368805159538358, "percentage": 62.74, "elapsed_time": "0:58:06", "remaining_time": "0:34:30", "throughput": 10180.17, "total_tokens": 35494016}
{"current_steps": 36970, "total_steps": 58920, "loss": 0.0, "lr": 7.329500239014972e-07, "epoch": 3.137304820095044, "percentage": 62.75, "elapsed_time": "0:58:06", "remaining_time": "0:34:30", "throughput": 10180.45, "total_tokens": 35498880}
{"current_steps": 36975, "total_steps": 58920, "loss": 0.0, "lr": 7.326645733726289e-07, "epoch": 3.1377291242362526, "percentage": 62.75, "elapsed_time": "0:58:07", "remaining_time": "0:34:29", "throughput": 10180.72, "total_tokens": 35503744}
{"current_steps": 36980, "total_steps": 58920, "loss": 0.0, "lr": 7.323791463014787e-07, "epoch": 3.138153428377461, "percentage": 62.76, "elapsed_time": "0:58:07", "remaining_time": "0:34:29", "throughput": 10180.93, "total_tokens": 35508288}
{"current_steps": 36985, "total_steps": 58920, "loss": 0.0001, "lr": 7.320937427130929e-07, "epoch": 3.1385777325186694, "percentage": 62.77, "elapsed_time": "0:58:08", "remaining_time": "0:34:28", "throughput": 10181.18, "total_tokens": 35513088}
{"current_steps": 36990, "total_steps": 58920, "loss": 0.0, "lr": 7.318083626325134e-07, "epoch": 3.139002036659878, "percentage": 62.78, "elapsed_time": "0:58:08", "remaining_time": "0:34:28", "throughput": 10181.39, "total_tokens": 35517632}
{"current_steps": 36995, "total_steps": 58920, "loss": 0.0141, "lr": 7.315230060847821e-07, "epoch": 3.1394263408010863, "percentage": 62.79, "elapsed_time": "0:58:08", "remaining_time": "0:34:27", "throughput": 10181.68, "total_tokens": 35522624}
{"current_steps": 37000, "total_steps": 58920, "loss": 0.0, "lr": 7.312376730949373e-07, "epoch": 3.1398506449422947, "percentage": 62.8, "elapsed_time": "0:58:09", "remaining_time": "0:34:27", "throughput": 10182.2, "total_tokens": 35528640}
{"current_steps": 37005, "total_steps": 58920, "loss": 0.0, "lr": 7.309523636880166e-07, "epoch": 3.140274949083503, "percentage": 62.81, "elapsed_time": "0:58:09", "remaining_time": "0:34:26", "throughput": 10182.55, "total_tokens": 35533888}
{"current_steps": 37010, "total_steps": 58920, "loss": 0.0, "lr": 7.306670778890547e-07, "epoch": 3.1406992532247116, "percentage": 62.81, "elapsed_time": "0:58:10", "remaining_time": "0:34:26", "throughput": 10182.9, "total_tokens": 35539072}
{"current_steps": 37015, "total_steps": 58920, "loss": 0.0, "lr": 7.30381815723084e-07, "epoch": 3.14112355736592, "percentage": 62.82, "elapsed_time": "0:58:10", "remaining_time": "0:34:25", "throughput": 10183.06, "total_tokens": 35543424}
{"current_steps": 37020, "total_steps": 58920, "loss": 0.0, "lr": 7.300965772151359e-07, "epoch": 3.1415478615071284, "percentage": 62.83, "elapsed_time": "0:58:10", "remaining_time": "0:34:25", "throughput": 10183.35, "total_tokens": 35548352}
{"current_steps": 37025, "total_steps": 58920, "loss": 0.0004, "lr": 7.298113623902383e-07, "epoch": 3.141972165648337, "percentage": 62.84, "elapsed_time": "0:58:11", "remaining_time": "0:34:24", "throughput": 10183.78, "total_tokens": 35553984}
{"current_steps": 37030, "total_steps": 58920, "loss": 0.0, "lr": 7.295261712734182e-07, "epoch": 3.1423964697895452, "percentage": 62.85, "elapsed_time": "0:58:11", "remaining_time": "0:34:24", "throughput": 10183.98, "total_tokens": 35558528}
{"current_steps": 37035, "total_steps": 58920, "loss": 0.0, "lr": 7.292410038897001e-07, "epoch": 3.1428207739307537, "percentage": 62.86, "elapsed_time": "0:58:11", "remaining_time": "0:34:23", "throughput": 10184.2, "total_tokens": 35563200}
{"current_steps": 37040, "total_steps": 58920, "loss": 0.0, "lr": 7.289558602641063e-07, "epoch": 3.143245078071962, "percentage": 62.86, "elapsed_time": "0:58:12", "remaining_time": "0:34:22", "throughput": 10184.46, "total_tokens": 35567936}
{"current_steps": 37045, "total_steps": 58920, "loss": 0.0003, "lr": 7.28670740421657e-07, "epoch": 3.1436693822131705, "percentage": 62.87, "elapsed_time": "0:58:12", "remaining_time": "0:34:22", "throughput": 10184.78, "total_tokens": 35573056}
{"current_steps": 37050, "total_steps": 58920, "loss": 0.0, "lr": 7.283856443873709e-07, "epoch": 3.144093686354379, "percentage": 62.88, "elapsed_time": "0:58:13", "remaining_time": "0:34:21", "throughput": 10184.97, "total_tokens": 35577600}
{"current_steps": 37055, "total_steps": 58920, "loss": 0.0, "lr": 7.28100572186264e-07, "epoch": 3.1445179904955873, "percentage": 62.89, "elapsed_time": "0:58:13", "remaining_time": "0:34:21", "throughput": 10185.19, "total_tokens": 35582208}
{"current_steps": 37060, "total_steps": 58920, "loss": 0.0, "lr": 7.278155238433497e-07, "epoch": 3.1449422946367958, "percentage": 62.9, "elapsed_time": "0:58:13", "remaining_time": "0:34:20", "throughput": 10185.37, "total_tokens": 35586688}
{"current_steps": 37065, "total_steps": 58920, "loss": 0.0093, "lr": 7.275304993836407e-07, "epoch": 3.145366598778004, "percentage": 62.91, "elapsed_time": "0:58:14", "remaining_time": "0:34:20", "throughput": 10185.77, "total_tokens": 35592128}
{"current_steps": 37070, "total_steps": 58920, "loss": 0.0, "lr": 7.272454988321464e-07, "epoch": 3.1457909029192126, "percentage": 62.92, "elapsed_time": "0:58:14", "remaining_time": "0:34:19", "throughput": 10186.05, "total_tokens": 35597056}
{"current_steps": 37075, "total_steps": 58920, "loss": 0.0, "lr": 7.269605222138753e-07, "epoch": 3.146215207060421, "percentage": 62.92, "elapsed_time": "0:58:15", "remaining_time": "0:34:19", "throughput": 10186.22, "total_tokens": 35601536}
{"current_steps": 37080, "total_steps": 58920, "loss": 0.0, "lr": 7.26675569553832e-07, "epoch": 3.1466395112016294, "percentage": 62.93, "elapsed_time": "0:58:15", "remaining_time": "0:34:18", "throughput": 10186.58, "total_tokens": 35606784}
{"current_steps": 37085, "total_steps": 58920, "loss": 0.0, "lr": 7.263906408770213e-07, "epoch": 3.147063815342838, "percentage": 62.94, "elapsed_time": "0:58:15", "remaining_time": "0:34:18", "throughput": 10186.77, "total_tokens": 35611264}
{"current_steps": 37090, "total_steps": 58920, "loss": 0.0, "lr": 7.261057362084433e-07, "epoch": 3.1474881194840463, "percentage": 62.95, "elapsed_time": "0:58:16", "remaining_time": "0:34:17", "throughput": 10187.06, "total_tokens": 35616192}
{"current_steps": 37095, "total_steps": 58920, "loss": 0.0, "lr": 7.258208555730984e-07, "epoch": 3.1479124236252547, "percentage": 62.96, "elapsed_time": "0:58:16", "remaining_time": "0:34:17", "throughput": 10187.36, "total_tokens": 35621184}
{"current_steps": 37100, "total_steps": 58920, "loss": 0.0, "lr": 7.255359989959838e-07, "epoch": 3.148336727766463, "percentage": 62.97, "elapsed_time": "0:58:16", "remaining_time": "0:34:16", "throughput": 10187.54, "total_tokens": 35625600}
{"current_steps": 37105, "total_steps": 58920, "loss": 0.0, "lr": 7.252511665020939e-07, "epoch": 3.1487610319076715, "percentage": 62.98, "elapsed_time": "0:58:17", "remaining_time": "0:34:16", "throughput": 10187.78, "total_tokens": 35630336}
{"current_steps": 37110, "total_steps": 58920, "loss": 0.0, "lr": 7.249663581164224e-07, "epoch": 3.14918533604888, "percentage": 62.98, "elapsed_time": "0:58:17", "remaining_time": "0:34:15", "throughput": 10188.04, "total_tokens": 35635072}
{"current_steps": 37115, "total_steps": 58920, "loss": 0.0, "lr": 7.246815738639598e-07, "epoch": 3.1496096401900884, "percentage": 62.99, "elapsed_time": "0:58:18", "remaining_time": "0:34:15", "throughput": 10189.01, "total_tokens": 35643392}
{"current_steps": 37120, "total_steps": 58920, "loss": 0.0, "lr": 7.243968137696952e-07, "epoch": 3.150033944331297, "percentage": 63.0, "elapsed_time": "0:58:18", "remaining_time": "0:34:14", "throughput": 10189.19, "total_tokens": 35647808}
{"current_steps": 37125, "total_steps": 58920, "loss": 0.0014, "lr": 7.241120778586149e-07, "epoch": 3.150458248472505, "percentage": 63.01, "elapsed_time": "0:58:18", "remaining_time": "0:34:14", "throughput": 10189.46, "total_tokens": 35652608}
{"current_steps": 37130, "total_steps": 58920, "loss": 0.0, "lr": 7.238273661557039e-07, "epoch": 3.1508825526137136, "percentage": 63.02, "elapsed_time": "0:58:19", "remaining_time": "0:34:13", "throughput": 10189.73, "total_tokens": 35657472}
{"current_steps": 37135, "total_steps": 58920, "loss": 0.0, "lr": 7.235426786859445e-07, "epoch": 3.151306856754922, "percentage": 63.03, "elapsed_time": "0:58:19", "remaining_time": "0:34:13", "throughput": 10189.85, "total_tokens": 35661632}
{"current_steps": 37140, "total_steps": 58920, "loss": 0.0, "lr": 7.232580154743166e-07, "epoch": 3.1517311608961305, "percentage": 63.03, "elapsed_time": "0:58:20", "remaining_time": "0:34:12", "throughput": 10190.12, "total_tokens": 35666432}
{"current_steps": 37145, "total_steps": 58920, "loss": 0.0, "lr": 7.22973376545799e-07, "epoch": 3.152155465037339, "percentage": 63.04, "elapsed_time": "0:58:20", "remaining_time": "0:34:12", "throughput": 10190.32, "total_tokens": 35671040}
{"current_steps": 37150, "total_steps": 58920, "loss": 0.0, "lr": 7.22688761925367e-07, "epoch": 3.1525797691785473, "percentage": 63.05, "elapsed_time": "0:58:20", "remaining_time": "0:34:11", "throughput": 10190.59, "total_tokens": 35675840}
{"current_steps": 37155, "total_steps": 58920, "loss": 0.0279, "lr": 7.224041716379951e-07, "epoch": 3.1530040733197557, "percentage": 63.06, "elapsed_time": "0:58:21", "remaining_time": "0:34:11", "throughput": 10191.06, "total_tokens": 35681600}
{"current_steps": 37160, "total_steps": 58920, "loss": 0.0, "lr": 7.221196057086547e-07, "epoch": 3.153428377460964, "percentage": 63.07, "elapsed_time": "0:58:21", "remaining_time": "0:34:10", "throughput": 10191.5, "total_tokens": 35687296}
{"current_steps": 37165, "total_steps": 58920, "loss": 0.0, "lr": 7.218350641623161e-07, "epoch": 3.1538526816021726, "percentage": 63.08, "elapsed_time": "0:58:22", "remaining_time": "0:34:09", "throughput": 10191.76, "total_tokens": 35692096}
{"current_steps": 37170, "total_steps": 58920, "loss": 0.0, "lr": 7.215505470239458e-07, "epoch": 3.154276985743381, "percentage": 63.09, "elapsed_time": "0:58:22", "remaining_time": "0:34:09", "throughput": 10191.95, "total_tokens": 35696640}
{"current_steps": 37175, "total_steps": 58920, "loss": 0.0244, "lr": 7.212660543185102e-07, "epoch": 3.1547012898845894, "percentage": 63.09, "elapsed_time": "0:58:22", "remaining_time": "0:34:08", "throughput": 10192.24, "total_tokens": 35701568}
{"current_steps": 37180, "total_steps": 58920, "loss": 0.0001, "lr": 7.209815860709716e-07, "epoch": 3.155125594025798, "percentage": 63.1, "elapsed_time": "0:58:23", "remaining_time": "0:34:08", "throughput": 10192.42, "total_tokens": 35706048}
{"current_steps": 37185, "total_steps": 58920, "loss": 0.0, "lr": 7.206971423062915e-07, "epoch": 3.1555498981670063, "percentage": 63.11, "elapsed_time": "0:58:23", "remaining_time": "0:34:07", "throughput": 10192.81, "total_tokens": 35711424}
{"current_steps": 37190, "total_steps": 58920, "loss": 0.0, "lr": 7.204127230494288e-07, "epoch": 3.1559742023082147, "percentage": 63.12, "elapsed_time": "0:58:23", "remaining_time": "0:34:07", "throughput": 10193.08, "total_tokens": 35716288}
{"current_steps": 37195, "total_steps": 58920, "loss": 0.0, "lr": 7.201283283253399e-07, "epoch": 3.156398506449423, "percentage": 63.13, "elapsed_time": "0:58:24", "remaining_time": "0:34:06", "throughput": 10193.32, "total_tokens": 35721024}
{"current_steps": 37200, "total_steps": 58920, "loss": 0.0, "lr": 7.198439581589802e-07, "epoch": 3.1568228105906315, "percentage": 63.14, "elapsed_time": "0:58:24", "remaining_time": "0:34:06", "throughput": 10193.48, "total_tokens": 35725376}
{"current_steps": 37205, "total_steps": 58920, "loss": 0.0, "lr": 7.195596125753013e-07, "epoch": 3.15724711473184, "percentage": 63.14, "elapsed_time": "0:58:25", "remaining_time": "0:34:05", "throughput": 10193.67, "total_tokens": 35729856}
{"current_steps": 37210, "total_steps": 58920, "loss": 0.0, "lr": 7.192752915992542e-07, "epoch": 3.1576714188730484, "percentage": 63.15, "elapsed_time": "0:58:25", "remaining_time": "0:34:05", "throughput": 10193.77, "total_tokens": 35733952}
{"current_steps": 37215, "total_steps": 58920, "loss": 0.0237, "lr": 7.189909952557863e-07, "epoch": 3.158095723014257, "percentage": 63.16, "elapsed_time": "0:58:25", "remaining_time": "0:34:04", "throughput": 10194.04, "total_tokens": 35738816}
{"current_steps": 37220, "total_steps": 58920, "loss": 0.0, "lr": 7.187067235698443e-07, "epoch": 3.158520027155465, "percentage": 63.17, "elapsed_time": "0:58:26", "remaining_time": "0:34:04", "throughput": 10194.18, "total_tokens": 35743104}
{"current_steps": 37225, "total_steps": 58920, "loss": 0.0, "lr": 7.184224765663717e-07, "epoch": 3.1589443312966736, "percentage": 63.18, "elapsed_time": "0:58:26", "remaining_time": "0:34:03", "throughput": 10194.32, "total_tokens": 35747392}
{"current_steps": 37230, "total_steps": 58920, "loss": 0.0, "lr": 7.181382542703098e-07, "epoch": 3.159368635437882, "percentage": 63.19, "elapsed_time": "0:58:26", "remaining_time": "0:34:03", "throughput": 10194.6, "total_tokens": 35752320}
{"current_steps": 37235, "total_steps": 58920, "loss": 0.0174, "lr": 7.178540567065989e-07, "epoch": 3.1597929395790905, "percentage": 63.2, "elapsed_time": "0:58:27", "remaining_time": "0:34:02", "throughput": 10194.75, "total_tokens": 35756608}
{"current_steps": 37240, "total_steps": 58920, "loss": 0.0, "lr": 7.175698839001756e-07, "epoch": 3.160217243720299, "percentage": 63.2, "elapsed_time": "0:58:27", "remaining_time": "0:34:02", "throughput": 10195.08, "total_tokens": 35761728}
{"current_steps": 37245, "total_steps": 58920, "loss": 0.0, "lr": 7.172857358759751e-07, "epoch": 3.1606415478615073, "percentage": 63.21, "elapsed_time": "0:58:28", "remaining_time": "0:34:01", "throughput": 10195.4, "total_tokens": 35766848}
{"current_steps": 37250, "total_steps": 58920, "loss": 0.0, "lr": 7.170016126589309e-07, "epoch": 3.1610658520027157, "percentage": 63.22, "elapsed_time": "0:58:28", "remaining_time": "0:34:01", "throughput": 10195.58, "total_tokens": 35771264}
{"current_steps": 37255, "total_steps": 58920, "loss": 0.0, "lr": 7.167175142739732e-07, "epoch": 3.161490156143924, "percentage": 63.23, "elapsed_time": "0:58:28", "remaining_time": "0:34:00", "throughput": 10195.83, "total_tokens": 35776064}
{"current_steps": 37260, "total_steps": 58920, "loss": 0.0, "lr": 7.164334407460312e-07, "epoch": 3.1619144602851326, "percentage": 63.24, "elapsed_time": "0:58:29", "remaining_time": "0:34:00", "throughput": 10196.07, "total_tokens": 35780800}
{"current_steps": 37265, "total_steps": 58920, "loss": 0.0, "lr": 7.161493921000305e-07, "epoch": 3.162338764426341, "percentage": 63.25, "elapsed_time": "0:58:29", "remaining_time": "0:33:59", "throughput": 10196.33, "total_tokens": 35785664}
{"current_steps": 37270, "total_steps": 58920, "loss": 0.0, "lr": 7.158653683608962e-07, "epoch": 3.1627630685675494, "percentage": 63.26, "elapsed_time": "0:58:30", "remaining_time": "0:33:58", "throughput": 10196.78, "total_tokens": 35791424}
{"current_steps": 37275, "total_steps": 58920, "loss": 0.0, "lr": 7.155813695535495e-07, "epoch": 3.163187372708758, "percentage": 63.26, "elapsed_time": "0:58:30", "remaining_time": "0:33:58", "throughput": 10197.02, "total_tokens": 35796160}
{"current_steps": 37280, "total_steps": 58920, "loss": 0.0, "lr": 7.15297395702911e-07, "epoch": 3.1636116768499662, "percentage": 63.27, "elapsed_time": "0:58:30", "remaining_time": "0:33:57", "throughput": 10197.29, "total_tokens": 35801024}
{"current_steps": 37285, "total_steps": 58920, "loss": 0.0, "lr": 7.150134468338979e-07, "epoch": 3.1640359809911747, "percentage": 63.28, "elapsed_time": "0:58:31", "remaining_time": "0:33:57", "throughput": 10197.52, "total_tokens": 35805696}
{"current_steps": 37290, "total_steps": 58920, "loss": 0.0, "lr": 7.147295229714263e-07, "epoch": 3.164460285132383, "percentage": 63.29, "elapsed_time": "0:58:31", "remaining_time": "0:33:56", "throughput": 10197.79, "total_tokens": 35810560}
{"current_steps": 37295, "total_steps": 58920, "loss": 0.0, "lr": 7.144456241404086e-07, "epoch": 3.1648845892735915, "percentage": 63.3, "elapsed_time": "0:58:31", "remaining_time": "0:33:56", "throughput": 10198.02, "total_tokens": 35815168}
{"current_steps": 37300, "total_steps": 58920, "loss": 0.0, "lr": 7.141617503657569e-07, "epoch": 3.1653088934148, "percentage": 63.31, "elapsed_time": "0:58:32", "remaining_time": "0:33:55", "throughput": 10198.24, "total_tokens": 35819840}
{"current_steps": 37305, "total_steps": 58920, "loss": 0.0, "lr": 7.138779016723794e-07, "epoch": 3.1657331975560083, "percentage": 63.31, "elapsed_time": "0:58:32", "remaining_time": "0:33:55", "throughput": 10198.53, "total_tokens": 35824768}
{"current_steps": 37310, "total_steps": 58920, "loss": 0.0, "lr": 7.135940780851828e-07, "epoch": 3.1661575016972168, "percentage": 63.32, "elapsed_time": "0:58:33", "remaining_time": "0:33:54", "throughput": 10198.82, "total_tokens": 35829696}
{"current_steps": 37315, "total_steps": 58920, "loss": 0.0, "lr": 7.133102796290721e-07, "epoch": 3.166581805838425, "percentage": 63.33, "elapsed_time": "0:58:33", "remaining_time": "0:33:54", "throughput": 10199.13, "total_tokens": 35834752}
{"current_steps": 37320, "total_steps": 58920, "loss": 0.0038, "lr": 7.130265063289488e-07, "epoch": 3.167006109979633, "percentage": 63.34, "elapsed_time": "0:58:33", "remaining_time": "0:33:53", "throughput": 10199.46, "total_tokens": 35839872}
{"current_steps": 37325, "total_steps": 58920, "loss": 0.0, "lr": 7.127427582097141e-07, "epoch": 3.167430414120842, "percentage": 63.35, "elapsed_time": "0:58:34", "remaining_time": "0:33:53", "throughput": 10199.64, "total_tokens": 35844352}
{"current_steps": 37330, "total_steps": 58920, "loss": 0.0, "lr": 7.124590352962646e-07, "epoch": 3.16785471826205, "percentage": 63.36, "elapsed_time": "0:58:34", "remaining_time": "0:33:52", "throughput": 10200.02, "total_tokens": 35849728}
{"current_steps": 37335, "total_steps": 58920, "loss": 0.0, "lr": 7.121753376134971e-07, "epoch": 3.168279022403259, "percentage": 63.37, "elapsed_time": "0:58:35", "remaining_time": "0:33:52", "throughput": 10200.16, "total_tokens": 35854016}
{"current_steps": 37340, "total_steps": 58920, "loss": 0.0, "lr": 7.11891665186304e-07, "epoch": 3.168703326544467, "percentage": 63.37, "elapsed_time": "0:58:35", "remaining_time": "0:33:51", "throughput": 10200.4, "total_tokens": 35858752}
{"current_steps": 37345, "total_steps": 58920, "loss": 0.0, "lr": 7.116080180395776e-07, "epoch": 3.1691276306856757, "percentage": 63.38, "elapsed_time": "0:58:35", "remaining_time": "0:33:51", "throughput": 10200.53, "total_tokens": 35862976}
{"current_steps": 37350, "total_steps": 58920, "loss": 0.0, "lr": 7.113243961982063e-07, "epoch": 3.1695519348268837, "percentage": 63.39, "elapsed_time": "0:58:36", "remaining_time": "0:33:50", "throughput": 10200.9, "total_tokens": 35868288}
{"current_steps": 37355, "total_steps": 58920, "loss": 0.0, "lr": 7.110407996870766e-07, "epoch": 3.1699762389680926, "percentage": 63.4, "elapsed_time": "0:58:36", "remaining_time": "0:33:50", "throughput": 10201.03, "total_tokens": 35872576}
{"current_steps": 37360, "total_steps": 58920, "loss": 0.0, "lr": 7.107572285310739e-07, "epoch": 3.1704005431093005, "percentage": 63.41, "elapsed_time": "0:58:36", "remaining_time": "0:33:49", "throughput": 10201.37, "total_tokens": 35877760}
{"current_steps": 37365, "total_steps": 58920, "loss": 0.0, "lr": 7.104736827550797e-07, "epoch": 3.1708248472505094, "percentage": 63.42, "elapsed_time": "0:58:37", "remaining_time": "0:33:49", "throughput": 10201.6, "total_tokens": 35882432}
{"current_steps": 37370, "total_steps": 58920, "loss": 0.0, "lr": 7.101901623839747e-07, "epoch": 3.1712491513917174, "percentage": 63.42, "elapsed_time": "0:58:37", "remaining_time": "0:33:48", "throughput": 10201.74, "total_tokens": 35886720}
{"current_steps": 37375, "total_steps": 58920, "loss": 0.0, "lr": 7.099066674426364e-07, "epoch": 3.1716734555329262, "percentage": 63.43, "elapsed_time": "0:58:38", "remaining_time": "0:33:48", "throughput": 10201.98, "total_tokens": 35891456}
{"current_steps": 37380, "total_steps": 58920, "loss": 0.0, "lr": 7.096231979559411e-07, "epoch": 3.172097759674134, "percentage": 63.44, "elapsed_time": "0:58:38", "remaining_time": "0:33:47", "throughput": 10202.28, "total_tokens": 35896448}
{"current_steps": 37385, "total_steps": 58920, "loss": 0.0325, "lr": 7.093397539487616e-07, "epoch": 3.1725220638153426, "percentage": 63.45, "elapsed_time": "0:58:38", "remaining_time": "0:33:46", "throughput": 10202.43, "total_tokens": 35900800}
{"current_steps": 37390, "total_steps": 58920, "loss": 0.0, "lr": 7.090563354459691e-07, "epoch": 3.172946367956551, "percentage": 63.46, "elapsed_time": "0:58:39", "remaining_time": "0:33:46", "throughput": 10202.6, "total_tokens": 35905216}
{"current_steps": 37395, "total_steps": 58920, "loss": 0.0, "lr": 7.087729424724327e-07, "epoch": 3.1733706720977595, "percentage": 63.47, "elapsed_time": "0:58:39", "remaining_time": "0:33:45", "throughput": 10202.76, "total_tokens": 35909568}
{"current_steps": 37400, "total_steps": 58920, "loss": 0.0, "lr": 7.084895750530193e-07, "epoch": 3.173794976238968, "percentage": 63.48, "elapsed_time": "0:58:39", "remaining_time": "0:33:45", "throughput": 10203.05, "total_tokens": 35914560}
{"current_steps": 37405, "total_steps": 58920, "loss": 0.0417, "lr": 7.082062332125931e-07, "epoch": 3.1742192803801763, "percentage": 63.48, "elapsed_time": "0:58:40", "remaining_time": "0:33:44", "throughput": 10203.4, "total_tokens": 35919744}
{"current_steps": 37410, "total_steps": 58920, "loss": 0.0007, "lr": 7.079229169760162e-07, "epoch": 3.1746435845213847, "percentage": 63.49, "elapsed_time": "0:58:40", "remaining_time": "0:33:44", "throughput": 10203.75, "total_tokens": 35924928}
{"current_steps": 37415, "total_steps": 58920, "loss": 0.0, "lr": 7.076396263681492e-07, "epoch": 3.175067888662593, "percentage": 63.5, "elapsed_time": "0:58:41", "remaining_time": "0:33:43", "throughput": 10203.91, "total_tokens": 35929344}
{"current_steps": 37420, "total_steps": 58920, "loss": 0.0, "lr": 7.073563614138492e-07, "epoch": 3.1754921928038016, "percentage": 63.51, "elapsed_time": "0:58:41", "remaining_time": "0:33:43", "throughput": 10204.11, "total_tokens": 35933888}
{"current_steps": 37425, "total_steps": 58920, "loss": 0.0, "lr": 7.070731221379721e-07, "epoch": 3.17591649694501, "percentage": 63.52, "elapsed_time": "0:58:41", "remaining_time": "0:33:42", "throughput": 10204.29, "total_tokens": 35938304}
{"current_steps": 37430, "total_steps": 58920, "loss": 0.0, "lr": 7.067899085653708e-07, "epoch": 3.1763408010862184, "percentage": 63.53, "elapsed_time": "0:58:42", "remaining_time": "0:33:42", "throughput": 10204.57, "total_tokens": 35943232}
{"current_steps": 37435, "total_steps": 58920, "loss": 0.0, "lr": 7.065067207208961e-07, "epoch": 3.176765105227427, "percentage": 63.54, "elapsed_time": "0:58:42", "remaining_time": "0:33:41", "throughput": 10204.81, "total_tokens": 35948032}
{"current_steps": 37440, "total_steps": 58920, "loss": 0.0, "lr": 7.062235586293976e-07, "epoch": 3.1771894093686353, "percentage": 63.54, "elapsed_time": "0:58:43", "remaining_time": "0:33:41", "throughput": 10205.03, "total_tokens": 35952640}
{"current_steps": 37445, "total_steps": 58920, "loss": 0.0, "lr": 7.059404223157206e-07, "epoch": 3.1776137135098437, "percentage": 63.55, "elapsed_time": "0:58:43", "remaining_time": "0:33:40", "throughput": 10205.26, "total_tokens": 35957312}
{"current_steps": 37450, "total_steps": 58920, "loss": 0.0, "lr": 7.056573118047102e-07, "epoch": 3.178038017651052, "percentage": 63.56, "elapsed_time": "0:58:43", "remaining_time": "0:33:40", "throughput": 10205.53, "total_tokens": 35962176}
{"current_steps": 37455, "total_steps": 58920, "loss": 0.0, "lr": 7.053742271212077e-07, "epoch": 3.1784623217922605, "percentage": 63.57, "elapsed_time": "0:58:44", "remaining_time": "0:33:39", "throughput": 10205.78, "total_tokens": 35966912}
{"current_steps": 37460, "total_steps": 58920, "loss": 0.0, "lr": 7.050911682900532e-07, "epoch": 3.178886625933469, "percentage": 63.58, "elapsed_time": "0:58:44", "remaining_time": "0:33:39", "throughput": 10205.89, "total_tokens": 35971072}
{"current_steps": 37465, "total_steps": 58920, "loss": 0.0, "lr": 7.048081353360839e-07, "epoch": 3.1793109300746774, "percentage": 63.59, "elapsed_time": "0:58:44", "remaining_time": "0:33:38", "throughput": 10206.17, "total_tokens": 35976064}
{"current_steps": 37470, "total_steps": 58920, "loss": 0.0, "lr": 7.04525128284135e-07, "epoch": 3.1797352342158858, "percentage": 63.59, "elapsed_time": "0:58:45", "remaining_time": "0:33:38", "throughput": 10206.38, "total_tokens": 35980672}
{"current_steps": 37475, "total_steps": 58920, "loss": 0.0, "lr": 7.042421471590394e-07, "epoch": 3.180159538357094, "percentage": 63.6, "elapsed_time": "0:58:45", "remaining_time": "0:33:37", "throughput": 10206.56, "total_tokens": 35985152}
{"current_steps": 37480, "total_steps": 58920, "loss": 0.0, "lr": 7.039591919856272e-07, "epoch": 3.1805838424983026, "percentage": 63.61, "elapsed_time": "0:58:46", "remaining_time": "0:33:37", "throughput": 10206.79, "total_tokens": 35989824}
{"current_steps": 37485, "total_steps": 58920, "loss": 0.0, "lr": 7.036762627887273e-07, "epoch": 3.181008146639511, "percentage": 63.62, "elapsed_time": "0:58:46", "remaining_time": "0:33:36", "throughput": 10207.09, "total_tokens": 35994816}
{"current_steps": 37490, "total_steps": 58920, "loss": 0.0, "lr": 7.033933595931653e-07, "epoch": 3.1814324507807195, "percentage": 63.63, "elapsed_time": "0:58:46", "remaining_time": "0:33:36", "throughput": 10207.43, "total_tokens": 36000000}
{"current_steps": 37495, "total_steps": 58920, "loss": 0.0, "lr": 7.031104824237652e-07, "epoch": 3.181856754921928, "percentage": 63.64, "elapsed_time": "0:58:47", "remaining_time": "0:33:35", "throughput": 10207.78, "total_tokens": 36005248}
{"current_steps": 37500, "total_steps": 58920, "loss": 0.0324, "lr": 7.028276313053481e-07, "epoch": 3.1822810590631363, "percentage": 63.65, "elapsed_time": "0:58:47", "remaining_time": "0:33:34", "throughput": 10208.03, "total_tokens": 36010048}
{"current_steps": 37505, "total_steps": 58920, "loss": 0.0, "lr": 7.025448062627339e-07, "epoch": 3.1827053632043447, "percentage": 63.65, "elapsed_time": "0:58:47", "remaining_time": "0:33:34", "throughput": 10208.26, "total_tokens": 36014720}
{"current_steps": 37510, "total_steps": 58920, "loss": 0.0001, "lr": 7.022620073207389e-07, "epoch": 3.183129667345553, "percentage": 63.66, "elapsed_time": "0:58:48", "remaining_time": "0:33:33", "throughput": 10208.47, "total_tokens": 36019264}
{"current_steps": 37515, "total_steps": 58920, "loss": 0.0, "lr": 7.019792345041775e-07, "epoch": 3.1835539714867616, "percentage": 63.67, "elapsed_time": "0:58:48", "remaining_time": "0:33:33", "throughput": 10208.72, "total_tokens": 36024000}
{"current_steps": 37520, "total_steps": 58920, "loss": 0.0, "lr": 7.016964878378624e-07, "epoch": 3.18397827562797, "percentage": 63.68, "elapsed_time": "0:58:49", "remaining_time": "0:33:32", "throughput": 10208.83, "total_tokens": 36028160}
{"current_steps": 37525, "total_steps": 58920, "loss": 0.0, "lr": 7.014137673466032e-07, "epoch": 3.1844025797691784, "percentage": 63.69, "elapsed_time": "0:58:49", "remaining_time": "0:33:32", "throughput": 10209.17, "total_tokens": 36033408}
{"current_steps": 37530, "total_steps": 58920, "loss": 0.0, "lr": 7.011310730552084e-07, "epoch": 3.184826883910387, "percentage": 63.7, "elapsed_time": "0:58:49", "remaining_time": "0:33:31", "throughput": 10209.33, "total_tokens": 36037760}
{"current_steps": 37535, "total_steps": 58920, "loss": 0.0, "lr": 7.008484049884824e-07, "epoch": 3.1852511880515952, "percentage": 63.71, "elapsed_time": "0:58:50", "remaining_time": "0:33:31", "throughput": 10209.48, "total_tokens": 36042112}
{"current_steps": 37540, "total_steps": 58920, "loss": 0.0, "lr": 7.005657631712293e-07, "epoch": 3.1856754921928037, "percentage": 63.71, "elapsed_time": "0:58:50", "remaining_time": "0:33:30", "throughput": 10209.7, "total_tokens": 36046720}
{"current_steps": 37545, "total_steps": 58920, "loss": 0.0, "lr": 7.002831476282489e-07, "epoch": 3.186099796334012, "percentage": 63.72, "elapsed_time": "0:58:51", "remaining_time": "0:33:30", "throughput": 10209.99, "total_tokens": 36051648}
{"current_steps": 37550, "total_steps": 58920, "loss": 0.0, "lr": 7.000005583843404e-07, "epoch": 3.1865241004752205, "percentage": 63.73, "elapsed_time": "0:58:51", "remaining_time": "0:33:29", "throughput": 10210.26, "total_tokens": 36056576}
{"current_steps": 37555, "total_steps": 58920, "loss": 0.0, "lr": 6.997179954642997e-07, "epoch": 3.186948404616429, "percentage": 63.74, "elapsed_time": "0:58:51", "remaining_time": "0:33:29", "throughput": 10210.53, "total_tokens": 36061440}
{"current_steps": 37560, "total_steps": 58920, "loss": 0.0, "lr": 6.994354588929208e-07, "epoch": 3.1873727087576373, "percentage": 63.75, "elapsed_time": "0:58:52", "remaining_time": "0:33:28", "throughput": 10210.7, "total_tokens": 36065856}
{"current_steps": 37565, "total_steps": 58920, "loss": 0.0, "lr": 6.991529486949952e-07, "epoch": 3.1877970128988458, "percentage": 63.76, "elapsed_time": "0:58:52", "remaining_time": "0:33:28", "throughput": 10210.85, "total_tokens": 36070208}
{"current_steps": 37570, "total_steps": 58920, "loss": 0.0, "lr": 6.988704648953119e-07, "epoch": 3.188221317040054, "percentage": 63.76, "elapsed_time": "0:58:53", "remaining_time": "0:33:27", "throughput": 10211.8, "total_tokens": 36078528}
{"current_steps": 37575, "total_steps": 58920, "loss": 0.0, "lr": 6.985880075186586e-07, "epoch": 3.1886456211812626, "percentage": 63.77, "elapsed_time": "0:58:53", "remaining_time": "0:33:27", "throughput": 10212.21, "total_tokens": 36084032}
{"current_steps": 37580, "total_steps": 58920, "loss": 0.0, "lr": 6.983055765898188e-07, "epoch": 3.189069925322471, "percentage": 63.78, "elapsed_time": "0:58:53", "remaining_time": "0:33:26", "throughput": 10212.58, "total_tokens": 36089344}
{"current_steps": 37585, "total_steps": 58920, "loss": 0.0, "lr": 6.980231721335756e-07, "epoch": 3.1894942294636794, "percentage": 63.79, "elapsed_time": "0:58:54", "remaining_time": "0:33:26", "throughput": 10212.72, "total_tokens": 36093632}
{"current_steps": 37590, "total_steps": 58920, "loss": 0.0, "lr": 6.977407941747087e-07, "epoch": 3.189918533604888, "percentage": 63.8, "elapsed_time": "0:58:54", "remaining_time": "0:33:25", "throughput": 10212.93, "total_tokens": 36098240}
{"current_steps": 37595, "total_steps": 58920, "loss": 0.0, "lr": 6.974584427379961e-07, "epoch": 3.1903428377460963, "percentage": 63.81, "elapsed_time": "0:58:54", "remaining_time": "0:33:25", "throughput": 10213.16, "total_tokens": 36102912}
{"current_steps": 37600, "total_steps": 58920, "loss": 0.0, "lr": 6.971761178482129e-07, "epoch": 3.1907671418873047, "percentage": 63.82, "elapsed_time": "0:58:55", "remaining_time": "0:33:24", "throughput": 10213.43, "total_tokens": 36107776}
{"current_steps": 37605, "total_steps": 58920, "loss": 0.0, "lr": 6.968938195301316e-07, "epoch": 3.191191446028513, "percentage": 63.82, "elapsed_time": "0:58:55", "remaining_time": "0:33:24", "throughput": 10213.7, "total_tokens": 36112704}
{"current_steps": 37610, "total_steps": 58920, "loss": 0.0, "lr": 6.966115478085235e-07, "epoch": 3.1916157501697215, "percentage": 63.83, "elapsed_time": "0:58:56", "remaining_time": "0:33:23", "throughput": 10213.94, "total_tokens": 36117440}
{"current_steps": 37615, "total_steps": 58920, "loss": 0.0, "lr": 6.963293027081567e-07, "epoch": 3.19204005431093, "percentage": 63.84, "elapsed_time": "0:58:56", "remaining_time": "0:33:23", "throughput": 10214.08, "total_tokens": 36121728}
{"current_steps": 37620, "total_steps": 58920, "loss": 0.0, "lr": 6.960470842537971e-07, "epoch": 3.1924643584521384, "percentage": 63.85, "elapsed_time": "0:58:56", "remaining_time": "0:33:22", "throughput": 10214.5, "total_tokens": 36127296}
{"current_steps": 37625, "total_steps": 58920, "loss": 0.0001, "lr": 6.957648924702083e-07, "epoch": 3.192888662593347, "percentage": 63.86, "elapsed_time": "0:58:57", "remaining_time": "0:33:22", "throughput": 10214.74, "total_tokens": 36132032}
{"current_steps": 37630, "total_steps": 58920, "loss": 0.0, "lr": 6.954827273821522e-07, "epoch": 3.1933129667345552, "percentage": 63.87, "elapsed_time": "0:58:57", "remaining_time": "0:33:21", "throughput": 10215.13, "total_tokens": 36137472}
{"current_steps": 37635, "total_steps": 58920, "loss": 0.0, "lr": 6.952005890143872e-07, "epoch": 3.1937372708757636, "percentage": 63.87, "elapsed_time": "0:58:58", "remaining_time": "0:33:20", "throughput": 10215.3, "total_tokens": 36141888}
{"current_steps": 37640, "total_steps": 58920, "loss": 0.0, "lr": 6.949184773916696e-07, "epoch": 3.194161575016972, "percentage": 63.88, "elapsed_time": "0:58:58", "remaining_time": "0:33:20", "throughput": 10215.56, "total_tokens": 36146752}
{"current_steps": 37645, "total_steps": 58920, "loss": 0.0, "lr": 6.946363925387545e-07, "epoch": 3.1945858791581805, "percentage": 63.89, "elapsed_time": "0:58:58", "remaining_time": "0:33:19", "throughput": 10215.71, "total_tokens": 36151040}
{"current_steps": 37650, "total_steps": 58920, "loss": 0.0271, "lr": 6.943543344803932e-07, "epoch": 3.195010183299389, "percentage": 63.9, "elapsed_time": "0:58:59", "remaining_time": "0:33:19", "throughput": 10215.93, "total_tokens": 36155648}
{"current_steps": 37655, "total_steps": 58920, "loss": 0.0, "lr": 6.940723032413358e-07, "epoch": 3.1954344874405973, "percentage": 63.91, "elapsed_time": "0:58:59", "remaining_time": "0:33:18", "throughput": 10216.18, "total_tokens": 36160512}
{"current_steps": 37660, "total_steps": 58920, "loss": 0.0, "lr": 6.937902988463288e-07, "epoch": 3.1958587915818057, "percentage": 63.92, "elapsed_time": "0:58:59", "remaining_time": "0:33:18", "throughput": 10216.39, "total_tokens": 36165056}
{"current_steps": 37665, "total_steps": 58920, "loss": 0.0, "lr": 6.935083213201182e-07, "epoch": 3.196283095723014, "percentage": 63.93, "elapsed_time": "0:59:00", "remaining_time": "0:33:17", "throughput": 10216.71, "total_tokens": 36170176}
{"current_steps": 37670, "total_steps": 58920, "loss": 0.0, "lr": 6.932263706874453e-07, "epoch": 3.1967073998642226, "percentage": 63.93, "elapsed_time": "0:59:00", "remaining_time": "0:33:17", "throughput": 10217.08, "total_tokens": 36175488}
{"current_steps": 37675, "total_steps": 58920, "loss": 0.0, "lr": 6.929444469730508e-07, "epoch": 3.197131704005431, "percentage": 63.94, "elapsed_time": "0:59:01", "remaining_time": "0:33:16", "throughput": 10217.46, "total_tokens": 36180864}
{"current_steps": 37680, "total_steps": 58920, "loss": 0.0, "lr": 6.926625502016729e-07, "epoch": 3.1975560081466394, "percentage": 63.95, "elapsed_time": "0:59:01", "remaining_time": "0:33:16", "throughput": 10217.69, "total_tokens": 36185536}
{"current_steps": 37685, "total_steps": 58920, "loss": 0.0001, "lr": 6.92380680398046e-07, "epoch": 3.197980312287848, "percentage": 63.96, "elapsed_time": "0:59:01", "remaining_time": "0:33:15", "throughput": 10217.83, "total_tokens": 36189824}
{"current_steps": 37690, "total_steps": 58920, "loss": 0.0, "lr": 6.920988375869043e-07, "epoch": 3.1984046164290563, "percentage": 63.97, "elapsed_time": "0:59:02", "remaining_time": "0:33:15", "throughput": 10218.12, "total_tokens": 36194752}
{"current_steps": 37695, "total_steps": 58920, "loss": 0.0, "lr": 6.918170217929773e-07, "epoch": 3.1988289205702647, "percentage": 63.98, "elapsed_time": "0:59:02", "remaining_time": "0:33:14", "throughput": 10218.43, "total_tokens": 36199808}
{"current_steps": 37700, "total_steps": 58920, "loss": 0.0, "lr": 6.915352330409945e-07, "epoch": 3.199253224711473, "percentage": 63.99, "elapsed_time": "0:59:03", "remaining_time": "0:33:14", "throughput": 10218.97, "total_tokens": 36206016}
{"current_steps": 37705, "total_steps": 58920, "loss": 0.0, "lr": 6.912534713556809e-07, "epoch": 3.1996775288526815, "percentage": 63.99, "elapsed_time": "0:59:03", "remaining_time": "0:33:13", "throughput": 10219.22, "total_tokens": 36210816}
{"current_steps": 37710, "total_steps": 58920, "loss": 0.0, "lr": 6.909717367617607e-07, "epoch": 3.20010183299389, "percentage": 64.0, "elapsed_time": "0:59:03", "remaining_time": "0:33:13", "throughput": 10219.42, "total_tokens": 36215360}
{"current_steps": 37715, "total_steps": 58920, "loss": 0.0, "lr": 6.906900292839546e-07, "epoch": 3.2005261371350984, "percentage": 64.01, "elapsed_time": "0:59:04", "remaining_time": "0:33:12", "throughput": 10219.6, "total_tokens": 36219840}
{"current_steps": 37720, "total_steps": 58920, "loss": 0.0, "lr": 6.90408348946982e-07, "epoch": 3.200950441276307, "percentage": 64.02, "elapsed_time": "0:59:04", "remaining_time": "0:33:12", "throughput": 10219.93, "total_tokens": 36225024}
{"current_steps": 37725, "total_steps": 58920, "loss": 0.0, "lr": 6.901266957755591e-07, "epoch": 3.201374745417515, "percentage": 64.03, "elapsed_time": "0:59:04", "remaining_time": "0:33:11", "throughput": 10220.36, "total_tokens": 36230656}
{"current_steps": 37730, "total_steps": 58920, "loss": 0.0506, "lr": 6.898450697943993e-07, "epoch": 3.2017990495587236, "percentage": 64.04, "elapsed_time": "0:59:05", "remaining_time": "0:33:11", "throughput": 10220.69, "total_tokens": 36235840}
{"current_steps": 37735, "total_steps": 58920, "loss": 0.0, "lr": 6.895634710282152e-07, "epoch": 3.202223353699932, "percentage": 64.04, "elapsed_time": "0:59:05", "remaining_time": "0:33:10", "throughput": 10220.89, "total_tokens": 36240384}
{"current_steps": 37740, "total_steps": 58920, "loss": 0.0, "lr": 6.892818995017154e-07, "epoch": 3.2026476578411405, "percentage": 64.05, "elapsed_time": "0:59:06", "remaining_time": "0:33:10", "throughput": 10221.14, "total_tokens": 36245184}
{"current_steps": 37745, "total_steps": 58920, "loss": 0.0, "lr": 6.890003552396075e-07, "epoch": 3.203071961982349, "percentage": 64.06, "elapsed_time": "0:59:06", "remaining_time": "0:33:09", "throughput": 10221.41, "total_tokens": 36250048}
{"current_steps": 37750, "total_steps": 58920, "loss": 0.0, "lr": 6.887188382665952e-07, "epoch": 3.2034962661235573, "percentage": 64.07, "elapsed_time": "0:59:06", "remaining_time": "0:33:09", "throughput": 10221.69, "total_tokens": 36254976}
{"current_steps": 37755, "total_steps": 58920, "loss": 0.0, "lr": 6.884373486073814e-07, "epoch": 3.2039205702647657, "percentage": 64.08, "elapsed_time": "0:59:07", "remaining_time": "0:33:08", "throughput": 10221.87, "total_tokens": 36259456}
{"current_steps": 37760, "total_steps": 58920, "loss": 0.0, "lr": 6.881558862866652e-07, "epoch": 3.204344874405974, "percentage": 64.09, "elapsed_time": "0:59:07", "remaining_time": "0:33:08", "throughput": 10222.04, "total_tokens": 36263872}
{"current_steps": 37765, "total_steps": 58920, "loss": 0.0, "lr": 6.878744513291439e-07, "epoch": 3.2047691785471826, "percentage": 64.1, "elapsed_time": "0:59:08", "remaining_time": "0:33:07", "throughput": 10222.34, "total_tokens": 36268928}
{"current_steps": 37770, "total_steps": 58920, "loss": 0.0, "lr": 6.875930437595126e-07, "epoch": 3.205193482688391, "percentage": 64.1, "elapsed_time": "0:59:08", "remaining_time": "0:33:06", "throughput": 10222.51, "total_tokens": 36273344}
{"current_steps": 37775, "total_steps": 58920, "loss": 0.0, "lr": 6.873116636024636e-07, "epoch": 3.2056177868295994, "percentage": 64.11, "elapsed_time": "0:59:08", "remaining_time": "0:33:06", "throughput": 10222.69, "total_tokens": 36277824}
{"current_steps": 37780, "total_steps": 58920, "loss": 0.0, "lr": 6.870303108826876e-07, "epoch": 3.206042090970808, "percentage": 64.12, "elapsed_time": "0:59:09", "remaining_time": "0:33:05", "throughput": 10222.98, "total_tokens": 36282880}
{"current_steps": 37785, "total_steps": 58920, "loss": 0.0, "lr": 6.867489856248714e-07, "epoch": 3.2064663951120163, "percentage": 64.13, "elapsed_time": "0:59:09", "remaining_time": "0:33:05", "throughput": 10223.32, "total_tokens": 36288064}
{"current_steps": 37790, "total_steps": 58920, "loss": 0.0, "lr": 6.864676878537011e-07, "epoch": 3.2068906992532247, "percentage": 64.14, "elapsed_time": "0:59:09", "remaining_time": "0:33:04", "throughput": 10223.5, "total_tokens": 36292544}
{"current_steps": 37795, "total_steps": 58920, "loss": 0.0, "lr": 6.861864175938589e-07, "epoch": 3.207315003394433, "percentage": 64.15, "elapsed_time": "0:59:10", "remaining_time": "0:33:04", "throughput": 10223.63, "total_tokens": 36296832}
{"current_steps": 37800, "total_steps": 58920, "loss": 0.0, "lr": 6.859051748700257e-07, "epoch": 3.2077393075356415, "percentage": 64.15, "elapsed_time": "0:59:10", "remaining_time": "0:33:03", "throughput": 10223.71, "total_tokens": 36300864}
{"current_steps": 37805, "total_steps": 58920, "loss": 0.0, "lr": 6.856239597068795e-07, "epoch": 3.20816361167685, "percentage": 64.16, "elapsed_time": "0:59:11", "remaining_time": "0:33:03", "throughput": 10223.84, "total_tokens": 36305152}
{"current_steps": 37810, "total_steps": 58920, "loss": 0.0, "lr": 6.853427721290954e-07, "epoch": 3.2085879158180584, "percentage": 64.17, "elapsed_time": "0:59:11", "remaining_time": "0:33:02", "throughput": 10224.2, "total_tokens": 36310464}
{"current_steps": 37815, "total_steps": 58920, "loss": 0.0, "lr": 6.850616121613474e-07, "epoch": 3.2090122199592668, "percentage": 64.18, "elapsed_time": "0:59:11", "remaining_time": "0:33:02", "throughput": 10224.51, "total_tokens": 36315520}
{"current_steps": 37820, "total_steps": 58920, "loss": 0.0, "lr": 6.847804798283055e-07, "epoch": 3.209436524100475, "percentage": 64.19, "elapsed_time": "0:59:12", "remaining_time": "0:33:01", "throughput": 10224.74, "total_tokens": 36320192}
{"current_steps": 37825, "total_steps": 58920, "loss": 0.0, "lr": 6.844993751546387e-07, "epoch": 3.2098608282416836, "percentage": 64.2, "elapsed_time": "0:59:12", "remaining_time": "0:33:01", "throughput": 10224.97, "total_tokens": 36324864}
{"current_steps": 37830, "total_steps": 58920, "loss": 0.0, "lr": 6.842182981650123e-07, "epoch": 3.210285132382892, "percentage": 64.21, "elapsed_time": "0:59:12", "remaining_time": "0:33:00", "throughput": 10225.23, "total_tokens": 36329728}
{"current_steps": 37835, "total_steps": 58920, "loss": 0.0, "lr": 6.839372488840903e-07, "epoch": 3.2107094365241005, "percentage": 64.21, "elapsed_time": "0:59:13", "remaining_time": "0:33:00", "throughput": 10225.52, "total_tokens": 36334656}
{"current_steps": 37840, "total_steps": 58920, "loss": 0.0, "lr": 6.836562273365334e-07, "epoch": 3.211133740665309, "percentage": 64.22, "elapsed_time": "0:59:13", "remaining_time": "0:32:59", "throughput": 10225.84, "total_tokens": 36339776}
{"current_steps": 37845, "total_steps": 58920, "loss": 0.0, "lr": 6.833752335470007e-07, "epoch": 3.2115580448065173, "percentage": 64.23, "elapsed_time": "0:59:14", "remaining_time": "0:32:59", "throughput": 10226.01, "total_tokens": 36344192}
{"current_steps": 37850, "total_steps": 58920, "loss": 0.0, "lr": 6.830942675401481e-07, "epoch": 3.2119823489477257, "percentage": 64.24, "elapsed_time": "0:59:14", "remaining_time": "0:32:58", "throughput": 10226.42, "total_tokens": 36349760}
{"current_steps": 37855, "total_steps": 58920, "loss": 0.0, "lr": 6.82813329340629e-07, "epoch": 3.212406653088934, "percentage": 64.25, "elapsed_time": "0:59:14", "remaining_time": "0:32:58", "throughput": 10226.58, "total_tokens": 36354176}
{"current_steps": 37860, "total_steps": 58920, "loss": 0.0, "lr": 6.825324189730953e-07, "epoch": 3.2128309572301426, "percentage": 64.26, "elapsed_time": "0:59:15", "remaining_time": "0:32:57", "throughput": 10226.85, "total_tokens": 36359040}
{"current_steps": 37865, "total_steps": 58920, "loss": 0.0, "lr": 6.822515364621953e-07, "epoch": 3.213255261371351, "percentage": 64.27, "elapsed_time": "0:59:15", "remaining_time": "0:32:57", "throughput": 10227.02, "total_tokens": 36363456}
{"current_steps": 37870, "total_steps": 58920, "loss": 0.0, "lr": 6.819706818325763e-07, "epoch": 3.2136795655125594, "percentage": 64.27, "elapsed_time": "0:59:16", "remaining_time": "0:32:56", "throughput": 10227.25, "total_tokens": 36368128}
{"current_steps": 37875, "total_steps": 58920, "loss": 0.0004, "lr": 6.816898551088812e-07, "epoch": 3.214103869653768, "percentage": 64.28, "elapsed_time": "0:59:16", "remaining_time": "0:32:56", "throughput": 10227.4, "total_tokens": 36372480}
{"current_steps": 37880, "total_steps": 58920, "loss": 0.0, "lr": 6.814090563157524e-07, "epoch": 3.2145281737949762, "percentage": 64.29, "elapsed_time": "0:59:16", "remaining_time": "0:32:55", "throughput": 10227.61, "total_tokens": 36377088}
{"current_steps": 37885, "total_steps": 58920, "loss": 0.0, "lr": 6.811282854778284e-07, "epoch": 3.2149524779361847, "percentage": 64.3, "elapsed_time": "0:59:17", "remaining_time": "0:32:55", "throughput": 10227.81, "total_tokens": 36381632}
{"current_steps": 37890, "total_steps": 58920, "loss": 0.0, "lr": 6.808475426197465e-07, "epoch": 3.215376782077393, "percentage": 64.31, "elapsed_time": "0:59:17", "remaining_time": "0:32:54", "throughput": 10228.02, "total_tokens": 36386240}
{"current_steps": 37895, "total_steps": 58920, "loss": 0.0, "lr": 6.805668277661401e-07, "epoch": 3.2158010862186015, "percentage": 64.32, "elapsed_time": "0:59:17", "remaining_time": "0:32:54", "throughput": 10228.32, "total_tokens": 36391296}
{"current_steps": 37900, "total_steps": 58920, "loss": 0.0, "lr": 6.802861409416409e-07, "epoch": 3.21622539035981, "percentage": 64.32, "elapsed_time": "0:59:18", "remaining_time": "0:32:53", "throughput": 10228.5, "total_tokens": 36395776}
{"current_steps": 37905, "total_steps": 58920, "loss": 0.0, "lr": 6.800054821708792e-07, "epoch": 3.2166496945010183, "percentage": 64.33, "elapsed_time": "0:59:18", "remaining_time": "0:32:52", "throughput": 10228.74, "total_tokens": 36400512}
{"current_steps": 37910, "total_steps": 58920, "loss": 0.0, "lr": 6.797248514784806e-07, "epoch": 3.2170739986422268, "percentage": 64.34, "elapsed_time": "0:59:19", "remaining_time": "0:32:52", "throughput": 10229.11, "total_tokens": 36405952}
{"current_steps": 37915, "total_steps": 58920, "loss": 0.0, "lr": 6.794442488890704e-07, "epoch": 3.217498302783435, "percentage": 64.35, "elapsed_time": "0:59:19", "remaining_time": "0:32:51", "throughput": 10229.38, "total_tokens": 36410816}
{"current_steps": 37920, "total_steps": 58920, "loss": 0.0, "lr": 6.791636744272695e-07, "epoch": 3.2179226069246436, "percentage": 64.36, "elapsed_time": "0:59:19", "remaining_time": "0:32:51", "throughput": 10229.72, "total_tokens": 36416064}
{"current_steps": 37925, "total_steps": 58920, "loss": 0.0, "lr": 6.788831281176981e-07, "epoch": 3.218346911065852, "percentage": 64.37, "elapsed_time": "0:59:20", "remaining_time": "0:32:50", "throughput": 10230.16, "total_tokens": 36421760}
{"current_steps": 37930, "total_steps": 58920, "loss": 0.0388, "lr": 6.786026099849729e-07, "epoch": 3.2187712152070604, "percentage": 64.38, "elapsed_time": "0:59:20", "remaining_time": "0:32:50", "throughput": 10230.5, "total_tokens": 36427008}
{"current_steps": 37935, "total_steps": 58920, "loss": 0.0, "lr": 6.783221200537079e-07, "epoch": 3.219195519348269, "percentage": 64.38, "elapsed_time": "0:59:21", "remaining_time": "0:32:49", "throughput": 10230.72, "total_tokens": 36431680}
{"current_steps": 37940, "total_steps": 58920, "loss": 0.0, "lr": 6.78041658348516e-07, "epoch": 3.2196198234894773, "percentage": 64.39, "elapsed_time": "0:59:21", "remaining_time": "0:32:49", "throughput": 10231.01, "total_tokens": 36436736}
{"current_steps": 37945, "total_steps": 58920, "loss": 0.0, "lr": 6.777612248940055e-07, "epoch": 3.2200441276306857, "percentage": 64.4, "elapsed_time": "0:59:21", "remaining_time": "0:32:48", "throughput": 10231.24, "total_tokens": 36441408}
{"current_steps": 37950, "total_steps": 58920, "loss": 0.0, "lr": 6.774808197147846e-07, "epoch": 3.220468431771894, "percentage": 64.41, "elapsed_time": "0:59:22", "remaining_time": "0:32:48", "throughput": 10231.42, "total_tokens": 36445952}
{"current_steps": 37955, "total_steps": 58920, "loss": 0.0, "lr": 6.772004428354569e-07, "epoch": 3.2208927359131025, "percentage": 64.42, "elapsed_time": "0:59:22", "remaining_time": "0:32:47", "throughput": 10231.6, "total_tokens": 36450432}
{"current_steps": 37960, "total_steps": 58920, "loss": 0.0002, "lr": 6.769200942806253e-07, "epoch": 3.221317040054311, "percentage": 64.43, "elapsed_time": "0:59:22", "remaining_time": "0:32:47", "throughput": 10231.91, "total_tokens": 36455552}
{"current_steps": 37965, "total_steps": 58920, "loss": 0.0, "lr": 6.766397740748885e-07, "epoch": 3.2217413441955194, "percentage": 64.43, "elapsed_time": "0:59:23", "remaining_time": "0:32:46", "throughput": 10232.21, "total_tokens": 36460544}
{"current_steps": 37970, "total_steps": 58920, "loss": 0.0, "lr": 6.763594822428444e-07, "epoch": 3.222165648336728, "percentage": 64.44, "elapsed_time": "0:59:23", "remaining_time": "0:32:46", "throughput": 10232.47, "total_tokens": 36465408}
{"current_steps": 37975, "total_steps": 58920, "loss": 0.0, "lr": 6.760792188090873e-07, "epoch": 3.2225899524779362, "percentage": 64.45, "elapsed_time": "0:59:24", "remaining_time": "0:32:45", "throughput": 10232.78, "total_tokens": 36470528}
{"current_steps": 37980, "total_steps": 58920, "loss": 0.0, "lr": 6.75798983798209e-07, "epoch": 3.2230142566191446, "percentage": 64.46, "elapsed_time": "0:59:24", "remaining_time": "0:32:45", "throughput": 10233.0, "total_tokens": 36475136}
{"current_steps": 37985, "total_steps": 58920, "loss": 0.0, "lr": 6.755187772347994e-07, "epoch": 3.223438560760353, "percentage": 64.47, "elapsed_time": "0:59:24", "remaining_time": "0:32:44", "throughput": 10233.17, "total_tokens": 36479552}
{"current_steps": 37990, "total_steps": 58920, "loss": 0.0, "lr": 6.752385991434454e-07, "epoch": 3.2238628649015615, "percentage": 64.48, "elapsed_time": "0:59:25", "remaining_time": "0:32:44", "throughput": 10233.51, "total_tokens": 36484800}
{"current_steps": 37995, "total_steps": 58920, "loss": 0.0, "lr": 6.749584495487321e-07, "epoch": 3.22428716904277, "percentage": 64.49, "elapsed_time": "0:59:25", "remaining_time": "0:32:43", "throughput": 10233.74, "total_tokens": 36489472}
{"current_steps": 38000, "total_steps": 58920, "loss": 0.0, "lr": 6.746783284752411e-07, "epoch": 3.2247114731839783, "percentage": 64.49, "elapsed_time": "0:59:25", "remaining_time": "0:32:43", "throughput": 10233.93, "total_tokens": 36494016}
{"current_steps": 38005, "total_steps": 58920, "loss": 0.0604, "lr": 6.743982359475524e-07, "epoch": 3.2251357773251867, "percentage": 64.5, "elapsed_time": "0:59:26", "remaining_time": "0:32:42", "throughput": 10234.11, "total_tokens": 36498496}
{"current_steps": 38010, "total_steps": 58920, "loss": 0.0003, "lr": 6.741181719902426e-07, "epoch": 3.225560081466395, "percentage": 64.51, "elapsed_time": "0:59:26", "remaining_time": "0:32:42", "throughput": 10234.44, "total_tokens": 36503680}
{"current_steps": 38015, "total_steps": 58920, "loss": 0.0, "lr": 6.738381366278866e-07, "epoch": 3.2259843856076036, "percentage": 64.52, "elapsed_time": "0:59:27", "remaining_time": "0:32:41", "throughput": 10234.69, "total_tokens": 36508480}
{"current_steps": 38020, "total_steps": 58920, "loss": 0.0, "lr": 6.73558129885057e-07, "epoch": 3.226408689748812, "percentage": 64.53, "elapsed_time": "0:59:27", "remaining_time": "0:32:41", "throughput": 10235.06, "total_tokens": 36513792}
{"current_steps": 38025, "total_steps": 58920, "loss": 0.0, "lr": 6.732781517863224e-07, "epoch": 3.2268329938900204, "percentage": 64.54, "elapsed_time": "0:59:27", "remaining_time": "0:32:40", "throughput": 10235.31, "total_tokens": 36518592}
{"current_steps": 38030, "total_steps": 58920, "loss": 0.0, "lr": 6.729982023562508e-07, "epoch": 3.227257298031229, "percentage": 64.55, "elapsed_time": "0:59:28", "remaining_time": "0:32:40", "throughput": 10235.59, "total_tokens": 36523520}
{"current_steps": 38035, "total_steps": 58920, "loss": 0.0, "lr": 6.727182816194059e-07, "epoch": 3.2276816021724373, "percentage": 64.55, "elapsed_time": "0:59:28", "remaining_time": "0:32:39", "throughput": 10235.77, "total_tokens": 36528000}
{"current_steps": 38040, "total_steps": 58920, "loss": 0.0001, "lr": 6.724383896003505e-07, "epoch": 3.2281059063136457, "percentage": 64.56, "elapsed_time": "0:59:29", "remaining_time": "0:32:39", "throughput": 10236.03, "total_tokens": 36532864}
{"current_steps": 38045, "total_steps": 58920, "loss": 0.0, "lr": 6.721585263236434e-07, "epoch": 3.228530210454854, "percentage": 64.57, "elapsed_time": "0:59:29", "remaining_time": "0:32:38", "throughput": 10236.34, "total_tokens": 36537920}
{"current_steps": 38050, "total_steps": 58920, "loss": 0.0456, "lr": 6.718786918138419e-07, "epoch": 3.2289545145960625, "percentage": 64.58, "elapsed_time": "0:59:29", "remaining_time": "0:32:38", "throughput": 10236.55, "total_tokens": 36542592}
{"current_steps": 38055, "total_steps": 58920, "loss": 0.0, "lr": 6.715988860955011e-07, "epoch": 3.229378818737271, "percentage": 64.59, "elapsed_time": "0:59:30", "remaining_time": "0:32:37", "throughput": 10236.75, "total_tokens": 36547200}
{"current_steps": 38060, "total_steps": 58920, "loss": 0.0, "lr": 6.713191091931717e-07, "epoch": 3.2298031228784794, "percentage": 64.6, "elapsed_time": "0:59:30", "remaining_time": "0:32:36", "throughput": 10237.06, "total_tokens": 36552320}
{"current_steps": 38065, "total_steps": 58920, "loss": 0.0, "lr": 6.710393611314042e-07, "epoch": 3.230227427019688, "percentage": 64.6, "elapsed_time": "0:59:30", "remaining_time": "0:32:36", "throughput": 10237.27, "total_tokens": 36556928}
{"current_steps": 38070, "total_steps": 58920, "loss": 0.0, "lr": 6.707596419347447e-07, "epoch": 3.230651731160896, "percentage": 64.61, "elapsed_time": "0:59:31", "remaining_time": "0:32:35", "throughput": 10237.5, "total_tokens": 36561664}
{"current_steps": 38075, "total_steps": 58920, "loss": 0.0, "lr": 6.704799516277382e-07, "epoch": 3.2310760353021046, "percentage": 64.62, "elapsed_time": "0:59:31", "remaining_time": "0:32:35", "throughput": 10237.87, "total_tokens": 36567040}
{"current_steps": 38080, "total_steps": 58920, "loss": 0.0, "lr": 6.702002902349259e-07, "epoch": 3.231500339443313, "percentage": 64.63, "elapsed_time": "0:59:32", "remaining_time": "0:32:34", "throughput": 10238.17, "total_tokens": 36572096}
{"current_steps": 38085, "total_steps": 58920, "loss": 0.0, "lr": 6.699206577808478e-07, "epoch": 3.2319246435845215, "percentage": 64.64, "elapsed_time": "0:59:32", "remaining_time": "0:32:34", "throughput": 10238.55, "total_tokens": 36577536}
{"current_steps": 38090, "total_steps": 58920, "loss": 0.0, "lr": 6.696410542900398e-07, "epoch": 3.23234894772573, "percentage": 64.65, "elapsed_time": "0:59:32", "remaining_time": "0:32:33", "throughput": 10238.75, "total_tokens": 36582144}
{"current_steps": 38095, "total_steps": 58920, "loss": 0.0, "lr": 6.693614797870371e-07, "epoch": 3.2327732518669383, "percentage": 64.66, "elapsed_time": "0:59:33", "remaining_time": "0:32:33", "throughput": 10238.93, "total_tokens": 36586624}
{"current_steps": 38100, "total_steps": 58920, "loss": 0.0, "lr": 6.690819342963702e-07, "epoch": 3.2331975560081467, "percentage": 64.66, "elapsed_time": "0:59:33", "remaining_time": "0:32:32", "throughput": 10239.12, "total_tokens": 36591168}
{"current_steps": 38105, "total_steps": 58920, "loss": 0.0, "lr": 6.688024178425692e-07, "epoch": 3.233621860149355, "percentage": 64.67, "elapsed_time": "0:59:34", "remaining_time": "0:32:32", "throughput": 10239.47, "total_tokens": 36596416}
{"current_steps": 38110, "total_steps": 58920, "loss": 0.0, "lr": 6.685229304501601e-07, "epoch": 3.2340461642905636, "percentage": 64.68, "elapsed_time": "0:59:34", "remaining_time": "0:32:31", "throughput": 10239.66, "total_tokens": 36600896}
{"current_steps": 38115, "total_steps": 58920, "loss": 0.0001, "lr": 6.682434721436668e-07, "epoch": 3.234470468431772, "percentage": 64.69, "elapsed_time": "0:59:34", "remaining_time": "0:32:31", "throughput": 10239.9, "total_tokens": 36605696}
{"current_steps": 38120, "total_steps": 58920, "loss": 0.0, "lr": 6.679640429476116e-07, "epoch": 3.2348947725729804, "percentage": 64.7, "elapsed_time": "0:59:35", "remaining_time": "0:32:30", "throughput": 10240.17, "total_tokens": 36610560}
{"current_steps": 38125, "total_steps": 58920, "loss": 0.0, "lr": 6.676846428865122e-07, "epoch": 3.235319076714189, "percentage": 64.71, "elapsed_time": "0:59:35", "remaining_time": "0:32:30", "throughput": 10240.43, "total_tokens": 36615424}
{"current_steps": 38130, "total_steps": 58920, "loss": 0.0, "lr": 6.674052719848862e-07, "epoch": 3.2357433808553973, "percentage": 64.71, "elapsed_time": "0:59:35", "remaining_time": "0:32:29", "throughput": 10240.77, "total_tokens": 36620736}
{"current_steps": 38135, "total_steps": 58920, "loss": 0.0, "lr": 6.671259302672461e-07, "epoch": 3.2361676849966057, "percentage": 64.72, "elapsed_time": "0:59:36", "remaining_time": "0:32:29", "throughput": 10240.95, "total_tokens": 36625280}
{"current_steps": 38140, "total_steps": 58920, "loss": 0.0, "lr": 6.668466177581042e-07, "epoch": 3.236591989137814, "percentage": 64.73, "elapsed_time": "0:59:36", "remaining_time": "0:32:28", "throughput": 10241.24, "total_tokens": 36630272}
{"current_steps": 38145, "total_steps": 58920, "loss": 0.0212, "lr": 6.665673344819688e-07, "epoch": 3.2370162932790225, "percentage": 64.74, "elapsed_time": "0:59:37", "remaining_time": "0:32:28", "throughput": 10241.63, "total_tokens": 36635776}
{"current_steps": 38150, "total_steps": 58920, "loss": 0.0, "lr": 6.662880804633455e-07, "epoch": 3.237440597420231, "percentage": 64.75, "elapsed_time": "0:59:37", "remaining_time": "0:32:27", "throughput": 10241.88, "total_tokens": 36640640}
{"current_steps": 38155, "total_steps": 58920, "loss": 0.0, "lr": 6.660088557267388e-07, "epoch": 3.2378649015614394, "percentage": 64.76, "elapsed_time": "0:59:37", "remaining_time": "0:32:27", "throughput": 10242.15, "total_tokens": 36645568}
{"current_steps": 38160, "total_steps": 58920, "loss": 0.0, "lr": 6.657296602966487e-07, "epoch": 3.2382892057026478, "percentage": 64.77, "elapsed_time": "0:59:38", "remaining_time": "0:32:26", "throughput": 10242.47, "total_tokens": 36650688}
{"current_steps": 38165, "total_steps": 58920, "loss": 0.0, "lr": 6.654504941975743e-07, "epoch": 3.238713509843856, "percentage": 64.77, "elapsed_time": "0:59:38", "remaining_time": "0:32:26", "throughput": 10242.63, "total_tokens": 36655104}
{"current_steps": 38170, "total_steps": 58920, "loss": 0.0127, "lr": 6.65171357454011e-07, "epoch": 3.2391378139850646, "percentage": 64.78, "elapsed_time": "0:59:39", "remaining_time": "0:32:25", "throughput": 10242.93, "total_tokens": 36660096}
{"current_steps": 38175, "total_steps": 58920, "loss": 0.0, "lr": 6.648922500904523e-07, "epoch": 3.239562118126273, "percentage": 64.79, "elapsed_time": "0:59:39", "remaining_time": "0:32:25", "throughput": 10243.14, "total_tokens": 36664768}
{"current_steps": 38180, "total_steps": 58920, "loss": 0.0, "lr": 6.64613172131389e-07, "epoch": 3.2399864222674815, "percentage": 64.8, "elapsed_time": "0:59:39", "remaining_time": "0:32:24", "throughput": 10243.28, "total_tokens": 36669056}
{"current_steps": 38185, "total_steps": 58920, "loss": 0.0, "lr": 6.643341236013084e-07, "epoch": 3.24041072640869, "percentage": 64.81, "elapsed_time": "0:59:40", "remaining_time": "0:32:24", "throughput": 10243.56, "total_tokens": 36674048}
{"current_steps": 38190, "total_steps": 58920, "loss": 0.0, "lr": 6.64055104524697e-07, "epoch": 3.2408350305498983, "percentage": 64.82, "elapsed_time": "0:59:40", "remaining_time": "0:32:23", "throughput": 10243.8, "total_tokens": 36678848}
{"current_steps": 38195, "total_steps": 58920, "loss": 0.0551, "lr": 6.637761149260369e-07, "epoch": 3.2412593346911067, "percentage": 64.83, "elapsed_time": "0:59:40", "remaining_time": "0:32:23", "throughput": 10243.98, "total_tokens": 36683328}
{"current_steps": 38200, "total_steps": 58920, "loss": 0.0, "lr": 6.63497154829809e-07, "epoch": 3.241683638832315, "percentage": 64.83, "elapsed_time": "0:59:41", "remaining_time": "0:32:22", "throughput": 10244.18, "total_tokens": 36687936}
{"current_steps": 38205, "total_steps": 58920, "loss": 0.0, "lr": 6.632182242604905e-07, "epoch": 3.2421079429735236, "percentage": 64.84, "elapsed_time": "0:59:41", "remaining_time": "0:32:22", "throughput": 10244.49, "total_tokens": 36692992}
{"current_steps": 38210, "total_steps": 58920, "loss": 0.0, "lr": 6.629393232425573e-07, "epoch": 3.242532247114732, "percentage": 64.85, "elapsed_time": "0:59:42", "remaining_time": "0:32:21", "throughput": 10244.82, "total_tokens": 36698176}
{"current_steps": 38215, "total_steps": 58920, "loss": 0.0, "lr": 6.626604518004812e-07, "epoch": 3.2429565512559404, "percentage": 64.86, "elapsed_time": "0:59:42", "remaining_time": "0:32:21", "throughput": 10245.02, "total_tokens": 36702784}
{"current_steps": 38220, "total_steps": 58920, "loss": 0.0, "lr": 6.62381609958733e-07, "epoch": 3.243380855397149, "percentage": 64.87, "elapsed_time": "0:59:42", "remaining_time": "0:32:20", "throughput": 10245.34, "total_tokens": 36707968}
{"current_steps": 38225, "total_steps": 58920, "loss": 0.0, "lr": 6.621027977417791e-07, "epoch": 3.2438051595383572, "percentage": 64.88, "elapsed_time": "0:59:43", "remaining_time": "0:32:19", "throughput": 10245.42, "total_tokens": 36712064}
{"current_steps": 38230, "total_steps": 58920, "loss": 0.0, "lr": 6.618240151740846e-07, "epoch": 3.2442294636795657, "percentage": 64.88, "elapsed_time": "0:59:43", "remaining_time": "0:32:19", "throughput": 10245.73, "total_tokens": 36717184}
{"current_steps": 38235, "total_steps": 58920, "loss": 0.0, "lr": 6.615452622801123e-07, "epoch": 3.244653767820774, "percentage": 64.89, "elapsed_time": "0:59:44", "remaining_time": "0:32:18", "throughput": 10245.94, "total_tokens": 36721856}
{"current_steps": 38240, "total_steps": 58920, "loss": 0.0, "lr": 6.612665390843208e-07, "epoch": 3.2450780719619825, "percentage": 64.9, "elapsed_time": "0:59:44", "remaining_time": "0:32:18", "throughput": 10246.1, "total_tokens": 36726272}
{"current_steps": 38245, "total_steps": 58920, "loss": 0.0, "lr": 6.609878456111679e-07, "epoch": 3.245502376103191, "percentage": 64.91, "elapsed_time": "0:59:44", "remaining_time": "0:32:17", "throughput": 10246.28, "total_tokens": 36730816}
{"current_steps": 38250, "total_steps": 58920, "loss": 0.0, "lr": 6.607091818851071e-07, "epoch": 3.2459266802443993, "percentage": 64.92, "elapsed_time": "0:59:45", "remaining_time": "0:32:17", "throughput": 10246.48, "total_tokens": 36735424}
{"current_steps": 38255, "total_steps": 58920, "loss": 0.0, "lr": 6.604305479305912e-07, "epoch": 3.2463509843856078, "percentage": 64.93, "elapsed_time": "0:59:45", "remaining_time": "0:32:16", "throughput": 10246.77, "total_tokens": 36740416}
{"current_steps": 38260, "total_steps": 58920, "loss": 0.0, "lr": 6.60151943772068e-07, "epoch": 3.246775288526816, "percentage": 64.94, "elapsed_time": "0:59:45", "remaining_time": "0:32:16", "throughput": 10246.94, "total_tokens": 36744832}
{"current_steps": 38265, "total_steps": 58920, "loss": 0.0, "lr": 6.59873369433985e-07, "epoch": 3.2471995926680246, "percentage": 64.94, "elapsed_time": "0:59:46", "remaining_time": "0:32:15", "throughput": 10247.32, "total_tokens": 36750272}
{"current_steps": 38270, "total_steps": 58920, "loss": 0.0, "lr": 6.595948249407861e-07, "epoch": 3.247623896809233, "percentage": 64.95, "elapsed_time": "0:59:46", "remaining_time": "0:32:15", "throughput": 10247.73, "total_tokens": 36755840}
{"current_steps": 38275, "total_steps": 58920, "loss": 0.0, "lr": 6.593163103169119e-07, "epoch": 3.2480482009504414, "percentage": 64.96, "elapsed_time": "0:59:47", "remaining_time": "0:32:14", "throughput": 10247.95, "total_tokens": 36760448}
{"current_steps": 38280, "total_steps": 58920, "loss": 0.0, "lr": 6.590378255868017e-07, "epoch": 3.24847250509165, "percentage": 64.97, "elapsed_time": "0:59:47", "remaining_time": "0:32:14", "throughput": 10248.19, "total_tokens": 36765184}
{"current_steps": 38285, "total_steps": 58920, "loss": 0.0, "lr": 6.587593707748911e-07, "epoch": 3.2488968092328583, "percentage": 64.98, "elapsed_time": "0:59:47", "remaining_time": "0:32:13", "throughput": 10248.42, "total_tokens": 36769856}
{"current_steps": 38290, "total_steps": 58920, "loss": 0.0, "lr": 6.584809459056137e-07, "epoch": 3.2493211133740667, "percentage": 64.99, "elapsed_time": "0:59:48", "remaining_time": "0:32:13", "throughput": 10248.75, "total_tokens": 36775104}
{"current_steps": 38295, "total_steps": 58920, "loss": 0.0258, "lr": 6.582025510033999e-07, "epoch": 3.249745417515275, "percentage": 64.99, "elapsed_time": "0:59:48", "remaining_time": "0:32:12", "throughput": 10249.13, "total_tokens": 36780544}
{"current_steps": 38298, "total_steps": 58920, "eval_loss": 0.149404376745224, "epoch": 3.25, "percentage": 65.0, "elapsed_time": "1:00:05", "remaining_time": "0:32:21", "throughput": 10202.64, "total_tokens": 36783040}
{"current_steps": 38300, "total_steps": 58920, "loss": 0.0, "lr": 6.579241860926789e-07, "epoch": 3.2501697216564835, "percentage": 65.0, "elapsed_time": "1:00:38", "remaining_time": "0:32:39", "throughput": 10108.98, "total_tokens": 36784768}
{"current_steps": 38305, "total_steps": 58920, "loss": 0.0, "lr": 6.576458511978753e-07, "epoch": 3.250594025797692, "percentage": 65.01, "elapsed_time": "1:00:39", "remaining_time": "0:32:38", "throughput": 10109.22, "total_tokens": 36789504}
{"current_steps": 38310, "total_steps": 58920, "loss": 0.0, "lr": 6.573675463434119e-07, "epoch": 3.2510183299389004, "percentage": 65.02, "elapsed_time": "1:00:39", "remaining_time": "0:32:38", "throughput": 10109.48, "total_tokens": 36794304}
{"current_steps": 38315, "total_steps": 58920, "loss": 0.0005, "lr": 6.570892715537094e-07, "epoch": 3.251442634080109, "percentage": 65.03, "elapsed_time": "1:00:39", "remaining_time": "0:32:37", "throughput": 10109.75, "total_tokens": 36799168}
{"current_steps": 38320, "total_steps": 58920, "loss": 0.0001, "lr": 6.568110268531852e-07, "epoch": 3.2518669382213172, "percentage": 65.04, "elapsed_time": "1:00:40", "remaining_time": "0:32:36", "throughput": 10109.89, "total_tokens": 36803456}
{"current_steps": 38325, "total_steps": 58920, "loss": 0.0, "lr": 6.565328122662543e-07, "epoch": 3.2522912423625256, "percentage": 65.05, "elapsed_time": "1:00:40", "remaining_time": "0:32:36", "throughput": 10110.13, "total_tokens": 36808192}
{"current_steps": 38330, "total_steps": 58920, "loss": 0.0, "lr": 6.562546278173291e-07, "epoch": 3.252715546503734, "percentage": 65.05, "elapsed_time": "1:00:41", "remaining_time": "0:32:35", "throughput": 10110.37, "total_tokens": 36812864}
{"current_steps": 38335, "total_steps": 58920, "loss": 0.0169, "lr": 6.559764735308193e-07, "epoch": 3.2531398506449425, "percentage": 65.06, "elapsed_time": "1:00:41", "remaining_time": "0:32:35", "throughput": 10110.69, "total_tokens": 36818048}
{"current_steps": 38340, "total_steps": 58920, "loss": 0.0, "lr": 6.556983494311317e-07, "epoch": 3.253564154786151, "percentage": 65.07, "elapsed_time": "1:00:41", "remaining_time": "0:32:34", "throughput": 10110.88, "total_tokens": 36822528}
{"current_steps": 38345, "total_steps": 58920, "loss": 0.0, "lr": 6.554202555426711e-07, "epoch": 3.253988458927359, "percentage": 65.08, "elapsed_time": "1:00:42", "remaining_time": "0:32:34", "throughput": 10111.18, "total_tokens": 36827584}
{"current_steps": 38350, "total_steps": 58920, "loss": 0.0, "lr": 6.551421918898387e-07, "epoch": 3.2544127630685677, "percentage": 65.09, "elapsed_time": "1:00:42", "remaining_time": "0:32:33", "throughput": 10111.4, "total_tokens": 36832192}
{"current_steps": 38355, "total_steps": 58920, "loss": 0.0, "lr": 6.548641584970338e-07, "epoch": 3.2548370672097757, "percentage": 65.1, "elapsed_time": "1:00:43", "remaining_time": "0:32:33", "throughput": 10111.73, "total_tokens": 36837376}
{"current_steps": 38360, "total_steps": 58920, "loss": 0.0, "lr": 6.545861553886532e-07, "epoch": 3.2552613713509846, "percentage": 65.11, "elapsed_time": "1:00:43", "remaining_time": "0:32:32", "throughput": 10111.9, "total_tokens": 36841792}
{"current_steps": 38365, "total_steps": 58920, "loss": 0.0, "lr": 6.543081825890901e-07, "epoch": 3.2556856754921926, "percentage": 65.11, "elapsed_time": "1:00:43", "remaining_time": "0:32:32", "throughput": 10112.09, "total_tokens": 36846336}
{"current_steps": 38370, "total_steps": 58920, "loss": 0.0, "lr": 6.540302401227361e-07, "epoch": 3.2561099796334014, "percentage": 65.12, "elapsed_time": "1:00:44", "remaining_time": "0:32:31", "throughput": 10112.36, "total_tokens": 36851200}
{"current_steps": 38375, "total_steps": 58920, "loss": 0.0, "lr": 6.537523280139791e-07, "epoch": 3.2565342837746094, "percentage": 65.13, "elapsed_time": "1:00:44", "remaining_time": "0:32:31", "throughput": 10112.63, "total_tokens": 36856064}
{"current_steps": 38380, "total_steps": 58920, "loss": 0.0, "lr": 6.534744462872053e-07, "epoch": 3.2569585879158183, "percentage": 65.14, "elapsed_time": "1:00:44", "remaining_time": "0:32:30", "throughput": 10112.93, "total_tokens": 36861120}
{"current_steps": 38385, "total_steps": 58920, "loss": 0.0, "lr": 6.531965949667978e-07, "epoch": 3.2573828920570262, "percentage": 65.15, "elapsed_time": "1:00:45", "remaining_time": "0:32:30", "throughput": 10113.23, "total_tokens": 36866112}
{"current_steps": 38390, "total_steps": 58920, "loss": 0.0, "lr": 6.529187740771369e-07, "epoch": 3.257807196198235, "percentage": 65.16, "elapsed_time": "1:00:45", "remaining_time": "0:32:29", "throughput": 10113.42, "total_tokens": 36870592}
{"current_steps": 38395, "total_steps": 58920, "loss": 0.0, "lr": 6.526409836426008e-07, "epoch": 3.258231500339443, "percentage": 65.16, "elapsed_time": "1:00:46", "remaining_time": "0:32:29", "throughput": 10113.79, "total_tokens": 36875904}
{"current_steps": 38400, "total_steps": 58920, "loss": 0.0, "lr": 6.523632236875637e-07, "epoch": 3.258655804480652, "percentage": 65.17, "elapsed_time": "1:00:46", "remaining_time": "0:32:28", "throughput": 10113.98, "total_tokens": 36880384}
{"current_steps": 38405, "total_steps": 58920, "loss": 0.0, "lr": 6.520854942363989e-07, "epoch": 3.25908010862186, "percentage": 65.18, "elapsed_time": "1:00:46", "remaining_time": "0:32:28", "throughput": 10114.31, "total_tokens": 36885568}
{"current_steps": 38410, "total_steps": 58920, "loss": 0.0, "lr": 6.518077953134756e-07, "epoch": 3.259504412763069, "percentage": 65.19, "elapsed_time": "1:00:47", "remaining_time": "0:32:27", "throughput": 10114.68, "total_tokens": 36890944}
{"current_steps": 38415, "total_steps": 58920, "loss": 0.0, "lr": 6.515301269431613e-07, "epoch": 3.2599287169042768, "percentage": 65.2, "elapsed_time": "1:00:47", "remaining_time": "0:32:27", "throughput": 10114.88, "total_tokens": 36895552}
{"current_steps": 38420, "total_steps": 58920, "loss": 0.0, "lr": 6.5125248914982e-07, "epoch": 3.2603530210454856, "percentage": 65.21, "elapsed_time": "1:00:48", "remaining_time": "0:32:26", "throughput": 10115.18, "total_tokens": 36900608}
{"current_steps": 38425, "total_steps": 58920, "loss": 0.0, "lr": 6.50974881957814e-07, "epoch": 3.2607773251866936, "percentage": 65.22, "elapsed_time": "1:00:48", "remaining_time": "0:32:25", "throughput": 10115.45, "total_tokens": 36905472}
{"current_steps": 38430, "total_steps": 58920, "loss": 0.0, "lr": 6.506973053915021e-07, "epoch": 3.2612016293279025, "percentage": 65.22, "elapsed_time": "1:00:48", "remaining_time": "0:32:25", "throughput": 10115.66, "total_tokens": 36910080}
{"current_steps": 38435, "total_steps": 58920, "loss": 0.0, "lr": 6.504197594752398e-07, "epoch": 3.2616259334691104, "percentage": 65.23, "elapsed_time": "1:00:49", "remaining_time": "0:32:24", "throughput": 10115.81, "total_tokens": 36914368}
{"current_steps": 38440, "total_steps": 58920, "loss": 0.0, "lr": 6.501422442333819e-07, "epoch": 3.2620502376103193, "percentage": 65.24, "elapsed_time": "1:00:49", "remaining_time": "0:32:24", "throughput": 10116.01, "total_tokens": 36918912}
{"current_steps": 38445, "total_steps": 58920, "loss": 0.0, "lr": 6.498647596902787e-07, "epoch": 3.2624745417515273, "percentage": 65.25, "elapsed_time": "1:00:49", "remaining_time": "0:32:23", "throughput": 10116.27, "total_tokens": 36923776}
{"current_steps": 38450, "total_steps": 58920, "loss": 0.0, "lr": 6.49587305870279e-07, "epoch": 3.262898845892736, "percentage": 65.26, "elapsed_time": "1:00:50", "remaining_time": "0:32:23", "throughput": 10116.49, "total_tokens": 36928512}
{"current_steps": 38455, "total_steps": 58920, "loss": 0.0, "lr": 6.493098827977277e-07, "epoch": 3.263323150033944, "percentage": 65.27, "elapsed_time": "1:00:50", "remaining_time": "0:32:22", "throughput": 10117.07, "total_tokens": 36934912}
{"current_steps": 38460, "total_steps": 58920, "loss": 0.0, "lr": 6.490324904969683e-07, "epoch": 3.263747454175153, "percentage": 65.27, "elapsed_time": "1:00:51", "remaining_time": "0:32:22", "throughput": 10117.24, "total_tokens": 36939392}
{"current_steps": 38465, "total_steps": 58920, "loss": 0.0, "lr": 6.487551289923404e-07, "epoch": 3.264171758316361, "percentage": 65.28, "elapsed_time": "1:00:51", "remaining_time": "0:32:21", "throughput": 10117.45, "total_tokens": 36944000}
{"current_steps": 38470, "total_steps": 58920, "loss": 0.0, "lr": 6.484777983081822e-07, "epoch": 3.2645960624575694, "percentage": 65.29, "elapsed_time": "1:00:51", "remaining_time": "0:32:21", "throughput": 10117.64, "total_tokens": 36948544}
{"current_steps": 38475, "total_steps": 58920, "loss": 0.0, "lr": 6.482004984688278e-07, "epoch": 3.265020366598778, "percentage": 65.3, "elapsed_time": "1:00:52", "remaining_time": "0:32:20", "throughput": 10117.92, "total_tokens": 36953472}
{"current_steps": 38480, "total_steps": 58920, "loss": 0.0, "lr": 6.479232294986092e-07, "epoch": 3.2654446707399862, "percentage": 65.31, "elapsed_time": "1:00:52", "remaining_time": "0:32:20", "throughput": 10118.19, "total_tokens": 36958336}
{"current_steps": 38485, "total_steps": 58920, "loss": 0.0, "lr": 6.476459914218566e-07, "epoch": 3.2658689748811947, "percentage": 65.32, "elapsed_time": "1:00:53", "remaining_time": "0:32:19", "throughput": 10118.49, "total_tokens": 36963328}
{"current_steps": 38490, "total_steps": 58920, "loss": 0.0, "lr": 6.473687842628955e-07, "epoch": 3.266293279022403, "percentage": 65.33, "elapsed_time": "1:00:53", "remaining_time": "0:32:19", "throughput": 10118.64, "total_tokens": 36967680}
{"current_steps": 38495, "total_steps": 58920, "loss": 0.0, "lr": 6.470916080460509e-07, "epoch": 3.2667175831636115, "percentage": 65.33, "elapsed_time": "1:00:53", "remaining_time": "0:32:18", "throughput": 10118.86, "total_tokens": 36972288}
{"current_steps": 38500, "total_steps": 58920, "loss": 0.0, "lr": 6.468144627956431e-07, "epoch": 3.26714188730482, "percentage": 65.34, "elapsed_time": "1:00:54", "remaining_time": "0:32:18", "throughput": 10118.99, "total_tokens": 36976512}
{"current_steps": 38505, "total_steps": 58920, "loss": 0.0, "lr": 6.465373485359913e-07, "epoch": 3.2675661914460283, "percentage": 65.35, "elapsed_time": "1:00:54", "remaining_time": "0:32:17", "throughput": 10119.23, "total_tokens": 36981248}
{"current_steps": 38510, "total_steps": 58920, "loss": 0.0474, "lr": 6.462602652914109e-07, "epoch": 3.2679904955872368, "percentage": 65.36, "elapsed_time": "1:00:54", "remaining_time": "0:32:17", "throughput": 10119.52, "total_tokens": 36986240}
{"current_steps": 38515, "total_steps": 58920, "loss": 0.0, "lr": 6.459832130862153e-07, "epoch": 3.268414799728445, "percentage": 65.37, "elapsed_time": "1:00:55", "remaining_time": "0:32:16", "throughput": 10119.89, "total_tokens": 36991552}
{"current_steps": 38520, "total_steps": 58920, "loss": 0.0, "lr": 6.457061919447144e-07, "epoch": 3.2688391038696536, "percentage": 65.38, "elapsed_time": "1:00:55", "remaining_time": "0:32:16", "throughput": 10120.13, "total_tokens": 36996288}
{"current_steps": 38525, "total_steps": 58920, "loss": 0.0, "lr": 6.454292018912158e-07, "epoch": 3.269263408010862, "percentage": 65.39, "elapsed_time": "1:00:56", "remaining_time": "0:32:15", "throughput": 10120.46, "total_tokens": 37001408}
{"current_steps": 38530, "total_steps": 58920, "loss": 0.0, "lr": 6.451522429500248e-07, "epoch": 3.2696877121520704, "percentage": 65.39, "elapsed_time": "1:00:56", "remaining_time": "0:32:15", "throughput": 10120.75, "total_tokens": 37006400}
{"current_steps": 38535, "total_steps": 58920, "loss": 0.0001, "lr": 6.448753151454432e-07, "epoch": 3.270112016293279, "percentage": 65.4, "elapsed_time": "1:00:56", "remaining_time": "0:32:14", "throughput": 10120.94, "total_tokens": 37010880}
{"current_steps": 38540, "total_steps": 58920, "loss": 0.0001, "lr": 6.445984185017706e-07, "epoch": 3.2705363204344873, "percentage": 65.41, "elapsed_time": "1:00:57", "remaining_time": "0:32:13", "throughput": 10121.15, "total_tokens": 37015488}
{"current_steps": 38545, "total_steps": 58920, "loss": 0.0078, "lr": 6.443215530433032e-07, "epoch": 3.2709606245756957, "percentage": 65.42, "elapsed_time": "1:00:57", "remaining_time": "0:32:13", "throughput": 10121.3, "total_tokens": 37019840}
{"current_steps": 38550, "total_steps": 58920, "loss": 0.0, "lr": 6.440447187943361e-07, "epoch": 3.271384928716904, "percentage": 65.43, "elapsed_time": "1:00:57", "remaining_time": "0:32:12", "throughput": 10121.52, "total_tokens": 37024448}
{"current_steps": 38555, "total_steps": 58920, "loss": 0.0, "lr": 6.437679157791595e-07, "epoch": 3.2718092328581125, "percentage": 65.44, "elapsed_time": "1:00:58", "remaining_time": "0:32:12", "throughput": 10121.83, "total_tokens": 37029504}
{"current_steps": 38560, "total_steps": 58920, "loss": 0.0, "lr": 6.434911440220618e-07, "epoch": 3.272233536999321, "percentage": 65.44, "elapsed_time": "1:00:58", "remaining_time": "0:32:11", "throughput": 10122.13, "total_tokens": 37034560}
{"current_steps": 38565, "total_steps": 58920, "loss": 0.0089, "lr": 6.432144035473293e-07, "epoch": 3.2726578411405294, "percentage": 65.45, "elapsed_time": "1:00:59", "remaining_time": "0:32:11", "throughput": 10122.4, "total_tokens": 37039488}
{"current_steps": 38570, "total_steps": 58920, "loss": 0.0, "lr": 6.429376943792443e-07, "epoch": 3.273082145281738, "percentage": 65.46, "elapsed_time": "1:00:59", "remaining_time": "0:32:10", "throughput": 10122.92, "total_tokens": 37045568}
{"current_steps": 38575, "total_steps": 58920, "loss": 0.0, "lr": 6.42661016542088e-07, "epoch": 3.273506449422946, "percentage": 65.47, "elapsed_time": "1:00:59", "remaining_time": "0:32:10", "throughput": 10123.14, "total_tokens": 37050240}
{"current_steps": 38580, "total_steps": 58920, "loss": 0.0014, "lr": 6.42384370060137e-07, "epoch": 3.2739307535641546, "percentage": 65.48, "elapsed_time": "1:01:00", "remaining_time": "0:32:09", "throughput": 10123.42, "total_tokens": 37055232}
{"current_steps": 38585, "total_steps": 58920, "loss": 0.0, "lr": 6.421077549576667e-07, "epoch": 3.274355057705363, "percentage": 65.49, "elapsed_time": "1:01:00", "remaining_time": "0:32:09", "throughput": 10123.59, "total_tokens": 37059712}
{"current_steps": 38590, "total_steps": 58920, "loss": 0.0, "lr": 6.418311712589483e-07, "epoch": 3.2747793618465715, "percentage": 65.5, "elapsed_time": "1:01:01", "remaining_time": "0:32:08", "throughput": 10123.92, "total_tokens": 37064832}
{"current_steps": 38595, "total_steps": 58920, "loss": 0.0, "lr": 6.415546189882517e-07, "epoch": 3.27520366598778, "percentage": 65.5, "elapsed_time": "1:01:01", "remaining_time": "0:32:08", "throughput": 10124.27, "total_tokens": 37070144}
{"current_steps": 38600, "total_steps": 58920, "loss": 0.0, "lr": 6.412780981698432e-07, "epoch": 3.2756279701289883, "percentage": 65.51, "elapsed_time": "1:01:01", "remaining_time": "0:32:07", "throughput": 10124.5, "total_tokens": 37074816}
{"current_steps": 38605, "total_steps": 58920, "loss": 0.0, "lr": 6.410016088279861e-07, "epoch": 3.2760522742701967, "percentage": 65.52, "elapsed_time": "1:01:02", "remaining_time": "0:32:07", "throughput": 10124.73, "total_tokens": 37079616}
{"current_steps": 38610, "total_steps": 58920, "loss": 0.0, "lr": 6.407251509869423e-07, "epoch": 3.276476578411405, "percentage": 65.53, "elapsed_time": "1:01:02", "remaining_time": "0:32:06", "throughput": 10125.09, "total_tokens": 37084992}
{"current_steps": 38615, "total_steps": 58920, "loss": 0.0, "lr": 6.404487246709687e-07, "epoch": 3.2769008825526136, "percentage": 65.54, "elapsed_time": "1:01:03", "remaining_time": "0:32:06", "throughput": 10125.29, "total_tokens": 37089600}
{"current_steps": 38620, "total_steps": 58920, "loss": 0.0, "lr": 6.401723299043218e-07, "epoch": 3.277325186693822, "percentage": 65.55, "elapsed_time": "1:01:03", "remaining_time": "0:32:05", "throughput": 10125.46, "total_tokens": 37094080}
{"current_steps": 38625, "total_steps": 58920, "loss": 0.0, "lr": 6.398959667112533e-07, "epoch": 3.2777494908350304, "percentage": 65.55, "elapsed_time": "1:01:03", "remaining_time": "0:32:05", "throughput": 10125.76, "total_tokens": 37099136}
{"current_steps": 38630, "total_steps": 58920, "loss": 0.0, "lr": 6.396196351160139e-07, "epoch": 3.278173794976239, "percentage": 65.56, "elapsed_time": "1:01:04", "remaining_time": "0:32:04", "throughput": 10125.99, "total_tokens": 37103808}
{"current_steps": 38635, "total_steps": 58920, "loss": 0.0, "lr": 6.393433351428501e-07, "epoch": 3.2785980991174473, "percentage": 65.57, "elapsed_time": "1:01:04", "remaining_time": "0:32:04", "throughput": 10126.11, "total_tokens": 37108032}
{"current_steps": 38640, "total_steps": 58920, "loss": 0.0, "lr": 6.39067066816007e-07, "epoch": 3.2790224032586557, "percentage": 65.58, "elapsed_time": "1:01:04", "remaining_time": "0:32:03", "throughput": 10126.32, "total_tokens": 37112640}
{"current_steps": 38645, "total_steps": 58920, "loss": 0.0001, "lr": 6.387908301597255e-07, "epoch": 3.279446707399864, "percentage": 65.59, "elapsed_time": "1:01:05", "remaining_time": "0:32:03", "throughput": 10126.57, "total_tokens": 37117440}
{"current_steps": 38650, "total_steps": 58920, "loss": 0.0, "lr": 6.385146251982443e-07, "epoch": 3.2798710115410725, "percentage": 65.6, "elapsed_time": "1:01:05", "remaining_time": "0:32:02", "throughput": 10126.83, "total_tokens": 37122304}
{"current_steps": 38655, "total_steps": 58920, "loss": 0.0, "lr": 6.382384519557996e-07, "epoch": 3.280295315682281, "percentage": 65.61, "elapsed_time": "1:01:06", "remaining_time": "0:32:01", "throughput": 10126.98, "total_tokens": 37126656}
{"current_steps": 38660, "total_steps": 58920, "loss": 0.0, "lr": 6.379623104566245e-07, "epoch": 3.2807196198234894, "percentage": 65.61, "elapsed_time": "1:01:06", "remaining_time": "0:32:01", "throughput": 10127.24, "total_tokens": 37131520}
{"current_steps": 38665, "total_steps": 58920, "loss": 0.0291, "lr": 6.3768620072495e-07, "epoch": 3.281143923964698, "percentage": 65.62, "elapsed_time": "1:01:06", "remaining_time": "0:32:00", "throughput": 10127.42, "total_tokens": 37136000}
{"current_steps": 38670, "total_steps": 58920, "loss": 0.0533, "lr": 6.374101227850026e-07, "epoch": 3.281568228105906, "percentage": 65.63, "elapsed_time": "1:01:07", "remaining_time": "0:32:00", "throughput": 10127.82, "total_tokens": 37141568}
{"current_steps": 38675, "total_steps": 58920, "loss": 0.0, "lr": 6.371340766610085e-07, "epoch": 3.2819925322471146, "percentage": 65.64, "elapsed_time": "1:01:07", "remaining_time": "0:31:59", "throughput": 10127.95, "total_tokens": 37145856}
{"current_steps": 38680, "total_steps": 58920, "loss": 0.0, "lr": 6.368580623771884e-07, "epoch": 3.282416836388323, "percentage": 65.65, "elapsed_time": "1:01:08", "remaining_time": "0:31:59", "throughput": 10128.19, "total_tokens": 37150592}
{"current_steps": 38685, "total_steps": 58920, "loss": 0.0, "lr": 6.365820799577628e-07, "epoch": 3.2828411405295315, "percentage": 65.66, "elapsed_time": "1:01:08", "remaining_time": "0:31:58", "throughput": 10128.52, "total_tokens": 37155776}
{"current_steps": 38690, "total_steps": 58920, "loss": 0.0, "lr": 6.363061294269474e-07, "epoch": 3.28326544467074, "percentage": 65.67, "elapsed_time": "1:01:08", "remaining_time": "0:31:58", "throughput": 10128.74, "total_tokens": 37160448}
{"current_steps": 38695, "total_steps": 58920, "loss": 0.0, "lr": 6.360302108089557e-07, "epoch": 3.2836897488119483, "percentage": 65.67, "elapsed_time": "1:01:09", "remaining_time": "0:31:57", "throughput": 10128.91, "total_tokens": 37164928}
{"current_steps": 38700, "total_steps": 58920, "loss": 0.0, "lr": 6.357543241279992e-07, "epoch": 3.2841140529531567, "percentage": 65.68, "elapsed_time": "1:01:09", "remaining_time": "0:31:57", "throughput": 10129.09, "total_tokens": 37169408}
{"current_steps": 38705, "total_steps": 58920, "loss": 0.0, "lr": 6.354784694082856e-07, "epoch": 3.284538357094365, "percentage": 65.69, "elapsed_time": "1:01:09", "remaining_time": "0:31:56", "throughput": 10129.31, "total_tokens": 37174080}
{"current_steps": 38710, "total_steps": 58920, "loss": 0.0, "lr": 6.352026466740204e-07, "epoch": 3.2849626612355736, "percentage": 65.7, "elapsed_time": "1:01:10", "remaining_time": "0:31:56", "throughput": 10129.54, "total_tokens": 37178816}
{"current_steps": 38715, "total_steps": 58920, "loss": 0.0, "lr": 6.349268559494053e-07, "epoch": 3.285386965376782, "percentage": 65.71, "elapsed_time": "1:01:10", "remaining_time": "0:31:55", "throughput": 10129.78, "total_tokens": 37183680}
{"current_steps": 38720, "total_steps": 58920, "loss": 0.0919, "lr": 6.34651097258641e-07, "epoch": 3.2858112695179904, "percentage": 65.72, "elapsed_time": "1:01:11", "remaining_time": "0:31:55", "throughput": 10129.96, "total_tokens": 37188160}
{"current_steps": 38725, "total_steps": 58920, "loss": 0.0, "lr": 6.343753706259238e-07, "epoch": 3.286235573659199, "percentage": 65.72, "elapsed_time": "1:01:11", "remaining_time": "0:31:54", "throughput": 10130.28, "total_tokens": 37193344}
{"current_steps": 38730, "total_steps": 58920, "loss": 0.0103, "lr": 6.340996760754473e-07, "epoch": 3.2866598778004072, "percentage": 65.73, "elapsed_time": "1:01:11", "remaining_time": "0:31:54", "throughput": 10130.54, "total_tokens": 37198208}
{"current_steps": 38735, "total_steps": 58920, "loss": 0.0, "lr": 6.338240136314037e-07, "epoch": 3.2870841819416157, "percentage": 65.74, "elapsed_time": "1:01:12", "remaining_time": "0:31:53", "throughput": 10130.77, "total_tokens": 37202944}
{"current_steps": 38740, "total_steps": 58920, "loss": 0.0, "lr": 6.335483833179804e-07, "epoch": 3.287508486082824, "percentage": 65.75, "elapsed_time": "1:01:12", "remaining_time": "0:31:53", "throughput": 10130.95, "total_tokens": 37207488}
{"current_steps": 38745, "total_steps": 58920, "loss": 0.0, "lr": 6.332727851593636e-07, "epoch": 3.2879327902240325, "percentage": 65.76, "elapsed_time": "1:01:13", "remaining_time": "0:31:52", "throughput": 10131.22, "total_tokens": 37212416}
{"current_steps": 38750, "total_steps": 58920, "loss": 0.0, "lr": 6.329972191797359e-07, "epoch": 3.288357094365241, "percentage": 65.77, "elapsed_time": "1:01:13", "remaining_time": "0:31:52", "throughput": 10131.55, "total_tokens": 37217664}
{"current_steps": 38755, "total_steps": 58920, "loss": 0.0, "lr": 6.32721685403277e-07, "epoch": 3.2887813985064493, "percentage": 65.78, "elapsed_time": "1:01:13", "remaining_time": "0:31:51", "throughput": 10131.76, "total_tokens": 37222336}
{"current_steps": 38760, "total_steps": 58920, "loss": 0.0, "lr": 6.324461838541641e-07, "epoch": 3.2892057026476578, "percentage": 65.78, "elapsed_time": "1:01:14", "remaining_time": "0:31:51", "throughput": 10132.0, "total_tokens": 37227072}
{"current_steps": 38765, "total_steps": 58920, "loss": 0.0, "lr": 6.321707145565719e-07, "epoch": 3.289630006788866, "percentage": 65.79, "elapsed_time": "1:01:14", "remaining_time": "0:31:50", "throughput": 10132.13, "total_tokens": 37231360}
{"current_steps": 38770, "total_steps": 58920, "loss": 0.0, "lr": 6.318952775346714e-07, "epoch": 3.2900543109300746, "percentage": 65.8, "elapsed_time": "1:01:14", "remaining_time": "0:31:49", "throughput": 10132.41, "total_tokens": 37236288}
{"current_steps": 38775, "total_steps": 58920, "loss": 0.0, "lr": 6.316198728126309e-07, "epoch": 3.290478615071283, "percentage": 65.81, "elapsed_time": "1:01:15", "remaining_time": "0:31:49", "throughput": 10132.81, "total_tokens": 37241856}
{"current_steps": 38780, "total_steps": 58920, "loss": 0.0, "lr": 6.313445004146168e-07, "epoch": 3.2909029192124915, "percentage": 65.82, "elapsed_time": "1:01:15", "remaining_time": "0:31:48", "throughput": 10133.0, "total_tokens": 37246400}
{"current_steps": 38785, "total_steps": 58920, "loss": 0.0, "lr": 6.310691603647914e-07, "epoch": 3.2913272233537, "percentage": 65.83, "elapsed_time": "1:01:16", "remaining_time": "0:31:48", "throughput": 10133.37, "total_tokens": 37251840}
{"current_steps": 38790, "total_steps": 58920, "loss": 0.0, "lr": 6.307938526873157e-07, "epoch": 3.2917515274949083, "percentage": 65.84, "elapsed_time": "1:01:16", "remaining_time": "0:31:47", "throughput": 10133.55, "total_tokens": 37256384}
{"current_steps": 38795, "total_steps": 58920, "loss": 0.0, "lr": 6.305185774063459e-07, "epoch": 3.2921758316361167, "percentage": 65.84, "elapsed_time": "1:01:16", "remaining_time": "0:31:47", "throughput": 10133.77, "total_tokens": 37261056}
{"current_steps": 38800, "total_steps": 58920, "loss": 0.0, "lr": 6.302433345460374e-07, "epoch": 3.292600135777325, "percentage": 65.85, "elapsed_time": "1:01:17", "remaining_time": "0:31:46", "throughput": 10134.03, "total_tokens": 37265984}
{"current_steps": 38805, "total_steps": 58920, "loss": 0.0, "lr": 6.299681241305408e-07, "epoch": 3.2930244399185336, "percentage": 65.86, "elapsed_time": "1:01:17", "remaining_time": "0:31:46", "throughput": 10134.51, "total_tokens": 37271936}
{"current_steps": 38810, "total_steps": 58920, "loss": 0.0, "lr": 6.296929461840056e-07, "epoch": 3.293448744059742, "percentage": 65.87, "elapsed_time": "1:01:18", "remaining_time": "0:31:45", "throughput": 10134.7, "total_tokens": 37276544}
{"current_steps": 38815, "total_steps": 58920, "loss": 0.0, "lr": 6.294178007305775e-07, "epoch": 3.2938730482009504, "percentage": 65.88, "elapsed_time": "1:01:18", "remaining_time": "0:31:45", "throughput": 10134.87, "total_tokens": 37281024}
{"current_steps": 38820, "total_steps": 58920, "loss": 0.0, "lr": 6.29142687794399e-07, "epoch": 3.294297352342159, "percentage": 65.89, "elapsed_time": "1:01:18", "remaining_time": "0:31:44", "throughput": 10135.12, "total_tokens": 37285952}
{"current_steps": 38825, "total_steps": 58920, "loss": 0.0001, "lr": 6.288676073996113e-07, "epoch": 3.2947216564833672, "percentage": 65.89, "elapsed_time": "1:01:19", "remaining_time": "0:31:44", "throughput": 10135.28, "total_tokens": 37290368}
{"current_steps": 38830, "total_steps": 58920, "loss": 0.0, "lr": 6.285925595703505e-07, "epoch": 3.2951459606245757, "percentage": 65.9, "elapsed_time": "1:01:19", "remaining_time": "0:31:43", "throughput": 10135.46, "total_tokens": 37294912}
{"current_steps": 38835, "total_steps": 58920, "loss": 0.0, "lr": 6.283175443307521e-07, "epoch": 3.295570264765784, "percentage": 65.91, "elapsed_time": "1:01:20", "remaining_time": "0:31:43", "throughput": 10135.73, "total_tokens": 37299904}
{"current_steps": 38840, "total_steps": 58920, "loss": 0.0, "lr": 6.280425617049467e-07, "epoch": 3.2959945689069925, "percentage": 65.92, "elapsed_time": "1:01:20", "remaining_time": "0:31:42", "throughput": 10136.01, "total_tokens": 37304896}
{"current_steps": 38845, "total_steps": 58920, "loss": 0.0, "lr": 6.277676117170639e-07, "epoch": 3.296418873048201, "percentage": 65.93, "elapsed_time": "1:01:20", "remaining_time": "0:31:42", "throughput": 10136.18, "total_tokens": 37309312}
{"current_steps": 38850, "total_steps": 58920, "loss": 0.0, "lr": 6.274926943912293e-07, "epoch": 3.2968431771894093, "percentage": 65.94, "elapsed_time": "1:01:21", "remaining_time": "0:31:41", "throughput": 10136.45, "total_tokens": 37314304}
{"current_steps": 38855, "total_steps": 58920, "loss": 0.0, "lr": 6.272178097515656e-07, "epoch": 3.2972674813306178, "percentage": 65.95, "elapsed_time": "1:01:21", "remaining_time": "0:31:41", "throughput": 10136.74, "total_tokens": 37319296}
{"current_steps": 38860, "total_steps": 58920, "loss": 0.0, "lr": 6.269429578221934e-07, "epoch": 3.297691785471826, "percentage": 65.95, "elapsed_time": "1:01:21", "remaining_time": "0:31:40", "throughput": 10136.99, "total_tokens": 37324160}
{"current_steps": 38865, "total_steps": 58920, "loss": 0.0, "lr": 6.266681386272295e-07, "epoch": 3.2981160896130346, "percentage": 65.96, "elapsed_time": "1:01:22", "remaining_time": "0:31:40", "throughput": 10137.4, "total_tokens": 37329792}
{"current_steps": 38870, "total_steps": 58920, "loss": 0.0, "lr": 6.263933521907887e-07, "epoch": 3.298540393754243, "percentage": 65.97, "elapsed_time": "1:01:22", "remaining_time": "0:31:39", "throughput": 10137.6, "total_tokens": 37334400}
{"current_steps": 38875, "total_steps": 58920, "loss": 0.0, "lr": 6.26118598536982e-07, "epoch": 3.2989646978954514, "percentage": 65.98, "elapsed_time": "1:01:23", "remaining_time": "0:31:39", "throughput": 10137.83, "total_tokens": 37339136}
{"current_steps": 38880, "total_steps": 58920, "loss": 0.0, "lr": 6.258438776899189e-07, "epoch": 3.29938900203666, "percentage": 65.99, "elapsed_time": "1:01:23", "remaining_time": "0:31:38", "throughput": 10137.99, "total_tokens": 37343488}
{"current_steps": 38885, "total_steps": 58920, "loss": 0.0, "lr": 6.255691896737042e-07, "epoch": 3.2998133061778683, "percentage": 66.0, "elapsed_time": "1:01:23", "remaining_time": "0:31:38", "throughput": 10138.25, "total_tokens": 37348416}
{"current_steps": 38890, "total_steps": 58920, "loss": 0.0003, "lr": 6.252945345124416e-07, "epoch": 3.3002376103190767, "percentage": 66.0, "elapsed_time": "1:01:24", "remaining_time": "0:31:37", "throughput": 10138.46, "total_tokens": 37353024}
{"current_steps": 38895, "total_steps": 58920, "loss": 0.0, "lr": 6.250199122302308e-07, "epoch": 3.300661914460285, "percentage": 66.01, "elapsed_time": "1:01:24", "remaining_time": "0:31:37", "throughput": 10138.7, "total_tokens": 37357760}
{"current_steps": 38900, "total_steps": 58920, "loss": 0.0219, "lr": 6.247453228511686e-07, "epoch": 3.3010862186014935, "percentage": 66.02, "elapsed_time": "1:01:25", "remaining_time": "0:31:36", "throughput": 10138.97, "total_tokens": 37362624}
{"current_steps": 38905, "total_steps": 58920, "loss": 0.0, "lr": 6.244707663993494e-07, "epoch": 3.301510522742702, "percentage": 66.03, "elapsed_time": "1:01:25", "remaining_time": "0:31:36", "throughput": 10139.18, "total_tokens": 37367232}
{"current_steps": 38910, "total_steps": 58920, "loss": 0.0, "lr": 6.241962428988645e-07, "epoch": 3.3019348268839104, "percentage": 66.04, "elapsed_time": "1:01:25", "remaining_time": "0:31:35", "throughput": 10139.33, "total_tokens": 37371584}
{"current_steps": 38915, "total_steps": 58920, "loss": 0.0001, "lr": 6.239217523738027e-07, "epoch": 3.302359131025119, "percentage": 66.05, "elapsed_time": "1:01:26", "remaining_time": "0:31:34", "throughput": 10139.52, "total_tokens": 37376128}
{"current_steps": 38920, "total_steps": 58920, "loss": 0.0, "lr": 6.236472948482492e-07, "epoch": 3.302783435166327, "percentage": 66.06, "elapsed_time": "1:01:26", "remaining_time": "0:31:34", "throughput": 10139.79, "total_tokens": 37381056}
{"current_steps": 38925, "total_steps": 58920, "loss": 0.0, "lr": 6.23372870346287e-07, "epoch": 3.3032077393075356, "percentage": 66.06, "elapsed_time": "1:01:26", "remaining_time": "0:31:33", "throughput": 10140.09, "total_tokens": 37386112}
{"current_steps": 38930, "total_steps": 58920, "loss": 0.0, "lr": 6.230984788919951e-07, "epoch": 3.303632043448744, "percentage": 66.07, "elapsed_time": "1:01:27", "remaining_time": "0:31:33", "throughput": 10140.18, "total_tokens": 37390208}
{"current_steps": 38935, "total_steps": 58920, "loss": 0.0, "lr": 6.228241205094513e-07, "epoch": 3.3040563475899525, "percentage": 66.08, "elapsed_time": "1:01:27", "remaining_time": "0:31:32", "throughput": 10140.46, "total_tokens": 37395200}
{"current_steps": 38940, "total_steps": 58920, "loss": 0.0001, "lr": 6.225497952227292e-07, "epoch": 3.304480651731161, "percentage": 66.09, "elapsed_time": "1:01:28", "remaining_time": "0:31:32", "throughput": 10140.8, "total_tokens": 37400448}
{"current_steps": 38945, "total_steps": 58920, "loss": 0.0, "lr": 6.222755030558994e-07, "epoch": 3.3049049558723693, "percentage": 66.1, "elapsed_time": "1:01:28", "remaining_time": "0:31:31", "throughput": 10141.11, "total_tokens": 37405568}
{"current_steps": 38950, "total_steps": 58920, "loss": 0.0, "lr": 6.220012440330309e-07, "epoch": 3.3053292600135777, "percentage": 66.11, "elapsed_time": "1:01:28", "remaining_time": "0:31:31", "throughput": 10141.44, "total_tokens": 37410880}
{"current_steps": 38955, "total_steps": 58920, "loss": 0.0, "lr": 6.217270181781882e-07, "epoch": 3.305753564154786, "percentage": 66.12, "elapsed_time": "1:01:29", "remaining_time": "0:31:30", "throughput": 10141.68, "total_tokens": 37415616}
{"current_steps": 38960, "total_steps": 58920, "loss": 0.0, "lr": 6.214528255154339e-07, "epoch": 3.3061778682959946, "percentage": 66.12, "elapsed_time": "1:01:29", "remaining_time": "0:31:30", "throughput": 10141.85, "total_tokens": 37420096}
{"current_steps": 38965, "total_steps": 58920, "loss": 0.0396, "lr": 6.211786660688274e-07, "epoch": 3.306602172437203, "percentage": 66.13, "elapsed_time": "1:01:30", "remaining_time": "0:31:29", "throughput": 10142.16, "total_tokens": 37425216}
{"current_steps": 38970, "total_steps": 58920, "loss": 0.0, "lr": 6.209045398624253e-07, "epoch": 3.3070264765784114, "percentage": 66.14, "elapsed_time": "1:01:30", "remaining_time": "0:31:29", "throughput": 10142.36, "total_tokens": 37429824}
{"current_steps": 38975, "total_steps": 58920, "loss": 0.0, "lr": 6.206304469202814e-07, "epoch": 3.30745078071962, "percentage": 66.15, "elapsed_time": "1:01:30", "remaining_time": "0:31:28", "throughput": 10142.71, "total_tokens": 37435136}
{"current_steps": 38980, "total_steps": 58920, "loss": 0.0, "lr": 6.203563872664455e-07, "epoch": 3.3078750848608283, "percentage": 66.16, "elapsed_time": "1:01:31", "remaining_time": "0:31:28", "throughput": 10142.96, "total_tokens": 37440000}
{"current_steps": 38985, "total_steps": 58920, "loss": 0.0, "lr": 6.200823609249665e-07, "epoch": 3.3082993890020367, "percentage": 66.17, "elapsed_time": "1:01:31", "remaining_time": "0:31:27", "throughput": 10143.16, "total_tokens": 37444544}
{"current_steps": 38990, "total_steps": 58920, "loss": 0.0, "lr": 6.198083679198881e-07, "epoch": 3.308723693143245, "percentage": 66.17, "elapsed_time": "1:01:31", "remaining_time": "0:31:27", "throughput": 10143.39, "total_tokens": 37449216}
{"current_steps": 38995, "total_steps": 58920, "loss": 0.0, "lr": 6.195344082752529e-07, "epoch": 3.3091479972844535, "percentage": 66.18, "elapsed_time": "1:01:32", "remaining_time": "0:31:26", "throughput": 10143.54, "total_tokens": 37453568}
{"current_steps": 39000, "total_steps": 58920, "loss": 0.0, "lr": 6.192604820150997e-07, "epoch": 3.309572301425662, "percentage": 66.19, "elapsed_time": "1:01:32", "remaining_time": "0:31:26", "throughput": 10143.8, "total_tokens": 37458432}
{"current_steps": 39005, "total_steps": 58920, "loss": 0.0, "lr": 6.189865891634649e-07, "epoch": 3.3099966055668704, "percentage": 66.2, "elapsed_time": "1:01:33", "remaining_time": "0:31:25", "throughput": 10144.03, "total_tokens": 37463104}
{"current_steps": 39010, "total_steps": 58920, "loss": 0.0, "lr": 6.187127297443808e-07, "epoch": 3.310420909708079, "percentage": 66.21, "elapsed_time": "1:01:33", "remaining_time": "0:31:25", "throughput": 10144.16, "total_tokens": 37467328}
{"current_steps": 39015, "total_steps": 58920, "loss": 0.0003, "lr": 6.184389037818785e-07, "epoch": 3.310845213849287, "percentage": 66.22, "elapsed_time": "1:01:33", "remaining_time": "0:31:24", "throughput": 10144.31, "total_tokens": 37471744}
{"current_steps": 39020, "total_steps": 58920, "loss": 0.0, "lr": 6.181651112999844e-07, "epoch": 3.3112695179904956, "percentage": 66.23, "elapsed_time": "1:01:34", "remaining_time": "0:31:24", "throughput": 10144.58, "total_tokens": 37476608}
{"current_steps": 39025, "total_steps": 58920, "loss": 0.0, "lr": 6.178913523227231e-07, "epoch": 3.311693822131704, "percentage": 66.23, "elapsed_time": "1:01:34", "remaining_time": "0:31:23", "throughput": 10145.01, "total_tokens": 37482304}
{"current_steps": 39030, "total_steps": 58920, "loss": 0.0, "lr": 6.176176268741164e-07, "epoch": 3.3121181262729125, "percentage": 66.24, "elapsed_time": "1:01:35", "remaining_time": "0:31:23", "throughput": 10145.35, "total_tokens": 37487616}
{"current_steps": 39035, "total_steps": 58920, "loss": 0.0, "lr": 6.173439349781819e-07, "epoch": 3.312542430414121, "percentage": 66.25, "elapsed_time": "1:01:35", "remaining_time": "0:31:22", "throughput": 10145.69, "total_tokens": 37492864}
{"current_steps": 39040, "total_steps": 58920, "loss": 0.0, "lr": 6.170702766589361e-07, "epoch": 3.3129667345553293, "percentage": 66.26, "elapsed_time": "1:01:35", "remaining_time": "0:31:21", "throughput": 10145.99, "total_tokens": 37497920}
{"current_steps": 39045, "total_steps": 58920, "loss": 0.0, "lr": 6.167966519403905e-07, "epoch": 3.3133910386965377, "percentage": 66.27, "elapsed_time": "1:01:36", "remaining_time": "0:31:21", "throughput": 10146.16, "total_tokens": 37502336}
{"current_steps": 39050, "total_steps": 58920, "loss": 0.0, "lr": 6.165230608465555e-07, "epoch": 3.313815342837746, "percentage": 66.28, "elapsed_time": "1:01:36", "remaining_time": "0:31:20", "throughput": 10146.54, "total_tokens": 37507712}
{"current_steps": 39055, "total_steps": 58920, "loss": 0.0, "lr": 6.162495034014369e-07, "epoch": 3.3142396469789546, "percentage": 66.28, "elapsed_time": "1:01:36", "remaining_time": "0:31:20", "throughput": 10146.68, "total_tokens": 37512000}
{"current_steps": 39060, "total_steps": 58920, "loss": 0.0, "lr": 6.159759796290392e-07, "epoch": 3.314663951120163, "percentage": 66.29, "elapsed_time": "1:01:37", "remaining_time": "0:31:19", "throughput": 10146.96, "total_tokens": 37516992}
{"current_steps": 39065, "total_steps": 58920, "loss": 0.0, "lr": 6.157024895533629e-07, "epoch": 3.3150882552613714, "percentage": 66.3, "elapsed_time": "1:01:37", "remaining_time": "0:31:19", "throughput": 10147.17, "total_tokens": 37521600}
{"current_steps": 39070, "total_steps": 58920, "loss": 0.0, "lr": 6.154290331984051e-07, "epoch": 3.31551255940258, "percentage": 66.31, "elapsed_time": "1:01:38", "remaining_time": "0:31:18", "throughput": 10147.35, "total_tokens": 37526080}
{"current_steps": 39075, "total_steps": 58920, "loss": 0.0, "lr": 6.151556105881618e-07, "epoch": 3.3159368635437882, "percentage": 66.32, "elapsed_time": "1:01:38", "remaining_time": "0:31:18", "throughput": 10147.72, "total_tokens": 37531520}
{"current_steps": 39080, "total_steps": 58920, "loss": 0.0244, "lr": 6.148822217466237e-07, "epoch": 3.3163611676849967, "percentage": 66.33, "elapsed_time": "1:01:38", "remaining_time": "0:31:17", "throughput": 10147.93, "total_tokens": 37536128}
{"current_steps": 39085, "total_steps": 58920, "loss": 0.0, "lr": 6.146088666977803e-07, "epoch": 3.316785471826205, "percentage": 66.34, "elapsed_time": "1:01:39", "remaining_time": "0:31:17", "throughput": 10148.32, "total_tokens": 37541568}
{"current_steps": 39090, "total_steps": 58920, "loss": 0.0, "lr": 6.143355454656174e-07, "epoch": 3.3172097759674135, "percentage": 66.34, "elapsed_time": "1:01:39", "remaining_time": "0:31:16", "throughput": 10148.53, "total_tokens": 37546176}
{"current_steps": 39095, "total_steps": 58920, "loss": 0.0, "lr": 6.140622580741182e-07, "epoch": 3.317634080108622, "percentage": 66.35, "elapsed_time": "1:01:40", "remaining_time": "0:31:16", "throughput": 10148.91, "total_tokens": 37551680}
{"current_steps": 39100, "total_steps": 58920, "loss": 0.0003, "lr": 6.137890045472625e-07, "epoch": 3.3180583842498304, "percentage": 66.36, "elapsed_time": "1:01:40", "remaining_time": "0:31:15", "throughput": 10149.05, "total_tokens": 37555968}
{"current_steps": 39105, "total_steps": 58920, "loss": 0.0, "lr": 6.135157849090267e-07, "epoch": 3.3184826883910388, "percentage": 66.37, "elapsed_time": "1:01:40", "remaining_time": "0:31:15", "throughput": 10149.41, "total_tokens": 37561344}
{"current_steps": 39110, "total_steps": 58920, "loss": 0.0, "lr": 6.132425991833859e-07, "epoch": 3.318906992532247, "percentage": 66.38, "elapsed_time": "1:01:41", "remaining_time": "0:31:14", "throughput": 10149.62, "total_tokens": 37565952}
{"current_steps": 39115, "total_steps": 58920, "loss": 0.0, "lr": 6.129694473943102e-07, "epoch": 3.3193312966734556, "percentage": 66.39, "elapsed_time": "1:01:41", "remaining_time": "0:31:14", "throughput": 10149.8, "total_tokens": 37570432}
{"current_steps": 39120, "total_steps": 58920, "loss": 0.0327, "lr": 6.126963295657683e-07, "epoch": 3.319755600814664, "percentage": 66.4, "elapsed_time": "1:01:41", "remaining_time": "0:31:13", "throughput": 10150.02, "total_tokens": 37575168}
{"current_steps": 39125, "total_steps": 58920, "loss": 0.0, "lr": 6.124232457217249e-07, "epoch": 3.3201799049558725, "percentage": 66.4, "elapsed_time": "1:01:42", "remaining_time": "0:31:13", "throughput": 10150.22, "total_tokens": 37579712}
{"current_steps": 39130, "total_steps": 58920, "loss": 0.0, "lr": 6.121501958861428e-07, "epoch": 3.320604209097081, "percentage": 66.41, "elapsed_time": "1:01:42", "remaining_time": "0:31:12", "throughput": 10150.46, "total_tokens": 37584512}
{"current_steps": 39135, "total_steps": 58920, "loss": 0.0, "lr": 6.118771800829803e-07, "epoch": 3.3210285132382893, "percentage": 66.42, "elapsed_time": "1:01:43", "remaining_time": "0:31:12", "throughput": 10150.76, "total_tokens": 37589568}
{"current_steps": 39140, "total_steps": 58920, "loss": 0.0, "lr": 6.116041983361943e-07, "epoch": 3.3214528173794977, "percentage": 66.43, "elapsed_time": "1:01:43", "remaining_time": "0:31:11", "throughput": 10150.99, "total_tokens": 37594304}
{"current_steps": 39145, "total_steps": 58920, "loss": 0.0, "lr": 6.113312506697375e-07, "epoch": 3.321877121520706, "percentage": 66.44, "elapsed_time": "1:01:43", "remaining_time": "0:31:11", "throughput": 10151.19, "total_tokens": 37598848}
{"current_steps": 39150, "total_steps": 58920, "loss": 0.0, "lr": 6.1105833710756e-07, "epoch": 3.3223014256619146, "percentage": 66.45, "elapsed_time": "1:01:44", "remaining_time": "0:31:10", "throughput": 10151.5, "total_tokens": 37603968}
{"current_steps": 39155, "total_steps": 58920, "loss": 0.0, "lr": 6.107854576736093e-07, "epoch": 3.322725729803123, "percentage": 66.45, "elapsed_time": "1:01:44", "remaining_time": "0:31:10", "throughput": 10151.79, "total_tokens": 37609024}
{"current_steps": 39160, "total_steps": 58920, "loss": 0.0, "lr": 6.105126123918292e-07, "epoch": 3.3231500339443314, "percentage": 66.46, "elapsed_time": "1:01:45", "remaining_time": "0:31:09", "throughput": 10151.95, "total_tokens": 37613440}
{"current_steps": 39165, "total_steps": 58920, "loss": 0.0, "lr": 6.102398012861616e-07, "epoch": 3.32357433808554, "percentage": 66.47, "elapsed_time": "1:01:45", "remaining_time": "0:31:09", "throughput": 10152.27, "total_tokens": 37618560}
{"current_steps": 39170, "total_steps": 58920, "loss": 0.0183, "lr": 6.099670243805437e-07, "epoch": 3.3239986422267482, "percentage": 66.48, "elapsed_time": "1:01:45", "remaining_time": "0:31:08", "throughput": 10152.54, "total_tokens": 37623488}
{"current_steps": 39175, "total_steps": 58920, "loss": 0.0, "lr": 6.096942816989115e-07, "epoch": 3.3244229463679567, "percentage": 66.49, "elapsed_time": "1:01:46", "remaining_time": "0:31:07", "throughput": 10152.71, "total_tokens": 37627904}
{"current_steps": 39180, "total_steps": 58920, "loss": 0.0, "lr": 6.094215732651966e-07, "epoch": 3.324847250509165, "percentage": 66.5, "elapsed_time": "1:01:46", "remaining_time": "0:31:07", "throughput": 10153.02, "total_tokens": 37633024}
{"current_steps": 39185, "total_steps": 58920, "loss": 0.0389, "lr": 6.091488991033287e-07, "epoch": 3.3252715546503735, "percentage": 66.51, "elapsed_time": "1:01:46", "remaining_time": "0:31:06", "throughput": 10153.14, "total_tokens": 37637248}
{"current_steps": 39190, "total_steps": 58920, "loss": 0.0, "lr": 6.08876259237234e-07, "epoch": 3.325695858791582, "percentage": 66.51, "elapsed_time": "1:01:47", "remaining_time": "0:31:06", "throughput": 10153.55, "total_tokens": 37642816}
{"current_steps": 39195, "total_steps": 58920, "loss": 0.0, "lr": 6.086036536908349e-07, "epoch": 3.3261201629327903, "percentage": 66.52, "elapsed_time": "1:01:47", "remaining_time": "0:31:05", "throughput": 10153.9, "total_tokens": 37648128}
{"current_steps": 39200, "total_steps": 58920, "loss": 0.0, "lr": 6.083310824880525e-07, "epoch": 3.3265444670739988, "percentage": 66.53, "elapsed_time": "1:01:48", "remaining_time": "0:31:05", "throughput": 10154.11, "total_tokens": 37652736}
{"current_steps": 39205, "total_steps": 58920, "loss": 0.0, "lr": 6.08058545652803e-07, "epoch": 3.326968771215207, "percentage": 66.54, "elapsed_time": "1:01:48", "remaining_time": "0:31:04", "throughput": 10154.27, "total_tokens": 37657152}
{"current_steps": 39210, "total_steps": 58920, "loss": 0.0, "lr": 6.077860432090014e-07, "epoch": 3.3273930753564156, "percentage": 66.55, "elapsed_time": "1:01:48", "remaining_time": "0:31:04", "throughput": 10154.6, "total_tokens": 37662336}
{"current_steps": 39215, "total_steps": 58920, "loss": 0.0, "lr": 6.07513575180558e-07, "epoch": 3.327817379497624, "percentage": 66.56, "elapsed_time": "1:01:49", "remaining_time": "0:31:03", "throughput": 10154.96, "total_tokens": 37667776}
{"current_steps": 39220, "total_steps": 58920, "loss": 0.0, "lr": 6.072411415913818e-07, "epoch": 3.3282416836388324, "percentage": 66.56, "elapsed_time": "1:01:49", "remaining_time": "0:31:03", "throughput": 10155.12, "total_tokens": 37672192}
{"current_steps": 39225, "total_steps": 58920, "loss": 0.0, "lr": 6.069687424653776e-07, "epoch": 3.328665987780041, "percentage": 66.57, "elapsed_time": "1:01:50", "remaining_time": "0:31:02", "throughput": 10155.31, "total_tokens": 37676736}
{"current_steps": 39230, "total_steps": 58920, "loss": 0.0, "lr": 6.066963778264465e-07, "epoch": 3.3290902919212493, "percentage": 66.58, "elapsed_time": "1:01:50", "remaining_time": "0:31:02", "throughput": 10155.5, "total_tokens": 37681280}
{"current_steps": 39235, "total_steps": 58920, "loss": 0.0, "lr": 6.064240476984886e-07, "epoch": 3.3295145960624577, "percentage": 66.59, "elapsed_time": "1:01:50", "remaining_time": "0:31:01", "throughput": 10155.72, "total_tokens": 37686016}
{"current_steps": 39240, "total_steps": 58920, "loss": 0.0, "lr": 6.061517521053994e-07, "epoch": 3.329938900203666, "percentage": 66.6, "elapsed_time": "1:01:51", "remaining_time": "0:31:01", "throughput": 10155.9, "total_tokens": 37690496}
{"current_steps": 39245, "total_steps": 58920, "loss": 0.0333, "lr": 6.05879491071072e-07, "epoch": 3.3303632043448745, "percentage": 66.61, "elapsed_time": "1:01:51", "remaining_time": "0:31:00", "throughput": 10156.15, "total_tokens": 37695360}
{"current_steps": 39250, "total_steps": 58920, "loss": 0.0, "lr": 6.056072646193962e-07, "epoch": 3.330787508486083, "percentage": 66.62, "elapsed_time": "1:01:51", "remaining_time": "0:31:00", "throughput": 10156.38, "total_tokens": 37700160}
{"current_steps": 39255, "total_steps": 58920, "loss": 0.0, "lr": 6.053350727742593e-07, "epoch": 3.3312118126272914, "percentage": 66.62, "elapsed_time": "1:01:52", "remaining_time": "0:30:59", "throughput": 10156.56, "total_tokens": 37704704}
{"current_steps": 39260, "total_steps": 58920, "loss": 0.0, "lr": 6.050629155595444e-07, "epoch": 3.3316361167685, "percentage": 66.63, "elapsed_time": "1:01:52", "remaining_time": "0:30:59", "throughput": 10156.76, "total_tokens": 37709312}
{"current_steps": 39265, "total_steps": 58920, "loss": 0.0695, "lr": 6.047907929991332e-07, "epoch": 3.332060420909708, "percentage": 66.64, "elapsed_time": "1:01:53", "remaining_time": "0:30:58", "throughput": 10156.96, "total_tokens": 37713920}
{"current_steps": 39270, "total_steps": 58920, "loss": 0.0, "lr": 6.045187051169028e-07, "epoch": 3.3324847250509166, "percentage": 66.65, "elapsed_time": "1:01:53", "remaining_time": "0:30:58", "throughput": 10157.16, "total_tokens": 37718528}
{"current_steps": 39275, "total_steps": 58920, "loss": 0.0, "lr": 6.04246651936728e-07, "epoch": 3.332909029192125, "percentage": 66.66, "elapsed_time": "1:01:53", "remaining_time": "0:30:57", "throughput": 10157.36, "total_tokens": 37723072}
{"current_steps": 39280, "total_steps": 58920, "loss": 0.0, "lr": 6.03974633482481e-07, "epoch": 3.3333333333333335, "percentage": 66.67, "elapsed_time": "1:01:54", "remaining_time": "0:30:57", "throughput": 10157.72, "total_tokens": 37728448}
{"current_steps": 39285, "total_steps": 58920, "loss": 0.0001, "lr": 6.037026497780296e-07, "epoch": 3.333757637474542, "percentage": 66.68, "elapsed_time": "1:01:54", "remaining_time": "0:30:56", "throughput": 10157.91, "total_tokens": 37732992}
{"current_steps": 39290, "total_steps": 58920, "loss": 0.0, "lr": 6.034307008472404e-07, "epoch": 3.3341819416157503, "percentage": 66.68, "elapsed_time": "1:01:55", "remaining_time": "0:30:56", "throughput": 10158.14, "total_tokens": 37737792}
{"current_steps": 39295, "total_steps": 58920, "loss": 0.0001, "lr": 6.031587867139749e-07, "epoch": 3.3346062457569587, "percentage": 66.69, "elapsed_time": "1:01:55", "remaining_time": "0:30:55", "throughput": 10158.46, "total_tokens": 37742912}
{"current_steps": 39300, "total_steps": 58920, "loss": 0.0004, "lr": 6.028869074020932e-07, "epoch": 3.335030549898167, "percentage": 66.7, "elapsed_time": "1:01:55", "remaining_time": "0:30:55", "throughput": 10158.59, "total_tokens": 37747136}
{"current_steps": 39305, "total_steps": 58920, "loss": 0.0, "lr": 6.026150629354516e-07, "epoch": 3.3354548540393756, "percentage": 66.71, "elapsed_time": "1:01:56", "remaining_time": "0:30:54", "throughput": 10158.76, "total_tokens": 37751616}
{"current_steps": 39310, "total_steps": 58920, "loss": 0.0, "lr": 6.023432533379036e-07, "epoch": 3.335879158180584, "percentage": 66.72, "elapsed_time": "1:01:56", "remaining_time": "0:30:54", "throughput": 10158.89, "total_tokens": 37755904}
{"current_steps": 39315, "total_steps": 58920, "loss": 0.0, "lr": 6.020714786332996e-07, "epoch": 3.3363034623217924, "percentage": 66.73, "elapsed_time": "1:01:56", "remaining_time": "0:30:53", "throughput": 10159.22, "total_tokens": 37761088}
{"current_steps": 39320, "total_steps": 58920, "loss": 0.0, "lr": 6.017997388454861e-07, "epoch": 3.336727766463001, "percentage": 66.73, "elapsed_time": "1:01:57", "remaining_time": "0:30:52", "throughput": 10159.41, "total_tokens": 37765696}
{"current_steps": 39325, "total_steps": 58920, "loss": 0.0222, "lr": 6.015280339983084e-07, "epoch": 3.3371520706042093, "percentage": 66.74, "elapsed_time": "1:01:57", "remaining_time": "0:30:52", "throughput": 10159.6, "total_tokens": 37770240}
{"current_steps": 39330, "total_steps": 58920, "loss": 0.0081, "lr": 6.012563641156065e-07, "epoch": 3.3375763747454177, "percentage": 66.75, "elapsed_time": "1:01:58", "remaining_time": "0:30:51", "throughput": 10159.8, "total_tokens": 37774848}
{"current_steps": 39335, "total_steps": 58920, "loss": 0.0, "lr": 6.009847292212191e-07, "epoch": 3.338000678886626, "percentage": 66.76, "elapsed_time": "1:01:58", "remaining_time": "0:30:51", "throughput": 10160.01, "total_tokens": 37779456}
{"current_steps": 39340, "total_steps": 58920, "loss": 0.0, "lr": 6.007131293389811e-07, "epoch": 3.3384249830278345, "percentage": 66.77, "elapsed_time": "1:01:58", "remaining_time": "0:30:50", "throughput": 10160.25, "total_tokens": 37784256}
{"current_steps": 39345, "total_steps": 58920, "loss": 0.0, "lr": 6.004415644927247e-07, "epoch": 3.338849287169043, "percentage": 66.78, "elapsed_time": "1:01:59", "remaining_time": "0:30:50", "throughput": 10160.58, "total_tokens": 37789440}
{"current_steps": 39350, "total_steps": 58920, "loss": 0.0, "lr": 6.001700347062783e-07, "epoch": 3.3392735913102514, "percentage": 66.79, "elapsed_time": "1:01:59", "remaining_time": "0:30:49", "throughput": 10160.82, "total_tokens": 37794240}
{"current_steps": 39355, "total_steps": 58920, "loss": 0.0001, "lr": 5.998985400034675e-07, "epoch": 3.33969789545146, "percentage": 66.79, "elapsed_time": "1:01:59", "remaining_time": "0:30:49", "throughput": 10161.07, "total_tokens": 37799040}
{"current_steps": 39360, "total_steps": 58920, "loss": 0.0, "lr": 5.996270804081154e-07, "epoch": 3.340122199592668, "percentage": 66.8, "elapsed_time": "1:02:00", "remaining_time": "0:30:48", "throughput": 10161.22, "total_tokens": 37803392}
{"current_steps": 39365, "total_steps": 58920, "loss": 0.0, "lr": 5.993556559440414e-07, "epoch": 3.3405465037338766, "percentage": 66.81, "elapsed_time": "1:02:00", "remaining_time": "0:30:48", "throughput": 10161.5, "total_tokens": 37808320}
{"current_steps": 39370, "total_steps": 58920, "loss": 0.0, "lr": 5.990842666350623e-07, "epoch": 3.340970807875085, "percentage": 66.82, "elapsed_time": "1:02:01", "remaining_time": "0:30:47", "throughput": 10161.84, "total_tokens": 37813632}
{"current_steps": 39375, "total_steps": 58920, "loss": 0.0, "lr": 5.98812912504991e-07, "epoch": 3.3413951120162935, "percentage": 66.83, "elapsed_time": "1:02:01", "remaining_time": "0:30:47", "throughput": 10162.15, "total_tokens": 37818752}
{"current_steps": 39380, "total_steps": 58920, "loss": 0.0, "lr": 5.985415935776383e-07, "epoch": 3.341819416157502, "percentage": 66.84, "elapsed_time": "1:02:01", "remaining_time": "0:30:46", "throughput": 10162.32, "total_tokens": 37823168}
{"current_steps": 39385, "total_steps": 58920, "loss": 0.0, "lr": 5.982703098768112e-07, "epoch": 3.3422437202987103, "percentage": 66.84, "elapsed_time": "1:02:02", "remaining_time": "0:30:46", "throughput": 10162.5, "total_tokens": 37827648}
{"current_steps": 39390, "total_steps": 58920, "loss": 0.0109, "lr": 5.979990614263142e-07, "epoch": 3.3426680244399183, "percentage": 66.85, "elapsed_time": "1:02:02", "remaining_time": "0:30:45", "throughput": 10162.76, "total_tokens": 37832512}
{"current_steps": 39395, "total_steps": 58920, "loss": 0.0, "lr": 5.977278482499481e-07, "epoch": 3.343092328581127, "percentage": 66.86, "elapsed_time": "1:02:03", "remaining_time": "0:30:45", "throughput": 10162.89, "total_tokens": 37836800}
{"current_steps": 39400, "total_steps": 58920, "loss": 0.0, "lr": 5.974566703715106e-07, "epoch": 3.343516632722335, "percentage": 66.87, "elapsed_time": "1:02:03", "remaining_time": "0:30:44", "throughput": 10163.06, "total_tokens": 37841216}
{"current_steps": 39405, "total_steps": 58920, "loss": 0.0, "lr": 5.971855278147974e-07, "epoch": 3.343940936863544, "percentage": 66.88, "elapsed_time": "1:02:03", "remaining_time": "0:30:44", "throughput": 10163.24, "total_tokens": 37845696}
{"current_steps": 39410, "total_steps": 58920, "loss": 0.0, "lr": 5.969144206035992e-07, "epoch": 3.344365241004752, "percentage": 66.89, "elapsed_time": "1:02:04", "remaining_time": "0:30:43", "throughput": 10163.56, "total_tokens": 37850880}
{"current_steps": 39415, "total_steps": 58920, "loss": 0.0467, "lr": 5.966433487617058e-07, "epoch": 3.344789545145961, "percentage": 66.9, "elapsed_time": "1:02:04", "remaining_time": "0:30:43", "throughput": 10163.86, "total_tokens": 37855936}
{"current_steps": 39420, "total_steps": 58920, "loss": 0.0, "lr": 5.963723123129019e-07, "epoch": 3.345213849287169, "percentage": 66.9, "elapsed_time": "1:02:04", "remaining_time": "0:30:42", "throughput": 10164.02, "total_tokens": 37860352}
{"current_steps": 39425, "total_steps": 58920, "loss": 0.0001, "lr": 5.961013112809703e-07, "epoch": 3.3456381534283777, "percentage": 66.91, "elapsed_time": "1:02:05", "remaining_time": "0:30:42", "throughput": 10164.16, "total_tokens": 37864704}
{"current_steps": 39430, "total_steps": 58920, "loss": 0.0001, "lr": 5.958303456896903e-07, "epoch": 3.3460624575695856, "percentage": 66.92, "elapsed_time": "1:02:05", "remaining_time": "0:30:41", "throughput": 10164.43, "total_tokens": 37869632}
{"current_steps": 39435, "total_steps": 58920, "loss": 0.0, "lr": 5.955594155628385e-07, "epoch": 3.3464867617107945, "percentage": 66.93, "elapsed_time": "1:02:06", "remaining_time": "0:30:41", "throughput": 10164.55, "total_tokens": 37873856}
{"current_steps": 39440, "total_steps": 58920, "loss": 0.0, "lr": 5.952885209241878e-07, "epoch": 3.3469110658520025, "percentage": 66.94, "elapsed_time": "1:02:06", "remaining_time": "0:30:40", "throughput": 10164.73, "total_tokens": 37878336}
{"current_steps": 39445, "total_steps": 58920, "loss": 0.0, "lr": 5.950176617975079e-07, "epoch": 3.3473353699932114, "percentage": 66.95, "elapsed_time": "1:02:06", "remaining_time": "0:30:40", "throughput": 10164.84, "total_tokens": 37882496}
{"current_steps": 39450, "total_steps": 58920, "loss": 0.0189, "lr": 5.947468382065661e-07, "epoch": 3.3477596741344193, "percentage": 66.96, "elapsed_time": "1:02:07", "remaining_time": "0:30:39", "throughput": 10165.07, "total_tokens": 37887232}
{"current_steps": 39455, "total_steps": 58920, "loss": 0.0001, "lr": 5.94476050175126e-07, "epoch": 3.348183978275628, "percentage": 66.96, "elapsed_time": "1:02:07", "remaining_time": "0:30:38", "throughput": 10165.21, "total_tokens": 37891584}
{"current_steps": 39460, "total_steps": 58920, "loss": 0.0, "lr": 5.942052977269485e-07, "epoch": 3.348608282416836, "percentage": 66.97, "elapsed_time": "1:02:07", "remaining_time": "0:30:38", "throughput": 10165.42, "total_tokens": 37896256}
{"current_steps": 39465, "total_steps": 58920, "loss": 0.0, "lr": 5.939345808857908e-07, "epoch": 3.349032586558045, "percentage": 66.98, "elapsed_time": "1:02:08", "remaining_time": "0:30:37", "throughput": 10165.67, "total_tokens": 37901184}
{"current_steps": 39470, "total_steps": 58920, "loss": 0.0, "lr": 5.93663899675408e-07, "epoch": 3.349456890699253, "percentage": 66.99, "elapsed_time": "1:02:08", "remaining_time": "0:30:37", "throughput": 10165.88, "total_tokens": 37905856}
{"current_steps": 39475, "total_steps": 58920, "loss": 0.0, "lr": 5.933932541195508e-07, "epoch": 3.349881194840462, "percentage": 67.0, "elapsed_time": "1:02:09", "remaining_time": "0:30:36", "throughput": 10166.09, "total_tokens": 37910528}
{"current_steps": 39480, "total_steps": 58920, "loss": 0.0, "lr": 5.93122644241967e-07, "epoch": 3.35030549898167, "percentage": 67.01, "elapsed_time": "1:02:09", "remaining_time": "0:30:36", "throughput": 10166.35, "total_tokens": 37915392}
{"current_steps": 39485, "total_steps": 58920, "loss": 0.0, "lr": 5.928520700664026e-07, "epoch": 3.3507298031228787, "percentage": 67.01, "elapsed_time": "1:02:09", "remaining_time": "0:30:35", "throughput": 10166.6, "total_tokens": 37920128}
{"current_steps": 39490, "total_steps": 58920, "loss": 0.0, "lr": 5.925815316165988e-07, "epoch": 3.3511541072640867, "percentage": 67.02, "elapsed_time": "1:02:10", "remaining_time": "0:30:35", "throughput": 10166.94, "total_tokens": 37925376}
{"current_steps": 39495, "total_steps": 58920, "loss": 0.0, "lr": 5.92311028916295e-07, "epoch": 3.3515784114052956, "percentage": 67.03, "elapsed_time": "1:02:10", "remaining_time": "0:30:34", "throughput": 10167.08, "total_tokens": 37929664}
{"current_steps": 39500, "total_steps": 58920, "loss": 0.0, "lr": 5.920405619892259e-07, "epoch": 3.3520027155465035, "percentage": 67.04, "elapsed_time": "1:02:11", "remaining_time": "0:30:34", "throughput": 10167.32, "total_tokens": 37934400}
{"current_steps": 39505, "total_steps": 58920, "loss": 0.0521, "lr": 5.917701308591249e-07, "epoch": 3.3524270196877124, "percentage": 67.05, "elapsed_time": "1:02:11", "remaining_time": "0:30:33", "throughput": 10167.6, "total_tokens": 37939392}
{"current_steps": 39510, "total_steps": 58920, "loss": 0.0, "lr": 5.914997355497208e-07, "epoch": 3.3528513238289204, "percentage": 67.06, "elapsed_time": "1:02:11", "remaining_time": "0:30:33", "throughput": 10167.87, "total_tokens": 37944320}
{"current_steps": 39515, "total_steps": 58920, "loss": 0.0, "lr": 5.912293760847402e-07, "epoch": 3.3532756279701292, "percentage": 67.07, "elapsed_time": "1:02:12", "remaining_time": "0:30:32", "throughput": 10168.19, "total_tokens": 37949504}
{"current_steps": 39520, "total_steps": 58920, "loss": 0.0, "lr": 5.909590524879063e-07, "epoch": 3.353699932111337, "percentage": 67.07, "elapsed_time": "1:02:12", "remaining_time": "0:30:32", "throughput": 10168.44, "total_tokens": 37954304}
{"current_steps": 39525, "total_steps": 58920, "loss": 0.0, "lr": 5.906887647829382e-07, "epoch": 3.3541242362525456, "percentage": 67.08, "elapsed_time": "1:02:12", "remaining_time": "0:30:31", "throughput": 10168.77, "total_tokens": 37959552}
{"current_steps": 39530, "total_steps": 58920, "loss": 0.0, "lr": 5.904185129935535e-07, "epoch": 3.354548540393754, "percentage": 67.09, "elapsed_time": "1:02:13", "remaining_time": "0:30:31", "throughput": 10169.11, "total_tokens": 37964864}
{"current_steps": 39535, "total_steps": 58920, "loss": 0.0, "lr": 5.901482971434652e-07, "epoch": 3.3549728445349625, "percentage": 67.1, "elapsed_time": "1:02:13", "remaining_time": "0:30:30", "throughput": 10169.54, "total_tokens": 37970560}
{"current_steps": 39540, "total_steps": 58920, "loss": 0.0, "lr": 5.898781172563845e-07, "epoch": 3.355397148676171, "percentage": 67.11, "elapsed_time": "1:02:14", "remaining_time": "0:30:30", "throughput": 10169.67, "total_tokens": 37974848}
{"current_steps": 39545, "total_steps": 58920, "loss": 0.0, "lr": 5.896079733560177e-07, "epoch": 3.3558214528173793, "percentage": 67.12, "elapsed_time": "1:02:14", "remaining_time": "0:30:29", "throughput": 10169.84, "total_tokens": 37979328}
{"current_steps": 39550, "total_steps": 58920, "loss": 0.0, "lr": 5.893378654660698e-07, "epoch": 3.3562457569585877, "percentage": 67.12, "elapsed_time": "1:02:14", "remaining_time": "0:30:29", "throughput": 10170.03, "total_tokens": 37983872}
{"current_steps": 39555, "total_steps": 58920, "loss": 0.0, "lr": 5.890677936102412e-07, "epoch": 3.356670061099796, "percentage": 67.13, "elapsed_time": "1:02:15", "remaining_time": "0:30:28", "throughput": 10170.27, "total_tokens": 37988672}
{"current_steps": 39560, "total_steps": 58920, "loss": 0.0, "lr": 5.887977578122307e-07, "epoch": 3.3570943652410046, "percentage": 67.14, "elapsed_time": "1:02:15", "remaining_time": "0:30:28", "throughput": 10170.52, "total_tokens": 37993472}
{"current_steps": 39565, "total_steps": 58920, "loss": 0.0, "lr": 5.885277580957321e-07, "epoch": 3.357518669382213, "percentage": 67.15, "elapsed_time": "1:02:16", "remaining_time": "0:30:27", "throughput": 10170.79, "total_tokens": 37998464}
{"current_steps": 39570, "total_steps": 58920, "loss": 0.0, "lr": 5.882577944844369e-07, "epoch": 3.3579429735234214, "percentage": 67.16, "elapsed_time": "1:02:16", "remaining_time": "0:30:27", "throughput": 10171.06, "total_tokens": 38003392}
{"current_steps": 39575, "total_steps": 58920, "loss": 0.0, "lr": 5.879878670020338e-07, "epoch": 3.35836727766463, "percentage": 67.17, "elapsed_time": "1:02:16", "remaining_time": "0:30:26", "throughput": 10171.24, "total_tokens": 38007872}
{"current_steps": 39580, "total_steps": 58920, "loss": 0.0, "lr": 5.877179756722074e-07, "epoch": 3.3587915818058383, "percentage": 67.18, "elapsed_time": "1:02:17", "remaining_time": "0:30:26", "throughput": 10171.54, "total_tokens": 38012928}
{"current_steps": 39585, "total_steps": 58920, "loss": 0.0216, "lr": 5.874481205186408e-07, "epoch": 3.3592158859470467, "percentage": 67.18, "elapsed_time": "1:02:17", "remaining_time": "0:30:25", "throughput": 10171.9, "total_tokens": 38018368}
{"current_steps": 39590, "total_steps": 58920, "loss": 0.0, "lr": 5.871783015650116e-07, "epoch": 3.359640190088255, "percentage": 67.19, "elapsed_time": "1:02:17", "remaining_time": "0:30:25", "throughput": 10172.09, "total_tokens": 38022912}
{"current_steps": 39595, "total_steps": 58920, "loss": 0.0287, "lr": 5.869085188349962e-07, "epoch": 3.3600644942294635, "percentage": 67.2, "elapsed_time": "1:02:18", "remaining_time": "0:30:24", "throughput": 10172.32, "total_tokens": 38027584}
{"current_steps": 39600, "total_steps": 58920, "loss": 0.0, "lr": 5.866387723522666e-07, "epoch": 3.360488798370672, "percentage": 67.21, "elapsed_time": "1:02:18", "remaining_time": "0:30:24", "throughput": 10172.49, "total_tokens": 38032000}
{"current_steps": 39605, "total_steps": 58920, "loss": 0.0, "lr": 5.863690621404926e-07, "epoch": 3.3609131025118804, "percentage": 67.22, "elapsed_time": "1:02:19", "remaining_time": "0:30:23", "throughput": 10172.72, "total_tokens": 38036736}
{"current_steps": 39610, "total_steps": 58920, "loss": 0.0006, "lr": 5.860993882233398e-07, "epoch": 3.3613374066530888, "percentage": 67.23, "elapsed_time": "1:02:19", "remaining_time": "0:30:23", "throughput": 10173.0, "total_tokens": 38041728}
{"current_steps": 39615, "total_steps": 58920, "loss": 0.0, "lr": 5.858297506244711e-07, "epoch": 3.361761710794297, "percentage": 67.24, "elapsed_time": "1:02:19", "remaining_time": "0:30:22", "throughput": 10173.26, "total_tokens": 38046592}
{"current_steps": 39620, "total_steps": 58920, "loss": 0.0, "lr": 5.855601493675468e-07, "epoch": 3.3621860149355056, "percentage": 67.24, "elapsed_time": "1:02:20", "remaining_time": "0:30:21", "throughput": 10173.38, "total_tokens": 38050816}
{"current_steps": 39625, "total_steps": 58920, "loss": 0.0, "lr": 5.852905844762229e-07, "epoch": 3.362610319076714, "percentage": 67.25, "elapsed_time": "1:02:20", "remaining_time": "0:30:21", "throughput": 10173.52, "total_tokens": 38055296}
{"current_steps": 39630, "total_steps": 58920, "loss": 0.0, "lr": 5.85021055974153e-07, "epoch": 3.3630346232179225, "percentage": 67.26, "elapsed_time": "1:02:21", "remaining_time": "0:30:20", "throughput": 10173.8, "total_tokens": 38060288}
{"current_steps": 39635, "total_steps": 58920, "loss": 0.0, "lr": 5.84751563884987e-07, "epoch": 3.363458927359131, "percentage": 67.27, "elapsed_time": "1:02:21", "remaining_time": "0:30:20", "throughput": 10174.18, "total_tokens": 38065792}
{"current_steps": 39640, "total_steps": 58920, "loss": 0.0, "lr": 5.844821082323719e-07, "epoch": 3.3638832315003393, "percentage": 67.28, "elapsed_time": "1:02:21", "remaining_time": "0:30:19", "throughput": 10174.52, "total_tokens": 38071040}
{"current_steps": 39645, "total_steps": 58920, "loss": 0.0399, "lr": 5.84212689039952e-07, "epoch": 3.3643075356415477, "percentage": 67.29, "elapsed_time": "1:02:22", "remaining_time": "0:30:19", "throughput": 10174.73, "total_tokens": 38075648}
{"current_steps": 39650, "total_steps": 58920, "loss": 0.0, "lr": 5.83943306331367e-07, "epoch": 3.364731839782756, "percentage": 67.29, "elapsed_time": "1:02:22", "remaining_time": "0:30:18", "throughput": 10174.86, "total_tokens": 38079936}
{"current_steps": 39655, "total_steps": 58920, "loss": 0.0001, "lr": 5.836739601302551e-07, "epoch": 3.3651561439239646, "percentage": 67.3, "elapsed_time": "1:02:22", "remaining_time": "0:30:18", "throughput": 10175.04, "total_tokens": 38084416}
{"current_steps": 39660, "total_steps": 58920, "loss": 0.0, "lr": 5.834046504602495e-07, "epoch": 3.365580448065173, "percentage": 67.31, "elapsed_time": "1:02:23", "remaining_time": "0:30:17", "throughput": 10175.36, "total_tokens": 38089600}
{"current_steps": 39665, "total_steps": 58920, "loss": 0.0, "lr": 5.831353773449825e-07, "epoch": 3.3660047522063814, "percentage": 67.32, "elapsed_time": "1:02:23", "remaining_time": "0:30:17", "throughput": 10175.55, "total_tokens": 38094144}
{"current_steps": 39670, "total_steps": 58920, "loss": 0.0087, "lr": 5.828661408080803e-07, "epoch": 3.36642905634759, "percentage": 67.33, "elapsed_time": "1:02:24", "remaining_time": "0:30:16", "throughput": 10175.76, "total_tokens": 38098944}
{"current_steps": 39675, "total_steps": 58920, "loss": 0.0, "lr": 5.82596940873169e-07, "epoch": 3.3668533604887982, "percentage": 67.34, "elapsed_time": "1:02:24", "remaining_time": "0:30:16", "throughput": 10176.04, "total_tokens": 38103872}
{"current_steps": 39680, "total_steps": 58920, "loss": 0.0, "lr": 5.823277775638682e-07, "epoch": 3.3672776646300067, "percentage": 67.35, "elapsed_time": "1:02:24", "remaining_time": "0:30:15", "throughput": 10176.27, "total_tokens": 38108608}
{"current_steps": 39685, "total_steps": 58920, "loss": 0.0, "lr": 5.820586509037972e-07, "epoch": 3.367701968771215, "percentage": 67.35, "elapsed_time": "1:02:25", "remaining_time": "0:30:15", "throughput": 10176.52, "total_tokens": 38113472}
{"current_steps": 39690, "total_steps": 58920, "loss": 0.0, "lr": 5.817895609165713e-07, "epoch": 3.3681262729124235, "percentage": 67.36, "elapsed_time": "1:02:25", "remaining_time": "0:30:14", "throughput": 10176.78, "total_tokens": 38118336}
{"current_steps": 39695, "total_steps": 58920, "loss": 0.0, "lr": 5.815205076258006e-07, "epoch": 3.368550577053632, "percentage": 67.37, "elapsed_time": "1:02:25", "remaining_time": "0:30:14", "throughput": 10176.93, "total_tokens": 38122688}
{"current_steps": 39700, "total_steps": 58920, "loss": 0.0, "lr": 5.812514910550952e-07, "epoch": 3.3689748811948403, "percentage": 67.38, "elapsed_time": "1:02:26", "remaining_time": "0:30:13", "throughput": 10177.2, "total_tokens": 38127552}
{"current_steps": 39705, "total_steps": 58920, "loss": 0.0, "lr": 5.809825112280587e-07, "epoch": 3.3693991853360488, "percentage": 67.39, "elapsed_time": "1:02:26", "remaining_time": "0:30:13", "throughput": 10177.38, "total_tokens": 38132032}
{"current_steps": 39710, "total_steps": 58920, "loss": 0.0, "lr": 5.807135681682948e-07, "epoch": 3.369823489477257, "percentage": 67.4, "elapsed_time": "1:02:27", "remaining_time": "0:30:12", "throughput": 10177.6, "total_tokens": 38136704}
{"current_steps": 39715, "total_steps": 58920, "loss": 0.0, "lr": 5.804446618994008e-07, "epoch": 3.3702477936184656, "percentage": 67.4, "elapsed_time": "1:02:27", "remaining_time": "0:30:12", "throughput": 10177.81, "total_tokens": 38141376}
{"current_steps": 39720, "total_steps": 58920, "loss": 0.0, "lr": 5.801757924449732e-07, "epoch": 3.370672097759674, "percentage": 67.41, "elapsed_time": "1:02:27", "remaining_time": "0:30:11", "throughput": 10178.11, "total_tokens": 38146432}
{"current_steps": 39725, "total_steps": 58920, "loss": 0.0, "lr": 5.799069598286041e-07, "epoch": 3.3710964019008824, "percentage": 67.42, "elapsed_time": "1:02:28", "remaining_time": "0:30:11", "throughput": 10178.31, "total_tokens": 38151040}
{"current_steps": 39730, "total_steps": 58920, "loss": 0.0, "lr": 5.796381640738825e-07, "epoch": 3.371520706042091, "percentage": 67.43, "elapsed_time": "1:02:28", "remaining_time": "0:30:10", "throughput": 10178.58, "total_tokens": 38156032}
{"current_steps": 39735, "total_steps": 58920, "loss": 0.0, "lr": 5.793694052043947e-07, "epoch": 3.3719450101832993, "percentage": 67.44, "elapsed_time": "1:02:29", "remaining_time": "0:30:10", "throughput": 10178.8, "total_tokens": 38160704}
{"current_steps": 39740, "total_steps": 58920, "loss": 0.0, "lr": 5.791006832437222e-07, "epoch": 3.3723693143245077, "percentage": 67.45, "elapsed_time": "1:02:29", "remaining_time": "0:30:09", "throughput": 10179.0, "total_tokens": 38165312}
{"current_steps": 39745, "total_steps": 58920, "loss": 0.0, "lr": 5.788319982154455e-07, "epoch": 3.372793618465716, "percentage": 67.46, "elapsed_time": "1:02:29", "remaining_time": "0:30:09", "throughput": 10179.28, "total_tokens": 38170304}
{"current_steps": 39750, "total_steps": 58920, "loss": 0.0, "lr": 5.785633501431402e-07, "epoch": 3.3732179226069245, "percentage": 67.46, "elapsed_time": "1:02:30", "remaining_time": "0:30:08", "throughput": 10179.59, "total_tokens": 38175488}
{"current_steps": 39755, "total_steps": 58920, "loss": 0.0, "lr": 5.782947390503794e-07, "epoch": 3.373642226748133, "percentage": 67.47, "elapsed_time": "1:02:30", "remaining_time": "0:30:08", "throughput": 10179.78, "total_tokens": 38180032}
{"current_steps": 39760, "total_steps": 58920, "loss": 0.0, "lr": 5.780261649607327e-07, "epoch": 3.3740665308893414, "percentage": 67.48, "elapsed_time": "1:02:30", "remaining_time": "0:30:07", "throughput": 10180.01, "total_tokens": 38184768}
{"current_steps": 39765, "total_steps": 58920, "loss": 0.0176, "lr": 5.777576278977665e-07, "epoch": 3.37449083503055, "percentage": 67.49, "elapsed_time": "1:02:31", "remaining_time": "0:30:07", "throughput": 10180.18, "total_tokens": 38189248}
{"current_steps": 39770, "total_steps": 58920, "loss": 0.0, "lr": 5.774891278850438e-07, "epoch": 3.3749151391717582, "percentage": 67.5, "elapsed_time": "1:02:31", "remaining_time": "0:30:06", "throughput": 10180.38, "total_tokens": 38193856}
{"current_steps": 39775, "total_steps": 58920, "loss": 0.0012, "lr": 5.772206649461248e-07, "epoch": 3.3753394433129666, "percentage": 67.51, "elapsed_time": "1:02:32", "remaining_time": "0:30:06", "throughput": 10180.63, "total_tokens": 38198720}
{"current_steps": 39780, "total_steps": 58920, "loss": 0.0, "lr": 5.76952239104566e-07, "epoch": 3.375763747454175, "percentage": 67.52, "elapsed_time": "1:02:32", "remaining_time": "0:30:05", "throughput": 10180.96, "total_tokens": 38203968}
{"current_steps": 39785, "total_steps": 58920, "loss": 0.0, "lr": 5.766838503839208e-07, "epoch": 3.3761880515953835, "percentage": 67.52, "elapsed_time": "1:02:32", "remaining_time": "0:30:04", "throughput": 10181.26, "total_tokens": 38209024}
{"current_steps": 39790, "total_steps": 58920, "loss": 0.0053, "lr": 5.764154988077394e-07, "epoch": 3.376612355736592, "percentage": 67.53, "elapsed_time": "1:02:33", "remaining_time": "0:30:04", "throughput": 10181.5, "total_tokens": 38214016}
{"current_steps": 39795, "total_steps": 58920, "loss": 0.0588, "lr": 5.761471843995687e-07, "epoch": 3.3770366598778003, "percentage": 67.54, "elapsed_time": "1:02:33", "remaining_time": "0:30:03", "throughput": 10181.76, "total_tokens": 38218944}
{"current_steps": 39800, "total_steps": 58920, "loss": 0.0, "lr": 5.75878907182952e-07, "epoch": 3.3774609640190087, "percentage": 67.55, "elapsed_time": "1:02:34", "remaining_time": "0:30:03", "throughput": 10182.04, "total_tokens": 38223936}
{"current_steps": 39805, "total_steps": 58920, "loss": 0.0, "lr": 5.7561066718143e-07, "epoch": 3.377885268160217, "percentage": 67.56, "elapsed_time": "1:02:34", "remaining_time": "0:30:02", "throughput": 10182.19, "total_tokens": 38228288}
{"current_steps": 39810, "total_steps": 58920, "loss": 0.0, "lr": 5.753424644185398e-07, "epoch": 3.3783095723014256, "percentage": 67.57, "elapsed_time": "1:02:34", "remaining_time": "0:30:02", "throughput": 10182.34, "total_tokens": 38232640}
{"current_steps": 39815, "total_steps": 58920, "loss": 0.0, "lr": 5.750742989178152e-07, "epoch": 3.378733876442634, "percentage": 67.57, "elapsed_time": "1:02:35", "remaining_time": "0:30:01", "throughput": 10182.5, "total_tokens": 38237056}
{"current_steps": 39820, "total_steps": 58920, "loss": 0.0, "lr": 5.748061707027864e-07, "epoch": 3.3791581805838424, "percentage": 67.58, "elapsed_time": "1:02:35", "remaining_time": "0:30:01", "throughput": 10182.7, "total_tokens": 38241664}
{"current_steps": 39825, "total_steps": 58920, "loss": 0.0, "lr": 5.745380797969812e-07, "epoch": 3.379582484725051, "percentage": 67.59, "elapsed_time": "1:02:35", "remaining_time": "0:30:00", "throughput": 10182.93, "total_tokens": 38246400}
{"current_steps": 39830, "total_steps": 58920, "loss": 0.0, "lr": 5.742700262239234e-07, "epoch": 3.3800067888662593, "percentage": 67.6, "elapsed_time": "1:02:36", "remaining_time": "0:30:00", "throughput": 10183.36, "total_tokens": 38252160}
{"current_steps": 39835, "total_steps": 58920, "loss": 0.0, "lr": 5.740020100071336e-07, "epoch": 3.3804310930074677, "percentage": 67.61, "elapsed_time": "1:02:36", "remaining_time": "0:29:59", "throughput": 10183.53, "total_tokens": 38256832}
{"current_steps": 39840, "total_steps": 58920, "loss": 0.0, "lr": 5.737340311701293e-07, "epoch": 3.380855397148676, "percentage": 67.62, "elapsed_time": "1:02:37", "remaining_time": "0:29:59", "throughput": 10183.74, "total_tokens": 38261504}
{"current_steps": 39845, "total_steps": 58920, "loss": 0.0, "lr": 5.73466089736425e-07, "epoch": 3.3812797012898845, "percentage": 67.63, "elapsed_time": "1:02:37", "remaining_time": "0:29:58", "throughput": 10183.89, "total_tokens": 38265856}
{"current_steps": 39850, "total_steps": 58920, "loss": 0.0, "lr": 5.731981857295306e-07, "epoch": 3.381704005431093, "percentage": 67.63, "elapsed_time": "1:02:37", "remaining_time": "0:29:58", "throughput": 10184.13, "total_tokens": 38270656}
{"current_steps": 39855, "total_steps": 58920, "loss": 0.0, "lr": 5.729303191729555e-07, "epoch": 3.3821283095723014, "percentage": 67.64, "elapsed_time": "1:02:38", "remaining_time": "0:29:57", "throughput": 10184.56, "total_tokens": 38276416}
{"current_steps": 39860, "total_steps": 58920, "loss": 0.0, "lr": 5.726624900902024e-07, "epoch": 3.38255261371351, "percentage": 67.65, "elapsed_time": "1:02:38", "remaining_time": "0:29:57", "throughput": 10184.72, "total_tokens": 38280768}
{"current_steps": 39865, "total_steps": 58920, "loss": 0.0, "lr": 5.723946985047729e-07, "epoch": 3.382976917854718, "percentage": 67.66, "elapsed_time": "1:02:39", "remaining_time": "0:29:56", "throughput": 10185.06, "total_tokens": 38286016}
{"current_steps": 39870, "total_steps": 58920, "loss": 0.0, "lr": 5.721269444401648e-07, "epoch": 3.3834012219959266, "percentage": 67.67, "elapsed_time": "1:02:39", "remaining_time": "0:29:56", "throughput": 10185.25, "total_tokens": 38290624}
{"current_steps": 39875, "total_steps": 58920, "loss": 0.0, "lr": 5.718592279198722e-07, "epoch": 3.383825526137135, "percentage": 67.68, "elapsed_time": "1:02:39", "remaining_time": "0:29:55", "throughput": 10185.39, "total_tokens": 38294976}
{"current_steps": 39880, "total_steps": 58920, "loss": 0.0, "lr": 5.715915489673871e-07, "epoch": 3.3842498302783435, "percentage": 67.68, "elapsed_time": "1:02:40", "remaining_time": "0:29:55", "throughput": 10185.71, "total_tokens": 38300160}
{"current_steps": 39885, "total_steps": 58920, "loss": 0.0, "lr": 5.713239076061962e-07, "epoch": 3.384674134419552, "percentage": 67.69, "elapsed_time": "1:02:40", "remaining_time": "0:29:54", "throughput": 10186.05, "total_tokens": 38305536}
{"current_steps": 39890, "total_steps": 58920, "loss": 0.0, "lr": 5.710563038597855e-07, "epoch": 3.3850984385607603, "percentage": 67.7, "elapsed_time": "1:02:40", "remaining_time": "0:29:54", "throughput": 10186.35, "total_tokens": 38310656}
{"current_steps": 39895, "total_steps": 58920, "loss": 0.0, "lr": 5.707887377516349e-07, "epoch": 3.3855227427019687, "percentage": 67.71, "elapsed_time": "1:02:41", "remaining_time": "0:29:53", "throughput": 10186.49, "total_tokens": 38315008}
{"current_steps": 39900, "total_steps": 58920, "loss": 0.0, "lr": 5.705212093052227e-07, "epoch": 3.385947046843177, "percentage": 67.72, "elapsed_time": "1:02:41", "remaining_time": "0:29:53", "throughput": 10186.67, "total_tokens": 38319552}
{"current_steps": 39905, "total_steps": 58920, "loss": 0.0, "lr": 5.702537185440244e-07, "epoch": 3.3863713509843856, "percentage": 67.73, "elapsed_time": "1:02:42", "remaining_time": "0:29:52", "throughput": 10186.82, "total_tokens": 38323904}
{"current_steps": 39910, "total_steps": 58920, "loss": 0.0, "lr": 5.699862654915099e-07, "epoch": 3.386795655125594, "percentage": 67.74, "elapsed_time": "1:02:42", "remaining_time": "0:29:52", "throughput": 10187.05, "total_tokens": 38328640}
{"current_steps": 39915, "total_steps": 58920, "loss": 0.0, "lr": 5.697188501711488e-07, "epoch": 3.3872199592668024, "percentage": 67.74, "elapsed_time": "1:02:42", "remaining_time": "0:29:51", "throughput": 10187.23, "total_tokens": 38333184}
{"current_steps": 39920, "total_steps": 58920, "loss": 0.0, "lr": 5.694514726064044e-07, "epoch": 3.387644263408011, "percentage": 67.75, "elapsed_time": "1:02:43", "remaining_time": "0:29:51", "throughput": 10187.39, "total_tokens": 38337600}
{"current_steps": 39925, "total_steps": 58920, "loss": 0.0, "lr": 5.691841328207396e-07, "epoch": 3.3880685675492193, "percentage": 67.76, "elapsed_time": "1:02:43", "remaining_time": "0:29:50", "throughput": 10187.59, "total_tokens": 38342208}
{"current_steps": 39930, "total_steps": 58920, "loss": 0.0, "lr": 5.689168308376109e-07, "epoch": 3.3884928716904277, "percentage": 67.77, "elapsed_time": "1:02:44", "remaining_time": "0:29:50", "throughput": 10187.89, "total_tokens": 38347264}
{"current_steps": 39935, "total_steps": 58920, "loss": 0.0, "lr": 5.686495666804741e-07, "epoch": 3.388917175831636, "percentage": 67.78, "elapsed_time": "1:02:44", "remaining_time": "0:29:49", "throughput": 10188.14, "total_tokens": 38352192}
{"current_steps": 39940, "total_steps": 58920, "loss": 0.0, "lr": 5.68382340372781e-07, "epoch": 3.3893414799728445, "percentage": 67.79, "elapsed_time": "1:02:44", "remaining_time": "0:29:49", "throughput": 10188.44, "total_tokens": 38357440}
{"current_steps": 39945, "total_steps": 58920, "loss": 0.0, "lr": 5.681151519379784e-07, "epoch": 3.389765784114053, "percentage": 67.8, "elapsed_time": "1:02:45", "remaining_time": "0:29:48", "throughput": 10188.66, "total_tokens": 38362176}
{"current_steps": 39950, "total_steps": 58920, "loss": 0.0, "lr": 5.678480013995126e-07, "epoch": 3.3901900882552614, "percentage": 67.8, "elapsed_time": "1:02:45", "remaining_time": "0:29:48", "throughput": 10188.89, "total_tokens": 38366912}
{"current_steps": 39955, "total_steps": 58920, "loss": 0.0, "lr": 5.675808887808236e-07, "epoch": 3.39061439239647, "percentage": 67.81, "elapsed_time": "1:02:45", "remaining_time": "0:29:47", "throughput": 10189.2, "total_tokens": 38372032}
{"current_steps": 39960, "total_steps": 58920, "loss": 0.0, "lr": 5.673138141053509e-07, "epoch": 3.391038696537678, "percentage": 67.82, "elapsed_time": "1:02:46", "remaining_time": "0:29:47", "throughput": 10189.4, "total_tokens": 38376640}
{"current_steps": 39965, "total_steps": 58920, "loss": 0.0109, "lr": 5.670467773965286e-07, "epoch": 3.3914630006788866, "percentage": 67.83, "elapsed_time": "1:02:46", "remaining_time": "0:29:46", "throughput": 10189.66, "total_tokens": 38381568}
{"current_steps": 39970, "total_steps": 58920, "loss": 0.0, "lr": 5.667797786777886e-07, "epoch": 3.391887304820095, "percentage": 67.84, "elapsed_time": "1:02:47", "remaining_time": "0:29:45", "throughput": 10189.82, "total_tokens": 38385984}
{"current_steps": 39975, "total_steps": 58920, "loss": 0.0, "lr": 5.665128179725587e-07, "epoch": 3.3923116089613035, "percentage": 67.85, "elapsed_time": "1:02:47", "remaining_time": "0:29:45", "throughput": 10190.06, "total_tokens": 38390720}
{"current_steps": 39980, "total_steps": 58920, "loss": 0.0001, "lr": 5.662458953042641e-07, "epoch": 3.392735913102512, "percentage": 67.85, "elapsed_time": "1:02:47", "remaining_time": "0:29:44", "throughput": 10190.42, "total_tokens": 38396096}
{"current_steps": 39985, "total_steps": 58920, "loss": 0.0, "lr": 5.65979010696326e-07, "epoch": 3.3931602172437203, "percentage": 67.86, "elapsed_time": "1:02:48", "remaining_time": "0:29:44", "throughput": 10190.61, "total_tokens": 38400704}
{"current_steps": 39990, "total_steps": 58920, "loss": 0.0, "lr": 5.657121641721627e-07, "epoch": 3.3935845213849287, "percentage": 67.87, "elapsed_time": "1:02:48", "remaining_time": "0:29:43", "throughput": 10190.93, "total_tokens": 38406016}
{"current_steps": 39995, "total_steps": 58920, "loss": 0.0, "lr": 5.654453557551892e-07, "epoch": 3.394008825526137, "percentage": 67.88, "elapsed_time": "1:02:49", "remaining_time": "0:29:43", "throughput": 10191.1, "total_tokens": 38410496}
{"current_steps": 40000, "total_steps": 58920, "loss": 0.0, "lr": 5.651785854688165e-07, "epoch": 3.3944331296673456, "percentage": 67.89, "elapsed_time": "1:02:49", "remaining_time": "0:29:42", "throughput": 10191.31, "total_tokens": 38415168}
{"current_steps": 40005, "total_steps": 58920, "loss": 0.0, "lr": 5.649118533364532e-07, "epoch": 3.394857433808554, "percentage": 67.9, "elapsed_time": "1:02:49", "remaining_time": "0:29:42", "throughput": 10191.51, "total_tokens": 38419776}
{"current_steps": 40010, "total_steps": 58920, "loss": 0.0, "lr": 5.646451593815038e-07, "epoch": 3.3952817379497624, "percentage": 67.91, "elapsed_time": "1:02:50", "remaining_time": "0:29:41", "throughput": 10191.71, "total_tokens": 38424384}
{"current_steps": 40015, "total_steps": 58920, "loss": 0.0, "lr": 5.643785036273699e-07, "epoch": 3.395706042090971, "percentage": 67.91, "elapsed_time": "1:02:50", "remaining_time": "0:29:41", "throughput": 10191.88, "total_tokens": 38428864}
{"current_steps": 40020, "total_steps": 58920, "loss": 0.0001, "lr": 5.641118860974494e-07, "epoch": 3.3961303462321792, "percentage": 67.92, "elapsed_time": "1:02:50", "remaining_time": "0:29:40", "throughput": 10192.06, "total_tokens": 38433344}
{"current_steps": 40025, "total_steps": 58920, "loss": 0.0, "lr": 5.638453068151372e-07, "epoch": 3.3965546503733877, "percentage": 67.93, "elapsed_time": "1:02:51", "remaining_time": "0:29:40", "throughput": 10192.29, "total_tokens": 38438144}
{"current_steps": 40030, "total_steps": 58920, "loss": 0.0, "lr": 5.635787658038245e-07, "epoch": 3.396978954514596, "percentage": 67.94, "elapsed_time": "1:02:51", "remaining_time": "0:29:39", "throughput": 10192.7, "total_tokens": 38443776}
{"current_steps": 40035, "total_steps": 58920, "loss": 0.0, "lr": 5.633122630868995e-07, "epoch": 3.3974032586558045, "percentage": 67.95, "elapsed_time": "1:02:52", "remaining_time": "0:29:39", "throughput": 10192.95, "total_tokens": 38448640}
{"current_steps": 40040, "total_steps": 58920, "loss": 0.0428, "lr": 5.630457986877469e-07, "epoch": 3.397827562797013, "percentage": 67.96, "elapsed_time": "1:02:52", "remaining_time": "0:29:38", "throughput": 10193.14, "total_tokens": 38453184}
{"current_steps": 40045, "total_steps": 58920, "loss": 0.0, "lr": 5.627793726297475e-07, "epoch": 3.3982518669382213, "percentage": 67.97, "elapsed_time": "1:02:52", "remaining_time": "0:29:38", "throughput": 10193.39, "total_tokens": 38458048}
{"current_steps": 40050, "total_steps": 58920, "loss": 0.0197, "lr": 5.625129849362797e-07, "epoch": 3.3986761710794298, "percentage": 67.97, "elapsed_time": "1:02:53", "remaining_time": "0:29:37", "throughput": 10193.52, "total_tokens": 38462400}
{"current_steps": 40055, "total_steps": 58920, "loss": 0.0, "lr": 5.622466356307181e-07, "epoch": 3.399100475220638, "percentage": 67.98, "elapsed_time": "1:02:53", "remaining_time": "0:29:37", "throughput": 10193.7, "total_tokens": 38466880}
{"current_steps": 40060, "total_steps": 58920, "loss": 0.0, "lr": 5.619803247364336e-07, "epoch": 3.3995247793618466, "percentage": 67.99, "elapsed_time": "1:02:53", "remaining_time": "0:29:36", "throughput": 10193.91, "total_tokens": 38471552}
{"current_steps": 40065, "total_steps": 58920, "loss": 0.0, "lr": 5.617140522767942e-07, "epoch": 3.399949083503055, "percentage": 68.0, "elapsed_time": "1:02:54", "remaining_time": "0:29:36", "throughput": 10194.21, "total_tokens": 38476672}
{"current_steps": 40070, "total_steps": 58920, "loss": 0.0, "lr": 5.614478182751642e-07, "epoch": 3.4003733876442634, "percentage": 68.01, "elapsed_time": "1:02:54", "remaining_time": "0:29:35", "throughput": 10194.4, "total_tokens": 38481216}
{"current_steps": 40075, "total_steps": 58920, "loss": 0.0, "lr": 5.611816227549047e-07, "epoch": 3.400797691785472, "percentage": 68.02, "elapsed_time": "1:02:55", "remaining_time": "0:29:35", "throughput": 10194.58, "total_tokens": 38485760}
{"current_steps": 40080, "total_steps": 58920, "loss": 0.0, "lr": 5.609154657393737e-07, "epoch": 3.4012219959266803, "percentage": 68.02, "elapsed_time": "1:02:55", "remaining_time": "0:29:34", "throughput": 10194.81, "total_tokens": 38490496}
{"current_steps": 40085, "total_steps": 58920, "loss": 0.0, "lr": 5.60649347251925e-07, "epoch": 3.4016463000678887, "percentage": 68.03, "elapsed_time": "1:02:55", "remaining_time": "0:29:34", "throughput": 10194.98, "total_tokens": 38494976}
{"current_steps": 40090, "total_steps": 58920, "loss": 0.0, "lr": 5.603832673159096e-07, "epoch": 3.402070604209097, "percentage": 68.04, "elapsed_time": "1:02:56", "remaining_time": "0:29:33", "throughput": 10195.31, "total_tokens": 38500224}
{"current_steps": 40095, "total_steps": 58920, "loss": 0.0, "lr": 5.601172259546761e-07, "epoch": 3.4024949083503055, "percentage": 68.05, "elapsed_time": "1:02:56", "remaining_time": "0:29:33", "throughput": 10195.48, "total_tokens": 38504704}
{"current_steps": 40100, "total_steps": 58920, "loss": 0.0, "lr": 5.598512231915669e-07, "epoch": 3.402919212491514, "percentage": 68.06, "elapsed_time": "1:02:57", "remaining_time": "0:29:32", "throughput": 10195.76, "total_tokens": 38509696}
{"current_steps": 40105, "total_steps": 58920, "loss": 0.0, "lr": 5.595852590499244e-07, "epoch": 3.4033435166327224, "percentage": 68.07, "elapsed_time": "1:02:57", "remaining_time": "0:29:32", "throughput": 10195.92, "total_tokens": 38514112}
{"current_steps": 40110, "total_steps": 58920, "loss": 0.0, "lr": 5.593193335530851e-07, "epoch": 3.403767820773931, "percentage": 68.08, "elapsed_time": "1:02:57", "remaining_time": "0:29:31", "throughput": 10196.1, "total_tokens": 38518656}
{"current_steps": 40115, "total_steps": 58920, "loss": 0.0, "lr": 5.590534467243829e-07, "epoch": 3.4041921249151392, "percentage": 68.08, "elapsed_time": "1:02:58", "remaining_time": "0:29:31", "throughput": 10196.3, "total_tokens": 38523264}
{"current_steps": 40120, "total_steps": 58920, "loss": 0.0, "lr": 5.587875985871493e-07, "epoch": 3.4046164290563476, "percentage": 68.09, "elapsed_time": "1:02:58", "remaining_time": "0:29:30", "throughput": 10196.42, "total_tokens": 38527552}
{"current_steps": 40125, "total_steps": 58920, "loss": 0.0343, "lr": 5.585217891647102e-07, "epoch": 3.405040733197556, "percentage": 68.1, "elapsed_time": "1:02:58", "remaining_time": "0:29:30", "throughput": 10196.88, "total_tokens": 38533376}
{"current_steps": 40130, "total_steps": 58920, "loss": 0.0004, "lr": 5.58256018480391e-07, "epoch": 3.4054650373387645, "percentage": 68.11, "elapsed_time": "1:02:59", "remaining_time": "0:29:29", "throughput": 10197.18, "total_tokens": 38538432}
{"current_steps": 40135, "total_steps": 58920, "loss": 0.0, "lr": 5.579902865575103e-07, "epoch": 3.405889341479973, "percentage": 68.12, "elapsed_time": "1:02:59", "remaining_time": "0:29:29", "throughput": 10197.38, "total_tokens": 38543104}
{"current_steps": 40140, "total_steps": 58920, "loss": 0.0, "lr": 5.57724593419387e-07, "epoch": 3.4063136456211813, "percentage": 68.13, "elapsed_time": "1:03:00", "remaining_time": "0:29:28", "throughput": 10197.56, "total_tokens": 38547648}
{"current_steps": 40145, "total_steps": 58920, "loss": 0.0, "lr": 5.574589390893335e-07, "epoch": 3.4067379497623897, "percentage": 68.13, "elapsed_time": "1:03:00", "remaining_time": "0:29:28", "throughput": 10197.75, "total_tokens": 38552192}
{"current_steps": 40150, "total_steps": 58920, "loss": 0.0, "lr": 5.571933235906599e-07, "epoch": 3.407162253903598, "percentage": 68.14, "elapsed_time": "1:03:00", "remaining_time": "0:29:27", "throughput": 10198.0, "total_tokens": 38557056}
{"current_steps": 40155, "total_steps": 58920, "loss": 0.0001, "lr": 5.56927746946674e-07, "epoch": 3.4075865580448066, "percentage": 68.15, "elapsed_time": "1:03:01", "remaining_time": "0:29:27", "throughput": 10198.3, "total_tokens": 38562176}
{"current_steps": 40160, "total_steps": 58920, "loss": 0.0, "lr": 5.56662209180678e-07, "epoch": 3.408010862186015, "percentage": 68.16, "elapsed_time": "1:03:01", "remaining_time": "0:29:26", "throughput": 10198.47, "total_tokens": 38566656}
{"current_steps": 40165, "total_steps": 58920, "loss": 0.0, "lr": 5.563967103159733e-07, "epoch": 3.4084351663272234, "percentage": 68.17, "elapsed_time": "1:03:01", "remaining_time": "0:29:25", "throughput": 10198.67, "total_tokens": 38571328}
{"current_steps": 40170, "total_steps": 58920, "loss": 0.0, "lr": 5.561312503758546e-07, "epoch": 3.408859470468432, "percentage": 68.18, "elapsed_time": "1:03:02", "remaining_time": "0:29:25", "throughput": 10198.89, "total_tokens": 38576064}
{"current_steps": 40175, "total_steps": 58920, "loss": 0.0, "lr": 5.558658293836167e-07, "epoch": 3.4092837746096403, "percentage": 68.19, "elapsed_time": "1:03:02", "remaining_time": "0:29:24", "throughput": 10199.15, "total_tokens": 38580928}
{"current_steps": 40180, "total_steps": 58920, "loss": 0.0341, "lr": 5.556004473625486e-07, "epoch": 3.4097080787508487, "percentage": 68.19, "elapsed_time": "1:03:03", "remaining_time": "0:29:24", "throughput": 10199.37, "total_tokens": 38585600}
{"current_steps": 40185, "total_steps": 58920, "loss": 0.0, "lr": 5.553351043359368e-07, "epoch": 3.410132382892057, "percentage": 68.2, "elapsed_time": "1:03:03", "remaining_time": "0:29:23", "throughput": 10199.52, "total_tokens": 38590016}
{"current_steps": 40190, "total_steps": 58920, "loss": 0.0, "lr": 5.550698003270646e-07, "epoch": 3.4105566870332655, "percentage": 68.21, "elapsed_time": "1:03:03", "remaining_time": "0:29:23", "throughput": 10199.74, "total_tokens": 38594688}
{"current_steps": 40195, "total_steps": 58920, "loss": 0.0, "lr": 5.548045353592104e-07, "epoch": 3.410980991174474, "percentage": 68.22, "elapsed_time": "1:03:04", "remaining_time": "0:29:22", "throughput": 10199.98, "total_tokens": 38599488}
{"current_steps": 40200, "total_steps": 58920, "loss": 0.0, "lr": 5.54539309455651e-07, "epoch": 3.4114052953156824, "percentage": 68.23, "elapsed_time": "1:03:04", "remaining_time": "0:29:22", "throughput": 10200.18, "total_tokens": 38604096}
{"current_steps": 40205, "total_steps": 58920, "loss": 0.0, "lr": 5.542741226396588e-07, "epoch": 3.411829599456891, "percentage": 68.24, "elapsed_time": "1:03:05", "remaining_time": "0:29:21", "throughput": 10200.46, "total_tokens": 38609088}
{"current_steps": 40210, "total_steps": 58920, "loss": 0.0, "lr": 5.540089749345031e-07, "epoch": 3.412253903598099, "percentage": 68.25, "elapsed_time": "1:03:05", "remaining_time": "0:29:21", "throughput": 10200.69, "total_tokens": 38613824}
{"current_steps": 40215, "total_steps": 58920, "loss": 0.0, "lr": 5.537438663634497e-07, "epoch": 3.4126782077393076, "percentage": 68.25, "elapsed_time": "1:03:05", "remaining_time": "0:29:20", "throughput": 10200.82, "total_tokens": 38618112}
{"current_steps": 40220, "total_steps": 58920, "loss": 0.0, "lr": 5.534787969497607e-07, "epoch": 3.413102511880516, "percentage": 68.26, "elapsed_time": "1:03:06", "remaining_time": "0:29:20", "throughput": 10201.05, "total_tokens": 38622912}
{"current_steps": 40225, "total_steps": 58920, "loss": 0.0, "lr": 5.532137667166951e-07, "epoch": 3.4135268160217245, "percentage": 68.27, "elapsed_time": "1:03:06", "remaining_time": "0:29:19", "throughput": 10201.23, "total_tokens": 38627392}
{"current_steps": 40230, "total_steps": 58920, "loss": 0.0, "lr": 5.529487756875086e-07, "epoch": 3.413951120162933, "percentage": 68.28, "elapsed_time": "1:03:06", "remaining_time": "0:29:19", "throughput": 10201.47, "total_tokens": 38632320}
{"current_steps": 40235, "total_steps": 58920, "loss": 0.0, "lr": 5.526838238854528e-07, "epoch": 3.4143754243041413, "percentage": 68.29, "elapsed_time": "1:03:07", "remaining_time": "0:29:18", "throughput": 10201.54, "total_tokens": 38636352}
{"current_steps": 40240, "total_steps": 58920, "loss": 0.0, "lr": 5.524189113337764e-07, "epoch": 3.4147997284453497, "percentage": 68.3, "elapsed_time": "1:03:07", "remaining_time": "0:29:18", "throughput": 10201.91, "total_tokens": 38641920}
{"current_steps": 40245, "total_steps": 58920, "loss": 0.0, "lr": 5.521540380557246e-07, "epoch": 3.415224032586558, "percentage": 68.3, "elapsed_time": "1:03:08", "remaining_time": "0:29:17", "throughput": 10202.11, "total_tokens": 38646528}
{"current_steps": 40250, "total_steps": 58920, "loss": 0.0, "lr": 5.51889204074539e-07, "epoch": 3.4156483367277666, "percentage": 68.31, "elapsed_time": "1:03:08", "remaining_time": "0:29:17", "throughput": 10202.18, "total_tokens": 38650624}
{"current_steps": 40255, "total_steps": 58920, "loss": 0.0, "lr": 5.516244094134578e-07, "epoch": 3.416072640868975, "percentage": 68.32, "elapsed_time": "1:03:08", "remaining_time": "0:29:16", "throughput": 10202.59, "total_tokens": 38656320}
{"current_steps": 40260, "total_steps": 58920, "loss": 0.0, "lr": 5.51359654095716e-07, "epoch": 3.4164969450101834, "percentage": 68.33, "elapsed_time": "1:03:09", "remaining_time": "0:29:16", "throughput": 10202.78, "total_tokens": 38660864}
{"current_steps": 40265, "total_steps": 58920, "loss": 0.0, "lr": 5.510949381445444e-07, "epoch": 3.416921249151392, "percentage": 68.34, "elapsed_time": "1:03:09", "remaining_time": "0:29:15", "throughput": 10202.36, "total_tokens": 38665920}
{"current_steps": 40270, "total_steps": 58920, "loss": 0.0, "lr": 5.508302615831714e-07, "epoch": 3.4173455532926003, "percentage": 68.35, "elapsed_time": "1:03:10", "remaining_time": "0:29:15", "throughput": 10202.63, "total_tokens": 38670912}
{"current_steps": 40275, "total_steps": 58920, "loss": 0.0, "lr": 5.505656244348214e-07, "epoch": 3.4177698574338087, "percentage": 68.36, "elapsed_time": "1:03:10", "remaining_time": "0:29:14", "throughput": 10202.89, "total_tokens": 38675840}
{"current_steps": 40280, "total_steps": 58920, "loss": 0.0, "lr": 5.503010267227149e-07, "epoch": 3.418194161575017, "percentage": 68.36, "elapsed_time": "1:03:11", "remaining_time": "0:29:14", "throughput": 10203.54, "total_tokens": 38682816}
{"current_steps": 40285, "total_steps": 58920, "loss": 0.0, "lr": 5.500364684700698e-07, "epoch": 3.4186184657162255, "percentage": 68.37, "elapsed_time": "1:03:11", "remaining_time": "0:29:13", "throughput": 10203.72, "total_tokens": 38687296}
{"current_steps": 40290, "total_steps": 58920, "loss": 0.0, "lr": 5.497719497001e-07, "epoch": 3.419042769857434, "percentage": 68.38, "elapsed_time": "1:03:11", "remaining_time": "0:29:13", "throughput": 10203.9, "total_tokens": 38691840}
{"current_steps": 40295, "total_steps": 58920, "loss": 0.0134, "lr": 5.495074704360161e-07, "epoch": 3.4194670739986424, "percentage": 68.39, "elapsed_time": "1:03:12", "remaining_time": "0:29:12", "throughput": 10204.15, "total_tokens": 38696704}
{"current_steps": 40300, "total_steps": 58920, "loss": 0.0, "lr": 5.492430307010252e-07, "epoch": 3.419891378139851, "percentage": 68.4, "elapsed_time": "1:03:12", "remaining_time": "0:29:12", "throughput": 10204.4, "total_tokens": 38701632}
{"current_steps": 40305, "total_steps": 58920, "loss": 0.0, "lr": 5.489786305183304e-07, "epoch": 3.420315682281059, "percentage": 68.41, "elapsed_time": "1:03:13", "remaining_time": "0:29:11", "throughput": 10204.61, "total_tokens": 38706304}
{"current_steps": 40310, "total_steps": 58920, "loss": 0.0, "lr": 5.487142699111331e-07, "epoch": 3.4207399864222676, "percentage": 68.41, "elapsed_time": "1:03:13", "remaining_time": "0:29:11", "throughput": 10204.89, "total_tokens": 38711296}
{"current_steps": 40315, "total_steps": 58920, "loss": 0.0, "lr": 5.484499489026291e-07, "epoch": 3.421164290563476, "percentage": 68.42, "elapsed_time": "1:03:13", "remaining_time": "0:29:10", "throughput": 10205.08, "total_tokens": 38715840}
{"current_steps": 40320, "total_steps": 58920, "loss": 0.0, "lr": 5.481856675160116e-07, "epoch": 3.4215885947046845, "percentage": 68.43, "elapsed_time": "1:03:14", "remaining_time": "0:29:10", "throughput": 10205.33, "total_tokens": 38720704}
{"current_steps": 40325, "total_steps": 58920, "loss": 0.0, "lr": 5.479214257744705e-07, "epoch": 3.422012898845893, "percentage": 68.44, "elapsed_time": "1:03:14", "remaining_time": "0:29:09", "throughput": 10205.6, "total_tokens": 38725632}
{"current_steps": 40330, "total_steps": 58920, "loss": 0.0, "lr": 5.476572237011917e-07, "epoch": 3.4224372029871013, "percentage": 68.45, "elapsed_time": "1:03:14", "remaining_time": "0:29:09", "throughput": 10205.94, "total_tokens": 38731008}
{"current_steps": 40335, "total_steps": 58920, "loss": 0.0392, "lr": 5.473930613193591e-07, "epoch": 3.4228615071283097, "percentage": 68.46, "elapsed_time": "1:03:15", "remaining_time": "0:29:08", "throughput": 10206.3, "total_tokens": 38736448}
{"current_steps": 40340, "total_steps": 58920, "loss": 0.0, "lr": 5.471289386521505e-07, "epoch": 3.423285811269518, "percentage": 68.47, "elapsed_time": "1:03:15", "remaining_time": "0:29:08", "throughput": 10206.47, "total_tokens": 38741056}
{"current_steps": 40345, "total_steps": 58920, "loss": 0.0, "lr": 5.468648557227434e-07, "epoch": 3.4237101154107266, "percentage": 68.47, "elapsed_time": "1:03:16", "remaining_time": "0:29:07", "throughput": 10206.7, "total_tokens": 38745856}
{"current_steps": 40350, "total_steps": 58920, "loss": 0.0, "lr": 5.46600812554308e-07, "epoch": 3.424134419551935, "percentage": 68.48, "elapsed_time": "1:03:16", "remaining_time": "0:29:07", "throughput": 10206.93, "total_tokens": 38750656}
{"current_steps": 40355, "total_steps": 58920, "loss": 0.0, "lr": 5.463368091700154e-07, "epoch": 3.4245587236931434, "percentage": 68.49, "elapsed_time": "1:03:16", "remaining_time": "0:29:06", "throughput": 10207.14, "total_tokens": 38755328}
{"current_steps": 40360, "total_steps": 58920, "loss": 0.0, "lr": 5.460728455930294e-07, "epoch": 3.424983027834352, "percentage": 68.5, "elapsed_time": "1:03:17", "remaining_time": "0:29:06", "throughput": 10207.46, "total_tokens": 38760576}
{"current_steps": 40365, "total_steps": 58920, "loss": 0.0, "lr": 5.458089218465118e-07, "epoch": 3.4254073319755602, "percentage": 68.51, "elapsed_time": "1:03:17", "remaining_time": "0:29:05", "throughput": 10207.66, "total_tokens": 38765248}
{"current_steps": 40370, "total_steps": 58920, "loss": 0.0, "lr": 5.455450379536224e-07, "epoch": 3.4258316361167687, "percentage": 68.52, "elapsed_time": "1:03:18", "remaining_time": "0:29:05", "throughput": 10207.99, "total_tokens": 38770496}
{"current_steps": 40375, "total_steps": 58920, "loss": 0.0, "lr": 5.452811939375141e-07, "epoch": 3.426255940257977, "percentage": 68.53, "elapsed_time": "1:03:18", "remaining_time": "0:29:04", "throughput": 10208.11, "total_tokens": 38774720}
{"current_steps": 40380, "total_steps": 58920, "loss": 0.0, "lr": 5.450173898213404e-07, "epoch": 3.4266802443991855, "percentage": 68.53, "elapsed_time": "1:03:18", "remaining_time": "0:29:04", "throughput": 10208.37, "total_tokens": 38779648}
{"current_steps": 40385, "total_steps": 58920, "loss": 0.0001, "lr": 5.44753625628247e-07, "epoch": 3.427104548540394, "percentage": 68.54, "elapsed_time": "1:03:19", "remaining_time": "0:29:03", "throughput": 10208.76, "total_tokens": 38785216}
{"current_steps": 40390, "total_steps": 58920, "loss": 0.0, "lr": 5.444899013813797e-07, "epoch": 3.4275288526816023, "percentage": 68.55, "elapsed_time": "1:03:19", "remaining_time": "0:29:03", "throughput": 10208.94, "total_tokens": 38789760}
{"current_steps": 40395, "total_steps": 58920, "loss": 0.0, "lr": 5.442262171038794e-07, "epoch": 3.4279531568228108, "percentage": 68.56, "elapsed_time": "1:03:19", "remaining_time": "0:29:02", "throughput": 10209.12, "total_tokens": 38794304}
{"current_steps": 40400, "total_steps": 58920, "loss": 0.0, "lr": 5.439625728188821e-07, "epoch": 3.428377460964019, "percentage": 68.57, "elapsed_time": "1:03:20", "remaining_time": "0:29:02", "throughput": 10209.34, "total_tokens": 38799040}
{"current_steps": 40405, "total_steps": 58920, "loss": 0.0, "lr": 5.436989685495235e-07, "epoch": 3.4288017651052276, "percentage": 68.58, "elapsed_time": "1:03:20", "remaining_time": "0:29:01", "throughput": 10209.53, "total_tokens": 38803648}
{"current_steps": 40410, "total_steps": 58920, "loss": 0.0325, "lr": 5.43435404318932e-07, "epoch": 3.429226069246436, "percentage": 68.58, "elapsed_time": "1:03:21", "remaining_time": "0:29:01", "throughput": 10209.87, "total_tokens": 38809024}
{"current_steps": 40415, "total_steps": 58920, "loss": 0.0, "lr": 5.431718801502357e-07, "epoch": 3.4296503733876444, "percentage": 68.59, "elapsed_time": "1:03:21", "remaining_time": "0:29:00", "throughput": 10210.03, "total_tokens": 38813440}
{"current_steps": 40420, "total_steps": 58920, "loss": 0.0, "lr": 5.429083960665577e-07, "epoch": 3.430074677528853, "percentage": 68.6, "elapsed_time": "1:03:21", "remaining_time": "0:29:00", "throughput": 10210.19, "total_tokens": 38817920}
{"current_steps": 40425, "total_steps": 58920, "loss": 0.0, "lr": 5.426449520910175e-07, "epoch": 3.4304989816700613, "percentage": 68.61, "elapsed_time": "1:03:22", "remaining_time": "0:28:59", "throughput": 10210.41, "total_tokens": 38822656}
{"current_steps": 40430, "total_steps": 58920, "loss": 0.0, "lr": 5.423815482467316e-07, "epoch": 3.4309232858112697, "percentage": 68.62, "elapsed_time": "1:03:22", "remaining_time": "0:28:59", "throughput": 10210.57, "total_tokens": 38827072}
{"current_steps": 40435, "total_steps": 58920, "loss": 0.0, "lr": 5.421181845568124e-07, "epoch": 3.431347589952478, "percentage": 68.63, "elapsed_time": "1:03:23", "remaining_time": "0:28:58", "throughput": 10210.95, "total_tokens": 38832576}
{"current_steps": 40440, "total_steps": 58920, "loss": 0.0002, "lr": 5.418548610443699e-07, "epoch": 3.4317718940936865, "percentage": 68.64, "elapsed_time": "1:03:23", "remaining_time": "0:28:58", "throughput": 10211.14, "total_tokens": 38837120}
{"current_steps": 40445, "total_steps": 58920, "loss": 0.0, "lr": 5.415915777325085e-07, "epoch": 3.4321961982348945, "percentage": 68.64, "elapsed_time": "1:03:23", "remaining_time": "0:28:57", "throughput": 10211.37, "total_tokens": 38841920}
{"current_steps": 40450, "total_steps": 58920, "loss": 0.0, "lr": 5.413283346443314e-07, "epoch": 3.4326205023761034, "percentage": 68.65, "elapsed_time": "1:03:24", "remaining_time": "0:28:57", "throughput": 10211.67, "total_tokens": 38847040}
{"current_steps": 40455, "total_steps": 58920, "loss": 0.0131, "lr": 5.410651318029368e-07, "epoch": 3.4330448065173114, "percentage": 68.66, "elapsed_time": "1:03:24", "remaining_time": "0:28:56", "throughput": 10211.79, "total_tokens": 38851264}
{"current_steps": 40460, "total_steps": 58920, "loss": 0.0, "lr": 5.4080196923142e-07, "epoch": 3.4334691106585202, "percentage": 68.67, "elapsed_time": "1:03:24", "remaining_time": "0:28:56", "throughput": 10212.04, "total_tokens": 38856128}
{"current_steps": 40465, "total_steps": 58920, "loss": 0.0202, "lr": 5.405388469528724e-07, "epoch": 3.433893414799728, "percentage": 68.68, "elapsed_time": "1:03:25", "remaining_time": "0:28:55", "throughput": 10212.46, "total_tokens": 38861824}
{"current_steps": 40470, "total_steps": 58920, "loss": 0.0, "lr": 5.402757649903822e-07, "epoch": 3.434317718940937, "percentage": 68.69, "elapsed_time": "1:03:25", "remaining_time": "0:28:55", "throughput": 10212.73, "total_tokens": 38866816}
{"current_steps": 40475, "total_steps": 58920, "loss": 0.0, "lr": 5.400127233670338e-07, "epoch": 3.434742023082145, "percentage": 68.69, "elapsed_time": "1:03:26", "remaining_time": "0:28:54", "throughput": 10213.02, "total_tokens": 38871872}
{"current_steps": 40480, "total_steps": 58920, "loss": 0.0033, "lr": 5.39749722105908e-07, "epoch": 3.435166327223354, "percentage": 68.7, "elapsed_time": "1:03:26", "remaining_time": "0:28:53", "throughput": 10213.25, "total_tokens": 38876672}
{"current_steps": 40485, "total_steps": 58920, "loss": 0.0, "lr": 5.394867612300824e-07, "epoch": 3.435590631364562, "percentage": 68.71, "elapsed_time": "1:03:26", "remaining_time": "0:28:53", "throughput": 10213.49, "total_tokens": 38881472}
{"current_steps": 40490, "total_steps": 58920, "loss": 0.0, "lr": 5.392238407626309e-07, "epoch": 3.4360149355057708, "percentage": 68.72, "elapsed_time": "1:03:27", "remaining_time": "0:28:52", "throughput": 10213.69, "total_tokens": 38886080}
{"current_steps": 40495, "total_steps": 58920, "loss": 0.0, "lr": 5.389609607266238e-07, "epoch": 3.4364392396469787, "percentage": 68.73, "elapsed_time": "1:03:27", "remaining_time": "0:28:52", "throughput": 10213.98, "total_tokens": 38891136}
{"current_steps": 40500, "total_steps": 58920, "loss": 0.0, "lr": 5.386981211451278e-07, "epoch": 3.4368635437881876, "percentage": 68.74, "elapsed_time": "1:03:28", "remaining_time": "0:28:51", "throughput": 10214.21, "total_tokens": 38895872}
{"current_steps": 40505, "total_steps": 58920, "loss": 0.0001, "lr": 5.384353220412061e-07, "epoch": 3.4372878479293956, "percentage": 68.75, "elapsed_time": "1:03:28", "remaining_time": "0:28:51", "throughput": 10214.3, "total_tokens": 38899968}
{"current_steps": 40510, "total_steps": 58920, "loss": 0.0, "lr": 5.381725634379184e-07, "epoch": 3.4377121520706044, "percentage": 68.75, "elapsed_time": "1:03:28", "remaining_time": "0:28:50", "throughput": 10214.63, "total_tokens": 38905216}
{"current_steps": 40515, "total_steps": 58920, "loss": 0.0, "lr": 5.379098453583209e-07, "epoch": 3.4381364562118124, "percentage": 68.76, "elapsed_time": "1:03:29", "remaining_time": "0:28:50", "throughput": 10215.07, "total_tokens": 38911104}
{"current_steps": 40520, "total_steps": 58920, "loss": 0.0, "lr": 5.376471678254655e-07, "epoch": 3.4385607603530213, "percentage": 68.77, "elapsed_time": "1:03:29", "remaining_time": "0:28:49", "throughput": 10215.17, "total_tokens": 38915264}
{"current_steps": 40525, "total_steps": 58920, "loss": 0.0, "lr": 5.373845308624027e-07, "epoch": 3.4389850644942292, "percentage": 68.78, "elapsed_time": "1:03:29", "remaining_time": "0:28:49", "throughput": 10215.38, "total_tokens": 38919936}
{"current_steps": 40530, "total_steps": 58920, "loss": 0.0, "lr": 5.371219344921768e-07, "epoch": 3.439409368635438, "percentage": 68.79, "elapsed_time": "1:03:30", "remaining_time": "0:28:48", "throughput": 10215.68, "total_tokens": 38925120}
{"current_steps": 40535, "total_steps": 58920, "loss": 0.0, "lr": 5.368593787378298e-07, "epoch": 3.439833672776646, "percentage": 68.8, "elapsed_time": "1:03:30", "remaining_time": "0:28:48", "throughput": 10215.85, "total_tokens": 38929664}
{"current_steps": 40540, "total_steps": 58920, "loss": 0.0, "lr": 5.365968636224002e-07, "epoch": 3.440257976917855, "percentage": 68.81, "elapsed_time": "1:03:31", "remaining_time": "0:28:47", "throughput": 10215.96, "total_tokens": 38933824}
{"current_steps": 40545, "total_steps": 58920, "loss": 0.0, "lr": 5.363343891689223e-07, "epoch": 3.440682281059063, "percentage": 68.81, "elapsed_time": "1:03:31", "remaining_time": "0:28:47", "throughput": 10216.15, "total_tokens": 38938432}
{"current_steps": 40550, "total_steps": 58920, "loss": 0.0272, "lr": 5.360719554004285e-07, "epoch": 3.441106585200272, "percentage": 68.82, "elapsed_time": "1:03:31", "remaining_time": "0:28:46", "throughput": 10216.32, "total_tokens": 38942912}
{"current_steps": 40555, "total_steps": 58920, "loss": 0.0, "lr": 5.358095623399448e-07, "epoch": 3.4415308893414798, "percentage": 68.83, "elapsed_time": "1:03:32", "remaining_time": "0:28:46", "throughput": 10216.56, "total_tokens": 38947776}
{"current_steps": 40560, "total_steps": 58920, "loss": 0.0, "lr": 5.355472100104969e-07, "epoch": 3.4419551934826886, "percentage": 68.84, "elapsed_time": "1:03:32", "remaining_time": "0:28:45", "throughput": 10216.78, "total_tokens": 38952448}
{"current_steps": 40565, "total_steps": 58920, "loss": 0.0, "lr": 5.352848984351039e-07, "epoch": 3.4423794976238966, "percentage": 68.85, "elapsed_time": "1:03:32", "remaining_time": "0:28:45", "throughput": 10217.01, "total_tokens": 38957248}
{"current_steps": 40570, "total_steps": 58920, "loss": 0.0, "lr": 5.350226276367833e-07, "epoch": 3.4428038017651055, "percentage": 68.86, "elapsed_time": "1:03:33", "remaining_time": "0:28:44", "throughput": 10217.28, "total_tokens": 38962240}
{"current_steps": 40575, "total_steps": 58920, "loss": 0.0, "lr": 5.347603976385485e-07, "epoch": 3.4432281059063135, "percentage": 68.86, "elapsed_time": "1:03:33", "remaining_time": "0:28:44", "throughput": 10217.55, "total_tokens": 38967232}
{"current_steps": 40580, "total_steps": 58920, "loss": 0.0393, "lr": 5.344982084634083e-07, "epoch": 3.443652410047522, "percentage": 68.87, "elapsed_time": "1:03:34", "remaining_time": "0:28:43", "throughput": 10217.77, "total_tokens": 38971904}
{"current_steps": 40585, "total_steps": 58920, "loss": 0.0, "lr": 5.342360601343706e-07, "epoch": 3.4440767141887303, "percentage": 68.88, "elapsed_time": "1:03:34", "remaining_time": "0:28:43", "throughput": 10218.04, "total_tokens": 38976896}
{"current_steps": 40590, "total_steps": 58920, "loss": 0.0, "lr": 5.339739526744363e-07, "epoch": 3.4445010183299387, "percentage": 68.89, "elapsed_time": "1:03:34", "remaining_time": "0:28:42", "throughput": 10218.33, "total_tokens": 38981952}
{"current_steps": 40595, "total_steps": 58920, "loss": 0.0318, "lr": 5.337118861066057e-07, "epoch": 3.444925322471147, "percentage": 68.9, "elapsed_time": "1:03:35", "remaining_time": "0:28:42", "throughput": 10218.54, "total_tokens": 38986688}
{"current_steps": 40600, "total_steps": 58920, "loss": 0.0, "lr": 5.334498604538728e-07, "epoch": 3.4453496266123556, "percentage": 68.91, "elapsed_time": "1:03:35", "remaining_time": "0:28:41", "throughput": 10218.75, "total_tokens": 38991360}
{"current_steps": 40605, "total_steps": 58920, "loss": 0.0, "lr": 5.331878757392306e-07, "epoch": 3.445773930753564, "percentage": 68.92, "elapsed_time": "1:03:36", "remaining_time": "0:28:41", "throughput": 10218.95, "total_tokens": 38995968}
{"current_steps": 40610, "total_steps": 58920, "loss": 0.0, "lr": 5.329259319856674e-07, "epoch": 3.4461982348947724, "percentage": 68.92, "elapsed_time": "1:03:36", "remaining_time": "0:28:40", "throughput": 10219.18, "total_tokens": 39000768}
{"current_steps": 40615, "total_steps": 58920, "loss": 0.0, "lr": 5.326640292161664e-07, "epoch": 3.446622539035981, "percentage": 68.93, "elapsed_time": "1:03:36", "remaining_time": "0:28:40", "throughput": 10219.36, "total_tokens": 39005312}
{"current_steps": 40620, "total_steps": 58920, "loss": 0.0, "lr": 5.324021674537102e-07, "epoch": 3.4470468431771892, "percentage": 68.94, "elapsed_time": "1:03:37", "remaining_time": "0:28:39", "throughput": 10219.59, "total_tokens": 39010112}
{"current_steps": 40625, "total_steps": 58920, "loss": 0.0, "lr": 5.321403467212748e-07, "epoch": 3.4474711473183977, "percentage": 68.95, "elapsed_time": "1:03:37", "remaining_time": "0:28:39", "throughput": 10219.74, "total_tokens": 39014528}
{"current_steps": 40630, "total_steps": 58920, "loss": 0.0, "lr": 5.318785670418353e-07, "epoch": 3.447895451459606, "percentage": 68.96, "elapsed_time": "1:03:37", "remaining_time": "0:28:38", "throughput": 10220.0, "total_tokens": 39019456}
{"current_steps": 40635, "total_steps": 58920, "loss": 0.0, "lr": 5.316168284383614e-07, "epoch": 3.4483197556008145, "percentage": 68.97, "elapsed_time": "1:03:38", "remaining_time": "0:28:38", "throughput": 10220.12, "total_tokens": 39023744}
{"current_steps": 40640, "total_steps": 58920, "loss": 0.0, "lr": 5.313551309338197e-07, "epoch": 3.448744059742023, "percentage": 68.97, "elapsed_time": "1:03:38", "remaining_time": "0:28:37", "throughput": 10220.29, "total_tokens": 39028224}
{"current_steps": 40645, "total_steps": 58920, "loss": 0.0, "lr": 5.310934745511732e-07, "epoch": 3.4491683638832313, "percentage": 68.98, "elapsed_time": "1:03:39", "remaining_time": "0:28:37", "throughput": 10220.56, "total_tokens": 39033280}
{"current_steps": 40650, "total_steps": 58920, "loss": 0.0, "lr": 5.308318593133812e-07, "epoch": 3.4495926680244398, "percentage": 68.99, "elapsed_time": "1:03:39", "remaining_time": "0:28:36", "throughput": 10220.93, "total_tokens": 39038784}
{"current_steps": 40655, "total_steps": 58920, "loss": 0.0, "lr": 5.305702852434002e-07, "epoch": 3.450016972165648, "percentage": 69.0, "elapsed_time": "1:03:39", "remaining_time": "0:28:36", "throughput": 10221.18, "total_tokens": 39043648}
{"current_steps": 40660, "total_steps": 58920, "loss": 0.0, "lr": 5.30308752364181e-07, "epoch": 3.4504412763068566, "percentage": 69.01, "elapsed_time": "1:03:40", "remaining_time": "0:28:35", "throughput": 10221.48, "total_tokens": 39048832}
{"current_steps": 40665, "total_steps": 58920, "loss": 0.0, "lr": 5.300472606986732e-07, "epoch": 3.450865580448065, "percentage": 69.02, "elapsed_time": "1:03:40", "remaining_time": "0:28:35", "throughput": 10221.68, "total_tokens": 39053440}
{"current_steps": 40670, "total_steps": 58920, "loss": 0.0, "lr": 5.297858102698216e-07, "epoch": 3.4512898845892734, "percentage": 69.03, "elapsed_time": "1:03:41", "remaining_time": "0:28:34", "throughput": 10221.93, "total_tokens": 39058304}
{"current_steps": 40675, "total_steps": 58920, "loss": 0.0, "lr": 5.295244011005676e-07, "epoch": 3.451714188730482, "percentage": 69.03, "elapsed_time": "1:03:41", "remaining_time": "0:28:34", "throughput": 10222.29, "total_tokens": 39063744}
{"current_steps": 40680, "total_steps": 58920, "loss": 0.0, "lr": 5.292630332138486e-07, "epoch": 3.4521384928716903, "percentage": 69.04, "elapsed_time": "1:03:41", "remaining_time": "0:28:33", "throughput": 10222.52, "total_tokens": 39068544}
{"current_steps": 40685, "total_steps": 58920, "loss": 0.0, "lr": 5.290017066325987e-07, "epoch": 3.4525627970128987, "percentage": 69.05, "elapsed_time": "1:03:42", "remaining_time": "0:28:33", "throughput": 10222.79, "total_tokens": 39073536}
{"current_steps": 40690, "total_steps": 58920, "loss": 0.0, "lr": 5.287404213797487e-07, "epoch": 3.452987101154107, "percentage": 69.06, "elapsed_time": "1:03:42", "remaining_time": "0:28:32", "throughput": 10223.16, "total_tokens": 39079040}
{"current_steps": 40695, "total_steps": 58920, "loss": 0.0, "lr": 5.284791774782253e-07, "epoch": 3.4534114052953155, "percentage": 69.07, "elapsed_time": "1:03:42", "remaining_time": "0:28:32", "throughput": 10223.38, "total_tokens": 39083776}
{"current_steps": 40700, "total_steps": 58920, "loss": 0.0, "lr": 5.282179749509516e-07, "epoch": 3.453835709436524, "percentage": 69.08, "elapsed_time": "1:03:43", "remaining_time": "0:28:31", "throughput": 10223.56, "total_tokens": 39088320}
{"current_steps": 40705, "total_steps": 58920, "loss": 0.0, "lr": 5.279568138208472e-07, "epoch": 3.4542600135777324, "percentage": 69.09, "elapsed_time": "1:03:43", "remaining_time": "0:28:31", "throughput": 10223.78, "total_tokens": 39093056}
{"current_steps": 40710, "total_steps": 58920, "loss": 0.0, "lr": 5.27695694110828e-07, "epoch": 3.454684317718941, "percentage": 69.09, "elapsed_time": "1:03:44", "remaining_time": "0:28:30", "throughput": 10224.01, "total_tokens": 39097856}
{"current_steps": 40715, "total_steps": 58920, "loss": 0.0, "lr": 5.274346158438065e-07, "epoch": 3.455108621860149, "percentage": 69.1, "elapsed_time": "1:03:44", "remaining_time": "0:28:30", "throughput": 10224.27, "total_tokens": 39102784}
{"current_steps": 40720, "total_steps": 58920, "loss": 0.0, "lr": 5.271735790426913e-07, "epoch": 3.4555329260013576, "percentage": 69.11, "elapsed_time": "1:03:44", "remaining_time": "0:28:29", "throughput": 10224.43, "total_tokens": 39107200}
{"current_steps": 40725, "total_steps": 58920, "loss": 0.0003, "lr": 5.269125837303874e-07, "epoch": 3.455957230142566, "percentage": 69.12, "elapsed_time": "1:03:45", "remaining_time": "0:28:29", "throughput": 10224.63, "total_tokens": 39111808}
{"current_steps": 40730, "total_steps": 58920, "loss": 0.0, "lr": 5.266516299297962e-07, "epoch": 3.4563815342837745, "percentage": 69.13, "elapsed_time": "1:03:45", "remaining_time": "0:28:28", "throughput": 10224.96, "total_tokens": 39117056}
{"current_steps": 40735, "total_steps": 58920, "loss": 0.0, "lr": 5.263907176638153e-07, "epoch": 3.456805838424983, "percentage": 69.14, "elapsed_time": "1:03:46", "remaining_time": "0:28:28", "throughput": 10225.13, "total_tokens": 39121600}
{"current_steps": 40740, "total_steps": 58920, "loss": 0.0, "lr": 5.261298469553392e-07, "epoch": 3.4572301425661913, "percentage": 69.14, "elapsed_time": "1:03:46", "remaining_time": "0:28:27", "throughput": 10225.45, "total_tokens": 39126848}
{"current_steps": 40745, "total_steps": 58920, "loss": 0.0, "lr": 5.25869017827258e-07, "epoch": 3.4576544467073997, "percentage": 69.15, "elapsed_time": "1:03:46", "remaining_time": "0:28:27", "throughput": 10225.63, "total_tokens": 39131392}
{"current_steps": 40750, "total_steps": 58920, "loss": 0.0, "lr": 5.256082303024587e-07, "epoch": 3.458078750848608, "percentage": 69.16, "elapsed_time": "1:03:47", "remaining_time": "0:28:26", "throughput": 10225.9, "total_tokens": 39136384}
{"current_steps": 40755, "total_steps": 58920, "loss": 0.0, "lr": 5.253474844038244e-07, "epoch": 3.4585030549898166, "percentage": 69.17, "elapsed_time": "1:03:47", "remaining_time": "0:28:25", "throughput": 10226.19, "total_tokens": 39141440}
{"current_steps": 40760, "total_steps": 58920, "loss": 0.0, "lr": 5.250867801542342e-07, "epoch": 3.458927359131025, "percentage": 69.18, "elapsed_time": "1:03:47", "remaining_time": "0:28:25", "throughput": 10226.48, "total_tokens": 39146560}
{"current_steps": 40765, "total_steps": 58920, "loss": 0.0, "lr": 5.248261175765652e-07, "epoch": 3.4593516632722334, "percentage": 69.19, "elapsed_time": "1:03:48", "remaining_time": "0:28:24", "throughput": 10226.66, "total_tokens": 39151104}
{"current_steps": 40770, "total_steps": 58920, "loss": 0.0, "lr": 5.245654966936879e-07, "epoch": 3.459775967413442, "percentage": 69.2, "elapsed_time": "1:03:48", "remaining_time": "0:28:24", "throughput": 10226.8, "total_tokens": 39155520}
{"current_steps": 40775, "total_steps": 58920, "loss": 0.0, "lr": 5.243049175284724e-07, "epoch": 3.4602002715546503, "percentage": 69.2, "elapsed_time": "1:03:49", "remaining_time": "0:28:23", "throughput": 10227.09, "total_tokens": 39160576}
{"current_steps": 40780, "total_steps": 58920, "loss": 0.0291, "lr": 5.240443801037827e-07, "epoch": 3.4606245756958587, "percentage": 69.21, "elapsed_time": "1:03:49", "remaining_time": "0:28:23", "throughput": 10227.43, "total_tokens": 39165888}
{"current_steps": 40785, "total_steps": 58920, "loss": 0.0, "lr": 5.237838844424802e-07, "epoch": 3.461048879837067, "percentage": 69.22, "elapsed_time": "1:03:49", "remaining_time": "0:28:22", "throughput": 10227.65, "total_tokens": 39170560}
{"current_steps": 40790, "total_steps": 58920, "loss": 0.0, "lr": 5.235234305674223e-07, "epoch": 3.4614731839782755, "percentage": 69.23, "elapsed_time": "1:03:50", "remaining_time": "0:28:22", "throughput": 10228.01, "total_tokens": 39176064}
{"current_steps": 40795, "total_steps": 58920, "loss": 0.0, "lr": 5.232630185014628e-07, "epoch": 3.461897488119484, "percentage": 69.24, "elapsed_time": "1:03:50", "remaining_time": "0:28:21", "throughput": 10228.22, "total_tokens": 39180736}
{"current_steps": 40800, "total_steps": 58920, "loss": 0.0, "lr": 5.23002648267453e-07, "epoch": 3.4623217922606924, "percentage": 69.25, "elapsed_time": "1:03:51", "remaining_time": "0:28:21", "throughput": 10228.51, "total_tokens": 39185792}
{"current_steps": 40805, "total_steps": 58920, "loss": 0.0, "lr": 5.227423198882379e-07, "epoch": 3.462746096401901, "percentage": 69.25, "elapsed_time": "1:03:51", "remaining_time": "0:28:20", "throughput": 10228.84, "total_tokens": 39191040}
{"current_steps": 40810, "total_steps": 58920, "loss": 0.0, "lr": 5.224820333866618e-07, "epoch": 3.463170400543109, "percentage": 69.26, "elapsed_time": "1:03:51", "remaining_time": "0:28:20", "throughput": 10229.03, "total_tokens": 39195648}
{"current_steps": 40815, "total_steps": 58920, "loss": 0.0, "lr": 5.222217887855627e-07, "epoch": 3.4635947046843176, "percentage": 69.27, "elapsed_time": "1:03:52", "remaining_time": "0:28:19", "throughput": 10229.27, "total_tokens": 39200512}
{"current_steps": 40820, "total_steps": 58920, "loss": 0.0, "lr": 5.219615861077763e-07, "epoch": 3.464019008825526, "percentage": 69.28, "elapsed_time": "1:03:52", "remaining_time": "0:28:19", "throughput": 10229.58, "total_tokens": 39205696}
{"current_steps": 40825, "total_steps": 58920, "loss": 0.0306, "lr": 5.217014253761356e-07, "epoch": 3.4644433129667345, "percentage": 69.29, "elapsed_time": "1:03:52", "remaining_time": "0:28:18", "throughput": 10229.79, "total_tokens": 39210368}
{"current_steps": 40830, "total_steps": 58920, "loss": 0.0, "lr": 5.214413066134671e-07, "epoch": 3.464867617107943, "percentage": 69.3, "elapsed_time": "1:03:53", "remaining_time": "0:28:18", "throughput": 10230.13, "total_tokens": 39215744}
{"current_steps": 40835, "total_steps": 58920, "loss": 0.0, "lr": 5.211812298425968e-07, "epoch": 3.4652919212491513, "percentage": 69.31, "elapsed_time": "1:03:53", "remaining_time": "0:28:17", "throughput": 10230.35, "total_tokens": 39220544}
{"current_steps": 40840, "total_steps": 58920, "loss": 0.0, "lr": 5.209211950863443e-07, "epoch": 3.4657162253903597, "percentage": 69.31, "elapsed_time": "1:03:54", "remaining_time": "0:28:17", "throughput": 10230.51, "total_tokens": 39225024}
{"current_steps": 40845, "total_steps": 58920, "loss": 0.0, "lr": 5.206612023675277e-07, "epoch": 3.466140529531568, "percentage": 69.32, "elapsed_time": "1:03:54", "remaining_time": "0:28:16", "throughput": 10230.69, "total_tokens": 39229568}
{"current_steps": 40850, "total_steps": 58920, "loss": 0.0, "lr": 5.204012517089593e-07, "epoch": 3.4665648336727766, "percentage": 69.33, "elapsed_time": "1:03:54", "remaining_time": "0:28:16", "throughput": 10230.87, "total_tokens": 39234112}
{"current_steps": 40855, "total_steps": 58920, "loss": 0.0, "lr": 5.2014134313345e-07, "epoch": 3.466989137813985, "percentage": 69.34, "elapsed_time": "1:03:55", "remaining_time": "0:28:15", "throughput": 10231.04, "total_tokens": 39238656}
{"current_steps": 40860, "total_steps": 58920, "loss": 0.0, "lr": 5.198814766638056e-07, "epoch": 3.4674134419551934, "percentage": 69.35, "elapsed_time": "1:03:55", "remaining_time": "0:28:15", "throughput": 10231.18, "total_tokens": 39243008}
{"current_steps": 40865, "total_steps": 58920, "loss": 0.0, "lr": 5.196216523228273e-07, "epoch": 3.467837746096402, "percentage": 69.36, "elapsed_time": "1:03:56", "remaining_time": "0:28:14", "throughput": 10231.46, "total_tokens": 39248064}
{"current_steps": 40870, "total_steps": 58920, "loss": 0.0, "lr": 5.193618701333155e-07, "epoch": 3.4682620502376103, "percentage": 69.37, "elapsed_time": "1:03:56", "remaining_time": "0:28:14", "throughput": 10231.71, "total_tokens": 39252992}
{"current_steps": 40875, "total_steps": 58920, "loss": 0.0, "lr": 5.191021301180634e-07, "epoch": 3.4686863543788187, "percentage": 69.37, "elapsed_time": "1:03:56", "remaining_time": "0:28:13", "throughput": 10231.82, "total_tokens": 39257216}
{"current_steps": 40880, "total_steps": 58920, "loss": 0.0, "lr": 5.188424322998634e-07, "epoch": 3.469110658520027, "percentage": 69.38, "elapsed_time": "1:03:57", "remaining_time": "0:28:13", "throughput": 10232.07, "total_tokens": 39262080}
{"current_steps": 40885, "total_steps": 58920, "loss": 0.0, "lr": 5.185827767015029e-07, "epoch": 3.4695349626612355, "percentage": 69.39, "elapsed_time": "1:03:57", "remaining_time": "0:28:12", "throughput": 10232.32, "total_tokens": 39266944}
{"current_steps": 40890, "total_steps": 58920, "loss": 0.0, "lr": 5.183231633457657e-07, "epoch": 3.469959266802444, "percentage": 69.4, "elapsed_time": "1:03:57", "remaining_time": "0:28:12", "throughput": 10232.56, "total_tokens": 39271808}
{"current_steps": 40895, "total_steps": 58920, "loss": 0.0, "lr": 5.180635922554317e-07, "epoch": 3.4703835709436524, "percentage": 69.41, "elapsed_time": "1:03:58", "remaining_time": "0:28:11", "throughput": 10232.8, "total_tokens": 39276672}
{"current_steps": 40900, "total_steps": 58920, "loss": 0.0, "lr": 5.178040634532775e-07, "epoch": 3.4708078750848608, "percentage": 69.42, "elapsed_time": "1:03:58", "remaining_time": "0:28:11", "throughput": 10233.02, "total_tokens": 39281408}
{"current_steps": 40905, "total_steps": 58920, "loss": 0.0, "lr": 5.175445769620756e-07, "epoch": 3.471232179226069, "percentage": 69.42, "elapsed_time": "1:03:59", "remaining_time": "0:28:10", "throughput": 10233.22, "total_tokens": 39286016}
{"current_steps": 40910, "total_steps": 58920, "loss": 0.0, "lr": 5.172851328045955e-07, "epoch": 3.4716564833672776, "percentage": 69.43, "elapsed_time": "1:03:59", "remaining_time": "0:28:10", "throughput": 10233.39, "total_tokens": 39290496}
{"current_steps": 40915, "total_steps": 58920, "loss": 0.0, "lr": 5.170257310036019e-07, "epoch": 3.472080787508486, "percentage": 69.44, "elapsed_time": "1:03:59", "remaining_time": "0:28:09", "throughput": 10233.53, "total_tokens": 39294848}
{"current_steps": 40920, "total_steps": 58920, "loss": 0.0, "lr": 5.167663715818566e-07, "epoch": 3.4725050916496945, "percentage": 69.45, "elapsed_time": "1:04:00", "remaining_time": "0:28:09", "throughput": 10233.72, "total_tokens": 39299392}
{"current_steps": 40925, "total_steps": 58920, "loss": 0.0393, "lr": 5.165070545621178e-07, "epoch": 3.472929395790903, "percentage": 69.46, "elapsed_time": "1:04:00", "remaining_time": "0:28:08", "throughput": 10233.97, "total_tokens": 39304320}
{"current_steps": 40930, "total_steps": 58920, "loss": 0.0, "lr": 5.16247779967139e-07, "epoch": 3.4733536999321113, "percentage": 69.47, "elapsed_time": "1:04:00", "remaining_time": "0:28:08", "throughput": 10234.22, "total_tokens": 39309184}
{"current_steps": 40935, "total_steps": 58920, "loss": 0.0, "lr": 5.15988547819671e-07, "epoch": 3.4737780040733197, "percentage": 69.48, "elapsed_time": "1:04:01", "remaining_time": "0:28:07", "throughput": 10234.34, "total_tokens": 39313472}
{"current_steps": 40940, "total_steps": 58920, "loss": 0.0, "lr": 5.157293581424604e-07, "epoch": 3.474202308214528, "percentage": 69.48, "elapsed_time": "1:04:01", "remaining_time": "0:28:07", "throughput": 10234.63, "total_tokens": 39318592}
{"current_steps": 40945, "total_steps": 58920, "loss": 0.0, "lr": 5.154702109582503e-07, "epoch": 3.4746266123557366, "percentage": 69.49, "elapsed_time": "1:04:02", "remaining_time": "0:28:06", "throughput": 10234.72, "total_tokens": 39322688}
{"current_steps": 40950, "total_steps": 58920, "loss": 0.0, "lr": 5.152111062897797e-07, "epoch": 3.475050916496945, "percentage": 69.5, "elapsed_time": "1:04:02", "remaining_time": "0:28:06", "throughput": 10235.01, "total_tokens": 39327808}
{"current_steps": 40955, "total_steps": 58920, "loss": 0.0, "lr": 5.149520441597843e-07, "epoch": 3.4754752206381534, "percentage": 69.51, "elapsed_time": "1:04:02", "remaining_time": "0:28:05", "throughput": 10235.15, "total_tokens": 39332160}
{"current_steps": 40960, "total_steps": 58920, "loss": 0.0, "lr": 5.146930245909957e-07, "epoch": 3.475899524779362, "percentage": 69.52, "elapsed_time": "1:04:03", "remaining_time": "0:28:05", "throughput": 10235.35, "total_tokens": 39336768}
{"current_steps": 40965, "total_steps": 58920, "loss": 0.0, "lr": 5.144340476061419e-07, "epoch": 3.4763238289205702, "percentage": 69.53, "elapsed_time": "1:04:03", "remaining_time": "0:28:04", "throughput": 10235.56, "total_tokens": 39341440}
{"current_steps": 40970, "total_steps": 58920, "loss": 0.0, "lr": 5.141751132279474e-07, "epoch": 3.4767481330617787, "percentage": 69.53, "elapsed_time": "1:04:03", "remaining_time": "0:28:04", "throughput": 10235.77, "total_tokens": 39346048}
{"current_steps": 40975, "total_steps": 58920, "loss": 0.0, "lr": 5.139162214791322e-07, "epoch": 3.477172437202987, "percentage": 69.54, "elapsed_time": "1:04:04", "remaining_time": "0:28:03", "throughput": 10235.94, "total_tokens": 39350592}
{"current_steps": 40980, "total_steps": 58920, "loss": 0.0, "lr": 5.136573723824144e-07, "epoch": 3.4775967413441955, "percentage": 69.55, "elapsed_time": "1:04:04", "remaining_time": "0:28:03", "throughput": 10236.1, "total_tokens": 39355008}
{"current_steps": 40985, "total_steps": 58920, "loss": 0.0, "lr": 5.133985659605058e-07, "epoch": 3.478021045485404, "percentage": 69.56, "elapsed_time": "1:04:05", "remaining_time": "0:28:02", "throughput": 10236.33, "total_tokens": 39359808}
{"current_steps": 40990, "total_steps": 58920, "loss": 0.0001, "lr": 5.131398022361162e-07, "epoch": 3.4784453496266123, "percentage": 69.57, "elapsed_time": "1:04:05", "remaining_time": "0:28:02", "throughput": 10236.56, "total_tokens": 39364608}
{"current_steps": 40995, "total_steps": 58920, "loss": 0.0, "lr": 5.128810812319513e-07, "epoch": 3.4788696537678208, "percentage": 69.58, "elapsed_time": "1:04:05", "remaining_time": "0:28:01", "throughput": 10236.72, "total_tokens": 39369024}
{"current_steps": 41000, "total_steps": 58920, "loss": 0.0001, "lr": 5.126224029707126e-07, "epoch": 3.479293957909029, "percentage": 69.59, "elapsed_time": "1:04:06", "remaining_time": "0:28:01", "throughput": 10236.9, "total_tokens": 39373568}
{"current_steps": 41005, "total_steps": 58920, "loss": 0.0, "lr": 5.123637674750984e-07, "epoch": 3.4797182620502376, "percentage": 69.59, "elapsed_time": "1:04:06", "remaining_time": "0:28:00", "throughput": 10237.06, "total_tokens": 39377984}
{"current_steps": 41010, "total_steps": 58920, "loss": 0.0001, "lr": 5.121051747678026e-07, "epoch": 3.480142566191446, "percentage": 69.6, "elapsed_time": "1:04:06", "remaining_time": "0:28:00", "throughput": 10237.28, "total_tokens": 39382720}
{"current_steps": 41015, "total_steps": 58920, "loss": 0.0, "lr": 5.11846624871517e-07, "epoch": 3.4805668703326544, "percentage": 69.61, "elapsed_time": "1:04:07", "remaining_time": "0:27:59", "throughput": 10237.44, "total_tokens": 39387136}
{"current_steps": 41020, "total_steps": 58920, "loss": 0.0, "lr": 5.115881178089267e-07, "epoch": 3.480991174473863, "percentage": 69.62, "elapsed_time": "1:04:07", "remaining_time": "0:27:59", "throughput": 10237.61, "total_tokens": 39391616}
{"current_steps": 41025, "total_steps": 58920, "loss": 0.0, "lr": 5.113296536027165e-07, "epoch": 3.4814154786150713, "percentage": 69.63, "elapsed_time": "1:04:08", "remaining_time": "0:27:58", "throughput": 10237.82, "total_tokens": 39396288}
{"current_steps": 41030, "total_steps": 58920, "loss": 0.0, "lr": 5.110712322755646e-07, "epoch": 3.4818397827562797, "percentage": 69.64, "elapsed_time": "1:04:08", "remaining_time": "0:27:58", "throughput": 10238.01, "total_tokens": 39400896}
{"current_steps": 41035, "total_steps": 58920, "loss": 0.0, "lr": 5.108128538501464e-07, "epoch": 3.482264086897488, "percentage": 69.65, "elapsed_time": "1:04:08", "remaining_time": "0:27:57", "throughput": 10238.22, "total_tokens": 39405568}
{"current_steps": 41040, "total_steps": 58920, "loss": 0.0, "lr": 5.105545183491347e-07, "epoch": 3.4826883910386965, "percentage": 69.65, "elapsed_time": "1:04:09", "remaining_time": "0:27:57", "throughput": 10238.45, "total_tokens": 39410368}
{"current_steps": 41045, "total_steps": 58920, "loss": 0.0, "lr": 5.102962257951962e-07, "epoch": 3.483112695179905, "percentage": 69.66, "elapsed_time": "1:04:09", "remaining_time": "0:27:56", "throughput": 10238.7, "total_tokens": 39415232}
{"current_steps": 41050, "total_steps": 58920, "loss": 0.0, "lr": 5.100379762109965e-07, "epoch": 3.4835369993211134, "percentage": 69.67, "elapsed_time": "1:04:10", "remaining_time": "0:27:55", "throughput": 10238.87, "total_tokens": 39419712}
{"current_steps": 41055, "total_steps": 58920, "loss": 0.0, "lr": 5.097797696191947e-07, "epoch": 3.483961303462322, "percentage": 69.68, "elapsed_time": "1:04:10", "remaining_time": "0:27:55", "throughput": 10239.19, "total_tokens": 39424960}
{"current_steps": 41060, "total_steps": 58920, "loss": 0.0283, "lr": 5.095216060424488e-07, "epoch": 3.48438560760353, "percentage": 69.69, "elapsed_time": "1:04:10", "remaining_time": "0:27:54", "throughput": 10239.54, "total_tokens": 39430400}
{"current_steps": 41065, "total_steps": 58920, "loss": 0.0, "lr": 5.092634855034109e-07, "epoch": 3.4848099117447386, "percentage": 69.7, "elapsed_time": "1:04:11", "remaining_time": "0:27:54", "throughput": 10239.74, "total_tokens": 39435008}
{"current_steps": 41070, "total_steps": 58920, "loss": 0.0, "lr": 5.090054080247299e-07, "epoch": 3.485234215885947, "percentage": 69.7, "elapsed_time": "1:04:11", "remaining_time": "0:27:53", "throughput": 10240.09, "total_tokens": 39440384}
{"current_steps": 41075, "total_steps": 58920, "loss": 0.0, "lr": 5.087473736290524e-07, "epoch": 3.4856585200271555, "percentage": 69.71, "elapsed_time": "1:04:11", "remaining_time": "0:27:53", "throughput": 10240.27, "total_tokens": 39444928}
{"current_steps": 41080, "total_steps": 58920, "loss": 0.0, "lr": 5.084893823390184e-07, "epoch": 3.486082824168364, "percentage": 69.72, "elapsed_time": "1:04:12", "remaining_time": "0:27:52", "throughput": 10240.46, "total_tokens": 39449536}
{"current_steps": 41085, "total_steps": 58920, "loss": 0.0, "lr": 5.082314341772673e-07, "epoch": 3.4865071283095723, "percentage": 69.73, "elapsed_time": "1:04:12", "remaining_time": "0:27:52", "throughput": 10240.64, "total_tokens": 39454016}
{"current_steps": 41090, "total_steps": 58920, "loss": 0.1072, "lr": 5.079735291664316e-07, "epoch": 3.4869314324507807, "percentage": 69.74, "elapsed_time": "1:04:13", "remaining_time": "0:27:51", "throughput": 10240.86, "total_tokens": 39458816}
{"current_steps": 41095, "total_steps": 58920, "loss": 0.0, "lr": 5.077156673291426e-07, "epoch": 3.487355736591989, "percentage": 69.75, "elapsed_time": "1:04:13", "remaining_time": "0:27:51", "throughput": 10240.98, "total_tokens": 39463104}
{"current_steps": 41100, "total_steps": 58920, "loss": 0.0003, "lr": 5.074578486880264e-07, "epoch": 3.4877800407331976, "percentage": 69.76, "elapsed_time": "1:04:13", "remaining_time": "0:27:50", "throughput": 10241.14, "total_tokens": 39467520}
{"current_steps": 41105, "total_steps": 58920, "loss": 0.0, "lr": 5.072000732657058e-07, "epoch": 3.488204344874406, "percentage": 69.76, "elapsed_time": "1:04:14", "remaining_time": "0:27:50", "throughput": 10241.41, "total_tokens": 39472576}
{"current_steps": 41110, "total_steps": 58920, "loss": 0.0, "lr": 5.069423410847997e-07, "epoch": 3.4886286490156144, "percentage": 69.77, "elapsed_time": "1:04:14", "remaining_time": "0:27:49", "throughput": 10241.63, "total_tokens": 39477312}
{"current_steps": 41115, "total_steps": 58920, "loss": 0.0, "lr": 5.066846521679223e-07, "epoch": 3.489052953156823, "percentage": 69.78, "elapsed_time": "1:04:14", "remaining_time": "0:27:49", "throughput": 10241.92, "total_tokens": 39482432}
{"current_steps": 41120, "total_steps": 58920, "loss": 0.0, "lr": 5.06427006537686e-07, "epoch": 3.4894772572980313, "percentage": 69.79, "elapsed_time": "1:04:15", "remaining_time": "0:27:48", "throughput": 10242.12, "total_tokens": 39487040}
{"current_steps": 41125, "total_steps": 58920, "loss": 0.0, "lr": 5.061694042166977e-07, "epoch": 3.4899015614392397, "percentage": 69.8, "elapsed_time": "1:04:15", "remaining_time": "0:27:48", "throughput": 10242.3, "total_tokens": 39491584}
{"current_steps": 41130, "total_steps": 58920, "loss": 0.0, "lr": 5.059118452275614e-07, "epoch": 3.490325865580448, "percentage": 69.81, "elapsed_time": "1:04:16", "remaining_time": "0:27:47", "throughput": 10242.53, "total_tokens": 39496384}
{"current_steps": 41135, "total_steps": 58920, "loss": 0.0, "lr": 5.056543295928767e-07, "epoch": 3.4907501697216565, "percentage": 69.82, "elapsed_time": "1:04:16", "remaining_time": "0:27:47", "throughput": 10242.64, "total_tokens": 39500608}
{"current_steps": 41140, "total_steps": 58920, "loss": 0.0, "lr": 5.053968573352396e-07, "epoch": 3.491174473862865, "percentage": 69.82, "elapsed_time": "1:04:16", "remaining_time": "0:27:46", "throughput": 10242.84, "total_tokens": 39505216}
{"current_steps": 41145, "total_steps": 58920, "loss": 0.0, "lr": 5.051394284772427e-07, "epoch": 3.4915987780040734, "percentage": 69.83, "elapsed_time": "1:04:17", "remaining_time": "0:27:46", "throughput": 10243.08, "total_tokens": 39510016}
{"current_steps": 41150, "total_steps": 58920, "loss": 0.0, "lr": 5.048820430414742e-07, "epoch": 3.492023082145282, "percentage": 69.84, "elapsed_time": "1:04:17", "remaining_time": "0:27:45", "throughput": 10243.39, "total_tokens": 39515264}
{"current_steps": 41155, "total_steps": 58920, "loss": 0.0, "lr": 5.046247010505189e-07, "epoch": 3.49244738628649, "percentage": 69.85, "elapsed_time": "1:04:18", "remaining_time": "0:27:45", "throughput": 10243.57, "total_tokens": 39519808}
{"current_steps": 41160, "total_steps": 58920, "loss": 0.0, "lr": 5.043674025269575e-07, "epoch": 3.4928716904276986, "percentage": 69.86, "elapsed_time": "1:04:18", "remaining_time": "0:27:44", "throughput": 10243.79, "total_tokens": 39524608}
{"current_steps": 41165, "total_steps": 58920, "loss": 0.0, "lr": 5.041101474933669e-07, "epoch": 3.493295994568907, "percentage": 69.87, "elapsed_time": "1:04:18", "remaining_time": "0:27:44", "throughput": 10243.94, "total_tokens": 39529024}
{"current_steps": 41170, "total_steps": 58920, "loss": 0.0, "lr": 5.038529359723207e-07, "epoch": 3.4937202987101155, "percentage": 69.87, "elapsed_time": "1:04:19", "remaining_time": "0:27:43", "throughput": 10244.08, "total_tokens": 39533376}
{"current_steps": 41175, "total_steps": 58920, "loss": 0.0001, "lr": 5.035957679863878e-07, "epoch": 3.494144602851324, "percentage": 69.88, "elapsed_time": "1:04:19", "remaining_time": "0:27:43", "throughput": 10244.24, "total_tokens": 39537792}
{"current_steps": 41180, "total_steps": 58920, "loss": 0.0, "lr": 5.033386435581342e-07, "epoch": 3.4945689069925323, "percentage": 69.89, "elapsed_time": "1:04:19", "remaining_time": "0:27:42", "throughput": 10244.5, "total_tokens": 39542720}
{"current_steps": 41185, "total_steps": 58920, "loss": 0.0, "lr": 5.030815627101212e-07, "epoch": 3.4949932111337407, "percentage": 69.9, "elapsed_time": "1:04:20", "remaining_time": "0:27:42", "throughput": 10244.7, "total_tokens": 39547392}
{"current_steps": 41190, "total_steps": 58920, "loss": 0.0, "lr": 5.028245254649072e-07, "epoch": 3.495417515274949, "percentage": 69.91, "elapsed_time": "1:04:20", "remaining_time": "0:27:41", "throughput": 10244.84, "total_tokens": 39551744}
{"current_steps": 41195, "total_steps": 58920, "loss": 0.0, "lr": 5.025675318450459e-07, "epoch": 3.4958418194161576, "percentage": 69.92, "elapsed_time": "1:04:21", "remaining_time": "0:27:41", "throughput": 10245.13, "total_tokens": 39556864}
{"current_steps": 41200, "total_steps": 58920, "loss": 0.0, "lr": 5.023105818730877e-07, "epoch": 3.496266123557366, "percentage": 69.93, "elapsed_time": "1:04:21", "remaining_time": "0:27:40", "throughput": 10245.34, "total_tokens": 39561536}
{"current_steps": 41205, "total_steps": 58920, "loss": 0.0, "lr": 5.020536755715792e-07, "epoch": 3.4966904276985744, "percentage": 69.93, "elapsed_time": "1:04:21", "remaining_time": "0:27:40", "throughput": 10245.54, "total_tokens": 39566144}
{"current_steps": 41210, "total_steps": 58920, "loss": 0.0, "lr": 5.017968129630628e-07, "epoch": 3.497114731839783, "percentage": 69.94, "elapsed_time": "1:04:22", "remaining_time": "0:27:39", "throughput": 10245.75, "total_tokens": 39570880}
{"current_steps": 41215, "total_steps": 58920, "loss": 0.0, "lr": 5.015399940700771e-07, "epoch": 3.4975390359809913, "percentage": 69.95, "elapsed_time": "1:04:22", "remaining_time": "0:27:39", "throughput": 10246.05, "total_tokens": 39576000}
{"current_steps": 41220, "total_steps": 58920, "loss": 0.0, "lr": 5.012832189151575e-07, "epoch": 3.4979633401221997, "percentage": 69.96, "elapsed_time": "1:04:22", "remaining_time": "0:27:38", "throughput": 10246.28, "total_tokens": 39580800}
{"current_steps": 41225, "total_steps": 58920, "loss": 0.0, "lr": 5.010264875208343e-07, "epoch": 3.498387644263408, "percentage": 69.97, "elapsed_time": "1:04:23", "remaining_time": "0:27:38", "throughput": 10246.55, "total_tokens": 39585792}
{"current_steps": 41230, "total_steps": 58920, "loss": 0.0, "lr": 5.007697999096361e-07, "epoch": 3.4988119484046165, "percentage": 69.98, "elapsed_time": "1:04:23", "remaining_time": "0:27:37", "throughput": 10246.74, "total_tokens": 39590464}
{"current_steps": 41235, "total_steps": 58920, "loss": 0.0315, "lr": 5.00513156104085e-07, "epoch": 3.499236252545825, "percentage": 69.98, "elapsed_time": "1:04:24", "remaining_time": "0:27:37", "throughput": 10247.0, "total_tokens": 39595392}
{"current_steps": 41240, "total_steps": 58920, "loss": 0.0, "lr": 5.002565561267012e-07, "epoch": 3.4996605566870334, "percentage": 69.99, "elapsed_time": "1:04:24", "remaining_time": "0:27:36", "throughput": 10247.43, "total_tokens": 39601152}
{"current_steps": 41244, "total_steps": 58920, "eval_loss": 0.15574397146701813, "epoch": 3.5, "percentage": 70.0, "elapsed_time": "1:04:41", "remaining_time": "0:27:43", "throughput": 10204.31, "total_tokens": 39604544}
{"current_steps": 41245, "total_steps": 58920, "loss": 0.0, "lr": 5.000000000000002e-07, "epoch": 3.5000848608282418, "percentage": 70.0, "elapsed_time": "1:05:15", "remaining_time": "0:27:57", "throughput": 10115.52, "total_tokens": 39605312}
{"current_steps": 41250, "total_steps": 58920, "loss": 0.0, "lr": 4.997434877464936e-07, "epoch": 3.50050916496945, "percentage": 70.01, "elapsed_time": "1:05:15", "remaining_time": "0:27:57", "throughput": 10115.69, "total_tokens": 39609792}
{"current_steps": 41255, "total_steps": 58920, "loss": 0.0, "lr": 4.994870193886906e-07, "epoch": 3.5009334691106586, "percentage": 70.02, "elapsed_time": "1:05:16", "remaining_time": "0:27:56", "throughput": 10115.87, "total_tokens": 39614272}
{"current_steps": 41260, "total_steps": 58920, "loss": 0.0, "lr": 4.992305949490937e-07, "epoch": 3.501357773251867, "percentage": 70.03, "elapsed_time": "1:05:16", "remaining_time": "0:27:56", "throughput": 10116.04, "total_tokens": 39618752}
{"current_steps": 41265, "total_steps": 58920, "loss": 0.0, "lr": 4.989742144502049e-07, "epoch": 3.5017820773930755, "percentage": 70.04, "elapsed_time": "1:05:16", "remaining_time": "0:27:55", "throughput": 10116.3, "total_tokens": 39623616}
{"current_steps": 41270, "total_steps": 58920, "loss": 0.0, "lr": 4.987178779145191e-07, "epoch": 3.502206381534284, "percentage": 70.04, "elapsed_time": "1:05:17", "remaining_time": "0:27:55", "throughput": 10116.52, "total_tokens": 39628352}
{"current_steps": 41275, "total_steps": 58920, "loss": 0.0, "lr": 4.984615853645302e-07, "epoch": 3.5026306856754923, "percentage": 70.05, "elapsed_time": "1:05:17", "remaining_time": "0:27:54", "throughput": 10116.7, "total_tokens": 39632896}
{"current_steps": 41280, "total_steps": 58920, "loss": 0.0, "lr": 4.982053368227262e-07, "epoch": 3.5030549898167007, "percentage": 70.06, "elapsed_time": "1:05:17", "remaining_time": "0:27:54", "throughput": 10116.89, "total_tokens": 39637504}
{"current_steps": 41285, "total_steps": 58920, "loss": 0.0, "lr": 4.979491323115917e-07, "epoch": 3.503479293957909, "percentage": 70.07, "elapsed_time": "1:05:18", "remaining_time": "0:27:53", "throughput": 10117.09, "total_tokens": 39642112}
{"current_steps": 41290, "total_steps": 58920, "loss": 0.0, "lr": 4.97692971853609e-07, "epoch": 3.5039035980991176, "percentage": 70.08, "elapsed_time": "1:05:18", "remaining_time": "0:27:53", "throughput": 10117.43, "total_tokens": 39647424}
{"current_steps": 41295, "total_steps": 58920, "loss": 0.0, "lr": 4.974368554712537e-07, "epoch": 3.504327902240326, "percentage": 70.09, "elapsed_time": "1:05:19", "remaining_time": "0:27:52", "throughput": 10117.67, "total_tokens": 39652224}
{"current_steps": 41300, "total_steps": 58920, "loss": 0.0002, "lr": 4.971807831870007e-07, "epoch": 3.5047522063815344, "percentage": 70.1, "elapsed_time": "1:05:19", "remaining_time": "0:27:52", "throughput": 10117.89, "total_tokens": 39656960}
{"current_steps": 41305, "total_steps": 58920, "loss": 0.0, "lr": 4.969247550233176e-07, "epoch": 3.505176510522743, "percentage": 70.1, "elapsed_time": "1:05:19", "remaining_time": "0:27:51", "throughput": 10118.17, "total_tokens": 39661952}
{"current_steps": 41310, "total_steps": 58920, "loss": 0.0, "lr": 4.966687710026714e-07, "epoch": 3.5056008146639512, "percentage": 70.11, "elapsed_time": "1:05:20", "remaining_time": "0:27:51", "throughput": 10118.3, "total_tokens": 39666176}
{"current_steps": 41315, "total_steps": 58920, "loss": 0.0, "lr": 4.964128311475237e-07, "epoch": 3.5060251188051597, "percentage": 70.12, "elapsed_time": "1:05:20", "remaining_time": "0:27:50", "throughput": 10118.75, "total_tokens": 39672064}
{"current_steps": 41320, "total_steps": 58920, "loss": 0.0, "lr": 4.961569354803309e-07, "epoch": 3.506449422946368, "percentage": 70.13, "elapsed_time": "1:05:21", "remaining_time": "0:27:50", "throughput": 10118.92, "total_tokens": 39676544}
{"current_steps": 41325, "total_steps": 58920, "loss": 0.0, "lr": 4.959010840235488e-07, "epoch": 3.5068737270875765, "percentage": 70.14, "elapsed_time": "1:05:21", "remaining_time": "0:27:49", "throughput": 10119.06, "total_tokens": 39680832}
{"current_steps": 41330, "total_steps": 58920, "loss": 0.0, "lr": 4.956452767996258e-07, "epoch": 3.507298031228785, "percentage": 70.15, "elapsed_time": "1:05:21", "remaining_time": "0:27:49", "throughput": 10119.21, "total_tokens": 39685184}
{"current_steps": 41335, "total_steps": 58920, "loss": 0.0, "lr": 4.95389513831009e-07, "epoch": 3.5077223353699933, "percentage": 70.15, "elapsed_time": "1:05:22", "remaining_time": "0:27:48", "throughput": 10119.47, "total_tokens": 39690048}
{"current_steps": 41340, "total_steps": 58920, "loss": 0.0, "lr": 4.951337951401407e-07, "epoch": 3.5081466395112018, "percentage": 70.16, "elapsed_time": "1:05:22", "remaining_time": "0:27:48", "throughput": 10119.68, "total_tokens": 39694720}
{"current_steps": 41345, "total_steps": 58920, "loss": 0.0, "lr": 4.948781207494589e-07, "epoch": 3.50857094365241, "percentage": 70.17, "elapsed_time": "1:05:22", "remaining_time": "0:27:47", "throughput": 10119.96, "total_tokens": 39699712}
{"current_steps": 41350, "total_steps": 58920, "loss": 0.0, "lr": 4.946224906813984e-07, "epoch": 3.5089952477936186, "percentage": 70.18, "elapsed_time": "1:05:23", "remaining_time": "0:27:47", "throughput": 10120.16, "total_tokens": 39704320}
{"current_steps": 41355, "total_steps": 58920, "loss": 0.0, "lr": 4.943669049583896e-07, "epoch": 3.509419551934827, "percentage": 70.19, "elapsed_time": "1:05:23", "remaining_time": "0:27:46", "throughput": 10120.47, "total_tokens": 39709568}
{"current_steps": 41360, "total_steps": 58920, "loss": 0.0, "lr": 4.941113636028597e-07, "epoch": 3.5098438560760354, "percentage": 70.2, "elapsed_time": "1:05:24", "remaining_time": "0:27:46", "throughput": 10120.74, "total_tokens": 39714496}
{"current_steps": 41365, "total_steps": 58920, "loss": 0.0, "lr": 4.938558666372303e-07, "epoch": 3.510268160217244, "percentage": 70.21, "elapsed_time": "1:05:24", "remaining_time": "0:27:45", "throughput": 10120.93, "total_tokens": 39719104}
{"current_steps": 41370, "total_steps": 58920, "loss": 0.0, "lr": 4.936004140839217e-07, "epoch": 3.5106924643584523, "percentage": 70.21, "elapsed_time": "1:05:24", "remaining_time": "0:27:44", "throughput": 10121.13, "total_tokens": 39723712}
{"current_steps": 41375, "total_steps": 58920, "loss": 0.0, "lr": 4.933450059653484e-07, "epoch": 3.5111167684996607, "percentage": 70.22, "elapsed_time": "1:05:25", "remaining_time": "0:27:44", "throughput": 10121.43, "total_tokens": 39728832}
{"current_steps": 41380, "total_steps": 58920, "loss": 0.0, "lr": 4.930896423039215e-07, "epoch": 3.511541072640869, "percentage": 70.23, "elapsed_time": "1:05:25", "remaining_time": "0:27:43", "throughput": 10121.65, "total_tokens": 39733504}
{"current_steps": 41385, "total_steps": 58920, "loss": 0.0, "lr": 4.928343231220483e-07, "epoch": 3.5119653767820775, "percentage": 70.24, "elapsed_time": "1:05:25", "remaining_time": "0:27:43", "throughput": 10121.83, "total_tokens": 39737984}
{"current_steps": 41390, "total_steps": 58920, "loss": 0.0, "lr": 4.925790484421321e-07, "epoch": 3.512389680923286, "percentage": 70.25, "elapsed_time": "1:05:26", "remaining_time": "0:27:42", "throughput": 10122.04, "total_tokens": 39742656}
{"current_steps": 41395, "total_steps": 58920, "loss": 0.0, "lr": 4.923238182865725e-07, "epoch": 3.5128139850644944, "percentage": 70.26, "elapsed_time": "1:05:26", "remaining_time": "0:27:42", "throughput": 10122.37, "total_tokens": 39747904}
{"current_steps": 41400, "total_steps": 58920, "loss": 0.0, "lr": 4.920686326777648e-07, "epoch": 3.513238289205703, "percentage": 70.26, "elapsed_time": "1:05:27", "remaining_time": "0:27:41", "throughput": 10122.56, "total_tokens": 39752448}
{"current_steps": 41405, "total_steps": 58920, "loss": 0.0, "lr": 4.918134916381007e-07, "epoch": 3.5136625933469112, "percentage": 70.27, "elapsed_time": "1:05:27", "remaining_time": "0:27:41", "throughput": 10122.78, "total_tokens": 39757184}
{"current_steps": 41410, "total_steps": 58920, "loss": 0.0, "lr": 4.915583951899679e-07, "epoch": 3.5140868974881196, "percentage": 70.28, "elapsed_time": "1:05:27", "remaining_time": "0:27:40", "throughput": 10123.0, "total_tokens": 39761856}
{"current_steps": 41415, "total_steps": 58920, "loss": 0.0, "lr": 4.913033433557501e-07, "epoch": 3.514511201629328, "percentage": 70.29, "elapsed_time": "1:05:28", "remaining_time": "0:27:40", "throughput": 10123.19, "total_tokens": 39766400}
{"current_steps": 41420, "total_steps": 58920, "loss": 0.0, "lr": 4.910483361578275e-07, "epoch": 3.5149355057705365, "percentage": 70.3, "elapsed_time": "1:05:28", "remaining_time": "0:27:39", "throughput": 10123.47, "total_tokens": 39771328}
{"current_steps": 41425, "total_steps": 58920, "loss": 0.0, "lr": 4.907933736185757e-07, "epoch": 3.515359809911745, "percentage": 70.31, "elapsed_time": "1:05:29", "remaining_time": "0:27:39", "throughput": 10123.82, "total_tokens": 39776704}
{"current_steps": 41430, "total_steps": 58920, "loss": 0.0, "lr": 4.905384557603669e-07, "epoch": 3.515784114052953, "percentage": 70.32, "elapsed_time": "1:05:29", "remaining_time": "0:27:38", "throughput": 10124.2, "total_tokens": 39782272}
{"current_steps": 41435, "total_steps": 58920, "loss": 0.0, "lr": 4.902835826055692e-07, "epoch": 3.5162084181941617, "percentage": 70.32, "elapsed_time": "1:05:29", "remaining_time": "0:27:38", "throughput": 10124.53, "total_tokens": 39787584}
{"current_steps": 41440, "total_steps": 58920, "loss": 0.0, "lr": 4.900287541765464e-07, "epoch": 3.5166327223353697, "percentage": 70.33, "elapsed_time": "1:05:30", "remaining_time": "0:27:37", "throughput": 10124.78, "total_tokens": 39792448}
{"current_steps": 41445, "total_steps": 58920, "loss": 0.0, "lr": 4.8977397049566e-07, "epoch": 3.5170570264765786, "percentage": 70.34, "elapsed_time": "1:05:30", "remaining_time": "0:27:37", "throughput": 10124.94, "total_tokens": 39796864}
{"current_steps": 41450, "total_steps": 58920, "loss": 0.0, "lr": 4.895192315852651e-07, "epoch": 3.5174813306177866, "percentage": 70.35, "elapsed_time": "1:05:30", "remaining_time": "0:27:36", "throughput": 10125.21, "total_tokens": 39801792}
{"current_steps": 41455, "total_steps": 58920, "loss": 0.0264, "lr": 4.892645374677146e-07, "epoch": 3.5179056347589954, "percentage": 70.36, "elapsed_time": "1:05:31", "remaining_time": "0:27:36", "throughput": 10125.36, "total_tokens": 39806144}
{"current_steps": 41460, "total_steps": 58920, "loss": 0.0, "lr": 4.890098881653569e-07, "epoch": 3.5183299389002034, "percentage": 70.37, "elapsed_time": "1:05:31", "remaining_time": "0:27:35", "throughput": 10125.52, "total_tokens": 39810560}
{"current_steps": 41465, "total_steps": 58920, "loss": 0.0, "lr": 4.887552837005362e-07, "epoch": 3.5187542430414123, "percentage": 70.38, "elapsed_time": "1:05:32", "remaining_time": "0:27:35", "throughput": 10125.7, "total_tokens": 39815040}
{"current_steps": 41470, "total_steps": 58920, "loss": 0.0, "lr": 4.885007240955943e-07, "epoch": 3.5191785471826202, "percentage": 70.38, "elapsed_time": "1:05:32", "remaining_time": "0:27:34", "throughput": 10125.91, "total_tokens": 39819648}
{"current_steps": 41475, "total_steps": 58920, "loss": 0.0002, "lr": 4.882462093728663e-07, "epoch": 3.519602851323829, "percentage": 70.39, "elapsed_time": "1:05:32", "remaining_time": "0:27:34", "throughput": 10126.13, "total_tokens": 39824384}
{"current_steps": 41480, "total_steps": 58920, "loss": 0.0, "lr": 4.879917395546865e-07, "epoch": 3.520027155465037, "percentage": 70.4, "elapsed_time": "1:05:33", "remaining_time": "0:27:33", "throughput": 10126.37, "total_tokens": 39829184}
{"current_steps": 41485, "total_steps": 58920, "loss": 0.0, "lr": 4.877373146633826e-07, "epoch": 3.520451459606246, "percentage": 70.41, "elapsed_time": "1:05:33", "remaining_time": "0:27:33", "throughput": 10126.57, "total_tokens": 39833728}
{"current_steps": 41490, "total_steps": 58920, "loss": 0.0, "lr": 4.874829347212799e-07, "epoch": 3.520875763747454, "percentage": 70.42, "elapsed_time": "1:05:33", "remaining_time": "0:27:32", "throughput": 10126.8, "total_tokens": 39838528}
{"current_steps": 41495, "total_steps": 58920, "loss": 0.0, "lr": 4.872285997506991e-07, "epoch": 3.521300067888663, "percentage": 70.43, "elapsed_time": "1:05:34", "remaining_time": "0:27:32", "throughput": 10127.07, "total_tokens": 39843520}
{"current_steps": 41500, "total_steps": 58920, "loss": 0.0, "lr": 4.86974309773957e-07, "epoch": 3.5217243720298708, "percentage": 70.43, "elapsed_time": "1:05:34", "remaining_time": "0:27:31", "throughput": 10127.53, "total_tokens": 39849472}
{"current_steps": 41505, "total_steps": 58920, "loss": 0.0, "lr": 4.867200648133677e-07, "epoch": 3.5221486761710796, "percentage": 70.44, "elapsed_time": "1:05:35", "remaining_time": "0:27:31", "throughput": 10127.82, "total_tokens": 39854528}
{"current_steps": 41510, "total_steps": 58920, "loss": 0.0, "lr": 4.864658648912387e-07, "epoch": 3.5225729803122876, "percentage": 70.45, "elapsed_time": "1:05:35", "remaining_time": "0:27:30", "throughput": 10128.02, "total_tokens": 39859072}
{"current_steps": 41515, "total_steps": 58920, "loss": 0.0, "lr": 4.862117100298769e-07, "epoch": 3.5229972844534965, "percentage": 70.46, "elapsed_time": "1:05:35", "remaining_time": "0:27:30", "throughput": 10128.24, "total_tokens": 39863744}
{"current_steps": 41520, "total_steps": 58920, "loss": 0.0, "lr": 4.859576002515816e-07, "epoch": 3.5234215885947044, "percentage": 70.47, "elapsed_time": "1:05:36", "remaining_time": "0:27:29", "throughput": 10128.46, "total_tokens": 39868480}
{"current_steps": 41525, "total_steps": 58920, "loss": 0.0, "lr": 4.857035355786514e-07, "epoch": 3.5238458927359133, "percentage": 70.48, "elapsed_time": "1:05:36", "remaining_time": "0:27:29", "throughput": 10128.65, "total_tokens": 39873024}
{"current_steps": 41530, "total_steps": 58920, "loss": 0.0, "lr": 4.854495160333793e-07, "epoch": 3.5242701968771213, "percentage": 70.49, "elapsed_time": "1:05:37", "remaining_time": "0:27:28", "throughput": 10128.88, "total_tokens": 39877824}
{"current_steps": 41535, "total_steps": 58920, "loss": 0.0, "lr": 4.851955416380539e-07, "epoch": 3.52469450101833, "percentage": 70.49, "elapsed_time": "1:05:37", "remaining_time": "0:27:28", "throughput": 10129.04, "total_tokens": 39882240}
{"current_steps": 41540, "total_steps": 58920, "loss": 0.0, "lr": 4.849416124149615e-07, "epoch": 3.525118805159538, "percentage": 70.5, "elapsed_time": "1:05:37", "remaining_time": "0:27:27", "throughput": 10129.28, "total_tokens": 39886976}
{"current_steps": 41545, "total_steps": 58920, "loss": 0.0, "lr": 4.846877283863825e-07, "epoch": 3.525543109300747, "percentage": 70.51, "elapsed_time": "1:05:38", "remaining_time": "0:27:27", "throughput": 10129.42, "total_tokens": 39891328}
{"current_steps": 41550, "total_steps": 58920, "loss": 0.0, "lr": 4.84433889574595e-07, "epoch": 3.525967413441955, "percentage": 70.52, "elapsed_time": "1:05:38", "remaining_time": "0:27:26", "throughput": 10129.58, "total_tokens": 39895808}
{"current_steps": 41555, "total_steps": 58920, "loss": 0.0, "lr": 4.841800960018723e-07, "epoch": 3.526391717583164, "percentage": 70.53, "elapsed_time": "1:05:38", "remaining_time": "0:27:25", "throughput": 10129.8, "total_tokens": 39900544}
{"current_steps": 41560, "total_steps": 58920, "loss": 0.0324, "lr": 4.839263476904839e-07, "epoch": 3.526816021724372, "percentage": 70.54, "elapsed_time": "1:05:39", "remaining_time": "0:27:25", "throughput": 10129.92, "total_tokens": 39904768}
{"current_steps": 41565, "total_steps": 58920, "loss": 0.0, "lr": 4.836726446626952e-07, "epoch": 3.5272403258655807, "percentage": 70.54, "elapsed_time": "1:05:39", "remaining_time": "0:27:24", "throughput": 10130.14, "total_tokens": 39909504}
{"current_steps": 41570, "total_steps": 58920, "loss": 0.0, "lr": 4.834189869407677e-07, "epoch": 3.5276646300067886, "percentage": 70.55, "elapsed_time": "1:05:40", "remaining_time": "0:27:24", "throughput": 10130.33, "total_tokens": 39914176}
{"current_steps": 41575, "total_steps": 58920, "loss": 0.0098, "lr": 4.831653745469593e-07, "epoch": 3.5280889341479975, "percentage": 70.56, "elapsed_time": "1:05:40", "remaining_time": "0:27:23", "throughput": 10130.46, "total_tokens": 39918464}
{"current_steps": 41580, "total_steps": 58920, "loss": 0.0, "lr": 4.829118075035226e-07, "epoch": 3.5285132382892055, "percentage": 70.57, "elapsed_time": "1:05:40", "remaining_time": "0:27:23", "throughput": 10130.67, "total_tokens": 39923200}
{"current_steps": 41585, "total_steps": 58920, "loss": 0.0, "lr": 4.826582858327082e-07, "epoch": 3.5289375424304144, "percentage": 70.58, "elapsed_time": "1:05:41", "remaining_time": "0:27:22", "throughput": 10130.79, "total_tokens": 39927488}
{"current_steps": 41590, "total_steps": 58920, "loss": 0.0, "lr": 4.824048095567613e-07, "epoch": 3.5293618465716223, "percentage": 70.59, "elapsed_time": "1:05:41", "remaining_time": "0:27:22", "throughput": 10130.94, "total_tokens": 39931840}
{"current_steps": 41595, "total_steps": 58920, "loss": 0.0, "lr": 4.821513786979236e-07, "epoch": 3.529786150712831, "percentage": 70.6, "elapsed_time": "1:05:41", "remaining_time": "0:27:21", "throughput": 10131.07, "total_tokens": 39936192}
{"current_steps": 41600, "total_steps": 58920, "loss": 0.0, "lr": 4.818979932784329e-07, "epoch": 3.530210454854039, "percentage": 70.6, "elapsed_time": "1:05:42", "remaining_time": "0:27:21", "throughput": 10131.23, "total_tokens": 39940672}
{"current_steps": 41605, "total_steps": 58920, "loss": 0.0, "lr": 4.816446533205225e-07, "epoch": 3.530634758995248, "percentage": 70.61, "elapsed_time": "1:05:42", "remaining_time": "0:27:20", "throughput": 10131.35, "total_tokens": 39945024}
{"current_steps": 41610, "total_steps": 58920, "loss": 0.0, "lr": 4.813913588464224e-07, "epoch": 3.531059063136456, "percentage": 70.62, "elapsed_time": "1:05:43", "remaining_time": "0:27:20", "throughput": 10131.53, "total_tokens": 39949632}
{"current_steps": 41615, "total_steps": 58920, "loss": 0.0, "lr": 4.81138109878358e-07, "epoch": 3.531483367277665, "percentage": 70.63, "elapsed_time": "1:05:43", "remaining_time": "0:27:19", "throughput": 10131.76, "total_tokens": 39954496}
{"current_steps": 41620, "total_steps": 58920, "loss": 0.0, "lr": 4.808849064385512e-07, "epoch": 3.531907671418873, "percentage": 70.64, "elapsed_time": "1:05:43", "remaining_time": "0:27:19", "throughput": 10131.94, "total_tokens": 39959104}
{"current_steps": 41625, "total_steps": 58920, "loss": 0.0, "lr": 4.806317485492195e-07, "epoch": 3.5323319755600817, "percentage": 70.65, "elapsed_time": "1:05:44", "remaining_time": "0:27:18", "throughput": 10132.12, "total_tokens": 39963712}
{"current_steps": 41630, "total_steps": 58920, "loss": 0.0, "lr": 4.803786362325768e-07, "epoch": 3.5327562797012897, "percentage": 70.66, "elapsed_time": "1:05:44", "remaining_time": "0:27:18", "throughput": 10132.31, "total_tokens": 39968384}
{"current_steps": 41635, "total_steps": 58920, "loss": 0.0, "lr": 4.801255695108326e-07, "epoch": 3.5331805838424986, "percentage": 70.66, "elapsed_time": "1:05:45", "remaining_time": "0:27:17", "throughput": 10132.65, "total_tokens": 39973760}
{"current_steps": 41640, "total_steps": 58920, "loss": 0.0, "lr": 4.798725484061927e-07, "epoch": 3.5336048879837065, "percentage": 70.67, "elapsed_time": "1:05:45", "remaining_time": "0:27:17", "throughput": 10133.0, "total_tokens": 39979136}
{"current_steps": 41645, "total_steps": 58920, "loss": 0.0, "lr": 4.796195729408589e-07, "epoch": 3.5340291921249154, "percentage": 70.68, "elapsed_time": "1:05:45", "remaining_time": "0:27:16", "throughput": 10133.29, "total_tokens": 39984320}
{"current_steps": 41650, "total_steps": 58920, "loss": 0.0053, "lr": 4.793666431370286e-07, "epoch": 3.5344534962661234, "percentage": 70.69, "elapsed_time": "1:05:46", "remaining_time": "0:27:16", "throughput": 10133.5, "total_tokens": 39988992}
{"current_steps": 41655, "total_steps": 58920, "loss": 0.0, "lr": 4.791137590168957e-07, "epoch": 3.5348778004073322, "percentage": 70.7, "elapsed_time": "1:05:46", "remaining_time": "0:27:15", "throughput": 10133.68, "total_tokens": 39993600}
{"current_steps": 41660, "total_steps": 58920, "loss": 0.0, "lr": 4.788609206026497e-07, "epoch": 3.53530210454854, "percentage": 70.71, "elapsed_time": "1:05:46", "remaining_time": "0:27:15", "throughput": 10133.95, "total_tokens": 39998592}
{"current_steps": 41665, "total_steps": 58920, "loss": 0.0, "lr": 4.786081279164764e-07, "epoch": 3.535726408689749, "percentage": 70.71, "elapsed_time": "1:05:47", "remaining_time": "0:27:14", "throughput": 10134.11, "total_tokens": 40003008}
{"current_steps": 41670, "total_steps": 58920, "loss": 0.0, "lr": 4.783553809805574e-07, "epoch": 3.536150712830957, "percentage": 70.72, "elapsed_time": "1:05:47", "remaining_time": "0:27:14", "throughput": 10134.25, "total_tokens": 40007360}
{"current_steps": 41675, "total_steps": 58920, "loss": 0.0, "lr": 4.781026798170703e-07, "epoch": 3.536575016972166, "percentage": 70.73, "elapsed_time": "1:05:48", "remaining_time": "0:27:13", "throughput": 10134.47, "total_tokens": 40012160}
{"current_steps": 41680, "total_steps": 58920, "loss": 0.0, "lr": 4.778500244481884e-07, "epoch": 3.536999321113374, "percentage": 70.74, "elapsed_time": "1:05:48", "remaining_time": "0:27:13", "throughput": 10134.71, "total_tokens": 40017024}
{"current_steps": 41685, "total_steps": 58920, "loss": 0.0, "lr": 4.775974148960824e-07, "epoch": 3.5374236252545828, "percentage": 70.75, "elapsed_time": "1:05:48", "remaining_time": "0:27:12", "throughput": 10134.9, "total_tokens": 40021632}
{"current_steps": 41690, "total_steps": 58920, "loss": 0.0, "lr": 4.773448511829164e-07, "epoch": 3.5378479293957907, "percentage": 70.76, "elapsed_time": "1:05:49", "remaining_time": "0:27:12", "throughput": 10135.22, "total_tokens": 40026816}
{"current_steps": 41695, "total_steps": 58920, "loss": 0.0, "lr": 4.770923333308534e-07, "epoch": 3.538272233536999, "percentage": 70.77, "elapsed_time": "1:05:49", "remaining_time": "0:27:11", "throughput": 10135.47, "total_tokens": 40031744}
{"current_steps": 41700, "total_steps": 58920, "loss": 0.0, "lr": 4.768398613620498e-07, "epoch": 3.5386965376782076, "percentage": 70.77, "elapsed_time": "1:05:50", "remaining_time": "0:27:11", "throughput": 10135.86, "total_tokens": 40037376}
{"current_steps": 41705, "total_steps": 58920, "loss": 0.0, "lr": 4.7658743529865955e-07, "epoch": 3.539120841819416, "percentage": 70.78, "elapsed_time": "1:05:50", "remaining_time": "0:27:10", "throughput": 10136.09, "total_tokens": 40042176}
{"current_steps": 41710, "total_steps": 58920, "loss": 0.0, "lr": 4.76335055162832e-07, "epoch": 3.5395451459606244, "percentage": 70.79, "elapsed_time": "1:05:50", "remaining_time": "0:27:10", "throughput": 10136.31, "total_tokens": 40046976}
{"current_steps": 41715, "total_steps": 58920, "loss": 0.0, "lr": 4.760827209767123e-07, "epoch": 3.539969450101833, "percentage": 70.8, "elapsed_time": "1:05:51", "remaining_time": "0:27:09", "throughput": 10136.57, "total_tokens": 40051968}
{"current_steps": 41720, "total_steps": 58920, "loss": 0.0, "lr": 4.758304327624431e-07, "epoch": 3.5403937542430413, "percentage": 70.81, "elapsed_time": "1:05:51", "remaining_time": "0:27:09", "throughput": 10136.9, "total_tokens": 40057280}
{"current_steps": 41725, "total_steps": 58920, "loss": 0.0001, "lr": 4.7557819054216e-07, "epoch": 3.5408180583842497, "percentage": 70.82, "elapsed_time": "1:05:52", "remaining_time": "0:27:08", "throughput": 10137.09, "total_tokens": 40061888}
{"current_steps": 41730, "total_steps": 58920, "loss": 0.0, "lr": 4.7532599433799816e-07, "epoch": 3.541242362525458, "percentage": 70.82, "elapsed_time": "1:05:52", "remaining_time": "0:27:08", "throughput": 10137.24, "total_tokens": 40066304}
{"current_steps": 41735, "total_steps": 58920, "loss": 0.0001, "lr": 4.750738441720855e-07, "epoch": 3.5416666666666665, "percentage": 70.83, "elapsed_time": "1:05:52", "remaining_time": "0:27:07", "throughput": 10137.48, "total_tokens": 40071168}
{"current_steps": 41740, "total_steps": 58920, "loss": 0.0, "lr": 4.7482174006654754e-07, "epoch": 3.542090970807875, "percentage": 70.84, "elapsed_time": "1:05:53", "remaining_time": "0:27:07", "throughput": 10137.75, "total_tokens": 40076224}
{"current_steps": 41745, "total_steps": 58920, "loss": 0.0865, "lr": 4.745696820435063e-07, "epoch": 3.5425152749490834, "percentage": 70.85, "elapsed_time": "1:05:53", "remaining_time": "0:27:06", "throughput": 10137.91, "total_tokens": 40080704}
{"current_steps": 41750, "total_steps": 58920, "loss": 0.0, "lr": 4.7431767012507785e-07, "epoch": 3.542939579090292, "percentage": 70.86, "elapsed_time": "1:05:53", "remaining_time": "0:27:06", "throughput": 10138.04, "total_tokens": 40085056}
{"current_steps": 41755, "total_steps": 58920, "loss": 0.0, "lr": 4.7406570433337643e-07, "epoch": 3.5433638832315, "percentage": 70.87, "elapsed_time": "1:05:54", "remaining_time": "0:27:05", "throughput": 10138.17, "total_tokens": 40089472}
{"current_steps": 41760, "total_steps": 58920, "loss": 0.0, "lr": 4.7381378469051004e-07, "epoch": 3.5437881873727086, "percentage": 70.88, "elapsed_time": "1:05:54", "remaining_time": "0:27:05", "throughput": 10138.35, "total_tokens": 40094080}
{"current_steps": 41765, "total_steps": 58920, "loss": 0.0, "lr": 4.735619112185845e-07, "epoch": 3.544212491513917, "percentage": 70.88, "elapsed_time": "1:05:55", "remaining_time": "0:27:04", "throughput": 10138.49, "total_tokens": 40098496}
{"current_steps": 41770, "total_steps": 58920, "loss": 0.0, "lr": 4.733100839397006e-07, "epoch": 3.5446367956551255, "percentage": 70.89, "elapsed_time": "1:05:55", "remaining_time": "0:27:04", "throughput": 10138.68, "total_tokens": 40103168}
{"current_steps": 41775, "total_steps": 58920, "loss": 0.0, "lr": 4.7305830287595516e-07, "epoch": 3.545061099796334, "percentage": 70.9, "elapsed_time": "1:05:55", "remaining_time": "0:27:03", "throughput": 10138.84, "total_tokens": 40107648}
{"current_steps": 41780, "total_steps": 58920, "loss": 0.0, "lr": 4.728065680494415e-07, "epoch": 3.5454854039375423, "percentage": 70.91, "elapsed_time": "1:05:56", "remaining_time": "0:27:03", "throughput": 10139.03, "total_tokens": 40112320}
{"current_steps": 41785, "total_steps": 58920, "loss": 0.0, "lr": 4.7255487948224746e-07, "epoch": 3.5459097080787507, "percentage": 70.92, "elapsed_time": "1:05:56", "remaining_time": "0:27:02", "throughput": 10139.18, "total_tokens": 40116864}
{"current_steps": 41790, "total_steps": 58920, "loss": 0.0, "lr": 4.72303237196459e-07, "epoch": 3.546334012219959, "percentage": 70.93, "elapsed_time": "1:05:57", "remaining_time": "0:27:02", "throughput": 10139.38, "total_tokens": 40121600}
{"current_steps": 41795, "total_steps": 58920, "loss": 0.0, "lr": 4.720516412141556e-07, "epoch": 3.5467583163611676, "percentage": 70.94, "elapsed_time": "1:05:57", "remaining_time": "0:27:01", "throughput": 10139.65, "total_tokens": 40126656}
{"current_steps": 41800, "total_steps": 58920, "loss": 0.0, "lr": 4.7180009155741485e-07, "epoch": 3.547182620502376, "percentage": 70.94, "elapsed_time": "1:05:57", "remaining_time": "0:27:00", "throughput": 10139.76, "total_tokens": 40130944}
{"current_steps": 41805, "total_steps": 58920, "loss": 0.0, "lr": 4.71548588248309e-07, "epoch": 3.5476069246435844, "percentage": 70.95, "elapsed_time": "1:05:58", "remaining_time": "0:27:00", "throughput": 10140.09, "total_tokens": 40136384}
{"current_steps": 41810, "total_steps": 58920, "loss": 0.0, "lr": 4.712971313089066e-07, "epoch": 3.548031228784793, "percentage": 70.96, "elapsed_time": "1:05:58", "remaining_time": "0:26:59", "throughput": 10140.45, "total_tokens": 40141888}
{"current_steps": 41815, "total_steps": 58920, "loss": 0.0, "lr": 4.7104572076127204e-07, "epoch": 3.5484555329260012, "percentage": 70.97, "elapsed_time": "1:05:58", "remaining_time": "0:26:59", "throughput": 10140.62, "total_tokens": 40146496}
{"current_steps": 41820, "total_steps": 58920, "loss": 0.0, "lr": 4.7079435662746567e-07, "epoch": 3.5488798370672097, "percentage": 70.98, "elapsed_time": "1:05:59", "remaining_time": "0:26:58", "throughput": 10140.8, "total_tokens": 40151104}
{"current_steps": 41825, "total_steps": 58920, "loss": 0.0303, "lr": 4.7054303892954395e-07, "epoch": 3.549304141208418, "percentage": 70.99, "elapsed_time": "1:05:59", "remaining_time": "0:26:58", "throughput": 10141.11, "total_tokens": 40156352}
{"current_steps": 41830, "total_steps": 58920, "loss": 0.0, "lr": 4.702917676895588e-07, "epoch": 3.5497284453496265, "percentage": 70.99, "elapsed_time": "1:06:00", "remaining_time": "0:26:57", "throughput": 10141.19, "total_tokens": 40160512}
{"current_steps": 41835, "total_steps": 58920, "loss": 0.0, "lr": 4.700405429295586e-07, "epoch": 3.550152749490835, "percentage": 71.0, "elapsed_time": "1:06:00", "remaining_time": "0:26:57", "throughput": 10141.44, "total_tokens": 40165440}
{"current_steps": 41840, "total_steps": 58920, "loss": 0.0, "lr": 4.697893646715874e-07, "epoch": 3.5505770536320433, "percentage": 71.01, "elapsed_time": "1:06:00", "remaining_time": "0:26:56", "throughput": 10141.75, "total_tokens": 40170688}
{"current_steps": 41845, "total_steps": 58920, "loss": 0.0, "lr": 4.69538232937685e-07, "epoch": 3.5510013577732518, "percentage": 71.02, "elapsed_time": "1:06:01", "remaining_time": "0:26:56", "throughput": 10141.82, "total_tokens": 40174720}
{"current_steps": 41850, "total_steps": 58920, "loss": 0.0, "lr": 4.6928714774988755e-07, "epoch": 3.55142566191446, "percentage": 71.03, "elapsed_time": "1:06:01", "remaining_time": "0:26:55", "throughput": 10142.04, "total_tokens": 40179520}
{"current_steps": 41855, "total_steps": 58920, "loss": 0.0, "lr": 4.6903610913022675e-07, "epoch": 3.5518499660556686, "percentage": 71.04, "elapsed_time": "1:06:02", "remaining_time": "0:26:55", "throughput": 10142.18, "total_tokens": 40183872}
{"current_steps": 41860, "total_steps": 58920, "loss": 0.0, "lr": 4.687851171007303e-07, "epoch": 3.552274270196877, "percentage": 71.05, "elapsed_time": "1:06:02", "remaining_time": "0:26:54", "throughput": 10142.37, "total_tokens": 40188480}
{"current_steps": 41865, "total_steps": 58920, "loss": 0.0, "lr": 4.6853417168342193e-07, "epoch": 3.5526985743380854, "percentage": 71.05, "elapsed_time": "1:06:02", "remaining_time": "0:26:54", "throughput": 10142.91, "total_tokens": 40194944}
{"current_steps": 41870, "total_steps": 58920, "loss": 0.0, "lr": 4.68283272900321e-07, "epoch": 3.553122878479294, "percentage": 71.06, "elapsed_time": "1:06:03", "remaining_time": "0:26:53", "throughput": 10143.21, "total_tokens": 40200064}
{"current_steps": 41875, "total_steps": 58920, "loss": 0.0, "lr": 4.680324207734433e-07, "epoch": 3.5535471826205023, "percentage": 71.07, "elapsed_time": "1:06:03", "remaining_time": "0:26:53", "throughput": 10143.46, "total_tokens": 40204928}
{"current_steps": 41880, "total_steps": 58920, "loss": 0.0, "lr": 4.6778161532479987e-07, "epoch": 3.5539714867617107, "percentage": 71.08, "elapsed_time": "1:06:04", "remaining_time": "0:26:52", "throughput": 10143.68, "total_tokens": 40209664}
{"current_steps": 41885, "total_steps": 58920, "loss": 0.0, "lr": 4.6753085657639823e-07, "epoch": 3.554395790902919, "percentage": 71.09, "elapsed_time": "1:06:04", "remaining_time": "0:26:52", "throughput": 10143.87, "total_tokens": 40214272}
{"current_steps": 41890, "total_steps": 58920, "loss": 0.0, "lr": 4.672801445502413e-07, "epoch": 3.5548200950441275, "percentage": 71.1, "elapsed_time": "1:06:04", "remaining_time": "0:26:51", "throughput": 10144.07, "total_tokens": 40218880}
{"current_steps": 41895, "total_steps": 58920, "loss": 0.0, "lr": 4.6702947926832816e-07, "epoch": 3.555244399185336, "percentage": 71.1, "elapsed_time": "1:06:05", "remaining_time": "0:26:51", "throughput": 10144.35, "total_tokens": 40223936}
{"current_steps": 41900, "total_steps": 58920, "loss": 0.0, "lr": 4.6677886075265447e-07, "epoch": 3.5556687033265444, "percentage": 71.11, "elapsed_time": "1:06:05", "remaining_time": "0:26:50", "throughput": 10144.59, "total_tokens": 40228800}
{"current_steps": 41905, "total_steps": 58920, "loss": 0.0001, "lr": 4.6652828902521037e-07, "epoch": 3.556093007467753, "percentage": 71.12, "elapsed_time": "1:06:05", "remaining_time": "0:26:50", "throughput": 10144.82, "total_tokens": 40233600}
{"current_steps": 41910, "total_steps": 58920, "loss": 0.0, "lr": 4.662777641079827e-07, "epoch": 3.5565173116089612, "percentage": 71.13, "elapsed_time": "1:06:06", "remaining_time": "0:26:49", "throughput": 10145.04, "total_tokens": 40238336}
{"current_steps": 41915, "total_steps": 58920, "loss": 0.0, "lr": 4.660272860229543e-07, "epoch": 3.5569416157501696, "percentage": 71.14, "elapsed_time": "1:06:06", "remaining_time": "0:26:49", "throughput": 10145.22, "total_tokens": 40242880}
{"current_steps": 41920, "total_steps": 58920, "loss": 0.0, "lr": 4.657768547921036e-07, "epoch": 3.557365919891378, "percentage": 71.15, "elapsed_time": "1:06:07", "remaining_time": "0:26:48", "throughput": 10145.32, "total_tokens": 40246976}
{"current_steps": 41925, "total_steps": 58920, "loss": 0.0, "lr": 4.6552647043740513e-07, "epoch": 3.5577902240325865, "percentage": 71.16, "elapsed_time": "1:06:07", "remaining_time": "0:26:48", "throughput": 10145.56, "total_tokens": 40251840}
{"current_steps": 41930, "total_steps": 58920, "loss": 0.0, "lr": 4.652761329808287e-07, "epoch": 3.558214528173795, "percentage": 71.16, "elapsed_time": "1:06:07", "remaining_time": "0:26:47", "throughput": 10145.72, "total_tokens": 40256256}
{"current_steps": 41935, "total_steps": 58920, "loss": 0.0, "lr": 4.650258424443418e-07, "epoch": 3.5586388323150033, "percentage": 71.17, "elapsed_time": "1:06:08", "remaining_time": "0:26:47", "throughput": 10146.19, "total_tokens": 40262272}
{"current_steps": 41940, "total_steps": 58920, "loss": 0.0, "lr": 4.64775598849905e-07, "epoch": 3.5590631364562118, "percentage": 71.18, "elapsed_time": "1:06:08", "remaining_time": "0:26:46", "throughput": 10146.31, "total_tokens": 40266560}
{"current_steps": 41945, "total_steps": 58920, "loss": 0.0, "lr": 4.6452540221947766e-07, "epoch": 3.55948744059742, "percentage": 71.19, "elapsed_time": "1:06:08", "remaining_time": "0:26:46", "throughput": 10146.52, "total_tokens": 40271232}
{"current_steps": 41950, "total_steps": 58920, "loss": 0.0, "lr": 4.6427525257501266e-07, "epoch": 3.5599117447386286, "percentage": 71.2, "elapsed_time": "1:06:09", "remaining_time": "0:26:45", "throughput": 10146.75, "total_tokens": 40276032}
{"current_steps": 41955, "total_steps": 58920, "loss": 0.0, "lr": 4.6402514993845955e-07, "epoch": 3.560336048879837, "percentage": 71.21, "elapsed_time": "1:06:09", "remaining_time": "0:26:45", "throughput": 10147.04, "total_tokens": 40281152}
{"current_steps": 41960, "total_steps": 58920, "loss": 0.0, "lr": 4.637750943317652e-07, "epoch": 3.5607603530210454, "percentage": 71.22, "elapsed_time": "1:06:10", "remaining_time": "0:26:44", "throughput": 10147.27, "total_tokens": 40285952}
{"current_steps": 41965, "total_steps": 58920, "loss": 0.0, "lr": 4.6352508577686954e-07, "epoch": 3.561184657162254, "percentage": 71.22, "elapsed_time": "1:06:10", "remaining_time": "0:26:44", "throughput": 10147.38, "total_tokens": 40290176}
{"current_steps": 41970, "total_steps": 58920, "loss": 0.0, "lr": 4.632751242957115e-07, "epoch": 3.5616089613034623, "percentage": 71.23, "elapsed_time": "1:06:10", "remaining_time": "0:26:43", "throughput": 10147.65, "total_tokens": 40295168}
{"current_steps": 41975, "total_steps": 58920, "loss": 0.0548, "lr": 4.6302520991022253e-07, "epoch": 3.5620332654446707, "percentage": 71.24, "elapsed_time": "1:06:11", "remaining_time": "0:26:43", "throughput": 10147.94, "total_tokens": 40300288}
{"current_steps": 41980, "total_steps": 58920, "loss": 0.0, "lr": 4.627753426423332e-07, "epoch": 3.562457569585879, "percentage": 71.25, "elapsed_time": "1:06:11", "remaining_time": "0:26:42", "throughput": 10148.41, "total_tokens": 40306368}
{"current_steps": 41985, "total_steps": 58920, "loss": 0.0, "lr": 4.6252552251396817e-07, "epoch": 3.5628818737270875, "percentage": 71.26, "elapsed_time": "1:06:12", "remaining_time": "0:26:42", "throughput": 10148.63, "total_tokens": 40311104}
{"current_steps": 41990, "total_steps": 58920, "loss": 0.0, "lr": 4.622757495470473e-07, "epoch": 3.563306177868296, "percentage": 71.27, "elapsed_time": "1:06:12", "remaining_time": "0:26:41", "throughput": 10148.99, "total_tokens": 40316608}
{"current_steps": 41995, "total_steps": 58920, "loss": 0.0306, "lr": 4.6202602376348865e-07, "epoch": 3.5637304820095044, "percentage": 71.27, "elapsed_time": "1:06:12", "remaining_time": "0:26:41", "throughput": 10149.15, "total_tokens": 40321088}
{"current_steps": 42000, "total_steps": 58920, "loss": 0.0, "lr": 4.6177634518520336e-07, "epoch": 3.564154786150713, "percentage": 71.28, "elapsed_time": "1:06:13", "remaining_time": "0:26:40", "throughput": 10149.52, "total_tokens": 40326656}
{"current_steps": 42005, "total_steps": 58920, "loss": 0.0, "lr": 4.6152671383410137e-07, "epoch": 3.564579090291921, "percentage": 71.29, "elapsed_time": "1:06:13", "remaining_time": "0:26:40", "throughput": 10149.92, "total_tokens": 40332288}
{"current_steps": 42010, "total_steps": 58920, "loss": 0.0, "lr": 4.612771297320852e-07, "epoch": 3.5650033944331296, "percentage": 71.3, "elapsed_time": "1:06:14", "remaining_time": "0:26:39", "throughput": 10150.14, "total_tokens": 40337024}
{"current_steps": 42015, "total_steps": 58920, "loss": 0.0, "lr": 4.6102759290105633e-07, "epoch": 3.565427698574338, "percentage": 71.31, "elapsed_time": "1:06:14", "remaining_time": "0:26:39", "throughput": 10150.42, "total_tokens": 40342080}
{"current_steps": 42020, "total_steps": 58920, "loss": 0.0, "lr": 4.6077810336291013e-07, "epoch": 3.5658520027155465, "percentage": 71.32, "elapsed_time": "1:06:14", "remaining_time": "0:26:38", "throughput": 10150.52, "total_tokens": 40346240}
{"current_steps": 42025, "total_steps": 58920, "loss": 0.0001, "lr": 4.605286611395386e-07, "epoch": 3.566276306856755, "percentage": 71.33, "elapsed_time": "1:06:15", "remaining_time": "0:26:38", "throughput": 10150.68, "total_tokens": 40350656}
{"current_steps": 42030, "total_steps": 58920, "loss": 0.0, "lr": 4.602792662528296e-07, "epoch": 3.5667006109979633, "percentage": 71.33, "elapsed_time": "1:06:15", "remaining_time": "0:26:37", "throughput": 10150.92, "total_tokens": 40355584}
{"current_steps": 42035, "total_steps": 58920, "loss": 0.0, "lr": 4.600299187246657e-07, "epoch": 3.5671249151391717, "percentage": 71.34, "elapsed_time": "1:06:15", "remaining_time": "0:26:37", "throughput": 10151.01, "total_tokens": 40359680}
{"current_steps": 42040, "total_steps": 58920, "loss": 0.0, "lr": 4.597806185769271e-07, "epoch": 3.56754921928038, "percentage": 71.35, "elapsed_time": "1:06:16", "remaining_time": "0:26:36", "throughput": 10151.22, "total_tokens": 40364416}
{"current_steps": 42045, "total_steps": 58920, "loss": 0.0, "lr": 4.595313658314889e-07, "epoch": 3.5679735234215886, "percentage": 71.36, "elapsed_time": "1:06:16", "remaining_time": "0:26:36", "throughput": 10151.51, "total_tokens": 40369536}
{"current_steps": 42050, "total_steps": 58920, "loss": 0.0, "lr": 4.5928216051022186e-07, "epoch": 3.568397827562797, "percentage": 71.37, "elapsed_time": "1:06:17", "remaining_time": "0:26:35", "throughput": 10151.87, "total_tokens": 40374976}
{"current_steps": 42055, "total_steps": 58920, "loss": 0.0, "lr": 4.590330026349931e-07, "epoch": 3.5688221317040054, "percentage": 71.38, "elapsed_time": "1:06:17", "remaining_time": "0:26:35", "throughput": 10152.12, "total_tokens": 40379904}
{"current_steps": 42060, "total_steps": 58920, "loss": 0.0, "lr": 4.587838922276651e-07, "epoch": 3.569246435845214, "percentage": 71.38, "elapsed_time": "1:06:17", "remaining_time": "0:26:34", "throughput": 10152.31, "total_tokens": 40384512}
{"current_steps": 42065, "total_steps": 58920, "loss": 0.0, "lr": 4.5853482931009655e-07, "epoch": 3.5696707399864223, "percentage": 71.39, "elapsed_time": "1:06:18", "remaining_time": "0:26:34", "throughput": 10152.51, "total_tokens": 40389120}
{"current_steps": 42070, "total_steps": 58920, "loss": 0.0, "lr": 4.582858139041418e-07, "epoch": 3.5700950441276307, "percentage": 71.4, "elapsed_time": "1:06:18", "remaining_time": "0:26:33", "throughput": 10152.73, "total_tokens": 40393856}
{"current_steps": 42075, "total_steps": 58920, "loss": 0.0, "lr": 4.5803684603165106e-07, "epoch": 3.570519348268839, "percentage": 71.41, "elapsed_time": "1:06:19", "remaining_time": "0:26:33", "throughput": 10152.99, "total_tokens": 40398784}
{"current_steps": 42080, "total_steps": 58920, "loss": 0.0005, "lr": 4.5778792571447024e-07, "epoch": 3.5709436524100475, "percentage": 71.42, "elapsed_time": "1:06:19", "remaining_time": "0:26:32", "throughput": 10153.18, "total_tokens": 40403328}
{"current_steps": 42085, "total_steps": 58920, "loss": 0.0, "lr": 4.575390529744414e-07, "epoch": 3.571367956551256, "percentage": 71.43, "elapsed_time": "1:06:19", "remaining_time": "0:26:31", "throughput": 10153.46, "total_tokens": 40408320}
{"current_steps": 42090, "total_steps": 58920, "loss": 0.0, "lr": 4.57290227833402e-07, "epoch": 3.5717922606924644, "percentage": 71.44, "elapsed_time": "1:06:20", "remaining_time": "0:26:31", "throughput": 10153.67, "total_tokens": 40412992}
{"current_steps": 42095, "total_steps": 58920, "loss": 0.0, "lr": 4.5704145031318576e-07, "epoch": 3.572216564833673, "percentage": 71.44, "elapsed_time": "1:06:20", "remaining_time": "0:26:30", "throughput": 10153.88, "total_tokens": 40417664}
{"current_steps": 42100, "total_steps": 58920, "loss": 0.0, "lr": 4.5679272043562176e-07, "epoch": 3.572640868974881, "percentage": 71.45, "elapsed_time": "1:06:20", "remaining_time": "0:26:30", "throughput": 10154.1, "total_tokens": 40422400}
{"current_steps": 42105, "total_steps": 58920, "loss": 0.0, "lr": 4.5654403822253553e-07, "epoch": 3.5730651731160896, "percentage": 71.46, "elapsed_time": "1:06:21", "remaining_time": "0:26:29", "throughput": 10154.4, "total_tokens": 40427584}
{"current_steps": 42110, "total_steps": 58920, "loss": 0.0, "lr": 4.562954036957476e-07, "epoch": 3.573489477257298, "percentage": 71.47, "elapsed_time": "1:06:21", "remaining_time": "0:26:29", "throughput": 10154.56, "total_tokens": 40432000}
{"current_steps": 42115, "total_steps": 58920, "loss": 0.0071, "lr": 4.5604681687707504e-07, "epoch": 3.5739137813985065, "percentage": 71.48, "elapsed_time": "1:06:22", "remaining_time": "0:26:28", "throughput": 10154.78, "total_tokens": 40436736}
{"current_steps": 42120, "total_steps": 58920, "loss": 0.0, "lr": 4.557982777883304e-07, "epoch": 3.574338085539715, "percentage": 71.49, "elapsed_time": "1:06:22", "remaining_time": "0:26:28", "throughput": 10155.07, "total_tokens": 40441792}
{"current_steps": 42125, "total_steps": 58920, "loss": 0.0, "lr": 4.55549786451322e-07, "epoch": 3.5747623896809233, "percentage": 71.5, "elapsed_time": "1:06:22", "remaining_time": "0:26:27", "throughput": 10155.29, "total_tokens": 40446528}
{"current_steps": 42130, "total_steps": 58920, "loss": 0.0, "lr": 4.5530134288785406e-07, "epoch": 3.5751866938221317, "percentage": 71.5, "elapsed_time": "1:06:23", "remaining_time": "0:26:27", "throughput": 10155.5, "total_tokens": 40451200}
{"current_steps": 42135, "total_steps": 58920, "loss": 0.0, "lr": 4.5505294711972677e-07, "epoch": 3.57561099796334, "percentage": 71.51, "elapsed_time": "1:06:23", "remaining_time": "0:26:26", "throughput": 10155.67, "total_tokens": 40455744}
{"current_steps": 42140, "total_steps": 58920, "loss": 0.0, "lr": 4.548045991687358e-07, "epoch": 3.5760353021045486, "percentage": 71.52, "elapsed_time": "1:06:23", "remaining_time": "0:26:26", "throughput": 10155.85, "total_tokens": 40460288}
{"current_steps": 42145, "total_steps": 58920, "loss": 0.0, "lr": 4.5455629905667247e-07, "epoch": 3.576459606245757, "percentage": 71.53, "elapsed_time": "1:06:24", "remaining_time": "0:26:25", "throughput": 10156.08, "total_tokens": 40465024}
{"current_steps": 42150, "total_steps": 58920, "loss": 0.0, "lr": 4.543080468053253e-07, "epoch": 3.5768839103869654, "percentage": 71.54, "elapsed_time": "1:06:24", "remaining_time": "0:26:25", "throughput": 10156.31, "total_tokens": 40469824}
{"current_steps": 42155, "total_steps": 58920, "loss": 0.0, "lr": 4.5405984243647644e-07, "epoch": 3.577308214528174, "percentage": 71.55, "elapsed_time": "1:06:25", "remaining_time": "0:26:24", "throughput": 10156.63, "total_tokens": 40475072}
{"current_steps": 42160, "total_steps": 58920, "loss": 0.0, "lr": 4.5381168597190523e-07, "epoch": 3.5777325186693822, "percentage": 71.55, "elapsed_time": "1:06:25", "remaining_time": "0:26:24", "throughput": 10156.94, "total_tokens": 40480256}
{"current_steps": 42165, "total_steps": 58920, "loss": 0.0, "lr": 4.535635774333867e-07, "epoch": 3.5781568228105907, "percentage": 71.56, "elapsed_time": "1:06:25", "remaining_time": "0:26:23", "throughput": 10157.02, "total_tokens": 40484288}
{"current_steps": 42170, "total_steps": 58920, "loss": 0.0, "lr": 4.5331551684269087e-07, "epoch": 3.578581126951799, "percentage": 71.57, "elapsed_time": "1:06:26", "remaining_time": "0:26:23", "throughput": 10157.21, "total_tokens": 40488896}
{"current_steps": 42175, "total_steps": 58920, "loss": 0.0, "lr": 4.530675042215855e-07, "epoch": 3.5790054310930075, "percentage": 71.58, "elapsed_time": "1:06:26", "remaining_time": "0:26:22", "throughput": 10157.39, "total_tokens": 40493440}
{"current_steps": 42180, "total_steps": 58920, "loss": 0.0, "lr": 4.5281953959183105e-07, "epoch": 3.579429735234216, "percentage": 71.59, "elapsed_time": "1:06:26", "remaining_time": "0:26:22", "throughput": 10157.74, "total_tokens": 40498816}
{"current_steps": 42185, "total_steps": 58920, "loss": 0.0, "lr": 4.525716229751873e-07, "epoch": 3.5798540393754243, "percentage": 71.6, "elapsed_time": "1:06:27", "remaining_time": "0:26:21", "throughput": 10157.96, "total_tokens": 40503552}
{"current_steps": 42190, "total_steps": 58920, "loss": 0.0, "lr": 4.5232375439340633e-07, "epoch": 3.5802783435166328, "percentage": 71.61, "elapsed_time": "1:06:27", "remaining_time": "0:26:21", "throughput": 10158.13, "total_tokens": 40508032}
{"current_steps": 42195, "total_steps": 58920, "loss": 0.0, "lr": 4.520759338682393e-07, "epoch": 3.580702647657841, "percentage": 71.61, "elapsed_time": "1:06:28", "remaining_time": "0:26:20", "throughput": 10158.29, "total_tokens": 40512448}
{"current_steps": 42200, "total_steps": 58920, "loss": 0.0, "lr": 4.5182816142143043e-07, "epoch": 3.5811269517990496, "percentage": 71.62, "elapsed_time": "1:06:28", "remaining_time": "0:26:20", "throughput": 10158.44, "total_tokens": 40516800}
{"current_steps": 42205, "total_steps": 58920, "loss": 0.0, "lr": 4.515804370747208e-07, "epoch": 3.581551255940258, "percentage": 71.63, "elapsed_time": "1:06:28", "remaining_time": "0:26:19", "throughput": 10158.66, "total_tokens": 40521536}
{"current_steps": 42210, "total_steps": 58920, "loss": 0.0, "lr": 4.513327608498486e-07, "epoch": 3.5819755600814664, "percentage": 71.64, "elapsed_time": "1:06:29", "remaining_time": "0:26:19", "throughput": 10159.0, "total_tokens": 40526976}
{"current_steps": 42215, "total_steps": 58920, "loss": 0.0018, "lr": 4.510851327685449e-07, "epoch": 3.582399864222675, "percentage": 71.65, "elapsed_time": "1:06:29", "remaining_time": "0:26:18", "throughput": 10159.25, "total_tokens": 40531840}
{"current_steps": 42220, "total_steps": 58920, "loss": 0.0, "lr": 4.5083755285253966e-07, "epoch": 3.5828241683638833, "percentage": 71.66, "elapsed_time": "1:06:30", "remaining_time": "0:26:18", "throughput": 10159.47, "total_tokens": 40536576}
{"current_steps": 42225, "total_steps": 58920, "loss": 0.0, "lr": 4.5059002112355573e-07, "epoch": 3.5832484725050917, "percentage": 71.66, "elapsed_time": "1:06:30", "remaining_time": "0:26:17", "throughput": 10159.76, "total_tokens": 40541632}
{"current_steps": 42230, "total_steps": 58920, "loss": 0.0, "lr": 4.503425376033141e-07, "epoch": 3.5836727766463, "percentage": 71.67, "elapsed_time": "1:06:30", "remaining_time": "0:26:17", "throughput": 10159.9, "total_tokens": 40545984}
{"current_steps": 42235, "total_steps": 58920, "loss": 0.0, "lr": 4.5009510231353074e-07, "epoch": 3.5840970807875085, "percentage": 71.68, "elapsed_time": "1:06:31", "remaining_time": "0:26:16", "throughput": 10160.11, "total_tokens": 40550656}
{"current_steps": 42240, "total_steps": 58920, "loss": 0.0, "lr": 4.498477152759159e-07, "epoch": 3.584521384928717, "percentage": 71.69, "elapsed_time": "1:06:31", "remaining_time": "0:26:16", "throughput": 10160.19, "total_tokens": 40554752}
{"current_steps": 42245, "total_steps": 58920, "loss": 0.0, "lr": 4.496003765121785e-07, "epoch": 3.5849456890699254, "percentage": 71.7, "elapsed_time": "1:06:31", "remaining_time": "0:26:15", "throughput": 10160.4, "total_tokens": 40559424}
{"current_steps": 42250, "total_steps": 58920, "loss": 0.0, "lr": 4.493530860440201e-07, "epoch": 3.585369993211134, "percentage": 71.71, "elapsed_time": "1:06:32", "remaining_time": "0:26:15", "throughput": 10160.62, "total_tokens": 40564096}
{"current_steps": 42255, "total_steps": 58920, "loss": 0.0, "lr": 4.4910584389314064e-07, "epoch": 3.5857942973523422, "percentage": 71.72, "elapsed_time": "1:06:32", "remaining_time": "0:26:14", "throughput": 10161.0, "total_tokens": 40569728}
{"current_steps": 42260, "total_steps": 58920, "loss": 0.0, "lr": 4.4885865008123447e-07, "epoch": 3.5862186014935507, "percentage": 71.72, "elapsed_time": "1:06:33", "remaining_time": "0:26:14", "throughput": 10161.27, "total_tokens": 40574720}
{"current_steps": 42265, "total_steps": 58920, "loss": 0.0, "lr": 4.4861150462999176e-07, "epoch": 3.586642905634759, "percentage": 71.73, "elapsed_time": "1:06:33", "remaining_time": "0:26:13", "throughput": 10161.43, "total_tokens": 40579200}
{"current_steps": 42270, "total_steps": 58920, "loss": 0.0, "lr": 4.4836440756109884e-07, "epoch": 3.5870672097759675, "percentage": 71.74, "elapsed_time": "1:06:33", "remaining_time": "0:26:13", "throughput": 10161.56, "total_tokens": 40583488}
{"current_steps": 42275, "total_steps": 58920, "loss": 0.0183, "lr": 4.481173588962375e-07, "epoch": 3.587491513917176, "percentage": 71.75, "elapsed_time": "1:06:34", "remaining_time": "0:26:12", "throughput": 10161.82, "total_tokens": 40588416}
{"current_steps": 42280, "total_steps": 58920, "loss": 0.0, "lr": 4.4787035865708557e-07, "epoch": 3.5879158180583843, "percentage": 71.76, "elapsed_time": "1:06:34", "remaining_time": "0:26:12", "throughput": 10162.13, "total_tokens": 40593600}
{"current_steps": 42285, "total_steps": 58920, "loss": 0.0264, "lr": 4.476234068653156e-07, "epoch": 3.5883401221995928, "percentage": 71.77, "elapsed_time": "1:06:34", "remaining_time": "0:26:11", "throughput": 10162.32, "total_tokens": 40598208}
{"current_steps": 42290, "total_steps": 58920, "loss": 0.0, "lr": 4.473765035425977e-07, "epoch": 3.588764426340801, "percentage": 71.78, "elapsed_time": "1:06:35", "remaining_time": "0:26:11", "throughput": 10162.6, "total_tokens": 40603264}
{"current_steps": 42295, "total_steps": 58920, "loss": 0.0, "lr": 4.471296487105963e-07, "epoch": 3.5891887304820096, "percentage": 71.78, "elapsed_time": "1:06:35", "remaining_time": "0:26:10", "throughput": 10162.96, "total_tokens": 40608704}
{"current_steps": 42300, "total_steps": 58920, "loss": 0.0078, "lr": 4.4688284239097207e-07, "epoch": 3.589613034623218, "percentage": 71.79, "elapsed_time": "1:06:36", "remaining_time": "0:26:10", "throughput": 10163.35, "total_tokens": 40614400}
{"current_steps": 42305, "total_steps": 58920, "loss": 0.0, "lr": 4.466360846053815e-07, "epoch": 3.5900373387644264, "percentage": 71.8, "elapsed_time": "1:06:36", "remaining_time": "0:26:09", "throughput": 10163.54, "total_tokens": 40619008}
{"current_steps": 42310, "total_steps": 58920, "loss": 0.0, "lr": 4.463893753754766e-07, "epoch": 3.590461642905635, "percentage": 71.81, "elapsed_time": "1:06:36", "remaining_time": "0:26:09", "throughput": 10163.72, "total_tokens": 40623616}
{"current_steps": 42315, "total_steps": 58920, "loss": 0.0, "lr": 4.461427147229051e-07, "epoch": 3.5908859470468433, "percentage": 71.82, "elapsed_time": "1:06:37", "remaining_time": "0:26:08", "throughput": 10163.92, "total_tokens": 40628288}
{"current_steps": 42320, "total_steps": 58920, "loss": 0.0, "lr": 4.4589610266931075e-07, "epoch": 3.5913102511880517, "percentage": 71.83, "elapsed_time": "1:06:37", "remaining_time": "0:26:08", "throughput": 10164.07, "total_tokens": 40632704}
{"current_steps": 42325, "total_steps": 58920, "loss": 0.0, "lr": 4.456495392363329e-07, "epoch": 3.59173455532926, "percentage": 71.83, "elapsed_time": "1:06:38", "remaining_time": "0:26:07", "throughput": 10164.24, "total_tokens": 40637184}
{"current_steps": 42330, "total_steps": 58920, "loss": 0.0, "lr": 4.454030244456063e-07, "epoch": 3.5921588594704685, "percentage": 71.84, "elapsed_time": "1:06:38", "remaining_time": "0:26:07", "throughput": 10164.45, "total_tokens": 40641856}
{"current_steps": 42335, "total_steps": 58920, "loss": 0.0, "lr": 4.4515655831876206e-07, "epoch": 3.592583163611677, "percentage": 71.85, "elapsed_time": "1:06:38", "remaining_time": "0:26:06", "throughput": 10164.68, "total_tokens": 40646656}
{"current_steps": 42340, "total_steps": 58920, "loss": 0.0, "lr": 4.449101408774266e-07, "epoch": 3.5930074677528854, "percentage": 71.86, "elapsed_time": "1:06:39", "remaining_time": "0:26:06", "throughput": 10165.07, "total_tokens": 40652352}
{"current_steps": 42345, "total_steps": 58920, "loss": 0.0148, "lr": 4.4466377214322214e-07, "epoch": 3.593431771894094, "percentage": 71.87, "elapsed_time": "1:06:39", "remaining_time": "0:26:05", "throughput": 10165.31, "total_tokens": 40657280}
{"current_steps": 42350, "total_steps": 58920, "loss": 0.0, "lr": 4.444174521377666e-07, "epoch": 3.593856076035302, "percentage": 71.88, "elapsed_time": "1:06:40", "remaining_time": "0:26:05", "throughput": 10165.6, "total_tokens": 40662400}
{"current_steps": 42355, "total_steps": 58920, "loss": 0.0, "lr": 4.441711808826737e-07, "epoch": 3.5942803801765106, "percentage": 71.89, "elapsed_time": "1:06:40", "remaining_time": "0:26:04", "throughput": 10165.88, "total_tokens": 40667520}
{"current_steps": 42360, "total_steps": 58920, "loss": 0.0, "lr": 4.439249583995525e-07, "epoch": 3.594704684317719, "percentage": 71.89, "elapsed_time": "1:06:40", "remaining_time": "0:26:04", "throughput": 10166.02, "total_tokens": 40671872}
{"current_steps": 42365, "total_steps": 58920, "loss": 0.0, "lr": 4.4367878471000916e-07, "epoch": 3.5951289884589275, "percentage": 71.9, "elapsed_time": "1:06:41", "remaining_time": "0:26:03", "throughput": 10166.21, "total_tokens": 40676480}
{"current_steps": 42370, "total_steps": 58920, "loss": 0.0, "lr": 4.434326598356437e-07, "epoch": 3.595553292600136, "percentage": 71.91, "elapsed_time": "1:06:41", "remaining_time": "0:26:03", "throughput": 10166.39, "total_tokens": 40681024}
{"current_steps": 42375, "total_steps": 58920, "loss": 0.0, "lr": 4.431865837980527e-07, "epoch": 3.5959775967413443, "percentage": 71.92, "elapsed_time": "1:06:41", "remaining_time": "0:26:02", "throughput": 10166.73, "total_tokens": 40686336}
{"current_steps": 42380, "total_steps": 58920, "loss": 0.0, "lr": 4.429405566188287e-07, "epoch": 3.5964019008825527, "percentage": 71.93, "elapsed_time": "1:06:42", "remaining_time": "0:26:02", "throughput": 10167.08, "total_tokens": 40691776}
{"current_steps": 42385, "total_steps": 58920, "loss": 0.0, "lr": 4.4269457831955915e-07, "epoch": 3.596826205023761, "percentage": 71.94, "elapsed_time": "1:06:42", "remaining_time": "0:26:01", "throughput": 10167.39, "total_tokens": 40697024}
{"current_steps": 42390, "total_steps": 58920, "loss": 0.0, "lr": 4.42448648921829e-07, "epoch": 3.5972505091649696, "percentage": 71.95, "elapsed_time": "1:06:43", "remaining_time": "0:26:01", "throughput": 10167.62, "total_tokens": 40701824}
{"current_steps": 42395, "total_steps": 58920, "loss": 0.0, "lr": 4.4220276844721615e-07, "epoch": 3.597674813306178, "percentage": 71.95, "elapsed_time": "1:06:43", "remaining_time": "0:26:00", "throughput": 10167.85, "total_tokens": 40706624}
{"current_steps": 42400, "total_steps": 58920, "loss": 0.0, "lr": 4.4195693691729716e-07, "epoch": 3.5980991174473864, "percentage": 71.96, "elapsed_time": "1:06:43", "remaining_time": "0:25:59", "throughput": 10168.01, "total_tokens": 40711104}
{"current_steps": 42405, "total_steps": 58920, "loss": 0.0, "lr": 4.417111543536418e-07, "epoch": 3.598523421588595, "percentage": 71.97, "elapsed_time": "1:06:44", "remaining_time": "0:25:59", "throughput": 10168.24, "total_tokens": 40715904}
{"current_steps": 42410, "total_steps": 58920, "loss": 0.0, "lr": 4.414654207778169e-07, "epoch": 3.5989477257298033, "percentage": 71.98, "elapsed_time": "1:06:44", "remaining_time": "0:25:58", "throughput": 10168.59, "total_tokens": 40721344}
{"current_steps": 42415, "total_steps": 58920, "loss": 0.0, "lr": 4.4121973621138477e-07, "epoch": 3.5993720298710117, "percentage": 71.99, "elapsed_time": "1:06:45", "remaining_time": "0:25:58", "throughput": 10168.97, "total_tokens": 40726976}
{"current_steps": 42420, "total_steps": 58920, "loss": 0.0, "lr": 4.40974100675903e-07, "epoch": 3.59979633401222, "percentage": 72.0, "elapsed_time": "1:06:45", "remaining_time": "0:25:57", "throughput": 10169.11, "total_tokens": 40731328}
{"current_steps": 42425, "total_steps": 58920, "loss": 0.0, "lr": 4.407285141929262e-07, "epoch": 3.6002206381534285, "percentage": 72.0, "elapsed_time": "1:06:45", "remaining_time": "0:25:57", "throughput": 10169.27, "total_tokens": 40735808}
{"current_steps": 42430, "total_steps": 58920, "loss": 0.0, "lr": 4.4048297678400235e-07, "epoch": 3.600644942294637, "percentage": 72.01, "elapsed_time": "1:06:46", "remaining_time": "0:25:56", "throughput": 10169.53, "total_tokens": 40740736}
{"current_steps": 42435, "total_steps": 58920, "loss": 0.0, "lr": 4.4023748847067786e-07, "epoch": 3.6010692464358454, "percentage": 72.02, "elapsed_time": "1:06:46", "remaining_time": "0:25:56", "throughput": 10170.08, "total_tokens": 40747328}
{"current_steps": 42440, "total_steps": 58920, "loss": 0.0, "lr": 4.3999204927449207e-07, "epoch": 3.601493550577054, "percentage": 72.03, "elapsed_time": "1:06:46", "remaining_time": "0:25:55", "throughput": 10170.44, "total_tokens": 40752832}
{"current_steps": 42445, "total_steps": 58920, "loss": 0.0, "lr": 4.3974665921698237e-07, "epoch": 3.601917854718262, "percentage": 72.04, "elapsed_time": "1:06:47", "remaining_time": "0:25:55", "throughput": 10170.55, "total_tokens": 40757120}
{"current_steps": 42450, "total_steps": 58920, "loss": 0.0, "lr": 4.39501318319681e-07, "epoch": 3.6023421588594706, "percentage": 72.05, "elapsed_time": "1:06:47", "remaining_time": "0:25:54", "throughput": 10170.65, "total_tokens": 40761216}
{"current_steps": 42455, "total_steps": 58920, "loss": 0.0, "lr": 4.3925602660411445e-07, "epoch": 3.602766463000679, "percentage": 72.06, "elapsed_time": "1:06:48", "remaining_time": "0:25:54", "throughput": 10170.75, "total_tokens": 40765376}
{"current_steps": 42460, "total_steps": 58920, "loss": 0.0, "lr": 4.390107840918077e-07, "epoch": 3.6031907671418875, "percentage": 72.06, "elapsed_time": "1:06:48", "remaining_time": "0:25:53", "throughput": 10170.96, "total_tokens": 40770112}
{"current_steps": 42465, "total_steps": 58920, "loss": 0.0, "lr": 4.3876559080427853e-07, "epoch": 3.603615071283096, "percentage": 72.07, "elapsed_time": "1:06:48", "remaining_time": "0:25:53", "throughput": 10171.1, "total_tokens": 40774464}
{"current_steps": 42470, "total_steps": 58920, "loss": 0.0, "lr": 4.3852044676304276e-07, "epoch": 3.6040393754243043, "percentage": 72.08, "elapsed_time": "1:06:49", "remaining_time": "0:25:52", "throughput": 10171.26, "total_tokens": 40778944}
{"current_steps": 42475, "total_steps": 58920, "loss": 0.0447, "lr": 4.382753519896106e-07, "epoch": 3.6044636795655127, "percentage": 72.09, "elapsed_time": "1:06:49", "remaining_time": "0:25:52", "throughput": 10171.45, "total_tokens": 40783552}
{"current_steps": 42480, "total_steps": 58920, "loss": 0.0, "lr": 4.380303065054882e-07, "epoch": 3.604887983706721, "percentage": 72.1, "elapsed_time": "1:06:49", "remaining_time": "0:25:51", "throughput": 10171.71, "total_tokens": 40788480}
{"current_steps": 42485, "total_steps": 58920, "loss": 0.0, "lr": 4.3778531033217746e-07, "epoch": 3.605312287847929, "percentage": 72.11, "elapsed_time": "1:06:50", "remaining_time": "0:25:51", "throughput": 10171.93, "total_tokens": 40793216}
{"current_steps": 42490, "total_steps": 58920, "loss": 0.0493, "lr": 4.3754036349117586e-07, "epoch": 3.605736591989138, "percentage": 72.11, "elapsed_time": "1:06:50", "remaining_time": "0:25:50", "throughput": 10172.18, "total_tokens": 40798144}
{"current_steps": 42495, "total_steps": 58920, "loss": 0.0, "lr": 4.372954660039769e-07, "epoch": 3.606160896130346, "percentage": 72.12, "elapsed_time": "1:06:51", "remaining_time": "0:25:50", "throughput": 10172.43, "total_tokens": 40803008}
{"current_steps": 42500, "total_steps": 58920, "loss": 0.0, "lr": 4.3705061789206855e-07, "epoch": 3.606585200271555, "percentage": 72.13, "elapsed_time": "1:06:51", "remaining_time": "0:25:49", "throughput": 10172.59, "total_tokens": 40807488}
{"current_steps": 42505, "total_steps": 58920, "loss": 0.0, "lr": 4.3680581917693627e-07, "epoch": 3.607009504412763, "percentage": 72.14, "elapsed_time": "1:06:51", "remaining_time": "0:25:49", "throughput": 10172.76, "total_tokens": 40812032}
{"current_steps": 42510, "total_steps": 58920, "loss": 0.0, "lr": 4.365610698800599e-07, "epoch": 3.6074338085539717, "percentage": 72.15, "elapsed_time": "1:06:52", "remaining_time": "0:25:48", "throughput": 10172.92, "total_tokens": 40816448}
{"current_steps": 42515, "total_steps": 58920, "loss": 0.0, "lr": 4.363163700229154e-07, "epoch": 3.6078581126951796, "percentage": 72.16, "elapsed_time": "1:06:52", "remaining_time": "0:25:48", "throughput": 10173.15, "total_tokens": 40821312}
{"current_steps": 42520, "total_steps": 58920, "loss": 0.001, "lr": 4.360717196269743e-07, "epoch": 3.6082824168363885, "percentage": 72.17, "elapsed_time": "1:06:53", "remaining_time": "0:25:47", "throughput": 10173.37, "total_tokens": 40826112}
{"current_steps": 42525, "total_steps": 58920, "loss": 0.0, "lr": 4.358271187137037e-07, "epoch": 3.6087067209775965, "percentage": 72.17, "elapsed_time": "1:06:53", "remaining_time": "0:25:47", "throughput": 10173.54, "total_tokens": 40830592}
{"current_steps": 42530, "total_steps": 58920, "loss": 0.0, "lr": 4.3558256730456656e-07, "epoch": 3.6091310251188053, "percentage": 72.18, "elapsed_time": "1:06:53", "remaining_time": "0:25:46", "throughput": 10173.75, "total_tokens": 40835264}
{"current_steps": 42535, "total_steps": 58920, "loss": 0.0, "lr": 4.353380654210213e-07, "epoch": 3.6095553292600133, "percentage": 72.19, "elapsed_time": "1:06:54", "remaining_time": "0:25:46", "throughput": 10173.98, "total_tokens": 40840128}
{"current_steps": 42540, "total_steps": 58920, "loss": 0.0, "lr": 4.3509361308452197e-07, "epoch": 3.609979633401222, "percentage": 72.2, "elapsed_time": "1:06:54", "remaining_time": "0:25:45", "throughput": 10174.3, "total_tokens": 40845312}
{"current_steps": 42545, "total_steps": 58920, "loss": 0.0, "lr": 4.348492103165187e-07, "epoch": 3.61040393754243, "percentage": 72.21, "elapsed_time": "1:06:54", "remaining_time": "0:25:45", "throughput": 10174.5, "total_tokens": 40850048}
{"current_steps": 42550, "total_steps": 58920, "loss": 0.0, "lr": 4.346048571384566e-07, "epoch": 3.610828241683639, "percentage": 72.22, "elapsed_time": "1:06:55", "remaining_time": "0:25:44", "throughput": 10174.67, "total_tokens": 40854528}
{"current_steps": 42555, "total_steps": 58920, "loss": 0.0, "lr": 4.34360553571777e-07, "epoch": 3.611252545824847, "percentage": 72.23, "elapsed_time": "1:06:55", "remaining_time": "0:25:44", "throughput": 10174.95, "total_tokens": 40859584}
{"current_steps": 42560, "total_steps": 58920, "loss": 0.0, "lr": 4.341162996379165e-07, "epoch": 3.611676849966056, "percentage": 72.23, "elapsed_time": "1:06:56", "remaining_time": "0:25:43", "throughput": 10175.12, "total_tokens": 40864128}
{"current_steps": 42565, "total_steps": 58920, "loss": 0.0002, "lr": 4.3387209535830773e-07, "epoch": 3.612101154107264, "percentage": 72.24, "elapsed_time": "1:06:56", "remaining_time": "0:25:43", "throughput": 10175.32, "total_tokens": 40868800}
{"current_steps": 42570, "total_steps": 58920, "loss": 0.0118, "lr": 4.336279407543786e-07, "epoch": 3.6125254582484727, "percentage": 72.25, "elapsed_time": "1:06:56", "remaining_time": "0:25:42", "throughput": 10175.5, "total_tokens": 40873344}
{"current_steps": 42575, "total_steps": 58920, "loss": 0.0, "lr": 4.333838358475527e-07, "epoch": 3.6129497623896807, "percentage": 72.26, "elapsed_time": "1:06:57", "remaining_time": "0:25:42", "throughput": 10175.78, "total_tokens": 40878400}
{"current_steps": 42580, "total_steps": 58920, "loss": 0.0001, "lr": 4.3313978065924936e-07, "epoch": 3.6133740665308896, "percentage": 72.27, "elapsed_time": "1:06:57", "remaining_time": "0:25:41", "throughput": 10175.96, "total_tokens": 40882944}
{"current_steps": 42585, "total_steps": 58920, "loss": 0.0, "lr": 4.328957752108838e-07, "epoch": 3.6137983706720975, "percentage": 72.28, "elapsed_time": "1:06:57", "remaining_time": "0:25:41", "throughput": 10176.1, "total_tokens": 40887296}
{"current_steps": 42590, "total_steps": 58920, "loss": 0.0, "lr": 4.326518195238664e-07, "epoch": 3.6142226748133064, "percentage": 72.28, "elapsed_time": "1:06:58", "remaining_time": "0:25:40", "throughput": 10176.25, "total_tokens": 40891712}
{"current_steps": 42595, "total_steps": 58920, "loss": 0.0, "lr": 4.324079136196034e-07, "epoch": 3.6146469789545144, "percentage": 72.29, "elapsed_time": "1:06:58", "remaining_time": "0:25:40", "throughput": 10176.54, "total_tokens": 40896832}
{"current_steps": 42600, "total_steps": 58920, "loss": 0.0486, "lr": 4.3216405751949634e-07, "epoch": 3.6150712830957232, "percentage": 72.3, "elapsed_time": "1:06:59", "remaining_time": "0:25:39", "throughput": 10176.7, "total_tokens": 40901312}
{"current_steps": 42605, "total_steps": 58920, "loss": 0.0, "lr": 4.319202512449438e-07, "epoch": 3.615495587236931, "percentage": 72.31, "elapsed_time": "1:06:59", "remaining_time": "0:25:39", "throughput": 10176.88, "total_tokens": 40905856}
{"current_steps": 42610, "total_steps": 58920, "loss": 0.0134, "lr": 4.3167649481733745e-07, "epoch": 3.61591989137814, "percentage": 72.32, "elapsed_time": "1:06:59", "remaining_time": "0:25:38", "throughput": 10177.09, "total_tokens": 40910592}
{"current_steps": 42615, "total_steps": 58920, "loss": 0.0, "lr": 4.314327882580675e-07, "epoch": 3.616344195519348, "percentage": 72.33, "elapsed_time": "1:07:00", "remaining_time": "0:25:38", "throughput": 10177.43, "total_tokens": 40915968}
{"current_steps": 42620, "total_steps": 58920, "loss": 0.0, "lr": 4.3118913158851723e-07, "epoch": 3.616768499660557, "percentage": 72.34, "elapsed_time": "1:07:00", "remaining_time": "0:25:37", "throughput": 10177.73, "total_tokens": 40921152}
{"current_steps": 42625, "total_steps": 58920, "loss": 0.0, "lr": 4.30945524830067e-07, "epoch": 3.617192803801765, "percentage": 72.34, "elapsed_time": "1:07:01", "remaining_time": "0:25:37", "throughput": 10177.82, "total_tokens": 40925312}
{"current_steps": 42630, "total_steps": 58920, "loss": 0.0022, "lr": 4.307019680040923e-07, "epoch": 3.6176171079429738, "percentage": 72.35, "elapsed_time": "1:07:01", "remaining_time": "0:25:36", "throughput": 10178.12, "total_tokens": 40930560}
{"current_steps": 42635, "total_steps": 58920, "loss": 0.0001, "lr": 4.3045846113196417e-07, "epoch": 3.6180414120841817, "percentage": 72.36, "elapsed_time": "1:07:01", "remaining_time": "0:25:36", "throughput": 10178.28, "total_tokens": 40935040}
{"current_steps": 42640, "total_steps": 58920, "loss": 0.0, "lr": 4.302150042350504e-07, "epoch": 3.6184657162253906, "percentage": 72.37, "elapsed_time": "1:07:02", "remaining_time": "0:25:35", "throughput": 10178.51, "total_tokens": 40939840}
{"current_steps": 42645, "total_steps": 58920, "loss": 0.0, "lr": 4.299715973347121e-07, "epoch": 3.6188900203665986, "percentage": 72.38, "elapsed_time": "1:07:02", "remaining_time": "0:25:35", "throughput": 10178.65, "total_tokens": 40944192}
{"current_steps": 42650, "total_steps": 58920, "loss": 0.0021, "lr": 4.297282404523088e-07, "epoch": 3.6193143245078074, "percentage": 72.39, "elapsed_time": "1:07:02", "remaining_time": "0:25:34", "throughput": 10178.9, "total_tokens": 40949120}
{"current_steps": 42655, "total_steps": 58920, "loss": 0.0, "lr": 4.2948493360919314e-07, "epoch": 3.6197386286490154, "percentage": 72.39, "elapsed_time": "1:07:03", "remaining_time": "0:25:34", "throughput": 10179.03, "total_tokens": 40953408}
{"current_steps": 42660, "total_steps": 58920, "loss": 0.0, "lr": 4.292416768267143e-07, "epoch": 3.6201629327902243, "percentage": 72.4, "elapsed_time": "1:07:03", "remaining_time": "0:25:33", "throughput": 10179.22, "total_tokens": 40958080}
{"current_steps": 42665, "total_steps": 58920, "loss": 0.0, "lr": 4.289984701262184e-07, "epoch": 3.6205872369314323, "percentage": 72.41, "elapsed_time": "1:07:04", "remaining_time": "0:25:33", "throughput": 10179.36, "total_tokens": 40962432}
{"current_steps": 42670, "total_steps": 58920, "loss": 0.0, "lr": 4.2875531352904437e-07, "epoch": 3.621011541072641, "percentage": 72.42, "elapsed_time": "1:07:04", "remaining_time": "0:25:32", "throughput": 10179.58, "total_tokens": 40967232}
{"current_steps": 42675, "total_steps": 58920, "loss": 0.0, "lr": 4.285122070565298e-07, "epoch": 3.621435845213849, "percentage": 72.43, "elapsed_time": "1:07:04", "remaining_time": "0:25:32", "throughput": 10179.83, "total_tokens": 40972160}
{"current_steps": 42680, "total_steps": 58920, "loss": 0.0, "lr": 4.28269150730005e-07, "epoch": 3.621860149355058, "percentage": 72.44, "elapsed_time": "1:07:05", "remaining_time": "0:25:31", "throughput": 10179.95, "total_tokens": 40976448}
{"current_steps": 42685, "total_steps": 58920, "loss": 0.0, "lr": 4.2802614457079845e-07, "epoch": 3.622284453496266, "percentage": 72.45, "elapsed_time": "1:07:05", "remaining_time": "0:25:31", "throughput": 10180.06, "total_tokens": 40980672}
{"current_steps": 42690, "total_steps": 58920, "loss": 0.0, "lr": 4.2778318860023254e-07, "epoch": 3.622708757637475, "percentage": 72.45, "elapsed_time": "1:07:05", "remaining_time": "0:25:30", "throughput": 10180.25, "total_tokens": 40985344}
{"current_steps": 42695, "total_steps": 58920, "loss": 0.0, "lr": 4.2754028283962585e-07, "epoch": 3.6231330617786828, "percentage": 72.46, "elapsed_time": "1:07:06", "remaining_time": "0:25:30", "throughput": 10180.48, "total_tokens": 40990144}
{"current_steps": 42700, "total_steps": 58920, "loss": 0.0, "lr": 4.2729742731029284e-07, "epoch": 3.6235573659198916, "percentage": 72.47, "elapsed_time": "1:07:06", "remaining_time": "0:25:29", "throughput": 10180.86, "total_tokens": 40995776}
{"current_steps": 42705, "total_steps": 58920, "loss": 0.0001, "lr": 4.270546220335421e-07, "epoch": 3.6239816700610996, "percentage": 72.48, "elapsed_time": "1:07:07", "remaining_time": "0:25:29", "throughput": 10181.42, "total_tokens": 41002496}
{"current_steps": 42710, "total_steps": 58920, "loss": 0.0, "lr": 4.2681186703068053e-07, "epoch": 3.6244059742023085, "percentage": 72.49, "elapsed_time": "1:07:07", "remaining_time": "0:25:28", "throughput": 10181.62, "total_tokens": 41007104}
{"current_steps": 42715, "total_steps": 58920, "loss": 0.0, "lr": 4.265691623230072e-07, "epoch": 3.6248302783435165, "percentage": 72.5, "elapsed_time": "1:07:07", "remaining_time": "0:25:28", "throughput": 10181.81, "total_tokens": 41011776}
{"current_steps": 42720, "total_steps": 58920, "loss": 0.0001, "lr": 4.2632650793182e-07, "epoch": 3.6252545824847253, "percentage": 72.51, "elapsed_time": "1:07:08", "remaining_time": "0:25:27", "throughput": 10182.05, "total_tokens": 41016640}
{"current_steps": 42725, "total_steps": 58920, "loss": 0.0, "lr": 4.260839038784105e-07, "epoch": 3.6256788866259333, "percentage": 72.51, "elapsed_time": "1:07:08", "remaining_time": "0:25:27", "throughput": 10182.3, "total_tokens": 41021568}
{"current_steps": 42730, "total_steps": 58920, "loss": 0.0, "lr": 4.2584135018406633e-07, "epoch": 3.626103190767142, "percentage": 72.52, "elapsed_time": "1:07:09", "remaining_time": "0:25:26", "throughput": 10182.52, "total_tokens": 41026304}
{"current_steps": 42735, "total_steps": 58920, "loss": 0.0, "lr": 4.2559884687007065e-07, "epoch": 3.62652749490835, "percentage": 72.53, "elapsed_time": "1:07:09", "remaining_time": "0:25:26", "throughput": 10182.77, "total_tokens": 41031232}
{"current_steps": 42740, "total_steps": 58920, "loss": 0.0, "lr": 4.253563939577023e-07, "epoch": 3.626951799049559, "percentage": 72.54, "elapsed_time": "1:07:09", "remaining_time": "0:25:25", "throughput": 10183.03, "total_tokens": 41036224}
{"current_steps": 42745, "total_steps": 58920, "loss": 0.0, "lr": 4.251139914682356e-07, "epoch": 3.627376103190767, "percentage": 72.55, "elapsed_time": "1:07:10", "remaining_time": "0:25:25", "throughput": 10183.38, "total_tokens": 41041664}
{"current_steps": 42750, "total_steps": 58920, "loss": 0.0, "lr": 4.248716394229406e-07, "epoch": 3.6278004073319754, "percentage": 72.56, "elapsed_time": "1:07:10", "remaining_time": "0:25:24", "throughput": 10183.61, "total_tokens": 41046464}
{"current_steps": 42755, "total_steps": 58920, "loss": 0.0186, "lr": 4.2462933784308264e-07, "epoch": 3.628224711473184, "percentage": 72.56, "elapsed_time": "1:07:11", "remaining_time": "0:25:24", "throughput": 10183.74, "total_tokens": 41050752}
{"current_steps": 42760, "total_steps": 58920, "loss": 0.0, "lr": 4.243870867499231e-07, "epoch": 3.6286490156143922, "percentage": 72.57, "elapsed_time": "1:07:11", "remaining_time": "0:25:23", "throughput": 10184.05, "total_tokens": 41056000}
{"current_steps": 42765, "total_steps": 58920, "loss": 0.0, "lr": 4.2414488616471834e-07, "epoch": 3.6290733197556007, "percentage": 72.58, "elapsed_time": "1:07:11", "remaining_time": "0:25:23", "throughput": 10184.24, "total_tokens": 41060608}
{"current_steps": 42770, "total_steps": 58920, "loss": 0.0, "lr": 4.2390273610872065e-07, "epoch": 3.629497623896809, "percentage": 72.59, "elapsed_time": "1:07:12", "remaining_time": "0:25:22", "throughput": 10184.39, "total_tokens": 41065024}
{"current_steps": 42775, "total_steps": 58920, "loss": 0.0, "lr": 4.23660636603178e-07, "epoch": 3.6299219280380175, "percentage": 72.6, "elapsed_time": "1:07:12", "remaining_time": "0:25:22", "throughput": 10184.55, "total_tokens": 41069504}
{"current_steps": 42780, "total_steps": 58920, "loss": 0.0, "lr": 4.2341858766933345e-07, "epoch": 3.630346232179226, "percentage": 72.61, "elapsed_time": "1:07:12", "remaining_time": "0:25:21", "throughput": 10184.7, "total_tokens": 41073920}
{"current_steps": 42785, "total_steps": 58920, "loss": 0.0, "lr": 4.2317658932842625e-07, "epoch": 3.6307705363204343, "percentage": 72.62, "elapsed_time": "1:07:13", "remaining_time": "0:25:21", "throughput": 10184.92, "total_tokens": 41078720}
{"current_steps": 42790, "total_steps": 58920, "loss": 0.0, "lr": 4.229346416016907e-07, "epoch": 3.6311948404616428, "percentage": 72.62, "elapsed_time": "1:07:13", "remaining_time": "0:25:20", "throughput": 10185.15, "total_tokens": 41083520}
{"current_steps": 42795, "total_steps": 58920, "loss": 0.0, "lr": 4.2269274451035676e-07, "epoch": 3.631619144602851, "percentage": 72.63, "elapsed_time": "1:07:14", "remaining_time": "0:25:20", "throughput": 10185.35, "total_tokens": 41088256}
{"current_steps": 42800, "total_steps": 58920, "loss": 0.0, "lr": 4.2245089807565026e-07, "epoch": 3.6320434487440596, "percentage": 72.64, "elapsed_time": "1:07:14", "remaining_time": "0:25:19", "throughput": 10185.68, "total_tokens": 41093632}
{"current_steps": 42805, "total_steps": 58920, "loss": 0.0, "lr": 4.222091023187921e-07, "epoch": 3.632467752885268, "percentage": 72.65, "elapsed_time": "1:07:14", "remaining_time": "0:25:19", "throughput": 10185.78, "total_tokens": 41097792}
{"current_steps": 42810, "total_steps": 58920, "loss": 0.0, "lr": 4.219673572609992e-07, "epoch": 3.6328920570264764, "percentage": 72.66, "elapsed_time": "1:07:15", "remaining_time": "0:25:18", "throughput": 10185.92, "total_tokens": 41102208}
{"current_steps": 42815, "total_steps": 58920, "loss": 0.0001, "lr": 4.2172566292348333e-07, "epoch": 3.633316361167685, "percentage": 72.67, "elapsed_time": "1:07:15", "remaining_time": "0:25:17", "throughput": 10186.13, "total_tokens": 41106944}
{"current_steps": 42820, "total_steps": 58920, "loss": 0.0, "lr": 4.2148401932745336e-07, "epoch": 3.6337406653088933, "percentage": 72.67, "elapsed_time": "1:07:15", "remaining_time": "0:25:17", "throughput": 10186.38, "total_tokens": 41111872}
{"current_steps": 42825, "total_steps": 58920, "loss": 0.0, "lr": 4.212424264941117e-07, "epoch": 3.6341649694501017, "percentage": 72.68, "elapsed_time": "1:07:16", "remaining_time": "0:25:16", "throughput": 10186.65, "total_tokens": 41116864}
{"current_steps": 42830, "total_steps": 58920, "loss": 0.0, "lr": 4.210008844446574e-07, "epoch": 3.63458927359131, "percentage": 72.69, "elapsed_time": "1:07:16", "remaining_time": "0:25:16", "throughput": 10186.8, "total_tokens": 41121280}
{"current_steps": 42835, "total_steps": 58920, "loss": 0.0, "lr": 4.207593932002852e-07, "epoch": 3.6350135777325185, "percentage": 72.7, "elapsed_time": "1:07:17", "remaining_time": "0:25:15", "throughput": 10186.98, "total_tokens": 41125824}
{"current_steps": 42840, "total_steps": 58920, "loss": 0.0, "lr": 4.2051795278218484e-07, "epoch": 3.635437881873727, "percentage": 72.71, "elapsed_time": "1:07:17", "remaining_time": "0:25:15", "throughput": 10187.22, "total_tokens": 41130752}
{"current_steps": 42845, "total_steps": 58920, "loss": 0.0, "lr": 4.202765632115418e-07, "epoch": 3.6358621860149354, "percentage": 72.72, "elapsed_time": "1:07:17", "remaining_time": "0:25:14", "throughput": 10187.43, "total_tokens": 41135424}
{"current_steps": 42850, "total_steps": 58920, "loss": 0.0, "lr": 4.20035224509537e-07, "epoch": 3.636286490156144, "percentage": 72.73, "elapsed_time": "1:07:18", "remaining_time": "0:25:14", "throughput": 10187.58, "total_tokens": 41139840}
{"current_steps": 42855, "total_steps": 58920, "loss": 0.0, "lr": 4.19793936697348e-07, "epoch": 3.6367107942973522, "percentage": 72.73, "elapsed_time": "1:07:18", "remaining_time": "0:25:13", "throughput": 10187.79, "total_tokens": 41144576}
{"current_steps": 42860, "total_steps": 58920, "loss": 0.0, "lr": 4.195526997961455e-07, "epoch": 3.6371350984385606, "percentage": 72.74, "elapsed_time": "1:07:19", "remaining_time": "0:25:13", "throughput": 10187.97, "total_tokens": 41149248}
{"current_steps": 42865, "total_steps": 58920, "loss": 0.0, "lr": 4.193115138270986e-07, "epoch": 3.637559402579769, "percentage": 72.75, "elapsed_time": "1:07:19", "remaining_time": "0:25:12", "throughput": 10188.16, "total_tokens": 41153856}
{"current_steps": 42870, "total_steps": 58920, "loss": 0.0, "lr": 4.190703788113694e-07, "epoch": 3.6379837067209775, "percentage": 72.76, "elapsed_time": "1:07:19", "remaining_time": "0:25:12", "throughput": 10188.34, "total_tokens": 41158464}
{"current_steps": 42875, "total_steps": 58920, "loss": 0.0, "lr": 4.188292947701167e-07, "epoch": 3.638408010862186, "percentage": 72.77, "elapsed_time": "1:07:20", "remaining_time": "0:25:11", "throughput": 10188.55, "total_tokens": 41163136}
{"current_steps": 42880, "total_steps": 58920, "loss": 0.0, "lr": 4.185882617244959e-07, "epoch": 3.6388323150033943, "percentage": 72.78, "elapsed_time": "1:07:20", "remaining_time": "0:25:11", "throughput": 10188.7, "total_tokens": 41167552}
{"current_steps": 42885, "total_steps": 58920, "loss": 0.0, "lr": 4.183472796956551e-07, "epoch": 3.6392566191446027, "percentage": 72.79, "elapsed_time": "1:07:20", "remaining_time": "0:25:10", "throughput": 10189.03, "total_tokens": 41172928}
{"current_steps": 42890, "total_steps": 58920, "loss": 0.0, "lr": 4.181063487047413e-07, "epoch": 3.639680923285811, "percentage": 72.79, "elapsed_time": "1:07:21", "remaining_time": "0:25:10", "throughput": 10189.17, "total_tokens": 41177344}
{"current_steps": 42895, "total_steps": 58920, "loss": 0.0, "lr": 4.1786546877289363e-07, "epoch": 3.6401052274270196, "percentage": 72.8, "elapsed_time": "1:07:21", "remaining_time": "0:25:09", "throughput": 10189.37, "total_tokens": 41182016}
{"current_steps": 42900, "total_steps": 58920, "loss": 0.0, "lr": 4.1762463992124965e-07, "epoch": 3.640529531568228, "percentage": 72.81, "elapsed_time": "1:07:22", "remaining_time": "0:25:09", "throughput": 10189.59, "total_tokens": 41186752}
{"current_steps": 42905, "total_steps": 58920, "loss": 0.0, "lr": 4.1738386217094123e-07, "epoch": 3.6409538357094364, "percentage": 72.82, "elapsed_time": "1:07:22", "remaining_time": "0:25:08", "throughput": 10189.89, "total_tokens": 41191936}
{"current_steps": 42910, "total_steps": 58920, "loss": 0.0002, "lr": 4.171431355430948e-07, "epoch": 3.641378139850645, "percentage": 72.83, "elapsed_time": "1:07:22", "remaining_time": "0:25:08", "throughput": 10190.04, "total_tokens": 41196352}
{"current_steps": 42915, "total_steps": 58920, "loss": 0.0, "lr": 4.1690246005883434e-07, "epoch": 3.6418024439918533, "percentage": 72.84, "elapsed_time": "1:07:23", "remaining_time": "0:25:07", "throughput": 10190.27, "total_tokens": 41201152}
{"current_steps": 42920, "total_steps": 58920, "loss": 0.0, "lr": 4.1666183573927713e-07, "epoch": 3.6422267481330617, "percentage": 72.84, "elapsed_time": "1:07:23", "remaining_time": "0:25:07", "throughput": 10190.59, "total_tokens": 41206464}
{"current_steps": 42925, "total_steps": 58920, "loss": 0.0, "lr": 4.1642126260553845e-07, "epoch": 3.64265105227427, "percentage": 72.85, "elapsed_time": "1:07:23", "remaining_time": "0:25:06", "throughput": 10190.79, "total_tokens": 41211136}
{"current_steps": 42930, "total_steps": 58920, "loss": 0.0, "lr": 4.161807406787262e-07, "epoch": 3.6430753564154785, "percentage": 72.86, "elapsed_time": "1:07:24", "remaining_time": "0:25:06", "throughput": 10190.98, "total_tokens": 41215744}
{"current_steps": 42935, "total_steps": 58920, "loss": 0.0, "lr": 4.1594026997994647e-07, "epoch": 3.643499660556687, "percentage": 72.87, "elapsed_time": "1:07:24", "remaining_time": "0:25:05", "throughput": 10191.19, "total_tokens": 41220480}
{"current_steps": 42940, "total_steps": 58920, "loss": 0.0, "lr": 4.156998505302993e-07, "epoch": 3.6439239646978954, "percentage": 72.88, "elapsed_time": "1:07:25", "remaining_time": "0:25:05", "throughput": 10191.41, "total_tokens": 41225280}
{"current_steps": 42945, "total_steps": 58920, "loss": 0.0, "lr": 4.1545948235088066e-07, "epoch": 3.644348268839104, "percentage": 72.89, "elapsed_time": "1:07:25", "remaining_time": "0:25:04", "throughput": 10191.75, "total_tokens": 41230720}
{"current_steps": 42950, "total_steps": 58920, "loss": 0.0, "lr": 4.1521916546278235e-07, "epoch": 3.644772572980312, "percentage": 72.9, "elapsed_time": "1:07:25", "remaining_time": "0:25:04", "throughput": 10191.95, "total_tokens": 41235392}
{"current_steps": 42955, "total_steps": 58920, "loss": 0.0, "lr": 4.149788998870901e-07, "epoch": 3.6451968771215206, "percentage": 72.9, "elapsed_time": "1:07:26", "remaining_time": "0:25:03", "throughput": 10192.25, "total_tokens": 41240576}
{"current_steps": 42960, "total_steps": 58920, "loss": 0.0, "lr": 4.147386856448877e-07, "epoch": 3.645621181262729, "percentage": 72.91, "elapsed_time": "1:07:26", "remaining_time": "0:25:03", "throughput": 10192.49, "total_tokens": 41245440}
{"current_steps": 42965, "total_steps": 58920, "loss": 0.0, "lr": 4.144985227572524e-07, "epoch": 3.6460454854039375, "percentage": 72.92, "elapsed_time": "1:07:27", "remaining_time": "0:25:02", "throughput": 10192.77, "total_tokens": 41250496}
{"current_steps": 42970, "total_steps": 58920, "loss": 0.0, "lr": 4.142584112452578e-07, "epoch": 3.646469789545146, "percentage": 72.93, "elapsed_time": "1:07:27", "remaining_time": "0:25:02", "throughput": 10193.02, "total_tokens": 41255488}
{"current_steps": 42975, "total_steps": 58920, "loss": 0.0, "lr": 4.1401835112997297e-07, "epoch": 3.6468940936863543, "percentage": 72.94, "elapsed_time": "1:07:27", "remaining_time": "0:25:01", "throughput": 10193.2, "total_tokens": 41260032}
{"current_steps": 42980, "total_steps": 58920, "loss": 0.0, "lr": 4.13778342432462e-07, "epoch": 3.6473183978275627, "percentage": 72.95, "elapsed_time": "1:07:28", "remaining_time": "0:25:01", "throughput": 10193.39, "total_tokens": 41264704}
{"current_steps": 42985, "total_steps": 58920, "loss": 0.0, "lr": 4.135383851737849e-07, "epoch": 3.647742701968771, "percentage": 72.95, "elapsed_time": "1:07:28", "remaining_time": "0:25:00", "throughput": 10193.55, "total_tokens": 41269120}
{"current_steps": 42990, "total_steps": 58920, "loss": 0.0, "lr": 4.1329847937499717e-07, "epoch": 3.6481670061099796, "percentage": 72.96, "elapsed_time": "1:07:28", "remaining_time": "0:25:00", "throughput": 10193.72, "total_tokens": 41273664}
{"current_steps": 42995, "total_steps": 58920, "loss": 0.0, "lr": 4.130586250571496e-07, "epoch": 3.648591310251188, "percentage": 72.97, "elapsed_time": "1:07:29", "remaining_time": "0:24:59", "throughput": 10193.99, "total_tokens": 41278720}
{"current_steps": 43000, "total_steps": 58920, "loss": 0.0, "lr": 4.128188222412885e-07, "epoch": 3.6490156143923964, "percentage": 72.98, "elapsed_time": "1:07:29", "remaining_time": "0:24:59", "throughput": 10194.29, "total_tokens": 41283968}
{"current_steps": 43005, "total_steps": 58920, "loss": 0.0, "lr": 4.125790709484558e-07, "epoch": 3.649439918533605, "percentage": 72.99, "elapsed_time": "1:07:30", "remaining_time": "0:24:58", "throughput": 10194.52, "total_tokens": 41288768}
{"current_steps": 43010, "total_steps": 58920, "loss": 0.0, "lr": 4.1233937119968865e-07, "epoch": 3.6498642226748133, "percentage": 73.0, "elapsed_time": "1:07:30", "remaining_time": "0:24:58", "throughput": 10194.82, "total_tokens": 41293952}
{"current_steps": 43015, "total_steps": 58920, "loss": 0.0, "lr": 4.1209972301602003e-07, "epoch": 3.6502885268160217, "percentage": 73.01, "elapsed_time": "1:07:30", "remaining_time": "0:24:57", "throughput": 10195.01, "total_tokens": 41298624}
{"current_steps": 43020, "total_steps": 58920, "loss": 0.0, "lr": 4.1186012641847813e-07, "epoch": 3.65071283095723, "percentage": 73.01, "elapsed_time": "1:07:31", "remaining_time": "0:24:57", "throughput": 10195.23, "total_tokens": 41303360}
{"current_steps": 43025, "total_steps": 58920, "loss": 0.0, "lr": 4.1162058142808655e-07, "epoch": 3.6511371350984385, "percentage": 73.02, "elapsed_time": "1:07:31", "remaining_time": "0:24:56", "throughput": 10195.3, "total_tokens": 41307392}
{"current_steps": 43030, "total_steps": 58920, "loss": 0.0, "lr": 4.113810880658647e-07, "epoch": 3.651561439239647, "percentage": 73.03, "elapsed_time": "1:07:31", "remaining_time": "0:24:56", "throughput": 10195.57, "total_tokens": 41312384}
{"current_steps": 43035, "total_steps": 58920, "loss": 0.0, "lr": 4.1114164635282713e-07, "epoch": 3.6519857433808554, "percentage": 73.04, "elapsed_time": "1:07:32", "remaining_time": "0:24:55", "throughput": 10195.72, "total_tokens": 41316800}
{"current_steps": 43040, "total_steps": 58920, "loss": 0.0, "lr": 4.109022563099841e-07, "epoch": 3.6524100475220638, "percentage": 73.05, "elapsed_time": "1:07:32", "remaining_time": "0:24:55", "throughput": 10195.83, "total_tokens": 41321024}
{"current_steps": 43045, "total_steps": 58920, "loss": 0.0368, "lr": 4.1066291795834106e-07, "epoch": 3.652834351663272, "percentage": 73.06, "elapsed_time": "1:07:33", "remaining_time": "0:24:54", "throughput": 10196.02, "total_tokens": 41325632}
{"current_steps": 43050, "total_steps": 58920, "loss": 0.0, "lr": 4.1042363131889926e-07, "epoch": 3.6532586558044806, "percentage": 73.07, "elapsed_time": "1:07:33", "remaining_time": "0:24:54", "throughput": 10196.21, "total_tokens": 41330304}
{"current_steps": 43055, "total_steps": 58920, "loss": 0.0, "lr": 4.10184396412655e-07, "epoch": 3.653682959945689, "percentage": 73.07, "elapsed_time": "1:07:33", "remaining_time": "0:24:53", "throughput": 10196.5, "total_tokens": 41335424}
{"current_steps": 43060, "total_steps": 58920, "loss": 0.0, "lr": 4.0994521326060063e-07, "epoch": 3.6541072640868975, "percentage": 73.08, "elapsed_time": "1:07:34", "remaining_time": "0:24:53", "throughput": 10196.62, "total_tokens": 41339712}
{"current_steps": 43065, "total_steps": 58920, "loss": 0.0, "lr": 4.097060818837229e-07, "epoch": 3.654531568228106, "percentage": 73.09, "elapsed_time": "1:07:34", "remaining_time": "0:24:52", "throughput": 10196.8, "total_tokens": 41344256}
{"current_steps": 43070, "total_steps": 58920, "loss": 0.0, "lr": 4.0946700230300603e-07, "epoch": 3.6549558723693143, "percentage": 73.1, "elapsed_time": "1:07:35", "remaining_time": "0:24:52", "throughput": 10196.92, "total_tokens": 41348544}
{"current_steps": 43075, "total_steps": 58920, "loss": 0.0, "lr": 4.0922797453942724e-07, "epoch": 3.6553801765105227, "percentage": 73.11, "elapsed_time": "1:07:35", "remaining_time": "0:24:51", "throughput": 10197.15, "total_tokens": 41353408}
{"current_steps": 43080, "total_steps": 58920, "loss": 0.0, "lr": 4.0898899861396064e-07, "epoch": 3.655804480651731, "percentage": 73.12, "elapsed_time": "1:07:35", "remaining_time": "0:24:51", "throughput": 10197.52, "total_tokens": 41359040}
{"current_steps": 43085, "total_steps": 58920, "loss": 0.0, "lr": 4.0875007454757573e-07, "epoch": 3.6562287847929396, "percentage": 73.12, "elapsed_time": "1:07:36", "remaining_time": "0:24:50", "throughput": 10197.6, "total_tokens": 41363072}
{"current_steps": 43090, "total_steps": 58920, "loss": 0.0, "lr": 4.085112023612366e-07, "epoch": 3.656653088934148, "percentage": 73.13, "elapsed_time": "1:07:36", "remaining_time": "0:24:50", "throughput": 10197.89, "total_tokens": 41368256}
{"current_steps": 43095, "total_steps": 58920, "loss": 0.0, "lr": 4.0827238207590463e-07, "epoch": 3.6570773930753564, "percentage": 73.14, "elapsed_time": "1:07:36", "remaining_time": "0:24:49", "throughput": 10198.15, "total_tokens": 41373248}
{"current_steps": 43100, "total_steps": 58920, "loss": 0.0004, "lr": 4.08033613712534e-07, "epoch": 3.657501697216565, "percentage": 73.15, "elapsed_time": "1:07:37", "remaining_time": "0:24:49", "throughput": 10198.38, "total_tokens": 41378048}
{"current_steps": 43105, "total_steps": 58920, "loss": 0.0, "lr": 4.077948972920772e-07, "epoch": 3.6579260013577732, "percentage": 73.16, "elapsed_time": "1:07:37", "remaining_time": "0:24:48", "throughput": 10198.62, "total_tokens": 41382976}
{"current_steps": 43110, "total_steps": 58920, "loss": 0.0, "lr": 4.0755623283547923e-07, "epoch": 3.6583503054989817, "percentage": 73.17, "elapsed_time": "1:07:38", "remaining_time": "0:24:48", "throughput": 10198.79, "total_tokens": 41387520}
{"current_steps": 43115, "total_steps": 58920, "loss": 0.0, "lr": 4.073176203636832e-07, "epoch": 3.65877460964019, "percentage": 73.18, "elapsed_time": "1:07:38", "remaining_time": "0:24:47", "throughput": 10198.96, "total_tokens": 41392064}
{"current_steps": 43120, "total_steps": 58920, "loss": 0.0, "lr": 4.070790598976266e-07, "epoch": 3.6591989137813985, "percentage": 73.18, "elapsed_time": "1:07:38", "remaining_time": "0:24:47", "throughput": 10199.18, "total_tokens": 41396864}
{"current_steps": 43125, "total_steps": 58920, "loss": 0.0, "lr": 4.068405514582409e-07, "epoch": 3.659623217922607, "percentage": 73.19, "elapsed_time": "1:07:39", "remaining_time": "0:24:46", "throughput": 10199.41, "total_tokens": 41401664}
{"current_steps": 43130, "total_steps": 58920, "loss": 0.0, "lr": 4.0660209506645607e-07, "epoch": 3.6600475220638153, "percentage": 73.2, "elapsed_time": "1:07:39", "remaining_time": "0:24:46", "throughput": 10199.68, "total_tokens": 41406720}
{"current_steps": 43135, "total_steps": 58920, "loss": 0.0, "lr": 4.063636907431941e-07, "epoch": 3.6604718262050238, "percentage": 73.21, "elapsed_time": "1:07:39", "remaining_time": "0:24:45", "throughput": 10199.85, "total_tokens": 41411200}
{"current_steps": 43140, "total_steps": 58920, "loss": 0.0, "lr": 4.061253385093757e-07, "epoch": 3.660896130346232, "percentage": 73.22, "elapsed_time": "1:07:40", "remaining_time": "0:24:45", "throughput": 10200.06, "total_tokens": 41415936}
{"current_steps": 43145, "total_steps": 58920, "loss": 0.0, "lr": 4.05887038385914e-07, "epoch": 3.6613204344874406, "percentage": 73.23, "elapsed_time": "1:07:40", "remaining_time": "0:24:44", "throughput": 10200.26, "total_tokens": 41420672}
{"current_steps": 43150, "total_steps": 58920, "loss": 0.0, "lr": 4.0564879039372e-07, "epoch": 3.661744738628649, "percentage": 73.23, "elapsed_time": "1:07:41", "remaining_time": "0:24:44", "throughput": 10200.46, "total_tokens": 41425344}
{"current_steps": 43155, "total_steps": 58920, "loss": 0.0, "lr": 4.054105945536991e-07, "epoch": 3.6621690427698574, "percentage": 73.24, "elapsed_time": "1:07:41", "remaining_time": "0:24:43", "throughput": 10200.68, "total_tokens": 41430080}
{"current_steps": 43160, "total_steps": 58920, "loss": 0.0, "lr": 4.05172450886751e-07, "epoch": 3.662593346911066, "percentage": 73.25, "elapsed_time": "1:07:41", "remaining_time": "0:24:43", "throughput": 10200.83, "total_tokens": 41434560}
{"current_steps": 43165, "total_steps": 58920, "loss": 0.0, "lr": 4.049343594137734e-07, "epoch": 3.6630176510522743, "percentage": 73.26, "elapsed_time": "1:07:42", "remaining_time": "0:24:42", "throughput": 10200.99, "total_tokens": 41439040}
{"current_steps": 43170, "total_steps": 58920, "loss": 0.0, "lr": 4.046963201556567e-07, "epoch": 3.6634419551934827, "percentage": 73.27, "elapsed_time": "1:07:42", "remaining_time": "0:24:42", "throughput": 10201.1, "total_tokens": 41443264}
{"current_steps": 43175, "total_steps": 58920, "loss": 0.0, "lr": 4.044583331332888e-07, "epoch": 3.663866259334691, "percentage": 73.28, "elapsed_time": "1:07:43", "remaining_time": "0:24:41", "throughput": 10201.37, "total_tokens": 41448320}
{"current_steps": 43180, "total_steps": 58920, "loss": 0.0, "lr": 4.0422039836755207e-07, "epoch": 3.6642905634758995, "percentage": 73.29, "elapsed_time": "1:07:43", "remaining_time": "0:24:41", "throughput": 10201.57, "total_tokens": 41452992}
{"current_steps": 43185, "total_steps": 58920, "loss": 0.0, "lr": 4.039825158793243e-07, "epoch": 3.664714867617108, "percentage": 73.29, "elapsed_time": "1:07:43", "remaining_time": "0:24:40", "throughput": 10201.69, "total_tokens": 41457280}
{"current_steps": 43190, "total_steps": 58920, "loss": 0.0, "lr": 4.037446856894788e-07, "epoch": 3.6651391717583164, "percentage": 73.3, "elapsed_time": "1:07:44", "remaining_time": "0:24:40", "throughput": 10201.84, "total_tokens": 41461696}
{"current_steps": 43195, "total_steps": 58920, "loss": 0.0, "lr": 4.035069078188844e-07, "epoch": 3.665563475899525, "percentage": 73.31, "elapsed_time": "1:07:44", "remaining_time": "0:24:39", "throughput": 10201.99, "total_tokens": 41466112}
{"current_steps": 43200, "total_steps": 58920, "loss": 0.0, "lr": 4.032691822884057e-07, "epoch": 3.6659877800407332, "percentage": 73.32, "elapsed_time": "1:07:44", "remaining_time": "0:24:39", "throughput": 10202.1, "total_tokens": 41470336}
{"current_steps": 43205, "total_steps": 58920, "loss": 0.0, "lr": 4.030315091189008e-07, "epoch": 3.6664120841819416, "percentage": 73.33, "elapsed_time": "1:07:45", "remaining_time": "0:24:38", "throughput": 10202.29, "total_tokens": 41475008}
{"current_steps": 43210, "total_steps": 58920, "loss": 0.0, "lr": 4.027938883312262e-07, "epoch": 3.66683638832315, "percentage": 73.34, "elapsed_time": "1:07:45", "remaining_time": "0:24:38", "throughput": 10202.45, "total_tokens": 41479488}
{"current_steps": 43215, "total_steps": 58920, "loss": 0.0027, "lr": 4.0255631994623164e-07, "epoch": 3.6672606924643585, "percentage": 73.35, "elapsed_time": "1:07:46", "remaining_time": "0:24:37", "throughput": 10202.73, "total_tokens": 41484608}
{"current_steps": 43220, "total_steps": 58920, "loss": 0.0, "lr": 4.023188039847628e-07, "epoch": 3.667684996605567, "percentage": 73.35, "elapsed_time": "1:07:46", "remaining_time": "0:24:37", "throughput": 10202.85, "total_tokens": 41488896}
{"current_steps": 43225, "total_steps": 58920, "loss": 0.0, "lr": 4.020813404676612e-07, "epoch": 3.6681093007467753, "percentage": 73.36, "elapsed_time": "1:07:46", "remaining_time": "0:24:36", "throughput": 10203.03, "total_tokens": 41493504}
{"current_steps": 43230, "total_steps": 58920, "loss": 0.0, "lr": 4.0184392941576307e-07, "epoch": 3.6685336048879837, "percentage": 73.37, "elapsed_time": "1:07:47", "remaining_time": "0:24:36", "throughput": 10203.41, "total_tokens": 41499072}
{"current_steps": 43235, "total_steps": 58920, "loss": 0.0, "lr": 4.016065708499005e-07, "epoch": 3.668957909029192, "percentage": 73.38, "elapsed_time": "1:07:47", "remaining_time": "0:24:35", "throughput": 10203.66, "total_tokens": 41504064}
{"current_steps": 43240, "total_steps": 58920, "loss": 0.0, "lr": 4.0136926479090085e-07, "epoch": 3.6693822131704006, "percentage": 73.39, "elapsed_time": "1:07:47", "remaining_time": "0:24:35", "throughput": 10203.97, "total_tokens": 41509376}
{"current_steps": 43245, "total_steps": 58920, "loss": 0.0, "lr": 4.0113201125958694e-07, "epoch": 3.669806517311609, "percentage": 73.4, "elapsed_time": "1:07:48", "remaining_time": "0:24:34", "throughput": 10204.22, "total_tokens": 41514304}
{"current_steps": 43250, "total_steps": 58920, "loss": 0.0, "lr": 4.008948102767767e-07, "epoch": 3.6702308214528174, "percentage": 73.4, "elapsed_time": "1:07:48", "remaining_time": "0:24:34", "throughput": 10204.37, "total_tokens": 41518784}
{"current_steps": 43255, "total_steps": 58920, "loss": 0.0, "lr": 4.00657661863284e-07, "epoch": 3.670655125594026, "percentage": 73.41, "elapsed_time": "1:07:49", "remaining_time": "0:24:33", "throughput": 10204.56, "total_tokens": 41523456}
{"current_steps": 43260, "total_steps": 58920, "loss": 0.0, "lr": 4.0042056603991735e-07, "epoch": 3.6710794297352343, "percentage": 73.42, "elapsed_time": "1:07:49", "remaining_time": "0:24:33", "throughput": 10204.73, "total_tokens": 41528000}
{"current_steps": 43265, "total_steps": 58920, "loss": 0.0, "lr": 4.0018352282748135e-07, "epoch": 3.6715037338764427, "percentage": 73.43, "elapsed_time": "1:07:49", "remaining_time": "0:24:32", "throughput": 10204.91, "total_tokens": 41532544}
{"current_steps": 43270, "total_steps": 58920, "loss": 0.0, "lr": 3.9994653224677564e-07, "epoch": 3.671928038017651, "percentage": 73.44, "elapsed_time": "1:07:50", "remaining_time": "0:24:32", "throughput": 10205.07, "total_tokens": 41537024}
{"current_steps": 43275, "total_steps": 58920, "loss": 0.0, "lr": 3.9970959431859517e-07, "epoch": 3.6723523421588595, "percentage": 73.45, "elapsed_time": "1:07:50", "remaining_time": "0:24:31", "throughput": 10205.23, "total_tokens": 41541504}
{"current_steps": 43280, "total_steps": 58920, "loss": 0.0, "lr": 3.994727090637301e-07, "epoch": 3.672776646300068, "percentage": 73.46, "elapsed_time": "1:07:51", "remaining_time": "0:24:31", "throughput": 10205.53, "total_tokens": 41546752}
{"current_steps": 43285, "total_steps": 58920, "loss": 0.0, "lr": 3.992358765029674e-07, "epoch": 3.6732009504412764, "percentage": 73.46, "elapsed_time": "1:07:51", "remaining_time": "0:24:30", "throughput": 10205.65, "total_tokens": 41551040}
{"current_steps": 43290, "total_steps": 58920, "loss": 0.0, "lr": 3.989990966570871e-07, "epoch": 3.673625254582485, "percentage": 73.47, "elapsed_time": "1:07:51", "remaining_time": "0:24:30", "throughput": 10205.79, "total_tokens": 41555392}
{"current_steps": 43295, "total_steps": 58920, "loss": 0.0, "lr": 3.9876236954686615e-07, "epoch": 3.674049558723693, "percentage": 73.48, "elapsed_time": "1:07:52", "remaining_time": "0:24:29", "throughput": 10206.0, "total_tokens": 41560128}
{"current_steps": 43300, "total_steps": 58920, "loss": 0.0, "lr": 3.9852569519307646e-07, "epoch": 3.6744738628649016, "percentage": 73.49, "elapsed_time": "1:07:52", "remaining_time": "0:24:29", "throughput": 10206.21, "total_tokens": 41564864}
{"current_steps": 43305, "total_steps": 58920, "loss": 0.0, "lr": 3.982890736164851e-07, "epoch": 3.67489816700611, "percentage": 73.5, "elapsed_time": "1:07:52", "remaining_time": "0:24:28", "throughput": 10206.5, "total_tokens": 41570048}
{"current_steps": 43310, "total_steps": 58920, "loss": 0.0, "lr": 3.980525048378558e-07, "epoch": 3.6753224711473185, "percentage": 73.51, "elapsed_time": "1:07:53", "remaining_time": "0:24:28", "throughput": 10206.71, "total_tokens": 41574784}
{"current_steps": 43315, "total_steps": 58920, "loss": 0.0, "lr": 3.978159888779451e-07, "epoch": 3.675746775288527, "percentage": 73.51, "elapsed_time": "1:07:53", "remaining_time": "0:24:27", "throughput": 10207.03, "total_tokens": 41580096}
{"current_steps": 43320, "total_steps": 58920, "loss": 0.0, "lr": 3.97579525757508e-07, "epoch": 3.6761710794297353, "percentage": 73.52, "elapsed_time": "1:07:54", "remaining_time": "0:24:27", "throughput": 10207.19, "total_tokens": 41584640}
{"current_steps": 43325, "total_steps": 58920, "loss": 0.0, "lr": 3.9734311549729204e-07, "epoch": 3.6765953835709437, "percentage": 73.53, "elapsed_time": "1:07:54", "remaining_time": "0:24:26", "throughput": 10207.37, "total_tokens": 41589184}
{"current_steps": 43330, "total_steps": 58920, "loss": 0.0, "lr": 3.9710675811804186e-07, "epoch": 3.677019687712152, "percentage": 73.54, "elapsed_time": "1:07:54", "remaining_time": "0:24:26", "throughput": 10207.53, "total_tokens": 41593664}
{"current_steps": 43335, "total_steps": 58920, "loss": 0.0, "lr": 3.9687045364049686e-07, "epoch": 3.6774439918533606, "percentage": 73.55, "elapsed_time": "1:07:55", "remaining_time": "0:24:25", "throughput": 10207.71, "total_tokens": 41598208}
{"current_steps": 43340, "total_steps": 58920, "loss": 0.0, "lr": 3.966342020853917e-07, "epoch": 3.677868295994569, "percentage": 73.56, "elapsed_time": "1:07:55", "remaining_time": "0:24:25", "throughput": 10207.91, "total_tokens": 41602880}
{"current_steps": 43345, "total_steps": 58920, "loss": 0.0, "lr": 3.963980034734574e-07, "epoch": 3.6782926001357774, "percentage": 73.57, "elapsed_time": "1:07:55", "remaining_time": "0:24:24", "throughput": 10208.03, "total_tokens": 41607168}
{"current_steps": 43350, "total_steps": 58920, "loss": 0.0, "lr": 3.9616185782541845e-07, "epoch": 3.678716904276986, "percentage": 73.57, "elapsed_time": "1:07:56", "remaining_time": "0:24:24", "throughput": 10208.23, "total_tokens": 41611840}
{"current_steps": 43355, "total_steps": 58920, "loss": 0.0493, "lr": 3.95925765161997e-07, "epoch": 3.6791412084181943, "percentage": 73.58, "elapsed_time": "1:07:56", "remaining_time": "0:24:23", "throughput": 10208.43, "total_tokens": 41616512}
{"current_steps": 43360, "total_steps": 58920, "loss": 0.0, "lr": 3.9568972550390787e-07, "epoch": 3.6795655125594027, "percentage": 73.59, "elapsed_time": "1:07:57", "remaining_time": "0:24:23", "throughput": 10208.87, "total_tokens": 41622528}
{"current_steps": 43365, "total_steps": 58920, "loss": 0.0, "lr": 3.9545373887186395e-07, "epoch": 3.679989816700611, "percentage": 73.6, "elapsed_time": "1:07:57", "remaining_time": "0:24:22", "throughput": 10209.11, "total_tokens": 41627392}
{"current_steps": 43370, "total_steps": 58920, "loss": 0.0586, "lr": 3.952178052865721e-07, "epoch": 3.6804141208418195, "percentage": 73.61, "elapsed_time": "1:07:57", "remaining_time": "0:24:22", "throughput": 10209.44, "total_tokens": 41632768}
{"current_steps": 43375, "total_steps": 58920, "loss": 0.0001, "lr": 3.949819247687335e-07, "epoch": 3.680838424983028, "percentage": 73.62, "elapsed_time": "1:07:58", "remaining_time": "0:24:21", "throughput": 10209.6, "total_tokens": 41637312}
{"current_steps": 43380, "total_steps": 58920, "loss": 0.0189, "lr": 3.9474609733904727e-07, "epoch": 3.6812627291242364, "percentage": 73.63, "elapsed_time": "1:07:58", "remaining_time": "0:24:21", "throughput": 10209.76, "total_tokens": 41641792}
{"current_steps": 43385, "total_steps": 58920, "loss": 0.0, "lr": 3.945103230182051e-07, "epoch": 3.6816870332654448, "percentage": 73.63, "elapsed_time": "1:07:59", "remaining_time": "0:24:20", "throughput": 10210.0, "total_tokens": 41646720}
{"current_steps": 43390, "total_steps": 58920, "loss": 0.0, "lr": 3.9427460182689634e-07, "epoch": 3.682111337406653, "percentage": 73.64, "elapsed_time": "1:07:59", "remaining_time": "0:24:20", "throughput": 10210.27, "total_tokens": 41651776}
{"current_steps": 43395, "total_steps": 58920, "loss": 0.0, "lr": 3.940389337858042e-07, "epoch": 3.6825356415478616, "percentage": 73.65, "elapsed_time": "1:07:59", "remaining_time": "0:24:19", "throughput": 10210.44, "total_tokens": 41656384}
{"current_steps": 43400, "total_steps": 58920, "loss": 0.0034, "lr": 3.938033189156079e-07, "epoch": 3.68295994568907, "percentage": 73.66, "elapsed_time": "1:08:00", "remaining_time": "0:24:19", "throughput": 10210.7, "total_tokens": 41661376}
{"current_steps": 43405, "total_steps": 58920, "loss": 0.0, "lr": 3.9356775723698167e-07, "epoch": 3.6833842498302785, "percentage": 73.67, "elapsed_time": "1:08:00", "remaining_time": "0:24:18", "throughput": 10210.92, "total_tokens": 41666176}
{"current_steps": 43410, "total_steps": 58920, "loss": 0.0, "lr": 3.9333224877059526e-07, "epoch": 3.683808553971487, "percentage": 73.68, "elapsed_time": "1:08:00", "remaining_time": "0:24:18", "throughput": 10211.13, "total_tokens": 41670976}
{"current_steps": 43415, "total_steps": 58920, "loss": 0.0005, "lr": 3.9309679353711403e-07, "epoch": 3.6842328581126953, "percentage": 73.68, "elapsed_time": "1:08:01", "remaining_time": "0:24:17", "throughput": 10211.29, "total_tokens": 41675456}
{"current_steps": 43420, "total_steps": 58920, "loss": 0.0, "lr": 3.928613915571971e-07, "epoch": 3.6846571622539037, "percentage": 73.69, "elapsed_time": "1:08:01", "remaining_time": "0:24:17", "throughput": 10211.48, "total_tokens": 41680128}
{"current_steps": 43425, "total_steps": 58920, "loss": 0.0, "lr": 3.9262604285150145e-07, "epoch": 3.685081466395112, "percentage": 73.7, "elapsed_time": "1:08:02", "remaining_time": "0:24:16", "throughput": 10211.64, "total_tokens": 41684608}
{"current_steps": 43430, "total_steps": 58920, "loss": 0.0, "lr": 3.9239074744067767e-07, "epoch": 3.6855057705363206, "percentage": 73.71, "elapsed_time": "1:08:02", "remaining_time": "0:24:16", "throughput": 10211.87, "total_tokens": 41689472}
{"current_steps": 43435, "total_steps": 58920, "loss": 0.0, "lr": 3.92155505345372e-07, "epoch": 3.685930074677529, "percentage": 73.72, "elapsed_time": "1:08:02", "remaining_time": "0:24:15", "throughput": 10212.11, "total_tokens": 41694400}
{"current_steps": 43440, "total_steps": 58920, "loss": 0.0, "lr": 3.9192031658622606e-07, "epoch": 3.6863543788187374, "percentage": 73.73, "elapsed_time": "1:08:03", "remaining_time": "0:24:15", "throughput": 10212.31, "total_tokens": 41699072}
{"current_steps": 43445, "total_steps": 58920, "loss": 0.0, "lr": 3.9168518118387695e-07, "epoch": 3.686778682959946, "percentage": 73.74, "elapsed_time": "1:08:03", "remaining_time": "0:24:14", "throughput": 10212.55, "total_tokens": 41704000}
{"current_steps": 43450, "total_steps": 58920, "loss": 0.0222, "lr": 3.9145009915895687e-07, "epoch": 3.6872029871011542, "percentage": 73.74, "elapsed_time": "1:08:03", "remaining_time": "0:24:14", "throughput": 10212.72, "total_tokens": 41708480}
{"current_steps": 43455, "total_steps": 58920, "loss": 0.0, "lr": 3.9121507053209333e-07, "epoch": 3.6876272912423627, "percentage": 73.75, "elapsed_time": "1:08:04", "remaining_time": "0:24:13", "throughput": 10212.97, "total_tokens": 41713408}
{"current_steps": 43460, "total_steps": 58920, "loss": 0.0, "lr": 3.9098009532390953e-07, "epoch": 3.688051595383571, "percentage": 73.76, "elapsed_time": "1:08:04", "remaining_time": "0:24:13", "throughput": 10213.21, "total_tokens": 41718272}
{"current_steps": 43465, "total_steps": 58920, "loss": 0.0, "lr": 3.9074517355502336e-07, "epoch": 3.6884758995247795, "percentage": 73.77, "elapsed_time": "1:08:05", "remaining_time": "0:24:12", "throughput": 10213.66, "total_tokens": 41724352}
{"current_steps": 43470, "total_steps": 58920, "loss": 0.0, "lr": 3.905103052460486e-07, "epoch": 3.688900203665988, "percentage": 73.78, "elapsed_time": "1:08:05", "remaining_time": "0:24:12", "throughput": 10213.84, "total_tokens": 41728960}
{"current_steps": 43475, "total_steps": 58920, "loss": 0.0, "lr": 3.902754904175939e-07, "epoch": 3.6893245078071963, "percentage": 73.79, "elapsed_time": "1:08:05", "remaining_time": "0:24:11", "throughput": 10214.12, "total_tokens": 41734144}
{"current_steps": 43480, "total_steps": 58920, "loss": 0.0, "lr": 3.9004072909026355e-07, "epoch": 3.6897488119484048, "percentage": 73.79, "elapsed_time": "1:08:06", "remaining_time": "0:24:11", "throughput": 10214.37, "total_tokens": 41739072}
{"current_steps": 43485, "total_steps": 58920, "loss": 0.0, "lr": 3.89806021284657e-07, "epoch": 3.690173116089613, "percentage": 73.8, "elapsed_time": "1:08:06", "remaining_time": "0:24:10", "throughput": 10214.59, "total_tokens": 41743872}
{"current_steps": 43490, "total_steps": 58920, "loss": 0.0419, "lr": 3.8957136702136894e-07, "epoch": 3.6905974202308216, "percentage": 73.81, "elapsed_time": "1:08:07", "remaining_time": "0:24:10", "throughput": 10214.77, "total_tokens": 41748480}
{"current_steps": 43495, "total_steps": 58920, "loss": 0.0, "lr": 3.8933676632098953e-07, "epoch": 3.69102172437203, "percentage": 73.82, "elapsed_time": "1:08:07", "remaining_time": "0:24:09", "throughput": 10214.93, "total_tokens": 41752960}
{"current_steps": 43500, "total_steps": 58920, "loss": 0.0, "lr": 3.8910221920410414e-07, "epoch": 3.6914460285132384, "percentage": 73.83, "elapsed_time": "1:08:07", "remaining_time": "0:24:09", "throughput": 10215.06, "total_tokens": 41757312}
{"current_steps": 43505, "total_steps": 58920, "loss": 0.0, "lr": 3.888677256912932e-07, "epoch": 3.691870332654447, "percentage": 73.84, "elapsed_time": "1:08:08", "remaining_time": "0:24:08", "throughput": 10215.3, "total_tokens": 41762240}
{"current_steps": 43510, "total_steps": 58920, "loss": 0.0, "lr": 3.8863328580313304e-07, "epoch": 3.6922946367956553, "percentage": 73.85, "elapsed_time": "1:08:08", "remaining_time": "0:24:08", "throughput": 10215.48, "total_tokens": 41766848}
{"current_steps": 43515, "total_steps": 58920, "loss": 0.0, "lr": 3.8839889956019454e-07, "epoch": 3.6927189409368637, "percentage": 73.85, "elapsed_time": "1:08:08", "remaining_time": "0:24:07", "throughput": 10215.7, "total_tokens": 41771648}
{"current_steps": 43520, "total_steps": 58920, "loss": 0.0, "lr": 3.8816456698304425e-07, "epoch": 3.693143245078072, "percentage": 73.86, "elapsed_time": "1:08:09", "remaining_time": "0:24:07", "throughput": 10215.92, "total_tokens": 41776448}
{"current_steps": 43525, "total_steps": 58920, "loss": 0.0001, "lr": 3.879302880922447e-07, "epoch": 3.6935675492192805, "percentage": 73.87, "elapsed_time": "1:08:09", "remaining_time": "0:24:06", "throughput": 10216.05, "total_tokens": 41780800}
{"current_steps": 43530, "total_steps": 58920, "loss": 0.0, "lr": 3.87696062908352e-07, "epoch": 3.693991853360489, "percentage": 73.88, "elapsed_time": "1:08:10", "remaining_time": "0:24:06", "throughput": 10216.42, "total_tokens": 41786432}
{"current_steps": 43535, "total_steps": 58920, "loss": 0.0, "lr": 3.8746189145191964e-07, "epoch": 3.6944161575016974, "percentage": 73.89, "elapsed_time": "1:08:10", "remaining_time": "0:24:05", "throughput": 10216.61, "total_tokens": 41791040}
{"current_steps": 43540, "total_steps": 58920, "loss": 0.0, "lr": 3.8722777374349437e-07, "epoch": 3.6948404616429054, "percentage": 73.9, "elapsed_time": "1:08:10", "remaining_time": "0:24:05", "throughput": 10216.96, "total_tokens": 41796544}
{"current_steps": 43545, "total_steps": 58920, "loss": 0.0, "lr": 3.8699370980361966e-07, "epoch": 3.6952647657841142, "percentage": 73.91, "elapsed_time": "1:08:11", "remaining_time": "0:24:04", "throughput": 10217.2, "total_tokens": 41801472}
{"current_steps": 43550, "total_steps": 58920, "loss": 0.0, "lr": 3.867596996528336e-07, "epoch": 3.695689069925322, "percentage": 73.91, "elapsed_time": "1:08:11", "remaining_time": "0:24:04", "throughput": 10217.36, "total_tokens": 41805952}
{"current_steps": 43555, "total_steps": 58920, "loss": 0.0, "lr": 3.8652574331166945e-07, "epoch": 3.696113374066531, "percentage": 73.92, "elapsed_time": "1:08:12", "remaining_time": "0:24:03", "throughput": 10217.49, "total_tokens": 41810240}
{"current_steps": 43560, "total_steps": 58920, "loss": 0.0165, "lr": 3.8629184080065716e-07, "epoch": 3.696537678207739, "percentage": 73.93, "elapsed_time": "1:08:12", "remaining_time": "0:24:03", "throughput": 10217.71, "total_tokens": 41815040}
{"current_steps": 43565, "total_steps": 58920, "loss": 0.0, "lr": 3.860579921403192e-07, "epoch": 3.696961982348948, "percentage": 73.94, "elapsed_time": "1:08:12", "remaining_time": "0:24:02", "throughput": 10218.03, "total_tokens": 41820416}
{"current_steps": 43570, "total_steps": 58920, "loss": 0.0, "lr": 3.8582419735117655e-07, "epoch": 3.697386286490156, "percentage": 73.95, "elapsed_time": "1:08:13", "remaining_time": "0:24:02", "throughput": 10218.24, "total_tokens": 41825216}
{"current_steps": 43575, "total_steps": 58920, "loss": 0.0, "lr": 3.855904564537429e-07, "epoch": 3.6978105906313647, "percentage": 73.96, "elapsed_time": "1:08:13", "remaining_time": "0:24:01", "throughput": 10218.48, "total_tokens": 41830080}
{"current_steps": 43580, "total_steps": 58920, "loss": 0.0, "lr": 3.853567694685279e-07, "epoch": 3.6982348947725727, "percentage": 73.96, "elapsed_time": "1:08:13", "remaining_time": "0:24:01", "throughput": 10218.86, "total_tokens": 41835776}
{"current_steps": 43585, "total_steps": 58920, "loss": 0.0, "lr": 3.851231364160379e-07, "epoch": 3.6986591989137816, "percentage": 73.97, "elapsed_time": "1:08:14", "remaining_time": "0:24:00", "throughput": 10219.02, "total_tokens": 41840256}
{"current_steps": 43590, "total_steps": 58920, "loss": 0.0, "lr": 3.84889557316772e-07, "epoch": 3.6990835030549896, "percentage": 73.98, "elapsed_time": "1:08:14", "remaining_time": "0:24:00", "throughput": 10219.24, "total_tokens": 41845056}
{"current_steps": 43595, "total_steps": 58920, "loss": 0.0, "lr": 3.8465603219122733e-07, "epoch": 3.6995078071961984, "percentage": 73.99, "elapsed_time": "1:08:15", "remaining_time": "0:23:59", "throughput": 10219.42, "total_tokens": 41849664}
{"current_steps": 43600, "total_steps": 58920, "loss": 0.0, "lr": 3.8442256105989346e-07, "epoch": 3.6999321113374064, "percentage": 74.0, "elapsed_time": "1:08:15", "remaining_time": "0:23:59", "throughput": 10219.68, "total_tokens": 41854720}
{"current_steps": 43605, "total_steps": 58920, "loss": 0.0, "lr": 3.8418914394325765e-07, "epoch": 3.7003564154786153, "percentage": 74.01, "elapsed_time": "1:08:15", "remaining_time": "0:23:58", "throughput": 10219.94, "total_tokens": 41859776}
{"current_steps": 43610, "total_steps": 58920, "loss": 0.0, "lr": 3.83955780861801e-07, "epoch": 3.7007807196198232, "percentage": 74.02, "elapsed_time": "1:08:16", "remaining_time": "0:23:58", "throughput": 10220.3, "total_tokens": 41865344}
{"current_steps": 43615, "total_steps": 58920, "loss": 0.0, "lr": 3.8372247183600046e-07, "epoch": 3.701205023761032, "percentage": 74.02, "elapsed_time": "1:08:16", "remaining_time": "0:23:57", "throughput": 10220.5, "total_tokens": 41870016}
{"current_steps": 43620, "total_steps": 58920, "loss": 0.0478, "lr": 3.834892168863283e-07, "epoch": 3.70162932790224, "percentage": 74.03, "elapsed_time": "1:08:17", "remaining_time": "0:23:57", "throughput": 10220.82, "total_tokens": 41875392}
{"current_steps": 43625, "total_steps": 58920, "loss": 0.0, "lr": 3.8325601603325076e-07, "epoch": 3.702053632043449, "percentage": 74.04, "elapsed_time": "1:08:17", "remaining_time": "0:23:56", "throughput": 10221.2, "total_tokens": 41881088}
{"current_steps": 43630, "total_steps": 58920, "loss": 0.0, "lr": 3.830228692972317e-07, "epoch": 3.702477936184657, "percentage": 74.05, "elapsed_time": "1:08:17", "remaining_time": "0:23:56", "throughput": 10221.37, "total_tokens": 41885696}
{"current_steps": 43635, "total_steps": 58920, "loss": 0.0, "lr": 3.827897766987277e-07, "epoch": 3.702902240325866, "percentage": 74.06, "elapsed_time": "1:08:18", "remaining_time": "0:23:55", "throughput": 10221.54, "total_tokens": 41890240}
{"current_steps": 43640, "total_steps": 58920, "loss": 0.0, "lr": 3.8255673825819256e-07, "epoch": 3.7033265444670738, "percentage": 74.07, "elapsed_time": "1:08:18", "remaining_time": "0:23:55", "throughput": 10221.83, "total_tokens": 41895424}
{"current_steps": 43645, "total_steps": 58920, "loss": 0.0, "lr": 3.8232375399607444e-07, "epoch": 3.7037508486082826, "percentage": 74.08, "elapsed_time": "1:08:18", "remaining_time": "0:23:54", "throughput": 10222.0, "total_tokens": 41899968}
{"current_steps": 43650, "total_steps": 58920, "loss": 0.0, "lr": 3.8209082393281676e-07, "epoch": 3.7041751527494906, "percentage": 74.08, "elapsed_time": "1:08:19", "remaining_time": "0:23:54", "throughput": 10222.23, "total_tokens": 41904896}
{"current_steps": 43655, "total_steps": 58920, "loss": 0.0, "lr": 3.818579480888584e-07, "epoch": 3.7045994568906995, "percentage": 74.09, "elapsed_time": "1:08:19", "remaining_time": "0:23:53", "throughput": 10222.49, "total_tokens": 41909888}
{"current_steps": 43660, "total_steps": 58920, "loss": 0.0, "lr": 3.816251264846333e-07, "epoch": 3.7050237610319074, "percentage": 74.1, "elapsed_time": "1:08:20", "remaining_time": "0:23:53", "throughput": 10222.62, "total_tokens": 41914240}
{"current_steps": 43665, "total_steps": 58920, "loss": 0.0, "lr": 3.8139235914057066e-07, "epoch": 3.7054480651731163, "percentage": 74.11, "elapsed_time": "1:08:20", "remaining_time": "0:23:52", "throughput": 10222.92, "total_tokens": 41919488}
{"current_steps": 43670, "total_steps": 58920, "loss": 0.0, "lr": 3.811596460770951e-07, "epoch": 3.7058723693143243, "percentage": 74.12, "elapsed_time": "1:08:20", "remaining_time": "0:23:52", "throughput": 10223.1, "total_tokens": 41924096}
{"current_steps": 43675, "total_steps": 58920, "loss": 0.0, "lr": 3.8092698731462625e-07, "epoch": 3.706296673455533, "percentage": 74.13, "elapsed_time": "1:08:21", "remaining_time": "0:23:51", "throughput": 10223.31, "total_tokens": 41928832}
{"current_steps": 43680, "total_steps": 58920, "loss": 0.0, "lr": 3.8069438287357903e-07, "epoch": 3.706720977596741, "percentage": 74.13, "elapsed_time": "1:08:21", "remaining_time": "0:23:51", "throughput": 10223.48, "total_tokens": 41933376}
{"current_steps": 43685, "total_steps": 58920, "loss": 0.0, "lr": 3.8046183277436386e-07, "epoch": 3.70714528173795, "percentage": 74.14, "elapsed_time": "1:08:22", "remaining_time": "0:23:50", "throughput": 10223.79, "total_tokens": 41938688}
{"current_steps": 43690, "total_steps": 58920, "loss": 0.0005, "lr": 3.802293370373859e-07, "epoch": 3.707569585879158, "percentage": 74.15, "elapsed_time": "1:08:22", "remaining_time": "0:23:50", "throughput": 10224.07, "total_tokens": 41943808}
{"current_steps": 43695, "total_steps": 58920, "loss": 0.0, "lr": 3.7999689568304607e-07, "epoch": 3.707993890020367, "percentage": 74.16, "elapsed_time": "1:08:22", "remaining_time": "0:23:49", "throughput": 10224.21, "total_tokens": 41948224}
{"current_steps": 43700, "total_steps": 58920, "loss": 0.0, "lr": 3.7976450873174007e-07, "epoch": 3.708418194161575, "percentage": 74.17, "elapsed_time": "1:08:23", "remaining_time": "0:23:49", "throughput": 10224.44, "total_tokens": 41953088}
{"current_steps": 43705, "total_steps": 58920, "loss": 0.0014, "lr": 3.7953217620385904e-07, "epoch": 3.7088424983027837, "percentage": 74.18, "elapsed_time": "1:08:23", "remaining_time": "0:23:48", "throughput": 10224.64, "total_tokens": 41957760}
{"current_steps": 43710, "total_steps": 58920, "loss": 0.0, "lr": 3.792998981197894e-07, "epoch": 3.7092668024439917, "percentage": 74.19, "elapsed_time": "1:08:24", "remaining_time": "0:23:48", "throughput": 10225.03, "total_tokens": 41963520}
{"current_steps": 43715, "total_steps": 58920, "loss": 0.0, "lr": 3.790676744999126e-07, "epoch": 3.7096911065852005, "percentage": 74.19, "elapsed_time": "1:08:24", "remaining_time": "0:23:47", "throughput": 10225.36, "total_tokens": 41968960}
{"current_steps": 43720, "total_steps": 58920, "loss": 0.0059, "lr": 3.788355053646055e-07, "epoch": 3.7101154107264085, "percentage": 74.2, "elapsed_time": "1:08:24", "remaining_time": "0:23:47", "throughput": 10225.49, "total_tokens": 41973312}
{"current_steps": 43725, "total_steps": 58920, "loss": 0.0, "lr": 3.786033907342402e-07, "epoch": 3.7105397148676174, "percentage": 74.21, "elapsed_time": "1:08:25", "remaining_time": "0:23:46", "throughput": 10225.71, "total_tokens": 41978112}
{"current_steps": 43730, "total_steps": 58920, "loss": 0.0542, "lr": 3.7837133062918383e-07, "epoch": 3.7109640190088253, "percentage": 74.22, "elapsed_time": "1:08:25", "remaining_time": "0:23:46", "throughput": 10225.93, "total_tokens": 41982976}
{"current_steps": 43735, "total_steps": 58920, "loss": 0.0, "lr": 3.781393250697984e-07, "epoch": 3.711388323150034, "percentage": 74.23, "elapsed_time": "1:08:25", "remaining_time": "0:23:45", "throughput": 10226.21, "total_tokens": 41988032}
{"current_steps": 43740, "total_steps": 58920, "loss": 0.0, "lr": 3.779073740764426e-07, "epoch": 3.711812627291242, "percentage": 74.24, "elapsed_time": "1:08:26", "remaining_time": "0:23:45", "throughput": 10226.5, "total_tokens": 41993280}
{"current_steps": 43745, "total_steps": 58920, "loss": 0.0, "lr": 3.776754776694684e-07, "epoch": 3.712236931432451, "percentage": 74.24, "elapsed_time": "1:08:26", "remaining_time": "0:23:44", "throughput": 10226.71, "total_tokens": 41998016}
{"current_steps": 43750, "total_steps": 58920, "loss": 0.0, "lr": 3.774436358692241e-07, "epoch": 3.712661235573659, "percentage": 74.25, "elapsed_time": "1:08:27", "remaining_time": "0:23:44", "throughput": 10226.89, "total_tokens": 42002624}
{"current_steps": 43755, "total_steps": 58920, "loss": 0.0, "lr": 3.7721184869605314e-07, "epoch": 3.713085539714868, "percentage": 74.26, "elapsed_time": "1:08:27", "remaining_time": "0:23:43", "throughput": 10227.17, "total_tokens": 42007744}
{"current_steps": 43760, "total_steps": 58920, "loss": 0.0, "lr": 3.769801161702938e-07, "epoch": 3.713509843856076, "percentage": 74.27, "elapsed_time": "1:08:27", "remaining_time": "0:23:43", "throughput": 10227.57, "total_tokens": 42013696}
{"current_steps": 43765, "total_steps": 58920, "loss": 0.0, "lr": 3.7674843831227985e-07, "epoch": 3.7139341479972847, "percentage": 74.28, "elapsed_time": "1:08:28", "remaining_time": "0:23:42", "throughput": 10227.85, "total_tokens": 42018816}
{"current_steps": 43770, "total_steps": 58920, "loss": 0.0, "lr": 3.765168151423399e-07, "epoch": 3.7143584521384927, "percentage": 74.29, "elapsed_time": "1:08:28", "remaining_time": "0:23:42", "throughput": 10228.03, "total_tokens": 42023488}
{"current_steps": 43775, "total_steps": 58920, "loss": 0.0, "lr": 3.76285246680799e-07, "epoch": 3.7147827562797016, "percentage": 74.3, "elapsed_time": "1:08:29", "remaining_time": "0:23:41", "throughput": 10228.35, "total_tokens": 42028928}
{"current_steps": 43780, "total_steps": 58920, "loss": 0.0, "lr": 3.7605373294797515e-07, "epoch": 3.7152070604209095, "percentage": 74.3, "elapsed_time": "1:08:29", "remaining_time": "0:23:41", "throughput": 10228.55, "total_tokens": 42033664}
{"current_steps": 43785, "total_steps": 58920, "loss": 0.0, "lr": 3.758222739641841e-07, "epoch": 3.7156313645621184, "percentage": 74.31, "elapsed_time": "1:08:29", "remaining_time": "0:23:40", "throughput": 10228.72, "total_tokens": 42038208}
{"current_steps": 43790, "total_steps": 58920, "loss": 0.0, "lr": 3.7559086974973466e-07, "epoch": 3.7160556687033264, "percentage": 74.32, "elapsed_time": "1:08:30", "remaining_time": "0:23:40", "throughput": 10228.91, "total_tokens": 42042816}
{"current_steps": 43795, "total_steps": 58920, "loss": 0.0, "lr": 3.753595203249316e-07, "epoch": 3.7164799728445352, "percentage": 74.33, "elapsed_time": "1:08:30", "remaining_time": "0:23:39", "throughput": 10229.47, "total_tokens": 42049536}
{"current_steps": 43800, "total_steps": 58920, "loss": 0.0, "lr": 3.7512822571007594e-07, "epoch": 3.716904276985743, "percentage": 74.34, "elapsed_time": "1:08:31", "remaining_time": "0:23:39", "throughput": 10229.69, "total_tokens": 42054400}
{"current_steps": 43805, "total_steps": 58920, "loss": 0.0, "lr": 3.748969859254618e-07, "epoch": 3.7173285811269516, "percentage": 74.35, "elapsed_time": "1:08:31", "remaining_time": "0:23:38", "throughput": 10229.82, "total_tokens": 42058688}
{"current_steps": 43810, "total_steps": 58920, "loss": 0.0, "lr": 3.74665800991381e-07, "epoch": 3.71775288526816, "percentage": 74.36, "elapsed_time": "1:08:31", "remaining_time": "0:23:38", "throughput": 10229.93, "total_tokens": 42062976}
{"current_steps": 43815, "total_steps": 58920, "loss": 0.0, "lr": 3.7443467092811766e-07, "epoch": 3.7181771894093685, "percentage": 74.36, "elapsed_time": "1:08:32", "remaining_time": "0:23:37", "throughput": 10230.15, "total_tokens": 42067840}
{"current_steps": 43820, "total_steps": 58920, "loss": 0.0, "lr": 3.7420359575595363e-07, "epoch": 3.718601493550577, "percentage": 74.37, "elapsed_time": "1:08:32", "remaining_time": "0:23:37", "throughput": 10230.37, "total_tokens": 42072640}
{"current_steps": 43825, "total_steps": 58920, "loss": 0.0, "lr": 3.73972575495165e-07, "epoch": 3.7190257976917853, "percentage": 74.38, "elapsed_time": "1:08:32", "remaining_time": "0:23:36", "throughput": 10230.53, "total_tokens": 42077184}
{"current_steps": 43830, "total_steps": 58920, "loss": 0.0, "lr": 3.7374161016602203e-07, "epoch": 3.7194501018329937, "percentage": 74.39, "elapsed_time": "1:08:33", "remaining_time": "0:23:36", "throughput": 10230.68, "total_tokens": 42081664}
{"current_steps": 43835, "total_steps": 58920, "loss": 0.0277, "lr": 3.7351069978879224e-07, "epoch": 3.719874405974202, "percentage": 74.4, "elapsed_time": "1:08:33", "remaining_time": "0:23:35", "throughput": 10230.9, "total_tokens": 42086464}
{"current_steps": 43840, "total_steps": 58920, "loss": 0.0, "lr": 3.732798443837359e-07, "epoch": 3.7202987101154106, "percentage": 74.41, "elapsed_time": "1:08:34", "remaining_time": "0:23:35", "throughput": 10231.1, "total_tokens": 42091264}
{"current_steps": 43845, "total_steps": 58920, "loss": 0.0, "lr": 3.7304904397111125e-07, "epoch": 3.720723014256619, "percentage": 74.41, "elapsed_time": "1:08:34", "remaining_time": "0:23:34", "throughput": 10231.43, "total_tokens": 42096704}
{"current_steps": 43850, "total_steps": 58920, "loss": 0.0, "lr": 3.7281829857116866e-07, "epoch": 3.7211473183978274, "percentage": 74.42, "elapsed_time": "1:08:34", "remaining_time": "0:23:34", "throughput": 10231.73, "total_tokens": 42101888}
{"current_steps": 43855, "total_steps": 58920, "loss": 0.0, "lr": 3.7258760820415626e-07, "epoch": 3.721571622539036, "percentage": 74.43, "elapsed_time": "1:08:35", "remaining_time": "0:23:33", "throughput": 10231.89, "total_tokens": 42106432}
{"current_steps": 43860, "total_steps": 58920, "loss": 0.0, "lr": 3.7235697289031597e-07, "epoch": 3.7219959266802443, "percentage": 74.44, "elapsed_time": "1:08:35", "remaining_time": "0:23:33", "throughput": 10232.15, "total_tokens": 42111424}
{"current_steps": 43865, "total_steps": 58920, "loss": 0.0529, "lr": 3.721263926498852e-07, "epoch": 3.7224202308214527, "percentage": 74.45, "elapsed_time": "1:08:35", "remaining_time": "0:23:32", "throughput": 10232.32, "total_tokens": 42115968}
{"current_steps": 43870, "total_steps": 58920, "loss": 0.0, "lr": 3.71895867503097e-07, "epoch": 3.722844534962661, "percentage": 74.46, "elapsed_time": "1:08:36", "remaining_time": "0:23:32", "throughput": 10232.48, "total_tokens": 42120512}
{"current_steps": 43875, "total_steps": 58920, "loss": 0.0069, "lr": 3.716653974701779e-07, "epoch": 3.7232688391038695, "percentage": 74.47, "elapsed_time": "1:08:36", "remaining_time": "0:23:31", "throughput": 10232.68, "total_tokens": 42125312}
{"current_steps": 43880, "total_steps": 58920, "loss": 0.0, "lr": 3.7143498257135184e-07, "epoch": 3.723693143245078, "percentage": 74.47, "elapsed_time": "1:08:37", "remaining_time": "0:23:31", "throughput": 10232.85, "total_tokens": 42129856}
{"current_steps": 43885, "total_steps": 58920, "loss": 0.0, "lr": 3.7120462282683674e-07, "epoch": 3.7241174473862864, "percentage": 74.48, "elapsed_time": "1:08:37", "remaining_time": "0:23:30", "throughput": 10233.06, "total_tokens": 42134720}
{"current_steps": 43890, "total_steps": 58920, "loss": 0.0, "lr": 3.709743182568458e-07, "epoch": 3.724541751527495, "percentage": 74.49, "elapsed_time": "1:08:37", "remaining_time": "0:23:30", "throughput": 10233.25, "total_tokens": 42139392}
{"current_steps": 43895, "total_steps": 58920, "loss": 0.0044, "lr": 3.7074406888158716e-07, "epoch": 3.724966055668703, "percentage": 74.5, "elapsed_time": "1:08:38", "remaining_time": "0:23:29", "throughput": 10233.34, "total_tokens": 42143552}
{"current_steps": 43900, "total_steps": 58920, "loss": 0.0, "lr": 3.705138747212647e-07, "epoch": 3.7253903598099116, "percentage": 74.51, "elapsed_time": "1:08:38", "remaining_time": "0:23:29", "throughput": 10233.58, "total_tokens": 42148480}
{"current_steps": 43905, "total_steps": 58920, "loss": 0.0, "lr": 3.70283735796077e-07, "epoch": 3.72581466395112, "percentage": 74.52, "elapsed_time": "1:08:39", "remaining_time": "0:23:28", "throughput": 10233.75, "total_tokens": 42153088}
{"current_steps": 43910, "total_steps": 58920, "loss": 0.0, "lr": 3.700536521262178e-07, "epoch": 3.7262389680923285, "percentage": 74.52, "elapsed_time": "1:08:39", "remaining_time": "0:23:28", "throughput": 10233.95, "total_tokens": 42157824}
{"current_steps": 43915, "total_steps": 58920, "loss": 0.0, "lr": 3.6982362373187625e-07, "epoch": 3.726663272233537, "percentage": 74.53, "elapsed_time": "1:08:39", "remaining_time": "0:23:27", "throughput": 10234.09, "total_tokens": 42162240}
{"current_steps": 43920, "total_steps": 58920, "loss": 0.0, "lr": 3.6959365063323645e-07, "epoch": 3.7270875763747453, "percentage": 74.54, "elapsed_time": "1:08:40", "remaining_time": "0:23:27", "throughput": 10234.35, "total_tokens": 42167424}
{"current_steps": 43925, "total_steps": 58920, "loss": 0.0, "lr": 3.6936373285047773e-07, "epoch": 3.7275118805159537, "percentage": 74.55, "elapsed_time": "1:08:40", "remaining_time": "0:23:26", "throughput": 10234.5, "total_tokens": 42171904}
{"current_steps": 43930, "total_steps": 58920, "loss": 0.0, "lr": 3.6913387040377466e-07, "epoch": 3.727936184657162, "percentage": 74.56, "elapsed_time": "1:08:40", "remaining_time": "0:23:26", "throughput": 10234.71, "total_tokens": 42176640}
{"current_steps": 43935, "total_steps": 58920, "loss": 0.0, "lr": 3.6890406331329657e-07, "epoch": 3.7283604887983706, "percentage": 74.57, "elapsed_time": "1:08:41", "remaining_time": "0:23:25", "throughput": 10234.91, "total_tokens": 42181376}
{"current_steps": 43940, "total_steps": 58920, "loss": 0.0, "lr": 3.6867431159920847e-07, "epoch": 3.728784792939579, "percentage": 74.58, "elapsed_time": "1:08:41", "remaining_time": "0:23:25", "throughput": 10235.09, "total_tokens": 42185984}
{"current_steps": 43945, "total_steps": 58920, "loss": 0.0, "lr": 3.6844461528167016e-07, "epoch": 3.7292090970807874, "percentage": 74.58, "elapsed_time": "1:08:42", "remaining_time": "0:23:24", "throughput": 10235.29, "total_tokens": 42190656}
{"current_steps": 43950, "total_steps": 58920, "loss": 0.0, "lr": 3.6821497438083647e-07, "epoch": 3.729633401221996, "percentage": 74.59, "elapsed_time": "1:08:42", "remaining_time": "0:23:24", "throughput": 10235.53, "total_tokens": 42195648}
{"current_steps": 43955, "total_steps": 58920, "loss": 0.0, "lr": 3.6798538891685795e-07, "epoch": 3.7300577053632042, "percentage": 74.6, "elapsed_time": "1:08:42", "remaining_time": "0:23:23", "throughput": 10235.74, "total_tokens": 42200384}
{"current_steps": 43960, "total_steps": 58920, "loss": 0.0, "lr": 3.6775585890987947e-07, "epoch": 3.7304820095044127, "percentage": 74.61, "elapsed_time": "1:08:43", "remaining_time": "0:23:23", "throughput": 10235.95, "total_tokens": 42205120}
{"current_steps": 43965, "total_steps": 58920, "loss": 0.0, "lr": 3.675263843800418e-07, "epoch": 3.730906313645621, "percentage": 74.62, "elapsed_time": "1:08:43", "remaining_time": "0:23:22", "throughput": 10236.27, "total_tokens": 42210496}
{"current_steps": 43970, "total_steps": 58920, "loss": 0.0, "lr": 3.6729696534748035e-07, "epoch": 3.7313306177868295, "percentage": 74.63, "elapsed_time": "1:08:44", "remaining_time": "0:23:22", "throughput": 10236.44, "total_tokens": 42215232}
{"current_steps": 43975, "total_steps": 58920, "loss": 0.0, "lr": 3.6706760183232575e-07, "epoch": 3.731754921928038, "percentage": 74.64, "elapsed_time": "1:08:44", "remaining_time": "0:23:21", "throughput": 10236.63, "total_tokens": 42219904}
{"current_steps": 43980, "total_steps": 58920, "loss": 0.0, "lr": 3.66838293854704e-07, "epoch": 3.7321792260692463, "percentage": 74.64, "elapsed_time": "1:08:44", "remaining_time": "0:23:21", "throughput": 10236.84, "total_tokens": 42224704}
{"current_steps": 43985, "total_steps": 58920, "loss": 0.0, "lr": 3.6660904143473547e-07, "epoch": 3.7326035302104548, "percentage": 74.65, "elapsed_time": "1:08:45", "remaining_time": "0:23:20", "throughput": 10236.99, "total_tokens": 42229184}
{"current_steps": 43990, "total_steps": 58920, "loss": 0.0, "lr": 3.6637984459253744e-07, "epoch": 3.733027834351663, "percentage": 74.66, "elapsed_time": "1:08:45", "remaining_time": "0:23:20", "throughput": 10237.1, "total_tokens": 42233472}
{"current_steps": 43995, "total_steps": 58920, "loss": 0.0, "lr": 3.6615070334822005e-07, "epoch": 3.7334521384928716, "percentage": 74.67, "elapsed_time": "1:08:45", "remaining_time": "0:23:19", "throughput": 10237.35, "total_tokens": 42238528}
{"current_steps": 44000, "total_steps": 58920, "loss": 0.0, "lr": 3.6592161772189e-07, "epoch": 3.73387644263408, "percentage": 74.68, "elapsed_time": "1:08:46", "remaining_time": "0:23:19", "throughput": 10237.56, "total_tokens": 42243264}
{"current_steps": 44005, "total_steps": 58920, "loss": 0.0, "lr": 3.6569258773364854e-07, "epoch": 3.7343007467752884, "percentage": 74.69, "elapsed_time": "1:08:46", "remaining_time": "0:23:18", "throughput": 10237.84, "total_tokens": 42248448}
{"current_steps": 44010, "total_steps": 58920, "loss": 0.0, "lr": 3.654636134035921e-07, "epoch": 3.734725050916497, "percentage": 74.69, "elapsed_time": "1:08:47", "remaining_time": "0:23:18", "throughput": 10238.09, "total_tokens": 42253376}
{"current_steps": 44015, "total_steps": 58920, "loss": 0.0, "lr": 3.6523469475181324e-07, "epoch": 3.7351493550577053, "percentage": 74.7, "elapsed_time": "1:08:47", "remaining_time": "0:23:17", "throughput": 10238.35, "total_tokens": 42258624}
{"current_steps": 44020, "total_steps": 58920, "loss": 0.0, "lr": 3.650058317983974e-07, "epoch": 3.7355736591989137, "percentage": 74.71, "elapsed_time": "1:08:47", "remaining_time": "0:23:17", "throughput": 10238.59, "total_tokens": 42263616}
{"current_steps": 44025, "total_steps": 58920, "loss": 0.0, "lr": 3.6477702456342797e-07, "epoch": 3.735997963340122, "percentage": 74.72, "elapsed_time": "1:08:48", "remaining_time": "0:23:16", "throughput": 10238.71, "total_tokens": 42267968}
{"current_steps": 44030, "total_steps": 58920, "loss": 0.0, "lr": 3.6454827306698035e-07, "epoch": 3.7364222674813306, "percentage": 74.73, "elapsed_time": "1:08:48", "remaining_time": "0:23:16", "throughput": 10238.98, "total_tokens": 42273024}
{"current_steps": 44035, "total_steps": 58920, "loss": 0.0135, "lr": 3.6431957732912786e-07, "epoch": 3.736846571622539, "percentage": 74.74, "elapsed_time": "1:08:49", "remaining_time": "0:23:15", "throughput": 10239.13, "total_tokens": 42277504}
{"current_steps": 44040, "total_steps": 58920, "loss": 0.0, "lr": 3.640909373699378e-07, "epoch": 3.7372708757637474, "percentage": 74.75, "elapsed_time": "1:08:49", "remaining_time": "0:23:15", "throughput": 10239.26, "total_tokens": 42281856}
{"current_steps": 44045, "total_steps": 58920, "loss": 0.0, "lr": 3.6386235320947124e-07, "epoch": 3.737695179904956, "percentage": 74.75, "elapsed_time": "1:08:49", "remaining_time": "0:23:14", "throughput": 10239.37, "total_tokens": 42286144}
{"current_steps": 44050, "total_steps": 58920, "loss": 0.005, "lr": 3.6363382486778714e-07, "epoch": 3.7381194840461642, "percentage": 74.76, "elapsed_time": "1:08:50", "remaining_time": "0:23:14", "throughput": 10239.48, "total_tokens": 42290432}
{"current_steps": 44055, "total_steps": 58920, "loss": 0.0, "lr": 3.6340535236493665e-07, "epoch": 3.7385437881873727, "percentage": 74.77, "elapsed_time": "1:08:50", "remaining_time": "0:23:13", "throughput": 10239.68, "total_tokens": 42295104}
{"current_steps": 44060, "total_steps": 58920, "loss": 0.0001, "lr": 3.6317693572096877e-07, "epoch": 3.738968092328581, "percentage": 74.78, "elapsed_time": "1:08:50", "remaining_time": "0:23:13", "throughput": 10239.88, "total_tokens": 42299840}
{"current_steps": 44065, "total_steps": 58920, "loss": 0.0708, "lr": 3.6294857495592477e-07, "epoch": 3.7393923964697895, "percentage": 74.79, "elapsed_time": "1:08:51", "remaining_time": "0:23:12", "throughput": 10240.11, "total_tokens": 42304768}
{"current_steps": 44070, "total_steps": 58920, "loss": 0.0, "lr": 3.627202700898436e-07, "epoch": 3.739816700610998, "percentage": 74.8, "elapsed_time": "1:08:51", "remaining_time": "0:23:12", "throughput": 10240.31, "total_tokens": 42309440}
{"current_steps": 44075, "total_steps": 58920, "loss": 0.0, "lr": 3.6249202114275823e-07, "epoch": 3.7402410047522063, "percentage": 74.8, "elapsed_time": "1:08:52", "remaining_time": "0:23:11", "throughput": 10240.48, "total_tokens": 42314048}
{"current_steps": 44080, "total_steps": 58920, "loss": 0.0, "lr": 3.622638281346956e-07, "epoch": 3.7406653088934148, "percentage": 74.81, "elapsed_time": "1:08:52", "remaining_time": "0:23:11", "throughput": 10240.53, "total_tokens": 42318016}
{"current_steps": 44085, "total_steps": 58920, "loss": 0.0, "lr": 3.620356910856802e-07, "epoch": 3.741089613034623, "percentage": 74.82, "elapsed_time": "1:08:52", "remaining_time": "0:23:10", "throughput": 10240.66, "total_tokens": 42322368}
{"current_steps": 44090, "total_steps": 58920, "loss": 0.0, "lr": 3.618076100157289e-07, "epoch": 3.7415139171758316, "percentage": 74.83, "elapsed_time": "1:08:53", "remaining_time": "0:23:10", "throughput": 10240.84, "total_tokens": 42326976}
{"current_steps": 44095, "total_steps": 58920, "loss": 0.0, "lr": 3.6157958494485595e-07, "epoch": 3.74193822131704, "percentage": 74.84, "elapsed_time": "1:08:53", "remaining_time": "0:23:09", "throughput": 10241.08, "total_tokens": 42331904}
{"current_steps": 44100, "total_steps": 58920, "loss": 0.0507, "lr": 3.6135161589306937e-07, "epoch": 3.7423625254582484, "percentage": 74.85, "elapsed_time": "1:08:53", "remaining_time": "0:23:09", "throughput": 10241.28, "total_tokens": 42336576}
{"current_steps": 44105, "total_steps": 58920, "loss": 0.0, "lr": 3.611237028803728e-07, "epoch": 3.742786829599457, "percentage": 74.86, "elapsed_time": "1:08:54", "remaining_time": "0:23:08", "throughput": 10241.43, "total_tokens": 42341248}
{"current_steps": 44110, "total_steps": 58920, "loss": 0.0, "lr": 3.608958459267645e-07, "epoch": 3.7432111337406653, "percentage": 74.86, "elapsed_time": "1:08:54", "remaining_time": "0:23:08", "throughput": 10241.59, "total_tokens": 42345792}
{"current_steps": 44115, "total_steps": 58920, "loss": 0.0, "lr": 3.6066804505223823e-07, "epoch": 3.7436354378818737, "percentage": 74.87, "elapsed_time": "1:08:55", "remaining_time": "0:23:07", "throughput": 10241.84, "total_tokens": 42350784}
{"current_steps": 44120, "total_steps": 58920, "loss": 0.0, "lr": 3.6044030027678283e-07, "epoch": 3.744059742023082, "percentage": 74.88, "elapsed_time": "1:08:55", "remaining_time": "0:23:07", "throughput": 10242.09, "total_tokens": 42355776}
{"current_steps": 44125, "total_steps": 58920, "loss": 0.0, "lr": 3.602126116203819e-07, "epoch": 3.7444840461642905, "percentage": 74.89, "elapsed_time": "1:08:55", "remaining_time": "0:23:06", "throughput": 10242.28, "total_tokens": 42360448}
{"current_steps": 44130, "total_steps": 58920, "loss": 0.0, "lr": 3.599849791030144e-07, "epoch": 3.744908350305499, "percentage": 74.9, "elapsed_time": "1:08:56", "remaining_time": "0:23:06", "throughput": 10242.36, "total_tokens": 42364608}
{"current_steps": 44135, "total_steps": 58920, "loss": 0.0, "lr": 3.597574027446542e-07, "epoch": 3.7453326544467074, "percentage": 74.91, "elapsed_time": "1:08:56", "remaining_time": "0:23:05", "throughput": 10242.61, "total_tokens": 42369600}
{"current_steps": 44140, "total_steps": 58920, "loss": 0.0, "lr": 3.595298825652703e-07, "epoch": 3.745756958587916, "percentage": 74.92, "elapsed_time": "1:08:56", "remaining_time": "0:23:05", "throughput": 10242.77, "total_tokens": 42374144}
{"current_steps": 44145, "total_steps": 58920, "loss": 0.0, "lr": 3.593024185848268e-07, "epoch": 3.746181262729124, "percentage": 74.92, "elapsed_time": "1:08:57", "remaining_time": "0:23:04", "throughput": 10242.99, "total_tokens": 42378944}
{"current_steps": 44150, "total_steps": 58920, "loss": 0.0, "lr": 3.5907501082328274e-07, "epoch": 3.7466055668703326, "percentage": 74.93, "elapsed_time": "1:08:57", "remaining_time": "0:23:04", "throughput": 10243.18, "total_tokens": 42383616}
{"current_steps": 44155, "total_steps": 58920, "loss": 0.0, "lr": 3.5884765930059256e-07, "epoch": 3.747029871011541, "percentage": 74.94, "elapsed_time": "1:08:58", "remaining_time": "0:23:03", "throughput": 10243.44, "total_tokens": 42388608}
{"current_steps": 44160, "total_steps": 58920, "loss": 0.0, "lr": 3.586203640367054e-07, "epoch": 3.7474541751527495, "percentage": 74.95, "elapsed_time": "1:08:58", "remaining_time": "0:23:03", "throughput": 10243.65, "total_tokens": 42393344}
{"current_steps": 44165, "total_steps": 58920, "loss": 0.0, "lr": 3.583931250515656e-07, "epoch": 3.747878479293958, "percentage": 74.96, "elapsed_time": "1:08:58", "remaining_time": "0:23:02", "throughput": 10243.88, "total_tokens": 42398272}
{"current_steps": 44170, "total_steps": 58920, "loss": 0.0, "lr": 3.5816594236511253e-07, "epoch": 3.7483027834351663, "percentage": 74.97, "elapsed_time": "1:08:59", "remaining_time": "0:23:02", "throughput": 10244.07, "total_tokens": 42403008}
{"current_steps": 44175, "total_steps": 58920, "loss": 0.0, "lr": 3.579388159972807e-07, "epoch": 3.7487270875763747, "percentage": 74.97, "elapsed_time": "1:08:59", "remaining_time": "0:23:01", "throughput": 10244.2, "total_tokens": 42407360}
{"current_steps": 44180, "total_steps": 58920, "loss": 0.0, "lr": 3.577117459679996e-07, "epoch": 3.749151391717583, "percentage": 74.98, "elapsed_time": "1:09:00", "remaining_time": "0:23:01", "throughput": 10244.42, "total_tokens": 42412224}
{"current_steps": 44185, "total_steps": 58920, "loss": 0.0, "lr": 3.574847322971938e-07, "epoch": 3.7495756958587916, "percentage": 74.99, "elapsed_time": "1:09:00", "remaining_time": "0:23:00", "throughput": 10244.58, "total_tokens": 42416768}
{"current_steps": 44190, "total_steps": 58920, "loss": 0.0, "lr": 3.572577750047829e-07, "epoch": 3.75, "percentage": 75.0, "elapsed_time": "1:09:00", "remaining_time": "0:23:00", "throughput": 10244.78, "total_tokens": 42421440}
{"current_steps": 44190, "total_steps": 58920, "eval_loss": 0.15534797310829163, "epoch": 3.75, "percentage": 75.0, "elapsed_time": "1:09:17", "remaining_time": "0:23:05", "throughput": 10204.32, "total_tokens": 42421440}
{"current_steps": 44195, "total_steps": 58920, "loss": 0.0, "lr": 3.570308741106818e-07, "epoch": 3.7504243041412084, "percentage": 75.01, "elapsed_time": "1:09:54", "remaining_time": "0:23:17", "throughput": 10114.31, "total_tokens": 42425728}
{"current_steps": 44200, "total_steps": 58920, "loss": 0.0013, "lr": 3.568040296347996e-07, "epoch": 3.750848608282417, "percentage": 75.02, "elapsed_time": "1:09:55", "remaining_time": "0:23:17", "throughput": 10114.67, "total_tokens": 42431296}
{"current_steps": 44205, "total_steps": 58920, "loss": 0.0167, "lr": 3.5657724159704227e-07, "epoch": 3.7512729124236253, "percentage": 75.03, "elapsed_time": "1:09:55", "remaining_time": "0:23:16", "throughput": 10115.16, "total_tokens": 42437632}
{"current_steps": 44210, "total_steps": 58920, "loss": 0.0, "lr": 3.563505100173085e-07, "epoch": 3.7516972165648337, "percentage": 75.03, "elapsed_time": "1:09:55", "remaining_time": "0:23:16", "throughput": 10115.41, "total_tokens": 42442560}
{"current_steps": 44215, "total_steps": 58920, "loss": 0.0, "lr": 3.5612383491549383e-07, "epoch": 3.752121520706042, "percentage": 75.04, "elapsed_time": "1:09:56", "remaining_time": "0:23:15", "throughput": 10115.58, "total_tokens": 42447104}
{"current_steps": 44220, "total_steps": 58920, "loss": 0.0, "lr": 3.558972163114877e-07, "epoch": 3.7525458248472505, "percentage": 75.05, "elapsed_time": "1:09:56", "remaining_time": "0:23:15", "throughput": 10115.8, "total_tokens": 42451904}
{"current_steps": 44225, "total_steps": 58920, "loss": 0.0, "lr": 3.556706542251751e-07, "epoch": 3.752970128988459, "percentage": 75.06, "elapsed_time": "1:09:56", "remaining_time": "0:23:14", "throughput": 10116.13, "total_tokens": 42457280}
{"current_steps": 44230, "total_steps": 58920, "loss": 0.0, "lr": 3.554441486764368e-07, "epoch": 3.7533944331296674, "percentage": 75.07, "elapsed_time": "1:09:57", "remaining_time": "0:23:14", "throughput": 10116.43, "total_tokens": 42462528}
{"current_steps": 44235, "total_steps": 58920, "loss": 0.0, "lr": 3.552176996851467e-07, "epoch": 3.753818737270876, "percentage": 75.08, "elapsed_time": "1:09:57", "remaining_time": "0:23:13", "throughput": 10116.62, "total_tokens": 42467200}
{"current_steps": 44240, "total_steps": 58920, "loss": 0.0, "lr": 3.5499130727117623e-07, "epoch": 3.754243041412084, "percentage": 75.08, "elapsed_time": "1:09:58", "remaining_time": "0:23:13", "throughput": 10116.89, "total_tokens": 42472320}
{"current_steps": 44245, "total_steps": 58920, "loss": 0.0, "lr": 3.547649714543892e-07, "epoch": 3.7546673455532926, "percentage": 75.09, "elapsed_time": "1:09:58", "remaining_time": "0:23:12", "throughput": 10117.14, "total_tokens": 42477248}
{"current_steps": 44250, "total_steps": 58920, "loss": 0.0, "lr": 3.545386922546462e-07, "epoch": 3.755091649694501, "percentage": 75.1, "elapsed_time": "1:09:58", "remaining_time": "0:23:12", "throughput": 10117.49, "total_tokens": 42482816}
{"current_steps": 44255, "total_steps": 58920, "loss": 0.0, "lr": 3.5431246969180305e-07, "epoch": 3.7555159538357095, "percentage": 75.11, "elapsed_time": "1:09:59", "remaining_time": "0:23:11", "throughput": 10117.71, "total_tokens": 42487616}
{"current_steps": 44260, "total_steps": 58920, "loss": 0.0, "lr": 3.540863037857088e-07, "epoch": 3.755940257976918, "percentage": 75.12, "elapsed_time": "1:09:59", "remaining_time": "0:23:11", "throughput": 10117.92, "total_tokens": 42492416}
{"current_steps": 44265, "total_steps": 58920, "loss": 0.0, "lr": 3.538601945562101e-07, "epoch": 3.7563645621181263, "percentage": 75.13, "elapsed_time": "1:10:00", "remaining_time": "0:23:10", "throughput": 10118.13, "total_tokens": 42497152}
{"current_steps": 44270, "total_steps": 58920, "loss": 0.0004, "lr": 3.5363414202314567e-07, "epoch": 3.7567888662593347, "percentage": 75.14, "elapsed_time": "1:10:00", "remaining_time": "0:23:10", "throughput": 10118.29, "total_tokens": 42501696}
{"current_steps": 44275, "total_steps": 58920, "loss": 0.0, "lr": 3.534081462063523e-07, "epoch": 3.757213170400543, "percentage": 75.14, "elapsed_time": "1:10:00", "remaining_time": "0:23:09", "throughput": 10118.42, "total_tokens": 42506048}
{"current_steps": 44280, "total_steps": 58920, "loss": 0.0, "lr": 3.5318220712565893e-07, "epoch": 3.7576374745417516, "percentage": 75.15, "elapsed_time": "1:10:01", "remaining_time": "0:23:09", "throughput": 10118.57, "total_tokens": 42510464}
{"current_steps": 44285, "total_steps": 58920, "loss": 0.0, "lr": 3.529563248008919e-07, "epoch": 3.75806177868296, "percentage": 75.16, "elapsed_time": "1:10:01", "remaining_time": "0:23:08", "throughput": 10118.71, "total_tokens": 42514880}
{"current_steps": 44290, "total_steps": 58920, "loss": 0.0, "lr": 3.5273049925187146e-07, "epoch": 3.7584860828241684, "percentage": 75.17, "elapsed_time": "1:10:02", "remaining_time": "0:23:08", "throughput": 10119.06, "total_tokens": 42520448}
{"current_steps": 44295, "total_steps": 58920, "loss": 0.0, "lr": 3.525047304984121e-07, "epoch": 3.758910386965377, "percentage": 75.18, "elapsed_time": "1:10:02", "remaining_time": "0:23:07", "throughput": 10119.27, "total_tokens": 42525184}
{"current_steps": 44300, "total_steps": 58920, "loss": 0.0, "lr": 3.522790185603256e-07, "epoch": 3.7593346911065852, "percentage": 75.19, "elapsed_time": "1:10:02", "remaining_time": "0:23:07", "throughput": 10119.43, "total_tokens": 42529664}
{"current_steps": 44305, "total_steps": 58920, "loss": 0.0095, "lr": 3.52053363457416e-07, "epoch": 3.7597589952477937, "percentage": 75.2, "elapsed_time": "1:10:03", "remaining_time": "0:23:06", "throughput": 10119.71, "total_tokens": 42534848}
{"current_steps": 44310, "total_steps": 58920, "loss": 0.0, "lr": 3.5182776520948463e-07, "epoch": 3.760183299389002, "percentage": 75.2, "elapsed_time": "1:10:03", "remaining_time": "0:23:06", "throughput": 10119.96, "total_tokens": 42539840}
{"current_steps": 44315, "total_steps": 58920, "loss": 0.0, "lr": 3.516022238363266e-07, "epoch": 3.7606076035302105, "percentage": 75.21, "elapsed_time": "1:10:03", "remaining_time": "0:23:05", "throughput": 10120.2, "total_tokens": 42544768}
{"current_steps": 44320, "total_steps": 58920, "loss": 0.0354, "lr": 3.513767393577325e-07, "epoch": 3.761031907671419, "percentage": 75.22, "elapsed_time": "1:10:04", "remaining_time": "0:23:04", "throughput": 10120.43, "total_tokens": 42549568}
{"current_steps": 44325, "total_steps": 58920, "loss": 0.0001, "lr": 3.5115131179348766e-07, "epoch": 3.7614562118126273, "percentage": 75.23, "elapsed_time": "1:10:04", "remaining_time": "0:23:04", "throughput": 10120.61, "total_tokens": 42554176}
{"current_steps": 44330, "total_steps": 58920, "loss": 0.0, "lr": 3.509259411633726e-07, "epoch": 3.7618805159538358, "percentage": 75.24, "elapsed_time": "1:10:05", "remaining_time": "0:23:03", "throughput": 10120.81, "total_tokens": 42558912}
{"current_steps": 44335, "total_steps": 58920, "loss": 0.0, "lr": 3.507006274871629e-07, "epoch": 3.762304820095044, "percentage": 75.25, "elapsed_time": "1:10:05", "remaining_time": "0:23:03", "throughput": 10121.06, "total_tokens": 42563904}
{"current_steps": 44340, "total_steps": 58920, "loss": 0.0, "lr": 3.504753707846283e-07, "epoch": 3.7627291242362526, "percentage": 75.25, "elapsed_time": "1:10:05", "remaining_time": "0:23:02", "throughput": 10121.24, "total_tokens": 42568512}
{"current_steps": 44345, "total_steps": 58920, "loss": 0.0, "lr": 3.502501710755351e-07, "epoch": 3.763153428377461, "percentage": 75.26, "elapsed_time": "1:10:06", "remaining_time": "0:23:02", "throughput": 10121.48, "total_tokens": 42573312}
{"current_steps": 44350, "total_steps": 58920, "loss": 0.0, "lr": 3.5002502837964354e-07, "epoch": 3.7635777325186694, "percentage": 75.27, "elapsed_time": "1:10:06", "remaining_time": "0:23:01", "throughput": 10121.74, "total_tokens": 42578368}
{"current_steps": 44355, "total_steps": 58920, "loss": 0.0, "lr": 3.49799942716709e-07, "epoch": 3.764002036659878, "percentage": 75.28, "elapsed_time": "1:10:07", "remaining_time": "0:23:01", "throughput": 10121.9, "total_tokens": 42582912}
{"current_steps": 44360, "total_steps": 58920, "loss": 0.0, "lr": 3.495749141064819e-07, "epoch": 3.7644263408010863, "percentage": 75.29, "elapsed_time": "1:10:07", "remaining_time": "0:23:00", "throughput": 10122.12, "total_tokens": 42587712}
{"current_steps": 44365, "total_steps": 58920, "loss": 0.0, "lr": 3.4934994256870776e-07, "epoch": 3.7648506449422947, "percentage": 75.3, "elapsed_time": "1:10:07", "remaining_time": "0:23:00", "throughput": 10122.32, "total_tokens": 42592384}
{"current_steps": 44370, "total_steps": 58920, "loss": 0.0, "lr": 3.4912502812312695e-07, "epoch": 3.765274949083503, "percentage": 75.31, "elapsed_time": "1:10:08", "remaining_time": "0:22:59", "throughput": 10122.6, "total_tokens": 42597568}
{"current_steps": 44375, "total_steps": 58920, "loss": 0.0, "lr": 3.48900170789475e-07, "epoch": 3.7656992532247116, "percentage": 75.31, "elapsed_time": "1:10:08", "remaining_time": "0:22:59", "throughput": 10122.84, "total_tokens": 42602432}
{"current_steps": 44380, "total_steps": 58920, "loss": 0.0, "lr": 3.486753705874823e-07, "epoch": 3.76612355736592, "percentage": 75.32, "elapsed_time": "1:10:08", "remaining_time": "0:22:58", "throughput": 10123.03, "total_tokens": 42607104}
{"current_steps": 44385, "total_steps": 58920, "loss": 0.0, "lr": 3.484506275368742e-07, "epoch": 3.7665478615071284, "percentage": 75.33, "elapsed_time": "1:10:09", "remaining_time": "0:22:58", "throughput": 10123.19, "total_tokens": 42611648}
{"current_steps": 44390, "total_steps": 58920, "loss": 0.0, "lr": 3.482259416573711e-07, "epoch": 3.766972165648337, "percentage": 75.34, "elapsed_time": "1:10:09", "remaining_time": "0:22:57", "throughput": 10123.46, "total_tokens": 42616704}
{"current_steps": 44395, "total_steps": 58920, "loss": 0.0, "lr": 3.480013129686884e-07, "epoch": 3.7673964697895452, "percentage": 75.35, "elapsed_time": "1:10:10", "remaining_time": "0:22:57", "throughput": 10123.73, "total_tokens": 42621760}
{"current_steps": 44400, "total_steps": 58920, "loss": 0.0, "lr": 3.4777674149053646e-07, "epoch": 3.7678207739307537, "percentage": 75.36, "elapsed_time": "1:10:10", "remaining_time": "0:22:56", "throughput": 10124.08, "total_tokens": 42627264}
{"current_steps": 44405, "total_steps": 58920, "loss": 0.0562, "lr": 3.4755222724262067e-07, "epoch": 3.768245078071962, "percentage": 75.36, "elapsed_time": "1:10:10", "remaining_time": "0:22:56", "throughput": 10124.34, "total_tokens": 42632320}
{"current_steps": 44410, "total_steps": 58920, "loss": 0.0138, "lr": 3.473277702446412e-07, "epoch": 3.7686693822131705, "percentage": 75.37, "elapsed_time": "1:10:11", "remaining_time": "0:22:55", "throughput": 10124.51, "total_tokens": 42636864}
{"current_steps": 44415, "total_steps": 58920, "loss": 0.0, "lr": 3.4710337051629355e-07, "epoch": 3.769093686354379, "percentage": 75.38, "elapsed_time": "1:10:11", "remaining_time": "0:22:55", "throughput": 10124.85, "total_tokens": 42642304}
{"current_steps": 44420, "total_steps": 58920, "loss": 0.0, "lr": 3.468790280772678e-07, "epoch": 3.7695179904955873, "percentage": 75.39, "elapsed_time": "1:10:12", "remaining_time": "0:22:54", "throughput": 10125.0, "total_tokens": 42646720}
{"current_steps": 44425, "total_steps": 58920, "loss": 0.0, "lr": 3.4665474294724917e-07, "epoch": 3.7699422946367958, "percentage": 75.4, "elapsed_time": "1:10:12", "remaining_time": "0:22:54", "throughput": 10125.21, "total_tokens": 42651456}
{"current_steps": 44430, "total_steps": 58920, "loss": 0.0, "lr": 3.46430515145918e-07, "epoch": 3.770366598778004, "percentage": 75.41, "elapsed_time": "1:10:12", "remaining_time": "0:22:53", "throughput": 10125.42, "total_tokens": 42656256}
{"current_steps": 44435, "total_steps": 58920, "loss": 0.0, "lr": 3.462063446929495e-07, "epoch": 3.7707909029192126, "percentage": 75.42, "elapsed_time": "1:10:13", "remaining_time": "0:22:53", "throughput": 10125.71, "total_tokens": 42661440}
{"current_steps": 44440, "total_steps": 58920, "loss": 0.0, "lr": 3.459822316080133e-07, "epoch": 3.771215207060421, "percentage": 75.42, "elapsed_time": "1:10:13", "remaining_time": "0:22:52", "throughput": 10125.85, "total_tokens": 42665792}
{"current_steps": 44445, "total_steps": 58920, "loss": 0.0, "lr": 3.457581759107757e-07, "epoch": 3.7716395112016294, "percentage": 75.43, "elapsed_time": "1:10:13", "remaining_time": "0:22:52", "throughput": 10126.07, "total_tokens": 42670592}
{"current_steps": 44450, "total_steps": 58920, "loss": 0.0, "lr": 3.4553417762089533e-07, "epoch": 3.772063815342838, "percentage": 75.44, "elapsed_time": "1:10:14", "remaining_time": "0:22:51", "throughput": 10126.26, "total_tokens": 42675264}
{"current_steps": 44455, "total_steps": 58920, "loss": 0.0, "lr": 3.453102367580286e-07, "epoch": 3.7724881194840463, "percentage": 75.45, "elapsed_time": "1:10:14", "remaining_time": "0:22:51", "throughput": 10126.48, "total_tokens": 42680064}
{"current_steps": 44460, "total_steps": 58920, "loss": 0.0, "lr": 3.4508635334182457e-07, "epoch": 3.7729124236252547, "percentage": 75.46, "elapsed_time": "1:10:15", "remaining_time": "0:22:50", "throughput": 10126.65, "total_tokens": 42684544}
{"current_steps": 44465, "total_steps": 58920, "loss": 0.0, "lr": 3.448625273919281e-07, "epoch": 3.773336727766463, "percentage": 75.47, "elapsed_time": "1:10:15", "remaining_time": "0:22:50", "throughput": 10126.84, "total_tokens": 42689152}
{"current_steps": 44470, "total_steps": 58920, "loss": 0.0, "lr": 3.446387589279801e-07, "epoch": 3.7737610319076715, "percentage": 75.48, "elapsed_time": "1:10:15", "remaining_time": "0:22:49", "throughput": 10127.0, "total_tokens": 42693632}
{"current_steps": 44475, "total_steps": 58920, "loss": 0.0, "lr": 3.444150479696143e-07, "epoch": 3.77418533604888, "percentage": 75.48, "elapsed_time": "1:10:16", "remaining_time": "0:22:49", "throughput": 10127.24, "total_tokens": 42698624}
{"current_steps": 44480, "total_steps": 58920, "loss": 0.0, "lr": 3.4419139453646163e-07, "epoch": 3.7746096401900884, "percentage": 75.49, "elapsed_time": "1:10:16", "remaining_time": "0:22:48", "throughput": 10127.45, "total_tokens": 42703360}
{"current_steps": 44485, "total_steps": 58920, "loss": 0.0, "lr": 3.439677986481456e-07, "epoch": 3.775033944331297, "percentage": 75.5, "elapsed_time": "1:10:16", "remaining_time": "0:22:48", "throughput": 10127.63, "total_tokens": 42707968}
{"current_steps": 44490, "total_steps": 58920, "loss": 0.0, "lr": 3.437442603242874e-07, "epoch": 3.775458248472505, "percentage": 75.51, "elapsed_time": "1:10:17", "remaining_time": "0:22:47", "throughput": 10127.85, "total_tokens": 42712768}
{"current_steps": 44495, "total_steps": 58920, "loss": 0.0, "lr": 3.4352077958450055e-07, "epoch": 3.7758825526137136, "percentage": 75.52, "elapsed_time": "1:10:17", "remaining_time": "0:22:47", "throughput": 10128.19, "total_tokens": 42718208}
{"current_steps": 44500, "total_steps": 58920, "loss": 0.0, "lr": 3.4329735644839484e-07, "epoch": 3.776306856754922, "percentage": 75.53, "elapsed_time": "1:10:18", "remaining_time": "0:22:46", "throughput": 10128.32, "total_tokens": 42722624}
{"current_steps": 44505, "total_steps": 58920, "loss": 0.001, "lr": 3.4307399093557567e-07, "epoch": 3.7767311608961305, "percentage": 75.53, "elapsed_time": "1:10:18", "remaining_time": "0:22:46", "throughput": 10128.41, "total_tokens": 42726784}
{"current_steps": 44510, "total_steps": 58920, "loss": 0.0, "lr": 3.4285068306564137e-07, "epoch": 3.777155465037339, "percentage": 75.54, "elapsed_time": "1:10:18", "remaining_time": "0:22:45", "throughput": 10128.61, "total_tokens": 42731456}
{"current_steps": 44515, "total_steps": 58920, "loss": 0.0, "lr": 3.426274328581876e-07, "epoch": 3.7775797691785473, "percentage": 75.55, "elapsed_time": "1:10:19", "remaining_time": "0:22:45", "throughput": 10128.78, "total_tokens": 42736064}
{"current_steps": 44520, "total_steps": 58920, "loss": 0.0, "lr": 3.4240424033280244e-07, "epoch": 3.7780040733197557, "percentage": 75.56, "elapsed_time": "1:10:19", "remaining_time": "0:22:44", "throughput": 10129.03, "total_tokens": 42741056}
{"current_steps": 44525, "total_steps": 58920, "loss": 0.0, "lr": 3.421811055090714e-07, "epoch": 3.778428377460964, "percentage": 75.57, "elapsed_time": "1:10:20", "remaining_time": "0:22:44", "throughput": 10129.25, "total_tokens": 42745920}
{"current_steps": 44530, "total_steps": 58920, "loss": 0.0, "lr": 3.419580284065733e-07, "epoch": 3.7788526816021726, "percentage": 75.58, "elapsed_time": "1:10:20", "remaining_time": "0:22:43", "throughput": 10129.33, "total_tokens": 42750016}
{"current_steps": 44535, "total_steps": 58920, "loss": 0.0, "lr": 3.417350090448824e-07, "epoch": 3.779276985743381, "percentage": 75.59, "elapsed_time": "1:10:20", "remaining_time": "0:22:43", "throughput": 10129.55, "total_tokens": 42754880}
{"current_steps": 44540, "total_steps": 58920, "loss": 0.0, "lr": 3.4151204744356797e-07, "epoch": 3.7797012898845894, "percentage": 75.59, "elapsed_time": "1:10:21", "remaining_time": "0:22:42", "throughput": 10129.62, "total_tokens": 42758976}
{"current_steps": 44545, "total_steps": 58920, "loss": 0.0, "lr": 3.412891436221934e-07, "epoch": 3.780125594025798, "percentage": 75.6, "elapsed_time": "1:10:21", "remaining_time": "0:22:42", "throughput": 10129.77, "total_tokens": 42763456}
{"current_steps": 44550, "total_steps": 58920, "loss": 0.0, "lr": 3.410662976003188e-07, "epoch": 3.7805498981670063, "percentage": 75.61, "elapsed_time": "1:10:21", "remaining_time": "0:22:41", "throughput": 10129.98, "total_tokens": 42768320}
{"current_steps": 44555, "total_steps": 58920, "loss": 0.0, "lr": 3.4084350939749684e-07, "epoch": 3.7809742023082147, "percentage": 75.62, "elapsed_time": "1:10:22", "remaining_time": "0:22:41", "throughput": 10130.28, "total_tokens": 42773632}
{"current_steps": 44560, "total_steps": 58920, "loss": 0.0, "lr": 3.4062077903327745e-07, "epoch": 3.781398506449423, "percentage": 75.63, "elapsed_time": "1:10:22", "remaining_time": "0:22:40", "throughput": 10130.46, "total_tokens": 42778304}
{"current_steps": 44565, "total_steps": 58920, "loss": 0.0, "lr": 3.40398106527204e-07, "epoch": 3.7818228105906315, "percentage": 75.64, "elapsed_time": "1:10:23", "remaining_time": "0:22:40", "throughput": 10130.64, "total_tokens": 42782912}
{"current_steps": 44570, "total_steps": 58920, "loss": 0.0, "lr": 3.401754918988152e-07, "epoch": 3.78224711473184, "percentage": 75.64, "elapsed_time": "1:10:23", "remaining_time": "0:22:39", "throughput": 10130.92, "total_tokens": 42788096}
{"current_steps": 44575, "total_steps": 58920, "loss": 0.0, "lr": 3.399529351676447e-07, "epoch": 3.7826714188730484, "percentage": 75.65, "elapsed_time": "1:10:23", "remaining_time": "0:22:39", "throughput": 10131.12, "total_tokens": 42792832}
{"current_steps": 44580, "total_steps": 58920, "loss": 0.0, "lr": 3.397304363532211e-07, "epoch": 3.783095723014257, "percentage": 75.66, "elapsed_time": "1:10:24", "remaining_time": "0:22:38", "throughput": 10131.27, "total_tokens": 42797376}
{"current_steps": 44585, "total_steps": 58920, "loss": 0.0, "lr": 3.3950799547506767e-07, "epoch": 3.7835200271554648, "percentage": 75.67, "elapsed_time": "1:10:24", "remaining_time": "0:22:38", "throughput": 10131.51, "total_tokens": 42802368}
{"current_steps": 44590, "total_steps": 58920, "loss": 0.0, "lr": 3.3928561255270317e-07, "epoch": 3.7839443312966736, "percentage": 75.68, "elapsed_time": "1:10:25", "remaining_time": "0:22:37", "throughput": 10131.7, "total_tokens": 42807040}
{"current_steps": 44595, "total_steps": 58920, "loss": 0.0184, "lr": 3.390632876056405e-07, "epoch": 3.7843686354378816, "percentage": 75.69, "elapsed_time": "1:10:25", "remaining_time": "0:22:37", "throughput": 10132.02, "total_tokens": 42812480}
{"current_steps": 44600, "total_steps": 58920, "loss": 0.0, "lr": 3.3884102065338806e-07, "epoch": 3.7847929395790905, "percentage": 75.7, "elapsed_time": "1:10:25", "remaining_time": "0:22:36", "throughput": 10132.14, "total_tokens": 42816832}
{"current_steps": 44605, "total_steps": 58920, "loss": 0.0, "lr": 3.3861881171544895e-07, "epoch": 3.7852172437202984, "percentage": 75.7, "elapsed_time": "1:10:26", "remaining_time": "0:22:36", "throughput": 10132.31, "total_tokens": 42821504}
{"current_steps": 44610, "total_steps": 58920, "loss": 0.0, "lr": 3.383966608113212e-07, "epoch": 3.7856415478615073, "percentage": 75.71, "elapsed_time": "1:10:26", "remaining_time": "0:22:35", "throughput": 10132.51, "total_tokens": 42826176}
{"current_steps": 44615, "total_steps": 58920, "loss": 0.0, "lr": 3.381745679604978e-07, "epoch": 3.7860658520027153, "percentage": 75.72, "elapsed_time": "1:10:26", "remaining_time": "0:22:35", "throughput": 10132.61, "total_tokens": 42830400}
{"current_steps": 44620, "total_steps": 58920, "loss": 0.0, "lr": 3.379525331824665e-07, "epoch": 3.786490156143924, "percentage": 75.73, "elapsed_time": "1:10:27", "remaining_time": "0:22:34", "throughput": 10132.83, "total_tokens": 42835264}
{"current_steps": 44625, "total_steps": 58920, "loss": 0.0, "lr": 3.3773055649671023e-07, "epoch": 3.786914460285132, "percentage": 75.74, "elapsed_time": "1:10:27", "remaining_time": "0:22:34", "throughput": 10133.05, "total_tokens": 42840192}
{"current_steps": 44630, "total_steps": 58920, "loss": 0.0, "lr": 3.3750863792270633e-07, "epoch": 3.787338764426341, "percentage": 75.75, "elapsed_time": "1:10:28", "remaining_time": "0:22:33", "throughput": 10133.43, "total_tokens": 42845952}
{"current_steps": 44635, "total_steps": 58920, "loss": 0.0, "lr": 3.3728677747992774e-07, "epoch": 3.787763068567549, "percentage": 75.76, "elapsed_time": "1:10:28", "remaining_time": "0:22:33", "throughput": 10133.67, "total_tokens": 42850816}
{"current_steps": 44640, "total_steps": 58920, "loss": 0.0193, "lr": 3.370649751878415e-07, "epoch": 3.788187372708758, "percentage": 75.76, "elapsed_time": "1:10:28", "remaining_time": "0:22:32", "throughput": 10133.82, "total_tokens": 42855296}
{"current_steps": 44645, "total_steps": 58920, "loss": 0.0, "lr": 3.368432310659103e-07, "epoch": 3.788611676849966, "percentage": 75.77, "elapsed_time": "1:10:29", "remaining_time": "0:22:32", "throughput": 10134.12, "total_tokens": 42860544}
{"current_steps": 44650, "total_steps": 58920, "loss": 0.0, "lr": 3.366215451335912e-07, "epoch": 3.7890359809911747, "percentage": 75.78, "elapsed_time": "1:10:29", "remaining_time": "0:22:31", "throughput": 10134.91, "total_tokens": 42868800}
{"current_steps": 44655, "total_steps": 58920, "loss": 0.0, "lr": 3.3639991741033615e-07, "epoch": 3.7894602851323826, "percentage": 75.79, "elapsed_time": "1:10:30", "remaining_time": "0:22:31", "throughput": 10135.11, "total_tokens": 42873600}
{"current_steps": 44660, "total_steps": 58920, "loss": 0.0215, "lr": 3.36178347915593e-07, "epoch": 3.7898845892735915, "percentage": 75.8, "elapsed_time": "1:10:30", "remaining_time": "0:22:30", "throughput": 10135.34, "total_tokens": 42878528}
{"current_steps": 44665, "total_steps": 58920, "loss": 0.0, "lr": 3.359568366688028e-07, "epoch": 3.7903088934147995, "percentage": 75.81, "elapsed_time": "1:10:30", "remaining_time": "0:22:30", "throughput": 10135.59, "total_tokens": 42883584}
{"current_steps": 44670, "total_steps": 58920, "loss": 0.0, "lr": 3.357353836894026e-07, "epoch": 3.7907331975560083, "percentage": 75.81, "elapsed_time": "1:10:31", "remaining_time": "0:22:29", "throughput": 10135.72, "total_tokens": 42888000}
{"current_steps": 44675, "total_steps": 58920, "loss": 0.0, "lr": 3.3551398899682424e-07, "epoch": 3.7911575016972163, "percentage": 75.82, "elapsed_time": "1:10:31", "remaining_time": "0:22:29", "throughput": 10136.03, "total_tokens": 42893376}
{"current_steps": 44680, "total_steps": 58920, "loss": 0.0, "lr": 3.352926526104942e-07, "epoch": 3.791581805838425, "percentage": 75.83, "elapsed_time": "1:10:32", "remaining_time": "0:22:28", "throughput": 10136.19, "total_tokens": 42897920}
{"current_steps": 44685, "total_steps": 58920, "loss": 0.0, "lr": 3.35071374549834e-07, "epoch": 3.792006109979633, "percentage": 75.84, "elapsed_time": "1:10:32", "remaining_time": "0:22:28", "throughput": 10136.38, "total_tokens": 42902656}
{"current_steps": 44690, "total_steps": 58920, "loss": 0.0, "lr": 3.348501548342596e-07, "epoch": 3.792430414120842, "percentage": 75.85, "elapsed_time": "1:10:32", "remaining_time": "0:22:27", "throughput": 10136.6, "total_tokens": 42907520}
{"current_steps": 44695, "total_steps": 58920, "loss": 0.0, "lr": 3.346289934831833e-07, "epoch": 3.79285471826205, "percentage": 75.86, "elapsed_time": "1:10:33", "remaining_time": "0:22:27", "throughput": 10136.74, "total_tokens": 42912000}
{"current_steps": 44700, "total_steps": 58920, "loss": 0.0507, "lr": 3.3440789051600983e-07, "epoch": 3.793279022403259, "percentage": 75.87, "elapsed_time": "1:10:33", "remaining_time": "0:22:26", "throughput": 10137.03, "total_tokens": 42917184}
{"current_steps": 44705, "total_steps": 58920, "loss": 0.0, "lr": 3.341868459521415e-07, "epoch": 3.793703326544467, "percentage": 75.87, "elapsed_time": "1:10:34", "remaining_time": "0:22:26", "throughput": 10137.29, "total_tokens": 42922304}
{"current_steps": 44710, "total_steps": 58920, "loss": 0.0, "lr": 3.3396585981097325e-07, "epoch": 3.7941276306856757, "percentage": 75.88, "elapsed_time": "1:10:34", "remaining_time": "0:22:25", "throughput": 10137.42, "total_tokens": 42926720}
{"current_steps": 44715, "total_steps": 58920, "loss": 0.0002, "lr": 3.337449321118957e-07, "epoch": 3.7945519348268837, "percentage": 75.89, "elapsed_time": "1:10:34", "remaining_time": "0:22:25", "throughput": 10137.57, "total_tokens": 42931264}
{"current_steps": 44720, "total_steps": 58920, "loss": 0.0, "lr": 3.3352406287429555e-07, "epoch": 3.7949762389680926, "percentage": 75.9, "elapsed_time": "1:10:35", "remaining_time": "0:22:24", "throughput": 10137.71, "total_tokens": 42935680}
{"current_steps": 44725, "total_steps": 58920, "loss": 0.0734, "lr": 3.3330325211755196e-07, "epoch": 3.7954005431093005, "percentage": 75.91, "elapsed_time": "1:10:35", "remaining_time": "0:22:24", "throughput": 10137.94, "total_tokens": 42940608}
{"current_steps": 44730, "total_steps": 58920, "loss": 0.0, "lr": 3.330824998610415e-07, "epoch": 3.7958248472505094, "percentage": 75.92, "elapsed_time": "1:10:36", "remaining_time": "0:22:23", "throughput": 10138.12, "total_tokens": 42945280}
{"current_steps": 44735, "total_steps": 58920, "loss": 0.0, "lr": 3.3286180612413317e-07, "epoch": 3.7962491513917174, "percentage": 75.92, "elapsed_time": "1:10:36", "remaining_time": "0:22:23", "throughput": 10138.26, "total_tokens": 42949824}
{"current_steps": 44740, "total_steps": 58920, "loss": 0.0, "lr": 3.3264117092619294e-07, "epoch": 3.7966734555329262, "percentage": 75.93, "elapsed_time": "1:10:36", "remaining_time": "0:22:22", "throughput": 10138.46, "total_tokens": 42954560}
{"current_steps": 44745, "total_steps": 58920, "loss": 0.0, "lr": 3.324205942865809e-07, "epoch": 3.797097759674134, "percentage": 75.94, "elapsed_time": "1:10:37", "remaining_time": "0:22:22", "throughput": 10138.75, "total_tokens": 42959808}
{"current_steps": 44750, "total_steps": 58920, "loss": 0.0, "lr": 3.3220007622465064e-07, "epoch": 3.797522063815343, "percentage": 75.95, "elapsed_time": "1:10:37", "remaining_time": "0:22:21", "throughput": 10138.93, "total_tokens": 42964480}
{"current_steps": 44755, "total_steps": 58920, "loss": 0.0, "lr": 3.3197961675975327e-07, "epoch": 3.797946367956551, "percentage": 75.96, "elapsed_time": "1:10:37", "remaining_time": "0:22:21", "throughput": 10139.24, "total_tokens": 42969856}
{"current_steps": 44760, "total_steps": 58920, "loss": 0.0, "lr": 3.31759215911232e-07, "epoch": 3.79837067209776, "percentage": 75.97, "elapsed_time": "1:10:38", "remaining_time": "0:22:20", "throughput": 10139.46, "total_tokens": 42974720}
{"current_steps": 44765, "total_steps": 58920, "loss": 0.0, "lr": 3.315388736984276e-07, "epoch": 3.798794976238968, "percentage": 75.98, "elapsed_time": "1:10:38", "remaining_time": "0:22:20", "throughput": 10139.67, "total_tokens": 42979584}
{"current_steps": 44770, "total_steps": 58920, "loss": 0.043, "lr": 3.3131859014067285e-07, "epoch": 3.7992192803801768, "percentage": 75.98, "elapsed_time": "1:10:39", "remaining_time": "0:22:19", "throughput": 10139.81, "total_tokens": 42984064}
{"current_steps": 44775, "total_steps": 58920, "loss": 0.0, "lr": 3.3109836525729795e-07, "epoch": 3.7996435845213847, "percentage": 75.99, "elapsed_time": "1:10:39", "remaining_time": "0:22:19", "throughput": 10139.95, "total_tokens": 42988480}
{"current_steps": 44780, "total_steps": 58920, "loss": 0.0002, "lr": 3.3087819906762636e-07, "epoch": 3.8000678886625936, "percentage": 76.0, "elapsed_time": "1:10:39", "remaining_time": "0:22:18", "throughput": 10140.1, "total_tokens": 42993024}
{"current_steps": 44785, "total_steps": 58920, "loss": 0.0, "lr": 3.306580915909769e-07, "epoch": 3.8004921928038016, "percentage": 76.01, "elapsed_time": "1:10:40", "remaining_time": "0:22:18", "throughput": 10140.28, "total_tokens": 42997632}
{"current_steps": 44790, "total_steps": 58920, "loss": 0.0, "lr": 3.3043804284666367e-07, "epoch": 3.8009164969450104, "percentage": 76.02, "elapsed_time": "1:10:40", "remaining_time": "0:22:17", "throughput": 10140.44, "total_tokens": 43002240}
{"current_steps": 44795, "total_steps": 58920, "loss": 0.0, "lr": 3.3021805285399405e-07, "epoch": 3.8013408010862184, "percentage": 76.03, "elapsed_time": "1:10:41", "remaining_time": "0:22:17", "throughput": 10140.71, "total_tokens": 43007424}
{"current_steps": 44800, "total_steps": 58920, "loss": 0.0, "lr": 3.299981216322724e-07, "epoch": 3.8017651052274273, "percentage": 76.04, "elapsed_time": "1:10:41", "remaining_time": "0:22:16", "throughput": 10140.86, "total_tokens": 43011904}
{"current_steps": 44805, "total_steps": 58920, "loss": 0.0, "lr": 3.2977824920079655e-07, "epoch": 3.8021894093686353, "percentage": 76.04, "elapsed_time": "1:10:41", "remaining_time": "0:22:16", "throughput": 10140.99, "total_tokens": 43016256}
{"current_steps": 44810, "total_steps": 58920, "loss": 0.0, "lr": 3.2955843557885944e-07, "epoch": 3.802613713509844, "percentage": 76.05, "elapsed_time": "1:10:42", "remaining_time": "0:22:15", "throughput": 10141.17, "total_tokens": 43020864}
{"current_steps": 44815, "total_steps": 58920, "loss": 0.0, "lr": 3.293386807857491e-07, "epoch": 3.803038017651052, "percentage": 76.06, "elapsed_time": "1:10:42", "remaining_time": "0:22:15", "throughput": 10141.54, "total_tokens": 43026624}
{"current_steps": 44820, "total_steps": 58920, "loss": 0.0, "lr": 3.2911898484074806e-07, "epoch": 3.803462321792261, "percentage": 76.07, "elapsed_time": "1:10:42", "remaining_time": "0:22:14", "throughput": 10141.64, "total_tokens": 43030848}
{"current_steps": 44825, "total_steps": 58920, "loss": 0.0313, "lr": 3.2889934776313386e-07, "epoch": 3.803886625933469, "percentage": 76.08, "elapsed_time": "1:10:43", "remaining_time": "0:22:14", "throughput": 10141.87, "total_tokens": 43035776}
{"current_steps": 44830, "total_steps": 58920, "loss": 0.0, "lr": 3.286797695721789e-07, "epoch": 3.804310930074678, "percentage": 76.09, "elapsed_time": "1:10:43", "remaining_time": "0:22:13", "throughput": 10142.08, "total_tokens": 43040576}
{"current_steps": 44835, "total_steps": 58920, "loss": 0.0, "lr": 3.284602502871504e-07, "epoch": 3.8047352342158858, "percentage": 76.09, "elapsed_time": "1:10:44", "remaining_time": "0:22:13", "throughput": 10142.26, "total_tokens": 43045248}
{"current_steps": 44840, "total_steps": 58920, "loss": 0.0, "lr": 3.282407899273103e-07, "epoch": 3.8051595383570946, "percentage": 76.1, "elapsed_time": "1:10:44", "remaining_time": "0:22:12", "throughput": 10142.41, "total_tokens": 43049664}
{"current_steps": 44845, "total_steps": 58920, "loss": 0.0, "lr": 3.2802138851191553e-07, "epoch": 3.8055838424983026, "percentage": 76.11, "elapsed_time": "1:10:44", "remaining_time": "0:22:12", "throughput": 10142.67, "total_tokens": 43054656}
{"current_steps": 44850, "total_steps": 58920, "loss": 0.0, "lr": 3.2780204606021776e-07, "epoch": 3.806008146639511, "percentage": 76.12, "elapsed_time": "1:10:45", "remaining_time": "0:22:11", "throughput": 10142.94, "total_tokens": 43059776}
{"current_steps": 44855, "total_steps": 58920, "loss": 0.0, "lr": 3.2758276259146356e-07, "epoch": 3.8064324507807195, "percentage": 76.13, "elapsed_time": "1:10:45", "remaining_time": "0:22:11", "throughput": 10143.14, "total_tokens": 43064512}
{"current_steps": 44860, "total_steps": 58920, "loss": 0.0, "lr": 3.27363538124894e-07, "epoch": 3.806856754921928, "percentage": 76.14, "elapsed_time": "1:10:46", "remaining_time": "0:22:10", "throughput": 10143.3, "total_tokens": 43069056}
{"current_steps": 44865, "total_steps": 58920, "loss": 0.0, "lr": 3.271443726797456e-07, "epoch": 3.8072810590631363, "percentage": 76.15, "elapsed_time": "1:10:46", "remaining_time": "0:22:10", "throughput": 10143.56, "total_tokens": 43074048}
{"current_steps": 44870, "total_steps": 58920, "loss": 0.0, "lr": 3.269252662752491e-07, "epoch": 3.8077053632043447, "percentage": 76.15, "elapsed_time": "1:10:46", "remaining_time": "0:22:09", "throughput": 10143.77, "total_tokens": 43078848}
{"current_steps": 44875, "total_steps": 58920, "loss": 0.0, "lr": 3.267062189306303e-07, "epoch": 3.808129667345553, "percentage": 76.16, "elapsed_time": "1:10:47", "remaining_time": "0:22:09", "throughput": 10143.94, "total_tokens": 43083392}
{"current_steps": 44880, "total_steps": 58920, "loss": 0.0, "lr": 3.2648723066511e-07, "epoch": 3.8085539714867616, "percentage": 76.17, "elapsed_time": "1:10:47", "remaining_time": "0:22:08", "throughput": 10144.36, "total_tokens": 43089344}
{"current_steps": 44885, "total_steps": 58920, "loss": 0.0375, "lr": 3.262683014979034e-07, "epoch": 3.80897827562797, "percentage": 76.18, "elapsed_time": "1:10:47", "remaining_time": "0:22:08", "throughput": 10144.54, "total_tokens": 43093952}
{"current_steps": 44890, "total_steps": 58920, "loss": 0.0, "lr": 3.2604943144822097e-07, "epoch": 3.8094025797691784, "percentage": 76.19, "elapsed_time": "1:10:48", "remaining_time": "0:22:07", "throughput": 10144.83, "total_tokens": 43099200}
{"current_steps": 44895, "total_steps": 58920, "loss": 0.0, "lr": 3.2583062053526757e-07, "epoch": 3.809826883910387, "percentage": 76.2, "elapsed_time": "1:10:48", "remaining_time": "0:22:07", "throughput": 10145.06, "total_tokens": 43104064}
{"current_steps": 44900, "total_steps": 58920, "loss": 0.0, "lr": 3.256118687782431e-07, "epoch": 3.8102511880515952, "percentage": 76.21, "elapsed_time": "1:10:49", "remaining_time": "0:22:06", "throughput": 10145.25, "total_tokens": 43108736}
{"current_steps": 44905, "total_steps": 58920, "loss": 0.0, "lr": 3.253931761963419e-07, "epoch": 3.8106754921928037, "percentage": 76.21, "elapsed_time": "1:10:49", "remaining_time": "0:22:06", "throughput": 10145.56, "total_tokens": 43114112}
{"current_steps": 44910, "total_steps": 58920, "loss": 0.0, "lr": 3.251745428087546e-07, "epoch": 3.811099796334012, "percentage": 76.22, "elapsed_time": "1:10:49", "remaining_time": "0:22:05", "throughput": 10145.78, "total_tokens": 43118912}
{"current_steps": 44915, "total_steps": 58920, "loss": 0.0, "lr": 3.249559686346643e-07, "epoch": 3.8115241004752205, "percentage": 76.23, "elapsed_time": "1:10:50", "remaining_time": "0:22:05", "throughput": 10145.99, "total_tokens": 43123648}
{"current_steps": 44920, "total_steps": 58920, "loss": 0.0, "lr": 3.247374536932506e-07, "epoch": 3.811948404616429, "percentage": 76.24, "elapsed_time": "1:10:50", "remaining_time": "0:22:04", "throughput": 10146.39, "total_tokens": 43129408}
{"current_steps": 44925, "total_steps": 58920, "loss": 0.0, "lr": 3.245189980036873e-07, "epoch": 3.8123727087576373, "percentage": 76.25, "elapsed_time": "1:10:51", "remaining_time": "0:22:04", "throughput": 10146.69, "total_tokens": 43134720}
{"current_steps": 44930, "total_steps": 58920, "loss": 0.0, "lr": 3.243006015851427e-07, "epoch": 3.8127970128988458, "percentage": 76.26, "elapsed_time": "1:10:51", "remaining_time": "0:22:03", "throughput": 10147.04, "total_tokens": 43140224}
{"current_steps": 44935, "total_steps": 58920, "loss": 0.0, "lr": 3.2408226445678145e-07, "epoch": 3.813221317040054, "percentage": 76.26, "elapsed_time": "1:10:51", "remaining_time": "0:22:03", "throughput": 10147.17, "total_tokens": 43144576}
{"current_steps": 44940, "total_steps": 58920, "loss": 0.0, "lr": 3.238639866377604e-07, "epoch": 3.8136456211812626, "percentage": 76.27, "elapsed_time": "1:10:52", "remaining_time": "0:22:02", "throughput": 10147.4, "total_tokens": 43149376}
{"current_steps": 44945, "total_steps": 58920, "loss": 0.0, "lr": 3.23645768147234e-07, "epoch": 3.814069925322471, "percentage": 76.28, "elapsed_time": "1:10:52", "remaining_time": "0:22:02", "throughput": 10147.64, "total_tokens": 43154304}
{"current_steps": 44950, "total_steps": 58920, "loss": 0.0, "lr": 3.2342760900434887e-07, "epoch": 3.8144942294636794, "percentage": 76.29, "elapsed_time": "1:10:53", "remaining_time": "0:22:01", "throughput": 10147.93, "total_tokens": 43159488}
{"current_steps": 44955, "total_steps": 58920, "loss": 0.0, "lr": 3.2320950922824866e-07, "epoch": 3.814918533604888, "percentage": 76.3, "elapsed_time": "1:10:53", "remaining_time": "0:22:01", "throughput": 10148.11, "total_tokens": 43164032}
{"current_steps": 44960, "total_steps": 58920, "loss": 0.0, "lr": 3.229914688380707e-07, "epoch": 3.8153428377460963, "percentage": 76.31, "elapsed_time": "1:10:53", "remaining_time": "0:22:00", "throughput": 10149.08, "total_tokens": 43173312}
{"current_steps": 44965, "total_steps": 58920, "loss": 0.0004, "lr": 3.227734878529463e-07, "epoch": 3.8157671418873047, "percentage": 76.32, "elapsed_time": "1:10:54", "remaining_time": "0:22:00", "throughput": 10149.26, "total_tokens": 43177920}
{"current_steps": 44970, "total_steps": 58920, "loss": 0.0, "lr": 3.225555662920041e-07, "epoch": 3.816191446028513, "percentage": 76.32, "elapsed_time": "1:10:54", "remaining_time": "0:21:59", "throughput": 10149.39, "total_tokens": 43182208}
{"current_steps": 44975, "total_steps": 58920, "loss": 0.0, "lr": 3.223377041743642e-07, "epoch": 3.8166157501697215, "percentage": 76.33, "elapsed_time": "1:10:55", "remaining_time": "0:21:59", "throughput": 10149.59, "total_tokens": 43186944}
{"current_steps": 44980, "total_steps": 58920, "loss": 0.0, "lr": 3.221199015191448e-07, "epoch": 3.81704005431093, "percentage": 76.34, "elapsed_time": "1:10:55", "remaining_time": "0:21:58", "throughput": 10149.81, "total_tokens": 43191808}
{"current_steps": 44985, "total_steps": 58920, "loss": 0.0, "lr": 3.2190215834545597e-07, "epoch": 3.8174643584521384, "percentage": 76.35, "elapsed_time": "1:10:55", "remaining_time": "0:21:58", "throughput": 10149.95, "total_tokens": 43196224}
{"current_steps": 44990, "total_steps": 58920, "loss": 0.0, "lr": 3.2168447467240465e-07, "epoch": 3.817888662593347, "percentage": 76.36, "elapsed_time": "1:10:56", "remaining_time": "0:21:57", "throughput": 10150.17, "total_tokens": 43201024}
{"current_steps": 44995, "total_steps": 58920, "loss": 0.0, "lr": 3.2146685051909217e-07, "epoch": 3.8183129667345552, "percentage": 76.37, "elapsed_time": "1:10:56", "remaining_time": "0:21:57", "throughput": 10150.34, "total_tokens": 43205568}
{"current_steps": 45000, "total_steps": 58920, "loss": 0.0, "lr": 3.2124928590461287e-07, "epoch": 3.8187372708757636, "percentage": 76.37, "elapsed_time": "1:10:56", "remaining_time": "0:21:56", "throughput": 10150.55, "total_tokens": 43210368}
{"current_steps": 45005, "total_steps": 58920, "loss": 0.0, "lr": 3.210317808480589e-07, "epoch": 3.819161575016972, "percentage": 76.38, "elapsed_time": "1:10:57", "remaining_time": "0:21:56", "throughput": 10150.74, "total_tokens": 43215040}
{"current_steps": 45010, "total_steps": 58920, "loss": 0.0682, "lr": 3.208143353685141e-07, "epoch": 3.8195858791581805, "percentage": 76.39, "elapsed_time": "1:10:57", "remaining_time": "0:21:55", "throughput": 10150.92, "total_tokens": 43219712}
{"current_steps": 45015, "total_steps": 58920, "loss": 0.0, "lr": 3.2059694948505945e-07, "epoch": 3.820010183299389, "percentage": 76.4, "elapsed_time": "1:10:58", "remaining_time": "0:21:55", "throughput": 10151.14, "total_tokens": 43224512}
{"current_steps": 45020, "total_steps": 58920, "loss": 0.0, "lr": 3.2037962321676947e-07, "epoch": 3.8204344874405973, "percentage": 76.41, "elapsed_time": "1:10:58", "remaining_time": "0:21:54", "throughput": 10151.38, "total_tokens": 43229376}
{"current_steps": 45025, "total_steps": 58920, "loss": 0.0, "lr": 3.2016235658271383e-07, "epoch": 3.8208587915818057, "percentage": 76.42, "elapsed_time": "1:10:58", "remaining_time": "0:21:54", "throughput": 10151.69, "total_tokens": 43234752}
{"current_steps": 45030, "total_steps": 58920, "loss": 0.0, "lr": 3.1994514960195686e-07, "epoch": 3.821283095723014, "percentage": 76.43, "elapsed_time": "1:10:59", "remaining_time": "0:21:53", "throughput": 10151.99, "total_tokens": 43240064}
{"current_steps": 45035, "total_steps": 58920, "loss": 0.0, "lr": 3.1972800229355777e-07, "epoch": 3.8217073998642226, "percentage": 76.43, "elapsed_time": "1:10:59", "remaining_time": "0:21:53", "throughput": 10152.19, "total_tokens": 43244736}
{"current_steps": 45040, "total_steps": 58920, "loss": 0.0, "lr": 3.1951091467657023e-07, "epoch": 3.822131704005431, "percentage": 76.44, "elapsed_time": "1:11:00", "remaining_time": "0:21:52", "throughput": 10152.47, "total_tokens": 43249856}
{"current_steps": 45045, "total_steps": 58920, "loss": 0.0001, "lr": 3.192938867700431e-07, "epoch": 3.8225560081466394, "percentage": 76.45, "elapsed_time": "1:11:00", "remaining_time": "0:21:52", "throughput": 10152.76, "total_tokens": 43255104}
{"current_steps": 45050, "total_steps": 58920, "loss": 0.0, "lr": 3.190769185930198e-07, "epoch": 3.822980312287848, "percentage": 76.46, "elapsed_time": "1:11:00", "remaining_time": "0:21:51", "throughput": 10153.04, "total_tokens": 43260288}
{"current_steps": 45055, "total_steps": 58920, "loss": 0.0, "lr": 3.1886001016453824e-07, "epoch": 3.8234046164290563, "percentage": 76.47, "elapsed_time": "1:11:01", "remaining_time": "0:21:51", "throughput": 10153.22, "total_tokens": 43264896}
{"current_steps": 45060, "total_steps": 58920, "loss": 0.0, "lr": 3.186431615036317e-07, "epoch": 3.8238289205702647, "percentage": 76.48, "elapsed_time": "1:11:01", "remaining_time": "0:21:50", "throughput": 10153.59, "total_tokens": 43270592}
{"current_steps": 45065, "total_steps": 58920, "loss": 0.0, "lr": 3.184263726293276e-07, "epoch": 3.824253224711473, "percentage": 76.49, "elapsed_time": "1:11:01", "remaining_time": "0:21:50", "throughput": 10153.72, "total_tokens": 43274944}
{"current_steps": 45070, "total_steps": 58920, "loss": 0.0001, "lr": 3.1820964356064864e-07, "epoch": 3.8246775288526815, "percentage": 76.49, "elapsed_time": "1:11:02", "remaining_time": "0:21:49", "throughput": 10153.99, "total_tokens": 43280000}
{"current_steps": 45075, "total_steps": 58920, "loss": 0.0, "lr": 3.1799297431661175e-07, "epoch": 3.82510183299389, "percentage": 76.5, "elapsed_time": "1:11:02", "remaining_time": "0:21:49", "throughput": 10154.18, "total_tokens": 43284608}
{"current_steps": 45080, "total_steps": 58920, "loss": 0.0, "lr": 3.1777636491622894e-07, "epoch": 3.8255261371350984, "percentage": 76.51, "elapsed_time": "1:11:03", "remaining_time": "0:21:48", "throughput": 10154.36, "total_tokens": 43289280}
{"current_steps": 45085, "total_steps": 58920, "loss": 0.0, "lr": 3.1755981537850706e-07, "epoch": 3.825950441276307, "percentage": 76.52, "elapsed_time": "1:11:03", "remaining_time": "0:21:48", "throughput": 10154.57, "total_tokens": 43294080}
{"current_steps": 45090, "total_steps": 58920, "loss": 0.0, "lr": 3.1734332572244737e-07, "epoch": 3.826374745417515, "percentage": 76.53, "elapsed_time": "1:11:03", "remaining_time": "0:21:47", "throughput": 10154.8, "total_tokens": 43299008}
{"current_steps": 45095, "total_steps": 58920, "loss": 0.0, "lr": 3.1712689596704623e-07, "epoch": 3.8267990495587236, "percentage": 76.54, "elapsed_time": "1:11:04", "remaining_time": "0:21:47", "throughput": 10154.97, "total_tokens": 43303552}
{"current_steps": 45100, "total_steps": 58920, "loss": 0.0, "lr": 3.1691052613129434e-07, "epoch": 3.827223353699932, "percentage": 76.54, "elapsed_time": "1:11:04", "remaining_time": "0:21:46", "throughput": 10155.15, "total_tokens": 43308160}
{"current_steps": 45105, "total_steps": 58920, "loss": 0.0, "lr": 3.1669421623417756e-07, "epoch": 3.8276476578411405, "percentage": 76.55, "elapsed_time": "1:11:05", "remaining_time": "0:21:46", "throughput": 10155.37, "total_tokens": 43312960}
{"current_steps": 45110, "total_steps": 58920, "loss": 0.0, "lr": 3.1647796629467616e-07, "epoch": 3.828071961982349, "percentage": 76.56, "elapsed_time": "1:11:05", "remaining_time": "0:21:45", "throughput": 10155.58, "total_tokens": 43317696}
{"current_steps": 45115, "total_steps": 58920, "loss": 0.0, "lr": 3.1626177633176553e-07, "epoch": 3.8284962661235573, "percentage": 76.57, "elapsed_time": "1:11:05", "remaining_time": "0:21:45", "throughput": 10155.81, "total_tokens": 43322560}
{"current_steps": 45120, "total_steps": 58920, "loss": 0.0, "lr": 3.1604564636441487e-07, "epoch": 3.8289205702647657, "percentage": 76.58, "elapsed_time": "1:11:06", "remaining_time": "0:21:44", "throughput": 10155.98, "total_tokens": 43327168}
{"current_steps": 45125, "total_steps": 58920, "loss": 0.0, "lr": 3.1582957641159013e-07, "epoch": 3.829344874405974, "percentage": 76.59, "elapsed_time": "1:11:06", "remaining_time": "0:21:44", "throughput": 10156.19, "total_tokens": 43331904}
{"current_steps": 45130, "total_steps": 58920, "loss": 0.0, "lr": 3.1561356649224957e-07, "epoch": 3.8297691785471826, "percentage": 76.6, "elapsed_time": "1:11:06", "remaining_time": "0:21:43", "throughput": 10156.39, "total_tokens": 43336704}
{"current_steps": 45135, "total_steps": 58920, "loss": 0.0154, "lr": 3.153976166253475e-07, "epoch": 3.830193482688391, "percentage": 76.6, "elapsed_time": "1:11:07", "remaining_time": "0:21:43", "throughput": 10156.61, "total_tokens": 43341504}
{"current_steps": 45140, "total_steps": 58920, "loss": 0.0, "lr": 3.151817268298329e-07, "epoch": 3.8306177868295994, "percentage": 76.61, "elapsed_time": "1:11:07", "remaining_time": "0:21:42", "throughput": 10156.71, "total_tokens": 43345728}
{"current_steps": 45145, "total_steps": 58920, "loss": 0.0014, "lr": 3.1496589712464885e-07, "epoch": 3.831042090970808, "percentage": 76.62, "elapsed_time": "1:11:08", "remaining_time": "0:21:42", "throughput": 10156.87, "total_tokens": 43350272}
{"current_steps": 45150, "total_steps": 58920, "loss": 0.0, "lr": 3.1475012752873466e-07, "epoch": 3.8314663951120163, "percentage": 76.63, "elapsed_time": "1:11:08", "remaining_time": "0:21:41", "throughput": 10157.06, "total_tokens": 43354880}
{"current_steps": 45155, "total_steps": 58920, "loss": 0.0, "lr": 3.145344180610221e-07, "epoch": 3.8318906992532247, "percentage": 76.64, "elapsed_time": "1:11:08", "remaining_time": "0:21:41", "throughput": 10157.21, "total_tokens": 43359360}
{"current_steps": 45160, "total_steps": 58920, "loss": 0.0, "lr": 3.1431876874044005e-07, "epoch": 3.832315003394433, "percentage": 76.65, "elapsed_time": "1:11:09", "remaining_time": "0:21:40", "throughput": 10157.36, "total_tokens": 43363840}
{"current_steps": 45165, "total_steps": 58920, "loss": 0.0, "lr": 3.1410317958591014e-07, "epoch": 3.8327393075356415, "percentage": 76.65, "elapsed_time": "1:11:09", "remaining_time": "0:21:40", "throughput": 10157.6, "total_tokens": 43368832}
{"current_steps": 45170, "total_steps": 58920, "loss": 0.0, "lr": 3.1388765061634957e-07, "epoch": 3.83316361167685, "percentage": 76.66, "elapsed_time": "1:11:09", "remaining_time": "0:21:39", "throughput": 10157.92, "total_tokens": 43374208}
{"current_steps": 45175, "total_steps": 58920, "loss": 0.0, "lr": 3.13672181850671e-07, "epoch": 3.8335879158180584, "percentage": 76.67, "elapsed_time": "1:11:10", "remaining_time": "0:21:39", "throughput": 10158.05, "total_tokens": 43378624}
{"current_steps": 45180, "total_steps": 58920, "loss": 0.0, "lr": 3.1345677330777985e-07, "epoch": 3.8340122199592668, "percentage": 76.68, "elapsed_time": "1:11:10", "remaining_time": "0:21:38", "throughput": 10158.19, "total_tokens": 43383040}
{"current_steps": 45185, "total_steps": 58920, "loss": 0.0432, "lr": 3.132414250065788e-07, "epoch": 3.834436524100475, "percentage": 76.69, "elapsed_time": "1:11:11", "remaining_time": "0:21:38", "throughput": 10158.57, "total_tokens": 43388800}
{"current_steps": 45190, "total_steps": 58920, "loss": 0.0, "lr": 3.1302613696596246e-07, "epoch": 3.8348608282416836, "percentage": 76.7, "elapsed_time": "1:11:11", "remaining_time": "0:21:37", "throughput": 10158.84, "total_tokens": 43393984}
{"current_steps": 45195, "total_steps": 58920, "loss": 0.0, "lr": 3.128109092048229e-07, "epoch": 3.835285132382892, "percentage": 76.71, "elapsed_time": "1:11:11", "remaining_time": "0:21:37", "throughput": 10159.0, "total_tokens": 43398528}
{"current_steps": 45200, "total_steps": 58920, "loss": 0.0, "lr": 3.125957417420444e-07, "epoch": 3.8357094365241005, "percentage": 76.71, "elapsed_time": "1:11:12", "remaining_time": "0:21:36", "throughput": 10159.37, "total_tokens": 43404160}
{"current_steps": 45205, "total_steps": 58920, "loss": 0.0014, "lr": 3.12380634596508e-07, "epoch": 3.836133740665309, "percentage": 76.72, "elapsed_time": "1:11:12", "remaining_time": "0:21:36", "throughput": 10159.71, "total_tokens": 43409728}
{"current_steps": 45210, "total_steps": 58920, "loss": 0.0, "lr": 3.121655877870886e-07, "epoch": 3.8365580448065173, "percentage": 76.73, "elapsed_time": "1:11:13", "remaining_time": "0:21:35", "throughput": 10159.94, "total_tokens": 43414592}
{"current_steps": 45215, "total_steps": 58920, "loss": 0.0, "lr": 3.119506013326548e-07, "epoch": 3.8369823489477257, "percentage": 76.74, "elapsed_time": "1:11:13", "remaining_time": "0:21:35", "throughput": 10160.19, "total_tokens": 43419584}
{"current_steps": 45220, "total_steps": 58920, "loss": 0.0, "lr": 3.1173567525207223e-07, "epoch": 3.837406653088934, "percentage": 76.75, "elapsed_time": "1:11:13", "remaining_time": "0:21:34", "throughput": 10160.29, "total_tokens": 43423808}
{"current_steps": 45225, "total_steps": 58920, "loss": 0.0, "lr": 3.115208095641985e-07, "epoch": 3.8378309572301426, "percentage": 76.76, "elapsed_time": "1:11:14", "remaining_time": "0:21:34", "throughput": 10160.49, "total_tokens": 43428544}
{"current_steps": 45230, "total_steps": 58920, "loss": 0.0, "lr": 3.1130600428788835e-07, "epoch": 3.838255261371351, "percentage": 76.77, "elapsed_time": "1:11:14", "remaining_time": "0:21:33", "throughput": 10160.63, "total_tokens": 43432960}
{"current_steps": 45235, "total_steps": 58920, "loss": 0.0, "lr": 3.1109125944198976e-07, "epoch": 3.8386795655125594, "percentage": 76.77, "elapsed_time": "1:11:15", "remaining_time": "0:21:33", "throughput": 10160.9, "total_tokens": 43438080}
{"current_steps": 45240, "total_steps": 58920, "loss": 0.0, "lr": 3.108765750453458e-07, "epoch": 3.839103869653768, "percentage": 76.78, "elapsed_time": "1:11:15", "remaining_time": "0:21:32", "throughput": 10161.22, "total_tokens": 43443520}
{"current_steps": 45245, "total_steps": 58920, "loss": 0.0, "lr": 3.106619511167944e-07, "epoch": 3.8395281737949762, "percentage": 76.79, "elapsed_time": "1:11:15", "remaining_time": "0:21:32", "throughput": 10161.4, "total_tokens": 43448128}
{"current_steps": 45250, "total_steps": 58920, "loss": 0.0, "lr": 3.10447387675168e-07, "epoch": 3.8399524779361847, "percentage": 76.8, "elapsed_time": "1:11:16", "remaining_time": "0:21:31", "throughput": 10161.68, "total_tokens": 43453248}
{"current_steps": 45255, "total_steps": 58920, "loss": 0.0169, "lr": 3.1023288473929356e-07, "epoch": 3.840376782077393, "percentage": 76.81, "elapsed_time": "1:11:16", "remaining_time": "0:21:31", "throughput": 10161.89, "total_tokens": 43458048}
{"current_steps": 45260, "total_steps": 58920, "loss": 0.0, "lr": 3.100184423279931e-07, "epoch": 3.8408010862186015, "percentage": 76.82, "elapsed_time": "1:11:16", "remaining_time": "0:21:30", "throughput": 10162.03, "total_tokens": 43462464}
{"current_steps": 45265, "total_steps": 58920, "loss": 0.0, "lr": 3.0980406046008335e-07, "epoch": 3.84122539035981, "percentage": 76.82, "elapsed_time": "1:11:17", "remaining_time": "0:21:30", "throughput": 10162.26, "total_tokens": 43467392}
{"current_steps": 45270, "total_steps": 58920, "loss": 0.0, "lr": 3.0958973915437516e-07, "epoch": 3.8416496945010183, "percentage": 76.83, "elapsed_time": "1:11:17", "remaining_time": "0:21:29", "throughput": 10162.48, "total_tokens": 43472256}
{"current_steps": 45275, "total_steps": 58920, "loss": 0.0, "lr": 3.093754784296747e-07, "epoch": 3.8420739986422268, "percentage": 76.84, "elapsed_time": "1:11:18", "remaining_time": "0:21:29", "throughput": 10162.73, "total_tokens": 43477312}
{"current_steps": 45280, "total_steps": 58920, "loss": 0.05, "lr": 3.0916127830478255e-07, "epoch": 3.842498302783435, "percentage": 76.85, "elapsed_time": "1:11:18", "remaining_time": "0:21:28", "throughput": 10163.02, "total_tokens": 43482560}
{"current_steps": 45285, "total_steps": 58920, "loss": 0.0, "lr": 3.08947138798494e-07, "epoch": 3.8429226069246436, "percentage": 76.86, "elapsed_time": "1:11:18", "remaining_time": "0:21:28", "throughput": 10163.19, "total_tokens": 43487104}
{"current_steps": 45290, "total_steps": 58920, "loss": 0.0, "lr": 3.087330599295989e-07, "epoch": 3.843346911065852, "percentage": 76.87, "elapsed_time": "1:11:19", "remaining_time": "0:21:27", "throughput": 10163.37, "total_tokens": 43491712}
{"current_steps": 45295, "total_steps": 58920, "loss": 0.0, "lr": 3.085190417168819e-07, "epoch": 3.8437712152070604, "percentage": 76.88, "elapsed_time": "1:11:19", "remaining_time": "0:21:27", "throughput": 10163.61, "total_tokens": 43496704}
{"current_steps": 45300, "total_steps": 58920, "loss": 0.0, "lr": 3.083050841791226e-07, "epoch": 3.844195519348269, "percentage": 76.88, "elapsed_time": "1:11:20", "remaining_time": "0:21:26", "throughput": 10163.85, "total_tokens": 43501632}
{"current_steps": 45305, "total_steps": 58920, "loss": 0.0, "lr": 3.080911873350948e-07, "epoch": 3.8446198234894773, "percentage": 76.89, "elapsed_time": "1:11:20", "remaining_time": "0:21:26", "throughput": 10163.97, "total_tokens": 43505920}
{"current_steps": 45310, "total_steps": 58920, "loss": 0.0676, "lr": 3.0787735120356706e-07, "epoch": 3.8450441276306857, "percentage": 76.9, "elapsed_time": "1:11:20", "remaining_time": "0:21:25", "throughput": 10164.18, "total_tokens": 43510784}
{"current_steps": 45315, "total_steps": 58920, "loss": 0.0, "lr": 3.0766357580330285e-07, "epoch": 3.845468431771894, "percentage": 76.91, "elapsed_time": "1:11:21", "remaining_time": "0:21:25", "throughput": 10164.44, "total_tokens": 43515840}
{"current_steps": 45320, "total_steps": 58920, "loss": 0.0, "lr": 3.0744986115306027e-07, "epoch": 3.8458927359131025, "percentage": 76.92, "elapsed_time": "1:11:21", "remaining_time": "0:21:24", "throughput": 10164.66, "total_tokens": 43520640}
{"current_steps": 45325, "total_steps": 58920, "loss": 0.0, "lr": 3.0723620727159185e-07, "epoch": 3.846317040054311, "percentage": 76.93, "elapsed_time": "1:11:21", "remaining_time": "0:21:24", "throughput": 10164.86, "total_tokens": 43525440}
{"current_steps": 45330, "total_steps": 58920, "loss": 0.0, "lr": 3.0702261417764506e-07, "epoch": 3.8467413441955194, "percentage": 76.93, "elapsed_time": "1:11:22", "remaining_time": "0:21:23", "throughput": 10165.09, "total_tokens": 43530304}
{"current_steps": 45335, "total_steps": 58920, "loss": 0.0, "lr": 3.0680908188996204e-07, "epoch": 3.847165648336728, "percentage": 76.94, "elapsed_time": "1:11:22", "remaining_time": "0:21:23", "throughput": 10165.36, "total_tokens": 43535424}
{"current_steps": 45340, "total_steps": 58920, "loss": 0.0004, "lr": 3.065956104272791e-07, "epoch": 3.8475899524779362, "percentage": 76.95, "elapsed_time": "1:11:23", "remaining_time": "0:21:22", "throughput": 10165.59, "total_tokens": 43540352}
{"current_steps": 45345, "total_steps": 58920, "loss": 0.0, "lr": 3.063821998083279e-07, "epoch": 3.8480142566191446, "percentage": 76.96, "elapsed_time": "1:11:23", "remaining_time": "0:21:22", "throughput": 10165.79, "total_tokens": 43545088}
{"current_steps": 45350, "total_steps": 58920, "loss": 0.0, "lr": 3.0616885005183445e-07, "epoch": 3.848438560760353, "percentage": 76.97, "elapsed_time": "1:11:23", "remaining_time": "0:21:21", "throughput": 10166.0, "total_tokens": 43549888}
{"current_steps": 45355, "total_steps": 58920, "loss": 0.0, "lr": 3.059555611765192e-07, "epoch": 3.8488628649015615, "percentage": 76.98, "elapsed_time": "1:11:24", "remaining_time": "0:21:21", "throughput": 10166.27, "total_tokens": 43554944}
{"current_steps": 45360, "total_steps": 58920, "loss": 0.0, "lr": 3.0574233320109746e-07, "epoch": 3.84928716904277, "percentage": 76.99, "elapsed_time": "1:11:24", "remaining_time": "0:21:20", "throughput": 10166.45, "total_tokens": 43559616}
{"current_steps": 45365, "total_steps": 58920, "loss": 0.0, "lr": 3.0552916614427994e-07, "epoch": 3.8497114731839783, "percentage": 76.99, "elapsed_time": "1:11:25", "remaining_time": "0:21:20", "throughput": 10166.62, "total_tokens": 43564224}
{"current_steps": 45370, "total_steps": 58920, "loss": 0.0, "lr": 3.053160600247701e-07, "epoch": 3.8501357773251867, "percentage": 77.0, "elapsed_time": "1:11:25", "remaining_time": "0:21:19", "throughput": 10166.91, "total_tokens": 43569472}
{"current_steps": 45375, "total_steps": 58920, "loss": 0.0, "lr": 3.051030148612684e-07, "epoch": 3.850560081466395, "percentage": 77.01, "elapsed_time": "1:11:25", "remaining_time": "0:21:19", "throughput": 10167.04, "total_tokens": 43573824}
{"current_steps": 45380, "total_steps": 58920, "loss": 0.0, "lr": 3.04890030672468e-07, "epoch": 3.8509843856076036, "percentage": 77.02, "elapsed_time": "1:11:26", "remaining_time": "0:21:18", "throughput": 10167.17, "total_tokens": 43578176}
{"current_steps": 45385, "total_steps": 58920, "loss": 0.0, "lr": 3.046771074770573e-07, "epoch": 3.851408689748812, "percentage": 77.03, "elapsed_time": "1:11:26", "remaining_time": "0:21:18", "throughput": 10167.32, "total_tokens": 43582656}
{"current_steps": 45390, "total_steps": 58920, "loss": 0.0, "lr": 3.044642452937207e-07, "epoch": 3.8518329938900204, "percentage": 77.04, "elapsed_time": "1:11:26", "remaining_time": "0:21:17", "throughput": 10167.55, "total_tokens": 43587520}
{"current_steps": 45395, "total_steps": 58920, "loss": 0.0, "lr": 3.042514441411347e-07, "epoch": 3.852257298031229, "percentage": 77.05, "elapsed_time": "1:11:27", "remaining_time": "0:21:17", "throughput": 10167.76, "total_tokens": 43592320}
{"current_steps": 45400, "total_steps": 58920, "loss": 0.0, "lr": 3.0403870403797315e-07, "epoch": 3.8526816021724373, "percentage": 77.05, "elapsed_time": "1:11:27", "remaining_time": "0:21:16", "throughput": 10168.08, "total_tokens": 43597760}
{"current_steps": 45405, "total_steps": 58920, "loss": 0.0, "lr": 3.038260250029019e-07, "epoch": 3.8531059063136457, "percentage": 77.06, "elapsed_time": "1:11:28", "remaining_time": "0:21:16", "throughput": 10168.31, "total_tokens": 43602624}
{"current_steps": 45410, "total_steps": 58920, "loss": 0.0, "lr": 3.0361340705458405e-07, "epoch": 3.853530210454854, "percentage": 77.07, "elapsed_time": "1:11:28", "remaining_time": "0:21:15", "throughput": 10168.54, "total_tokens": 43607552}
{"current_steps": 45415, "total_steps": 58920, "loss": 0.0, "lr": 3.0340085021167506e-07, "epoch": 3.8539545145960625, "percentage": 77.08, "elapsed_time": "1:11:28", "remaining_time": "0:21:15", "throughput": 10168.83, "total_tokens": 43612736}
{"current_steps": 45420, "total_steps": 58920, "loss": 0.0, "lr": 3.0318835449282623e-07, "epoch": 3.854378818737271, "percentage": 77.09, "elapsed_time": "1:11:29", "remaining_time": "0:21:14", "throughput": 10168.98, "total_tokens": 43617216}
{"current_steps": 45425, "total_steps": 58920, "loss": 0.0, "lr": 3.0297591991668393e-07, "epoch": 3.8548031228784794, "percentage": 77.1, "elapsed_time": "1:11:29", "remaining_time": "0:21:14", "throughput": 10169.17, "total_tokens": 43621888}
{"current_steps": 45430, "total_steps": 58920, "loss": 0.0, "lr": 3.027635465018875e-07, "epoch": 3.855227427019688, "percentage": 77.1, "elapsed_time": "1:11:30", "remaining_time": "0:21:13", "throughput": 10169.38, "total_tokens": 43626688}
{"current_steps": 45435, "total_steps": 58920, "loss": 0.0, "lr": 3.025512342670732e-07, "epoch": 3.855651731160896, "percentage": 77.11, "elapsed_time": "1:11:30", "remaining_time": "0:21:13", "throughput": 10169.7, "total_tokens": 43632064}
{"current_steps": 45440, "total_steps": 58920, "loss": 0.0251, "lr": 3.0233898323086927e-07, "epoch": 3.8560760353021046, "percentage": 77.12, "elapsed_time": "1:11:30", "remaining_time": "0:21:12", "throughput": 10169.86, "total_tokens": 43636608}
{"current_steps": 45445, "total_steps": 58920, "loss": 0.0, "lr": 3.0212679341190093e-07, "epoch": 3.856500339443313, "percentage": 77.13, "elapsed_time": "1:11:31", "remaining_time": "0:21:12", "throughput": 10170.04, "total_tokens": 43641344}
{"current_steps": 45450, "total_steps": 58920, "loss": 0.0, "lr": 3.019146648287869e-07, "epoch": 3.8569246435845215, "percentage": 77.14, "elapsed_time": "1:11:31", "remaining_time": "0:21:11", "throughput": 10170.16, "total_tokens": 43645632}
{"current_steps": 45455, "total_steps": 58920, "loss": 0.0, "lr": 3.017025975001406e-07, "epoch": 3.85734894772573, "percentage": 77.15, "elapsed_time": "1:11:31", "remaining_time": "0:21:11", "throughput": 10170.28, "total_tokens": 43649920}
{"current_steps": 45460, "total_steps": 58920, "loss": 0.0, "lr": 3.0149059144457044e-07, "epoch": 3.8577732518669383, "percentage": 77.16, "elapsed_time": "1:11:32", "remaining_time": "0:21:10", "throughput": 10170.43, "total_tokens": 43654400}
{"current_steps": 45465, "total_steps": 58920, "loss": 0.0, "lr": 3.012786466806784e-07, "epoch": 3.8581975560081467, "percentage": 77.16, "elapsed_time": "1:11:32", "remaining_time": "0:21:10", "throughput": 10170.61, "total_tokens": 43659008}
{"current_steps": 45470, "total_steps": 58920, "loss": 0.0, "lr": 3.010667632270626e-07, "epoch": 3.858621860149355, "percentage": 77.17, "elapsed_time": "1:11:33", "remaining_time": "0:21:09", "throughput": 10170.82, "total_tokens": 43663872}
{"current_steps": 45475, "total_steps": 58920, "loss": 0.0, "lr": 3.008549411023149e-07, "epoch": 3.8590461642905636, "percentage": 77.18, "elapsed_time": "1:11:33", "remaining_time": "0:21:09", "throughput": 10170.97, "total_tokens": 43668352}
{"current_steps": 45480, "total_steps": 58920, "loss": 0.0, "lr": 3.006431803250218e-07, "epoch": 3.859470468431772, "percentage": 77.19, "elapsed_time": "1:11:33", "remaining_time": "0:21:08", "throughput": 10171.11, "total_tokens": 43672768}
{"current_steps": 45485, "total_steps": 58920, "loss": 0.0156, "lr": 3.004314809137646e-07, "epoch": 3.8598947725729804, "percentage": 77.2, "elapsed_time": "1:11:34", "remaining_time": "0:21:08", "throughput": 10171.42, "total_tokens": 43678080}
{"current_steps": 45490, "total_steps": 58920, "loss": 0.0, "lr": 3.0021984288711924e-07, "epoch": 3.860319076714189, "percentage": 77.21, "elapsed_time": "1:11:34", "remaining_time": "0:21:07", "throughput": 10171.7, "total_tokens": 43683264}
{"current_steps": 45495, "total_steps": 58920, "loss": 0.0, "lr": 3.0000826626365606e-07, "epoch": 3.8607433808553973, "percentage": 77.21, "elapsed_time": "1:11:34", "remaining_time": "0:21:07", "throughput": 10171.82, "total_tokens": 43687616}
{"current_steps": 45500, "total_steps": 58920, "loss": 0.0, "lr": 2.9979675106194023e-07, "epoch": 3.8611676849966057, "percentage": 77.22, "elapsed_time": "1:11:35", "remaining_time": "0:21:06", "throughput": 10172.06, "total_tokens": 43692672}
{"current_steps": 45505, "total_steps": 58920, "loss": 0.0, "lr": 2.995852973005314e-07, "epoch": 3.861591989137814, "percentage": 77.23, "elapsed_time": "1:11:35", "remaining_time": "0:21:06", "throughput": 10172.32, "total_tokens": 43697728}
{"current_steps": 45510, "total_steps": 58920, "loss": 0.0, "lr": 2.99373904997984e-07, "epoch": 3.8620162932790225, "percentage": 77.24, "elapsed_time": "1:11:36", "remaining_time": "0:21:05", "throughput": 10172.46, "total_tokens": 43702144}
{"current_steps": 45515, "total_steps": 58920, "loss": 0.0, "lr": 2.991625741728467e-07, "epoch": 3.862440597420231, "percentage": 77.25, "elapsed_time": "1:11:36", "remaining_time": "0:21:05", "throughput": 10172.6, "total_tokens": 43706560}
{"current_steps": 45520, "total_steps": 58920, "loss": 0.0, "lr": 2.9895130484366327e-07, "epoch": 3.8628649015614394, "percentage": 77.26, "elapsed_time": "1:11:36", "remaining_time": "0:21:04", "throughput": 10172.76, "total_tokens": 43711104}
{"current_steps": 45525, "total_steps": 58920, "loss": 0.0, "lr": 2.987400970289716e-07, "epoch": 3.8632892057026478, "percentage": 77.27, "elapsed_time": "1:11:37", "remaining_time": "0:21:04", "throughput": 10173.18, "total_tokens": 43717120}
{"current_steps": 45530, "total_steps": 58920, "loss": 0.0, "lr": 2.985289507473046e-07, "epoch": 3.863713509843856, "percentage": 77.27, "elapsed_time": "1:11:37", "remaining_time": "0:21:03", "throughput": 10173.43, "total_tokens": 43722176}
{"current_steps": 45535, "total_steps": 58920, "loss": 0.0, "lr": 2.9831786601718945e-07, "epoch": 3.8641378139850646, "percentage": 77.28, "elapsed_time": "1:11:38", "remaining_time": "0:21:03", "throughput": 10173.66, "total_tokens": 43727104}
{"current_steps": 45540, "total_steps": 58920, "loss": 0.0, "lr": 2.9810684285714815e-07, "epoch": 3.864562118126273, "percentage": 77.29, "elapsed_time": "1:11:38", "remaining_time": "0:21:02", "throughput": 10173.86, "total_tokens": 43731904}
{"current_steps": 45545, "total_steps": 58920, "loss": 0.0, "lr": 2.978958812856973e-07, "epoch": 3.8649864222674815, "percentage": 77.3, "elapsed_time": "1:11:38", "remaining_time": "0:21:02", "throughput": 10173.96, "total_tokens": 43736128}
{"current_steps": 45550, "total_steps": 58920, "loss": 0.0, "lr": 2.976849813213479e-07, "epoch": 3.86541072640869, "percentage": 77.31, "elapsed_time": "1:11:39", "remaining_time": "0:21:01", "throughput": 10174.15, "total_tokens": 43740864}
{"current_steps": 45555, "total_steps": 58920, "loss": 0.0, "lr": 2.9747414298260567e-07, "epoch": 3.8658350305498983, "percentage": 77.32, "elapsed_time": "1:11:39", "remaining_time": "0:21:01", "throughput": 10174.24, "total_tokens": 43745024}
{"current_steps": 45560, "total_steps": 58920, "loss": 0.0, "lr": 2.972633662879709e-07, "epoch": 3.8662593346911067, "percentage": 77.33, "elapsed_time": "1:11:39", "remaining_time": "0:21:00", "throughput": 10174.42, "total_tokens": 43749696}
{"current_steps": 45565, "total_steps": 58920, "loss": 0.0, "lr": 2.970526512559386e-07, "epoch": 3.866683638832315, "percentage": 77.33, "elapsed_time": "1:11:40", "remaining_time": "0:21:00", "throughput": 10174.7, "total_tokens": 43754880}
{"current_steps": 45570, "total_steps": 58920, "loss": 0.0, "lr": 2.968419979049981e-07, "epoch": 3.8671079429735236, "percentage": 77.34, "elapsed_time": "1:11:40", "remaining_time": "0:20:59", "throughput": 10174.84, "total_tokens": 43759296}
{"current_steps": 45575, "total_steps": 58920, "loss": 0.0, "lr": 2.9663140625363326e-07, "epoch": 3.867532247114732, "percentage": 77.35, "elapsed_time": "1:11:41", "remaining_time": "0:20:59", "throughput": 10175.01, "total_tokens": 43763904}
{"current_steps": 45580, "total_steps": 58920, "loss": 0.0, "lr": 2.964208763203236e-07, "epoch": 3.8679565512559404, "percentage": 77.36, "elapsed_time": "1:11:41", "remaining_time": "0:20:58", "throughput": 10175.16, "total_tokens": 43768320}
{"current_steps": 45585, "total_steps": 58920, "loss": 0.0, "lr": 2.962104081235416e-07, "epoch": 3.868380855397149, "percentage": 77.37, "elapsed_time": "1:11:41", "remaining_time": "0:20:58", "throughput": 10175.44, "total_tokens": 43773504}
{"current_steps": 45590, "total_steps": 58920, "loss": 0.0, "lr": 2.960000016817551e-07, "epoch": 3.8688051595383572, "percentage": 77.38, "elapsed_time": "1:11:42", "remaining_time": "0:20:57", "throughput": 10175.71, "total_tokens": 43778688}
{"current_steps": 45595, "total_steps": 58920, "loss": 0.0, "lr": 2.9578965701342685e-07, "epoch": 3.8692294636795657, "percentage": 77.38, "elapsed_time": "1:11:42", "remaining_time": "0:20:57", "throughput": 10175.91, "total_tokens": 43783424}
{"current_steps": 45600, "total_steps": 58920, "loss": 0.0, "lr": 2.9557937413701315e-07, "epoch": 3.869653767820774, "percentage": 77.39, "elapsed_time": "1:11:43", "remaining_time": "0:20:56", "throughput": 10176.15, "total_tokens": 43788288}
{"current_steps": 45605, "total_steps": 58920, "loss": 0.0, "lr": 2.953691530709668e-07, "epoch": 3.8700780719619825, "percentage": 77.4, "elapsed_time": "1:11:43", "remaining_time": "0:20:56", "throughput": 10176.26, "total_tokens": 43792576}
{"current_steps": 45610, "total_steps": 58920, "loss": 0.0029, "lr": 2.951589938337326e-07, "epoch": 3.870502376103191, "percentage": 77.41, "elapsed_time": "1:11:43", "remaining_time": "0:20:55", "throughput": 10176.55, "total_tokens": 43797760}
{"current_steps": 45615, "total_steps": 58920, "loss": 0.0, "lr": 2.949488964437524e-07, "epoch": 3.8709266802443993, "percentage": 77.42, "elapsed_time": "1:11:44", "remaining_time": "0:20:55", "throughput": 10176.68, "total_tokens": 43802112}
{"current_steps": 45620, "total_steps": 58920, "loss": 0.0, "lr": 2.9473886091946046e-07, "epoch": 3.8713509843856078, "percentage": 77.43, "elapsed_time": "1:11:44", "remaining_time": "0:20:54", "throughput": 10176.86, "total_tokens": 43806720}
{"current_steps": 45625, "total_steps": 58920, "loss": 0.0, "lr": 2.945288872792877e-07, "epoch": 3.871775288526816, "percentage": 77.44, "elapsed_time": "1:11:44", "remaining_time": "0:20:54", "throughput": 10177.08, "total_tokens": 43811520}
{"current_steps": 45630, "total_steps": 58920, "loss": 0.0, "lr": 2.9431897554165766e-07, "epoch": 3.8721995926680246, "percentage": 77.44, "elapsed_time": "1:11:45", "remaining_time": "0:20:53", "throughput": 10177.22, "total_tokens": 43815936}
{"current_steps": 45635, "total_steps": 58920, "loss": 0.0, "lr": 2.9410912572498935e-07, "epoch": 3.872623896809233, "percentage": 77.45, "elapsed_time": "1:11:45", "remaining_time": "0:20:53", "throughput": 10177.53, "total_tokens": 43821248}
{"current_steps": 45640, "total_steps": 58920, "loss": 0.0, "lr": 2.9389933784769727e-07, "epoch": 3.873048200950441, "percentage": 77.46, "elapsed_time": "1:11:46", "remaining_time": "0:20:52", "throughput": 10177.7, "total_tokens": 43825792}
{"current_steps": 45645, "total_steps": 58920, "loss": 0.0, "lr": 2.9368961192818844e-07, "epoch": 3.87347250509165, "percentage": 77.47, "elapsed_time": "1:11:46", "remaining_time": "0:20:52", "throughput": 10177.95, "total_tokens": 43830848}
{"current_steps": 45650, "total_steps": 58920, "loss": 0.0195, "lr": 2.934799479848665e-07, "epoch": 3.873896809232858, "percentage": 77.48, "elapsed_time": "1:11:46", "remaining_time": "0:20:51", "throughput": 10178.22, "total_tokens": 43835904}
{"current_steps": 45655, "total_steps": 58920, "loss": 0.0, "lr": 2.9327034603612767e-07, "epoch": 3.8743211133740667, "percentage": 77.49, "elapsed_time": "1:11:47", "remaining_time": "0:20:51", "throughput": 10178.43, "total_tokens": 43840704}
{"current_steps": 45660, "total_steps": 58920, "loss": 0.0, "lr": 2.9306080610036463e-07, "epoch": 3.8747454175152747, "percentage": 77.49, "elapsed_time": "1:11:47", "remaining_time": "0:20:50", "throughput": 10178.69, "total_tokens": 43845824}
{"current_steps": 45665, "total_steps": 58920, "loss": 0.0, "lr": 2.928513281959638e-07, "epoch": 3.8751697216564835, "percentage": 77.5, "elapsed_time": "1:11:47", "remaining_time": "0:20:50", "throughput": 10178.91, "total_tokens": 43850624}
{"current_steps": 45670, "total_steps": 58920, "loss": 0.0, "lr": 2.926419123413051e-07, "epoch": 3.8755940257976915, "percentage": 77.51, "elapsed_time": "1:11:48", "remaining_time": "0:20:49", "throughput": 10179.13, "total_tokens": 43855424}
{"current_steps": 45675, "total_steps": 58920, "loss": 0.0, "lr": 2.9243255855476533e-07, "epoch": 3.8760183299389004, "percentage": 77.52, "elapsed_time": "1:11:48", "remaining_time": "0:20:49", "throughput": 10179.21, "total_tokens": 43859520}
{"current_steps": 45680, "total_steps": 58920, "loss": 0.0, "lr": 2.922232668547133e-07, "epoch": 3.8764426340801084, "percentage": 77.53, "elapsed_time": "1:11:49", "remaining_time": "0:20:48", "throughput": 10179.35, "total_tokens": 43863936}
{"current_steps": 45685, "total_steps": 58920, "loss": 0.0, "lr": 2.920140372595148e-07, "epoch": 3.8768669382213172, "percentage": 77.54, "elapsed_time": "1:11:49", "remaining_time": "0:20:48", "throughput": 10179.59, "total_tokens": 43868864}
{"current_steps": 45690, "total_steps": 58920, "loss": 0.0, "lr": 2.918048697875277e-07, "epoch": 3.877291242362525, "percentage": 77.55, "elapsed_time": "1:11:49", "remaining_time": "0:20:47", "throughput": 10179.86, "total_tokens": 43873984}
{"current_steps": 45695, "total_steps": 58920, "loss": 0.0, "lr": 2.9159576445710676e-07, "epoch": 3.877715546503734, "percentage": 77.55, "elapsed_time": "1:11:50", "remaining_time": "0:20:47", "throughput": 10180.09, "total_tokens": 43878848}
{"current_steps": 45700, "total_steps": 58920, "loss": 0.0, "lr": 2.9138672128659967e-07, "epoch": 3.878139850644942, "percentage": 77.56, "elapsed_time": "1:11:50", "remaining_time": "0:20:46", "throughput": 10180.27, "total_tokens": 43883520}
{"current_steps": 45705, "total_steps": 58920, "loss": 0.0, "lr": 2.911777402943495e-07, "epoch": 3.878564154786151, "percentage": 77.57, "elapsed_time": "1:11:51", "remaining_time": "0:20:46", "throughput": 10180.44, "total_tokens": 43888064}
{"current_steps": 45710, "total_steps": 58920, "loss": 0.0, "lr": 2.9096882149869364e-07, "epoch": 3.878988458927359, "percentage": 77.58, "elapsed_time": "1:11:51", "remaining_time": "0:20:45", "throughput": 10180.65, "total_tokens": 43892864}
{"current_steps": 45715, "total_steps": 58920, "loss": 0.0, "lr": 2.907599649179631e-07, "epoch": 3.8794127630685677, "percentage": 77.59, "elapsed_time": "1:11:51", "remaining_time": "0:20:45", "throughput": 10180.89, "total_tokens": 43897792}
{"current_steps": 45720, "total_steps": 58920, "loss": 0.0, "lr": 2.905511705704853e-07, "epoch": 3.8798370672097757, "percentage": 77.6, "elapsed_time": "1:11:52", "remaining_time": "0:20:44", "throughput": 10181.09, "total_tokens": 43902528}
{"current_steps": 45725, "total_steps": 58920, "loss": 0.0, "lr": 2.9034243847458075e-07, "epoch": 3.8802613713509846, "percentage": 77.61, "elapsed_time": "1:11:52", "remaining_time": "0:20:44", "throughput": 10181.34, "total_tokens": 43907584}
{"current_steps": 45730, "total_steps": 58920, "loss": 0.0, "lr": 2.901337686485651e-07, "epoch": 3.8806856754921926, "percentage": 77.61, "elapsed_time": "1:11:52", "remaining_time": "0:20:43", "throughput": 10181.6, "total_tokens": 43912640}
{"current_steps": 45735, "total_steps": 58920, "loss": 0.0, "lr": 2.8992516111074826e-07, "epoch": 3.8811099796334014, "percentage": 77.62, "elapsed_time": "1:11:53", "remaining_time": "0:20:43", "throughput": 10181.88, "total_tokens": 43917824}
{"current_steps": 45740, "total_steps": 58920, "loss": 0.0, "lr": 2.8971661587943485e-07, "epoch": 3.8815342837746094, "percentage": 77.63, "elapsed_time": "1:11:53", "remaining_time": "0:20:43", "throughput": 10182.18, "total_tokens": 43923072}
{"current_steps": 45745, "total_steps": 58920, "loss": 0.0, "lr": 2.8950813297292386e-07, "epoch": 3.8819585879158183, "percentage": 77.64, "elapsed_time": "1:11:54", "remaining_time": "0:20:42", "throughput": 10182.3, "total_tokens": 43927424}
{"current_steps": 45750, "total_steps": 58920, "loss": 0.0, "lr": 2.8929971240950903e-07, "epoch": 3.8823828920570262, "percentage": 77.65, "elapsed_time": "1:11:54", "remaining_time": "0:20:42", "throughput": 10182.5, "total_tokens": 43932224}
{"current_steps": 45755, "total_steps": 58920, "loss": 0.043, "lr": 2.8909135420747844e-07, "epoch": 3.882807196198235, "percentage": 77.66, "elapsed_time": "1:11:54", "remaining_time": "0:20:41", "throughput": 10182.66, "total_tokens": 43936768}
{"current_steps": 45760, "total_steps": 58920, "loss": 0.0, "lr": 2.8888305838511486e-07, "epoch": 3.883231500339443, "percentage": 77.66, "elapsed_time": "1:11:55", "remaining_time": "0:20:41", "throughput": 10182.85, "total_tokens": 43941440}
{"current_steps": 45765, "total_steps": 58920, "loss": 0.0, "lr": 2.8867482496069527e-07, "epoch": 3.883655804480652, "percentage": 77.67, "elapsed_time": "1:11:55", "remaining_time": "0:20:40", "throughput": 10183.02, "total_tokens": 43946048}
{"current_steps": 45770, "total_steps": 58920, "loss": 0.0, "lr": 2.884666539524917e-07, "epoch": 3.88408010862186, "percentage": 77.68, "elapsed_time": "1:11:55", "remaining_time": "0:20:40", "throughput": 10183.06, "total_tokens": 43949952}
{"current_steps": 45775, "total_steps": 58920, "loss": 0.0, "lr": 2.8825854537877024e-07, "epoch": 3.884504412763069, "percentage": 77.69, "elapsed_time": "1:11:56", "remaining_time": "0:20:39", "throughput": 10183.15, "total_tokens": 43954112}
{"current_steps": 45780, "total_steps": 58920, "loss": 0.0, "lr": 2.8805049925779167e-07, "epoch": 3.8849287169042768, "percentage": 77.7, "elapsed_time": "1:11:56", "remaining_time": "0:20:39", "throughput": 10183.42, "total_tokens": 43959232}
{"current_steps": 45785, "total_steps": 58920, "loss": 0.0, "lr": 2.8784251560781134e-07, "epoch": 3.8853530210454856, "percentage": 77.71, "elapsed_time": "1:11:57", "remaining_time": "0:20:38", "throughput": 10183.69, "total_tokens": 43964352}
{"current_steps": 45790, "total_steps": 58920, "loss": 0.0, "lr": 2.8763459444707895e-07, "epoch": 3.8857773251866936, "percentage": 77.72, "elapsed_time": "1:11:57", "remaining_time": "0:20:38", "throughput": 10184.16, "total_tokens": 43970688}
{"current_steps": 45795, "total_steps": 58920, "loss": 0.0, "lr": 2.87426735793839e-07, "epoch": 3.8862016293279025, "percentage": 77.72, "elapsed_time": "1:11:57", "remaining_time": "0:20:37", "throughput": 10184.44, "total_tokens": 43975872}
{"current_steps": 45800, "total_steps": 58920, "loss": 0.0, "lr": 2.8721893966633024e-07, "epoch": 3.8866259334691104, "percentage": 77.73, "elapsed_time": "1:11:58", "remaining_time": "0:20:37", "throughput": 10184.61, "total_tokens": 43980416}
{"current_steps": 45805, "total_steps": 58920, "loss": 0.0, "lr": 2.8701120608278594e-07, "epoch": 3.8870502376103193, "percentage": 77.74, "elapsed_time": "1:11:58", "remaining_time": "0:20:36", "throughput": 10184.87, "total_tokens": 43985472}
{"current_steps": 45810, "total_steps": 58920, "loss": 0.0, "lr": 2.868035350614342e-07, "epoch": 3.8874745417515273, "percentage": 77.75, "elapsed_time": "1:11:59", "remaining_time": "0:20:36", "throughput": 10185.1, "total_tokens": 43990400}
{"current_steps": 45815, "total_steps": 58920, "loss": 0.0, "lr": 2.8659592662049725e-07, "epoch": 3.887898845892736, "percentage": 77.76, "elapsed_time": "1:11:59", "remaining_time": "0:20:35", "throughput": 10185.3, "total_tokens": 43995136}
{"current_steps": 45820, "total_steps": 58920, "loss": 0.0, "lr": 2.8638838077819194e-07, "epoch": 3.888323150033944, "percentage": 77.77, "elapsed_time": "1:11:59", "remaining_time": "0:20:35", "throughput": 10185.51, "total_tokens": 43999936}
{"current_steps": 45825, "total_steps": 58920, "loss": 0.0, "lr": 2.8618089755272945e-07, "epoch": 3.888747454175153, "percentage": 77.77, "elapsed_time": "1:12:00", "remaining_time": "0:20:34", "throughput": 10185.74, "total_tokens": 44004864}
{"current_steps": 45830, "total_steps": 58920, "loss": 0.0, "lr": 2.8597347696231654e-07, "epoch": 3.889171758316361, "percentage": 77.78, "elapsed_time": "1:12:00", "remaining_time": "0:20:34", "throughput": 10185.92, "total_tokens": 44009472}
{"current_steps": 45835, "total_steps": 58920, "loss": 0.0, "lr": 2.857661190251528e-07, "epoch": 3.88959606245757, "percentage": 77.79, "elapsed_time": "1:12:01", "remaining_time": "0:20:33", "throughput": 10186.14, "total_tokens": 44014400}
{"current_steps": 45840, "total_steps": 58920, "loss": 0.0, "lr": 2.855588237594334e-07, "epoch": 3.890020366598778, "percentage": 77.8, "elapsed_time": "1:12:01", "remaining_time": "0:20:33", "throughput": 10186.51, "total_tokens": 44020096}
{"current_steps": 45845, "total_steps": 58920, "loss": 0.0, "lr": 2.8535159118334774e-07, "epoch": 3.8904446707399867, "percentage": 77.81, "elapsed_time": "1:12:01", "remaining_time": "0:20:32", "throughput": 10186.78, "total_tokens": 44025216}
{"current_steps": 45850, "total_steps": 58920, "loss": 0.0, "lr": 2.8514442131507934e-07, "epoch": 3.8908689748811947, "percentage": 77.82, "elapsed_time": "1:12:02", "remaining_time": "0:20:32", "throughput": 10186.92, "total_tokens": 44029632}
{"current_steps": 45855, "total_steps": 58920, "loss": 0.0, "lr": 2.8493731417280764e-07, "epoch": 3.8912932790224035, "percentage": 77.83, "elapsed_time": "1:12:02", "remaining_time": "0:20:31", "throughput": 10187.14, "total_tokens": 44034496}
{"current_steps": 45860, "total_steps": 58920, "loss": 0.0272, "lr": 2.847302697747044e-07, "epoch": 3.8917175831636115, "percentage": 77.83, "elapsed_time": "1:12:02", "remaining_time": "0:20:31", "throughput": 10187.29, "total_tokens": 44039040}
{"current_steps": 45865, "total_steps": 58920, "loss": 0.0, "lr": 2.84523288138938e-07, "epoch": 3.8921418873048204, "percentage": 77.84, "elapsed_time": "1:12:03", "remaining_time": "0:20:30", "throughput": 10187.53, "total_tokens": 44043968}
{"current_steps": 45870, "total_steps": 58920, "loss": 0.0, "lr": 2.843163692836692e-07, "epoch": 3.8925661914460283, "percentage": 77.85, "elapsed_time": "1:12:03", "remaining_time": "0:20:30", "throughput": 10187.7, "total_tokens": 44048576}
{"current_steps": 45875, "total_steps": 58920, "loss": 0.0, "lr": 2.8410951322705544e-07, "epoch": 3.892990495587237, "percentage": 77.86, "elapsed_time": "1:12:04", "remaining_time": "0:20:29", "throughput": 10187.97, "total_tokens": 44053696}
{"current_steps": 45880, "total_steps": 58920, "loss": 0.0, "lr": 2.8390271998724746e-07, "epoch": 3.893414799728445, "percentage": 77.87, "elapsed_time": "1:12:04", "remaining_time": "0:20:29", "throughput": 10188.16, "total_tokens": 44058368}
{"current_steps": 45885, "total_steps": 58920, "loss": 0.0121, "lr": 2.836959895823897e-07, "epoch": 3.893839103869654, "percentage": 77.88, "elapsed_time": "1:12:04", "remaining_time": "0:20:28", "throughput": 10188.32, "total_tokens": 44062912}
{"current_steps": 45890, "total_steps": 58920, "loss": 0.0, "lr": 2.8348932203062324e-07, "epoch": 3.894263408010862, "percentage": 77.89, "elapsed_time": "1:12:05", "remaining_time": "0:20:28", "throughput": 10188.48, "total_tokens": 44067456}
{"current_steps": 45895, "total_steps": 58920, "loss": 0.0, "lr": 2.8328271735008125e-07, "epoch": 3.894687712152071, "percentage": 77.89, "elapsed_time": "1:12:05", "remaining_time": "0:20:27", "throughput": 10188.65, "total_tokens": 44072064}
{"current_steps": 45900, "total_steps": 58920, "loss": 0.0, "lr": 2.8307617555889374e-07, "epoch": 3.895112016293279, "percentage": 77.9, "elapsed_time": "1:12:05", "remaining_time": "0:20:27", "throughput": 10188.86, "total_tokens": 44076864}
{"current_steps": 45905, "total_steps": 58920, "loss": 0.0, "lr": 2.8286969667518267e-07, "epoch": 3.8955363204344873, "percentage": 77.91, "elapsed_time": "1:12:06", "remaining_time": "0:20:26", "throughput": 10189.04, "total_tokens": 44081472}
{"current_steps": 45910, "total_steps": 58920, "loss": 0.0, "lr": 2.82663280717067e-07, "epoch": 3.8959606245756957, "percentage": 77.92, "elapsed_time": "1:12:06", "remaining_time": "0:20:26", "throughput": 10189.42, "total_tokens": 44087232}
{"current_steps": 45915, "total_steps": 58920, "loss": 0.0, "lr": 2.824569277026587e-07, "epoch": 3.896384928716904, "percentage": 77.93, "elapsed_time": "1:12:07", "remaining_time": "0:20:25", "throughput": 10189.7, "total_tokens": 44092416}
{"current_steps": 45920, "total_steps": 58920, "loss": 0.0, "lr": 2.8225063765006376e-07, "epoch": 3.8968092328581125, "percentage": 77.94, "elapsed_time": "1:12:07", "remaining_time": "0:20:25", "throughput": 10189.84, "total_tokens": 44096832}
{"current_steps": 45925, "total_steps": 58920, "loss": 0.0, "lr": 2.8204441057738447e-07, "epoch": 3.897233536999321, "percentage": 77.94, "elapsed_time": "1:12:07", "remaining_time": "0:20:24", "throughput": 10190.03, "total_tokens": 44101568}
{"current_steps": 45930, "total_steps": 58920, "loss": 0.0, "lr": 2.8183824650271546e-07, "epoch": 3.8976578411405294, "percentage": 77.95, "elapsed_time": "1:12:08", "remaining_time": "0:20:24", "throughput": 10190.37, "total_tokens": 44107136}
{"current_steps": 45935, "total_steps": 58920, "loss": 0.0, "lr": 2.816321454441477e-07, "epoch": 3.898082145281738, "percentage": 77.96, "elapsed_time": "1:12:08", "remaining_time": "0:20:23", "throughput": 10190.56, "total_tokens": 44111872}
{"current_steps": 45940, "total_steps": 58920, "loss": 0.0, "lr": 2.8142610741976545e-07, "epoch": 3.898506449422946, "percentage": 77.97, "elapsed_time": "1:12:09", "remaining_time": "0:20:23", "throughput": 10190.83, "total_tokens": 44117056}
{"current_steps": 45945, "total_steps": 58920, "loss": 0.0, "lr": 2.81220132447648e-07, "epoch": 3.8989307535641546, "percentage": 77.98, "elapsed_time": "1:12:09", "remaining_time": "0:20:22", "throughput": 10191.0, "total_tokens": 44121664}
{"current_steps": 45950, "total_steps": 58920, "loss": 0.0, "lr": 2.8101422054586864e-07, "epoch": 3.899355057705363, "percentage": 77.99, "elapsed_time": "1:12:09", "remaining_time": "0:20:22", "throughput": 10191.25, "total_tokens": 44126720}
{"current_steps": 45955, "total_steps": 58920, "loss": 0.0, "lr": 2.808083717324956e-07, "epoch": 3.8997793618465715, "percentage": 78.0, "elapsed_time": "1:12:10", "remaining_time": "0:20:21", "throughput": 10191.46, "total_tokens": 44131520}
{"current_steps": 45960, "total_steps": 58920, "loss": 0.0, "lr": 2.806025860255914e-07, "epoch": 3.90020366598778, "percentage": 78.0, "elapsed_time": "1:12:10", "remaining_time": "0:20:21", "throughput": 10191.6, "total_tokens": 44135936}
{"current_steps": 45965, "total_steps": 58920, "loss": 0.0, "lr": 2.803968634432128e-07, "epoch": 3.9006279701289883, "percentage": 78.01, "elapsed_time": "1:12:11", "remaining_time": "0:20:20", "throughput": 10191.91, "total_tokens": 44141312}
{"current_steps": 45970, "total_steps": 58920, "loss": 0.0, "lr": 2.801912040034113e-07, "epoch": 3.9010522742701967, "percentage": 78.02, "elapsed_time": "1:12:11", "remaining_time": "0:20:20", "throughput": 10192.2, "total_tokens": 44146560}
{"current_steps": 45975, "total_steps": 58920, "loss": 0.0, "lr": 2.7998560772423287e-07, "epoch": 3.901476578411405, "percentage": 78.03, "elapsed_time": "1:12:11", "remaining_time": "0:20:19", "throughput": 10192.52, "total_tokens": 44152064}
{"current_steps": 45980, "total_steps": 58920, "loss": 0.0, "lr": 2.7978007462371767e-07, "epoch": 3.9019008825526136, "percentage": 78.04, "elapsed_time": "1:12:12", "remaining_time": "0:20:19", "throughput": 10192.8, "total_tokens": 44157248}
{"current_steps": 45985, "total_steps": 58920, "loss": 0.0, "lr": 2.795746047199007e-07, "epoch": 3.902325186693822, "percentage": 78.05, "elapsed_time": "1:12:12", "remaining_time": "0:20:18", "throughput": 10192.98, "total_tokens": 44161920}
{"current_steps": 45990, "total_steps": 58920, "loss": 0.0, "lr": 2.793691980308109e-07, "epoch": 3.9027494908350304, "percentage": 78.05, "elapsed_time": "1:12:12", "remaining_time": "0:20:18", "throughput": 10193.14, "total_tokens": 44166400}
{"current_steps": 45995, "total_steps": 58920, "loss": 0.0, "lr": 2.7916385457447233e-07, "epoch": 3.903173794976239, "percentage": 78.06, "elapsed_time": "1:12:13", "remaining_time": "0:20:17", "throughput": 10193.31, "total_tokens": 44171008}
{"current_steps": 46000, "total_steps": 58920, "loss": 0.0, "lr": 2.7895857436890293e-07, "epoch": 3.9035980991174473, "percentage": 78.07, "elapsed_time": "1:12:13", "remaining_time": "0:20:17", "throughput": 10193.75, "total_tokens": 44177152}
{"current_steps": 46005, "total_steps": 58920, "loss": 0.0, "lr": 2.7875335743211527e-07, "epoch": 3.9040224032586557, "percentage": 78.08, "elapsed_time": "1:12:14", "remaining_time": "0:20:16", "throughput": 10193.94, "total_tokens": 44181824}
{"current_steps": 46010, "total_steps": 58920, "loss": 0.0, "lr": 2.785482037821164e-07, "epoch": 3.904446707399864, "percentage": 78.09, "elapsed_time": "1:12:14", "remaining_time": "0:20:16", "throughput": 10194.08, "total_tokens": 44186240}
{"current_steps": 46015, "total_steps": 58920, "loss": 0.0, "lr": 2.7834311343690786e-07, "epoch": 3.9048710115410725, "percentage": 78.1, "elapsed_time": "1:12:14", "remaining_time": "0:20:15", "throughput": 10194.37, "total_tokens": 44191488}
{"current_steps": 46020, "total_steps": 58920, "loss": 0.0, "lr": 2.7813808641448564e-07, "epoch": 3.905295315682281, "percentage": 78.11, "elapsed_time": "1:12:15", "remaining_time": "0:20:15", "throughput": 10194.57, "total_tokens": 44196224}
{"current_steps": 46025, "total_steps": 58920, "loss": 0.0, "lr": 2.779331227328401e-07, "epoch": 3.9057196198234894, "percentage": 78.11, "elapsed_time": "1:12:15", "remaining_time": "0:20:14", "throughput": 10194.82, "total_tokens": 44201280}
{"current_steps": 46030, "total_steps": 58920, "loss": 0.0, "lr": 2.7772822240995584e-07, "epoch": 3.906143923964698, "percentage": 78.12, "elapsed_time": "1:12:16", "remaining_time": "0:20:14", "throughput": 10194.97, "total_tokens": 44205824}
{"current_steps": 46035, "total_steps": 58920, "loss": 0.0, "lr": 2.775233854638125e-07, "epoch": 3.906568228105906, "percentage": 78.13, "elapsed_time": "1:12:16", "remaining_time": "0:20:13", "throughput": 10195.17, "total_tokens": 44210624}
{"current_steps": 46040, "total_steps": 58920, "loss": 0.0, "lr": 2.773186119123833e-07, "epoch": 3.9069925322471146, "percentage": 78.14, "elapsed_time": "1:12:16", "remaining_time": "0:20:13", "throughput": 10195.34, "total_tokens": 44215232}
{"current_steps": 46045, "total_steps": 58920, "loss": 0.0, "lr": 2.7711390177363716e-07, "epoch": 3.907416836388323, "percentage": 78.15, "elapsed_time": "1:12:17", "remaining_time": "0:20:12", "throughput": 10195.58, "total_tokens": 44220224}
{"current_steps": 46050, "total_steps": 58920, "loss": 0.0, "lr": 2.7690925506553595e-07, "epoch": 3.9078411405295315, "percentage": 78.16, "elapsed_time": "1:12:17", "remaining_time": "0:20:12", "throughput": 10195.82, "total_tokens": 44225216}
{"current_steps": 46055, "total_steps": 58920, "loss": 0.0, "lr": 2.7670467180603686e-07, "epoch": 3.90826544467074, "percentage": 78.17, "elapsed_time": "1:12:17", "remaining_time": "0:20:11", "throughput": 10195.94, "total_tokens": 44229504}
{"current_steps": 46060, "total_steps": 58920, "loss": 0.0, "lr": 2.765001520130914e-07, "epoch": 3.9086897488119483, "percentage": 78.17, "elapsed_time": "1:12:18", "remaining_time": "0:20:11", "throughput": 10196.15, "total_tokens": 44234304}
{"current_steps": 46065, "total_steps": 58920, "loss": 0.0, "lr": 2.762956957046451e-07, "epoch": 3.9091140529531567, "percentage": 78.18, "elapsed_time": "1:12:18", "remaining_time": "0:20:10", "throughput": 10196.37, "total_tokens": 44239168}
{"current_steps": 46070, "total_steps": 58920, "loss": 0.0, "lr": 2.760913028986391e-07, "epoch": 3.909538357094365, "percentage": 78.19, "elapsed_time": "1:12:19", "remaining_time": "0:20:10", "throughput": 10196.56, "total_tokens": 44243840}
{"current_steps": 46075, "total_steps": 58920, "loss": 0.0, "lr": 2.7588697361300716e-07, "epoch": 3.9099626612355736, "percentage": 78.2, "elapsed_time": "1:12:19", "remaining_time": "0:20:09", "throughput": 10196.77, "total_tokens": 44248640}
{"current_steps": 46080, "total_steps": 58920, "loss": 0.0, "lr": 2.756827078656794e-07, "epoch": 3.910386965376782, "percentage": 78.21, "elapsed_time": "1:12:19", "remaining_time": "0:20:09", "throughput": 10197.09, "total_tokens": 44254080}
{"current_steps": 46085, "total_steps": 58920, "loss": 0.0, "lr": 2.7547850567457853e-07, "epoch": 3.9108112695179904, "percentage": 78.22, "elapsed_time": "1:12:20", "remaining_time": "0:20:08", "throughput": 10197.27, "total_tokens": 44258688}
{"current_steps": 46090, "total_steps": 58920, "loss": 0.0, "lr": 2.7527436705762277e-07, "epoch": 3.911235573659199, "percentage": 78.22, "elapsed_time": "1:12:20", "remaining_time": "0:20:08", "throughput": 10197.47, "total_tokens": 44263488}
{"current_steps": 46095, "total_steps": 58920, "loss": 0.0, "lr": 2.7507029203272516e-07, "epoch": 3.9116598778004072, "percentage": 78.23, "elapsed_time": "1:12:21", "remaining_time": "0:20:07", "throughput": 10197.76, "total_tokens": 44268736}
{"current_steps": 46100, "total_steps": 58920, "loss": 0.0, "lr": 2.748662806177915e-07, "epoch": 3.9120841819416157, "percentage": 78.24, "elapsed_time": "1:12:21", "remaining_time": "0:20:07", "throughput": 10197.94, "total_tokens": 44273344}
{"current_steps": 46105, "total_steps": 58920, "loss": 0.0, "lr": 2.7466233283072427e-07, "epoch": 3.912508486082824, "percentage": 78.25, "elapsed_time": "1:12:21", "remaining_time": "0:20:06", "throughput": 10198.22, "total_tokens": 44278528}
{"current_steps": 46110, "total_steps": 58920, "loss": 0.0, "lr": 2.744584486894179e-07, "epoch": 3.9129327902240325, "percentage": 78.26, "elapsed_time": "1:12:22", "remaining_time": "0:20:06", "throughput": 10198.35, "total_tokens": 44282944}
{"current_steps": 46115, "total_steps": 58920, "loss": 0.0, "lr": 2.742546282117637e-07, "epoch": 3.913357094365241, "percentage": 78.27, "elapsed_time": "1:12:22", "remaining_time": "0:20:05", "throughput": 10198.73, "total_tokens": 44288704}
{"current_steps": 46120, "total_steps": 58920, "loss": 0.0, "lr": 2.74050871415645e-07, "epoch": 3.9137813985064493, "percentage": 78.28, "elapsed_time": "1:12:22", "remaining_time": "0:20:05", "throughput": 10198.93, "total_tokens": 44293504}
{"current_steps": 46125, "total_steps": 58920, "loss": 0.0, "lr": 2.7384717831894154e-07, "epoch": 3.9142057026476578, "percentage": 78.28, "elapsed_time": "1:12:23", "remaining_time": "0:20:04", "throughput": 10199.1, "total_tokens": 44298048}
{"current_steps": 46130, "total_steps": 58920, "loss": 0.0, "lr": 2.736435489395267e-07, "epoch": 3.914630006788866, "percentage": 78.29, "elapsed_time": "1:12:23", "remaining_time": "0:20:04", "throughput": 10199.24, "total_tokens": 44302528}
{"current_steps": 46135, "total_steps": 58920, "loss": 0.0068, "lr": 2.734399832952674e-07, "epoch": 3.9150543109300746, "percentage": 78.3, "elapsed_time": "1:12:24", "remaining_time": "0:20:03", "throughput": 10199.59, "total_tokens": 44308160}
{"current_steps": 46140, "total_steps": 58920, "loss": 0.0, "lr": 2.732364814040269e-07, "epoch": 3.915478615071283, "percentage": 78.31, "elapsed_time": "1:12:24", "remaining_time": "0:20:03", "throughput": 10199.75, "total_tokens": 44312704}
{"current_steps": 46145, "total_steps": 58920, "loss": 0.0, "lr": 2.730330432836606e-07, "epoch": 3.9159029192124915, "percentage": 78.32, "elapsed_time": "1:12:24", "remaining_time": "0:20:02", "throughput": 10199.94, "total_tokens": 44317376}
{"current_steps": 46150, "total_steps": 58920, "loss": 0.0, "lr": 2.728296689520204e-07, "epoch": 3.9163272233537, "percentage": 78.33, "elapsed_time": "1:12:25", "remaining_time": "0:20:02", "throughput": 10200.1, "total_tokens": 44321920}
{"current_steps": 46155, "total_steps": 58920, "loss": 0.0159, "lr": 2.7262635842695124e-07, "epoch": 3.9167515274949083, "percentage": 78.34, "elapsed_time": "1:12:25", "remaining_time": "0:20:01", "throughput": 10200.35, "total_tokens": 44326976}
{"current_steps": 46160, "total_steps": 58920, "loss": 0.0, "lr": 2.7242311172629307e-07, "epoch": 3.9171758316361167, "percentage": 78.34, "elapsed_time": "1:12:26", "remaining_time": "0:20:01", "throughput": 10200.6, "total_tokens": 44332032}
{"current_steps": 46165, "total_steps": 58920, "loss": 0.0, "lr": 2.722199288678798e-07, "epoch": 3.917600135777325, "percentage": 78.35, "elapsed_time": "1:12:26", "remaining_time": "0:20:00", "throughput": 10201.13, "total_tokens": 44338752}
{"current_steps": 46170, "total_steps": 58920, "loss": 0.0, "lr": 2.7201680986954024e-07, "epoch": 3.9180244399185336, "percentage": 78.36, "elapsed_time": "1:12:26", "remaining_time": "0:20:00", "throughput": 10201.32, "total_tokens": 44343424}
{"current_steps": 46175, "total_steps": 58920, "loss": 0.0, "lr": 2.7181375474909715e-07, "epoch": 3.918448744059742, "percentage": 78.37, "elapsed_time": "1:12:27", "remaining_time": "0:19:59", "throughput": 10201.44, "total_tokens": 44347776}
{"current_steps": 46180, "total_steps": 58920, "loss": 0.0006, "lr": 2.716107635243681e-07, "epoch": 3.9188730482009504, "percentage": 78.38, "elapsed_time": "1:12:27", "remaining_time": "0:19:59", "throughput": 10201.66, "total_tokens": 44352640}
{"current_steps": 46185, "total_steps": 58920, "loss": 0.0, "lr": 2.7140783621316453e-07, "epoch": 3.919297352342159, "percentage": 78.39, "elapsed_time": "1:12:27", "remaining_time": "0:19:58", "throughput": 10201.86, "total_tokens": 44357440}
{"current_steps": 46190, "total_steps": 58920, "loss": 0.0, "lr": 2.712049728332929e-07, "epoch": 3.9197216564833672, "percentage": 78.39, "elapsed_time": "1:12:28", "remaining_time": "0:19:58", "throughput": 10202.04, "total_tokens": 44362112}
{"current_steps": 46195, "total_steps": 58920, "loss": 0.0001, "lr": 2.710021734025535e-07, "epoch": 3.9201459606245757, "percentage": 78.4, "elapsed_time": "1:12:28", "remaining_time": "0:19:57", "throughput": 10202.26, "total_tokens": 44366912}
{"current_steps": 46200, "total_steps": 58920, "loss": 0.0, "lr": 2.707994379387415e-07, "epoch": 3.920570264765784, "percentage": 78.41, "elapsed_time": "1:12:29", "remaining_time": "0:19:57", "throughput": 10202.49, "total_tokens": 44371776}
{"current_steps": 46205, "total_steps": 58920, "loss": 0.0003, "lr": 2.705967664596459e-07, "epoch": 3.9209945689069925, "percentage": 78.42, "elapsed_time": "1:12:29", "remaining_time": "0:19:56", "throughput": 10202.66, "total_tokens": 44376384}
{"current_steps": 46210, "total_steps": 58920, "loss": 0.0, "lr": 2.7039415898305063e-07, "epoch": 3.921418873048201, "percentage": 78.43, "elapsed_time": "1:12:29", "remaining_time": "0:19:56", "throughput": 10202.86, "total_tokens": 44381120}
{"current_steps": 46215, "total_steps": 58920, "loss": 0.0, "lr": 2.7019161552673363e-07, "epoch": 3.9218431771894093, "percentage": 78.44, "elapsed_time": "1:12:30", "remaining_time": "0:19:55", "throughput": 10203.02, "total_tokens": 44385664}
{"current_steps": 46220, "total_steps": 58920, "loss": 0.0, "lr": 2.699891361084674e-07, "epoch": 3.9222674813306178, "percentage": 78.45, "elapsed_time": "1:12:30", "remaining_time": "0:19:55", "throughput": 10203.15, "total_tokens": 44390016}
{"current_steps": 46225, "total_steps": 58920, "loss": 0.0, "lr": 2.697867207460188e-07, "epoch": 3.922691785471826, "percentage": 78.45, "elapsed_time": "1:12:31", "remaining_time": "0:19:54", "throughput": 10203.38, "total_tokens": 44394944}
{"current_steps": 46230, "total_steps": 58920, "loss": 0.0, "lr": 2.69584369457149e-07, "epoch": 3.9231160896130346, "percentage": 78.46, "elapsed_time": "1:12:31", "remaining_time": "0:19:54", "throughput": 10203.5, "total_tokens": 44399296}
{"current_steps": 46235, "total_steps": 58920, "loss": 0.0, "lr": 2.6938208225961367e-07, "epoch": 3.923540393754243, "percentage": 78.47, "elapsed_time": "1:12:31", "remaining_time": "0:19:53", "throughput": 10203.61, "total_tokens": 44403584}
{"current_steps": 46240, "total_steps": 58920, "loss": 0.0, "lr": 2.691798591711628e-07, "epoch": 3.9239646978954514, "percentage": 78.48, "elapsed_time": "1:12:32", "remaining_time": "0:19:53", "throughput": 10203.81, "total_tokens": 44408384}
{"current_steps": 46245, "total_steps": 58920, "loss": 0.0, "lr": 2.689777002095406e-07, "epoch": 3.92438900203666, "percentage": 78.49, "elapsed_time": "1:12:32", "remaining_time": "0:19:52", "throughput": 10204.03, "total_tokens": 44413248}
{"current_steps": 46250, "total_steps": 58920, "loss": 0.0013, "lr": 2.687756053924859e-07, "epoch": 3.9248133061778683, "percentage": 78.5, "elapsed_time": "1:12:32", "remaining_time": "0:19:52", "throughput": 10204.25, "total_tokens": 44418112}
{"current_steps": 46255, "total_steps": 58920, "loss": 0.0, "lr": 2.685735747377317e-07, "epoch": 3.9252376103190767, "percentage": 78.5, "elapsed_time": "1:12:33", "remaining_time": "0:19:51", "throughput": 10204.39, "total_tokens": 44422528}
{"current_steps": 46260, "total_steps": 58920, "loss": 0.0, "lr": 2.6837160826300555e-07, "epoch": 3.925661914460285, "percentage": 78.51, "elapsed_time": "1:12:33", "remaining_time": "0:19:51", "throughput": 10204.6, "total_tokens": 44427392}
{"current_steps": 46265, "total_steps": 58920, "loss": 0.0, "lr": 2.681697059860292e-07, "epoch": 3.9260862186014935, "percentage": 78.52, "elapsed_time": "1:12:34", "remaining_time": "0:19:50", "throughput": 10204.75, "total_tokens": 44431936}
{"current_steps": 46270, "total_steps": 58920, "loss": 0.0, "lr": 2.6796786792451886e-07, "epoch": 3.926510522742702, "percentage": 78.53, "elapsed_time": "1:12:34", "remaining_time": "0:19:50", "throughput": 10204.92, "total_tokens": 44436544}
{"current_steps": 46275, "total_steps": 58920, "loss": 0.0001, "lr": 2.6776609409618513e-07, "epoch": 3.9269348268839104, "percentage": 78.54, "elapsed_time": "1:12:34", "remaining_time": "0:19:49", "throughput": 10205.12, "total_tokens": 44441344}
{"current_steps": 46280, "total_steps": 58920, "loss": 0.0, "lr": 2.6756438451873263e-07, "epoch": 3.927359131025119, "percentage": 78.55, "elapsed_time": "1:12:35", "remaining_time": "0:19:49", "throughput": 10205.33, "total_tokens": 44446144}
{"current_steps": 46285, "total_steps": 58920, "loss": 0.0449, "lr": 2.6736273920986164e-07, "epoch": 3.927783435166327, "percentage": 78.56, "elapsed_time": "1:12:35", "remaining_time": "0:19:48", "throughput": 10205.43, "total_tokens": 44450304}
{"current_steps": 46290, "total_steps": 58920, "loss": 0.0, "lr": 2.6716115818726436e-07, "epoch": 3.9282077393075356, "percentage": 78.56, "elapsed_time": "1:12:35", "remaining_time": "0:19:48", "throughput": 10205.52, "total_tokens": 44454464}
{"current_steps": 46295, "total_steps": 58920, "loss": 0.0, "lr": 2.6695964146863027e-07, "epoch": 3.928632043448744, "percentage": 78.57, "elapsed_time": "1:12:36", "remaining_time": "0:19:47", "throughput": 10205.63, "total_tokens": 44458752}
{"current_steps": 46300, "total_steps": 58920, "loss": 0.0, "lr": 2.667581890716406e-07, "epoch": 3.9290563475899525, "percentage": 78.58, "elapsed_time": "1:12:36", "remaining_time": "0:19:47", "throughput": 10205.85, "total_tokens": 44463616}
{"current_steps": 46305, "total_steps": 58920, "loss": 0.0001, "lr": 2.6655680101397225e-07, "epoch": 3.929480651731161, "percentage": 78.59, "elapsed_time": "1:12:37", "remaining_time": "0:19:47", "throughput": 10206.0, "total_tokens": 44468096}
{"current_steps": 46310, "total_steps": 58920, "loss": 0.0, "lr": 2.663554773132971e-07, "epoch": 3.9299049558723693, "percentage": 78.6, "elapsed_time": "1:12:37", "remaining_time": "0:19:46", "throughput": 10206.17, "total_tokens": 44472704}
{"current_steps": 46315, "total_steps": 58920, "loss": 0.0, "lr": 2.6615421798727946e-07, "epoch": 3.9303292600135777, "percentage": 78.61, "elapsed_time": "1:12:37", "remaining_time": "0:19:46", "throughput": 10206.32, "total_tokens": 44477184}
{"current_steps": 46320, "total_steps": 58920, "loss": 0.0, "lr": 2.6595302305358026e-07, "epoch": 3.930753564154786, "percentage": 78.62, "elapsed_time": "1:12:38", "remaining_time": "0:19:45", "throughput": 10206.48, "total_tokens": 44481792}
{"current_steps": 46325, "total_steps": 58920, "loss": 0.0, "lr": 2.657518925298523e-07, "epoch": 3.9311778682959946, "percentage": 78.62, "elapsed_time": "1:12:38", "remaining_time": "0:19:45", "throughput": 10206.63, "total_tokens": 44486272}
{"current_steps": 46330, "total_steps": 58920, "loss": 0.0, "lr": 2.655508264337455e-07, "epoch": 3.931602172437203, "percentage": 78.63, "elapsed_time": "1:12:38", "remaining_time": "0:19:44", "throughput": 10206.85, "total_tokens": 44491136}
{"current_steps": 46335, "total_steps": 58920, "loss": 0.0, "lr": 2.6534982478290157e-07, "epoch": 3.9320264765784114, "percentage": 78.64, "elapsed_time": "1:12:39", "remaining_time": "0:19:44", "throughput": 10207.19, "total_tokens": 44496704}
{"current_steps": 46340, "total_steps": 58920, "loss": 0.0, "lr": 2.651488875949578e-07, "epoch": 3.93245078071962, "percentage": 78.65, "elapsed_time": "1:12:39", "remaining_time": "0:19:43", "throughput": 10207.36, "total_tokens": 44501312}
{"current_steps": 46345, "total_steps": 58920, "loss": 0.0, "lr": 2.649480148875466e-07, "epoch": 3.9328750848608283, "percentage": 78.66, "elapsed_time": "1:12:40", "remaining_time": "0:19:43", "throughput": 10207.54, "total_tokens": 44505984}
{"current_steps": 46350, "total_steps": 58920, "loss": 0.0, "lr": 2.647472066782925e-07, "epoch": 3.9332993890020367, "percentage": 78.67, "elapsed_time": "1:12:40", "remaining_time": "0:19:42", "throughput": 10207.8, "total_tokens": 44511040}
{"current_steps": 46355, "total_steps": 58920, "loss": 0.0, "lr": 2.645464629848172e-07, "epoch": 3.933723693143245, "percentage": 78.67, "elapsed_time": "1:12:40", "remaining_time": "0:19:42", "throughput": 10207.95, "total_tokens": 44515584}
{"current_steps": 46360, "total_steps": 58920, "loss": 0.0, "lr": 2.643457838247337e-07, "epoch": 3.9341479972844535, "percentage": 78.68, "elapsed_time": "1:12:41", "remaining_time": "0:19:41", "throughput": 10208.18, "total_tokens": 44520512}
{"current_steps": 46365, "total_steps": 58920, "loss": 0.0, "lr": 2.641451692156519e-07, "epoch": 3.934572301425662, "percentage": 78.69, "elapsed_time": "1:12:41", "remaining_time": "0:19:41", "throughput": 10208.49, "total_tokens": 44525952}
{"current_steps": 46370, "total_steps": 58920, "loss": 0.0, "lr": 2.639446191751747e-07, "epoch": 3.9349966055668704, "percentage": 78.7, "elapsed_time": "1:12:42", "remaining_time": "0:19:40", "throughput": 10208.7, "total_tokens": 44530752}
{"current_steps": 46375, "total_steps": 58920, "loss": 0.0, "lr": 2.6374413372089965e-07, "epoch": 3.935420909708079, "percentage": 78.71, "elapsed_time": "1:12:42", "remaining_time": "0:19:40", "throughput": 10208.83, "total_tokens": 44535168}
{"current_steps": 46380, "total_steps": 58920, "loss": 0.0011, "lr": 2.63543712870419e-07, "epoch": 3.935845213849287, "percentage": 78.72, "elapsed_time": "1:12:42", "remaining_time": "0:19:39", "throughput": 10208.99, "total_tokens": 44539712}
{"current_steps": 46385, "total_steps": 58920, "loss": 0.0, "lr": 2.633433566413179e-07, "epoch": 3.9362695179904956, "percentage": 78.73, "elapsed_time": "1:12:43", "remaining_time": "0:19:39", "throughput": 10209.2, "total_tokens": 44544512}
{"current_steps": 46390, "total_steps": 58920, "loss": 0.0, "lr": 2.631430650511779e-07, "epoch": 3.936693822131704, "percentage": 78.73, "elapsed_time": "1:12:43", "remaining_time": "0:19:38", "throughput": 10209.36, "total_tokens": 44549056}
{"current_steps": 46395, "total_steps": 58920, "loss": 0.0, "lr": 2.6294283811757344e-07, "epoch": 3.9371181262729125, "percentage": 78.74, "elapsed_time": "1:12:43", "remaining_time": "0:19:38", "throughput": 10209.53, "total_tokens": 44553664}
{"current_steps": 46400, "total_steps": 58920, "loss": 0.0, "lr": 2.6274267585807386e-07, "epoch": 3.937542430414121, "percentage": 78.75, "elapsed_time": "1:12:44", "remaining_time": "0:19:37", "throughput": 10209.78, "total_tokens": 44558784}
{"current_steps": 46405, "total_steps": 58920, "loss": 0.0, "lr": 2.625425782902426e-07, "epoch": 3.9379667345553293, "percentage": 78.76, "elapsed_time": "1:12:44", "remaining_time": "0:19:37", "throughput": 10210.01, "total_tokens": 44563712}
{"current_steps": 46410, "total_steps": 58920, "loss": 0.0318, "lr": 2.623425454316376e-07, "epoch": 3.9383910386965377, "percentage": 78.77, "elapsed_time": "1:12:45", "remaining_time": "0:19:36", "throughput": 10210.14, "total_tokens": 44568128}
{"current_steps": 46415, "total_steps": 58920, "loss": 0.0, "lr": 2.6214257729981093e-07, "epoch": 3.938815342837746, "percentage": 78.78, "elapsed_time": "1:12:45", "remaining_time": "0:19:36", "throughput": 10210.31, "total_tokens": 44572736}
{"current_steps": 46420, "total_steps": 58920, "loss": 0.0, "lr": 2.6194267391230905e-07, "epoch": 3.9392396469789546, "percentage": 78.78, "elapsed_time": "1:12:45", "remaining_time": "0:19:35", "throughput": 10210.63, "total_tokens": 44578240}
{"current_steps": 46425, "total_steps": 58920, "loss": 0.0, "lr": 2.617428352866727e-07, "epoch": 3.939663951120163, "percentage": 78.79, "elapsed_time": "1:12:46", "remaining_time": "0:19:35", "throughput": 10210.78, "total_tokens": 44582720}
{"current_steps": 46430, "total_steps": 58920, "loss": 0.0, "lr": 2.6154306144043726e-07, "epoch": 3.9400882552613714, "percentage": 78.8, "elapsed_time": "1:12:46", "remaining_time": "0:19:34", "throughput": 10210.93, "total_tokens": 44587200}
{"current_steps": 46435, "total_steps": 58920, "loss": 0.0, "lr": 2.6134335239113183e-07, "epoch": 3.94051255940258, "percentage": 78.81, "elapsed_time": "1:12:47", "remaining_time": "0:19:34", "throughput": 10211.12, "total_tokens": 44592000}
{"current_steps": 46440, "total_steps": 58920, "loss": 0.0, "lr": 2.611437081562804e-07, "epoch": 3.9409368635437882, "percentage": 78.82, "elapsed_time": "1:12:47", "remaining_time": "0:19:33", "throughput": 10211.44, "total_tokens": 44597440}
{"current_steps": 46445, "total_steps": 58920, "loss": 0.0, "lr": 2.6094412875340086e-07, "epoch": 3.9413611676849967, "percentage": 78.83, "elapsed_time": "1:12:47", "remaining_time": "0:19:33", "throughput": 10211.56, "total_tokens": 44601728}
{"current_steps": 46450, "total_steps": 58920, "loss": 0.0, "lr": 2.607446142000058e-07, "epoch": 3.941785471826205, "percentage": 78.84, "elapsed_time": "1:12:48", "remaining_time": "0:19:32", "throughput": 10211.71, "total_tokens": 44606208}
{"current_steps": 46455, "total_steps": 58920, "loss": 0.0, "lr": 2.605451645136016e-07, "epoch": 3.9422097759674135, "percentage": 78.84, "elapsed_time": "1:12:48", "remaining_time": "0:19:32", "throughput": 10211.84, "total_tokens": 44610624}
{"current_steps": 46460, "total_steps": 58920, "loss": 0.0, "lr": 2.603457797116896e-07, "epoch": 3.942634080108622, "percentage": 78.85, "elapsed_time": "1:12:48", "remaining_time": "0:19:31", "throughput": 10212.08, "total_tokens": 44615616}
{"current_steps": 46465, "total_steps": 58920, "loss": 0.0, "lr": 2.6014645981176485e-07, "epoch": 3.9430583842498304, "percentage": 78.86, "elapsed_time": "1:12:49", "remaining_time": "0:19:31", "throughput": 10212.3, "total_tokens": 44620480}
{"current_steps": 46470, "total_steps": 58920, "loss": 0.0, "lr": 2.5994720483131706e-07, "epoch": 3.9434826883910388, "percentage": 78.87, "elapsed_time": "1:12:49", "remaining_time": "0:19:30", "throughput": 10212.58, "total_tokens": 44625728}
{"current_steps": 46475, "total_steps": 58920, "loss": 0.0186, "lr": 2.5974801478783003e-07, "epoch": 3.943906992532247, "percentage": 78.88, "elapsed_time": "1:12:50", "remaining_time": "0:19:30", "throughput": 10212.79, "total_tokens": 44630528}
{"current_steps": 46480, "total_steps": 58920, "loss": 0.0, "lr": 2.595488896987821e-07, "epoch": 3.9443312966734556, "percentage": 78.89, "elapsed_time": "1:12:50", "remaining_time": "0:19:29", "throughput": 10213.08, "total_tokens": 44635840}
{"current_steps": 46485, "total_steps": 58920, "loss": 0.0, "lr": 2.5934982958164563e-07, "epoch": 3.944755600814664, "percentage": 78.9, "elapsed_time": "1:12:50", "remaining_time": "0:19:29", "throughput": 10213.26, "total_tokens": 44640448}
{"current_steps": 46490, "total_steps": 58920, "loss": 0.0, "lr": 2.5915083445388763e-07, "epoch": 3.9451799049558725, "percentage": 78.9, "elapsed_time": "1:12:51", "remaining_time": "0:19:28", "throughput": 10213.69, "total_tokens": 44646656}
{"current_steps": 46495, "total_steps": 58920, "loss": 0.0, "lr": 2.5895190433296865e-07, "epoch": 3.945604209097081, "percentage": 78.91, "elapsed_time": "1:12:51", "remaining_time": "0:19:28", "throughput": 10213.94, "total_tokens": 44651776}
{"current_steps": 46500, "total_steps": 58920, "loss": 0.0, "lr": 2.587530392363452e-07, "epoch": 3.9460285132382893, "percentage": 78.92, "elapsed_time": "1:12:52", "remaining_time": "0:19:27", "throughput": 10214.07, "total_tokens": 44656192}
{"current_steps": 46505, "total_steps": 58920, "loss": 0.0, "lr": 2.5855423918146603e-07, "epoch": 3.9464528173794977, "percentage": 78.93, "elapsed_time": "1:12:52", "remaining_time": "0:19:27", "throughput": 10214.34, "total_tokens": 44661440}
{"current_steps": 46510, "total_steps": 58920, "loss": 0.0, "lr": 2.583555041857752e-07, "epoch": 3.946877121520706, "percentage": 78.94, "elapsed_time": "1:12:52", "remaining_time": "0:19:26", "throughput": 10214.55, "total_tokens": 44666304}
{"current_steps": 46515, "total_steps": 58920, "loss": 0.0, "lr": 2.5815683426671144e-07, "epoch": 3.9473014256619146, "percentage": 78.95, "elapsed_time": "1:12:53", "remaining_time": "0:19:26", "throughput": 10214.76, "total_tokens": 44671168}
{"current_steps": 46520, "total_steps": 58920, "loss": 0.0, "lr": 2.5795822944170656e-07, "epoch": 3.947725729803123, "percentage": 78.95, "elapsed_time": "1:12:53", "remaining_time": "0:19:25", "throughput": 10214.95, "total_tokens": 44675904}
{"current_steps": 46525, "total_steps": 58920, "loss": 0.0, "lr": 2.577596897281886e-07, "epoch": 3.9481500339443314, "percentage": 78.96, "elapsed_time": "1:12:53", "remaining_time": "0:19:25", "throughput": 10215.12, "total_tokens": 44680448}
{"current_steps": 46530, "total_steps": 58920, "loss": 0.0, "lr": 2.5756121514357743e-07, "epoch": 3.94857433808554, "percentage": 78.97, "elapsed_time": "1:12:54", "remaining_time": "0:19:24", "throughput": 10215.33, "total_tokens": 44685312}
{"current_steps": 46535, "total_steps": 58920, "loss": 0.0, "lr": 2.573628057052896e-07, "epoch": 3.9489986422267482, "percentage": 78.98, "elapsed_time": "1:12:54", "remaining_time": "0:19:24", "throughput": 10215.57, "total_tokens": 44690304}
{"current_steps": 46540, "total_steps": 58920, "loss": 0.0, "lr": 2.5716446143073377e-07, "epoch": 3.9494229463679567, "percentage": 78.99, "elapsed_time": "1:12:55", "remaining_time": "0:19:23", "throughput": 10215.84, "total_tokens": 44695488}
{"current_steps": 46545, "total_steps": 58920, "loss": 0.0, "lr": 2.5696618233731507e-07, "epoch": 3.949847250509165, "percentage": 79.0, "elapsed_time": "1:12:55", "remaining_time": "0:19:23", "throughput": 10216.08, "total_tokens": 44700480}
{"current_steps": 46550, "total_steps": 58920, "loss": 0.0, "lr": 2.5676796844243075e-07, "epoch": 3.9502715546503735, "percentage": 79.01, "elapsed_time": "1:12:55", "remaining_time": "0:19:22", "throughput": 10216.21, "total_tokens": 44704896}
{"current_steps": 46555, "total_steps": 58920, "loss": 0.0, "lr": 2.5656981976347347e-07, "epoch": 3.950695858791582, "percentage": 79.01, "elapsed_time": "1:12:56", "remaining_time": "0:19:22", "throughput": 10216.44, "total_tokens": 44709824}
{"current_steps": 46560, "total_steps": 58920, "loss": 0.0, "lr": 2.5637173631783107e-07, "epoch": 3.9511201629327903, "percentage": 79.02, "elapsed_time": "1:12:56", "remaining_time": "0:19:21", "throughput": 10216.57, "total_tokens": 44714240}
{"current_steps": 46565, "total_steps": 58920, "loss": 0.0, "lr": 2.5617371812288324e-07, "epoch": 3.9515444670739988, "percentage": 79.03, "elapsed_time": "1:12:57", "remaining_time": "0:19:21", "throughput": 10216.71, "total_tokens": 44718656}
{"current_steps": 46570, "total_steps": 58920, "loss": 0.0, "lr": 2.5597576519600674e-07, "epoch": 3.951968771215207, "percentage": 79.04, "elapsed_time": "1:12:57", "remaining_time": "0:19:20", "throughput": 10216.86, "total_tokens": 44723200}
{"current_steps": 46575, "total_steps": 58920, "loss": 0.0, "lr": 2.5577787755456995e-07, "epoch": 3.9523930753564156, "percentage": 79.05, "elapsed_time": "1:12:57", "remaining_time": "0:19:20", "throughput": 10217.2, "total_tokens": 44728768}
{"current_steps": 46580, "total_steps": 58920, "loss": 0.0, "lr": 2.555800552159377e-07, "epoch": 3.952817379497624, "percentage": 79.06, "elapsed_time": "1:12:58", "remaining_time": "0:19:19", "throughput": 10217.42, "total_tokens": 44733696}
{"current_steps": 46585, "total_steps": 58920, "loss": 0.0, "lr": 2.5538229819746813e-07, "epoch": 3.9532416836388324, "percentage": 79.06, "elapsed_time": "1:12:58", "remaining_time": "0:19:19", "throughput": 10217.65, "total_tokens": 44738624}
{"current_steps": 46590, "total_steps": 58920, "loss": 0.0, "lr": 2.55184606516513e-07, "epoch": 3.953665987780041, "percentage": 79.07, "elapsed_time": "1:12:58", "remaining_time": "0:19:18", "throughput": 10217.94, "total_tokens": 44743936}
{"current_steps": 46595, "total_steps": 58920, "loss": 0.0, "lr": 2.5498698019042e-07, "epoch": 3.9540902919212493, "percentage": 79.08, "elapsed_time": "1:12:59", "remaining_time": "0:19:18", "throughput": 10218.12, "total_tokens": 44748608}
{"current_steps": 46600, "total_steps": 58920, "loss": 0.0, "lr": 2.5478941923652895e-07, "epoch": 3.9545145960624577, "percentage": 79.09, "elapsed_time": "1:12:59", "remaining_time": "0:19:17", "throughput": 10218.33, "total_tokens": 44753408}
{"current_steps": 46605, "total_steps": 58920, "loss": 0.0, "lr": 2.5459192367217617e-07, "epoch": 3.954938900203666, "percentage": 79.1, "elapsed_time": "1:13:00", "remaining_time": "0:19:17", "throughput": 10218.49, "total_tokens": 44757952}
{"current_steps": 46610, "total_steps": 58920, "loss": 0.0, "lr": 2.5439449351469087e-07, "epoch": 3.9553632043448745, "percentage": 79.11, "elapsed_time": "1:13:00", "remaining_time": "0:19:16", "throughput": 10218.63, "total_tokens": 44762432}
{"current_steps": 46615, "total_steps": 58920, "loss": 0.0, "lr": 2.541971287813966e-07, "epoch": 3.955787508486083, "percentage": 79.12, "elapsed_time": "1:13:00", "remaining_time": "0:19:16", "throughput": 10218.84, "total_tokens": 44767232}
{"current_steps": 46620, "total_steps": 58920, "loss": 0.0, "lr": 2.5399982948961176e-07, "epoch": 3.9562118126272914, "percentage": 79.12, "elapsed_time": "1:13:01", "remaining_time": "0:19:15", "throughput": 10219.03, "total_tokens": 44772032}
{"current_steps": 46625, "total_steps": 58920, "loss": 0.0, "lr": 2.538025956566484e-07, "epoch": 3.9566361167685, "percentage": 79.13, "elapsed_time": "1:13:01", "remaining_time": "0:19:15", "throughput": 10219.19, "total_tokens": 44776576}
{"current_steps": 46630, "total_steps": 58920, "loss": 0.0, "lr": 2.536054272998134e-07, "epoch": 3.957060420909708, "percentage": 79.14, "elapsed_time": "1:13:02", "remaining_time": "0:19:14", "throughput": 10219.55, "total_tokens": 44782208}
{"current_steps": 46635, "total_steps": 58920, "loss": 0.0, "lr": 2.5340832443640667e-07, "epoch": 3.9574847250509166, "percentage": 79.15, "elapsed_time": "1:13:02", "remaining_time": "0:19:14", "throughput": 10219.7, "total_tokens": 44786688}
{"current_steps": 46640, "total_steps": 58920, "loss": 0.0, "lr": 2.532112870837243e-07, "epoch": 3.957909029192125, "percentage": 79.16, "elapsed_time": "1:13:02", "remaining_time": "0:19:13", "throughput": 10219.86, "total_tokens": 44791232}
{"current_steps": 46645, "total_steps": 58920, "loss": 0.0, "lr": 2.5301431525905523e-07, "epoch": 3.9583333333333335, "percentage": 79.17, "elapsed_time": "1:13:03", "remaining_time": "0:19:13", "throughput": 10220.03, "total_tokens": 44795840}
{"current_steps": 46650, "total_steps": 58920, "loss": 0.0, "lr": 2.5281740897968294e-07, "epoch": 3.958757637474542, "percentage": 79.18, "elapsed_time": "1:13:03", "remaining_time": "0:19:12", "throughput": 10220.24, "total_tokens": 44800640}
{"current_steps": 46655, "total_steps": 58920, "loss": 0.0, "lr": 2.5262056826288535e-07, "epoch": 3.9591819416157503, "percentage": 79.18, "elapsed_time": "1:13:03", "remaining_time": "0:19:12", "throughput": 10220.49, "total_tokens": 44805696}
{"current_steps": 46660, "total_steps": 58920, "loss": 0.0001, "lr": 2.5242379312593456e-07, "epoch": 3.9596062457569587, "percentage": 79.19, "elapsed_time": "1:13:04", "remaining_time": "0:19:11", "throughput": 10220.7, "total_tokens": 44810496}
{"current_steps": 46665, "total_steps": 58920, "loss": 0.0, "lr": 2.522270835860967e-07, "epoch": 3.960030549898167, "percentage": 79.2, "elapsed_time": "1:13:04", "remaining_time": "0:19:11", "throughput": 10220.92, "total_tokens": 44815424}
{"current_steps": 46670, "total_steps": 58920, "loss": 0.0, "lr": 2.520304396606324e-07, "epoch": 3.9604548540393756, "percentage": 79.21, "elapsed_time": "1:13:05", "remaining_time": "0:19:10", "throughput": 10221.13, "total_tokens": 44820224}
{"current_steps": 46675, "total_steps": 58920, "loss": 0.0, "lr": 2.5183386136679664e-07, "epoch": 3.960879158180584, "percentage": 79.22, "elapsed_time": "1:13:05", "remaining_time": "0:19:10", "throughput": 10221.29, "total_tokens": 44824768}
{"current_steps": 46680, "total_steps": 58920, "loss": 0.0, "lr": 2.5163734872183815e-07, "epoch": 3.9613034623217924, "percentage": 79.23, "elapsed_time": "1:13:05", "remaining_time": "0:19:10", "throughput": 10221.53, "total_tokens": 44829824}
{"current_steps": 46685, "total_steps": 58920, "loss": 0.0, "lr": 2.514409017430005e-07, "epoch": 3.961727766463001, "percentage": 79.23, "elapsed_time": "1:13:06", "remaining_time": "0:19:09", "throughput": 10221.82, "total_tokens": 44835136}
{"current_steps": 46690, "total_steps": 58920, "loss": 0.0, "lr": 2.5124452044752097e-07, "epoch": 3.9621520706042093, "percentage": 79.24, "elapsed_time": "1:13:06", "remaining_time": "0:19:09", "throughput": 10222.07, "total_tokens": 44840192}
{"current_steps": 46695, "total_steps": 58920, "loss": 0.0, "lr": 2.510482048526313e-07, "epoch": 3.9625763747454172, "percentage": 79.25, "elapsed_time": "1:13:06", "remaining_time": "0:19:08", "throughput": 10222.32, "total_tokens": 44845248}
{"current_steps": 46700, "total_steps": 58920, "loss": 0.0021, "lr": 2.508519549755578e-07, "epoch": 3.963000678886626, "percentage": 79.26, "elapsed_time": "1:13:07", "remaining_time": "0:19:08", "throughput": 10222.5, "total_tokens": 44849920}
{"current_steps": 46705, "total_steps": 58920, "loss": 0.0, "lr": 2.506557708335203e-07, "epoch": 3.963424983027834, "percentage": 79.27, "elapsed_time": "1:13:07", "remaining_time": "0:19:07", "throughput": 10222.65, "total_tokens": 44854464}
{"current_steps": 46710, "total_steps": 58920, "loss": 0.0402, "lr": 2.5045965244373345e-07, "epoch": 3.963849287169043, "percentage": 79.28, "elapsed_time": "1:13:08", "remaining_time": "0:19:07", "throughput": 10222.98, "total_tokens": 44859968}
{"current_steps": 46715, "total_steps": 58920, "loss": 0.0459, "lr": 2.5026359982340597e-07, "epoch": 3.964273591310251, "percentage": 79.29, "elapsed_time": "1:13:08", "remaining_time": "0:19:06", "throughput": 10223.14, "total_tokens": 44864512}
{"current_steps": 46720, "total_steps": 58920, "loss": 0.0, "lr": 2.5006761298974067e-07, "epoch": 3.96469789545146, "percentage": 79.29, "elapsed_time": "1:13:08", "remaining_time": "0:19:06", "throughput": 10223.25, "total_tokens": 44868800}
{"current_steps": 46725, "total_steps": 58920, "loss": 0.0033, "lr": 2.4987169195993465e-07, "epoch": 3.9651221995926678, "percentage": 79.3, "elapsed_time": "1:13:09", "remaining_time": "0:19:05", "throughput": 10223.45, "total_tokens": 44873536}
{"current_steps": 46730, "total_steps": 58920, "loss": 0.0, "lr": 2.496758367511793e-07, "epoch": 3.9655465037338766, "percentage": 79.31, "elapsed_time": "1:13:09", "remaining_time": "0:19:05", "throughput": 10223.68, "total_tokens": 44878528}
{"current_steps": 46735, "total_steps": 58920, "loss": 0.0, "lr": 2.4948004738066e-07, "epoch": 3.9659708078750846, "percentage": 79.32, "elapsed_time": "1:13:10", "remaining_time": "0:19:04", "throughput": 10223.93, "total_tokens": 44883648}
{"current_steps": 46740, "total_steps": 58920, "loss": 0.0, "lr": 2.4928432386555743e-07, "epoch": 3.9663951120162935, "percentage": 79.33, "elapsed_time": "1:13:10", "remaining_time": "0:19:04", "throughput": 10224.1, "total_tokens": 44888320}
{"current_steps": 46745, "total_steps": 58920, "loss": 0.0309, "lr": 2.4908866622304436e-07, "epoch": 3.9668194161575014, "percentage": 79.34, "elapsed_time": "1:13:10", "remaining_time": "0:19:03", "throughput": 10224.23, "total_tokens": 44892736}
{"current_steps": 46750, "total_steps": 58920, "loss": 0.0, "lr": 2.488930744702903e-07, "epoch": 3.9672437202987103, "percentage": 79.34, "elapsed_time": "1:13:11", "remaining_time": "0:19:03", "throughput": 10224.45, "total_tokens": 44897600}
{"current_steps": 46755, "total_steps": 58920, "loss": 0.0271, "lr": 2.4869754862445667e-07, "epoch": 3.9676680244399183, "percentage": 79.35, "elapsed_time": "1:13:11", "remaining_time": "0:19:02", "throughput": 10224.73, "total_tokens": 44902848}
{"current_steps": 46760, "total_steps": 58920, "loss": 0.0, "lr": 2.4850208870270074e-07, "epoch": 3.968092328581127, "percentage": 79.36, "elapsed_time": "1:13:11", "remaining_time": "0:19:02", "throughput": 10224.92, "total_tokens": 44907584}
{"current_steps": 46765, "total_steps": 58920, "loss": 0.0, "lr": 2.4830669472217325e-07, "epoch": 3.968516632722335, "percentage": 79.37, "elapsed_time": "1:13:12", "remaining_time": "0:19:01", "throughput": 10225.16, "total_tokens": 44912576}
{"current_steps": 46770, "total_steps": 58920, "loss": 0.0, "lr": 2.481113667000189e-07, "epoch": 3.968940936863544, "percentage": 79.38, "elapsed_time": "1:13:12", "remaining_time": "0:19:01", "throughput": 10225.35, "total_tokens": 44917248}
{"current_steps": 46775, "total_steps": 58920, "loss": 0.0, "lr": 2.479161046533781e-07, "epoch": 3.969365241004752, "percentage": 79.39, "elapsed_time": "1:13:13", "remaining_time": "0:19:00", "throughput": 10225.58, "total_tokens": 44922176}
{"current_steps": 46780, "total_steps": 58920, "loss": 0.0, "lr": 2.4772090859938313e-07, "epoch": 3.969789545145961, "percentage": 79.4, "elapsed_time": "1:13:13", "remaining_time": "0:19:00", "throughput": 10225.78, "total_tokens": 44926976}
{"current_steps": 46785, "total_steps": 58920, "loss": 0.0, "lr": 2.47525778555163e-07, "epoch": 3.970213849287169, "percentage": 79.4, "elapsed_time": "1:13:13", "remaining_time": "0:18:59", "throughput": 10225.91, "total_tokens": 44931328}
{"current_steps": 46790, "total_steps": 58920, "loss": 0.0, "lr": 2.4733071453783826e-07, "epoch": 3.9706381534283777, "percentage": 79.41, "elapsed_time": "1:13:14", "remaining_time": "0:18:59", "throughput": 10226.14, "total_tokens": 44936320}
{"current_steps": 46795, "total_steps": 58920, "loss": 0.0375, "lr": 2.4713571656452623e-07, "epoch": 3.9710624575695856, "percentage": 79.42, "elapsed_time": "1:13:14", "remaining_time": "0:18:58", "throughput": 10226.52, "total_tokens": 44942144}
{"current_steps": 46800, "total_steps": 58920, "loss": 0.0, "lr": 2.4694078465233713e-07, "epoch": 3.9714867617107945, "percentage": 79.43, "elapsed_time": "1:13:15", "remaining_time": "0:18:58", "throughput": 10226.74, "total_tokens": 44947008}
{"current_steps": 46805, "total_steps": 58920, "loss": 0.0, "lr": 2.467459188183747e-07, "epoch": 3.9719110658520025, "percentage": 79.44, "elapsed_time": "1:13:15", "remaining_time": "0:18:57", "throughput": 10226.87, "total_tokens": 44951424}
{"current_steps": 46810, "total_steps": 58920, "loss": 0.0, "lr": 2.465511190797388e-07, "epoch": 3.9723353699932114, "percentage": 79.45, "elapsed_time": "1:13:15", "remaining_time": "0:18:57", "throughput": 10227.06, "total_tokens": 44956160}
{"current_steps": 46815, "total_steps": 58920, "loss": 0.0, "lr": 2.4635638545352135e-07, "epoch": 3.9727596741344193, "percentage": 79.46, "elapsed_time": "1:13:16", "remaining_time": "0:18:56", "throughput": 10227.23, "total_tokens": 44960768}
{"current_steps": 46820, "total_steps": 58920, "loss": 0.0, "lr": 2.461617179568106e-07, "epoch": 3.973183978275628, "percentage": 79.46, "elapsed_time": "1:13:16", "remaining_time": "0:18:56", "throughput": 10227.49, "total_tokens": 44965952}
{"current_steps": 46825, "total_steps": 58920, "loss": 0.0, "lr": 2.459671166066869e-07, "epoch": 3.973608282416836, "percentage": 79.47, "elapsed_time": "1:13:16", "remaining_time": "0:18:55", "throughput": 10227.66, "total_tokens": 44970496}
{"current_steps": 46830, "total_steps": 58920, "loss": 0.0, "lr": 2.457725814202265e-07, "epoch": 3.974032586558045, "percentage": 79.48, "elapsed_time": "1:13:17", "remaining_time": "0:18:55", "throughput": 10227.74, "total_tokens": 44974656}
{"current_steps": 46835, "total_steps": 58920, "loss": 0.0, "lr": 2.455781124144993e-07, "epoch": 3.974456890699253, "percentage": 79.49, "elapsed_time": "1:13:17", "remaining_time": "0:18:54", "throughput": 10227.95, "total_tokens": 44979520}
{"current_steps": 46840, "total_steps": 58920, "loss": 0.0001, "lr": 2.453837096065683e-07, "epoch": 3.974881194840462, "percentage": 79.5, "elapsed_time": "1:13:18", "remaining_time": "0:18:54", "throughput": 10228.2, "total_tokens": 44984576}
{"current_steps": 46845, "total_steps": 58920, "loss": 0.0, "lr": 2.4518937301349275e-07, "epoch": 3.97530549898167, "percentage": 79.51, "elapsed_time": "1:13:18", "remaining_time": "0:18:53", "throughput": 10228.35, "total_tokens": 44989056}
{"current_steps": 46850, "total_steps": 58920, "loss": 0.0, "lr": 2.4499510265232406e-07, "epoch": 3.9757298031228787, "percentage": 79.51, "elapsed_time": "1:13:18", "remaining_time": "0:18:53", "throughput": 10228.61, "total_tokens": 44994112}
{"current_steps": 46855, "total_steps": 58920, "loss": 0.0, "lr": 2.4480089854010934e-07, "epoch": 3.9761541072640867, "percentage": 79.52, "elapsed_time": "1:13:19", "remaining_time": "0:18:52", "throughput": 10228.72, "total_tokens": 44998400}
{"current_steps": 46860, "total_steps": 58920, "loss": 0.0, "lr": 2.446067606938892e-07, "epoch": 3.9765784114052956, "percentage": 79.53, "elapsed_time": "1:13:19", "remaining_time": "0:18:52", "throughput": 10228.88, "total_tokens": 45002944}
{"current_steps": 46865, "total_steps": 58920, "loss": 0.0, "lr": 2.4441268913069836e-07, "epoch": 3.9770027155465035, "percentage": 79.54, "elapsed_time": "1:13:19", "remaining_time": "0:18:51", "throughput": 10229.08, "total_tokens": 45007744}
{"current_steps": 46870, "total_steps": 58920, "loss": 0.0, "lr": 2.442186838675662e-07, "epoch": 3.9774270196877124, "percentage": 79.55, "elapsed_time": "1:13:20", "remaining_time": "0:18:51", "throughput": 10229.21, "total_tokens": 45012160}
{"current_steps": 46875, "total_steps": 58920, "loss": 0.0, "lr": 2.440247449215156e-07, "epoch": 3.9778513238289204, "percentage": 79.56, "elapsed_time": "1:13:20", "remaining_time": "0:18:50", "throughput": 10229.4, "total_tokens": 45016896}
{"current_steps": 46880, "total_steps": 58920, "loss": 0.0, "lr": 2.4383087230956436e-07, "epoch": 3.9782756279701292, "percentage": 79.57, "elapsed_time": "1:13:21", "remaining_time": "0:18:50", "throughput": 10229.52, "total_tokens": 45021248}
{"current_steps": 46885, "total_steps": 58920, "loss": 0.0001, "lr": 2.436370660487238e-07, "epoch": 3.978699932111337, "percentage": 79.57, "elapsed_time": "1:13:21", "remaining_time": "0:18:49", "throughput": 10229.73, "total_tokens": 45026112}
{"current_steps": 46890, "total_steps": 58920, "loss": 0.0, "lr": 2.434433261559999e-07, "epoch": 3.979124236252546, "percentage": 79.58, "elapsed_time": "1:13:21", "remaining_time": "0:18:49", "throughput": 10229.87, "total_tokens": 45030528}
{"current_steps": 46895, "total_steps": 58920, "loss": 0.0, "lr": 2.432496526483927e-07, "epoch": 3.979548540393754, "percentage": 79.59, "elapsed_time": "1:13:22", "remaining_time": "0:18:48", "throughput": 10230.09, "total_tokens": 45035456}
{"current_steps": 46900, "total_steps": 58920, "loss": 0.0, "lr": 2.4305604554289614e-07, "epoch": 3.979972844534963, "percentage": 79.6, "elapsed_time": "1:13:22", "remaining_time": "0:18:48", "throughput": 10230.35, "total_tokens": 45040640}
{"current_steps": 46905, "total_steps": 58920, "loss": 0.0, "lr": 2.428625048564986e-07, "epoch": 3.980397148676171, "percentage": 79.61, "elapsed_time": "1:13:23", "remaining_time": "0:18:47", "throughput": 10230.57, "total_tokens": 45045568}
{"current_steps": 46910, "total_steps": 58920, "loss": 0.0, "lr": 2.426690306061827e-07, "epoch": 3.9808214528173798, "percentage": 79.62, "elapsed_time": "1:13:23", "remaining_time": "0:18:47", "throughput": 10230.71, "total_tokens": 45050048}
{"current_steps": 46915, "total_steps": 58920, "loss": 0.0, "lr": 2.424756228089251e-07, "epoch": 3.9812457569585877, "percentage": 79.62, "elapsed_time": "1:13:23", "remaining_time": "0:18:46", "throughput": 10230.93, "total_tokens": 45054912}
{"current_steps": 46920, "total_steps": 58920, "loss": 0.0, "lr": 2.422822814816965e-07, "epoch": 3.9816700610997966, "percentage": 79.63, "elapsed_time": "1:13:24", "remaining_time": "0:18:46", "throughput": 10231.06, "total_tokens": 45059264}
{"current_steps": 46925, "total_steps": 58920, "loss": 0.0, "lr": 2.4208900664146193e-07, "epoch": 3.9820943652410046, "percentage": 79.64, "elapsed_time": "1:13:24", "remaining_time": "0:18:45", "throughput": 10231.16, "total_tokens": 45063488}
{"current_steps": 46930, "total_steps": 58920, "loss": 0.0, "lr": 2.418957983051806e-07, "epoch": 3.9825186693822134, "percentage": 79.65, "elapsed_time": "1:13:24", "remaining_time": "0:18:45", "throughput": 10231.51, "total_tokens": 45069120}
{"current_steps": 46935, "total_steps": 58920, "loss": 0.0, "lr": 2.417026564898059e-07, "epoch": 3.9829429735234214, "percentage": 79.66, "elapsed_time": "1:13:25", "remaining_time": "0:18:44", "throughput": 10231.85, "total_tokens": 45074752}
{"current_steps": 46940, "total_steps": 58920, "loss": 0.0, "lr": 2.4150958121228526e-07, "epoch": 3.9833672776646303, "percentage": 79.67, "elapsed_time": "1:13:25", "remaining_time": "0:18:44", "throughput": 10231.98, "total_tokens": 45079168}
{"current_steps": 46945, "total_steps": 58920, "loss": 0.0, "lr": 2.4131657248956027e-07, "epoch": 3.9837915818058383, "percentage": 79.68, "elapsed_time": "1:13:26", "remaining_time": "0:18:43", "throughput": 10232.29, "total_tokens": 45084544}
{"current_steps": 46950, "total_steps": 58920, "loss": 0.0, "lr": 2.4112363033856666e-07, "epoch": 3.984215885947047, "percentage": 79.68, "elapsed_time": "1:13:26", "remaining_time": "0:18:43", "throughput": 10232.45, "total_tokens": 45089216}
{"current_steps": 46955, "total_steps": 58920, "loss": 0.0, "lr": 2.4093075477623514e-07, "epoch": 3.984640190088255, "percentage": 79.69, "elapsed_time": "1:13:26", "remaining_time": "0:18:42", "throughput": 10232.65, "total_tokens": 45094016}
{"current_steps": 46960, "total_steps": 58920, "loss": 0.0, "lr": 2.407379458194886e-07, "epoch": 3.9850644942294635, "percentage": 79.7, "elapsed_time": "1:13:27", "remaining_time": "0:18:42", "throughput": 10232.8, "total_tokens": 45098496}
{"current_steps": 46965, "total_steps": 58920, "loss": 0.0, "lr": 2.4054520348524663e-07, "epoch": 3.985488798370672, "percentage": 79.71, "elapsed_time": "1:13:27", "remaining_time": "0:18:41", "throughput": 10233.0, "total_tokens": 45103360}
{"current_steps": 46970, "total_steps": 58920, "loss": 0.0, "lr": 2.403525277904208e-07, "epoch": 3.9859131025118804, "percentage": 79.72, "elapsed_time": "1:13:28", "remaining_time": "0:18:41", "throughput": 10233.2, "total_tokens": 45108096}
{"current_steps": 46975, "total_steps": 58920, "loss": 0.0, "lr": 2.40159918751918e-07, "epoch": 3.9863374066530888, "percentage": 79.73, "elapsed_time": "1:13:28", "remaining_time": "0:18:40", "throughput": 10233.38, "total_tokens": 45112768}
{"current_steps": 46980, "total_steps": 58920, "loss": 0.0, "lr": 2.399673763866389e-07, "epoch": 3.986761710794297, "percentage": 79.74, "elapsed_time": "1:13:28", "remaining_time": "0:18:40", "throughput": 10233.53, "total_tokens": 45117312}
{"current_steps": 46985, "total_steps": 58920, "loss": 0.0, "lr": 2.397749007114781e-07, "epoch": 3.9871860149355056, "percentage": 79.74, "elapsed_time": "1:13:29", "remaining_time": "0:18:40", "throughput": 10233.83, "total_tokens": 45122688}
{"current_steps": 46990, "total_steps": 58920, "loss": 0.0, "lr": 2.395824917433256e-07, "epoch": 3.987610319076714, "percentage": 79.75, "elapsed_time": "1:13:29", "remaining_time": "0:18:39", "throughput": 10234.05, "total_tokens": 45127616}
{"current_steps": 46995, "total_steps": 58920, "loss": 0.0, "lr": 2.3939014949906333e-07, "epoch": 3.9880346232179225, "percentage": 79.76, "elapsed_time": "1:13:29", "remaining_time": "0:18:39", "throughput": 10234.18, "total_tokens": 45132032}
{"current_steps": 47000, "total_steps": 58920, "loss": 0.0, "lr": 2.391978739955699e-07, "epoch": 3.988458927359131, "percentage": 79.77, "elapsed_time": "1:13:30", "remaining_time": "0:18:38", "throughput": 10234.45, "total_tokens": 45137280}
{"current_steps": 47005, "total_steps": 58920, "loss": 0.0, "lr": 2.3900566524971587e-07, "epoch": 3.9888832315003393, "percentage": 79.78, "elapsed_time": "1:13:30", "remaining_time": "0:18:38", "throughput": 10234.6, "total_tokens": 45141760}
{"current_steps": 47010, "total_steps": 58920, "loss": 0.0, "lr": 2.388135232783669e-07, "epoch": 3.9893075356415477, "percentage": 79.79, "elapsed_time": "1:13:31", "remaining_time": "0:18:37", "throughput": 10234.76, "total_tokens": 45146368}
{"current_steps": 47015, "total_steps": 58920, "loss": 0.0, "lr": 2.386214480983836e-07, "epoch": 3.989731839782756, "percentage": 79.79, "elapsed_time": "1:13:31", "remaining_time": "0:18:37", "throughput": 10234.91, "total_tokens": 45150912}
{"current_steps": 47020, "total_steps": 58920, "loss": 0.0382, "lr": 2.3842943972661867e-07, "epoch": 3.9901561439239646, "percentage": 79.8, "elapsed_time": "1:13:31", "remaining_time": "0:18:36", "throughput": 10235.09, "total_tokens": 45155584}
{"current_steps": 47025, "total_steps": 58920, "loss": 0.0, "lr": 2.3823749817992134e-07, "epoch": 3.990580448065173, "percentage": 79.81, "elapsed_time": "1:13:32", "remaining_time": "0:18:36", "throughput": 10235.24, "total_tokens": 45160064}
{"current_steps": 47030, "total_steps": 58920, "loss": 0.0, "lr": 2.3804562347513257e-07, "epoch": 3.9910047522063814, "percentage": 79.82, "elapsed_time": "1:13:32", "remaining_time": "0:18:35", "throughput": 10235.5, "total_tokens": 45165248}
{"current_steps": 47035, "total_steps": 58920, "loss": 0.0, "lr": 2.3785381562909002e-07, "epoch": 3.99142905634759, "percentage": 79.83, "elapsed_time": "1:13:32", "remaining_time": "0:18:35", "throughput": 10235.65, "total_tokens": 45169792}
{"current_steps": 47040, "total_steps": 58920, "loss": 0.0, "lr": 2.3766207465862275e-07, "epoch": 3.9918533604887982, "percentage": 79.84, "elapsed_time": "1:13:33", "remaining_time": "0:18:34", "throughput": 10235.86, "total_tokens": 45174656}
{"current_steps": 47045, "total_steps": 58920, "loss": 0.0, "lr": 2.3747040058055635e-07, "epoch": 3.9922776646300067, "percentage": 79.85, "elapsed_time": "1:13:33", "remaining_time": "0:18:34", "throughput": 10236.08, "total_tokens": 45179584}
{"current_steps": 47050, "total_steps": 58920, "loss": 0.0, "lr": 2.3727879341170942e-07, "epoch": 3.992701968771215, "percentage": 79.85, "elapsed_time": "1:13:34", "remaining_time": "0:18:33", "throughput": 10236.29, "total_tokens": 45184448}
{"current_steps": 47055, "total_steps": 58920, "loss": 0.0, "lr": 2.370872531688941e-07, "epoch": 3.9931262729124235, "percentage": 79.86, "elapsed_time": "1:13:34", "remaining_time": "0:18:33", "throughput": 10236.37, "total_tokens": 45188608}
{"current_steps": 47060, "total_steps": 58920, "loss": 0.0, "lr": 2.368957798689184e-07, "epoch": 3.993550577053632, "percentage": 79.87, "elapsed_time": "1:13:34", "remaining_time": "0:18:32", "throughput": 10236.57, "total_tokens": 45193472}
{"current_steps": 47065, "total_steps": 58920, "loss": 0.0, "lr": 2.3670437352858218e-07, "epoch": 3.9939748811948403, "percentage": 79.88, "elapsed_time": "1:13:35", "remaining_time": "0:18:32", "throughput": 10236.71, "total_tokens": 45197888}
{"current_steps": 47070, "total_steps": 58920, "loss": 0.0, "lr": 2.3651303416468161e-07, "epoch": 3.9943991853360488, "percentage": 79.89, "elapsed_time": "1:13:35", "remaining_time": "0:18:31", "throughput": 10236.83, "total_tokens": 45202240}
{"current_steps": 47075, "total_steps": 58920, "loss": 0.0, "lr": 2.3632176179400577e-07, "epoch": 3.994823489477257, "percentage": 79.9, "elapsed_time": "1:13:36", "remaining_time": "0:18:31", "throughput": 10237.08, "total_tokens": 45207360}
{"current_steps": 47080, "total_steps": 58920, "loss": 0.0, "lr": 2.3613055643333813e-07, "epoch": 3.9952477936184656, "percentage": 79.9, "elapsed_time": "1:13:36", "remaining_time": "0:18:30", "throughput": 10237.19, "total_tokens": 45211648}
{"current_steps": 47085, "total_steps": 58920, "loss": 0.0, "lr": 2.3593941809945616e-07, "epoch": 3.995672097759674, "percentage": 79.91, "elapsed_time": "1:13:36", "remaining_time": "0:18:30", "throughput": 10237.39, "total_tokens": 45216384}
{"current_steps": 47090, "total_steps": 58920, "loss": 0.0, "lr": 2.357483468091317e-07, "epoch": 3.9960964019008824, "percentage": 79.92, "elapsed_time": "1:13:37", "remaining_time": "0:18:29", "throughput": 10237.58, "total_tokens": 45221056}
{"current_steps": 47095, "total_steps": 58920, "loss": 0.0593, "lr": 2.355573425791304e-07, "epoch": 3.996520706042091, "percentage": 79.93, "elapsed_time": "1:13:37", "remaining_time": "0:18:29", "throughput": 10237.2, "total_tokens": 45225920}
{"current_steps": 47100, "total_steps": 58920, "loss": 0.0, "lr": 2.3536640542621221e-07, "epoch": 3.9969450101832993, "percentage": 79.94, "elapsed_time": "1:13:38", "remaining_time": "0:18:28", "throughput": 10237.36, "total_tokens": 45230528}
{"current_steps": 47105, "total_steps": 58920, "loss": 0.0, "lr": 2.3517553536713142e-07, "epoch": 3.9973693143245077, "percentage": 79.95, "elapsed_time": "1:13:38", "remaining_time": "0:18:28", "throughput": 10237.48, "total_tokens": 45234880}
{"current_steps": 47110, "total_steps": 58920, "loss": 0.0, "lr": 2.349847324186359e-07, "epoch": 3.997793618465716, "percentage": 79.96, "elapsed_time": "1:13:38", "remaining_time": "0:18:27", "throughput": 10237.64, "total_tokens": 45239488}
{"current_steps": 47115, "total_steps": 58920, "loss": 0.0, "lr": 2.3479399659746813e-07, "epoch": 3.9982179226069245, "percentage": 79.96, "elapsed_time": "1:13:39", "remaining_time": "0:18:27", "throughput": 10237.87, "total_tokens": 45244480}
{"current_steps": 47120, "total_steps": 58920, "loss": 0.0, "lr": 2.346033279203643e-07, "epoch": 3.998642226748133, "percentage": 79.97, "elapsed_time": "1:13:39", "remaining_time": "0:18:26", "throughput": 10238.04, "total_tokens": 45249088}
{"current_steps": 47125, "total_steps": 58920, "loss": 0.0345, "lr": 2.3441272640405497e-07, "epoch": 3.9990665308893414, "percentage": 79.98, "elapsed_time": "1:13:40", "remaining_time": "0:18:26", "throughput": 10238.38, "total_tokens": 45254592}
{"current_steps": 47130, "total_steps": 58920, "loss": 0.0, "lr": 2.3422219206526484e-07, "epoch": 3.99949083503055, "percentage": 79.99, "elapsed_time": "1:13:40", "remaining_time": "0:18:25", "throughput": 10238.54, "total_tokens": 45259200}
{"current_steps": 47135, "total_steps": 58920, "loss": 0.0, "lr": 2.3403172492071255e-07, "epoch": 3.9999151391717582, "percentage": 80.0, "elapsed_time": "1:13:40", "remaining_time": "0:18:25", "throughput": 10238.9, "total_tokens": 45264896}
{"current_steps": 47136, "total_steps": 58920, "eval_loss": 0.14622636139392853, "epoch": 4.0, "percentage": 80.0, "elapsed_time": "1:13:57", "remaining_time": "0:18:29", "throughput": 10200.92, "total_tokens": 45265344}
{"current_steps": 47140, "total_steps": 58920, "loss": 0.0, "lr": 2.3384132498711072e-07, "epoch": 4.000339443312967, "percentage": 80.01, "elapsed_time": "1:14:30", "remaining_time": "0:18:37", "throughput": 10125.94, "total_tokens": 45269696}
{"current_steps": 47145, "total_steps": 58920, "loss": 0.0, "lr": 2.3365099228116658e-07, "epoch": 4.000763747454175, "percentage": 80.02, "elapsed_time": "1:14:31", "remaining_time": "0:18:36", "throughput": 10126.12, "total_tokens": 45274368}
{"current_steps": 47150, "total_steps": 58920, "loss": 0.0, "lr": 2.3346072681958097e-07, "epoch": 4.001188051595384, "percentage": 80.02, "elapsed_time": "1:14:31", "remaining_time": "0:18:36", "throughput": 10126.25, "total_tokens": 45278784}
{"current_steps": 47155, "total_steps": 58920, "loss": 0.0, "lr": 2.3327052861904895e-07, "epoch": 4.001612355736592, "percentage": 80.03, "elapsed_time": "1:14:31", "remaining_time": "0:18:35", "throughput": 10126.48, "total_tokens": 45283712}
{"current_steps": 47160, "total_steps": 58920, "loss": 0.0, "lr": 2.3308039769625976e-07, "epoch": 4.002036659877801, "percentage": 80.04, "elapsed_time": "1:14:32", "remaining_time": "0:18:35", "throughput": 10126.63, "total_tokens": 45288192}
{"current_steps": 47165, "total_steps": 58920, "loss": 0.0, "lr": 2.3289033406789672e-07, "epoch": 4.002460964019009, "percentage": 80.05, "elapsed_time": "1:14:32", "remaining_time": "0:18:34", "throughput": 10126.82, "total_tokens": 45292928}
{"current_steps": 47170, "total_steps": 58920, "loss": 0.0, "lr": 2.3270033775063725e-07, "epoch": 4.002885268160218, "percentage": 80.06, "elapsed_time": "1:14:32", "remaining_time": "0:18:34", "throughput": 10127.21, "total_tokens": 45298752}
{"current_steps": 47175, "total_steps": 58920, "loss": 0.0, "lr": 2.3251040876115279e-07, "epoch": 4.003309572301426, "percentage": 80.07, "elapsed_time": "1:14:33", "remaining_time": "0:18:33", "throughput": 10127.58, "total_tokens": 45304576}
{"current_steps": 47180, "total_steps": 58920, "loss": 0.0, "lr": 2.3232054711610906e-07, "epoch": 4.0037338764426345, "percentage": 80.07, "elapsed_time": "1:14:33", "remaining_time": "0:18:33", "throughput": 10127.79, "total_tokens": 45309376}
{"current_steps": 47185, "total_steps": 58920, "loss": 0.0, "lr": 2.3213075283216543e-07, "epoch": 4.004158180583842, "percentage": 80.08, "elapsed_time": "1:14:34", "remaining_time": "0:18:32", "throughput": 10128.2, "total_tokens": 45315392}
{"current_steps": 47190, "total_steps": 58920, "loss": 0.0, "lr": 2.3194102592597598e-07, "epoch": 4.004582484725051, "percentage": 80.09, "elapsed_time": "1:14:34", "remaining_time": "0:18:32", "throughput": 10128.43, "total_tokens": 45320384}
{"current_steps": 47195, "total_steps": 58920, "loss": 0.0, "lr": 2.3175136641418847e-07, "epoch": 4.005006788866259, "percentage": 80.1, "elapsed_time": "1:14:34", "remaining_time": "0:18:31", "throughput": 10128.58, "total_tokens": 45324864}
{"current_steps": 47200, "total_steps": 58920, "loss": 0.0, "lr": 2.3156177431344448e-07, "epoch": 4.005431093007468, "percentage": 80.11, "elapsed_time": "1:14:35", "remaining_time": "0:18:31", "throughput": 10128.77, "total_tokens": 45329600}
{"current_steps": 47205, "total_steps": 58920, "loss": 0.0, "lr": 2.3137224964038093e-07, "epoch": 4.005855397148676, "percentage": 80.12, "elapsed_time": "1:14:35", "remaining_time": "0:18:30", "throughput": 10128.94, "total_tokens": 45334208}
{"current_steps": 47210, "total_steps": 58920, "loss": 0.0, "lr": 2.3118279241162675e-07, "epoch": 4.006279701289885, "percentage": 80.13, "elapsed_time": "1:14:36", "remaining_time": "0:18:30", "throughput": 10129.15, "total_tokens": 45339008}
{"current_steps": 47215, "total_steps": 58920, "loss": 0.0, "lr": 2.309934026438074e-07, "epoch": 4.006704005431093, "percentage": 80.13, "elapsed_time": "1:14:36", "remaining_time": "0:18:29", "throughput": 10129.31, "total_tokens": 45343552}
{"current_steps": 47220, "total_steps": 58920, "loss": 0.0, "lr": 2.3080408035354004e-07, "epoch": 4.007128309572302, "percentage": 80.14, "elapsed_time": "1:14:36", "remaining_time": "0:18:29", "throughput": 10129.49, "total_tokens": 45348160}
{"current_steps": 47225, "total_steps": 58920, "loss": 0.0, "lr": 2.3061482555743728e-07, "epoch": 4.00755261371351, "percentage": 80.15, "elapsed_time": "1:14:37", "remaining_time": "0:18:28", "throughput": 10129.7, "total_tokens": 45352960}
{"current_steps": 47230, "total_steps": 58920, "loss": 0.0, "lr": 2.3042563827210625e-07, "epoch": 4.007976917854719, "percentage": 80.16, "elapsed_time": "1:14:37", "remaining_time": "0:18:28", "throughput": 10129.91, "total_tokens": 45357760}
{"current_steps": 47235, "total_steps": 58920, "loss": 0.0, "lr": 2.3023651851414638e-07, "epoch": 4.008401221995927, "percentage": 80.17, "elapsed_time": "1:14:37", "remaining_time": "0:18:27", "throughput": 10130.13, "total_tokens": 45362688}
{"current_steps": 47240, "total_steps": 58920, "loss": 0.0, "lr": 2.3004746630015337e-07, "epoch": 4.0088255261371355, "percentage": 80.18, "elapsed_time": "1:14:38", "remaining_time": "0:18:27", "throughput": 10130.38, "total_tokens": 45367680}
{"current_steps": 47245, "total_steps": 58920, "loss": 0.0, "lr": 2.2985848164671473e-07, "epoch": 4.0092498302783435, "percentage": 80.18, "elapsed_time": "1:14:38", "remaining_time": "0:18:26", "throughput": 10130.53, "total_tokens": 45372160}
{"current_steps": 47250, "total_steps": 58920, "loss": 0.0, "lr": 2.296695645704143e-07, "epoch": 4.009674134419552, "percentage": 80.19, "elapsed_time": "1:14:39", "remaining_time": "0:18:26", "throughput": 10130.77, "total_tokens": 45377152}
{"current_steps": 47255, "total_steps": 58920, "loss": 0.0, "lr": 2.2948071508782807e-07, "epoch": 4.01009843856076, "percentage": 80.2, "elapsed_time": "1:14:39", "remaining_time": "0:18:25", "throughput": 10130.91, "total_tokens": 45381568}
{"current_steps": 47260, "total_steps": 58920, "loss": 0.0, "lr": 2.2929193321552675e-07, "epoch": 4.010522742701969, "percentage": 80.21, "elapsed_time": "1:14:39", "remaining_time": "0:18:25", "throughput": 10131.1, "total_tokens": 45386304}
{"current_steps": 47265, "total_steps": 58920, "loss": 0.0, "lr": 2.2910321897007635e-07, "epoch": 4.010947046843177, "percentage": 80.22, "elapsed_time": "1:14:40", "remaining_time": "0:18:24", "throughput": 10131.23, "total_tokens": 45390656}
{"current_steps": 47270, "total_steps": 58920, "loss": 0.0, "lr": 2.2891457236803446e-07, "epoch": 4.011371350984386, "percentage": 80.23, "elapsed_time": "1:14:40", "remaining_time": "0:18:24", "throughput": 10131.4, "total_tokens": 45395264}
{"current_steps": 47275, "total_steps": 58920, "loss": 0.0, "lr": 2.2872599342595557e-07, "epoch": 4.011795655125594, "percentage": 80.24, "elapsed_time": "1:14:41", "remaining_time": "0:18:23", "throughput": 10131.62, "total_tokens": 45400192}
{"current_steps": 47280, "total_steps": 58920, "loss": 0.0, "lr": 2.2853748216038538e-07, "epoch": 4.012219959266803, "percentage": 80.24, "elapsed_time": "1:14:41", "remaining_time": "0:18:23", "throughput": 10131.82, "total_tokens": 45404992}
{"current_steps": 47285, "total_steps": 58920, "loss": 0.0, "lr": 2.2834903858786615e-07, "epoch": 4.012644263408011, "percentage": 80.25, "elapsed_time": "1:14:41", "remaining_time": "0:18:22", "throughput": 10132.0, "total_tokens": 45409664}
{"current_steps": 47290, "total_steps": 58920, "loss": 0.0, "lr": 2.2816066272493272e-07, "epoch": 4.01306856754922, "percentage": 80.26, "elapsed_time": "1:14:42", "remaining_time": "0:18:22", "throughput": 10132.18, "total_tokens": 45414272}
{"current_steps": 47295, "total_steps": 58920, "loss": 0.0, "lr": 2.2797235458811447e-07, "epoch": 4.013492871690428, "percentage": 80.27, "elapsed_time": "1:14:42", "remaining_time": "0:18:21", "throughput": 10132.37, "total_tokens": 45418944}
{"current_steps": 47300, "total_steps": 58920, "loss": 0.0, "lr": 2.2778411419393496e-07, "epoch": 4.0139171758316365, "percentage": 80.28, "elapsed_time": "1:14:42", "remaining_time": "0:18:21", "throughput": 10132.62, "total_tokens": 45424064}
{"current_steps": 47305, "total_steps": 58920, "loss": 0.0, "lr": 2.275959415589107e-07, "epoch": 4.0143414799728445, "percentage": 80.29, "elapsed_time": "1:14:43", "remaining_time": "0:18:20", "throughput": 10132.77, "total_tokens": 45428544}
{"current_steps": 47310, "total_steps": 58920, "loss": 0.0, "lr": 2.2740783669955422e-07, "epoch": 4.014765784114053, "percentage": 80.3, "elapsed_time": "1:14:43", "remaining_time": "0:18:20", "throughput": 10132.96, "total_tokens": 45433280}
{"current_steps": 47315, "total_steps": 58920, "loss": 0.0, "lr": 2.2721979963237058e-07, "epoch": 4.015190088255261, "percentage": 80.3, "elapsed_time": "1:14:44", "remaining_time": "0:18:19", "throughput": 10133.18, "total_tokens": 45438144}
{"current_steps": 47320, "total_steps": 58920, "loss": 0.0, "lr": 2.2703183037385941e-07, "epoch": 4.01561439239647, "percentage": 80.31, "elapsed_time": "1:14:44", "remaining_time": "0:18:19", "throughput": 10133.41, "total_tokens": 45443136}
{"current_steps": 47325, "total_steps": 58920, "loss": 0.0, "lr": 2.268439289405144e-07, "epoch": 4.016038696537678, "percentage": 80.32, "elapsed_time": "1:14:44", "remaining_time": "0:18:18", "throughput": 10133.6, "total_tokens": 45447808}
{"current_steps": 47330, "total_steps": 58920, "loss": 0.0, "lr": 2.26656095348823e-07, "epoch": 4.016463000678887, "percentage": 80.33, "elapsed_time": "1:14:45", "remaining_time": "0:18:18", "throughput": 10133.94, "total_tokens": 45453504}
{"current_steps": 47335, "total_steps": 58920, "loss": 0.0, "lr": 2.264683296152673e-07, "epoch": 4.016887304820095, "percentage": 80.34, "elapsed_time": "1:14:45", "remaining_time": "0:18:17", "throughput": 10134.13, "total_tokens": 45458176}
{"current_steps": 47340, "total_steps": 58920, "loss": 0.0, "lr": 2.2628063175632273e-07, "epoch": 4.017311608961304, "percentage": 80.35, "elapsed_time": "1:14:46", "remaining_time": "0:18:17", "throughput": 10134.27, "total_tokens": 45462592}
{"current_steps": 47345, "total_steps": 58920, "loss": 0.0, "lr": 2.2609300178845926e-07, "epoch": 4.017735913102512, "percentage": 80.35, "elapsed_time": "1:14:46", "remaining_time": "0:18:16", "throughput": 10134.51, "total_tokens": 45467584}
{"current_steps": 47350, "total_steps": 58920, "loss": 0.0, "lr": 2.2590543972814058e-07, "epoch": 4.01816021724372, "percentage": 80.36, "elapsed_time": "1:14:46", "remaining_time": "0:18:16", "throughput": 10134.77, "total_tokens": 45472768}
{"current_steps": 47355, "total_steps": 58920, "loss": 0.0, "lr": 2.2571794559182488e-07, "epoch": 4.018584521384929, "percentage": 80.37, "elapsed_time": "1:14:47", "remaining_time": "0:18:15", "throughput": 10135.05, "total_tokens": 45478016}
{"current_steps": 47360, "total_steps": 58920, "loss": 0.0, "lr": 2.255305193959638e-07, "epoch": 4.019008825526137, "percentage": 80.38, "elapsed_time": "1:14:47", "remaining_time": "0:18:15", "throughput": 10135.19, "total_tokens": 45482432}
{"current_steps": 47365, "total_steps": 58920, "loss": 0.0, "lr": 2.2534316115700347e-07, "epoch": 4.019433129667346, "percentage": 80.39, "elapsed_time": "1:14:47", "remaining_time": "0:18:14", "throughput": 10135.44, "total_tokens": 45487424}
{"current_steps": 47370, "total_steps": 58920, "loss": 0.0, "lr": 2.2515587089138387e-07, "epoch": 4.0198574338085535, "percentage": 80.4, "elapsed_time": "1:14:48", "remaining_time": "0:18:14", "throughput": 10135.57, "total_tokens": 45491776}
{"current_steps": 47375, "total_steps": 58920, "loss": 0.0, "lr": 2.24968648615539e-07, "epoch": 4.020281737949762, "percentage": 80.41, "elapsed_time": "1:14:48", "remaining_time": "0:18:13", "throughput": 10135.7, "total_tokens": 45496128}
{"current_steps": 47380, "total_steps": 58920, "loss": 0.0, "lr": 2.24781494345897e-07, "epoch": 4.02070604209097, "percentage": 80.41, "elapsed_time": "1:14:49", "remaining_time": "0:18:13", "throughput": 10135.84, "total_tokens": 45500544}
{"current_steps": 47385, "total_steps": 58920, "loss": 0.0, "lr": 2.2459440809887998e-07, "epoch": 4.021130346232179, "percentage": 80.42, "elapsed_time": "1:14:49", "remaining_time": "0:18:12", "throughput": 10135.98, "total_tokens": 45504960}
{"current_steps": 47390, "total_steps": 58920, "loss": 0.0, "lr": 2.2440738989090403e-07, "epoch": 4.021554650373387, "percentage": 80.43, "elapsed_time": "1:14:49", "remaining_time": "0:18:12", "throughput": 10136.15, "total_tokens": 45509632}
{"current_steps": 47395, "total_steps": 58920, "loss": 0.0, "lr": 2.2422043973837933e-07, "epoch": 4.021978954514596, "percentage": 80.44, "elapsed_time": "1:14:50", "remaining_time": "0:18:11", "throughput": 10136.36, "total_tokens": 45514432}
{"current_steps": 47400, "total_steps": 58920, "loss": 0.0, "lr": 2.2403355765771014e-07, "epoch": 4.022403258655804, "percentage": 80.45, "elapsed_time": "1:14:50", "remaining_time": "0:18:11", "throughput": 10136.54, "total_tokens": 45519104}
{"current_steps": 47405, "total_steps": 58920, "loss": 0.0, "lr": 2.2384674366529467e-07, "epoch": 4.022827562797013, "percentage": 80.46, "elapsed_time": "1:14:50", "remaining_time": "0:18:10", "throughput": 10136.67, "total_tokens": 45523456}
{"current_steps": 47410, "total_steps": 58920, "loss": 0.0, "lr": 2.236599977775251e-07, "epoch": 4.023251866938221, "percentage": 80.47, "elapsed_time": "1:14:51", "remaining_time": "0:18:10", "throughput": 10136.88, "total_tokens": 45528256}
{"current_steps": 47415, "total_steps": 58920, "loss": 0.0004, "lr": 2.2347332001078755e-07, "epoch": 4.02367617107943, "percentage": 80.47, "elapsed_time": "1:14:51", "remaining_time": "0:18:09", "throughput": 10137.06, "total_tokens": 45532928}
{"current_steps": 47420, "total_steps": 58920, "loss": 0.0, "lr": 2.2328671038146307e-07, "epoch": 4.024100475220638, "percentage": 80.48, "elapsed_time": "1:14:52", "remaining_time": "0:18:09", "throughput": 10137.13, "total_tokens": 45537088}
{"current_steps": 47425, "total_steps": 58920, "loss": 0.0, "lr": 2.231001689059251e-07, "epoch": 4.024524779361847, "percentage": 80.49, "elapsed_time": "1:14:52", "remaining_time": "0:18:08", "throughput": 10137.37, "total_tokens": 45542144}
{"current_steps": 47430, "total_steps": 58920, "loss": 0.0, "lr": 2.229136956005424e-07, "epoch": 4.024949083503055, "percentage": 80.5, "elapsed_time": "1:14:52", "remaining_time": "0:18:08", "throughput": 10137.54, "total_tokens": 45546752}
{"current_steps": 47435, "total_steps": 58920, "loss": 0.0, "lr": 2.2272729048167714e-07, "epoch": 4.0253733876442634, "percentage": 80.51, "elapsed_time": "1:14:53", "remaining_time": "0:18:07", "throughput": 10137.65, "total_tokens": 45551104}
{"current_steps": 47440, "total_steps": 58920, "loss": 0.0, "lr": 2.2254095356568558e-07, "epoch": 4.025797691785471, "percentage": 80.52, "elapsed_time": "1:14:53", "remaining_time": "0:18:07", "throughput": 10137.88, "total_tokens": 45556096}
{"current_steps": 47445, "total_steps": 58920, "loss": 0.0, "lr": 2.2235468486891896e-07, "epoch": 4.02622199592668, "percentage": 80.52, "elapsed_time": "1:14:54", "remaining_time": "0:18:06", "throughput": 10138.05, "total_tokens": 45560768}
{"current_steps": 47450, "total_steps": 58920, "loss": 0.0, "lr": 2.2216848440772052e-07, "epoch": 4.026646300067888, "percentage": 80.53, "elapsed_time": "1:14:54", "remaining_time": "0:18:06", "throughput": 10138.14, "total_tokens": 45564992}
{"current_steps": 47455, "total_steps": 58920, "loss": 0.0, "lr": 2.2198235219842963e-07, "epoch": 4.027070604209097, "percentage": 80.54, "elapsed_time": "1:14:54", "remaining_time": "0:18:05", "throughput": 10138.53, "total_tokens": 45570944}
{"current_steps": 47460, "total_steps": 58920, "loss": 0.0, "lr": 2.2179628825737794e-07, "epoch": 4.027494908350305, "percentage": 80.55, "elapsed_time": "1:14:55", "remaining_time": "0:18:05", "throughput": 10138.66, "total_tokens": 45575424}
{"current_steps": 47465, "total_steps": 58920, "loss": 0.0, "lr": 2.216102926008927e-07, "epoch": 4.027919212491514, "percentage": 80.56, "elapsed_time": "1:14:55", "remaining_time": "0:18:04", "throughput": 10138.75, "total_tokens": 45579584}
{"current_steps": 47470, "total_steps": 58920, "loss": 0.0001, "lr": 2.2142436524529374e-07, "epoch": 4.028343516632722, "percentage": 80.57, "elapsed_time": "1:14:55", "remaining_time": "0:18:04", "throughput": 10138.82, "total_tokens": 45583680}
{"current_steps": 47475, "total_steps": 58920, "loss": 0.0, "lr": 2.2123850620689534e-07, "epoch": 4.028767820773931, "percentage": 80.58, "elapsed_time": "1:14:56", "remaining_time": "0:18:03", "throughput": 10138.96, "total_tokens": 45588160}
{"current_steps": 47480, "total_steps": 58920, "loss": 0.0, "lr": 2.2105271550200687e-07, "epoch": 4.029192124915139, "percentage": 80.58, "elapsed_time": "1:14:56", "remaining_time": "0:18:03", "throughput": 10139.19, "total_tokens": 45593152}
{"current_steps": 47485, "total_steps": 58920, "loss": 0.0, "lr": 2.2086699314692969e-07, "epoch": 4.029616429056348, "percentage": 80.59, "elapsed_time": "1:14:57", "remaining_time": "0:18:02", "throughput": 10139.36, "total_tokens": 45597888}
{"current_steps": 47490, "total_steps": 58920, "loss": 0.0, "lr": 2.2068133915796127e-07, "epoch": 4.030040733197556, "percentage": 80.6, "elapsed_time": "1:14:57", "remaining_time": "0:18:02", "throughput": 10139.53, "total_tokens": 45602624}
{"current_steps": 47495, "total_steps": 58920, "loss": 0.0, "lr": 2.2049575355139115e-07, "epoch": 4.0304650373387645, "percentage": 80.61, "elapsed_time": "1:14:57", "remaining_time": "0:18:01", "throughput": 10139.75, "total_tokens": 45607552}
{"current_steps": 47500, "total_steps": 58920, "loss": 0.0, "lr": 2.2031023634350466e-07, "epoch": 4.0308893414799725, "percentage": 80.62, "elapsed_time": "1:14:58", "remaining_time": "0:18:01", "throughput": 10139.95, "total_tokens": 45612416}
{"current_steps": 47505, "total_steps": 58920, "loss": 0.0, "lr": 2.2012478755058006e-07, "epoch": 4.031313645621181, "percentage": 80.63, "elapsed_time": "1:14:58", "remaining_time": "0:18:00", "throughput": 10140.1, "total_tokens": 45617024}
{"current_steps": 47510, "total_steps": 58920, "loss": 0.0, "lr": 2.1993940718888902e-07, "epoch": 4.031737949762389, "percentage": 80.63, "elapsed_time": "1:14:59", "remaining_time": "0:18:00", "throughput": 10140.44, "total_tokens": 45622656}
{"current_steps": 47515, "total_steps": 58920, "loss": 0.0, "lr": 2.1975409527469914e-07, "epoch": 4.032162253903598, "percentage": 80.64, "elapsed_time": "1:14:59", "remaining_time": "0:18:00", "throughput": 10140.7, "total_tokens": 45627776}
{"current_steps": 47520, "total_steps": 58920, "loss": 0.0, "lr": 2.1956885182426988e-07, "epoch": 4.032586558044806, "percentage": 80.65, "elapsed_time": "1:14:59", "remaining_time": "0:17:59", "throughput": 10140.86, "total_tokens": 45632448}
{"current_steps": 47525, "total_steps": 58920, "loss": 0.0, "lr": 2.193836768538564e-07, "epoch": 4.033010862186015, "percentage": 80.66, "elapsed_time": "1:15:00", "remaining_time": "0:17:59", "throughput": 10141.08, "total_tokens": 45637376}
{"current_steps": 47530, "total_steps": 58920, "loss": 0.0, "lr": 2.191985703797068e-07, "epoch": 4.033435166327223, "percentage": 80.67, "elapsed_time": "1:15:00", "remaining_time": "0:17:58", "throughput": 10141.35, "total_tokens": 45642624}
{"current_steps": 47535, "total_steps": 58920, "loss": 0.0, "lr": 2.1901353241806365e-07, "epoch": 4.033859470468432, "percentage": 80.68, "elapsed_time": "1:15:01", "remaining_time": "0:17:58", "throughput": 10141.52, "total_tokens": 45647232}
{"current_steps": 47540, "total_steps": 58920, "loss": 0.0, "lr": 2.1882856298516317e-07, "epoch": 4.03428377460964, "percentage": 80.69, "elapsed_time": "1:15:01", "remaining_time": "0:17:57", "throughput": 10141.67, "total_tokens": 45651776}
{"current_steps": 47545, "total_steps": 58920, "loss": 0.0, "lr": 2.1864366209723594e-07, "epoch": 4.034708078750849, "percentage": 80.69, "elapsed_time": "1:15:01", "remaining_time": "0:17:57", "throughput": 10141.83, "total_tokens": 45656320}
{"current_steps": 47550, "total_steps": 58920, "loss": 0.0, "lr": 2.1845882977050667e-07, "epoch": 4.035132382892057, "percentage": 80.7, "elapsed_time": "1:15:02", "remaining_time": "0:17:56", "throughput": 10142.11, "total_tokens": 45661568}
{"current_steps": 47555, "total_steps": 58920, "loss": 0.0, "lr": 2.182740660211927e-07, "epoch": 4.0355566870332655, "percentage": 80.71, "elapsed_time": "1:15:02", "remaining_time": "0:17:56", "throughput": 10142.33, "total_tokens": 45666496}
{"current_steps": 47560, "total_steps": 58920, "loss": 0.0, "lr": 2.1808937086550727e-07, "epoch": 4.0359809911744735, "percentage": 80.72, "elapsed_time": "1:15:02", "remaining_time": "0:17:55", "throughput": 10142.52, "total_tokens": 45671232}
{"current_steps": 47565, "total_steps": 58920, "loss": 0.0, "lr": 2.1790474431965657e-07, "epoch": 4.036405295315682, "percentage": 80.73, "elapsed_time": "1:15:03", "remaining_time": "0:17:55", "throughput": 10142.67, "total_tokens": 45675712}
{"current_steps": 47570, "total_steps": 58920, "loss": 0.0, "lr": 2.177201863998407e-07, "epoch": 4.03682959945689, "percentage": 80.74, "elapsed_time": "1:15:03", "remaining_time": "0:17:54", "throughput": 10142.89, "total_tokens": 45680576}
{"current_steps": 47575, "total_steps": 58920, "loss": 0.0, "lr": 2.1753569712225418e-07, "epoch": 4.037253903598099, "percentage": 80.75, "elapsed_time": "1:15:04", "remaining_time": "0:17:54", "throughput": 10143.16, "total_tokens": 45685760}
{"current_steps": 47580, "total_steps": 58920, "loss": 0.0, "lr": 2.1735127650308505e-07, "epoch": 4.037678207739307, "percentage": 80.75, "elapsed_time": "1:15:04", "remaining_time": "0:17:53", "throughput": 10143.38, "total_tokens": 45690752}
{"current_steps": 47585, "total_steps": 58920, "loss": 0.0, "lr": 2.171669245585157e-07, "epoch": 4.038102511880516, "percentage": 80.76, "elapsed_time": "1:15:04", "remaining_time": "0:17:53", "throughput": 10143.56, "total_tokens": 45695424}
{"current_steps": 47590, "total_steps": 58920, "loss": 0.0, "lr": 2.1698264130472233e-07, "epoch": 4.038526816021724, "percentage": 80.77, "elapsed_time": "1:15:05", "remaining_time": "0:17:52", "throughput": 10143.78, "total_tokens": 45700288}
{"current_steps": 47595, "total_steps": 58920, "loss": 0.0, "lr": 2.1679842675787507e-07, "epoch": 4.038951120162933, "percentage": 80.78, "elapsed_time": "1:15:05", "remaining_time": "0:17:52", "throughput": 10144.03, "total_tokens": 45705408}
{"current_steps": 47600, "total_steps": 58920, "loss": 0.0, "lr": 2.1661428093413813e-07, "epoch": 4.039375424304141, "percentage": 80.79, "elapsed_time": "1:15:06", "remaining_time": "0:17:51", "throughput": 10144.19, "total_tokens": 45709952}
{"current_steps": 47605, "total_steps": 58920, "loss": 0.0, "lr": 2.164302038496697e-07, "epoch": 4.03979972844535, "percentage": 80.8, "elapsed_time": "1:15:06", "remaining_time": "0:17:51", "throughput": 10144.38, "total_tokens": 45714688}
{"current_steps": 47610, "total_steps": 58920, "loss": 0.0, "lr": 2.1624619552062185e-07, "epoch": 4.040224032586558, "percentage": 80.8, "elapsed_time": "1:15:06", "remaining_time": "0:17:50", "throughput": 10144.65, "total_tokens": 45719936}
{"current_steps": 47615, "total_steps": 58920, "loss": 0.0, "lr": 2.1606225596314054e-07, "epoch": 4.040648336727767, "percentage": 80.81, "elapsed_time": "1:15:07", "remaining_time": "0:17:50", "throughput": 10144.87, "total_tokens": 45724864}
{"current_steps": 47620, "total_steps": 58920, "loss": 0.0, "lr": 2.1587838519336589e-07, "epoch": 4.0410726408689746, "percentage": 80.82, "elapsed_time": "1:15:07", "remaining_time": "0:17:49", "throughput": 10145.13, "total_tokens": 45729984}
{"current_steps": 47625, "total_steps": 58920, "loss": 0.0, "lr": 2.1569458322743184e-07, "epoch": 4.041496945010183, "percentage": 80.83, "elapsed_time": "1:15:07", "remaining_time": "0:17:49", "throughput": 10145.42, "total_tokens": 45735296}
{"current_steps": 47630, "total_steps": 58920, "loss": 0.0, "lr": 2.155108500814664e-07, "epoch": 4.041921249151391, "percentage": 80.84, "elapsed_time": "1:15:08", "remaining_time": "0:17:48", "throughput": 10145.54, "total_tokens": 45739712}
{"current_steps": 47635, "total_steps": 58920, "loss": 0.0, "lr": 2.1532718577159147e-07, "epoch": 4.0423455532926, "percentage": 80.85, "elapsed_time": "1:15:08", "remaining_time": "0:17:48", "throughput": 10145.62, "total_tokens": 45743872}
{"current_steps": 47640, "total_steps": 58920, "loss": 0.0, "lr": 2.1514359031392294e-07, "epoch": 4.042769857433808, "percentage": 80.86, "elapsed_time": "1:15:09", "remaining_time": "0:17:47", "throughput": 10145.83, "total_tokens": 45748800}
{"current_steps": 47645, "total_steps": 58920, "loss": 0.0, "lr": 2.1496006372457065e-07, "epoch": 4.043194161575017, "percentage": 80.86, "elapsed_time": "1:15:09", "remaining_time": "0:17:47", "throughput": 10145.97, "total_tokens": 45753280}
{"current_steps": 47650, "total_steps": 58920, "loss": 0.0, "lr": 2.1477660601963842e-07, "epoch": 4.043618465716225, "percentage": 80.87, "elapsed_time": "1:15:09", "remaining_time": "0:17:46", "throughput": 10146.07, "total_tokens": 45757504}
{"current_steps": 47655, "total_steps": 58920, "loss": 0.0, "lr": 2.1459321721522373e-07, "epoch": 4.044042769857434, "percentage": 80.88, "elapsed_time": "1:15:10", "remaining_time": "0:17:46", "throughput": 10146.21, "total_tokens": 45761920}
{"current_steps": 47660, "total_steps": 58920, "loss": 0.0, "lr": 2.14409897327419e-07, "epoch": 4.044467073998642, "percentage": 80.89, "elapsed_time": "1:15:10", "remaining_time": "0:17:45", "throughput": 10146.41, "total_tokens": 45766720}
{"current_steps": 47665, "total_steps": 58920, "loss": 0.0, "lr": 2.1422664637230893e-07, "epoch": 4.044891378139851, "percentage": 80.9, "elapsed_time": "1:15:11", "remaining_time": "0:17:45", "throughput": 10146.54, "total_tokens": 45771072}
{"current_steps": 47670, "total_steps": 58920, "loss": 0.0, "lr": 2.1404346436597408e-07, "epoch": 4.045315682281059, "percentage": 80.91, "elapsed_time": "1:15:11", "remaining_time": "0:17:44", "throughput": 10146.73, "total_tokens": 45775808}
{"current_steps": 47675, "total_steps": 58920, "loss": 0.0, "lr": 2.1386035132448743e-07, "epoch": 4.045739986422268, "percentage": 80.91, "elapsed_time": "1:15:11", "remaining_time": "0:17:44", "throughput": 10147.05, "total_tokens": 45781312}
{"current_steps": 47680, "total_steps": 58920, "loss": 0.0, "lr": 2.1367730726391642e-07, "epoch": 4.046164290563476, "percentage": 80.92, "elapsed_time": "1:15:12", "remaining_time": "0:17:43", "throughput": 10147.18, "total_tokens": 45785728}
{"current_steps": 47685, "total_steps": 58920, "loss": 0.0, "lr": 2.1349433220032287e-07, "epoch": 4.0465885947046845, "percentage": 80.93, "elapsed_time": "1:15:12", "remaining_time": "0:17:43", "throughput": 10147.38, "total_tokens": 45790592}
{"current_steps": 47690, "total_steps": 58920, "loss": 0.0, "lr": 2.133114261497616e-07, "epoch": 4.047012898845892, "percentage": 80.94, "elapsed_time": "1:15:12", "remaining_time": "0:17:42", "throughput": 10147.57, "total_tokens": 45795392}
{"current_steps": 47695, "total_steps": 58920, "loss": 0.0, "lr": 2.1312858912828292e-07, "epoch": 4.047437202987101, "percentage": 80.95, "elapsed_time": "1:15:13", "remaining_time": "0:17:42", "throughput": 10147.78, "total_tokens": 45800192}
{"current_steps": 47700, "total_steps": 58920, "loss": 0.0, "lr": 2.1294582115192906e-07, "epoch": 4.047861507128309, "percentage": 80.96, "elapsed_time": "1:15:13", "remaining_time": "0:17:41", "throughput": 10147.95, "total_tokens": 45804800}
{"current_steps": 47705, "total_steps": 58920, "loss": 0.0, "lr": 2.127631222367382e-07, "epoch": 4.048285811269518, "percentage": 80.97, "elapsed_time": "1:15:14", "remaining_time": "0:17:41", "throughput": 10148.14, "total_tokens": 45809536}
{"current_steps": 47710, "total_steps": 58920, "loss": 0.0, "lr": 2.1258049239874065e-07, "epoch": 4.048710115410726, "percentage": 80.97, "elapsed_time": "1:15:14", "remaining_time": "0:17:40", "throughput": 10148.32, "total_tokens": 45814272}
{"current_steps": 47715, "total_steps": 58920, "loss": 0.0, "lr": 2.1239793165396214e-07, "epoch": 4.049134419551935, "percentage": 80.98, "elapsed_time": "1:15:14", "remaining_time": "0:17:40", "throughput": 10148.48, "total_tokens": 45818880}
{"current_steps": 47720, "total_steps": 58920, "loss": 0.0, "lr": 2.1221544001842173e-07, "epoch": 4.049558723693143, "percentage": 80.99, "elapsed_time": "1:15:15", "remaining_time": "0:17:39", "throughput": 10148.68, "total_tokens": 45823680}
{"current_steps": 47725, "total_steps": 58920, "loss": 0.0, "lr": 2.1203301750813164e-07, "epoch": 4.049983027834352, "percentage": 81.0, "elapsed_time": "1:15:15", "remaining_time": "0:17:39", "throughput": 10149.01, "total_tokens": 45829184}
{"current_steps": 47730, "total_steps": 58920, "loss": 0.0, "lr": 2.1185066413909992e-07, "epoch": 4.05040733197556, "percentage": 81.01, "elapsed_time": "1:15:16", "remaining_time": "0:17:38", "throughput": 10149.13, "total_tokens": 45833536}
{"current_steps": 47735, "total_steps": 58920, "loss": 0.0, "lr": 2.1166837992732623e-07, "epoch": 4.050831636116769, "percentage": 81.02, "elapsed_time": "1:15:16", "remaining_time": "0:17:38", "throughput": 10149.25, "total_tokens": 45837888}
{"current_steps": 47740, "total_steps": 58920, "loss": 0.0, "lr": 2.114861648888062e-07, "epoch": 4.051255940257977, "percentage": 81.03, "elapsed_time": "1:15:16", "remaining_time": "0:17:37", "throughput": 10149.41, "total_tokens": 45842432}
{"current_steps": 47745, "total_steps": 58920, "loss": 0.0, "lr": 2.1130401903952831e-07, "epoch": 4.0516802443991855, "percentage": 81.03, "elapsed_time": "1:15:17", "remaining_time": "0:17:37", "throughput": 10149.62, "total_tokens": 45847296}
{"current_steps": 47750, "total_steps": 58920, "loss": 0.0, "lr": 2.1112194239547521e-07, "epoch": 4.0521045485403935, "percentage": 81.04, "elapsed_time": "1:15:17", "remaining_time": "0:17:36", "throughput": 10149.82, "total_tokens": 45852032}
{"current_steps": 47755, "total_steps": 58920, "loss": 0.0, "lr": 2.109399349726233e-07, "epoch": 4.052528852681602, "percentage": 81.05, "elapsed_time": "1:15:17", "remaining_time": "0:17:36", "throughput": 10150.06, "total_tokens": 45857088}
{"current_steps": 47760, "total_steps": 58920, "loss": 0.0, "lr": 2.107579967869433e-07, "epoch": 4.05295315682281, "percentage": 81.06, "elapsed_time": "1:15:18", "remaining_time": "0:17:35", "throughput": 10150.23, "total_tokens": 45861696}
{"current_steps": 47765, "total_steps": 58920, "loss": 0.0, "lr": 2.105761278543998e-07, "epoch": 4.053377460964019, "percentage": 81.07, "elapsed_time": "1:15:18", "remaining_time": "0:17:35", "throughput": 10150.48, "total_tokens": 45866816}
{"current_steps": 47770, "total_steps": 58920, "loss": 0.0, "lr": 2.1039432819095037e-07, "epoch": 4.053801765105227, "percentage": 81.08, "elapsed_time": "1:15:19", "remaining_time": "0:17:34", "throughput": 10150.75, "total_tokens": 45872064}
{"current_steps": 47775, "total_steps": 58920, "loss": 0.0, "lr": 2.1021259781254796e-07, "epoch": 4.054226069246436, "percentage": 81.08, "elapsed_time": "1:15:19", "remaining_time": "0:17:34", "throughput": 10150.93, "total_tokens": 45876672}
{"current_steps": 47780, "total_steps": 58920, "loss": 0.0, "lr": 2.1003093673513872e-07, "epoch": 4.054650373387644, "percentage": 81.09, "elapsed_time": "1:15:19", "remaining_time": "0:17:33", "throughput": 10151.14, "total_tokens": 45881472}
{"current_steps": 47785, "total_steps": 58920, "loss": 0.0, "lr": 2.0984934497466243e-07, "epoch": 4.055074677528853, "percentage": 81.1, "elapsed_time": "1:15:20", "remaining_time": "0:17:33", "throughput": 10151.35, "total_tokens": 45886272}
{"current_steps": 47790, "total_steps": 58920, "loss": 0.0, "lr": 2.096678225470534e-07, "epoch": 4.055498981670061, "percentage": 81.11, "elapsed_time": "1:15:20", "remaining_time": "0:17:32", "throughput": 10151.51, "total_tokens": 45890816}
{"current_steps": 47795, "total_steps": 58920, "loss": 0.0, "lr": 2.094863694682395e-07, "epoch": 4.05592328581127, "percentage": 81.12, "elapsed_time": "1:15:20", "remaining_time": "0:17:32", "throughput": 10151.67, "total_tokens": 45895424}
{"current_steps": 47800, "total_steps": 58920, "loss": 0.0, "lr": 2.0930498575414245e-07, "epoch": 4.056347589952478, "percentage": 81.13, "elapsed_time": "1:15:21", "remaining_time": "0:17:31", "throughput": 10151.83, "total_tokens": 45899968}
{"current_steps": 47805, "total_steps": 58920, "loss": 0.0, "lr": 2.091236714206781e-07, "epoch": 4.0567718940936865, "percentage": 81.14, "elapsed_time": "1:15:21", "remaining_time": "0:17:31", "throughput": 10152.02, "total_tokens": 45904640}
{"current_steps": 47810, "total_steps": 58920, "loss": 0.0, "lr": 2.0894242648375627e-07, "epoch": 4.0571961982348945, "percentage": 81.14, "elapsed_time": "1:15:22", "remaining_time": "0:17:30", "throughput": 10152.25, "total_tokens": 45909568}
{"current_steps": 47815, "total_steps": 58920, "loss": 0.0, "lr": 2.0876125095928033e-07, "epoch": 4.057620502376103, "percentage": 81.15, "elapsed_time": "1:15:22", "remaining_time": "0:17:30", "throughput": 10152.49, "total_tokens": 45914560}
{"current_steps": 47820, "total_steps": 58920, "loss": 0.0, "lr": 2.085801448631478e-07, "epoch": 4.058044806517311, "percentage": 81.16, "elapsed_time": "1:15:22", "remaining_time": "0:17:29", "throughput": 10152.75, "total_tokens": 45919744}
{"current_steps": 47825, "total_steps": 58920, "loss": 0.0, "lr": 2.0839910821125018e-07, "epoch": 4.05846911065852, "percentage": 81.17, "elapsed_time": "1:15:23", "remaining_time": "0:17:29", "throughput": 10152.98, "total_tokens": 45924672}
{"current_steps": 47830, "total_steps": 58920, "loss": 0.0, "lr": 2.0821814101947276e-07, "epoch": 4.058893414799728, "percentage": 81.18, "elapsed_time": "1:15:23", "remaining_time": "0:17:28", "throughput": 10153.15, "total_tokens": 45929280}
{"current_steps": 47835, "total_steps": 58920, "loss": 0.0, "lr": 2.0803724330369478e-07, "epoch": 4.059317718940937, "percentage": 81.19, "elapsed_time": "1:15:24", "remaining_time": "0:17:28", "throughput": 10153.29, "total_tokens": 45933824}
{"current_steps": 47840, "total_steps": 58920, "loss": 0.0, "lr": 2.0785641507978934e-07, "epoch": 4.059742023082145, "percentage": 81.19, "elapsed_time": "1:15:24", "remaining_time": "0:17:27", "throughput": 10153.41, "total_tokens": 45938176}
{"current_steps": 47845, "total_steps": 58920, "loss": 0.0, "lr": 2.076756563636234e-07, "epoch": 4.060166327223354, "percentage": 81.2, "elapsed_time": "1:15:24", "remaining_time": "0:17:27", "throughput": 10153.66, "total_tokens": 45943232}
{"current_steps": 47850, "total_steps": 58920, "loss": 0.0, "lr": 2.0749496717105797e-07, "epoch": 4.060590631364562, "percentage": 81.21, "elapsed_time": "1:15:25", "remaining_time": "0:17:26", "throughput": 10153.83, "total_tokens": 45947840}
{"current_steps": 47855, "total_steps": 58920, "loss": 0.0006, "lr": 2.0731434751794785e-07, "epoch": 4.061014935505771, "percentage": 81.22, "elapsed_time": "1:15:25", "remaining_time": "0:17:26", "throughput": 10154.09, "total_tokens": 45952960}
{"current_steps": 47860, "total_steps": 58920, "loss": 0.0, "lr": 2.071337974201417e-07, "epoch": 4.061439239646979, "percentage": 81.23, "elapsed_time": "1:15:25", "remaining_time": "0:17:25", "throughput": 10154.21, "total_tokens": 45957312}
{"current_steps": 47865, "total_steps": 58920, "loss": 0.0, "lr": 2.0695331689348227e-07, "epoch": 4.061863543788188, "percentage": 81.24, "elapsed_time": "1:15:26", "remaining_time": "0:17:25", "throughput": 10154.51, "total_tokens": 45962688}
{"current_steps": 47870, "total_steps": 58920, "loss": 0.0, "lr": 2.067729059538057e-07, "epoch": 4.062287847929396, "percentage": 81.25, "elapsed_time": "1:15:26", "remaining_time": "0:17:24", "throughput": 10154.7, "total_tokens": 45967424}
{"current_steps": 47875, "total_steps": 58920, "loss": 0.0, "lr": 2.0659256461694318e-07, "epoch": 4.062712152070604, "percentage": 81.25, "elapsed_time": "1:15:27", "remaining_time": "0:17:24", "throughput": 10154.88, "total_tokens": 45972032}
{"current_steps": 47880, "total_steps": 58920, "loss": 0.0, "lr": 2.0641229289871809e-07, "epoch": 4.063136456211812, "percentage": 81.26, "elapsed_time": "1:15:27", "remaining_time": "0:17:23", "throughput": 10155.02, "total_tokens": 45976448}
{"current_steps": 47885, "total_steps": 58920, "loss": 0.0, "lr": 2.0623209081494954e-07, "epoch": 4.063560760353021, "percentage": 81.27, "elapsed_time": "1:15:27", "remaining_time": "0:17:23", "throughput": 10155.21, "total_tokens": 45981184}
{"current_steps": 47890, "total_steps": 58920, "loss": 0.0, "lr": 2.0605195838144885e-07, "epoch": 4.063985064494229, "percentage": 81.28, "elapsed_time": "1:15:28", "remaining_time": "0:17:22", "throughput": 10155.4, "total_tokens": 45985856}
{"current_steps": 47895, "total_steps": 58920, "loss": 0.0, "lr": 2.058718956140223e-07, "epoch": 4.064409368635438, "percentage": 81.29, "elapsed_time": "1:15:28", "remaining_time": "0:17:22", "throughput": 10155.56, "total_tokens": 45990464}
{"current_steps": 47900, "total_steps": 58920, "loss": 0.0, "lr": 2.0569190252846968e-07, "epoch": 4.064833672776646, "percentage": 81.3, "elapsed_time": "1:15:28", "remaining_time": "0:17:21", "throughput": 10155.71, "total_tokens": 45994944}
{"current_steps": 47905, "total_steps": 58920, "loss": 0.0, "lr": 2.055119791405846e-07, "epoch": 4.065257976917855, "percentage": 81.31, "elapsed_time": "1:15:29", "remaining_time": "0:17:21", "throughput": 10155.85, "total_tokens": 45999424}
{"current_steps": 47910, "total_steps": 58920, "loss": 0.0, "lr": 2.053321254661553e-07, "epoch": 4.065682281059063, "percentage": 81.31, "elapsed_time": "1:15:29", "remaining_time": "0:17:20", "throughput": 10156.08, "total_tokens": 46004352}
{"current_steps": 47915, "total_steps": 58920, "loss": 0.0, "lr": 2.051523415209624e-07, "epoch": 4.066106585200272, "percentage": 81.32, "elapsed_time": "1:15:30", "remaining_time": "0:17:20", "throughput": 10156.27, "total_tokens": 46009024}
{"current_steps": 47920, "total_steps": 58920, "loss": 0.0, "lr": 2.0497262732078224e-07, "epoch": 4.06653088934148, "percentage": 81.33, "elapsed_time": "1:15:30", "remaining_time": "0:17:19", "throughput": 10156.53, "total_tokens": 46014208}
{"current_steps": 47925, "total_steps": 58920, "loss": 0.0, "lr": 2.0479298288138335e-07, "epoch": 4.066955193482689, "percentage": 81.34, "elapsed_time": "1:15:30", "remaining_time": "0:17:19", "throughput": 10156.75, "total_tokens": 46019072}
{"current_steps": 47930, "total_steps": 58920, "loss": 0.0, "lr": 2.046134082185288e-07, "epoch": 4.067379497623897, "percentage": 81.35, "elapsed_time": "1:15:31", "remaining_time": "0:17:18", "throughput": 10156.95, "total_tokens": 46023808}
{"current_steps": 47935, "total_steps": 58920, "loss": 0.0, "lr": 2.044339033479766e-07, "epoch": 4.0678038017651055, "percentage": 81.36, "elapsed_time": "1:15:31", "remaining_time": "0:17:18", "throughput": 10157.1, "total_tokens": 46028288}
{"current_steps": 47940, "total_steps": 58920, "loss": 0.0, "lr": 2.0425446828547634e-07, "epoch": 4.0682281059063135, "percentage": 81.36, "elapsed_time": "1:15:32", "remaining_time": "0:17:17", "throughput": 10157.28, "total_tokens": 46032960}
{"current_steps": 47945, "total_steps": 58920, "loss": 0.0, "lr": 2.0407510304677412e-07, "epoch": 4.068652410047522, "percentage": 81.37, "elapsed_time": "1:15:32", "remaining_time": "0:17:17", "throughput": 10157.5, "total_tokens": 46037888}
{"current_steps": 47950, "total_steps": 58920, "loss": 0.0, "lr": 2.0389580764760727e-07, "epoch": 4.06907671418873, "percentage": 81.38, "elapsed_time": "1:15:32", "remaining_time": "0:17:17", "throughput": 10157.68, "total_tokens": 46042560}
{"current_steps": 47955, "total_steps": 58920, "loss": 0.0, "lr": 2.0371658210370935e-07, "epoch": 4.069501018329939, "percentage": 81.39, "elapsed_time": "1:15:33", "remaining_time": "0:17:16", "throughput": 10157.89, "total_tokens": 46047360}
{"current_steps": 47960, "total_steps": 58920, "loss": 0.0, "lr": 2.035374264308063e-07, "epoch": 4.069925322471147, "percentage": 81.4, "elapsed_time": "1:15:33", "remaining_time": "0:17:16", "throughput": 10158.05, "total_tokens": 46051904}
{"current_steps": 47965, "total_steps": 58920, "loss": 0.0, "lr": 2.0335834064461844e-07, "epoch": 4.070349626612356, "percentage": 81.41, "elapsed_time": "1:15:33", "remaining_time": "0:17:15", "throughput": 10158.16, "total_tokens": 46056192}
{"current_steps": 47970, "total_steps": 58920, "loss": 0.0, "lr": 2.031793247608603e-07, "epoch": 4.070773930753564, "percentage": 81.42, "elapsed_time": "1:15:34", "remaining_time": "0:17:15", "throughput": 10158.36, "total_tokens": 46060992}
{"current_steps": 47975, "total_steps": 58920, "loss": 0.0, "lr": 2.030003787952389e-07, "epoch": 4.071198234894773, "percentage": 81.42, "elapsed_time": "1:15:34", "remaining_time": "0:17:14", "throughput": 10158.66, "total_tokens": 46066304}
{"current_steps": 47980, "total_steps": 58920, "loss": 0.0, "lr": 2.0282150276345722e-07, "epoch": 4.071622539035981, "percentage": 81.43, "elapsed_time": "1:15:35", "remaining_time": "0:17:14", "throughput": 10158.92, "total_tokens": 46071488}
{"current_steps": 47985, "total_steps": 58920, "loss": 0.0, "lr": 2.0264269668121003e-07, "epoch": 4.07204684317719, "percentage": 81.44, "elapsed_time": "1:15:35", "remaining_time": "0:17:13", "throughput": 10159.12, "total_tokens": 46076288}
{"current_steps": 47990, "total_steps": 58920, "loss": 0.0, "lr": 2.0246396056418757e-07, "epoch": 4.072471147318398, "percentage": 81.45, "elapsed_time": "1:15:35", "remaining_time": "0:17:13", "throughput": 10159.32, "total_tokens": 46081152}
{"current_steps": 47995, "total_steps": 58920, "loss": 0.0, "lr": 2.0228529442807308e-07, "epoch": 4.0728954514596065, "percentage": 81.46, "elapsed_time": "1:15:36", "remaining_time": "0:17:12", "throughput": 10159.53, "total_tokens": 46085952}
{"current_steps": 48000, "total_steps": 58920, "loss": 0.0, "lr": 2.0210669828854377e-07, "epoch": 4.0733197556008145, "percentage": 81.47, "elapsed_time": "1:15:36", "remaining_time": "0:17:12", "throughput": 10159.77, "total_tokens": 46090944}
{"current_steps": 48005, "total_steps": 58920, "loss": 0.0, "lr": 2.01928172161271e-07, "epoch": 4.073744059742023, "percentage": 81.47, "elapsed_time": "1:15:37", "remaining_time": "0:17:11", "throughput": 10160.04, "total_tokens": 46096128}
{"current_steps": 48010, "total_steps": 58920, "loss": 0.0, "lr": 2.0174971606191972e-07, "epoch": 4.074168363883231, "percentage": 81.48, "elapsed_time": "1:15:37", "remaining_time": "0:17:11", "throughput": 10160.2, "total_tokens": 46100736}
{"current_steps": 48015, "total_steps": 58920, "loss": 0.0, "lr": 2.0157133000614878e-07, "epoch": 4.07459266802444, "percentage": 81.49, "elapsed_time": "1:15:37", "remaining_time": "0:17:10", "throughput": 10160.47, "total_tokens": 46105920}
{"current_steps": 48020, "total_steps": 58920, "loss": 0.0, "lr": 2.0139301400961084e-07, "epoch": 4.075016972165648, "percentage": 81.5, "elapsed_time": "1:15:38", "remaining_time": "0:17:10", "throughput": 10160.69, "total_tokens": 46110848}
{"current_steps": 48025, "total_steps": 58920, "loss": 0.0, "lr": 2.0121476808795267e-07, "epoch": 4.075441276306857, "percentage": 81.51, "elapsed_time": "1:15:38", "remaining_time": "0:17:09", "throughput": 10160.92, "total_tokens": 46115840}
{"current_steps": 48030, "total_steps": 58920, "loss": 0.0, "lr": 2.0103659225681446e-07, "epoch": 4.075865580448065, "percentage": 81.52, "elapsed_time": "1:15:38", "remaining_time": "0:17:09", "throughput": 10161.12, "total_tokens": 46120640}
{"current_steps": 48035, "total_steps": 58920, "loss": 0.0, "lr": 2.0085848653183079e-07, "epoch": 4.076289884589274, "percentage": 81.53, "elapsed_time": "1:15:39", "remaining_time": "0:17:08", "throughput": 10161.43, "total_tokens": 46126080}
{"current_steps": 48040, "total_steps": 58920, "loss": 0.0, "lr": 2.006804509286295e-07, "epoch": 4.076714188730482, "percentage": 81.53, "elapsed_time": "1:15:39", "remaining_time": "0:17:08", "throughput": 10161.63, "total_tokens": 46130880}
{"current_steps": 48045, "total_steps": 58920, "loss": 0.0, "lr": 2.0050248546283277e-07, "epoch": 4.077138492871691, "percentage": 81.54, "elapsed_time": "1:15:40", "remaining_time": "0:17:07", "throughput": 10162.1, "total_tokens": 46137280}
{"current_steps": 48050, "total_steps": 58920, "loss": 0.0, "lr": 2.0032459015005642e-07, "epoch": 4.077562797012899, "percentage": 81.55, "elapsed_time": "1:15:40", "remaining_time": "0:17:07", "throughput": 10162.29, "total_tokens": 46141952}
{"current_steps": 48055, "total_steps": 58920, "loss": 0.0, "lr": 2.0014676500590998e-07, "epoch": 4.077987101154108, "percentage": 81.56, "elapsed_time": "1:15:40", "remaining_time": "0:17:06", "throughput": 10162.58, "total_tokens": 46147264}
{"current_steps": 48060, "total_steps": 58920, "loss": 0.0, "lr": 1.9996901004599708e-07, "epoch": 4.0784114052953155, "percentage": 81.57, "elapsed_time": "1:15:41", "remaining_time": "0:17:06", "throughput": 10162.73, "total_tokens": 46151808}
{"current_steps": 48065, "total_steps": 58920, "loss": 0.0, "lr": 1.9979132528591513e-07, "epoch": 4.078835709436524, "percentage": 81.58, "elapsed_time": "1:15:41", "remaining_time": "0:17:05", "throughput": 10162.97, "total_tokens": 46156736}
{"current_steps": 48070, "total_steps": 58920, "loss": 0.0, "lr": 1.996137107412551e-07, "epoch": 4.079260013577732, "percentage": 81.59, "elapsed_time": "1:15:42", "remaining_time": "0:17:05", "throughput": 10163.17, "total_tokens": 46161536}
{"current_steps": 48075, "total_steps": 58920, "loss": 0.0, "lr": 1.994361664276023e-07, "epoch": 4.079684317718941, "percentage": 81.59, "elapsed_time": "1:15:42", "remaining_time": "0:17:04", "throughput": 10163.28, "total_tokens": 46165888}
{"current_steps": 48080, "total_steps": 58920, "loss": 0.0, "lr": 1.9925869236053538e-07, "epoch": 4.080108621860149, "percentage": 81.6, "elapsed_time": "1:15:42", "remaining_time": "0:17:04", "throughput": 10163.44, "total_tokens": 46170432}
{"current_steps": 48085, "total_steps": 58920, "loss": 0.0, "lr": 1.990812885556269e-07, "epoch": 4.080532926001358, "percentage": 81.61, "elapsed_time": "1:15:43", "remaining_time": "0:17:03", "throughput": 10163.57, "total_tokens": 46174848}
{"current_steps": 48090, "total_steps": 58920, "loss": 0.0, "lr": 1.9890395502844415e-07, "epoch": 4.080957230142566, "percentage": 81.62, "elapsed_time": "1:15:43", "remaining_time": "0:17:03", "throughput": 10163.83, "total_tokens": 46179968}
{"current_steps": 48095, "total_steps": 58920, "loss": 0.0, "lr": 1.987266917945468e-07, "epoch": 4.081381534283775, "percentage": 81.63, "elapsed_time": "1:15:43", "remaining_time": "0:17:02", "throughput": 10164.15, "total_tokens": 46185472}
{"current_steps": 48100, "total_steps": 58920, "loss": 0.0, "lr": 1.9854949886948924e-07, "epoch": 4.081805838424983, "percentage": 81.64, "elapsed_time": "1:15:44", "remaining_time": "0:17:02", "throughput": 10164.35, "total_tokens": 46190208}
{"current_steps": 48105, "total_steps": 58920, "loss": 0.0, "lr": 1.9837237626881952e-07, "epoch": 4.082230142566192, "percentage": 81.64, "elapsed_time": "1:15:44", "remaining_time": "0:17:01", "throughput": 10164.5, "total_tokens": 46194752}
{"current_steps": 48110, "total_steps": 58920, "loss": 0.0, "lr": 1.9819532400807947e-07, "epoch": 4.0826544467074, "percentage": 81.65, "elapsed_time": "1:15:45", "remaining_time": "0:17:01", "throughput": 10164.66, "total_tokens": 46199296}
{"current_steps": 48115, "total_steps": 58920, "loss": 0.0, "lr": 1.9801834210280488e-07, "epoch": 4.083078750848609, "percentage": 81.66, "elapsed_time": "1:15:45", "remaining_time": "0:17:00", "throughput": 10164.95, "total_tokens": 46204736}
{"current_steps": 48120, "total_steps": 58920, "loss": 0.0, "lr": 1.9784143056852497e-07, "epoch": 4.083503054989817, "percentage": 81.67, "elapsed_time": "1:15:45", "remaining_time": "0:17:00", "throughput": 10165.17, "total_tokens": 46209600}
{"current_steps": 48125, "total_steps": 58920, "loss": 0.0, "lr": 1.976645894207638e-07, "epoch": 4.0839273591310254, "percentage": 81.68, "elapsed_time": "1:15:46", "remaining_time": "0:16:59", "throughput": 10165.39, "total_tokens": 46214592}
{"current_steps": 48130, "total_steps": 58920, "loss": 0.0, "lr": 1.9748781867503762e-07, "epoch": 4.084351663272233, "percentage": 81.69, "elapsed_time": "1:15:46", "remaining_time": "0:16:59", "throughput": 10165.66, "total_tokens": 46219776}
{"current_steps": 48135, "total_steps": 58920, "loss": 0.0, "lr": 1.9731111834685842e-07, "epoch": 4.084775967413442, "percentage": 81.7, "elapsed_time": "1:15:47", "remaining_time": "0:16:58", "throughput": 10165.8, "total_tokens": 46224192}
{"current_steps": 48140, "total_steps": 58920, "loss": 0.0, "lr": 1.9713448845173031e-07, "epoch": 4.08520027155465, "percentage": 81.7, "elapsed_time": "1:15:47", "remaining_time": "0:16:58", "throughput": 10165.96, "total_tokens": 46228800}
{"current_steps": 48145, "total_steps": 58920, "loss": 0.0, "lr": 1.9695792900515172e-07, "epoch": 4.085624575695859, "percentage": 81.71, "elapsed_time": "1:15:47", "remaining_time": "0:16:57", "throughput": 10166.16, "total_tokens": 46233600}
{"current_steps": 48150, "total_steps": 58920, "loss": 0.0, "lr": 1.967814400226161e-07, "epoch": 4.086048879837067, "percentage": 81.72, "elapsed_time": "1:15:48", "remaining_time": "0:16:57", "throughput": 10166.39, "total_tokens": 46238592}
{"current_steps": 48155, "total_steps": 58920, "loss": 0.0, "lr": 1.9660502151960845e-07, "epoch": 4.086473183978276, "percentage": 81.73, "elapsed_time": "1:15:48", "remaining_time": "0:16:56", "throughput": 10166.48, "total_tokens": 46242816}
{"current_steps": 48160, "total_steps": 58920, "loss": 0.0, "lr": 1.964286735116102e-07, "epoch": 4.086897488119484, "percentage": 81.74, "elapsed_time": "1:15:48", "remaining_time": "0:16:56", "throughput": 10166.77, "total_tokens": 46248128}
{"current_steps": 48165, "total_steps": 58920, "loss": 0.0, "lr": 1.9625239601409392e-07, "epoch": 4.087321792260693, "percentage": 81.75, "elapsed_time": "1:15:49", "remaining_time": "0:16:55", "throughput": 10166.98, "total_tokens": 46253056}
{"current_steps": 48170, "total_steps": 58920, "loss": 0.0, "lr": 1.9607618904252853e-07, "epoch": 4.087746096401901, "percentage": 81.75, "elapsed_time": "1:15:49", "remaining_time": "0:16:55", "throughput": 10167.53, "total_tokens": 46259968}
{"current_steps": 48175, "total_steps": 58920, "loss": 0.0, "lr": 1.9590005261237476e-07, "epoch": 4.08817040054311, "percentage": 81.76, "elapsed_time": "1:15:50", "remaining_time": "0:16:54", "throughput": 10167.67, "total_tokens": 46264448}
{"current_steps": 48180, "total_steps": 58920, "loss": 0.0, "lr": 1.9572398673908785e-07, "epoch": 4.088594704684318, "percentage": 81.77, "elapsed_time": "1:15:50", "remaining_time": "0:16:54", "throughput": 10167.81, "total_tokens": 46268864}
{"current_steps": 48185, "total_steps": 58920, "loss": 0.0, "lr": 1.9554799143811796e-07, "epoch": 4.0890190088255265, "percentage": 81.78, "elapsed_time": "1:15:50", "remaining_time": "0:16:53", "throughput": 10168.02, "total_tokens": 46273728}
{"current_steps": 48190, "total_steps": 58920, "loss": 0.0, "lr": 1.953720667249067e-07, "epoch": 4.0894433129667345, "percentage": 81.79, "elapsed_time": "1:15:51", "remaining_time": "0:16:53", "throughput": 10168.26, "total_tokens": 46278720}
{"current_steps": 48195, "total_steps": 58920, "loss": 0.0, "lr": 1.9519621261489205e-07, "epoch": 4.089867617107943, "percentage": 81.8, "elapsed_time": "1:15:51", "remaining_time": "0:16:52", "throughput": 10168.37, "total_tokens": 46283008}
{"current_steps": 48200, "total_steps": 58920, "loss": 0.0, "lr": 1.9502042912350347e-07, "epoch": 4.090291921249151, "percentage": 81.81, "elapsed_time": "1:15:52", "remaining_time": "0:16:52", "throughput": 10168.52, "total_tokens": 46287488}
{"current_steps": 48205, "total_steps": 58920, "loss": 0.0, "lr": 1.9484471626616605e-07, "epoch": 4.09071622539036, "percentage": 81.81, "elapsed_time": "1:15:52", "remaining_time": "0:16:51", "throughput": 10168.81, "total_tokens": 46292800}
{"current_steps": 48210, "total_steps": 58920, "loss": 0.0, "lr": 1.946690740582979e-07, "epoch": 4.091140529531568, "percentage": 81.82, "elapsed_time": "1:15:52", "remaining_time": "0:16:51", "throughput": 10168.92, "total_tokens": 46297088}
{"current_steps": 48215, "total_steps": 58920, "loss": 0.0, "lr": 1.9449350251531082e-07, "epoch": 4.091564833672777, "percentage": 81.83, "elapsed_time": "1:15:53", "remaining_time": "0:16:50", "throughput": 10169.13, "total_tokens": 46301952}
{"current_steps": 48220, "total_steps": 58920, "loss": 0.0, "lr": 1.9431800165261092e-07, "epoch": 4.091989137813985, "percentage": 81.84, "elapsed_time": "1:15:53", "remaining_time": "0:16:50", "throughput": 10169.37, "total_tokens": 46307008}
{"current_steps": 48225, "total_steps": 58920, "loss": 0.0, "lr": 1.9414257148559697e-07, "epoch": 4.092413441955194, "percentage": 81.85, "elapsed_time": "1:15:53", "remaining_time": "0:16:49", "throughput": 10169.51, "total_tokens": 46311424}
{"current_steps": 48230, "total_steps": 58920, "loss": 0.0, "lr": 1.9396721202966305e-07, "epoch": 4.092837746096402, "percentage": 81.86, "elapsed_time": "1:15:54", "remaining_time": "0:16:49", "throughput": 10169.67, "total_tokens": 46315968}
{"current_steps": 48235, "total_steps": 58920, "loss": 0.0, "lr": 1.937919233001961e-07, "epoch": 4.093262050237611, "percentage": 81.87, "elapsed_time": "1:15:54", "remaining_time": "0:16:48", "throughput": 10169.77, "total_tokens": 46320256}
{"current_steps": 48240, "total_steps": 58920, "loss": 0.0, "lr": 1.9361670531257702e-07, "epoch": 4.093686354378819, "percentage": 81.87, "elapsed_time": "1:15:55", "remaining_time": "0:16:48", "throughput": 10169.94, "total_tokens": 46324864}
{"current_steps": 48245, "total_steps": 58920, "loss": 0.0, "lr": 1.9344155808218065e-07, "epoch": 4.0941106585200275, "percentage": 81.88, "elapsed_time": "1:15:55", "remaining_time": "0:16:47", "throughput": 10170.13, "total_tokens": 46329600}
{"current_steps": 48250, "total_steps": 58920, "loss": 0.0, "lr": 1.9326648162437554e-07, "epoch": 4.0945349626612355, "percentage": 81.89, "elapsed_time": "1:15:55", "remaining_time": "0:16:47", "throughput": 10170.32, "total_tokens": 46334400}
{"current_steps": 48255, "total_steps": 58920, "loss": 0.0, "lr": 1.9309147595452402e-07, "epoch": 4.094959266802444, "percentage": 81.9, "elapsed_time": "1:15:56", "remaining_time": "0:16:46", "throughput": 10170.51, "total_tokens": 46339136}
{"current_steps": 48260, "total_steps": 58920, "loss": 0.0, "lr": 1.9291654108798206e-07, "epoch": 4.095383570943652, "percentage": 81.91, "elapsed_time": "1:15:56", "remaining_time": "0:16:46", "throughput": 10170.74, "total_tokens": 46344128}
{"current_steps": 48265, "total_steps": 58920, "loss": 0.0, "lr": 1.927416770400997e-07, "epoch": 4.095807875084861, "percentage": 81.92, "elapsed_time": "1:15:57", "remaining_time": "0:16:46", "throughput": 10171.01, "total_tokens": 46349440}
{"current_steps": 48270, "total_steps": 58920, "loss": 0.0, "lr": 1.9256688382622056e-07, "epoch": 4.096232179226069, "percentage": 81.92, "elapsed_time": "1:15:57", "remaining_time": "0:16:45", "throughput": 10171.19, "total_tokens": 46354112}
{"current_steps": 48275, "total_steps": 58920, "loss": 0.0, "lr": 1.9239216146168213e-07, "epoch": 4.096656483367278, "percentage": 81.93, "elapsed_time": "1:15:57", "remaining_time": "0:16:45", "throughput": 10171.43, "total_tokens": 46359168}
{"current_steps": 48280, "total_steps": 58920, "loss": 0.0, "lr": 1.9221750996181563e-07, "epoch": 4.097080787508486, "percentage": 81.94, "elapsed_time": "1:15:58", "remaining_time": "0:16:44", "throughput": 10171.68, "total_tokens": 46364288}
{"current_steps": 48285, "total_steps": 58920, "loss": 0.0, "lr": 1.9204292934194622e-07, "epoch": 4.097505091649695, "percentage": 81.95, "elapsed_time": "1:15:58", "remaining_time": "0:16:44", "throughput": 10171.96, "total_tokens": 46369536}
{"current_steps": 48290, "total_steps": 58920, "loss": 0.0, "lr": 1.9186841961739265e-07, "epoch": 4.097929395790903, "percentage": 81.96, "elapsed_time": "1:15:58", "remaining_time": "0:16:43", "throughput": 10172.14, "total_tokens": 46374208}
{"current_steps": 48295, "total_steps": 58920, "loss": 0.0, "lr": 1.9169398080346742e-07, "epoch": 4.098353699932112, "percentage": 81.97, "elapsed_time": "1:15:59", "remaining_time": "0:16:43", "throughput": 10172.28, "total_tokens": 46378688}
{"current_steps": 48300, "total_steps": 58920, "loss": 0.0, "lr": 1.9151961291547703e-07, "epoch": 4.09877800407332, "percentage": 81.98, "elapsed_time": "1:15:59", "remaining_time": "0:16:42", "throughput": 10172.52, "total_tokens": 46383744}
{"current_steps": 48305, "total_steps": 58920, "loss": 0.0, "lr": 1.9134531596872173e-07, "epoch": 4.099202308214529, "percentage": 81.98, "elapsed_time": "1:16:00", "remaining_time": "0:16:42", "throughput": 10172.67, "total_tokens": 46388224}
{"current_steps": 48310, "total_steps": 58920, "loss": 0.0, "lr": 1.9117108997849518e-07, "epoch": 4.0996266123557366, "percentage": 81.99, "elapsed_time": "1:16:00", "remaining_time": "0:16:41", "throughput": 10172.84, "total_tokens": 46392832}
{"current_steps": 48315, "total_steps": 58920, "loss": 0.0, "lr": 1.909969349600852e-07, "epoch": 4.100050916496945, "percentage": 82.0, "elapsed_time": "1:16:00", "remaining_time": "0:16:41", "throughput": 10173.13, "total_tokens": 46398144}
{"current_steps": 48320, "total_steps": 58920, "loss": 0.0, "lr": 1.9082285092877337e-07, "epoch": 4.100475220638153, "percentage": 82.01, "elapsed_time": "1:16:01", "remaining_time": "0:16:40", "throughput": 10173.33, "total_tokens": 46402944}
{"current_steps": 48325, "total_steps": 58920, "loss": 0.0, "lr": 1.9064883789983478e-07, "epoch": 4.100899524779362, "percentage": 82.02, "elapsed_time": "1:16:01", "remaining_time": "0:16:40", "throughput": 10173.48, "total_tokens": 46407488}
{"current_steps": 48330, "total_steps": 58920, "loss": 0.0, "lr": 1.904748958885386e-07, "epoch": 4.10132382892057, "percentage": 82.03, "elapsed_time": "1:16:01", "remaining_time": "0:16:39", "throughput": 10173.67, "total_tokens": 46412160}
{"current_steps": 48335, "total_steps": 58920, "loss": 0.0, "lr": 1.903010249101472e-07, "epoch": 4.101748133061779, "percentage": 82.03, "elapsed_time": "1:16:02", "remaining_time": "0:16:39", "throughput": 10173.85, "total_tokens": 46416832}
{"current_steps": 48340, "total_steps": 58920, "loss": 0.0, "lr": 1.9012722497991795e-07, "epoch": 4.102172437202987, "percentage": 82.04, "elapsed_time": "1:16:02", "remaining_time": "0:16:38", "throughput": 10173.98, "total_tokens": 46421248}
{"current_steps": 48345, "total_steps": 58920, "loss": 0.0, "lr": 1.8995349611310053e-07, "epoch": 4.102596741344196, "percentage": 82.05, "elapsed_time": "1:16:03", "remaining_time": "0:16:38", "throughput": 10174.22, "total_tokens": 46426240}
{"current_steps": 48350, "total_steps": 58920, "loss": 0.0, "lr": 1.8977983832493903e-07, "epoch": 4.103021045485404, "percentage": 82.06, "elapsed_time": "1:16:03", "remaining_time": "0:16:37", "throughput": 10174.46, "total_tokens": 46431360}
{"current_steps": 48355, "total_steps": 58920, "loss": 0.0, "lr": 1.8960625163067156e-07, "epoch": 4.103445349626613, "percentage": 82.07, "elapsed_time": "1:16:03", "remaining_time": "0:16:37", "throughput": 10174.63, "total_tokens": 46435968}
{"current_steps": 48360, "total_steps": 58920, "loss": 0.0, "lr": 1.8943273604552923e-07, "epoch": 4.103869653767821, "percentage": 82.08, "elapsed_time": "1:16:04", "remaining_time": "0:16:36", "throughput": 10174.79, "total_tokens": 46440512}
{"current_steps": 48365, "total_steps": 58920, "loss": 0.0, "lr": 1.892592915847383e-07, "epoch": 4.10429395790903, "percentage": 82.09, "elapsed_time": "1:16:04", "remaining_time": "0:16:36", "throughput": 10174.95, "total_tokens": 46445120}
{"current_steps": 48370, "total_steps": 58920, "loss": 0.0, "lr": 1.8908591826351695e-07, "epoch": 4.104718262050238, "percentage": 82.09, "elapsed_time": "1:16:05", "remaining_time": "0:16:35", "throughput": 10175.22, "total_tokens": 46450304}
{"current_steps": 48375, "total_steps": 58920, "loss": 0.0, "lr": 1.8891261609707887e-07, "epoch": 4.1051425661914465, "percentage": 82.1, "elapsed_time": "1:16:05", "remaining_time": "0:16:35", "throughput": 10175.44, "total_tokens": 46455168}
{"current_steps": 48380, "total_steps": 58920, "loss": 0.0, "lr": 1.8873938510062982e-07, "epoch": 4.105566870332654, "percentage": 82.11, "elapsed_time": "1:16:05", "remaining_time": "0:16:34", "throughput": 10175.68, "total_tokens": 46460224}
{"current_steps": 48385, "total_steps": 58920, "loss": 0.0, "lr": 1.8856622528937127e-07, "epoch": 4.105991174473862, "percentage": 82.12, "elapsed_time": "1:16:06", "remaining_time": "0:16:34", "throughput": 10175.85, "total_tokens": 46464832}
{"current_steps": 48390, "total_steps": 58920, "loss": 0.0, "lr": 1.8839313667849642e-07, "epoch": 4.106415478615071, "percentage": 82.13, "elapsed_time": "1:16:06", "remaining_time": "0:16:33", "throughput": 10176.01, "total_tokens": 46469376}
{"current_steps": 48395, "total_steps": 58920, "loss": 0.0, "lr": 1.8822011928319338e-07, "epoch": 4.10683978275628, "percentage": 82.14, "elapsed_time": "1:16:06", "remaining_time": "0:16:33", "throughput": 10176.13, "total_tokens": 46473728}
{"current_steps": 48400, "total_steps": 58920, "loss": 0.0, "lr": 1.8804717311864436e-07, "epoch": 4.107264086897488, "percentage": 82.15, "elapsed_time": "1:16:07", "remaining_time": "0:16:32", "throughput": 10176.29, "total_tokens": 46478336}
{"current_steps": 48405, "total_steps": 58920, "loss": 0.0, "lr": 1.8787429820002387e-07, "epoch": 4.107688391038696, "percentage": 82.15, "elapsed_time": "1:16:07", "remaining_time": "0:16:32", "throughput": 10176.52, "total_tokens": 46483264}
{"current_steps": 48410, "total_steps": 58920, "loss": 0.0, "lr": 1.8770149454250217e-07, "epoch": 4.108112695179905, "percentage": 82.16, "elapsed_time": "1:16:08", "remaining_time": "0:16:31", "throughput": 10176.72, "total_tokens": 46488128}
{"current_steps": 48415, "total_steps": 58920, "loss": 0.0, "lr": 1.8752876216124092e-07, "epoch": 4.108536999321114, "percentage": 82.17, "elapsed_time": "1:16:08", "remaining_time": "0:16:31", "throughput": 10176.94, "total_tokens": 46492992}
{"current_steps": 48420, "total_steps": 58920, "loss": 0.0, "lr": 1.8735610107139765e-07, "epoch": 4.108961303462322, "percentage": 82.18, "elapsed_time": "1:16:08", "remaining_time": "0:16:30", "throughput": 10177.1, "total_tokens": 46497600}
{"current_steps": 48425, "total_steps": 58920, "loss": 0.0, "lr": 1.8718351128812272e-07, "epoch": 4.10938560760353, "percentage": 82.19, "elapsed_time": "1:16:09", "remaining_time": "0:16:30", "throughput": 10177.29, "total_tokens": 46502336}
{"current_steps": 48430, "total_steps": 58920, "loss": 0.0, "lr": 1.8701099282655953e-07, "epoch": 4.109809911744739, "percentage": 82.2, "elapsed_time": "1:16:09", "remaining_time": "0:16:29", "throughput": 10177.5, "total_tokens": 46507200}
{"current_steps": 48435, "total_steps": 58920, "loss": 0.0, "lr": 1.8683854570184688e-07, "epoch": 4.110234215885947, "percentage": 82.2, "elapsed_time": "1:16:09", "remaining_time": "0:16:29", "throughput": 10177.67, "total_tokens": 46511872}
{"current_steps": 48440, "total_steps": 58920, "loss": 0.0, "lr": 1.8666616992911543e-07, "epoch": 4.1106585200271555, "percentage": 82.21, "elapsed_time": "1:16:10", "remaining_time": "0:16:28", "throughput": 10177.91, "total_tokens": 46516864}
{"current_steps": 48445, "total_steps": 58920, "loss": 0.0, "lr": 1.8649386552349134e-07, "epoch": 4.1110828241683635, "percentage": 82.22, "elapsed_time": "1:16:10", "remaining_time": "0:16:28", "throughput": 10178.21, "total_tokens": 46522304}
{"current_steps": 48450, "total_steps": 58920, "loss": 0.0, "lr": 1.8632163250009337e-07, "epoch": 4.111507128309572, "percentage": 82.23, "elapsed_time": "1:16:11", "remaining_time": "0:16:27", "throughput": 10178.44, "total_tokens": 46527232}
{"current_steps": 48455, "total_steps": 58920, "loss": 0.0, "lr": 1.8614947087403444e-07, "epoch": 4.11193143245078, "percentage": 82.24, "elapsed_time": "1:16:11", "remaining_time": "0:16:27", "throughput": 10178.57, "total_tokens": 46531712}
{"current_steps": 48460, "total_steps": 58920, "loss": 0.0, "lr": 1.85977380660421e-07, "epoch": 4.112355736591989, "percentage": 82.25, "elapsed_time": "1:16:11", "remaining_time": "0:16:26", "throughput": 10178.88, "total_tokens": 46537152}
{"current_steps": 48465, "total_steps": 58920, "loss": 0.0, "lr": 1.8580536187435336e-07, "epoch": 4.112780040733197, "percentage": 82.26, "elapsed_time": "1:16:12", "remaining_time": "0:16:26", "throughput": 10179.1, "total_tokens": 46542080}
{"current_steps": 48470, "total_steps": 58920, "loss": 0.0, "lr": 1.8563341453092583e-07, "epoch": 4.113204344874406, "percentage": 82.26, "elapsed_time": "1:16:12", "remaining_time": "0:16:25", "throughput": 10179.31, "total_tokens": 46546944}
{"current_steps": 48475, "total_steps": 58920, "loss": 0.0, "lr": 1.854615386452254e-07, "epoch": 4.113628649015614, "percentage": 82.27, "elapsed_time": "1:16:13", "remaining_time": "0:16:25", "throughput": 10179.51, "total_tokens": 46551744}
{"current_steps": 48480, "total_steps": 58920, "loss": 0.0, "lr": 1.8528973423233442e-07, "epoch": 4.114052953156823, "percentage": 82.28, "elapsed_time": "1:16:13", "remaining_time": "0:16:24", "throughput": 10179.73, "total_tokens": 46556672}
{"current_steps": 48485, "total_steps": 58920, "loss": 0.0, "lr": 1.8511800130732767e-07, "epoch": 4.114477257298031, "percentage": 82.29, "elapsed_time": "1:16:13", "remaining_time": "0:16:24", "throughput": 10179.89, "total_tokens": 46561280}
{"current_steps": 48490, "total_steps": 58920, "loss": 0.0, "lr": 1.849463398852742e-07, "epoch": 4.11490156143924, "percentage": 82.3, "elapsed_time": "1:16:14", "remaining_time": "0:16:23", "throughput": 10180.11, "total_tokens": 46566208}
{"current_steps": 48495, "total_steps": 58920, "loss": 0.0, "lr": 1.8477474998123677e-07, "epoch": 4.115325865580448, "percentage": 82.31, "elapsed_time": "1:16:14", "remaining_time": "0:16:23", "throughput": 10180.36, "total_tokens": 46571328}
{"current_steps": 48500, "total_steps": 58920, "loss": 0.0, "lr": 1.846032316102716e-07, "epoch": 4.1157501697216565, "percentage": 82.32, "elapsed_time": "1:16:15", "remaining_time": "0:16:22", "throughput": 10180.57, "total_tokens": 46576256}
{"current_steps": 48505, "total_steps": 58920, "loss": 0.0, "lr": 1.8443178478742883e-07, "epoch": 4.1161744738628645, "percentage": 82.32, "elapsed_time": "1:16:15", "remaining_time": "0:16:22", "throughput": 10180.72, "total_tokens": 46580736}
{"current_steps": 48510, "total_steps": 58920, "loss": 0.0, "lr": 1.8426040952775236e-07, "epoch": 4.116598778004073, "percentage": 82.33, "elapsed_time": "1:16:15", "remaining_time": "0:16:21", "throughput": 10180.9, "total_tokens": 46585472}
{"current_steps": 48515, "total_steps": 58920, "loss": 0.0, "lr": 1.840891058462798e-07, "epoch": 4.117023082145281, "percentage": 82.34, "elapsed_time": "1:16:16", "remaining_time": "0:16:21", "throughput": 10181.1, "total_tokens": 46590272}
{"current_steps": 48520, "total_steps": 58920, "loss": 0.0, "lr": 1.8391787375804225e-07, "epoch": 4.11744738628649, "percentage": 82.35, "elapsed_time": "1:16:16", "remaining_time": "0:16:20", "throughput": 10181.28, "total_tokens": 46594944}
{"current_steps": 48525, "total_steps": 58920, "loss": 0.0, "lr": 1.837467132780649e-07, "epoch": 4.117871690427698, "percentage": 82.36, "elapsed_time": "1:16:16", "remaining_time": "0:16:20", "throughput": 10181.5, "total_tokens": 46599872}
{"current_steps": 48530, "total_steps": 58920, "loss": 0.0, "lr": 1.8357562442136643e-07, "epoch": 4.118295994568907, "percentage": 82.37, "elapsed_time": "1:16:17", "remaining_time": "0:16:19", "throughput": 10181.72, "total_tokens": 46604800}
{"current_steps": 48535, "total_steps": 58920, "loss": 0.0, "lr": 1.8340460720295915e-07, "epoch": 4.118720298710115, "percentage": 82.37, "elapsed_time": "1:16:17", "remaining_time": "0:16:19", "throughput": 10181.86, "total_tokens": 46609280}
{"current_steps": 48540, "total_steps": 58920, "loss": 0.0, "lr": 1.8323366163784937e-07, "epoch": 4.119144602851324, "percentage": 82.38, "elapsed_time": "1:16:18", "remaining_time": "0:16:18", "throughput": 10182.07, "total_tokens": 46614144}
{"current_steps": 48545, "total_steps": 58920, "loss": 0.0, "lr": 1.8306278774103678e-07, "epoch": 4.119568906992532, "percentage": 82.39, "elapsed_time": "1:16:18", "remaining_time": "0:16:18", "throughput": 10182.23, "total_tokens": 46618752}
{"current_steps": 48550, "total_steps": 58920, "loss": 0.0, "lr": 1.8289198552751507e-07, "epoch": 4.119993211133741, "percentage": 82.4, "elapsed_time": "1:16:18", "remaining_time": "0:16:18", "throughput": 10182.42, "total_tokens": 46623488}
{"current_steps": 48555, "total_steps": 58920, "loss": 0.0, "lr": 1.8272125501227143e-07, "epoch": 4.120417515274949, "percentage": 82.41, "elapsed_time": "1:16:19", "remaining_time": "0:16:17", "throughput": 10182.52, "total_tokens": 46627776}
{"current_steps": 48560, "total_steps": 58920, "loss": 0.0, "lr": 1.825505962102869e-07, "epoch": 4.120841819416158, "percentage": 82.42, "elapsed_time": "1:16:19", "remaining_time": "0:16:17", "throughput": 10182.8, "total_tokens": 46633024}
{"current_steps": 48565, "total_steps": 58920, "loss": 0.0, "lr": 1.8238000913653618e-07, "epoch": 4.1212661235573655, "percentage": 82.43, "elapsed_time": "1:16:19", "remaining_time": "0:16:16", "throughput": 10182.97, "total_tokens": 46637632}
{"current_steps": 48570, "total_steps": 58920, "loss": 0.0, "lr": 1.8220949380598772e-07, "epoch": 4.121690427698574, "percentage": 82.43, "elapsed_time": "1:16:20", "remaining_time": "0:16:16", "throughput": 10183.2, "total_tokens": 46642624}
{"current_steps": 48575, "total_steps": 58920, "loss": 0.0, "lr": 1.8203905023360322e-07, "epoch": 4.122114731839782, "percentage": 82.44, "elapsed_time": "1:16:20", "remaining_time": "0:16:15", "throughput": 10183.4, "total_tokens": 46647360}
{"current_steps": 48580, "total_steps": 58920, "loss": 0.0, "lr": 1.8186867843433927e-07, "epoch": 4.122539035980991, "percentage": 82.45, "elapsed_time": "1:16:21", "remaining_time": "0:16:15", "throughput": 10183.74, "total_tokens": 46652992}
{"current_steps": 48585, "total_steps": 58920, "loss": 0.0, "lr": 1.816983784231446e-07, "epoch": 4.122963340122199, "percentage": 82.46, "elapsed_time": "1:16:21", "remaining_time": "0:16:14", "throughput": 10183.97, "total_tokens": 46658048}
{"current_steps": 48590, "total_steps": 58920, "loss": 0.0, "lr": 1.8152815021496314e-07, "epoch": 4.123387644263408, "percentage": 82.47, "elapsed_time": "1:16:21", "remaining_time": "0:16:14", "throughput": 10184.14, "total_tokens": 46662656}
{"current_steps": 48595, "total_steps": 58920, "loss": 0.0, "lr": 1.8135799382473115e-07, "epoch": 4.123811948404616, "percentage": 82.48, "elapsed_time": "1:16:22", "remaining_time": "0:16:13", "throughput": 10184.35, "total_tokens": 46667520}
{"current_steps": 48600, "total_steps": 58920, "loss": 0.0, "lr": 1.811879092673796e-07, "epoch": 4.124236252545825, "percentage": 82.48, "elapsed_time": "1:16:22", "remaining_time": "0:16:13", "throughput": 10184.59, "total_tokens": 46672576}
{"current_steps": 48605, "total_steps": 58920, "loss": 0.0, "lr": 1.810178965578326e-07, "epoch": 4.124660556687033, "percentage": 82.49, "elapsed_time": "1:16:23", "remaining_time": "0:16:12", "throughput": 10184.75, "total_tokens": 46677120}
{"current_steps": 48610, "total_steps": 58920, "loss": 0.0, "lr": 1.8084795571100809e-07, "epoch": 4.125084860828242, "percentage": 82.5, "elapsed_time": "1:16:23", "remaining_time": "0:16:12", "throughput": 10184.93, "total_tokens": 46681920}
{"current_steps": 48615, "total_steps": 58920, "loss": 0.0, "lr": 1.806780867418184e-07, "epoch": 4.12550916496945, "percentage": 82.51, "elapsed_time": "1:16:23", "remaining_time": "0:16:11", "throughput": 10185.13, "total_tokens": 46686720}
{"current_steps": 48620, "total_steps": 58920, "loss": 0.0, "lr": 1.8050828966516797e-07, "epoch": 4.125933469110659, "percentage": 82.52, "elapsed_time": "1:16:24", "remaining_time": "0:16:11", "throughput": 10185.5, "total_tokens": 46692608}
{"current_steps": 48625, "total_steps": 58920, "loss": 0.0, "lr": 1.8033856449595687e-07, "epoch": 4.126357773251867, "percentage": 82.53, "elapsed_time": "1:16:24", "remaining_time": "0:16:10", "throughput": 10185.7, "total_tokens": 46697408}
{"current_steps": 48630, "total_steps": 58920, "loss": 0.0, "lr": 1.8016891124907684e-07, "epoch": 4.1267820773930755, "percentage": 82.54, "elapsed_time": "1:16:24", "remaining_time": "0:16:10", "throughput": 10185.91, "total_tokens": 46702336}
{"current_steps": 48635, "total_steps": 58920, "loss": 0.0, "lr": 1.7999932993941502e-07, "epoch": 4.127206381534283, "percentage": 82.54, "elapsed_time": "1:16:25", "remaining_time": "0:16:09", "throughput": 10186.07, "total_tokens": 46706944}
{"current_steps": 48640, "total_steps": 58920, "loss": 0.0, "lr": 1.798298205818518e-07, "epoch": 4.127630685675492, "percentage": 82.55, "elapsed_time": "1:16:25", "remaining_time": "0:16:09", "throughput": 10186.35, "total_tokens": 46712192}
{"current_steps": 48645, "total_steps": 58920, "loss": 0.0, "lr": 1.7966038319125998e-07, "epoch": 4.1280549898167, "percentage": 82.56, "elapsed_time": "1:16:26", "remaining_time": "0:16:08", "throughput": 10186.5, "total_tokens": 46716736}
{"current_steps": 48650, "total_steps": 58920, "loss": 0.0, "lr": 1.794910177825083e-07, "epoch": 4.128479293957909, "percentage": 82.57, "elapsed_time": "1:16:26", "remaining_time": "0:16:08", "throughput": 10186.87, "total_tokens": 46722560}
{"current_steps": 48655, "total_steps": 58920, "loss": 0.0, "lr": 1.793217243704568e-07, "epoch": 4.128903598099117, "percentage": 82.58, "elapsed_time": "1:16:26", "remaining_time": "0:16:07", "throughput": 10187.05, "total_tokens": 46727232}
{"current_steps": 48660, "total_steps": 58920, "loss": 0.0, "lr": 1.791525029699612e-07, "epoch": 4.129327902240326, "percentage": 82.59, "elapsed_time": "1:16:27", "remaining_time": "0:16:07", "throughput": 10187.48, "total_tokens": 46733440}
{"current_steps": 48665, "total_steps": 58920, "loss": 0.0, "lr": 1.789833535958699e-07, "epoch": 4.129752206381534, "percentage": 82.6, "elapsed_time": "1:16:27", "remaining_time": "0:16:06", "throughput": 10187.66, "total_tokens": 46738176}
{"current_steps": 48670, "total_steps": 58920, "loss": 0.0, "lr": 1.7881427626302493e-07, "epoch": 4.130176510522743, "percentage": 82.6, "elapsed_time": "1:16:28", "remaining_time": "0:16:06", "throughput": 10187.8, "total_tokens": 46742592}
{"current_steps": 48675, "total_steps": 58920, "loss": 0.0, "lr": 1.7864527098626248e-07, "epoch": 4.130600814663951, "percentage": 82.61, "elapsed_time": "1:16:28", "remaining_time": "0:16:05", "throughput": 10188.0, "total_tokens": 46747392}
{"current_steps": 48680, "total_steps": 58920, "loss": 0.0, "lr": 1.7847633778041182e-07, "epoch": 4.13102511880516, "percentage": 82.62, "elapsed_time": "1:16:28", "remaining_time": "0:16:05", "throughput": 10188.17, "total_tokens": 46752064}
{"current_steps": 48685, "total_steps": 58920, "loss": 0.0, "lr": 1.7830747666029687e-07, "epoch": 4.131449422946368, "percentage": 82.63, "elapsed_time": "1:16:29", "remaining_time": "0:16:04", "throughput": 10188.47, "total_tokens": 46757440}
{"current_steps": 48690, "total_steps": 58920, "loss": 0.0, "lr": 1.7813868764073347e-07, "epoch": 4.1318737270875765, "percentage": 82.64, "elapsed_time": "1:16:29", "remaining_time": "0:16:04", "throughput": 10188.64, "total_tokens": 46762240}
{"current_steps": 48695, "total_steps": 58920, "loss": 0.0, "lr": 1.779699707365333e-07, "epoch": 4.1322980312287845, "percentage": 82.65, "elapsed_time": "1:16:30", "remaining_time": "0:16:03", "throughput": 10188.86, "total_tokens": 46767168}
{"current_steps": 48700, "total_steps": 58920, "loss": 0.0, "lr": 1.778013259625002e-07, "epoch": 4.132722335369993, "percentage": 82.65, "elapsed_time": "1:16:30", "remaining_time": "0:16:03", "throughput": 10189.04, "total_tokens": 46771840}
{"current_steps": 48705, "total_steps": 58920, "loss": 0.0, "lr": 1.776327533334322e-07, "epoch": 4.133146639511201, "percentage": 82.66, "elapsed_time": "1:16:30", "remaining_time": "0:16:02", "throughput": 10189.22, "total_tokens": 46776576}
{"current_steps": 48710, "total_steps": 58920, "loss": 0.0, "lr": 1.7746425286412093e-07, "epoch": 4.13357094365241, "percentage": 82.67, "elapsed_time": "1:16:31", "remaining_time": "0:16:02", "throughput": 10189.49, "total_tokens": 46781824}
{"current_steps": 48715, "total_steps": 58920, "loss": 0.0, "lr": 1.7729582456935178e-07, "epoch": 4.133995247793618, "percentage": 82.68, "elapsed_time": "1:16:31", "remaining_time": "0:16:01", "throughput": 10189.65, "total_tokens": 46786496}
{"current_steps": 48720, "total_steps": 58920, "loss": 0.0, "lr": 1.7712746846390359e-07, "epoch": 4.134419551934827, "percentage": 82.69, "elapsed_time": "1:16:31", "remaining_time": "0:16:01", "throughput": 10189.96, "total_tokens": 46791936}
{"current_steps": 48725, "total_steps": 58920, "loss": 0.0, "lr": 1.769591845625491e-07, "epoch": 4.134843856076035, "percentage": 82.7, "elapsed_time": "1:16:32", "remaining_time": "0:16:00", "throughput": 10190.16, "total_tokens": 46796800}
{"current_steps": 48730, "total_steps": 58920, "loss": 0.0, "lr": 1.7679097288005462e-07, "epoch": 4.135268160217244, "percentage": 82.71, "elapsed_time": "1:16:32", "remaining_time": "0:16:00", "throughput": 10190.29, "total_tokens": 46801216}
{"current_steps": 48735, "total_steps": 58920, "loss": 0.0, "lr": 1.7662283343118012e-07, "epoch": 4.135692464358452, "percentage": 82.71, "elapsed_time": "1:16:33", "remaining_time": "0:15:59", "throughput": 10190.49, "total_tokens": 46806080}
{"current_steps": 48740, "total_steps": 58920, "loss": 0.0, "lr": 1.7645476623067913e-07, "epoch": 4.136116768499661, "percentage": 82.72, "elapsed_time": "1:16:33", "remaining_time": "0:15:59", "throughput": 10190.63, "total_tokens": 46810752}
{"current_steps": 48745, "total_steps": 58920, "loss": 0.0, "lr": 1.7628677129329904e-07, "epoch": 4.136541072640869, "percentage": 82.73, "elapsed_time": "1:16:33", "remaining_time": "0:15:58", "throughput": 10190.91, "total_tokens": 46816064}
{"current_steps": 48750, "total_steps": 58920, "loss": 0.0, "lr": 1.7611884863378067e-07, "epoch": 4.1369653767820775, "percentage": 82.74, "elapsed_time": "1:16:34", "remaining_time": "0:15:58", "throughput": 10191.06, "total_tokens": 46820608}
{"current_steps": 48755, "total_steps": 58920, "loss": 0.0, "lr": 1.7595099826685887e-07, "epoch": 4.1373896809232855, "percentage": 82.75, "elapsed_time": "1:16:34", "remaining_time": "0:15:57", "throughput": 10191.24, "total_tokens": 46825344}
{"current_steps": 48760, "total_steps": 58920, "loss": 0.0, "lr": 1.7578322020726167e-07, "epoch": 4.137813985064494, "percentage": 82.76, "elapsed_time": "1:16:35", "remaining_time": "0:15:57", "throughput": 10191.51, "total_tokens": 46830592}
{"current_steps": 48765, "total_steps": 58920, "loss": 0.0, "lr": 1.7561551446971102e-07, "epoch": 4.138238289205702, "percentage": 82.76, "elapsed_time": "1:16:35", "remaining_time": "0:15:56", "throughput": 10191.77, "total_tokens": 46835712}
{"current_steps": 48770, "total_steps": 58920, "loss": 0.0, "lr": 1.754478810689226e-07, "epoch": 4.138662593346911, "percentage": 82.77, "elapsed_time": "1:16:35", "remaining_time": "0:15:56", "throughput": 10191.86, "total_tokens": 46839936}
{"current_steps": 48775, "total_steps": 58920, "loss": 0.0, "lr": 1.7528032001960568e-07, "epoch": 4.139086897488119, "percentage": 82.78, "elapsed_time": "1:16:36", "remaining_time": "0:15:55", "throughput": 10191.96, "total_tokens": 46844224}
{"current_steps": 48780, "total_steps": 58920, "loss": 0.0, "lr": 1.7511283133646294e-07, "epoch": 4.139511201629328, "percentage": 82.79, "elapsed_time": "1:16:36", "remaining_time": "0:15:55", "throughput": 10192.17, "total_tokens": 46849088}
{"current_steps": 48785, "total_steps": 58920, "loss": 0.0, "lr": 1.7494541503419102e-07, "epoch": 4.139935505770536, "percentage": 82.8, "elapsed_time": "1:16:36", "remaining_time": "0:15:55", "throughput": 10192.38, "total_tokens": 46854208}
{"current_steps": 48790, "total_steps": 58920, "loss": 0.0, "lr": 1.7477807112747978e-07, "epoch": 4.140359809911745, "percentage": 82.81, "elapsed_time": "1:16:37", "remaining_time": "0:15:54", "throughput": 10192.63, "total_tokens": 46859264}
{"current_steps": 48795, "total_steps": 58920, "loss": 0.0, "lr": 1.7461079963101388e-07, "epoch": 4.140784114052953, "percentage": 82.82, "elapsed_time": "1:16:37", "remaining_time": "0:15:54", "throughput": 10192.93, "total_tokens": 46864768}
{"current_steps": 48800, "total_steps": 58920, "loss": 0.0, "lr": 1.7444360055946982e-07, "epoch": 4.141208418194162, "percentage": 82.82, "elapsed_time": "1:16:38", "remaining_time": "0:15:53", "throughput": 10193.13, "total_tokens": 46869632}
{"current_steps": 48805, "total_steps": 58920, "loss": 0.0, "lr": 1.7427647392751965e-07, "epoch": 4.14163272233537, "percentage": 82.83, "elapsed_time": "1:16:38", "remaining_time": "0:15:53", "throughput": 10193.28, "total_tokens": 46874112}
{"current_steps": 48810, "total_steps": 58920, "loss": 0.0, "lr": 1.7410941974982729e-07, "epoch": 4.142057026476579, "percentage": 82.84, "elapsed_time": "1:16:38", "remaining_time": "0:15:52", "throughput": 10193.48, "total_tokens": 46878912}
{"current_steps": 48815, "total_steps": 58920, "loss": 0.0, "lr": 1.7394243804105157e-07, "epoch": 4.142481330617787, "percentage": 82.85, "elapsed_time": "1:16:39", "remaining_time": "0:15:52", "throughput": 10193.68, "total_tokens": 46883776}
{"current_steps": 48820, "total_steps": 58920, "loss": 0.0, "lr": 1.7377552881584434e-07, "epoch": 4.142905634758995, "percentage": 82.86, "elapsed_time": "1:16:39", "remaining_time": "0:15:51", "throughput": 10193.84, "total_tokens": 46888320}
{"current_steps": 48825, "total_steps": 58920, "loss": 0.0, "lr": 1.736086920888512e-07, "epoch": 4.143329938900203, "percentage": 82.87, "elapsed_time": "1:16:40", "remaining_time": "0:15:51", "throughput": 10194.01, "total_tokens": 46892992}
{"current_steps": 48830, "total_steps": 58920, "loss": 0.0, "lr": 1.7344192787471213e-07, "epoch": 4.143754243041412, "percentage": 82.88, "elapsed_time": "1:16:40", "remaining_time": "0:15:50", "throughput": 10194.15, "total_tokens": 46897664}
{"current_steps": 48835, "total_steps": 58920, "loss": 0.0, "lr": 1.7327523618805916e-07, "epoch": 4.14417854718262, "percentage": 82.88, "elapsed_time": "1:16:40", "remaining_time": "0:15:50", "throughput": 10194.35, "total_tokens": 46902464}
{"current_steps": 48840, "total_steps": 58920, "loss": 0.0, "lr": 1.7310861704351987e-07, "epoch": 4.144602851323829, "percentage": 82.89, "elapsed_time": "1:16:41", "remaining_time": "0:15:49", "throughput": 10194.62, "total_tokens": 46907776}
{"current_steps": 48845, "total_steps": 58920, "loss": 0.0, "lr": 1.7294207045571363e-07, "epoch": 4.145027155465037, "percentage": 82.9, "elapsed_time": "1:16:41", "remaining_time": "0:15:49", "throughput": 10194.84, "total_tokens": 46912704}
{"current_steps": 48850, "total_steps": 58920, "loss": 0.0, "lr": 1.7277559643925432e-07, "epoch": 4.145451459606246, "percentage": 82.91, "elapsed_time": "1:16:41", "remaining_time": "0:15:48", "throughput": 10195.01, "total_tokens": 46917376}
{"current_steps": 48855, "total_steps": 58920, "loss": 0.0, "lr": 1.7260919500875038e-07, "epoch": 4.145875763747454, "percentage": 82.92, "elapsed_time": "1:16:42", "remaining_time": "0:15:48", "throughput": 10195.15, "total_tokens": 46921856}
{"current_steps": 48860, "total_steps": 58920, "loss": 0.0, "lr": 1.7244286617880166e-07, "epoch": 4.146300067888663, "percentage": 82.93, "elapsed_time": "1:16:42", "remaining_time": "0:15:47", "throughput": 10195.37, "total_tokens": 46926784}
{"current_steps": 48865, "total_steps": 58920, "loss": 0.0, "lr": 1.7227660996400416e-07, "epoch": 4.146724372029871, "percentage": 82.93, "elapsed_time": "1:16:43", "remaining_time": "0:15:47", "throughput": 10195.54, "total_tokens": 46931456}
{"current_steps": 48870, "total_steps": 58920, "loss": 0.0, "lr": 1.7211042637894513e-07, "epoch": 4.14714867617108, "percentage": 82.94, "elapsed_time": "1:16:43", "remaining_time": "0:15:46", "throughput": 10195.82, "total_tokens": 46936768}
{"current_steps": 48875, "total_steps": 58920, "loss": 0.0, "lr": 1.719443154382073e-07, "epoch": 4.147572980312288, "percentage": 82.95, "elapsed_time": "1:16:43", "remaining_time": "0:15:46", "throughput": 10196.03, "total_tokens": 46941696}
{"current_steps": 48880, "total_steps": 58920, "loss": 0.0, "lr": 1.7177827715636616e-07, "epoch": 4.1479972844534965, "percentage": 82.96, "elapsed_time": "1:16:44", "remaining_time": "0:15:45", "throughput": 10196.23, "total_tokens": 46946560}
{"current_steps": 48885, "total_steps": 58920, "loss": 0.0, "lr": 1.7161231154799093e-07, "epoch": 4.1484215885947044, "percentage": 82.97, "elapsed_time": "1:16:44", "remaining_time": "0:15:45", "throughput": 10196.38, "total_tokens": 46951232}
{"current_steps": 48890, "total_steps": 58920, "loss": 0.0, "lr": 1.7144641862764463e-07, "epoch": 4.148845892735913, "percentage": 82.98, "elapsed_time": "1:16:45", "remaining_time": "0:15:44", "throughput": 10196.66, "total_tokens": 46956544}
{"current_steps": 48895, "total_steps": 58920, "loss": 0.0, "lr": 1.7128059840988317e-07, "epoch": 4.149270196877121, "percentage": 82.99, "elapsed_time": "1:16:45", "remaining_time": "0:15:44", "throughput": 10196.84, "total_tokens": 46961216}
{"current_steps": 48900, "total_steps": 58920, "loss": 0.0, "lr": 1.711148509092577e-07, "epoch": 4.14969450101833, "percentage": 82.99, "elapsed_time": "1:16:45", "remaining_time": "0:15:43", "throughput": 10197.09, "total_tokens": 46966336}
{"current_steps": 48905, "total_steps": 58920, "loss": 0.0, "lr": 1.709491761403108e-07, "epoch": 4.150118805159538, "percentage": 83.0, "elapsed_time": "1:16:46", "remaining_time": "0:15:43", "throughput": 10197.41, "total_tokens": 46971904}
{"current_steps": 48910, "total_steps": 58920, "loss": 0.0, "lr": 1.707835741175807e-07, "epoch": 4.150543109300747, "percentage": 83.01, "elapsed_time": "1:16:46", "remaining_time": "0:15:42", "throughput": 10197.52, "total_tokens": 46976192}
{"current_steps": 48915, "total_steps": 58920, "loss": 0.0, "lr": 1.7061804485559807e-07, "epoch": 4.150967413441955, "percentage": 83.02, "elapsed_time": "1:16:47", "remaining_time": "0:15:42", "throughput": 10197.68, "total_tokens": 46980736}
{"current_steps": 48920, "total_steps": 58920, "loss": 0.0, "lr": 1.7045258836888755e-07, "epoch": 4.151391717583164, "percentage": 83.03, "elapsed_time": "1:16:47", "remaining_time": "0:15:41", "throughput": 10197.88, "total_tokens": 46985600}
{"current_steps": 48925, "total_steps": 58920, "loss": 0.0, "lr": 1.7028720467196732e-07, "epoch": 4.151816021724372, "percentage": 83.04, "elapsed_time": "1:16:47", "remaining_time": "0:15:41", "throughput": 10197.99, "total_tokens": 46989888}
{"current_steps": 48930, "total_steps": 58920, "loss": 0.0, "lr": 1.7012189377934917e-07, "epoch": 4.152240325865581, "percentage": 83.04, "elapsed_time": "1:16:48", "remaining_time": "0:15:40", "throughput": 10198.1, "total_tokens": 46994240}
{"current_steps": 48935, "total_steps": 58920, "loss": 0.0, "lr": 1.6995665570553864e-07, "epoch": 4.152664630006789, "percentage": 83.05, "elapsed_time": "1:16:48", "remaining_time": "0:15:40", "throughput": 10198.31, "total_tokens": 46999104}
{"current_steps": 48940, "total_steps": 58920, "loss": 0.0, "lr": 1.697914904650347e-07, "epoch": 4.1530889341479975, "percentage": 83.06, "elapsed_time": "1:16:48", "remaining_time": "0:15:39", "throughput": 10198.44, "total_tokens": 47003520}
{"current_steps": 48945, "total_steps": 58920, "loss": 0.0, "lr": 1.6962639807233002e-07, "epoch": 4.1535132382892055, "percentage": 83.07, "elapsed_time": "1:16:49", "remaining_time": "0:15:39", "throughput": 10198.64, "total_tokens": 47008320}
{"current_steps": 48950, "total_steps": 58920, "loss": 0.0, "lr": 1.6946137854191077e-07, "epoch": 4.153937542430414, "percentage": 83.08, "elapsed_time": "1:16:49", "remaining_time": "0:15:38", "throughput": 10198.85, "total_tokens": 47013184}
{"current_steps": 48955, "total_steps": 58920, "loss": 0.0, "lr": 1.6929643188825705e-07, "epoch": 4.154361846571622, "percentage": 83.09, "elapsed_time": "1:16:50", "remaining_time": "0:15:38", "throughput": 10199.01, "total_tokens": 47017792}
{"current_steps": 48960, "total_steps": 58920, "loss": 0.0, "lr": 1.6913155812584212e-07, "epoch": 4.154786150712831, "percentage": 83.1, "elapsed_time": "1:16:50", "remaining_time": "0:15:37", "throughput": 10199.32, "total_tokens": 47023296}
{"current_steps": 48965, "total_steps": 58920, "loss": 0.0, "lr": 1.6896675726913312e-07, "epoch": 4.155210454854039, "percentage": 83.1, "elapsed_time": "1:16:50", "remaining_time": "0:15:37", "throughput": 10199.5, "total_tokens": 47027968}
{"current_steps": 48970, "total_steps": 58920, "loss": 0.0, "lr": 1.688020293325908e-07, "epoch": 4.155634758995248, "percentage": 83.11, "elapsed_time": "1:16:51", "remaining_time": "0:15:36", "throughput": 10199.72, "total_tokens": 47032896}
{"current_steps": 48975, "total_steps": 58920, "loss": 0.0, "lr": 1.6863737433066926e-07, "epoch": 4.156059063136456, "percentage": 83.12, "elapsed_time": "1:16:51", "remaining_time": "0:15:36", "throughput": 10199.83, "total_tokens": 47037248}
{"current_steps": 48980, "total_steps": 58920, "loss": 0.0, "lr": 1.6847279227781663e-07, "epoch": 4.156483367277665, "percentage": 83.13, "elapsed_time": "1:16:51", "remaining_time": "0:15:35", "throughput": 10199.97, "total_tokens": 47041728}
{"current_steps": 48985, "total_steps": 58920, "loss": 0.0, "lr": 1.6830828318847412e-07, "epoch": 4.156907671418873, "percentage": 83.14, "elapsed_time": "1:16:52", "remaining_time": "0:15:35", "throughput": 10200.23, "total_tokens": 47046912}
{"current_steps": 48990, "total_steps": 58920, "loss": 0.0, "lr": 1.6814384707707706e-07, "epoch": 4.157331975560082, "percentage": 83.15, "elapsed_time": "1:16:52", "remaining_time": "0:15:34", "throughput": 10200.47, "total_tokens": 47051968}
{"current_steps": 48995, "total_steps": 58920, "loss": 0.0, "lr": 1.6797948395805396e-07, "epoch": 4.15775627970129, "percentage": 83.16, "elapsed_time": "1:16:53", "remaining_time": "0:15:34", "throughput": 10200.69, "total_tokens": 47057088}
{"current_steps": 49000, "total_steps": 58920, "loss": 0.0, "lr": 1.678151938458272e-07, "epoch": 4.158180583842499, "percentage": 83.16, "elapsed_time": "1:16:53", "remaining_time": "0:15:33", "throughput": 10200.84, "total_tokens": 47061632}
{"current_steps": 49005, "total_steps": 58920, "loss": 0.0, "lr": 1.6765097675481233e-07, "epoch": 4.1586048879837065, "percentage": 83.17, "elapsed_time": "1:16:53", "remaining_time": "0:15:33", "throughput": 10201.11, "total_tokens": 47066880}
{"current_steps": 49010, "total_steps": 58920, "loss": 0.0, "lr": 1.6748683269941943e-07, "epoch": 4.159029192124915, "percentage": 83.18, "elapsed_time": "1:16:54", "remaining_time": "0:15:33", "throughput": 10201.3, "total_tokens": 47071680}
{"current_steps": 49015, "total_steps": 58920, "loss": 0.0, "lr": 1.6732276169405112e-07, "epoch": 4.159453496266123, "percentage": 83.19, "elapsed_time": "1:16:54", "remaining_time": "0:15:32", "throughput": 10201.44, "total_tokens": 47076160}
{"current_steps": 49020, "total_steps": 58920, "loss": 0.0, "lr": 1.6715876375310402e-07, "epoch": 4.159877800407332, "percentage": 83.2, "elapsed_time": "1:16:55", "remaining_time": "0:15:32", "throughput": 10201.59, "total_tokens": 47080704}
{"current_steps": 49025, "total_steps": 58920, "loss": 0.0, "lr": 1.6699483889096843e-07, "epoch": 4.16030210454854, "percentage": 83.21, "elapsed_time": "1:16:55", "remaining_time": "0:15:31", "throughput": 10201.78, "total_tokens": 47085440}
{"current_steps": 49030, "total_steps": 58920, "loss": 0.0, "lr": 1.6683098712202814e-07, "epoch": 4.160726408689749, "percentage": 83.21, "elapsed_time": "1:16:55", "remaining_time": "0:15:31", "throughput": 10201.99, "total_tokens": 47090368}
{"current_steps": 49035, "total_steps": 58920, "loss": 0.0, "lr": 1.6666720846066062e-07, "epoch": 4.161150712830957, "percentage": 83.22, "elapsed_time": "1:16:56", "remaining_time": "0:15:30", "throughput": 10202.23, "total_tokens": 47095360}
{"current_steps": 49040, "total_steps": 58920, "loss": 0.0, "lr": 1.665035029212366e-07, "epoch": 4.161575016972166, "percentage": 83.23, "elapsed_time": "1:16:56", "remaining_time": "0:15:30", "throughput": 10202.38, "total_tokens": 47099840}
{"current_steps": 49045, "total_steps": 58920, "loss": 0.0, "lr": 1.6633987051812137e-07, "epoch": 4.161999321113374, "percentage": 83.24, "elapsed_time": "1:16:56", "remaining_time": "0:15:29", "throughput": 10202.52, "total_tokens": 47104320}
{"current_steps": 49050, "total_steps": 58920, "loss": 0.0, "lr": 1.661763112656721e-07, "epoch": 4.162423625254583, "percentage": 83.25, "elapsed_time": "1:16:57", "remaining_time": "0:15:29", "throughput": 10202.78, "total_tokens": 47109504}
{"current_steps": 49055, "total_steps": 58920, "loss": 0.0, "lr": 1.6601282517824145e-07, "epoch": 4.162847929395791, "percentage": 83.26, "elapsed_time": "1:16:57", "remaining_time": "0:15:28", "throughput": 10202.98, "total_tokens": 47114368}
{"current_steps": 49060, "total_steps": 58920, "loss": 0.0, "lr": 1.6584941227017403e-07, "epoch": 4.163272233537, "percentage": 83.27, "elapsed_time": "1:16:58", "remaining_time": "0:15:28", "throughput": 10203.38, "total_tokens": 47120448}
{"current_steps": 49065, "total_steps": 58920, "loss": 0.0, "lr": 1.656860725558088e-07, "epoch": 4.163696537678208, "percentage": 83.27, "elapsed_time": "1:16:58", "remaining_time": "0:15:27", "throughput": 10203.62, "total_tokens": 47125568}
{"current_steps": 49070, "total_steps": 58920, "loss": 0.0, "lr": 1.6552280604947888e-07, "epoch": 4.164120841819416, "percentage": 83.28, "elapsed_time": "1:16:58", "remaining_time": "0:15:27", "throughput": 10203.95, "total_tokens": 47131200}
{"current_steps": 49075, "total_steps": 58920, "loss": 0.0, "lr": 1.6535961276550948e-07, "epoch": 4.164545145960624, "percentage": 83.29, "elapsed_time": "1:16:59", "remaining_time": "0:15:26", "throughput": 10204.13, "total_tokens": 47135936}
{"current_steps": 49080, "total_steps": 58920, "loss": 0.0, "lr": 1.65196492718221e-07, "epoch": 4.164969450101833, "percentage": 83.3, "elapsed_time": "1:16:59", "remaining_time": "0:15:26", "throughput": 10204.3, "total_tokens": 47140608}
{"current_steps": 49085, "total_steps": 58920, "loss": 0.0, "lr": 1.650334459219257e-07, "epoch": 4.165393754243041, "percentage": 83.31, "elapsed_time": "1:17:00", "remaining_time": "0:15:25", "throughput": 10204.54, "total_tokens": 47145664}
{"current_steps": 49090, "total_steps": 58920, "loss": 0.0, "lr": 1.648704723909312e-07, "epoch": 4.16581805838425, "percentage": 83.32, "elapsed_time": "1:17:00", "remaining_time": "0:15:25", "throughput": 10204.65, "total_tokens": 47150016}
{"current_steps": 49095, "total_steps": 58920, "loss": 0.0, "lr": 1.6470757213953778e-07, "epoch": 4.166242362525458, "percentage": 83.32, "elapsed_time": "1:17:00", "remaining_time": "0:15:24", "throughput": 10204.88, "total_tokens": 47155008}
{"current_steps": 49100, "total_steps": 58920, "loss": 0.0, "lr": 1.6454474518203855e-07, "epoch": 4.166666666666667, "percentage": 83.33, "elapsed_time": "1:17:01", "remaining_time": "0:15:24", "throughput": 10205.07, "total_tokens": 47160064}
{"current_steps": 49105, "total_steps": 58920, "loss": 0.0, "lr": 1.6438199153272204e-07, "epoch": 4.167090970807875, "percentage": 83.34, "elapsed_time": "1:17:01", "remaining_time": "0:15:23", "throughput": 10205.26, "total_tokens": 47164800}
{"current_steps": 49110, "total_steps": 58920, "loss": 0.0, "lr": 1.642193112058683e-07, "epoch": 4.167515274949084, "percentage": 83.35, "elapsed_time": "1:17:01", "remaining_time": "0:15:23", "throughput": 10205.39, "total_tokens": 47169216}
{"current_steps": 49115, "total_steps": 58920, "loss": 0.0, "lr": 1.640567042157529e-07, "epoch": 4.167939579090292, "percentage": 83.36, "elapsed_time": "1:17:02", "remaining_time": "0:15:22", "throughput": 10205.59, "total_tokens": 47174080}
{"current_steps": 49120, "total_steps": 58920, "loss": 0.0, "lr": 1.6389417057664312e-07, "epoch": 4.168363883231501, "percentage": 83.37, "elapsed_time": "1:17:02", "remaining_time": "0:15:22", "throughput": 10205.82, "total_tokens": 47179072}
{"current_steps": 49125, "total_steps": 58920, "loss": 0.0, "lr": 1.6373171030280132e-07, "epoch": 4.168788187372709, "percentage": 83.38, "elapsed_time": "1:17:03", "remaining_time": "0:15:21", "throughput": 10206.17, "total_tokens": 47184832}
{"current_steps": 49130, "total_steps": 58920, "loss": 0.0, "lr": 1.6356932340848263e-07, "epoch": 4.1692124915139175, "percentage": 83.38, "elapsed_time": "1:17:03", "remaining_time": "0:15:21", "throughput": 10206.35, "total_tokens": 47189568}
{"current_steps": 49135, "total_steps": 58920, "loss": 0.0, "lr": 1.6340700990793587e-07, "epoch": 4.1696367956551255, "percentage": 83.39, "elapsed_time": "1:17:03", "remaining_time": "0:15:20", "throughput": 10206.59, "total_tokens": 47194624}
{"current_steps": 49140, "total_steps": 58920, "loss": 0.0, "lr": 1.632447698154037e-07, "epoch": 4.170061099796334, "percentage": 83.4, "elapsed_time": "1:17:04", "remaining_time": "0:15:20", "throughput": 10206.8, "total_tokens": 47199552}
{"current_steps": 49145, "total_steps": 58920, "loss": 0.0, "lr": 1.6308260314512146e-07, "epoch": 4.170485403937542, "percentage": 83.41, "elapsed_time": "1:17:04", "remaining_time": "0:15:19", "throughput": 10206.95, "total_tokens": 47204096}
{"current_steps": 49150, "total_steps": 58920, "loss": 0.0, "lr": 1.6292050991131923e-07, "epoch": 4.170909708078751, "percentage": 83.42, "elapsed_time": "1:17:05", "remaining_time": "0:15:19", "throughput": 10207.11, "total_tokens": 47208704}
{"current_steps": 49155, "total_steps": 58920, "loss": 0.0, "lr": 1.6275849012822018e-07, "epoch": 4.171334012219959, "percentage": 83.43, "elapsed_time": "1:17:05", "remaining_time": "0:15:18", "throughput": 10207.44, "total_tokens": 47214336}
{"current_steps": 49160, "total_steps": 58920, "loss": 0.0, "lr": 1.6259654381004063e-07, "epoch": 4.171758316361168, "percentage": 83.44, "elapsed_time": "1:17:05", "remaining_time": "0:15:18", "throughput": 10207.63, "total_tokens": 47219136}
{"current_steps": 49165, "total_steps": 58920, "loss": 0.0, "lr": 1.6243467097099096e-07, "epoch": 4.172182620502376, "percentage": 83.44, "elapsed_time": "1:17:06", "remaining_time": "0:15:17", "throughput": 10207.89, "total_tokens": 47224384}
{"current_steps": 49170, "total_steps": 58920, "loss": 0.0, "lr": 1.6227287162527493e-07, "epoch": 4.172606924643585, "percentage": 83.45, "elapsed_time": "1:17:06", "remaining_time": "0:15:17", "throughput": 10208.03, "total_tokens": 47228864}
{"current_steps": 49175, "total_steps": 58920, "loss": 0.0, "lr": 1.6211114578708984e-07, "epoch": 4.173031228784793, "percentage": 83.46, "elapsed_time": "1:17:07", "remaining_time": "0:15:16", "throughput": 10208.18, "total_tokens": 47233408}
{"current_steps": 49180, "total_steps": 58920, "loss": 0.0, "lr": 1.6194949347062647e-07, "epoch": 4.173455532926002, "percentage": 83.47, "elapsed_time": "1:17:07", "remaining_time": "0:15:16", "throughput": 10208.36, "total_tokens": 47238144}
{"current_steps": 49185, "total_steps": 58920, "loss": 0.0, "lr": 1.6178791469006924e-07, "epoch": 4.17387983706721, "percentage": 83.48, "elapsed_time": "1:17:07", "remaining_time": "0:15:15", "throughput": 10208.54, "total_tokens": 47242880}
{"current_steps": 49190, "total_steps": 58920, "loss": 0.0, "lr": 1.6162640945959616e-07, "epoch": 4.1743041412084185, "percentage": 83.49, "elapsed_time": "1:17:08", "remaining_time": "0:15:15", "throughput": 10208.73, "total_tokens": 47247680}
{"current_steps": 49195, "total_steps": 58920, "loss": 0.0, "lr": 1.6146497779337875e-07, "epoch": 4.1747284453496265, "percentage": 83.49, "elapsed_time": "1:17:08", "remaining_time": "0:15:14", "throughput": 10208.81, "total_tokens": 47251840}
{"current_steps": 49200, "total_steps": 58920, "loss": 0.0, "lr": 1.6130361970558204e-07, "epoch": 4.175152749490835, "percentage": 83.5, "elapsed_time": "1:17:08", "remaining_time": "0:15:14", "throughput": 10209.05, "total_tokens": 47256896}
{"current_steps": 49205, "total_steps": 58920, "loss": 0.0, "lr": 1.6114233521036458e-07, "epoch": 4.175577053632043, "percentage": 83.51, "elapsed_time": "1:17:09", "remaining_time": "0:15:14", "throughput": 10209.3, "total_tokens": 47262080}
{"current_steps": 49210, "total_steps": 58920, "loss": 0.0, "lr": 1.6098112432187848e-07, "epoch": 4.176001357773252, "percentage": 83.52, "elapsed_time": "1:17:09", "remaining_time": "0:15:13", "throughput": 10209.57, "total_tokens": 47267392}
{"current_steps": 49215, "total_steps": 58920, "loss": 0.0, "lr": 1.6081998705426957e-07, "epoch": 4.17642566191446, "percentage": 83.53, "elapsed_time": "1:17:10", "remaining_time": "0:15:13", "throughput": 10209.71, "total_tokens": 47271872}
{"current_steps": 49220, "total_steps": 58920, "loss": 0.0, "lr": 1.6065892342167687e-07, "epoch": 4.176849966055669, "percentage": 83.54, "elapsed_time": "1:17:10", "remaining_time": "0:15:12", "throughput": 10209.86, "total_tokens": 47276416}
{"current_steps": 49225, "total_steps": 58920, "loss": 0.0, "lr": 1.6049793343823315e-07, "epoch": 4.177274270196877, "percentage": 83.55, "elapsed_time": "1:17:10", "remaining_time": "0:15:12", "throughput": 10210.03, "total_tokens": 47281088}
{"current_steps": 49230, "total_steps": 58920, "loss": 0.0, "lr": 1.603370171180648e-07, "epoch": 4.177698574338086, "percentage": 83.55, "elapsed_time": "1:17:11", "remaining_time": "0:15:11", "throughput": 10210.17, "total_tokens": 47285568}
{"current_steps": 49235, "total_steps": 58920, "loss": 0.0, "lr": 1.6017617447529164e-07, "epoch": 4.178122878479294, "percentage": 83.56, "elapsed_time": "1:17:11", "remaining_time": "0:15:11", "throughput": 10210.29, "total_tokens": 47289984}
{"current_steps": 49240, "total_steps": 58920, "loss": 0.0, "lr": 1.6001540552402702e-07, "epoch": 4.178547182620503, "percentage": 83.57, "elapsed_time": "1:17:11", "remaining_time": "0:15:10", "throughput": 10210.55, "total_tokens": 47295168}
{"current_steps": 49245, "total_steps": 58920, "loss": 0.0, "lr": 1.598547102783777e-07, "epoch": 4.178971486761711, "percentage": 83.58, "elapsed_time": "1:17:12", "remaining_time": "0:15:10", "throughput": 10210.81, "total_tokens": 47300416}
{"current_steps": 49250, "total_steps": 58920, "loss": 0.0, "lr": 1.5969408875244438e-07, "epoch": 4.17939579090292, "percentage": 83.59, "elapsed_time": "1:17:12", "remaining_time": "0:15:09", "throughput": 10211.03, "total_tokens": 47305408}
{"current_steps": 49255, "total_steps": 58920, "loss": 0.0, "lr": 1.5953354096032046e-07, "epoch": 4.1798200950441275, "percentage": 83.6, "elapsed_time": "1:17:13", "remaining_time": "0:15:09", "throughput": 10211.23, "total_tokens": 47310208}
{"current_steps": 49260, "total_steps": 58920, "loss": 0.0, "lr": 1.593730669160944e-07, "epoch": 4.180244399185336, "percentage": 83.6, "elapsed_time": "1:17:13", "remaining_time": "0:15:08", "throughput": 10211.45, "total_tokens": 47315200}
{"current_steps": 49265, "total_steps": 58920, "loss": 0.0, "lr": 1.5921266663384647e-07, "epoch": 4.180668703326544, "percentage": 83.61, "elapsed_time": "1:17:13", "remaining_time": "0:15:08", "throughput": 10211.64, "total_tokens": 47320000}
{"current_steps": 49270, "total_steps": 58920, "loss": 0.0, "lr": 1.5905234012765123e-07, "epoch": 4.181093007467753, "percentage": 83.62, "elapsed_time": "1:17:14", "remaining_time": "0:15:07", "throughput": 10211.85, "total_tokens": 47324864}
{"current_steps": 49275, "total_steps": 58920, "loss": 0.0, "lr": 1.58892087411577e-07, "epoch": 4.181517311608961, "percentage": 83.63, "elapsed_time": "1:17:14", "remaining_time": "0:15:07", "throughput": 10211.97, "total_tokens": 47329216}
{"current_steps": 49280, "total_steps": 58920, "loss": 0.0, "lr": 1.587319084996851e-07, "epoch": 4.18194161575017, "percentage": 83.64, "elapsed_time": "1:17:15", "remaining_time": "0:15:06", "throughput": 10212.13, "total_tokens": 47333824}
{"current_steps": 49285, "total_steps": 58920, "loss": 0.0, "lr": 1.5857180340603128e-07, "epoch": 4.182365919891378, "percentage": 83.65, "elapsed_time": "1:17:15", "remaining_time": "0:15:06", "throughput": 10212.26, "total_tokens": 47338304}
{"current_steps": 49290, "total_steps": 58920, "loss": 0.0, "lr": 1.5841177214466327e-07, "epoch": 4.182790224032587, "percentage": 83.66, "elapsed_time": "1:17:15", "remaining_time": "0:15:05", "throughput": 10212.39, "total_tokens": 47342720}
{"current_steps": 49295, "total_steps": 58920, "loss": 0.0, "lr": 1.5825181472962412e-07, "epoch": 4.183214528173795, "percentage": 83.66, "elapsed_time": "1:17:16", "remaining_time": "0:15:05", "throughput": 10212.55, "total_tokens": 47347264}
{"current_steps": 49300, "total_steps": 58920, "loss": 0.0, "lr": 1.5809193117494867e-07, "epoch": 4.183638832315004, "percentage": 83.67, "elapsed_time": "1:17:16", "remaining_time": "0:15:04", "throughput": 10212.69, "total_tokens": 47351808}
{"current_steps": 49305, "total_steps": 58920, "loss": 0.0, "lr": 1.5793212149466716e-07, "epoch": 4.184063136456212, "percentage": 83.68, "elapsed_time": "1:17:16", "remaining_time": "0:15:04", "throughput": 10212.79, "total_tokens": 47356032}
{"current_steps": 49310, "total_steps": 58920, "loss": 0.0, "lr": 1.5777238570280138e-07, "epoch": 4.184487440597421, "percentage": 83.69, "elapsed_time": "1:17:17", "remaining_time": "0:15:03", "throughput": 10212.96, "total_tokens": 47360704}
{"current_steps": 49315, "total_steps": 58920, "loss": 0.0, "lr": 1.5761272381336765e-07, "epoch": 4.184911744738629, "percentage": 83.7, "elapsed_time": "1:17:17", "remaining_time": "0:15:03", "throughput": 10213.15, "total_tokens": 47365440}
{"current_steps": 49320, "total_steps": 58920, "loss": 0.0, "lr": 1.5745313584037645e-07, "epoch": 4.1853360488798375, "percentage": 83.71, "elapsed_time": "1:17:18", "remaining_time": "0:15:02", "throughput": 10213.32, "total_tokens": 47370112}
{"current_steps": 49325, "total_steps": 58920, "loss": 0.0, "lr": 1.5729362179783013e-07, "epoch": 4.185760353021045, "percentage": 83.72, "elapsed_time": "1:17:18", "remaining_time": "0:15:02", "throughput": 10213.47, "total_tokens": 47374656}
{"current_steps": 49330, "total_steps": 58920, "loss": 0.0, "lr": 1.5713418169972635e-07, "epoch": 4.186184657162254, "percentage": 83.72, "elapsed_time": "1:17:18", "remaining_time": "0:15:01", "throughput": 10213.73, "total_tokens": 47379904}
{"current_steps": 49335, "total_steps": 58920, "loss": 0.0, "lr": 1.5697481556005454e-07, "epoch": 4.186608961303462, "percentage": 83.73, "elapsed_time": "1:17:19", "remaining_time": "0:15:01", "throughput": 10214.11, "total_tokens": 47385920}
{"current_steps": 49340, "total_steps": 58920, "loss": 0.0, "lr": 1.5681552339279912e-07, "epoch": 4.187033265444671, "percentage": 83.74, "elapsed_time": "1:17:19", "remaining_time": "0:15:00", "throughput": 10214.24, "total_tokens": 47390336}
{"current_steps": 49345, "total_steps": 58920, "loss": 0.0, "lr": 1.566563052119375e-07, "epoch": 4.187457569585879, "percentage": 83.75, "elapsed_time": "1:17:20", "remaining_time": "0:15:00", "throughput": 10214.38, "total_tokens": 47394816}
{"current_steps": 49350, "total_steps": 58920, "loss": 0.0, "lr": 1.5649716103143972e-07, "epoch": 4.187881873727088, "percentage": 83.76, "elapsed_time": "1:17:20", "remaining_time": "0:14:59", "throughput": 10214.51, "total_tokens": 47399232}
{"current_steps": 49355, "total_steps": 58920, "loss": 0.0, "lr": 1.5633809086527117e-07, "epoch": 4.188306177868296, "percentage": 83.77, "elapsed_time": "1:17:20", "remaining_time": "0:14:59", "throughput": 10214.72, "total_tokens": 47404160}
{"current_steps": 49360, "total_steps": 58920, "loss": 0.0, "lr": 1.5617909472738855e-07, "epoch": 4.188730482009505, "percentage": 83.77, "elapsed_time": "1:17:21", "remaining_time": "0:14:58", "throughput": 10214.84, "total_tokens": 47408576}
{"current_steps": 49365, "total_steps": 58920, "loss": 0.0, "lr": 1.5602017263174394e-07, "epoch": 4.189154786150713, "percentage": 83.78, "elapsed_time": "1:17:21", "remaining_time": "0:14:58", "throughput": 10214.93, "total_tokens": 47412800}
{"current_steps": 49370, "total_steps": 58920, "loss": 0.0, "lr": 1.5586132459228218e-07, "epoch": 4.189579090291922, "percentage": 83.79, "elapsed_time": "1:17:21", "remaining_time": "0:14:57", "throughput": 10215.05, "total_tokens": 47417152}
{"current_steps": 49375, "total_steps": 58920, "loss": 0.0, "lr": 1.5570255062294123e-07, "epoch": 4.19000339443313, "percentage": 83.8, "elapsed_time": "1:17:22", "remaining_time": "0:14:57", "throughput": 10215.2, "total_tokens": 47421696}
{"current_steps": 49380, "total_steps": 58920, "loss": 0.0, "lr": 1.555438507376533e-07, "epoch": 4.1904276985743385, "percentage": 83.81, "elapsed_time": "1:17:22", "remaining_time": "0:14:56", "throughput": 10215.44, "total_tokens": 47426816}
{"current_steps": 49385, "total_steps": 58920, "loss": 0.0, "lr": 1.5538522495034357e-07, "epoch": 4.1908520027155465, "percentage": 83.82, "elapsed_time": "1:17:23", "remaining_time": "0:14:56", "throughput": 10215.57, "total_tokens": 47431232}
{"current_steps": 49390, "total_steps": 58920, "loss": 0.0, "lr": 1.55226673274931e-07, "epoch": 4.191276306856755, "percentage": 83.83, "elapsed_time": "1:17:23", "remaining_time": "0:14:55", "throughput": 10215.69, "total_tokens": 47435648}
{"current_steps": 49395, "total_steps": 58920, "loss": 0.0, "lr": 1.5506819572532748e-07, "epoch": 4.191700610997963, "percentage": 83.83, "elapsed_time": "1:17:23", "remaining_time": "0:14:55", "throughput": 10215.95, "total_tokens": 47440832}
{"current_steps": 49400, "total_steps": 58920, "loss": 0.0, "lr": 1.5490979231543932e-07, "epoch": 4.192124915139172, "percentage": 83.84, "elapsed_time": "1:17:24", "remaining_time": "0:14:54", "throughput": 10216.15, "total_tokens": 47445696}
{"current_steps": 49405, "total_steps": 58920, "loss": 0.0, "lr": 1.5475146305916564e-07, "epoch": 4.19254921928038, "percentage": 83.85, "elapsed_time": "1:17:24", "remaining_time": "0:14:54", "throughput": 10216.25, "total_tokens": 47449984}
{"current_steps": 49410, "total_steps": 58920, "loss": 0.0, "lr": 1.5459320797039943e-07, "epoch": 4.192973523421589, "percentage": 83.86, "elapsed_time": "1:17:24", "remaining_time": "0:14:54", "throughput": 10216.38, "total_tokens": 47454400}
{"current_steps": 49415, "total_steps": 58920, "loss": 0.0, "lr": 1.544350270630268e-07, "epoch": 4.193397827562797, "percentage": 83.87, "elapsed_time": "1:17:25", "remaining_time": "0:14:53", "throughput": 10216.59, "total_tokens": 47459328}
{"current_steps": 49420, "total_steps": 58920, "loss": 0.0, "lr": 1.5427692035092776e-07, "epoch": 4.193822131704005, "percentage": 83.88, "elapsed_time": "1:17:25", "remaining_time": "0:14:53", "throughput": 10216.72, "total_tokens": 47463744}
{"current_steps": 49425, "total_steps": 58920, "loss": 0.0, "lr": 1.5411888784797545e-07, "epoch": 4.194246435845214, "percentage": 83.88, "elapsed_time": "1:17:26", "remaining_time": "0:14:52", "throughput": 10216.93, "total_tokens": 47468608}
{"current_steps": 49430, "total_steps": 58920, "loss": 0.0, "lr": 1.5396092956803664e-07, "epoch": 4.194670739986423, "percentage": 83.89, "elapsed_time": "1:17:26", "remaining_time": "0:14:52", "throughput": 10217.18, "total_tokens": 47473728}
{"current_steps": 49435, "total_steps": 58920, "loss": 0.0, "lr": 1.538030455249716e-07, "epoch": 4.195095044127631, "percentage": 83.9, "elapsed_time": "1:17:26", "remaining_time": "0:14:51", "throughput": 10217.31, "total_tokens": 47478144}
{"current_steps": 49440, "total_steps": 58920, "loss": 0.0, "lr": 1.5364523573263422e-07, "epoch": 4.195519348268839, "percentage": 83.91, "elapsed_time": "1:17:27", "remaining_time": "0:14:51", "throughput": 10217.6, "total_tokens": 47483584}
{"current_steps": 49445, "total_steps": 58920, "loss": 0.0, "lr": 1.5348750020487166e-07, "epoch": 4.1959436524100475, "percentage": 83.92, "elapsed_time": "1:17:27", "remaining_time": "0:14:50", "throughput": 10217.69, "total_tokens": 47487808}
{"current_steps": 49450, "total_steps": 58920, "loss": 0.0, "lr": 1.5332983895552464e-07, "epoch": 4.196367956551256, "percentage": 83.93, "elapsed_time": "1:17:27", "remaining_time": "0:14:50", "throughput": 10217.85, "total_tokens": 47492480}
{"current_steps": 49455, "total_steps": 58920, "loss": 0.0, "lr": 1.531722519984273e-07, "epoch": 4.196792260692464, "percentage": 83.94, "elapsed_time": "1:17:28", "remaining_time": "0:14:49", "throughput": 10217.98, "total_tokens": 47496896}
{"current_steps": 49460, "total_steps": 58920, "loss": 0.0, "lr": 1.530147393474074e-07, "epoch": 4.197216564833672, "percentage": 83.94, "elapsed_time": "1:17:28", "remaining_time": "0:14:49", "throughput": 10218.18, "total_tokens": 47501824}
{"current_steps": 49465, "total_steps": 58920, "loss": 0.0, "lr": 1.5285730101628612e-07, "epoch": 4.197640868974881, "percentage": 83.95, "elapsed_time": "1:17:29", "remaining_time": "0:14:48", "throughput": 10218.36, "total_tokens": 47506624}
{"current_steps": 49470, "total_steps": 58920, "loss": 0.0, "lr": 1.5269993701887806e-07, "epoch": 4.19806517311609, "percentage": 83.96, "elapsed_time": "1:17:29", "remaining_time": "0:14:48", "throughput": 10218.63, "total_tokens": 47511872}
{"current_steps": 49475, "total_steps": 58920, "loss": 0.0, "lr": 1.5254264736899136e-07, "epoch": 4.198489477257298, "percentage": 83.97, "elapsed_time": "1:17:29", "remaining_time": "0:14:47", "throughput": 10218.9, "total_tokens": 47517184}
{"current_steps": 49480, "total_steps": 58920, "loss": 0.0, "lr": 1.5238543208042763e-07, "epoch": 4.198913781398506, "percentage": 83.98, "elapsed_time": "1:17:30", "remaining_time": "0:14:47", "throughput": 10219.06, "total_tokens": 47521792}
{"current_steps": 49485, "total_steps": 58920, "loss": 0.0, "lr": 1.5222829116698199e-07, "epoch": 4.199338085539715, "percentage": 83.99, "elapsed_time": "1:17:30", "remaining_time": "0:14:46", "throughput": 10219.17, "total_tokens": 47526144}
{"current_steps": 49490, "total_steps": 58920, "loss": 0.0, "lr": 1.5207122464244294e-07, "epoch": 4.199762389680923, "percentage": 84.0, "elapsed_time": "1:17:31", "remaining_time": "0:14:46", "throughput": 10219.36, "total_tokens": 47530880}
{"current_steps": 49495, "total_steps": 58920, "loss": 0.0, "lr": 1.519142325205921e-07, "epoch": 4.200186693822132, "percentage": 84.0, "elapsed_time": "1:17:31", "remaining_time": "0:14:45", "throughput": 10219.48, "total_tokens": 47535296}
{"current_steps": 49500, "total_steps": 58920, "loss": 0.0, "lr": 1.5175731481520592e-07, "epoch": 4.20061099796334, "percentage": 84.01, "elapsed_time": "1:17:31", "remaining_time": "0:14:45", "throughput": 10219.67, "total_tokens": 47540096}
{"current_steps": 49505, "total_steps": 58920, "loss": 0.0, "lr": 1.516004715400524e-07, "epoch": 4.201035302104549, "percentage": 84.02, "elapsed_time": "1:17:32", "remaining_time": "0:14:44", "throughput": 10219.77, "total_tokens": 47544384}
{"current_steps": 49510, "total_steps": 58920, "loss": 0.0, "lr": 1.5144370270889473e-07, "epoch": 4.2014596062457565, "percentage": 84.03, "elapsed_time": "1:17:32", "remaining_time": "0:14:44", "throughput": 10219.98, "total_tokens": 47549312}
{"current_steps": 49515, "total_steps": 58920, "loss": 0.0, "lr": 1.5128700833548823e-07, "epoch": 4.201883910386965, "percentage": 84.04, "elapsed_time": "1:17:32", "remaining_time": "0:14:43", "throughput": 10220.17, "total_tokens": 47554112}
{"current_steps": 49520, "total_steps": 58920, "loss": 0.0, "lr": 1.511303884335825e-07, "epoch": 4.202308214528173, "percentage": 84.05, "elapsed_time": "1:17:33", "remaining_time": "0:14:43", "throughput": 10220.38, "total_tokens": 47559040}
{"current_steps": 49525, "total_steps": 58920, "loss": 0.0, "lr": 1.509738430169204e-07, "epoch": 4.202732518669382, "percentage": 84.05, "elapsed_time": "1:17:33", "remaining_time": "0:14:42", "throughput": 10220.57, "total_tokens": 47563840}
{"current_steps": 49530, "total_steps": 58920, "loss": 0.0, "lr": 1.5081737209923795e-07, "epoch": 4.20315682281059, "percentage": 84.06, "elapsed_time": "1:17:34", "remaining_time": "0:14:42", "throughput": 10220.77, "total_tokens": 47568704}
{"current_steps": 49535, "total_steps": 58920, "loss": 0.0, "lr": 1.506609756942655e-07, "epoch": 4.203581126951799, "percentage": 84.07, "elapsed_time": "1:17:34", "remaining_time": "0:14:41", "throughput": 10221.02, "total_tokens": 47573888}
{"current_steps": 49540, "total_steps": 58920, "loss": 0.0, "lr": 1.5050465381572552e-07, "epoch": 4.204005431093007, "percentage": 84.08, "elapsed_time": "1:17:34", "remaining_time": "0:14:41", "throughput": 10221.17, "total_tokens": 47578432}
{"current_steps": 49545, "total_steps": 58920, "loss": 0.0, "lr": 1.503484064773355e-07, "epoch": 4.204429735234216, "percentage": 84.09, "elapsed_time": "1:17:35", "remaining_time": "0:14:40", "throughput": 10221.34, "total_tokens": 47583104}
{"current_steps": 49550, "total_steps": 58920, "loss": 0.0, "lr": 1.5019223369280476e-07, "epoch": 4.204854039375424, "percentage": 84.1, "elapsed_time": "1:17:35", "remaining_time": "0:14:40", "throughput": 10221.56, "total_tokens": 47588096}
{"current_steps": 49555, "total_steps": 58920, "loss": 0.0, "lr": 1.5003613547583748e-07, "epoch": 4.205278343516633, "percentage": 84.11, "elapsed_time": "1:17:36", "remaining_time": "0:14:39", "throughput": 10221.74, "total_tokens": 47592832}
{"current_steps": 49560, "total_steps": 58920, "loss": 0.0, "lr": 1.498801118401307e-07, "epoch": 4.205702647657841, "percentage": 84.11, "elapsed_time": "1:17:36", "remaining_time": "0:14:39", "throughput": 10221.97, "total_tokens": 47597888}
{"current_steps": 49565, "total_steps": 58920, "loss": 0.0, "lr": 1.4972416279937438e-07, "epoch": 4.20612695179905, "percentage": 84.12, "elapsed_time": "1:17:36", "remaining_time": "0:14:38", "throughput": 10222.19, "total_tokens": 47602816}
{"current_steps": 49570, "total_steps": 58920, "loss": 0.0, "lr": 1.4956828836725333e-07, "epoch": 4.206551255940258, "percentage": 84.13, "elapsed_time": "1:17:37", "remaining_time": "0:14:38", "throughput": 10222.41, "total_tokens": 47607872}
{"current_steps": 49575, "total_steps": 58920, "loss": 0.0, "lr": 1.4941248855744404e-07, "epoch": 4.2069755600814664, "percentage": 84.14, "elapsed_time": "1:17:37", "remaining_time": "0:14:37", "throughput": 10222.63, "total_tokens": 47612800}
{"current_steps": 49580, "total_steps": 58920, "loss": 0.0, "lr": 1.4925676338361803e-07, "epoch": 4.207399864222674, "percentage": 84.15, "elapsed_time": "1:17:37", "remaining_time": "0:14:37", "throughput": 10222.82, "total_tokens": 47617536}
{"current_steps": 49585, "total_steps": 58920, "loss": 0.0, "lr": 1.4910111285943948e-07, "epoch": 4.207824168363883, "percentage": 84.16, "elapsed_time": "1:17:38", "remaining_time": "0:14:36", "throughput": 10223.06, "total_tokens": 47622592}
{"current_steps": 49590, "total_steps": 58920, "loss": 0.0, "lr": 1.4894553699856606e-07, "epoch": 4.208248472505091, "percentage": 84.16, "elapsed_time": "1:17:38", "remaining_time": "0:14:36", "throughput": 10223.26, "total_tokens": 47627520}
{"current_steps": 49595, "total_steps": 58920, "loss": 0.0, "lr": 1.487900358146491e-07, "epoch": 4.2086727766463, "percentage": 84.17, "elapsed_time": "1:17:39", "remaining_time": "0:14:36", "throughput": 10223.39, "total_tokens": 47631936}
{"current_steps": 49600, "total_steps": 58920, "loss": 0.0, "lr": 1.4863460932133322e-07, "epoch": 4.209097080787508, "percentage": 84.18, "elapsed_time": "1:17:39", "remaining_time": "0:14:35", "throughput": 10223.54, "total_tokens": 47636480}
{"current_steps": 49605, "total_steps": 58920, "loss": 0.0, "lr": 1.4847925753225676e-07, "epoch": 4.209521384928717, "percentage": 84.19, "elapsed_time": "1:17:39", "remaining_time": "0:14:35", "throughput": 10223.65, "total_tokens": 47640768}
{"current_steps": 49610, "total_steps": 58920, "loss": 0.0, "lr": 1.4832398046105055e-07, "epoch": 4.209945689069925, "percentage": 84.2, "elapsed_time": "1:17:40", "remaining_time": "0:14:34", "throughput": 10223.77, "total_tokens": 47645248}
{"current_steps": 49615, "total_steps": 58920, "loss": 0.0, "lr": 1.4816877812134033e-07, "epoch": 4.210369993211134, "percentage": 84.21, "elapsed_time": "1:17:40", "remaining_time": "0:14:34", "throughput": 10223.96, "total_tokens": 47650048}
{"current_steps": 49620, "total_steps": 58920, "loss": 0.0, "lr": 1.480136505267443e-07, "epoch": 4.210794297352342, "percentage": 84.22, "elapsed_time": "1:17:40", "remaining_time": "0:14:33", "throughput": 10224.08, "total_tokens": 47654400}
{"current_steps": 49625, "total_steps": 58920, "loss": 0.0, "lr": 1.478585976908744e-07, "epoch": 4.211218601493551, "percentage": 84.22, "elapsed_time": "1:17:41", "remaining_time": "0:14:33", "throughput": 10224.21, "total_tokens": 47658880}
{"current_steps": 49630, "total_steps": 58920, "loss": 0.0, "lr": 1.477036196273359e-07, "epoch": 4.211642905634759, "percentage": 84.23, "elapsed_time": "1:17:41", "remaining_time": "0:14:32", "throughput": 10224.34, "total_tokens": 47663296}
{"current_steps": 49635, "total_steps": 58920, "loss": 0.0, "lr": 1.4754871634972754e-07, "epoch": 4.2120672097759675, "percentage": 84.24, "elapsed_time": "1:17:42", "remaining_time": "0:14:32", "throughput": 10224.64, "total_tokens": 47668800}
{"current_steps": 49640, "total_steps": 58920, "loss": 0.0, "lr": 1.4739388787164152e-07, "epoch": 4.2124915139171755, "percentage": 84.25, "elapsed_time": "1:17:42", "remaining_time": "0:14:31", "throughput": 10224.82, "total_tokens": 47673536}
{"current_steps": 49645, "total_steps": 58920, "loss": 0.0, "lr": 1.4723913420666357e-07, "epoch": 4.212915818058384, "percentage": 84.26, "elapsed_time": "1:17:42", "remaining_time": "0:14:31", "throughput": 10224.98, "total_tokens": 47678144}
{"current_steps": 49650, "total_steps": 58920, "loss": 0.0, "lr": 1.4708445536837267e-07, "epoch": 4.213340122199592, "percentage": 84.27, "elapsed_time": "1:17:43", "remaining_time": "0:14:30", "throughput": 10225.07, "total_tokens": 47682368}
{"current_steps": 49655, "total_steps": 58920, "loss": 0.0, "lr": 1.469298513703414e-07, "epoch": 4.213764426340801, "percentage": 84.28, "elapsed_time": "1:17:43", "remaining_time": "0:14:30", "throughput": 10225.34, "total_tokens": 47687680}
{"current_steps": 49660, "total_steps": 58920, "loss": 0.0, "lr": 1.4677532222613577e-07, "epoch": 4.214188730482009, "percentage": 84.28, "elapsed_time": "1:17:44", "remaining_time": "0:14:29", "throughput": 10225.45, "total_tokens": 47692032}
{"current_steps": 49665, "total_steps": 58920, "loss": 0.0, "lr": 1.4662086794931495e-07, "epoch": 4.214613034623218, "percentage": 84.29, "elapsed_time": "1:17:44", "remaining_time": "0:14:29", "throughput": 10225.72, "total_tokens": 47697344}
{"current_steps": 49670, "total_steps": 58920, "loss": 0.0, "lr": 1.464664885534319e-07, "epoch": 4.215037338764426, "percentage": 84.3, "elapsed_time": "1:17:44", "remaining_time": "0:14:28", "throughput": 10225.88, "total_tokens": 47702016}
{"current_steps": 49675, "total_steps": 58920, "loss": 0.0, "lr": 1.463121840520327e-07, "epoch": 4.215461642905635, "percentage": 84.31, "elapsed_time": "1:17:45", "remaining_time": "0:14:28", "throughput": 10226.19, "total_tokens": 47707648}
{"current_steps": 49680, "total_steps": 58920, "loss": 0.0, "lr": 1.461579544586573e-07, "epoch": 4.215885947046843, "percentage": 84.32, "elapsed_time": "1:17:45", "remaining_time": "0:14:27", "throughput": 10226.32, "total_tokens": 47712064}
{"current_steps": 49685, "total_steps": 58920, "loss": 0.0, "lr": 1.4600379978683852e-07, "epoch": 4.216310251188052, "percentage": 84.33, "elapsed_time": "1:17:46", "remaining_time": "0:14:27", "throughput": 10226.59, "total_tokens": 47717376}
{"current_steps": 49690, "total_steps": 58920, "loss": 0.0, "lr": 1.45849720050103e-07, "epoch": 4.21673455532926, "percentage": 84.33, "elapsed_time": "1:17:46", "remaining_time": "0:14:26", "throughput": 10226.89, "total_tokens": 47722816}
{"current_steps": 49695, "total_steps": 58920, "loss": 0.0, "lr": 1.4569571526197054e-07, "epoch": 4.2171588594704685, "percentage": 84.34, "elapsed_time": "1:17:46", "remaining_time": "0:14:26", "throughput": 10227.05, "total_tokens": 47727488}
{"current_steps": 49700, "total_steps": 58920, "loss": 0.0, "lr": 1.4554178543595474e-07, "epoch": 4.2175831636116765, "percentage": 84.35, "elapsed_time": "1:17:47", "remaining_time": "0:14:25", "throughput": 10227.14, "total_tokens": 47731712}
{"current_steps": 49705, "total_steps": 58920, "loss": 0.0, "lr": 1.453879305855622e-07, "epoch": 4.218007467752885, "percentage": 84.36, "elapsed_time": "1:17:47", "remaining_time": "0:14:25", "throughput": 10227.29, "total_tokens": 47736320}
{"current_steps": 49710, "total_steps": 58920, "loss": 0.0, "lr": 1.452341507242929e-07, "epoch": 4.218431771894093, "percentage": 84.37, "elapsed_time": "1:17:47", "remaining_time": "0:14:24", "throughput": 10227.58, "total_tokens": 47741696}
{"current_steps": 49715, "total_steps": 58920, "loss": 0.0, "lr": 1.4508044586564128e-07, "epoch": 4.218856076035302, "percentage": 84.38, "elapsed_time": "1:17:48", "remaining_time": "0:14:24", "throughput": 10227.78, "total_tokens": 47746624}
{"current_steps": 49720, "total_steps": 58920, "loss": 0.0, "lr": 1.4492681602309343e-07, "epoch": 4.21928038017651, "percentage": 84.39, "elapsed_time": "1:17:48", "remaining_time": "0:14:23", "throughput": 10227.87, "total_tokens": 47750912}
{"current_steps": 49725, "total_steps": 58920, "loss": 0.0, "lr": 1.4477326121013068e-07, "epoch": 4.219704684317719, "percentage": 84.39, "elapsed_time": "1:17:49", "remaining_time": "0:14:23", "throughput": 10228.07, "total_tokens": 47755840}
{"current_steps": 49730, "total_steps": 58920, "loss": 0.0, "lr": 1.4461978144022624e-07, "epoch": 4.220128988458927, "percentage": 84.4, "elapsed_time": "1:17:49", "remaining_time": "0:14:22", "throughput": 10228.25, "total_tokens": 47760576}
{"current_steps": 49735, "total_steps": 58920, "loss": 0.0, "lr": 1.4446637672684758e-07, "epoch": 4.220553292600136, "percentage": 84.41, "elapsed_time": "1:17:49", "remaining_time": "0:14:22", "throughput": 10228.47, "total_tokens": 47765632}
{"current_steps": 49740, "total_steps": 58920, "loss": 0.0, "lr": 1.443130470834556e-07, "epoch": 4.220977596741344, "percentage": 84.42, "elapsed_time": "1:17:50", "remaining_time": "0:14:21", "throughput": 10228.63, "total_tokens": 47770240}
{"current_steps": 49745, "total_steps": 58920, "loss": 0.0, "lr": 1.4415979252350398e-07, "epoch": 4.221401900882553, "percentage": 84.43, "elapsed_time": "1:17:50", "remaining_time": "0:14:21", "throughput": 10228.85, "total_tokens": 47775232}
{"current_steps": 49750, "total_steps": 58920, "loss": 0.0, "lr": 1.4400661306044104e-07, "epoch": 4.221826205023761, "percentage": 84.44, "elapsed_time": "1:17:51", "remaining_time": "0:14:20", "throughput": 10229.0, "total_tokens": 47779776}
{"current_steps": 49755, "total_steps": 58920, "loss": 0.0, "lr": 1.4385350870770675e-07, "epoch": 4.22225050916497, "percentage": 84.45, "elapsed_time": "1:17:51", "remaining_time": "0:14:20", "throughput": 10229.15, "total_tokens": 47784384}
{"current_steps": 49760, "total_steps": 58920, "loss": 0.0, "lr": 1.4370047947873652e-07, "epoch": 4.2226748133061776, "percentage": 84.45, "elapsed_time": "1:17:51", "remaining_time": "0:14:19", "throughput": 10229.3, "total_tokens": 47788928}
{"current_steps": 49765, "total_steps": 58920, "loss": 0.0, "lr": 1.4354752538695724e-07, "epoch": 4.223099117447386, "percentage": 84.46, "elapsed_time": "1:17:52", "remaining_time": "0:14:19", "throughput": 10229.45, "total_tokens": 47793664}
{"current_steps": 49770, "total_steps": 58920, "loss": 0.0, "lr": 1.4339464644579024e-07, "epoch": 4.223523421588594, "percentage": 84.47, "elapsed_time": "1:17:52", "remaining_time": "0:14:19", "throughput": 10229.66, "total_tokens": 47798592}
{"current_steps": 49775, "total_steps": 58920, "loss": 0.0, "lr": 1.4324184266865068e-07, "epoch": 4.223947725729803, "percentage": 84.48, "elapsed_time": "1:17:52", "remaining_time": "0:14:18", "throughput": 10229.77, "total_tokens": 47802880}
{"current_steps": 49780, "total_steps": 58920, "loss": 0.0, "lr": 1.4308911406894563e-07, "epoch": 4.224372029871011, "percentage": 84.49, "elapsed_time": "1:17:53", "remaining_time": "0:14:18", "throughput": 10229.94, "total_tokens": 47807552}
{"current_steps": 49785, "total_steps": 58920, "loss": 0.0, "lr": 1.4293646066007748e-07, "epoch": 4.22479633401222, "percentage": 84.5, "elapsed_time": "1:17:53", "remaining_time": "0:14:17", "throughput": 10230.07, "total_tokens": 47811968}
{"current_steps": 49790, "total_steps": 58920, "loss": 0.0, "lr": 1.4278388245543994e-07, "epoch": 4.225220638153428, "percentage": 84.5, "elapsed_time": "1:17:54", "remaining_time": "0:14:17", "throughput": 10230.22, "total_tokens": 47816512}
{"current_steps": 49795, "total_steps": 58920, "loss": 0.0, "lr": 1.4263137946842208e-07, "epoch": 4.225644942294637, "percentage": 84.51, "elapsed_time": "1:17:54", "remaining_time": "0:14:16", "throughput": 10230.4, "total_tokens": 47821312}
{"current_steps": 49800, "total_steps": 58920, "loss": 0.0, "lr": 1.424789517124051e-07, "epoch": 4.226069246435845, "percentage": 84.52, "elapsed_time": "1:17:54", "remaining_time": "0:14:16", "throughput": 10230.58, "total_tokens": 47826048}
{"current_steps": 49805, "total_steps": 58920, "loss": 0.0, "lr": 1.4232659920076396e-07, "epoch": 4.226493550577054, "percentage": 84.53, "elapsed_time": "1:17:55", "remaining_time": "0:14:15", "throughput": 10230.76, "total_tokens": 47830784}
{"current_steps": 49810, "total_steps": 58920, "loss": 0.0, "lr": 1.421743219468674e-07, "epoch": 4.226917854718262, "percentage": 84.54, "elapsed_time": "1:17:55", "remaining_time": "0:14:15", "throughput": 10230.89, "total_tokens": 47835264}
{"current_steps": 49815, "total_steps": 58920, "loss": 0.0, "lr": 1.4202211996407652e-07, "epoch": 4.227342158859471, "percentage": 84.55, "elapsed_time": "1:17:55", "remaining_time": "0:14:14", "throughput": 10231.02, "total_tokens": 47839872}
{"current_steps": 49820, "total_steps": 58920, "loss": 0.0, "lr": 1.4186999326574734e-07, "epoch": 4.227766463000679, "percentage": 84.56, "elapsed_time": "1:17:56", "remaining_time": "0:14:14", "throughput": 10231.12, "total_tokens": 47844160}
{"current_steps": 49825, "total_steps": 58920, "loss": 0.0001, "lr": 1.4171794186522756e-07, "epoch": 4.2281907671418875, "percentage": 84.56, "elapsed_time": "1:17:56", "remaining_time": "0:14:13", "throughput": 10231.4, "total_tokens": 47849472}
{"current_steps": 49830, "total_steps": 58920, "loss": 0.0, "lr": 1.4156596577585978e-07, "epoch": 4.228615071283095, "percentage": 84.57, "elapsed_time": "1:17:57", "remaining_time": "0:14:13", "throughput": 10231.64, "total_tokens": 47854592}
{"current_steps": 49835, "total_steps": 58920, "loss": 0.0, "lr": 1.4141406501097908e-07, "epoch": 4.229039375424304, "percentage": 84.58, "elapsed_time": "1:17:57", "remaining_time": "0:14:12", "throughput": 10231.89, "total_tokens": 47859776}
{"current_steps": 49840, "total_steps": 58920, "loss": 0.0, "lr": 1.4126223958391426e-07, "epoch": 4.229463679565512, "percentage": 84.59, "elapsed_time": "1:17:57", "remaining_time": "0:14:12", "throughput": 10232.08, "total_tokens": 47864576}
{"current_steps": 49845, "total_steps": 58920, "loss": 0.0, "lr": 1.4111048950798755e-07, "epoch": 4.229887983706721, "percentage": 84.6, "elapsed_time": "1:17:58", "remaining_time": "0:14:11", "throughput": 10232.38, "total_tokens": 47870080}
{"current_steps": 49850, "total_steps": 58920, "loss": 0.0, "lr": 1.4095881479651429e-07, "epoch": 4.230312287847929, "percentage": 84.61, "elapsed_time": "1:17:58", "remaining_time": "0:14:11", "throughput": 10232.58, "total_tokens": 47875008}
{"current_steps": 49855, "total_steps": 58920, "loss": 0.0, "lr": 1.408072154628035e-07, "epoch": 4.230736591989138, "percentage": 84.61, "elapsed_time": "1:17:59", "remaining_time": "0:14:10", "throughput": 10232.82, "total_tokens": 47880128}
{"current_steps": 49860, "total_steps": 58920, "loss": 0.0, "lr": 1.4065569152015743e-07, "epoch": 4.231160896130346, "percentage": 84.62, "elapsed_time": "1:17:59", "remaining_time": "0:14:10", "throughput": 10233.01, "total_tokens": 47884928}
{"current_steps": 49865, "total_steps": 58920, "loss": 0.0, "lr": 1.405042429818718e-07, "epoch": 4.231585200271555, "percentage": 84.63, "elapsed_time": "1:17:59", "remaining_time": "0:14:09", "throughput": 10233.16, "total_tokens": 47889536}
{"current_steps": 49870, "total_steps": 58920, "loss": 0.0, "lr": 1.403528698612356e-07, "epoch": 4.232009504412763, "percentage": 84.64, "elapsed_time": "1:18:00", "remaining_time": "0:14:09", "throughput": 10233.3, "total_tokens": 47894016}
{"current_steps": 49875, "total_steps": 58920, "loss": 0.0, "lr": 1.4020157217153138e-07, "epoch": 4.232433808553972, "percentage": 84.65, "elapsed_time": "1:18:00", "remaining_time": "0:14:08", "throughput": 10233.58, "total_tokens": 47899392}
{"current_steps": 49880, "total_steps": 58920, "loss": 0.0, "lr": 1.4005034992603492e-07, "epoch": 4.23285811269518, "percentage": 84.66, "elapsed_time": "1:18:00", "remaining_time": "0:14:08", "throughput": 10233.75, "total_tokens": 47904064}
{"current_steps": 49885, "total_steps": 58920, "loss": 0.0, "lr": 1.3989920313801552e-07, "epoch": 4.2332824168363885, "percentage": 84.67, "elapsed_time": "1:18:01", "remaining_time": "0:14:07", "throughput": 10234.0, "total_tokens": 47909248}
{"current_steps": 49890, "total_steps": 58920, "loss": 0.0, "lr": 1.3974813182073553e-07, "epoch": 4.2337067209775965, "percentage": 84.67, "elapsed_time": "1:18:01", "remaining_time": "0:14:07", "throughput": 10234.15, "total_tokens": 47913728}
{"current_steps": 49895, "total_steps": 58920, "loss": 0.0, "lr": 1.3959713598745104e-07, "epoch": 4.234131025118805, "percentage": 84.68, "elapsed_time": "1:18:02", "remaining_time": "0:14:06", "throughput": 10234.32, "total_tokens": 47918400}
{"current_steps": 49900, "total_steps": 58920, "loss": 0.0, "lr": 1.3944621565141146e-07, "epoch": 4.234555329260013, "percentage": 84.69, "elapsed_time": "1:18:02", "remaining_time": "0:14:06", "throughput": 10234.48, "total_tokens": 47923072}
{"current_steps": 49905, "total_steps": 58920, "loss": 0.0, "lr": 1.392953708258594e-07, "epoch": 4.234979633401222, "percentage": 84.7, "elapsed_time": "1:18:02", "remaining_time": "0:14:05", "throughput": 10234.74, "total_tokens": 47928320}
{"current_steps": 49910, "total_steps": 58920, "loss": 0.0, "lr": 1.3914460152403096e-07, "epoch": 4.23540393754243, "percentage": 84.71, "elapsed_time": "1:18:03", "remaining_time": "0:14:05", "throughput": 10234.93, "total_tokens": 47933120}
{"current_steps": 49915, "total_steps": 58920, "loss": 0.0, "lr": 1.3899390775915565e-07, "epoch": 4.235828241683639, "percentage": 84.72, "elapsed_time": "1:18:03", "remaining_time": "0:14:04", "throughput": 10235.25, "total_tokens": 47938816}
{"current_steps": 49920, "total_steps": 58920, "loss": 0.0, "lr": 1.3884328954445635e-07, "epoch": 4.236252545824847, "percentage": 84.73, "elapsed_time": "1:18:04", "remaining_time": "0:14:04", "throughput": 10235.42, "total_tokens": 47943488}
{"current_steps": 49925, "total_steps": 58920, "loss": 0.0, "lr": 1.386927468931489e-07, "epoch": 4.236676849966056, "percentage": 84.73, "elapsed_time": "1:18:04", "remaining_time": "0:14:04", "throughput": 10235.73, "total_tokens": 47949056}
{"current_steps": 49930, "total_steps": 58920, "loss": 0.0, "lr": 1.3854227981844358e-07, "epoch": 4.237101154107264, "percentage": 84.74, "elapsed_time": "1:18:04", "remaining_time": "0:14:03", "throughput": 10236.08, "total_tokens": 47954880}
{"current_steps": 49935, "total_steps": 58920, "loss": 0.0, "lr": 1.3839188833354276e-07, "epoch": 4.237525458248473, "percentage": 84.75, "elapsed_time": "1:18:05", "remaining_time": "0:14:03", "throughput": 10236.25, "total_tokens": 47959552}
{"current_steps": 49940, "total_steps": 58920, "loss": 0.0, "lr": 1.3824157245164293e-07, "epoch": 4.237949762389681, "percentage": 84.76, "elapsed_time": "1:18:05", "remaining_time": "0:14:02", "throughput": 10236.48, "total_tokens": 47964736}
{"current_steps": 49945, "total_steps": 58920, "loss": 0.0, "lr": 1.380913321859337e-07, "epoch": 4.2383740665308896, "percentage": 84.77, "elapsed_time": "1:18:06", "remaining_time": "0:14:02", "throughput": 10236.68, "total_tokens": 47969600}
{"current_steps": 49950, "total_steps": 58920, "loss": 0.0, "lr": 1.3794116754959828e-07, "epoch": 4.2387983706720975, "percentage": 84.78, "elapsed_time": "1:18:06", "remaining_time": "0:14:01", "throughput": 10236.86, "total_tokens": 47974336}
{"current_steps": 49955, "total_steps": 58920, "loss": 0.0, "lr": 1.3779107855581284e-07, "epoch": 4.239222674813306, "percentage": 84.78, "elapsed_time": "1:18:06", "remaining_time": "0:14:01", "throughput": 10236.96, "total_tokens": 47978624}
{"current_steps": 49960, "total_steps": 58920, "loss": 0.0, "lr": 1.376410652177471e-07, "epoch": 4.239646978954514, "percentage": 84.79, "elapsed_time": "1:18:07", "remaining_time": "0:14:00", "throughput": 10237.08, "total_tokens": 47983040}
{"current_steps": 49965, "total_steps": 58920, "loss": 0.0, "lr": 1.3749112754856472e-07, "epoch": 4.240071283095723, "percentage": 84.8, "elapsed_time": "1:18:07", "remaining_time": "0:14:00", "throughput": 10237.31, "total_tokens": 47988160}
{"current_steps": 49970, "total_steps": 58920, "loss": 0.0, "lr": 1.3734126556142145e-07, "epoch": 4.240495587236931, "percentage": 84.81, "elapsed_time": "1:18:07", "remaining_time": "0:13:59", "throughput": 10237.45, "total_tokens": 47992640}
{"current_steps": 49975, "total_steps": 58920, "loss": 0.0, "lr": 1.3719147926946796e-07, "epoch": 4.24091989137814, "percentage": 84.82, "elapsed_time": "1:18:08", "remaining_time": "0:13:59", "throughput": 10237.55, "total_tokens": 47996928}
{"current_steps": 49980, "total_steps": 58920, "loss": 0.0, "lr": 1.370417686858467e-07, "epoch": 4.241344195519348, "percentage": 84.83, "elapsed_time": "1:18:08", "remaining_time": "0:13:58", "throughput": 10237.77, "total_tokens": 48001984}
{"current_steps": 49985, "total_steps": 58920, "loss": 0.0, "lr": 1.3689213382369447e-07, "epoch": 4.241768499660557, "percentage": 84.84, "elapsed_time": "1:18:09", "remaining_time": "0:13:58", "throughput": 10237.85, "total_tokens": 48006208}
{"current_steps": 49990, "total_steps": 58920, "loss": 0.0, "lr": 1.3674257469614158e-07, "epoch": 4.242192803801765, "percentage": 84.84, "elapsed_time": "1:18:09", "remaining_time": "0:13:57", "throughput": 10238.07, "total_tokens": 48011136}
{"current_steps": 49995, "total_steps": 58920, "loss": 0.0, "lr": 1.3659309131631058e-07, "epoch": 4.242617107942974, "percentage": 84.85, "elapsed_time": "1:18:09", "remaining_time": "0:13:57", "throughput": 10238.19, "total_tokens": 48015552}
{"current_steps": 50000, "total_steps": 58920, "loss": 0.0, "lr": 1.3644368369731896e-07, "epoch": 4.243041412084182, "percentage": 84.86, "elapsed_time": "1:18:10", "remaining_time": "0:13:56", "throughput": 10238.4, "total_tokens": 48020480}
{"current_steps": 50005, "total_steps": 58920, "loss": 0.0, "lr": 1.3629435185227568e-07, "epoch": 4.243465716225391, "percentage": 84.87, "elapsed_time": "1:18:10", "remaining_time": "0:13:56", "throughput": 10238.53, "total_tokens": 48024960}
{"current_steps": 50010, "total_steps": 58920, "loss": 0.0, "lr": 1.36145095794285e-07, "epoch": 4.243890020366599, "percentage": 84.88, "elapsed_time": "1:18:11", "remaining_time": "0:13:55", "throughput": 10238.77, "total_tokens": 48030144}
{"current_steps": 50015, "total_steps": 58920, "loss": 0.0, "lr": 1.359959155364433e-07, "epoch": 4.244314324507807, "percentage": 84.89, "elapsed_time": "1:18:11", "remaining_time": "0:13:55", "throughput": 10238.93, "total_tokens": 48034816}
{"current_steps": 50020, "total_steps": 58920, "loss": 0.0, "lr": 1.3584681109184025e-07, "epoch": 4.244738628649015, "percentage": 84.89, "elapsed_time": "1:18:11", "remaining_time": "0:13:54", "throughput": 10239.11, "total_tokens": 48039552}
{"current_steps": 50025, "total_steps": 58920, "loss": 0.0, "lr": 1.356977824735599e-07, "epoch": 4.245162932790224, "percentage": 84.9, "elapsed_time": "1:18:12", "remaining_time": "0:13:54", "throughput": 10239.31, "total_tokens": 48044416}
{"current_steps": 50030, "total_steps": 58920, "loss": 0.0, "lr": 1.3554882969467806e-07, "epoch": 4.245587236931432, "percentage": 84.91, "elapsed_time": "1:18:12", "remaining_time": "0:13:53", "throughput": 10239.49, "total_tokens": 48049152}
{"current_steps": 50035, "total_steps": 58920, "loss": 0.0, "lr": 1.353999527682659e-07, "epoch": 4.246011541072641, "percentage": 84.92, "elapsed_time": "1:18:12", "remaining_time": "0:13:53", "throughput": 10239.56, "total_tokens": 48053248}
{"current_steps": 50040, "total_steps": 58920, "loss": 0.0, "lr": 1.3525115170738576e-07, "epoch": 4.246435845213849, "percentage": 84.93, "elapsed_time": "1:18:13", "remaining_time": "0:13:52", "throughput": 10239.74, "total_tokens": 48057984}
{"current_steps": 50045, "total_steps": 58920, "loss": 0.0, "lr": 1.3510242652509507e-07, "epoch": 4.246860149355058, "percentage": 84.94, "elapsed_time": "1:18:13", "remaining_time": "0:13:52", "throughput": 10239.87, "total_tokens": 48062656}
{"current_steps": 50050, "total_steps": 58920, "loss": 0.0, "lr": 1.3495377723444378e-07, "epoch": 4.247284453496266, "percentage": 84.95, "elapsed_time": "1:18:14", "remaining_time": "0:13:51", "throughput": 10240.12, "total_tokens": 48067840}
{"current_steps": 50055, "total_steps": 58920, "loss": 0.0, "lr": 1.3480520384847538e-07, "epoch": 4.247708757637475, "percentage": 84.95, "elapsed_time": "1:18:14", "remaining_time": "0:13:51", "throughput": 10240.38, "total_tokens": 48073152}
{"current_steps": 50060, "total_steps": 58920, "loss": 0.0, "lr": 1.3465670638022664e-07, "epoch": 4.248133061778683, "percentage": 84.96, "elapsed_time": "1:18:14", "remaining_time": "0:13:50", "throughput": 10240.5, "total_tokens": 48077568}
{"current_steps": 50065, "total_steps": 58920, "loss": 0.0, "lr": 1.3450828484272724e-07, "epoch": 4.248557365919892, "percentage": 84.97, "elapsed_time": "1:18:15", "remaining_time": "0:13:50", "throughput": 10240.72, "total_tokens": 48082560}
{"current_steps": 50070, "total_steps": 58920, "loss": 0.0, "lr": 1.3435993924900125e-07, "epoch": 4.2489816700611, "percentage": 84.98, "elapsed_time": "1:18:15", "remaining_time": "0:13:49", "throughput": 10240.95, "total_tokens": 48087616}
{"current_steps": 50075, "total_steps": 58920, "loss": 0.0, "lr": 1.3421166961206521e-07, "epoch": 4.2494059742023085, "percentage": 84.99, "elapsed_time": "1:18:15", "remaining_time": "0:13:49", "throughput": 10241.07, "total_tokens": 48092032}
{"current_steps": 50080, "total_steps": 58920, "loss": 0.0, "lr": 1.3406347594492918e-07, "epoch": 4.2498302783435165, "percentage": 85.0, "elapsed_time": "1:18:16", "remaining_time": "0:13:48", "throughput": 10241.32, "total_tokens": 48097216}
{"current_steps": 50082, "total_steps": 58920, "eval_loss": 0.1777358204126358, "epoch": 4.25, "percentage": 85.0, "elapsed_time": "1:18:32", "remaining_time": "0:13:51", "throughput": 10205.7, "total_tokens": 48098944}
{"current_steps": 50085, "total_steps": 58920, "loss": 0.0, "lr": 1.3391535826059675e-07, "epoch": 4.250254582484725, "percentage": 85.01, "elapsed_time": "1:19:14", "remaining_time": "0:13:58", "throughput": 10116.27, "total_tokens": 48101696}
{"current_steps": 50090, "total_steps": 58920, "loss": 0.0, "lr": 1.3376731657206463e-07, "epoch": 4.250678886625933, "percentage": 85.01, "elapsed_time": "1:19:15", "remaining_time": "0:13:58", "throughput": 10116.48, "total_tokens": 48106560}
{"current_steps": 50095, "total_steps": 58920, "loss": 0.0, "lr": 1.336193508923229e-07, "epoch": 4.251103190767142, "percentage": 85.02, "elapsed_time": "1:19:15", "remaining_time": "0:13:57", "throughput": 10116.68, "total_tokens": 48111424}
{"current_steps": 50100, "total_steps": 58920, "loss": 0.0, "lr": 1.3347146123435517e-07, "epoch": 4.25152749490835, "percentage": 85.03, "elapsed_time": "1:19:16", "remaining_time": "0:13:57", "throughput": 10116.8, "total_tokens": 48115776}
{"current_steps": 50105, "total_steps": 58920, "loss": 0.0, "lr": 1.3332364761113814e-07, "epoch": 4.251951799049559, "percentage": 85.04, "elapsed_time": "1:19:16", "remaining_time": "0:13:56", "throughput": 10117.02, "total_tokens": 48120704}
{"current_steps": 50110, "total_steps": 58920, "loss": 0.0, "lr": 1.3317591003564176e-07, "epoch": 4.252376103190767, "percentage": 85.05, "elapsed_time": "1:19:16", "remaining_time": "0:13:56", "throughput": 10117.17, "total_tokens": 48125248}
{"current_steps": 50115, "total_steps": 58920, "loss": 0.0, "lr": 1.3302824852082972e-07, "epoch": 4.252800407331976, "percentage": 85.06, "elapsed_time": "1:19:17", "remaining_time": "0:13:55", "throughput": 10117.29, "total_tokens": 48129600}
{"current_steps": 50120, "total_steps": 58920, "loss": 0.0, "lr": 1.3288066307965872e-07, "epoch": 4.253224711473184, "percentage": 85.06, "elapsed_time": "1:19:17", "remaining_time": "0:13:55", "throughput": 10117.38, "total_tokens": 48133760}
{"current_steps": 50125, "total_steps": 58920, "loss": 0.0, "lr": 1.3273315372507876e-07, "epoch": 4.253649015614393, "percentage": 85.07, "elapsed_time": "1:19:17", "remaining_time": "0:13:54", "throughput": 10117.53, "total_tokens": 48138432}
{"current_steps": 50130, "total_steps": 58920, "loss": 0.0, "lr": 1.3258572047003336e-07, "epoch": 4.254073319755601, "percentage": 85.08, "elapsed_time": "1:19:18", "remaining_time": "0:13:54", "throughput": 10117.74, "total_tokens": 48143296}
{"current_steps": 50135, "total_steps": 58920, "loss": 0.0, "lr": 1.3243836332745916e-07, "epoch": 4.2544976238968095, "percentage": 85.09, "elapsed_time": "1:19:18", "remaining_time": "0:13:53", "throughput": 10117.97, "total_tokens": 48148352}
{"current_steps": 50140, "total_steps": 58920, "loss": 0.0, "lr": 1.3229108231028618e-07, "epoch": 4.2549219280380175, "percentage": 85.1, "elapsed_time": "1:19:19", "remaining_time": "0:13:53", "throughput": 10118.11, "total_tokens": 48152832}
{"current_steps": 50145, "total_steps": 58920, "loss": 0.0, "lr": 1.3214387743143795e-07, "epoch": 4.255346232179226, "percentage": 85.11, "elapsed_time": "1:19:19", "remaining_time": "0:13:52", "throughput": 10118.32, "total_tokens": 48157696}
{"current_steps": 50150, "total_steps": 58920, "loss": 0.0, "lr": 1.3199674870383115e-07, "epoch": 4.255770536320434, "percentage": 85.12, "elapsed_time": "1:19:19", "remaining_time": "0:13:52", "throughput": 10118.43, "total_tokens": 48161984}
{"current_steps": 50155, "total_steps": 58920, "loss": 0.0, "lr": 1.3184969614037566e-07, "epoch": 4.256194840461643, "percentage": 85.12, "elapsed_time": "1:19:20", "remaining_time": "0:13:51", "throughput": 10118.61, "total_tokens": 48166656}
{"current_steps": 50160, "total_steps": 58920, "loss": 0.0, "lr": 1.3170271975397495e-07, "epoch": 4.256619144602851, "percentage": 85.13, "elapsed_time": "1:19:20", "remaining_time": "0:13:51", "throughput": 10118.92, "total_tokens": 48172224}
{"current_steps": 50165, "total_steps": 58920, "loss": 0.0, "lr": 1.3155581955752547e-07, "epoch": 4.25704344874406, "percentage": 85.14, "elapsed_time": "1:19:20", "remaining_time": "0:13:50", "throughput": 10119.11, "total_tokens": 48176960}
{"current_steps": 50170, "total_steps": 58920, "loss": 0.0, "lr": 1.314089955639175e-07, "epoch": 4.257467752885268, "percentage": 85.15, "elapsed_time": "1:19:21", "remaining_time": "0:13:50", "throughput": 10119.22, "total_tokens": 48181248}
{"current_steps": 50175, "total_steps": 58920, "loss": 0.0, "lr": 1.312622477860338e-07, "epoch": 4.257892057026477, "percentage": 85.16, "elapsed_time": "1:19:21", "remaining_time": "0:13:49", "throughput": 10119.4, "total_tokens": 48185920}
{"current_steps": 50180, "total_steps": 58920, "loss": 0.0, "lr": 1.3111557623675174e-07, "epoch": 4.258316361167685, "percentage": 85.17, "elapsed_time": "1:19:22", "remaining_time": "0:13:49", "throughput": 10119.53, "total_tokens": 48190336}
{"current_steps": 50185, "total_steps": 58920, "loss": 0.0, "lr": 1.309689809289406e-07, "epoch": 4.258740665308894, "percentage": 85.17, "elapsed_time": "1:19:22", "remaining_time": "0:13:48", "throughput": 10119.67, "total_tokens": 48194816}
{"current_steps": 50190, "total_steps": 58920, "loss": 0.0, "lr": 1.3082246187546375e-07, "epoch": 4.259164969450102, "percentage": 85.18, "elapsed_time": "1:19:22", "remaining_time": "0:13:48", "throughput": 10119.94, "total_tokens": 48200064}
{"current_steps": 50195, "total_steps": 58920, "loss": 0.0, "lr": 1.3067601908917768e-07, "epoch": 4.259589273591311, "percentage": 85.19, "elapsed_time": "1:19:23", "remaining_time": "0:13:47", "throughput": 10120.09, "total_tokens": 48204608}
{"current_steps": 50200, "total_steps": 58920, "loss": 0.0, "lr": 1.3052965258293202e-07, "epoch": 4.2600135777325185, "percentage": 85.2, "elapsed_time": "1:19:23", "remaining_time": "0:13:47", "throughput": 10120.25, "total_tokens": 48209216}
{"current_steps": 50205, "total_steps": 58920, "loss": 0.0, "lr": 1.303833623695707e-07, "epoch": 4.260437881873727, "percentage": 85.21, "elapsed_time": "1:19:24", "remaining_time": "0:13:46", "throughput": 10120.37, "total_tokens": 48213568}
{"current_steps": 50210, "total_steps": 58920, "loss": 0.0, "lr": 1.30237148461929e-07, "epoch": 4.260862186014935, "percentage": 85.22, "elapsed_time": "1:19:24", "remaining_time": "0:13:46", "throughput": 10120.52, "total_tokens": 48218112}
{"current_steps": 50215, "total_steps": 58920, "loss": 0.0, "lr": 1.300910108728378e-07, "epoch": 4.261286490156144, "percentage": 85.23, "elapsed_time": "1:19:24", "remaining_time": "0:13:45", "throughput": 10120.68, "total_tokens": 48222720}
{"current_steps": 50220, "total_steps": 58920, "loss": 0.0, "lr": 1.2994494961511915e-07, "epoch": 4.261710794297352, "percentage": 85.23, "elapsed_time": "1:19:25", "remaining_time": "0:13:45", "throughput": 10120.81, "total_tokens": 48227136}
{"current_steps": 50225, "total_steps": 58920, "loss": 0.0, "lr": 1.2979896470159002e-07, "epoch": 4.262135098438561, "percentage": 85.24, "elapsed_time": "1:19:25", "remaining_time": "0:13:45", "throughput": 10121.0, "total_tokens": 48232000}
{"current_steps": 50230, "total_steps": 58920, "loss": 0.0, "lr": 1.2965305614506016e-07, "epoch": 4.262559402579769, "percentage": 85.25, "elapsed_time": "1:19:25", "remaining_time": "0:13:44", "throughput": 10121.18, "total_tokens": 48236736}
{"current_steps": 50235, "total_steps": 58920, "loss": 0.0, "lr": 1.2950722395833168e-07, "epoch": 4.262983706720978, "percentage": 85.26, "elapsed_time": "1:19:26", "remaining_time": "0:13:44", "throughput": 10121.39, "total_tokens": 48241536}
{"current_steps": 50240, "total_steps": 58920, "loss": 0.0, "lr": 1.2936146815420202e-07, "epoch": 4.263408010862186, "percentage": 85.27, "elapsed_time": "1:19:26", "remaining_time": "0:13:43", "throughput": 10121.5, "total_tokens": 48245888}
{"current_steps": 50245, "total_steps": 58920, "loss": 0.0, "lr": 1.2921578874545957e-07, "epoch": 4.263832315003395, "percentage": 85.28, "elapsed_time": "1:19:27", "remaining_time": "0:13:43", "throughput": 10121.74, "total_tokens": 48251008}
{"current_steps": 50250, "total_steps": 58920, "loss": 0.0, "lr": 1.2907018574488815e-07, "epoch": 4.264256619144603, "percentage": 85.29, "elapsed_time": "1:19:27", "remaining_time": "0:13:42", "throughput": 10121.85, "total_tokens": 48255360}
{"current_steps": 50255, "total_steps": 58920, "loss": 0.0, "lr": 1.2892465916526296e-07, "epoch": 4.264680923285812, "percentage": 85.29, "elapsed_time": "1:19:27", "remaining_time": "0:13:42", "throughput": 10121.98, "total_tokens": 48260032}
{"current_steps": 50260, "total_steps": 58920, "loss": 0.0002, "lr": 1.2877920901935423e-07, "epoch": 4.26510522742702, "percentage": 85.3, "elapsed_time": "1:19:28", "remaining_time": "0:13:41", "throughput": 10122.26, "total_tokens": 48265408}
{"current_steps": 50265, "total_steps": 58920, "loss": 0.0, "lr": 1.2863383531992455e-07, "epoch": 4.2655295315682284, "percentage": 85.31, "elapsed_time": "1:19:28", "remaining_time": "0:13:41", "throughput": 10122.42, "total_tokens": 48269952}
{"current_steps": 50270, "total_steps": 58920, "loss": 0.0, "lr": 1.2848853807972936e-07, "epoch": 4.265953835709436, "percentage": 85.32, "elapsed_time": "1:19:28", "remaining_time": "0:13:40", "throughput": 10122.54, "total_tokens": 48274304}
{"current_steps": 50275, "total_steps": 58920, "loss": 0.0, "lr": 1.2834331731151882e-07, "epoch": 4.266378139850645, "percentage": 85.33, "elapsed_time": "1:19:29", "remaining_time": "0:13:40", "throughput": 10122.7, "total_tokens": 48278976}
{"current_steps": 50280, "total_steps": 58920, "loss": 0.0, "lr": 1.281981730280346e-07, "epoch": 4.266802443991853, "percentage": 85.34, "elapsed_time": "1:19:29", "remaining_time": "0:13:39", "throughput": 10122.92, "total_tokens": 48283904}
{"current_steps": 50285, "total_steps": 58920, "loss": 0.0, "lr": 1.280531052420133e-07, "epoch": 4.267226748133062, "percentage": 85.34, "elapsed_time": "1:19:30", "remaining_time": "0:13:39", "throughput": 10123.09, "total_tokens": 48288576}
{"current_steps": 50290, "total_steps": 58920, "loss": 0.0, "lr": 1.2790811396618385e-07, "epoch": 4.26765105227427, "percentage": 85.35, "elapsed_time": "1:19:30", "remaining_time": "0:13:38", "throughput": 10123.28, "total_tokens": 48293312}
{"current_steps": 50295, "total_steps": 58920, "loss": 0.0, "lr": 1.2776319921326872e-07, "epoch": 4.268075356415479, "percentage": 85.36, "elapsed_time": "1:19:30", "remaining_time": "0:13:38", "throughput": 10123.44, "total_tokens": 48297920}
{"current_steps": 50300, "total_steps": 58920, "loss": 0.0, "lr": 1.2761836099598367e-07, "epoch": 4.268499660556687, "percentage": 85.37, "elapsed_time": "1:19:31", "remaining_time": "0:13:37", "throughput": 10123.68, "total_tokens": 48303040}
{"current_steps": 50305, "total_steps": 58920, "loss": 0.0, "lr": 1.2747359932703772e-07, "epoch": 4.268923964697896, "percentage": 85.38, "elapsed_time": "1:19:31", "remaining_time": "0:13:37", "throughput": 10123.8, "total_tokens": 48307456}
{"current_steps": 50310, "total_steps": 58920, "loss": 0.0, "lr": 1.2732891421913327e-07, "epoch": 4.269348268839104, "percentage": 85.39, "elapsed_time": "1:19:32", "remaining_time": "0:13:36", "throughput": 10124.0, "total_tokens": 48312320}
{"current_steps": 50315, "total_steps": 58920, "loss": 0.0, "lr": 1.2718430568496574e-07, "epoch": 4.269772572980313, "percentage": 85.4, "elapsed_time": "1:19:32", "remaining_time": "0:13:36", "throughput": 10124.19, "total_tokens": 48317120}
{"current_steps": 50320, "total_steps": 58920, "loss": 0.0, "lr": 1.2703977373722407e-07, "epoch": 4.270196877121521, "percentage": 85.4, "elapsed_time": "1:19:32", "remaining_time": "0:13:35", "throughput": 10124.5, "total_tokens": 48322624}
{"current_steps": 50325, "total_steps": 58920, "loss": 0.0, "lr": 1.2689531838859046e-07, "epoch": 4.2706211812627295, "percentage": 85.41, "elapsed_time": "1:19:33", "remaining_time": "0:13:35", "throughput": 10124.71, "total_tokens": 48327552}
{"current_steps": 50330, "total_steps": 58920, "loss": 0.0, "lr": 1.2675093965174043e-07, "epoch": 4.2710454854039375, "percentage": 85.42, "elapsed_time": "1:19:33", "remaining_time": "0:13:34", "throughput": 10124.9, "total_tokens": 48332288}
{"current_steps": 50335, "total_steps": 58920, "loss": 0.0, "lr": 1.2660663753934254e-07, "epoch": 4.271469789545146, "percentage": 85.43, "elapsed_time": "1:19:33", "remaining_time": "0:13:34", "throughput": 10125.05, "total_tokens": 48336832}
{"current_steps": 50340, "total_steps": 58920, "loss": 0.0, "lr": 1.2646241206405882e-07, "epoch": 4.271894093686354, "percentage": 85.44, "elapsed_time": "1:19:34", "remaining_time": "0:13:33", "throughput": 10125.15, "total_tokens": 48341120}
{"current_steps": 50345, "total_steps": 58920, "loss": 0.0, "lr": 1.2631826323854455e-07, "epoch": 4.272318397827563, "percentage": 85.45, "elapsed_time": "1:19:34", "remaining_time": "0:13:33", "throughput": 10125.34, "total_tokens": 48345984}
{"current_steps": 50350, "total_steps": 58920, "loss": 0.0, "lr": 1.2617419107544825e-07, "epoch": 4.272742701968771, "percentage": 85.45, "elapsed_time": "1:19:35", "remaining_time": "0:13:32", "throughput": 10125.54, "total_tokens": 48350912}
{"current_steps": 50355, "total_steps": 58920, "loss": 0.0, "lr": 1.2603019558741167e-07, "epoch": 4.27316700610998, "percentage": 85.46, "elapsed_time": "1:19:35", "remaining_time": "0:13:32", "throughput": 10125.77, "total_tokens": 48355968}
{"current_steps": 50360, "total_steps": 58920, "loss": 0.0, "lr": 1.258862767870701e-07, "epoch": 4.273591310251188, "percentage": 85.47, "elapsed_time": "1:19:35", "remaining_time": "0:13:31", "throughput": 10125.9, "total_tokens": 48360448}
{"current_steps": 50365, "total_steps": 58920, "loss": 0.0, "lr": 1.257424346870517e-07, "epoch": 4.274015614392397, "percentage": 85.48, "elapsed_time": "1:19:36", "remaining_time": "0:13:31", "throughput": 10126.06, "total_tokens": 48365056}
{"current_steps": 50370, "total_steps": 58920, "loss": 0.0, "lr": 1.255986692999782e-07, "epoch": 4.274439918533605, "percentage": 85.49, "elapsed_time": "1:19:36", "remaining_time": "0:13:30", "throughput": 10126.25, "total_tokens": 48369856}
{"current_steps": 50375, "total_steps": 58920, "loss": 0.0, "lr": 1.254549806384645e-07, "epoch": 4.274864222674814, "percentage": 85.5, "elapsed_time": "1:19:37", "remaining_time": "0:13:30", "throughput": 10126.48, "total_tokens": 48374912}
{"current_steps": 50380, "total_steps": 58920, "loss": 0.0, "lr": 1.253113687151186e-07, "epoch": 4.275288526816022, "percentage": 85.51, "elapsed_time": "1:19:37", "remaining_time": "0:13:29", "throughput": 10126.71, "total_tokens": 48380032}
{"current_steps": 50385, "total_steps": 58920, "loss": 0.0, "lr": 1.2516783354254213e-07, "epoch": 4.2757128309572305, "percentage": 85.51, "elapsed_time": "1:19:37", "remaining_time": "0:13:29", "throughput": 10126.96, "total_tokens": 48385280}
{"current_steps": 50390, "total_steps": 58920, "loss": 0.0, "lr": 1.2502437513332964e-07, "epoch": 4.2761371350984385, "percentage": 85.52, "elapsed_time": "1:19:38", "remaining_time": "0:13:28", "throughput": 10127.07, "total_tokens": 48389632}
{"current_steps": 50395, "total_steps": 58920, "loss": 0.0, "lr": 1.2488099350006919e-07, "epoch": 4.276561439239647, "percentage": 85.53, "elapsed_time": "1:19:38", "remaining_time": "0:13:28", "throughput": 10127.21, "total_tokens": 48394112}
{"current_steps": 50400, "total_steps": 58920, "loss": 0.0, "lr": 1.2473768865534195e-07, "epoch": 4.276985743380855, "percentage": 85.54, "elapsed_time": "1:19:39", "remaining_time": "0:13:27", "throughput": 10127.32, "total_tokens": 48398528}
{"current_steps": 50405, "total_steps": 58920, "loss": 0.0, "lr": 1.2459446061172241e-07, "epoch": 4.277410047522064, "percentage": 85.55, "elapsed_time": "1:19:39", "remaining_time": "0:13:27", "throughput": 10127.46, "total_tokens": 48403008}
{"current_steps": 50410, "total_steps": 58920, "loss": 0.0, "lr": 1.2445130938177828e-07, "epoch": 4.277834351663272, "percentage": 85.56, "elapsed_time": "1:19:39", "remaining_time": "0:13:26", "throughput": 10127.68, "total_tokens": 48408000}
{"current_steps": 50415, "total_steps": 58920, "loss": 0.0, "lr": 1.243082349780704e-07, "epoch": 4.278258655804481, "percentage": 85.57, "elapsed_time": "1:19:40", "remaining_time": "0:13:26", "throughput": 10127.85, "total_tokens": 48412672}
{"current_steps": 50420, "total_steps": 58920, "loss": 0.0, "lr": 1.2416523741315365e-07, "epoch": 4.278682959945689, "percentage": 85.57, "elapsed_time": "1:19:40", "remaining_time": "0:13:25", "throughput": 10128.0, "total_tokens": 48417280}
{"current_steps": 50425, "total_steps": 58920, "loss": 0.0, "lr": 1.2402231669957463e-07, "epoch": 4.279107264086898, "percentage": 85.58, "elapsed_time": "1:19:40", "remaining_time": "0:13:25", "throughput": 10128.34, "total_tokens": 48423168}
{"current_steps": 50430, "total_steps": 58920, "loss": 0.0, "lr": 1.238794728498752e-07, "epoch": 4.279531568228106, "percentage": 85.59, "elapsed_time": "1:19:41", "remaining_time": "0:13:24", "throughput": 10128.54, "total_tokens": 48428032}
{"current_steps": 50435, "total_steps": 58920, "loss": 0.0, "lr": 1.2373670587658847e-07, "epoch": 4.279955872369315, "percentage": 85.6, "elapsed_time": "1:19:41", "remaining_time": "0:13:24", "throughput": 10128.78, "total_tokens": 48433152}
{"current_steps": 50440, "total_steps": 58920, "loss": 0.0, "lr": 1.2359401579224192e-07, "epoch": 4.280380176510523, "percentage": 85.61, "elapsed_time": "1:19:42", "remaining_time": "0:13:23", "throughput": 10128.94, "total_tokens": 48437888}
{"current_steps": 50445, "total_steps": 58920, "loss": 0.0, "lr": 1.234514026093566e-07, "epoch": 4.280804480651732, "percentage": 85.62, "elapsed_time": "1:19:42", "remaining_time": "0:13:23", "throughput": 10129.15, "total_tokens": 48442816}
{"current_steps": 50450, "total_steps": 58920, "loss": 0.0, "lr": 1.2330886634044557e-07, "epoch": 4.28122878479294, "percentage": 85.62, "elapsed_time": "1:19:42", "remaining_time": "0:13:22", "throughput": 10129.28, "total_tokens": 48447296}
{"current_steps": 50455, "total_steps": 58920, "loss": 0.0, "lr": 1.2316640699801662e-07, "epoch": 4.2816530889341475, "percentage": 85.63, "elapsed_time": "1:19:43", "remaining_time": "0:13:22", "throughput": 10129.5, "total_tokens": 48452352}
{"current_steps": 50460, "total_steps": 58920, "loss": 0.0, "lr": 1.2302402459456928e-07, "epoch": 4.282077393075356, "percentage": 85.64, "elapsed_time": "1:19:43", "remaining_time": "0:13:22", "throughput": 10129.71, "total_tokens": 48457344}
{"current_steps": 50465, "total_steps": 58920, "loss": 0.0, "lr": 1.2288171914259783e-07, "epoch": 4.282501697216565, "percentage": 85.65, "elapsed_time": "1:19:44", "remaining_time": "0:13:21", "throughput": 10129.91, "total_tokens": 48462208}
{"current_steps": 50470, "total_steps": 58920, "loss": 0.0, "lr": 1.2273949065458833e-07, "epoch": 4.282926001357773, "percentage": 85.66, "elapsed_time": "1:19:44", "remaining_time": "0:13:21", "throughput": 10130.19, "total_tokens": 48467712}
{"current_steps": 50475, "total_steps": 58920, "loss": 0.0, "lr": 1.225973391430214e-07, "epoch": 4.283350305498981, "percentage": 85.67, "elapsed_time": "1:19:44", "remaining_time": "0:13:20", "throughput": 10130.36, "total_tokens": 48472384}
{"current_steps": 50480, "total_steps": 58920, "loss": 0.0, "lr": 1.2245526462037026e-07, "epoch": 4.28377460964019, "percentage": 85.68, "elapsed_time": "1:19:45", "remaining_time": "0:13:20", "throughput": 10130.5, "total_tokens": 48476864}
{"current_steps": 50485, "total_steps": 58920, "loss": 0.0, "lr": 1.2231326709910096e-07, "epoch": 4.284198913781399, "percentage": 85.68, "elapsed_time": "1:19:45", "remaining_time": "0:13:19", "throughput": 10130.73, "total_tokens": 48481920}
{"current_steps": 50490, "total_steps": 58920, "loss": 0.0, "lr": 1.2217134659167393e-07, "epoch": 4.284623217922607, "percentage": 85.69, "elapsed_time": "1:19:46", "remaining_time": "0:13:19", "throughput": 10130.91, "total_tokens": 48486656}
{"current_steps": 50495, "total_steps": 58920, "loss": 0.0, "lr": 1.220295031105415e-07, "epoch": 4.285047522063815, "percentage": 85.7, "elapsed_time": "1:19:46", "remaining_time": "0:13:18", "throughput": 10131.09, "total_tokens": 48491392}
{"current_steps": 50500, "total_steps": 58920, "loss": 0.0, "lr": 1.2188773666815045e-07, "epoch": 4.285471826205024, "percentage": 85.71, "elapsed_time": "1:19:46", "remaining_time": "0:13:18", "throughput": 10131.18, "total_tokens": 48495680}
{"current_steps": 50505, "total_steps": 58920, "loss": 0.0911, "lr": 1.2174604727694004e-07, "epoch": 4.285896130346233, "percentage": 85.72, "elapsed_time": "1:19:47", "remaining_time": "0:13:17", "throughput": 10131.32, "total_tokens": 48500160}
{"current_steps": 50510, "total_steps": 58920, "loss": 0.0, "lr": 1.2160443494934314e-07, "epoch": 4.286320434487441, "percentage": 85.73, "elapsed_time": "1:19:47", "remaining_time": "0:13:17", "throughput": 10131.53, "total_tokens": 48505088}
{"current_steps": 50515, "total_steps": 58920, "loss": 0.0, "lr": 1.2146289969778567e-07, "epoch": 4.286744738628649, "percentage": 85.73, "elapsed_time": "1:19:47", "remaining_time": "0:13:16", "throughput": 10131.65, "total_tokens": 48509504}
{"current_steps": 50520, "total_steps": 58920, "loss": 0.0, "lr": 1.213214415346867e-07, "epoch": 4.287169042769857, "percentage": 85.74, "elapsed_time": "1:19:48", "remaining_time": "0:13:16", "throughput": 10131.77, "total_tokens": 48513856}
{"current_steps": 50525, "total_steps": 58920, "loss": 0.0, "lr": 1.211800604724591e-07, "epoch": 4.287593346911066, "percentage": 85.75, "elapsed_time": "1:19:48", "remaining_time": "0:13:15", "throughput": 10131.88, "total_tokens": 48518208}
{"current_steps": 50530, "total_steps": 58920, "loss": 0.0, "lr": 1.210387565235077e-07, "epoch": 4.288017651052274, "percentage": 85.76, "elapsed_time": "1:19:49", "remaining_time": "0:13:15", "throughput": 10132.01, "total_tokens": 48522624}
{"current_steps": 50535, "total_steps": 58920, "loss": 0.0, "lr": 1.2089752970023225e-07, "epoch": 4.288441955193482, "percentage": 85.77, "elapsed_time": "1:19:49", "remaining_time": "0:13:14", "throughput": 10132.3, "total_tokens": 48528064}
{"current_steps": 50540, "total_steps": 58920, "loss": 0.0, "lr": 1.2075638001502454e-07, "epoch": 4.288866259334691, "percentage": 85.78, "elapsed_time": "1:19:49", "remaining_time": "0:13:14", "throughput": 10132.6, "total_tokens": 48533568}
{"current_steps": 50545, "total_steps": 58920, "loss": 0.0, "lr": 1.2061530748026993e-07, "epoch": 4.2892905634759, "percentage": 85.79, "elapsed_time": "1:19:50", "remaining_time": "0:13:13", "throughput": 10132.85, "total_tokens": 48538752}
{"current_steps": 50550, "total_steps": 58920, "loss": 0.0, "lr": 1.2047431210834713e-07, "epoch": 4.289714867617108, "percentage": 85.79, "elapsed_time": "1:19:50", "remaining_time": "0:13:13", "throughput": 10133.2, "total_tokens": 48544640}
{"current_steps": 50555, "total_steps": 58920, "loss": 0.0, "lr": 1.2033339391162788e-07, "epoch": 4.290139171758316, "percentage": 85.8, "elapsed_time": "1:19:51", "remaining_time": "0:13:12", "throughput": 10133.4, "total_tokens": 48549568}
{"current_steps": 50560, "total_steps": 58920, "loss": 0.0, "lr": 1.2019255290247733e-07, "epoch": 4.290563475899525, "percentage": 85.81, "elapsed_time": "1:19:51", "remaining_time": "0:13:12", "throughput": 10133.53, "total_tokens": 48554048}
{"current_steps": 50565, "total_steps": 58920, "loss": 0.0, "lr": 1.2005178909325375e-07, "epoch": 4.290987780040734, "percentage": 85.82, "elapsed_time": "1:19:51", "remaining_time": "0:13:11", "throughput": 10133.74, "total_tokens": 48558912}
{"current_steps": 50570, "total_steps": 58920, "loss": 0.0, "lr": 1.1991110249630865e-07, "epoch": 4.291412084181942, "percentage": 85.83, "elapsed_time": "1:19:52", "remaining_time": "0:13:11", "throughput": 10133.9, "total_tokens": 48563520}
{"current_steps": 50575, "total_steps": 58920, "loss": 0.0, "lr": 1.1977049312398668e-07, "epoch": 4.29183638832315, "percentage": 85.84, "elapsed_time": "1:19:52", "remaining_time": "0:13:10", "throughput": 10134.09, "total_tokens": 48568320}
{"current_steps": 50580, "total_steps": 58920, "loss": 0.0, "lr": 1.19629960988626e-07, "epoch": 4.2922606924643585, "percentage": 85.85, "elapsed_time": "1:19:52", "remaining_time": "0:13:10", "throughput": 10134.24, "total_tokens": 48572928}
{"current_steps": 50585, "total_steps": 58920, "loss": 0.0, "lr": 1.1948950610255759e-07, "epoch": 4.2926849966055665, "percentage": 85.85, "elapsed_time": "1:19:53", "remaining_time": "0:13:09", "throughput": 10134.49, "total_tokens": 48578112}
{"current_steps": 50590, "total_steps": 58920, "loss": 0.0001, "lr": 1.1934912847810595e-07, "epoch": 4.293109300746775, "percentage": 85.86, "elapsed_time": "1:19:53", "remaining_time": "0:13:09", "throughput": 10134.63, "total_tokens": 48582656}
{"current_steps": 50595, "total_steps": 58920, "loss": 0.0, "lr": 1.192088281275887e-07, "epoch": 4.293533604887983, "percentage": 85.87, "elapsed_time": "1:19:54", "remaining_time": "0:13:08", "throughput": 10134.91, "total_tokens": 48588096}
{"current_steps": 50600, "total_steps": 58920, "loss": 0.0, "lr": 1.1906860506331673e-07, "epoch": 4.293957909029192, "percentage": 85.88, "elapsed_time": "1:19:54", "remaining_time": "0:13:08", "throughput": 10135.22, "total_tokens": 48593792}
{"current_steps": 50605, "total_steps": 58920, "loss": 0.0, "lr": 1.189284592975941e-07, "epoch": 4.2943822131704, "percentage": 85.89, "elapsed_time": "1:19:54", "remaining_time": "0:13:07", "throughput": 10135.39, "total_tokens": 48598528}
{"current_steps": 50610, "total_steps": 58920, "loss": 0.0, "lr": 1.1878839084271807e-07, "epoch": 4.294806517311609, "percentage": 85.9, "elapsed_time": "1:19:55", "remaining_time": "0:13:07", "throughput": 10135.47, "total_tokens": 48602752}
{"current_steps": 50615, "total_steps": 58920, "loss": 0.0, "lr": 1.1864839971097906e-07, "epoch": 4.295230821452817, "percentage": 85.9, "elapsed_time": "1:19:55", "remaining_time": "0:13:06", "throughput": 10135.82, "total_tokens": 48608640}
{"current_steps": 50620, "total_steps": 58920, "loss": 0.0, "lr": 1.185084859146609e-07, "epoch": 4.295655125594026, "percentage": 85.91, "elapsed_time": "1:19:56", "remaining_time": "0:13:06", "throughput": 10136.03, "total_tokens": 48613632}
{"current_steps": 50625, "total_steps": 58920, "loss": 0.0, "lr": 1.1836864946604052e-07, "epoch": 4.296079429735234, "percentage": 85.92, "elapsed_time": "1:19:56", "remaining_time": "0:13:05", "throughput": 10136.22, "total_tokens": 48618496}
{"current_steps": 50630, "total_steps": 58920, "loss": 0.0, "lr": 1.1822889037738782e-07, "epoch": 4.296503733876443, "percentage": 85.93, "elapsed_time": "1:19:56", "remaining_time": "0:13:05", "throughput": 10136.46, "total_tokens": 48623616}
{"current_steps": 50635, "total_steps": 58920, "loss": 0.0, "lr": 1.1808920866096683e-07, "epoch": 4.296928038017651, "percentage": 85.94, "elapsed_time": "1:19:57", "remaining_time": "0:13:04", "throughput": 10136.65, "total_tokens": 48628480}
{"current_steps": 50640, "total_steps": 58920, "loss": 0.0, "lr": 1.1794960432903311e-07, "epoch": 4.2973523421588595, "percentage": 85.95, "elapsed_time": "1:19:57", "remaining_time": "0:13:04", "throughput": 10136.89, "total_tokens": 48633728}
{"current_steps": 50645, "total_steps": 58920, "loss": 0.0, "lr": 1.1781007739383752e-07, "epoch": 4.2977766463000675, "percentage": 85.96, "elapsed_time": "1:19:58", "remaining_time": "0:13:03", "throughput": 10137.03, "total_tokens": 48638272}
{"current_steps": 50650, "total_steps": 58920, "loss": 0.0, "lr": 1.1767062786762227e-07, "epoch": 4.298200950441276, "percentage": 85.96, "elapsed_time": "1:19:58", "remaining_time": "0:13:03", "throughput": 10137.16, "total_tokens": 48642752}
{"current_steps": 50655, "total_steps": 58920, "loss": 0.0, "lr": 1.1753125576262379e-07, "epoch": 4.298625254582484, "percentage": 85.97, "elapsed_time": "1:19:58", "remaining_time": "0:13:02", "throughput": 10137.42, "total_tokens": 48647936}
{"current_steps": 50660, "total_steps": 58920, "loss": 0.0, "lr": 1.1739196109107141e-07, "epoch": 4.299049558723693, "percentage": 85.98, "elapsed_time": "1:19:59", "remaining_time": "0:13:02", "throughput": 10137.72, "total_tokens": 48653440}
{"current_steps": 50665, "total_steps": 58920, "loss": 0.0, "lr": 1.1725274386518758e-07, "epoch": 4.299473862864901, "percentage": 85.99, "elapsed_time": "1:19:59", "remaining_time": "0:13:02", "throughput": 10137.91, "total_tokens": 48658304}
{"current_steps": 50670, "total_steps": 58920, "loss": 0.0, "lr": 1.1711360409718884e-07, "epoch": 4.29989816700611, "percentage": 86.0, "elapsed_time": "1:20:00", "remaining_time": "0:13:01", "throughput": 10138.05, "total_tokens": 48662784}
{"current_steps": 50675, "total_steps": 58920, "loss": 0.0, "lr": 1.1697454179928323e-07, "epoch": 4.300322471147318, "percentage": 86.01, "elapsed_time": "1:20:00", "remaining_time": "0:13:01", "throughput": 10138.19, "total_tokens": 48667328}
{"current_steps": 50680, "total_steps": 58920, "loss": 0.0, "lr": 1.1683555698367387e-07, "epoch": 4.300746775288527, "percentage": 86.01, "elapsed_time": "1:20:00", "remaining_time": "0:13:00", "throughput": 10138.44, "total_tokens": 48672448}
{"current_steps": 50685, "total_steps": 58920, "loss": 0.0, "lr": 1.1669664966255543e-07, "epoch": 4.301171079429735, "percentage": 86.02, "elapsed_time": "1:20:01", "remaining_time": "0:13:00", "throughput": 10138.54, "total_tokens": 48676672}
{"current_steps": 50690, "total_steps": 58920, "loss": 0.0, "lr": 1.1655781984811675e-07, "epoch": 4.301595383570944, "percentage": 86.03, "elapsed_time": "1:20:01", "remaining_time": "0:12:59", "throughput": 10138.79, "total_tokens": 48681856}
{"current_steps": 50695, "total_steps": 58920, "loss": 0.0, "lr": 1.1641906755254005e-07, "epoch": 4.302019687712152, "percentage": 86.04, "elapsed_time": "1:20:01", "remaining_time": "0:12:59", "throughput": 10139.01, "total_tokens": 48686848}
{"current_steps": 50700, "total_steps": 58920, "loss": 0.0, "lr": 1.1628039278799962e-07, "epoch": 4.302443991853361, "percentage": 86.05, "elapsed_time": "1:20:02", "remaining_time": "0:12:58", "throughput": 10139.17, "total_tokens": 48691520}
{"current_steps": 50705, "total_steps": 58920, "loss": 0.0, "lr": 1.1614179556666448e-07, "epoch": 4.3028682959945685, "percentage": 86.06, "elapsed_time": "1:20:02", "remaining_time": "0:12:58", "throughput": 10139.28, "total_tokens": 48695744}
{"current_steps": 50710, "total_steps": 58920, "loss": 0.0, "lr": 1.1600327590069525e-07, "epoch": 4.303292600135777, "percentage": 86.07, "elapsed_time": "1:20:03", "remaining_time": "0:12:57", "throughput": 10139.55, "total_tokens": 48701056}
{"current_steps": 50715, "total_steps": 58920, "loss": 0.0, "lr": 1.158648338022471e-07, "epoch": 4.303716904276985, "percentage": 86.07, "elapsed_time": "1:20:03", "remaining_time": "0:12:57", "throughput": 10139.71, "total_tokens": 48705664}
{"current_steps": 50720, "total_steps": 58920, "loss": 0.0, "lr": 1.1572646928346763e-07, "epoch": 4.304141208418194, "percentage": 86.08, "elapsed_time": "1:20:03", "remaining_time": "0:12:56", "throughput": 10139.88, "total_tokens": 48710272}
{"current_steps": 50725, "total_steps": 58920, "loss": 0.0, "lr": 1.1558818235649781e-07, "epoch": 4.304565512559402, "percentage": 86.09, "elapsed_time": "1:20:04", "remaining_time": "0:12:56", "throughput": 10140.0, "total_tokens": 48714688}
{"current_steps": 50730, "total_steps": 58920, "loss": 0.0, "lr": 1.1544997303347204e-07, "epoch": 4.304989816700611, "percentage": 86.1, "elapsed_time": "1:20:04", "remaining_time": "0:12:55", "throughput": 10140.22, "total_tokens": 48719680}
{"current_steps": 50735, "total_steps": 58920, "loss": 0.0, "lr": 1.1531184132651705e-07, "epoch": 4.305414120841819, "percentage": 86.11, "elapsed_time": "1:20:04", "remaining_time": "0:12:55", "throughput": 10140.43, "total_tokens": 48724608}
{"current_steps": 50740, "total_steps": 58920, "loss": 0.0, "lr": 1.1517378724775418e-07, "epoch": 4.305838424983028, "percentage": 86.12, "elapsed_time": "1:20:05", "remaining_time": "0:12:54", "throughput": 10140.64, "total_tokens": 48729472}
{"current_steps": 50745, "total_steps": 58920, "loss": 0.0, "lr": 1.1503581080929648e-07, "epoch": 4.306262729124236, "percentage": 86.13, "elapsed_time": "1:20:05", "remaining_time": "0:12:54", "throughput": 10140.83, "total_tokens": 48734272}
{"current_steps": 50750, "total_steps": 58920, "loss": 0.0, "lr": 1.148979120232515e-07, "epoch": 4.306687033265445, "percentage": 86.13, "elapsed_time": "1:20:06", "remaining_time": "0:12:53", "throughput": 10140.99, "total_tokens": 48738880}
{"current_steps": 50755, "total_steps": 58920, "loss": 0.0002, "lr": 1.1476009090171901e-07, "epoch": 4.307111337406653, "percentage": 86.14, "elapsed_time": "1:20:06", "remaining_time": "0:12:53", "throughput": 10141.22, "total_tokens": 48743936}
{"current_steps": 50760, "total_steps": 58920, "loss": 0.0, "lr": 1.1462234745679245e-07, "epoch": 4.307535641547862, "percentage": 86.15, "elapsed_time": "1:20:06", "remaining_time": "0:12:52", "throughput": 10141.41, "total_tokens": 48748672}
{"current_steps": 50765, "total_steps": 58920, "loss": 0.0, "lr": 1.1448468170055814e-07, "epoch": 4.30795994568907, "percentage": 86.16, "elapsed_time": "1:20:07", "remaining_time": "0:12:52", "throughput": 10141.68, "total_tokens": 48753984}
{"current_steps": 50770, "total_steps": 58920, "loss": 0.0, "lr": 1.1434709364509598e-07, "epoch": 4.3083842498302785, "percentage": 86.17, "elapsed_time": "1:20:07", "remaining_time": "0:12:51", "throughput": 10141.81, "total_tokens": 48758400}
{"current_steps": 50775, "total_steps": 58920, "loss": 0.0, "lr": 1.1420958330247865e-07, "epoch": 4.308808553971486, "percentage": 86.18, "elapsed_time": "1:20:08", "remaining_time": "0:12:51", "throughput": 10142.02, "total_tokens": 48763328}
{"current_steps": 50780, "total_steps": 58920, "loss": 0.0, "lr": 1.1407215068477238e-07, "epoch": 4.309232858112695, "percentage": 86.18, "elapsed_time": "1:20:08", "remaining_time": "0:12:50", "throughput": 10142.45, "total_tokens": 48769664}
{"current_steps": 50785, "total_steps": 58920, "loss": 0.0, "lr": 1.1393479580403609e-07, "epoch": 4.309657162253903, "percentage": 86.19, "elapsed_time": "1:20:08", "remaining_time": "0:12:50", "throughput": 10142.59, "total_tokens": 48774208}
{"current_steps": 50790, "total_steps": 58920, "loss": 0.0, "lr": 1.1379751867232246e-07, "epoch": 4.310081466395112, "percentage": 86.2, "elapsed_time": "1:20:09", "remaining_time": "0:12:49", "throughput": 10142.74, "total_tokens": 48778688}
{"current_steps": 50795, "total_steps": 58920, "loss": 0.0, "lr": 1.1366031930167685e-07, "epoch": 4.31050577053632, "percentage": 86.21, "elapsed_time": "1:20:09", "remaining_time": "0:12:49", "throughput": 10142.82, "total_tokens": 48782848}
{"current_steps": 50800, "total_steps": 58920, "loss": 0.0, "lr": 1.135231977041382e-07, "epoch": 4.310930074677529, "percentage": 86.22, "elapsed_time": "1:20:09", "remaining_time": "0:12:48", "throughput": 10143.05, "total_tokens": 48787904}
{"current_steps": 50805, "total_steps": 58920, "loss": 0.0, "lr": 1.1338615389173833e-07, "epoch": 4.311354378818737, "percentage": 86.23, "elapsed_time": "1:20:10", "remaining_time": "0:12:48", "throughput": 10143.28, "total_tokens": 48792960}
{"current_steps": 50810, "total_steps": 58920, "loss": 0.0, "lr": 1.1324918787650228e-07, "epoch": 4.311778682959946, "percentage": 86.24, "elapsed_time": "1:20:10", "remaining_time": "0:12:47", "throughput": 10143.48, "total_tokens": 48797824}
{"current_steps": 50815, "total_steps": 58920, "loss": 0.0, "lr": 1.1311229967044844e-07, "epoch": 4.312202987101154, "percentage": 86.24, "elapsed_time": "1:20:11", "remaining_time": "0:12:47", "throughput": 10143.68, "total_tokens": 48802688}
{"current_steps": 50820, "total_steps": 58920, "loss": 0.0, "lr": 1.129754892855882e-07, "epoch": 4.312627291242363, "percentage": 86.25, "elapsed_time": "1:20:11", "remaining_time": "0:12:46", "throughput": 10143.83, "total_tokens": 48807232}
{"current_steps": 50825, "total_steps": 58920, "loss": 0.0, "lr": 1.1283875673392617e-07, "epoch": 4.313051595383571, "percentage": 86.26, "elapsed_time": "1:20:11", "remaining_time": "0:12:46", "throughput": 10143.91, "total_tokens": 48811392}
{"current_steps": 50830, "total_steps": 58920, "loss": 0.0, "lr": 1.1270210202746022e-07, "epoch": 4.3134758995247795, "percentage": 86.27, "elapsed_time": "1:20:12", "remaining_time": "0:12:45", "throughput": 10144.08, "total_tokens": 48816000}
{"current_steps": 50835, "total_steps": 58920, "loss": 0.0, "lr": 1.1256552517818119e-07, "epoch": 4.3139002036659875, "percentage": 86.28, "elapsed_time": "1:20:12", "remaining_time": "0:12:45", "throughput": 10144.26, "total_tokens": 48820672}
{"current_steps": 50840, "total_steps": 58920, "loss": 0.0, "lr": 1.1242902619807326e-07, "epoch": 4.314324507807196, "percentage": 86.29, "elapsed_time": "1:20:13", "remaining_time": "0:12:44", "throughput": 10144.47, "total_tokens": 48825600}
{"current_steps": 50845, "total_steps": 58920, "loss": 0.0, "lr": 1.1229260509911353e-07, "epoch": 4.314748811948404, "percentage": 86.29, "elapsed_time": "1:20:13", "remaining_time": "0:12:44", "throughput": 10144.69, "total_tokens": 48830592}
{"current_steps": 50850, "total_steps": 58920, "loss": 0.0, "lr": 1.1215626189327299e-07, "epoch": 4.315173116089613, "percentage": 86.3, "elapsed_time": "1:20:13", "remaining_time": "0:12:43", "throughput": 10144.82, "total_tokens": 48835008}
{"current_steps": 50855, "total_steps": 58920, "loss": 0.0, "lr": 1.1201999659251482e-07, "epoch": 4.315597420230821, "percentage": 86.31, "elapsed_time": "1:20:14", "remaining_time": "0:12:43", "throughput": 10144.99, "total_tokens": 48839680}
{"current_steps": 50860, "total_steps": 58920, "loss": 0.0, "lr": 1.1188380920879581e-07, "epoch": 4.31602172437203, "percentage": 86.32, "elapsed_time": "1:20:14", "remaining_time": "0:12:42", "throughput": 10145.05, "total_tokens": 48843648}
{"current_steps": 50865, "total_steps": 58920, "loss": 0.0, "lr": 1.1174769975406606e-07, "epoch": 4.316446028513238, "percentage": 86.33, "elapsed_time": "1:20:14", "remaining_time": "0:12:42", "throughput": 10145.17, "total_tokens": 48848064}
{"current_steps": 50870, "total_steps": 58920, "loss": 0.0, "lr": 1.1161166824026868e-07, "epoch": 4.316870332654447, "percentage": 86.34, "elapsed_time": "1:20:15", "remaining_time": "0:12:42", "throughput": 10145.39, "total_tokens": 48852992}
{"current_steps": 50875, "total_steps": 58920, "loss": 0.0, "lr": 1.114757146793398e-07, "epoch": 4.317294636795655, "percentage": 86.35, "elapsed_time": "1:20:15", "remaining_time": "0:12:41", "throughput": 10145.61, "total_tokens": 48858048}
{"current_steps": 50880, "total_steps": 58920, "loss": 0.0, "lr": 1.1133983908320888e-07, "epoch": 4.317718940936864, "percentage": 86.35, "elapsed_time": "1:20:16", "remaining_time": "0:12:41", "throughput": 10145.77, "total_tokens": 48862592}
{"current_steps": 50885, "total_steps": 58920, "loss": 0.0, "lr": 1.1120404146379891e-07, "epoch": 4.318143245078072, "percentage": 86.36, "elapsed_time": "1:20:16", "remaining_time": "0:12:40", "throughput": 10146.03, "total_tokens": 48867840}
{"current_steps": 50890, "total_steps": 58920, "loss": 0.0, "lr": 1.1106832183302483e-07, "epoch": 4.3185675492192805, "percentage": 86.37, "elapsed_time": "1:20:16", "remaining_time": "0:12:40", "throughput": 10146.19, "total_tokens": 48872448}
{"current_steps": 50895, "total_steps": 58920, "loss": 0.0, "lr": 1.1093268020279656e-07, "epoch": 4.3189918533604885, "percentage": 86.38, "elapsed_time": "1:20:17", "remaining_time": "0:12:39", "throughput": 10146.33, "total_tokens": 48876992}
{"current_steps": 50900, "total_steps": 58920, "loss": 0.0, "lr": 1.1079711658501545e-07, "epoch": 4.319416157501697, "percentage": 86.39, "elapsed_time": "1:20:17", "remaining_time": "0:12:39", "throughput": 10146.54, "total_tokens": 48881920}
{"current_steps": 50905, "total_steps": 58920, "loss": 0.0, "lr": 1.1066163099157655e-07, "epoch": 4.319840461642905, "percentage": 86.4, "elapsed_time": "1:20:17", "remaining_time": "0:12:38", "throughput": 10146.7, "total_tokens": 48886528}
{"current_steps": 50910, "total_steps": 58920, "loss": 0.0, "lr": 1.1052622343436913e-07, "epoch": 4.320264765784114, "percentage": 86.41, "elapsed_time": "1:20:18", "remaining_time": "0:12:38", "throughput": 10146.85, "total_tokens": 48891072}
{"current_steps": 50915, "total_steps": 58920, "loss": 0.0, "lr": 1.1039089392527379e-07, "epoch": 4.320689069925322, "percentage": 86.41, "elapsed_time": "1:20:18", "remaining_time": "0:12:37", "throughput": 10146.96, "total_tokens": 48895360}
{"current_steps": 50920, "total_steps": 58920, "loss": 0.0, "lr": 1.1025564247616593e-07, "epoch": 4.321113374066531, "percentage": 86.42, "elapsed_time": "1:20:19", "remaining_time": "0:12:37", "throughput": 10147.18, "total_tokens": 48900288}
{"current_steps": 50925, "total_steps": 58920, "loss": 0.0, "lr": 1.1012046909891259e-07, "epoch": 4.321537678207739, "percentage": 86.43, "elapsed_time": "1:20:19", "remaining_time": "0:12:36", "throughput": 10147.35, "total_tokens": 48905024}
{"current_steps": 50930, "total_steps": 58920, "loss": 0.0, "lr": 1.0998537380537542e-07, "epoch": 4.321961982348948, "percentage": 86.44, "elapsed_time": "1:20:19", "remaining_time": "0:12:36", "throughput": 10147.49, "total_tokens": 48909504}
{"current_steps": 50935, "total_steps": 58920, "loss": 0.0, "lr": 1.0985035660740849e-07, "epoch": 4.322386286490156, "percentage": 86.45, "elapsed_time": "1:20:20", "remaining_time": "0:12:35", "throughput": 10147.82, "total_tokens": 48915200}
{"current_steps": 50940, "total_steps": 58920, "loss": 0.0, "lr": 1.0971541751685853e-07, "epoch": 4.322810590631365, "percentage": 86.46, "elapsed_time": "1:20:20", "remaining_time": "0:12:35", "throughput": 10148.03, "total_tokens": 48920128}
{"current_steps": 50945, "total_steps": 58920, "loss": 0.0, "lr": 1.0958055654556675e-07, "epoch": 4.323234894772573, "percentage": 86.46, "elapsed_time": "1:20:21", "remaining_time": "0:12:34", "throughput": 10148.17, "total_tokens": 48924608}
{"current_steps": 50950, "total_steps": 58920, "loss": 0.0, "lr": 1.0944577370536589e-07, "epoch": 4.323659198913782, "percentage": 86.47, "elapsed_time": "1:20:21", "remaining_time": "0:12:34", "throughput": 10148.38, "total_tokens": 48929472}
{"current_steps": 50955, "total_steps": 58920, "loss": 0.0, "lr": 1.093110690080834e-07, "epoch": 4.32408350305499, "percentage": 86.48, "elapsed_time": "1:20:21", "remaining_time": "0:12:33", "throughput": 10148.6, "total_tokens": 48934528}
{"current_steps": 50960, "total_steps": 58920, "loss": 0.0, "lr": 1.0917644246553836e-07, "epoch": 4.324507807196198, "percentage": 86.49, "elapsed_time": "1:20:22", "remaining_time": "0:12:33", "throughput": 10148.68, "total_tokens": 48938688}
{"current_steps": 50965, "total_steps": 58920, "loss": 0.0, "lr": 1.0904189408954445e-07, "epoch": 4.324932111337406, "percentage": 86.5, "elapsed_time": "1:20:22", "remaining_time": "0:12:32", "throughput": 10148.82, "total_tokens": 48943104}
{"current_steps": 50970, "total_steps": 58920, "loss": 0.0, "lr": 1.0890742389190754e-07, "epoch": 4.325356415478615, "percentage": 86.51, "elapsed_time": "1:20:22", "remaining_time": "0:12:32", "throughput": 10149.11, "total_tokens": 48948544}
{"current_steps": 50975, "total_steps": 58920, "loss": 0.0, "lr": 1.0877303188442688e-07, "epoch": 4.325780719619823, "percentage": 86.52, "elapsed_time": "1:20:23", "remaining_time": "0:12:31", "throughput": 10149.29, "total_tokens": 48953344}
{"current_steps": 50980, "total_steps": 58920, "loss": 0.0, "lr": 1.0863871807889513e-07, "epoch": 4.326205023761032, "percentage": 86.52, "elapsed_time": "1:20:23", "remaining_time": "0:12:31", "throughput": 10149.41, "total_tokens": 48957696}
{"current_steps": 50985, "total_steps": 58920, "loss": 0.0, "lr": 1.0850448248709731e-07, "epoch": 4.32662932790224, "percentage": 86.53, "elapsed_time": "1:20:24", "remaining_time": "0:12:30", "throughput": 10149.61, "total_tokens": 48962560}
{"current_steps": 50990, "total_steps": 58920, "loss": 0.0, "lr": 1.0837032512081245e-07, "epoch": 4.327053632043449, "percentage": 86.54, "elapsed_time": "1:20:24", "remaining_time": "0:12:30", "throughput": 10149.71, "total_tokens": 48966784}
{"current_steps": 50995, "total_steps": 58920, "loss": 0.0, "lr": 1.0823624599181247e-07, "epoch": 4.327477936184657, "percentage": 86.55, "elapsed_time": "1:20:24", "remaining_time": "0:12:29", "throughput": 10149.82, "total_tokens": 48971072}
{"current_steps": 51000, "total_steps": 58920, "loss": 0.0, "lr": 1.0810224511186216e-07, "epoch": 4.327902240325866, "percentage": 86.56, "elapsed_time": "1:20:25", "remaining_time": "0:12:29", "throughput": 10150.01, "total_tokens": 48975936}
{"current_steps": 51005, "total_steps": 58920, "loss": 0.0, "lr": 1.0796832249271959e-07, "epoch": 4.328326544467074, "percentage": 86.57, "elapsed_time": "1:20:25", "remaining_time": "0:12:28", "throughput": 10150.12, "total_tokens": 48980224}
{"current_steps": 51010, "total_steps": 58920, "loss": 0.0, "lr": 1.078344781461361e-07, "epoch": 4.328750848608283, "percentage": 86.58, "elapsed_time": "1:20:25", "remaining_time": "0:12:28", "throughput": 10150.37, "total_tokens": 48985344}
{"current_steps": 51015, "total_steps": 58920, "loss": 0.0, "lr": 1.0770071208385611e-07, "epoch": 4.329175152749491, "percentage": 86.58, "elapsed_time": "1:20:26", "remaining_time": "0:12:27", "throughput": 10150.49, "total_tokens": 48989696}
{"current_steps": 51020, "total_steps": 58920, "loss": 0.0, "lr": 1.0756702431761689e-07, "epoch": 4.3295994568906995, "percentage": 86.59, "elapsed_time": "1:20:26", "remaining_time": "0:12:27", "throughput": 10150.77, "total_tokens": 48995072}
{"current_steps": 51025, "total_steps": 58920, "loss": 0.0, "lr": 1.0743341485914914e-07, "epoch": 4.3300237610319074, "percentage": 86.6, "elapsed_time": "1:20:27", "remaining_time": "0:12:26", "throughput": 10150.89, "total_tokens": 48999488}
{"current_steps": 51030, "total_steps": 58920, "loss": 0.0, "lr": 1.0729988372017673e-07, "epoch": 4.330448065173116, "percentage": 86.61, "elapsed_time": "1:20:27", "remaining_time": "0:12:26", "throughput": 10151.1, "total_tokens": 49004352}
{"current_steps": 51035, "total_steps": 58920, "loss": 0.0, "lr": 1.0716643091241639e-07, "epoch": 4.330872369314324, "percentage": 86.62, "elapsed_time": "1:20:27", "remaining_time": "0:12:25", "throughput": 10151.23, "total_tokens": 49008768}
{"current_steps": 51040, "total_steps": 58920, "loss": 0.0, "lr": 1.0703305644757821e-07, "epoch": 4.331296673455533, "percentage": 86.63, "elapsed_time": "1:20:28", "remaining_time": "0:12:25", "throughput": 10151.37, "total_tokens": 49013248}
{"current_steps": 51045, "total_steps": 58920, "loss": 0.0, "lr": 1.0689976033736526e-07, "epoch": 4.331720977596741, "percentage": 86.63, "elapsed_time": "1:20:28", "remaining_time": "0:12:24", "throughput": 10151.49, "total_tokens": 49017600}
{"current_steps": 51050, "total_steps": 58920, "loss": 0.0921, "lr": 1.0676654259347373e-07, "epoch": 4.33214528173795, "percentage": 86.64, "elapsed_time": "1:20:28", "remaining_time": "0:12:24", "throughput": 10151.58, "total_tokens": 49021824}
{"current_steps": 51055, "total_steps": 58920, "loss": 0.0, "lr": 1.0663340322759318e-07, "epoch": 4.332569585879158, "percentage": 86.65, "elapsed_time": "1:20:29", "remaining_time": "0:12:23", "throughput": 10151.68, "total_tokens": 49026112}
{"current_steps": 51060, "total_steps": 58920, "loss": 0.0, "lr": 1.0650034225140603e-07, "epoch": 4.332993890020367, "percentage": 86.66, "elapsed_time": "1:20:29", "remaining_time": "0:12:23", "throughput": 10151.83, "total_tokens": 49030656}
{"current_steps": 51065, "total_steps": 58920, "loss": 0.0, "lr": 1.0636735967658784e-07, "epoch": 4.333418194161575, "percentage": 86.67, "elapsed_time": "1:20:30", "remaining_time": "0:12:22", "throughput": 10151.99, "total_tokens": 49035264}
{"current_steps": 51070, "total_steps": 58920, "loss": 0.0, "lr": 1.0623445551480736e-07, "epoch": 4.333842498302784, "percentage": 86.68, "elapsed_time": "1:20:30", "remaining_time": "0:12:22", "throughput": 10152.23, "total_tokens": 49040448}
{"current_steps": 51075, "total_steps": 58920, "loss": 0.0, "lr": 1.0610162977772652e-07, "epoch": 4.334266802443992, "percentage": 86.69, "elapsed_time": "1:20:30", "remaining_time": "0:12:22", "throughput": 10152.46, "total_tokens": 49045568}
{"current_steps": 51080, "total_steps": 58920, "loss": 0.0, "lr": 1.0596888247700031e-07, "epoch": 4.3346911065852005, "percentage": 86.69, "elapsed_time": "1:20:31", "remaining_time": "0:12:21", "throughput": 10152.71, "total_tokens": 49050752}
{"current_steps": 51085, "total_steps": 58920, "loss": 0.0, "lr": 1.0583621362427664e-07, "epoch": 4.3351154107264085, "percentage": 86.7, "elapsed_time": "1:20:31", "remaining_time": "0:12:21", "throughput": 10152.99, "total_tokens": 49056128}
{"current_steps": 51090, "total_steps": 58920, "loss": 0.0, "lr": 1.0570362323119697e-07, "epoch": 4.335539714867617, "percentage": 86.71, "elapsed_time": "1:20:32", "remaining_time": "0:12:20", "throughput": 10153.24, "total_tokens": 49061312}
{"current_steps": 51095, "total_steps": 58920, "loss": 0.0, "lr": 1.0557111130939523e-07, "epoch": 4.335964019008825, "percentage": 86.72, "elapsed_time": "1:20:32", "remaining_time": "0:12:20", "throughput": 10153.43, "total_tokens": 49066112}
{"current_steps": 51100, "total_steps": 58920, "loss": 0.0, "lr": 1.0543867787049965e-07, "epoch": 4.336388323150034, "percentage": 86.73, "elapsed_time": "1:20:32", "remaining_time": "0:12:19", "throughput": 10153.67, "total_tokens": 49071168}
{"current_steps": 51105, "total_steps": 58920, "loss": 0.0, "lr": 1.0530632292613007e-07, "epoch": 4.336812627291242, "percentage": 86.74, "elapsed_time": "1:20:33", "remaining_time": "0:12:19", "throughput": 10153.84, "total_tokens": 49075840}
{"current_steps": 51110, "total_steps": 58920, "loss": 0.0, "lr": 1.0517404648790029e-07, "epoch": 4.337236931432451, "percentage": 86.74, "elapsed_time": "1:20:33", "remaining_time": "0:12:18", "throughput": 10154.07, "total_tokens": 49080896}
{"current_steps": 51115, "total_steps": 58920, "loss": 0.0, "lr": 1.0504184856741727e-07, "epoch": 4.337661235573659, "percentage": 86.75, "elapsed_time": "1:20:33", "remaining_time": "0:12:18", "throughput": 10154.2, "total_tokens": 49085312}
{"current_steps": 51120, "total_steps": 58920, "loss": 0.0, "lr": 1.0490972917628049e-07, "epoch": 4.338085539714868, "percentage": 86.76, "elapsed_time": "1:20:34", "remaining_time": "0:12:17", "throughput": 10154.44, "total_tokens": 49090432}
{"current_steps": 51125, "total_steps": 58920, "loss": 0.0, "lr": 1.047776883260838e-07, "epoch": 4.338509843856076, "percentage": 86.77, "elapsed_time": "1:20:34", "remaining_time": "0:12:17", "throughput": 10154.65, "total_tokens": 49095360}
{"current_steps": 51130, "total_steps": 58920, "loss": 0.0, "lr": 1.0464572602841226e-07, "epoch": 4.338934147997285, "percentage": 86.78, "elapsed_time": "1:20:35", "remaining_time": "0:12:16", "throughput": 10154.89, "total_tokens": 49100480}
{"current_steps": 51135, "total_steps": 58920, "loss": 0.0, "lr": 1.0451384229484606e-07, "epoch": 4.339358452138493, "percentage": 86.79, "elapsed_time": "1:20:35", "remaining_time": "0:12:16", "throughput": 10155.15, "total_tokens": 49105728}
{"current_steps": 51140, "total_steps": 58920, "loss": 0.0, "lr": 1.0438203713695671e-07, "epoch": 4.339782756279702, "percentage": 86.8, "elapsed_time": "1:20:35", "remaining_time": "0:12:15", "throughput": 10155.31, "total_tokens": 49110336}
{"current_steps": 51145, "total_steps": 58920, "loss": 0.0, "lr": 1.0425031056631007e-07, "epoch": 4.3402070604209095, "percentage": 86.8, "elapsed_time": "1:20:36", "remaining_time": "0:12:15", "throughput": 10155.42, "total_tokens": 49114688}
{"current_steps": 51150, "total_steps": 58920, "loss": 0.0, "lr": 1.0411866259446489e-07, "epoch": 4.340631364562118, "percentage": 86.81, "elapsed_time": "1:20:36", "remaining_time": "0:12:14", "throughput": 10155.49, "total_tokens": 49118784}
{"current_steps": 51155, "total_steps": 58920, "loss": 0.0, "lr": 1.0398709323297205e-07, "epoch": 4.341055668703326, "percentage": 86.82, "elapsed_time": "1:20:37", "remaining_time": "0:12:14", "throughput": 10155.66, "total_tokens": 49123392}
{"current_steps": 51160, "total_steps": 58920, "loss": 0.0, "lr": 1.038556024933771e-07, "epoch": 4.341479972844535, "percentage": 86.83, "elapsed_time": "1:20:37", "remaining_time": "0:12:13", "throughput": 10155.86, "total_tokens": 49128256}
{"current_steps": 51165, "total_steps": 58920, "loss": 0.0, "lr": 1.0372419038721714e-07, "epoch": 4.341904276985743, "percentage": 86.84, "elapsed_time": "1:20:37", "remaining_time": "0:12:13", "throughput": 10156.07, "total_tokens": 49133120}
{"current_steps": 51170, "total_steps": 58920, "loss": 0.0, "lr": 1.0359285692602393e-07, "epoch": 4.342328581126952, "percentage": 86.85, "elapsed_time": "1:20:38", "remaining_time": "0:12:12", "throughput": 10156.2, "total_tokens": 49137536}
{"current_steps": 51175, "total_steps": 58920, "loss": 0.0, "lr": 1.034616021213206e-07, "epoch": 4.34275288526816, "percentage": 86.86, "elapsed_time": "1:20:38", "remaining_time": "0:12:12", "throughput": 10156.39, "total_tokens": 49142336}
{"current_steps": 51180, "total_steps": 58920, "loss": 0.0, "lr": 1.0333042598462493e-07, "epoch": 4.343177189409369, "percentage": 86.86, "elapsed_time": "1:20:38", "remaining_time": "0:12:11", "throughput": 10156.52, "total_tokens": 49146752}
{"current_steps": 51185, "total_steps": 58920, "loss": 0.0, "lr": 1.0319932852744728e-07, "epoch": 4.343601493550577, "percentage": 86.87, "elapsed_time": "1:20:39", "remaining_time": "0:12:11", "throughput": 10156.73, "total_tokens": 49151680}
{"current_steps": 51190, "total_steps": 58920, "loss": 0.0, "lr": 1.0306830976129011e-07, "epoch": 4.344025797691786, "percentage": 86.88, "elapsed_time": "1:20:39", "remaining_time": "0:12:10", "throughput": 10156.9, "total_tokens": 49156352}
{"current_steps": 51195, "total_steps": 58920, "loss": 0.0, "lr": 1.0293736969765088e-07, "epoch": 4.344450101832994, "percentage": 86.89, "elapsed_time": "1:20:40", "remaining_time": "0:12:10", "throughput": 10157.13, "total_tokens": 49161408}
{"current_steps": 51200, "total_steps": 58920, "loss": 0.0, "lr": 1.028065083480183e-07, "epoch": 4.344874405974203, "percentage": 86.9, "elapsed_time": "1:20:40", "remaining_time": "0:12:09", "throughput": 10157.55, "total_tokens": 49167680}
{"current_steps": 51205, "total_steps": 58920, "loss": 0.0, "lr": 1.026757257238754e-07, "epoch": 4.345298710115411, "percentage": 86.91, "elapsed_time": "1:20:40", "remaining_time": "0:12:09", "throughput": 10157.75, "total_tokens": 49172608}
{"current_steps": 51210, "total_steps": 58920, "loss": 0.0, "lr": 1.0254502183669777e-07, "epoch": 4.345723014256619, "percentage": 86.91, "elapsed_time": "1:20:41", "remaining_time": "0:12:08", "throughput": 10157.9, "total_tokens": 49177152}
{"current_steps": 51215, "total_steps": 58920, "loss": 0.0, "lr": 1.0241439669795438e-07, "epoch": 4.346147318397827, "percentage": 86.92, "elapsed_time": "1:20:41", "remaining_time": "0:12:08", "throughput": 10158.1, "total_tokens": 49182016}
{"current_steps": 51220, "total_steps": 58920, "loss": 0.0, "lr": 1.022838503191068e-07, "epoch": 4.346571622539036, "percentage": 86.93, "elapsed_time": "1:20:42", "remaining_time": "0:12:07", "throughput": 10158.29, "total_tokens": 49186752}
{"current_steps": 51225, "total_steps": 58920, "loss": 0.0368, "lr": 1.0215338271161023e-07, "epoch": 4.346995926680244, "percentage": 86.94, "elapsed_time": "1:20:42", "remaining_time": "0:12:07", "throughput": 10158.62, "total_tokens": 49192448}
{"current_steps": 51230, "total_steps": 58920, "loss": 0.0, "lr": 1.0202299388691272e-07, "epoch": 4.347420230821453, "percentage": 86.95, "elapsed_time": "1:20:42", "remaining_time": "0:12:06", "throughput": 10158.81, "total_tokens": 49197312}
{"current_steps": 51235, "total_steps": 58920, "loss": 0.0, "lr": 1.0189268385645522e-07, "epoch": 4.347844534962661, "percentage": 86.96, "elapsed_time": "1:20:43", "remaining_time": "0:12:06", "throughput": 10158.95, "total_tokens": 49201792}
{"current_steps": 51240, "total_steps": 58920, "loss": 0.0, "lr": 1.0176245263167227e-07, "epoch": 4.34826883910387, "percentage": 86.97, "elapsed_time": "1:20:43", "remaining_time": "0:12:05", "throughput": 10159.19, "total_tokens": 49206848}
{"current_steps": 51245, "total_steps": 58920, "loss": 0.0, "lr": 1.0163230022399094e-07, "epoch": 4.348693143245078, "percentage": 86.97, "elapsed_time": "1:20:43", "remaining_time": "0:12:05", "throughput": 10159.35, "total_tokens": 49211456}
{"current_steps": 51250, "total_steps": 58920, "loss": 0.0, "lr": 1.0150222664483165e-07, "epoch": 4.349117447386287, "percentage": 86.98, "elapsed_time": "1:20:44", "remaining_time": "0:12:04", "throughput": 10159.64, "total_tokens": 49216832}
{"current_steps": 51255, "total_steps": 58920, "loss": 0.0, "lr": 1.0137223190560806e-07, "epoch": 4.349541751527495, "percentage": 86.99, "elapsed_time": "1:20:44", "remaining_time": "0:12:04", "throughput": 10159.82, "total_tokens": 49221632}
{"current_steps": 51260, "total_steps": 58920, "loss": 0.0, "lr": 1.012423160177266e-07, "epoch": 4.349966055668704, "percentage": 87.0, "elapsed_time": "1:20:45", "remaining_time": "0:12:04", "throughput": 10159.93, "total_tokens": 49225920}
{"current_steps": 51265, "total_steps": 58920, "loss": 0.0, "lr": 1.0111247899258701e-07, "epoch": 4.350390359809912, "percentage": 87.01, "elapsed_time": "1:20:45", "remaining_time": "0:12:03", "throughput": 10160.1, "total_tokens": 49230656}
{"current_steps": 51270, "total_steps": 58920, "loss": 0.0, "lr": 1.0098272084158188e-07, "epoch": 4.3508146639511205, "percentage": 87.02, "elapsed_time": "1:20:45", "remaining_time": "0:12:03", "throughput": 10160.33, "total_tokens": 49235776}
{"current_steps": 51275, "total_steps": 58920, "loss": 0.0, "lr": 1.008530415760972e-07, "epoch": 4.3512389680923285, "percentage": 87.02, "elapsed_time": "1:20:46", "remaining_time": "0:12:02", "throughput": 10160.56, "total_tokens": 49240832}
{"current_steps": 51280, "total_steps": 58920, "loss": 0.0, "lr": 1.0072344120751175e-07, "epoch": 4.351663272233537, "percentage": 87.03, "elapsed_time": "1:20:46", "remaining_time": "0:12:02", "throughput": 10160.79, "total_tokens": 49245888}
{"current_steps": 51285, "total_steps": 58920, "loss": 0.0, "lr": 1.0059391974719744e-07, "epoch": 4.352087576374745, "percentage": 87.04, "elapsed_time": "1:20:47", "remaining_time": "0:12:01", "throughput": 10160.98, "total_tokens": 49250688}
{"current_steps": 51290, "total_steps": 58920, "loss": 0.0, "lr": 1.004644772065194e-07, "epoch": 4.352511880515954, "percentage": 87.05, "elapsed_time": "1:20:47", "remaining_time": "0:12:01", "throughput": 10161.29, "total_tokens": 49256320}
{"current_steps": 51295, "total_steps": 58920, "loss": 0.0, "lr": 1.0033511359683578e-07, "epoch": 4.352936184657162, "percentage": 87.06, "elapsed_time": "1:20:47", "remaining_time": "0:12:00", "throughput": 10161.48, "total_tokens": 49261120}
{"current_steps": 51300, "total_steps": 58920, "loss": 0.0, "lr": 1.002058289294977e-07, "epoch": 4.353360488798371, "percentage": 87.07, "elapsed_time": "1:20:48", "remaining_time": "0:12:00", "throughput": 10161.64, "total_tokens": 49265664}
{"current_steps": 51305, "total_steps": 58920, "loss": 0.0, "lr": 1.0007662321584942e-07, "epoch": 4.353784792939579, "percentage": 87.08, "elapsed_time": "1:20:48", "remaining_time": "0:11:59", "throughput": 10161.84, "total_tokens": 49270592}
{"current_steps": 51310, "total_steps": 58920, "loss": 0.0, "lr": 9.994749646722822e-08, "epoch": 4.354209097080788, "percentage": 87.08, "elapsed_time": "1:20:48", "remaining_time": "0:11:59", "throughput": 10161.99, "total_tokens": 49275200}
{"current_steps": 51315, "total_steps": 58920, "loss": 0.0088, "lr": 9.98184486949647e-08, "epoch": 4.354633401221996, "percentage": 87.09, "elapsed_time": "1:20:49", "remaining_time": "0:11:58", "throughput": 10162.25, "total_tokens": 49280384}
{"current_steps": 51320, "total_steps": 58920, "loss": 0.0, "lr": 9.968947991038212e-08, "epoch": 4.355057705363205, "percentage": 87.1, "elapsed_time": "1:20:49", "remaining_time": "0:11:58", "throughput": 10162.4, "total_tokens": 49284992}
{"current_steps": 51325, "total_steps": 58920, "loss": 0.0, "lr": 9.956059012479722e-08, "epoch": 4.355482009504413, "percentage": 87.11, "elapsed_time": "1:20:50", "remaining_time": "0:11:57", "throughput": 10162.57, "total_tokens": 49289664}
{"current_steps": 51330, "total_steps": 58920, "loss": 0.0, "lr": 9.94317793495194e-08, "epoch": 4.3559063136456215, "percentage": 87.12, "elapsed_time": "1:20:50", "remaining_time": "0:11:57", "throughput": 10162.78, "total_tokens": 49294592}
{"current_steps": 51335, "total_steps": 58920, "loss": 0.0, "lr": 9.93030475958514e-08, "epoch": 4.3563306177868295, "percentage": 87.13, "elapsed_time": "1:20:50", "remaining_time": "0:11:56", "throughput": 10163.05, "total_tokens": 49299904}
{"current_steps": 51340, "total_steps": 58920, "loss": 0.0, "lr": 9.917439487508927e-08, "epoch": 4.356754921928038, "percentage": 87.14, "elapsed_time": "1:20:51", "remaining_time": "0:11:56", "throughput": 10163.19, "total_tokens": 49304384}
{"current_steps": 51345, "total_steps": 58920, "loss": 0.0, "lr": 9.904582119852123e-08, "epoch": 4.357179226069246, "percentage": 87.14, "elapsed_time": "1:20:51", "remaining_time": "0:11:55", "throughput": 10163.29, "total_tokens": 49308672}
{"current_steps": 51350, "total_steps": 58920, "loss": 0.0, "lr": 9.891732657742991e-08, "epoch": 4.357603530210455, "percentage": 87.15, "elapsed_time": "1:20:52", "remaining_time": "0:11:55", "throughput": 10163.5, "total_tokens": 49313536}
{"current_steps": 51355, "total_steps": 58920, "loss": 0.0, "lr": 9.878891102308962e-08, "epoch": 4.358027834351663, "percentage": 87.16, "elapsed_time": "1:20:52", "remaining_time": "0:11:54", "throughput": 10163.72, "total_tokens": 49318528}
{"current_steps": 51360, "total_steps": 58920, "loss": 0.0, "lr": 9.866057454676847e-08, "epoch": 4.358452138492872, "percentage": 87.17, "elapsed_time": "1:20:52", "remaining_time": "0:11:54", "throughput": 10163.9, "total_tokens": 49323264}
{"current_steps": 51365, "total_steps": 58920, "loss": 0.0, "lr": 9.853231715972787e-08, "epoch": 4.35887644263408, "percentage": 87.18, "elapsed_time": "1:20:53", "remaining_time": "0:11:53", "throughput": 10164.07, "total_tokens": 49327936}
{"current_steps": 51370, "total_steps": 58920, "loss": 0.0, "lr": 9.840413887322142e-08, "epoch": 4.359300746775289, "percentage": 87.19, "elapsed_time": "1:20:53", "remaining_time": "0:11:53", "throughput": 10164.26, "total_tokens": 49332736}
{"current_steps": 51375, "total_steps": 58920, "loss": 0.0, "lr": 9.827603969849685e-08, "epoch": 4.359725050916497, "percentage": 87.19, "elapsed_time": "1:20:53", "remaining_time": "0:11:52", "throughput": 10164.39, "total_tokens": 49337152}
{"current_steps": 51380, "total_steps": 58920, "loss": 0.0, "lr": 9.814801964679387e-08, "epoch": 4.360149355057706, "percentage": 87.2, "elapsed_time": "1:20:54", "remaining_time": "0:11:52", "throughput": 10164.5, "total_tokens": 49341504}
{"current_steps": 51385, "total_steps": 58920, "loss": 0.0, "lr": 9.802007872934637e-08, "epoch": 4.360573659198914, "percentage": 87.21, "elapsed_time": "1:20:54", "remaining_time": "0:11:51", "throughput": 10164.69, "total_tokens": 49346240}
{"current_steps": 51390, "total_steps": 58920, "loss": 0.0, "lr": 9.789221695738004e-08, "epoch": 4.360997963340123, "percentage": 87.22, "elapsed_time": "1:20:55", "remaining_time": "0:11:51", "throughput": 10164.84, "total_tokens": 49350848}
{"current_steps": 51395, "total_steps": 58920, "loss": 0.0, "lr": 9.776443434211478e-08, "epoch": 4.3614222674813306, "percentage": 87.23, "elapsed_time": "1:20:55", "remaining_time": "0:11:50", "throughput": 10165.01, "total_tokens": 49355584}
{"current_steps": 51400, "total_steps": 58920, "loss": 0.0, "lr": 9.76367308947631e-08, "epoch": 4.361846571622539, "percentage": 87.24, "elapsed_time": "1:20:55", "remaining_time": "0:11:50", "throughput": 10165.2, "total_tokens": 49360384}
{"current_steps": 51405, "total_steps": 58920, "loss": 0.0, "lr": 9.750910662653e-08, "epoch": 4.362270875763747, "percentage": 87.25, "elapsed_time": "1:20:56", "remaining_time": "0:11:49", "throughput": 10165.34, "total_tokens": 49364864}
{"current_steps": 51410, "total_steps": 58920, "loss": 0.0, "lr": 9.738156154861465e-08, "epoch": 4.362695179904956, "percentage": 87.25, "elapsed_time": "1:20:56", "remaining_time": "0:11:49", "throughput": 10165.49, "total_tokens": 49369408}
{"current_steps": 51415, "total_steps": 58920, "loss": 0.0, "lr": 9.725409567220799e-08, "epoch": 4.363119484046164, "percentage": 87.26, "elapsed_time": "1:20:56", "remaining_time": "0:11:48", "throughput": 10165.69, "total_tokens": 49374272}
{"current_steps": 51420, "total_steps": 58920, "loss": 0.0, "lr": 9.712670900849529e-08, "epoch": 4.363543788187373, "percentage": 87.27, "elapsed_time": "1:20:57", "remaining_time": "0:11:48", "throughput": 10165.94, "total_tokens": 49379520}
{"current_steps": 51425, "total_steps": 58920, "loss": 0.0, "lr": 9.699940156865416e-08, "epoch": 4.363968092328581, "percentage": 87.28, "elapsed_time": "1:20:57", "remaining_time": "0:11:47", "throughput": 10166.2, "total_tokens": 49384768}
{"current_steps": 51430, "total_steps": 58920, "loss": 0.0, "lr": 9.687217336385511e-08, "epoch": 4.36439239646979, "percentage": 87.29, "elapsed_time": "1:20:58", "remaining_time": "0:11:47", "throughput": 10166.41, "total_tokens": 49389696}
{"current_steps": 51435, "total_steps": 58920, "loss": 0.0, "lr": 9.674502440526222e-08, "epoch": 4.364816700610998, "percentage": 87.3, "elapsed_time": "1:20:58", "remaining_time": "0:11:47", "throughput": 10166.58, "total_tokens": 49394368}
{"current_steps": 51440, "total_steps": 58920, "loss": 0.0, "lr": 9.661795470403222e-08, "epoch": 4.365241004752207, "percentage": 87.3, "elapsed_time": "1:20:58", "remaining_time": "0:11:46", "throughput": 10166.82, "total_tokens": 49399552}
{"current_steps": 51445, "total_steps": 58920, "loss": 0.0, "lr": 9.649096427131508e-08, "epoch": 4.365665308893415, "percentage": 87.31, "elapsed_time": "1:20:59", "remaining_time": "0:11:46", "throughput": 10167.1, "total_tokens": 49404864}
{"current_steps": 51450, "total_steps": 58920, "loss": 0.0, "lr": 9.636405311825368e-08, "epoch": 4.366089613034624, "percentage": 87.32, "elapsed_time": "1:20:59", "remaining_time": "0:11:45", "throughput": 10167.3, "total_tokens": 49409792}
{"current_steps": 51455, "total_steps": 58920, "loss": 0.0, "lr": 9.62372212559841e-08, "epoch": 4.366513917175832, "percentage": 87.33, "elapsed_time": "1:21:00", "remaining_time": "0:11:45", "throughput": 10167.5, "total_tokens": 49414656}
{"current_steps": 51460, "total_steps": 58920, "loss": 0.0, "lr": 9.611046869563533e-08, "epoch": 4.3669382213170405, "percentage": 87.34, "elapsed_time": "1:21:00", "remaining_time": "0:11:44", "throughput": 10167.62, "total_tokens": 49419008}
{"current_steps": 51465, "total_steps": 58920, "loss": 0.0, "lr": 9.598379544832946e-08, "epoch": 4.367362525458248, "percentage": 87.35, "elapsed_time": "1:21:00", "remaining_time": "0:11:44", "throughput": 10167.82, "total_tokens": 49423936}
{"current_steps": 51470, "total_steps": 58920, "loss": 0.0, "lr": 9.585720152518151e-08, "epoch": 4.367786829599457, "percentage": 87.36, "elapsed_time": "1:21:01", "remaining_time": "0:11:43", "throughput": 10167.93, "total_tokens": 49428224}
{"current_steps": 51475, "total_steps": 58920, "loss": 0.0, "lr": 9.57306869372998e-08, "epoch": 4.368211133740665, "percentage": 87.36, "elapsed_time": "1:21:01", "remaining_time": "0:11:43", "throughput": 10168.09, "total_tokens": 49432896}
{"current_steps": 51480, "total_steps": 58920, "loss": 0.0, "lr": 9.560425169578546e-08, "epoch": 4.368635437881874, "percentage": 87.37, "elapsed_time": "1:21:01", "remaining_time": "0:11:42", "throughput": 10168.31, "total_tokens": 49437888}
{"current_steps": 51485, "total_steps": 58920, "loss": 0.0, "lr": 9.547789581173271e-08, "epoch": 4.369059742023082, "percentage": 87.38, "elapsed_time": "1:21:02", "remaining_time": "0:11:42", "throughput": 10168.46, "total_tokens": 49442432}
{"current_steps": 51490, "total_steps": 58920, "loss": 0.0, "lr": 9.535161929622893e-08, "epoch": 4.36948404616429, "percentage": 87.39, "elapsed_time": "1:21:02", "remaining_time": "0:11:41", "throughput": 10168.71, "total_tokens": 49447552}
{"current_steps": 51495, "total_steps": 58920, "loss": 0.0, "lr": 9.522542216035423e-08, "epoch": 4.369908350305499, "percentage": 87.4, "elapsed_time": "1:21:03", "remaining_time": "0:11:41", "throughput": 10169.07, "total_tokens": 49453568}
{"current_steps": 51500, "total_steps": 58920, "loss": 0.0, "lr": 9.509930441518211e-08, "epoch": 4.370332654446708, "percentage": 87.41, "elapsed_time": "1:21:03", "remaining_time": "0:11:40", "throughput": 10169.25, "total_tokens": 49458304}
{"current_steps": 51505, "total_steps": 58920, "loss": 0.0, "lr": 9.49732660717788e-08, "epoch": 4.370756958587916, "percentage": 87.42, "elapsed_time": "1:21:03", "remaining_time": "0:11:40", "throughput": 10169.37, "total_tokens": 49462656}
{"current_steps": 51510, "total_steps": 58920, "loss": 0.0, "lr": 9.484730714120393e-08, "epoch": 4.371181262729124, "percentage": 87.42, "elapsed_time": "1:21:04", "remaining_time": "0:11:39", "throughput": 10169.68, "total_tokens": 49468288}
{"current_steps": 51515, "total_steps": 58920, "loss": 0.0, "lr": 9.472142763450974e-08, "epoch": 4.371605566870333, "percentage": 87.43, "elapsed_time": "1:21:04", "remaining_time": "0:11:39", "throughput": 10169.79, "total_tokens": 49472576}
{"current_steps": 51520, "total_steps": 58920, "loss": 0.0, "lr": 9.459562756274175e-08, "epoch": 4.3720298710115415, "percentage": 87.44, "elapsed_time": "1:21:05", "remaining_time": "0:11:38", "throughput": 10170.04, "total_tokens": 49477760}
{"current_steps": 51525, "total_steps": 58920, "loss": 0.0, "lr": 9.446990693693857e-08, "epoch": 4.3724541751527495, "percentage": 87.45, "elapsed_time": "1:21:05", "remaining_time": "0:11:38", "throughput": 10170.21, "total_tokens": 49482432}
{"current_steps": 51530, "total_steps": 58920, "loss": 0.0, "lr": 9.434426576813159e-08, "epoch": 4.3728784792939575, "percentage": 87.46, "elapsed_time": "1:21:05", "remaining_time": "0:11:37", "throughput": 10170.48, "total_tokens": 49487744}
{"current_steps": 51535, "total_steps": 58920, "loss": 0.0, "lr": 9.421870406734555e-08, "epoch": 4.373302783435166, "percentage": 87.47, "elapsed_time": "1:21:06", "remaining_time": "0:11:37", "throughput": 10170.64, "total_tokens": 49492352}
{"current_steps": 51540, "total_steps": 58920, "loss": 0.0, "lr": 9.409322184559776e-08, "epoch": 4.373727087576375, "percentage": 87.47, "elapsed_time": "1:21:06", "remaining_time": "0:11:36", "throughput": 10170.8, "total_tokens": 49496960}
{"current_steps": 51545, "total_steps": 58920, "loss": 0.0, "lr": 9.396781911389905e-08, "epoch": 4.374151391717583, "percentage": 87.48, "elapsed_time": "1:21:06", "remaining_time": "0:11:36", "throughput": 10171.06, "total_tokens": 49502272}
{"current_steps": 51550, "total_steps": 58920, "loss": 0.0, "lr": 9.384249588325288e-08, "epoch": 4.374575695858791, "percentage": 87.49, "elapsed_time": "1:21:07", "remaining_time": "0:11:35", "throughput": 10171.22, "total_tokens": 49506944}
{"current_steps": 51555, "total_steps": 58920, "loss": 0.0, "lr": 9.371725216465632e-08, "epoch": 4.375, "percentage": 87.5, "elapsed_time": "1:21:07", "remaining_time": "0:11:35", "throughput": 10171.53, "total_tokens": 49512512}
{"current_steps": 51560, "total_steps": 58920, "loss": 0.0, "lr": 9.359208796909845e-08, "epoch": 4.375424304141209, "percentage": 87.51, "elapsed_time": "1:21:08", "remaining_time": "0:11:34", "throughput": 10171.75, "total_tokens": 49517504}
{"current_steps": 51565, "total_steps": 58920, "loss": 0.0, "lr": 9.346700330756264e-08, "epoch": 4.375848608282417, "percentage": 87.52, "elapsed_time": "1:21:08", "remaining_time": "0:11:34", "throughput": 10171.91, "total_tokens": 49522112}
{"current_steps": 51570, "total_steps": 58920, "loss": 0.0, "lr": 9.334199819102406e-08, "epoch": 4.376272912423625, "percentage": 87.53, "elapsed_time": "1:21:08", "remaining_time": "0:11:33", "throughput": 10172.08, "total_tokens": 49526784}
{"current_steps": 51575, "total_steps": 58920, "loss": 0.0, "lr": 9.321707263045142e-08, "epoch": 4.376697216564834, "percentage": 87.53, "elapsed_time": "1:21:09", "remaining_time": "0:11:33", "throughput": 10172.25, "total_tokens": 49531520}
{"current_steps": 51580, "total_steps": 58920, "loss": 0.0, "lr": 9.309222663680716e-08, "epoch": 4.3771215207060425, "percentage": 87.54, "elapsed_time": "1:21:09", "remaining_time": "0:11:32", "throughput": 10172.41, "total_tokens": 49536192}
{"current_steps": 51585, "total_steps": 58920, "loss": 0.0, "lr": 9.29674602210453e-08, "epoch": 4.3775458248472505, "percentage": 87.55, "elapsed_time": "1:21:10", "remaining_time": "0:11:32", "throughput": 10172.65, "total_tokens": 49541312}
{"current_steps": 51590, "total_steps": 58920, "loss": 0.0, "lr": 9.284277339411428e-08, "epoch": 4.3779701289884585, "percentage": 87.56, "elapsed_time": "1:21:10", "remaining_time": "0:11:32", "throughput": 10172.88, "total_tokens": 49546368}
{"current_steps": 51595, "total_steps": 58920, "loss": 0.0, "lr": 9.271816616695438e-08, "epoch": 4.378394433129667, "percentage": 87.57, "elapsed_time": "1:21:10", "remaining_time": "0:11:31", "throughput": 10173.09, "total_tokens": 49551296}
{"current_steps": 51600, "total_steps": 58920, "loss": 0.0, "lr": 9.259363855049984e-08, "epoch": 4.378818737270876, "percentage": 87.58, "elapsed_time": "1:21:11", "remaining_time": "0:11:31", "throughput": 10173.2, "total_tokens": 49555648}
{"current_steps": 51605, "total_steps": 58920, "loss": 0.0, "lr": 9.246919055567726e-08, "epoch": 4.379243041412084, "percentage": 87.58, "elapsed_time": "1:21:11", "remaining_time": "0:11:30", "throughput": 10173.28, "total_tokens": 49559808}
{"current_steps": 51610, "total_steps": 58920, "loss": 0.0, "lr": 9.234482219340645e-08, "epoch": 4.379667345553292, "percentage": 87.59, "elapsed_time": "1:21:11", "remaining_time": "0:11:30", "throughput": 10173.44, "total_tokens": 49564416}
{"current_steps": 51615, "total_steps": 58920, "loss": 0.0, "lr": 9.222053347460068e-08, "epoch": 4.380091649694501, "percentage": 87.6, "elapsed_time": "1:21:12", "remaining_time": "0:11:29", "throughput": 10173.63, "total_tokens": 49569216}
{"current_steps": 51620, "total_steps": 58920, "loss": 0.0, "lr": 9.209632441016535e-08, "epoch": 4.38051595383571, "percentage": 87.61, "elapsed_time": "1:21:12", "remaining_time": "0:11:29", "throughput": 10173.78, "total_tokens": 49573760}
{"current_steps": 51625, "total_steps": 58920, "loss": 0.0, "lr": 9.197219501099984e-08, "epoch": 4.380940257976918, "percentage": 87.62, "elapsed_time": "1:21:13", "remaining_time": "0:11:28", "throughput": 10173.97, "total_tokens": 49578560}
{"current_steps": 51630, "total_steps": 58920, "loss": 0.0, "lr": 9.184814528799545e-08, "epoch": 4.381364562118126, "percentage": 87.63, "elapsed_time": "1:21:13", "remaining_time": "0:11:28", "throughput": 10174.05, "total_tokens": 49582720}
{"current_steps": 51635, "total_steps": 58920, "loss": 0.0, "lr": 9.172417525203757e-08, "epoch": 4.381788866259335, "percentage": 87.64, "elapsed_time": "1:21:13", "remaining_time": "0:11:27", "throughput": 10174.16, "total_tokens": 49587072}
{"current_steps": 51640, "total_steps": 58920, "loss": 0.0, "lr": 9.160028491400407e-08, "epoch": 4.382213170400543, "percentage": 87.64, "elapsed_time": "1:21:14", "remaining_time": "0:11:27", "throughput": 10174.37, "total_tokens": 49592000}
{"current_steps": 51645, "total_steps": 58920, "loss": 0.0, "lr": 9.14764742847658e-08, "epoch": 4.382637474541752, "percentage": 87.65, "elapsed_time": "1:21:14", "remaining_time": "0:11:26", "throughput": 10174.55, "total_tokens": 49596736}
{"current_steps": 51650, "total_steps": 58920, "loss": 0.0, "lr": 9.135274337518683e-08, "epoch": 4.3830617786829595, "percentage": 87.66, "elapsed_time": "1:21:14", "remaining_time": "0:11:26", "throughput": 10174.72, "total_tokens": 49601408}
{"current_steps": 51655, "total_steps": 58920, "loss": 0.0, "lr": 9.122909219612363e-08, "epoch": 4.383486082824168, "percentage": 87.67, "elapsed_time": "1:21:15", "remaining_time": "0:11:25", "throughput": 10174.85, "total_tokens": 49605824}
{"current_steps": 51660, "total_steps": 58920, "loss": 0.0, "lr": 9.110552075842682e-08, "epoch": 4.383910386965376, "percentage": 87.68, "elapsed_time": "1:21:15", "remaining_time": "0:11:25", "throughput": 10175.06, "total_tokens": 49610752}
{"current_steps": 51665, "total_steps": 58920, "loss": 0.0, "lr": 9.098202907293872e-08, "epoch": 4.384334691106585, "percentage": 87.69, "elapsed_time": "1:21:16", "remaining_time": "0:11:24", "throughput": 10175.15, "total_tokens": 49614976}
{"current_steps": 51670, "total_steps": 58920, "loss": 0.0, "lr": 9.08586171504957e-08, "epoch": 4.384758995247793, "percentage": 87.7, "elapsed_time": "1:21:16", "remaining_time": "0:11:24", "throughput": 10175.26, "total_tokens": 49619328}
{"current_steps": 51675, "total_steps": 58920, "loss": 0.0329, "lr": 9.073528500192662e-08, "epoch": 4.385183299389002, "percentage": 87.7, "elapsed_time": "1:21:16", "remaining_time": "0:11:23", "throughput": 10175.37, "total_tokens": 49623680}
{"current_steps": 51680, "total_steps": 58920, "loss": 0.0, "lr": 9.061203263805339e-08, "epoch": 4.38560760353021, "percentage": 87.71, "elapsed_time": "1:21:17", "remaining_time": "0:11:23", "throughput": 10175.5, "total_tokens": 49628096}
{"current_steps": 51685, "total_steps": 58920, "loss": 0.0, "lr": 9.048886006969093e-08, "epoch": 4.386031907671419, "percentage": 87.72, "elapsed_time": "1:21:17", "remaining_time": "0:11:22", "throughput": 10175.65, "total_tokens": 49632640}
{"current_steps": 51690, "total_steps": 58920, "loss": 0.0, "lr": 9.036576730764723e-08, "epoch": 4.386456211812627, "percentage": 87.73, "elapsed_time": "1:21:17", "remaining_time": "0:11:22", "throughput": 10175.81, "total_tokens": 49637248}
{"current_steps": 51695, "total_steps": 58920, "loss": 0.0, "lr": 9.024275436272322e-08, "epoch": 4.386880515953836, "percentage": 87.74, "elapsed_time": "1:21:18", "remaining_time": "0:11:21", "throughput": 10176.03, "total_tokens": 49642176}
{"current_steps": 51700, "total_steps": 58920, "loss": 0.0, "lr": 9.011982124571293e-08, "epoch": 4.387304820095044, "percentage": 87.75, "elapsed_time": "1:21:18", "remaining_time": "0:11:21", "throughput": 10176.15, "total_tokens": 49646656}
{"current_steps": 51705, "total_steps": 58920, "loss": 0.0, "lr": 8.999696796740309e-08, "epoch": 4.387729124236253, "percentage": 87.75, "elapsed_time": "1:21:19", "remaining_time": "0:11:20", "throughput": 10176.27, "total_tokens": 49651072}
{"current_steps": 51710, "total_steps": 58920, "loss": 0.0, "lr": 8.98741945385738e-08, "epoch": 4.388153428377461, "percentage": 87.76, "elapsed_time": "1:21:19", "remaining_time": "0:11:20", "throughput": 10176.49, "total_tokens": 49656064}
{"current_steps": 51715, "total_steps": 58920, "loss": 0.0, "lr": 8.975150096999795e-08, "epoch": 4.3885777325186694, "percentage": 87.77, "elapsed_time": "1:21:19", "remaining_time": "0:11:19", "throughput": 10176.7, "total_tokens": 49660992}
{"current_steps": 51720, "total_steps": 58920, "loss": 0.0, "lr": 8.962888727244156e-08, "epoch": 4.389002036659877, "percentage": 87.78, "elapsed_time": "1:21:20", "remaining_time": "0:11:19", "throughput": 10176.85, "total_tokens": 49665600}
{"current_steps": 51725, "total_steps": 58920, "loss": 0.0001, "lr": 8.950635345666325e-08, "epoch": 4.389426340801086, "percentage": 87.79, "elapsed_time": "1:21:20", "remaining_time": "0:11:18", "throughput": 10176.98, "total_tokens": 49670080}
{"current_steps": 51730, "total_steps": 58920, "loss": 0.0, "lr": 8.938389953341518e-08, "epoch": 4.389850644942294, "percentage": 87.8, "elapsed_time": "1:21:21", "remaining_time": "0:11:18", "throughput": 10177.18, "total_tokens": 49675008}
{"current_steps": 51735, "total_steps": 58920, "loss": 0.0, "lr": 8.926152551344224e-08, "epoch": 4.390274949083503, "percentage": 87.81, "elapsed_time": "1:21:21", "remaining_time": "0:11:17", "throughput": 10177.39, "total_tokens": 49680064}
{"current_steps": 51740, "total_steps": 58920, "loss": 0.0, "lr": 8.913923140748215e-08, "epoch": 4.390699253224711, "percentage": 87.81, "elapsed_time": "1:21:21", "remaining_time": "0:11:17", "throughput": 10177.49, "total_tokens": 49684352}
{"current_steps": 51745, "total_steps": 58920, "loss": 0.0, "lr": 8.901701722626586e-08, "epoch": 4.39112355736592, "percentage": 87.82, "elapsed_time": "1:21:22", "remaining_time": "0:11:16", "throughput": 10177.6, "total_tokens": 49688704}
{"current_steps": 51750, "total_steps": 58920, "loss": 0.0, "lr": 8.889488298051717e-08, "epoch": 4.391547861507128, "percentage": 87.83, "elapsed_time": "1:21:22", "remaining_time": "0:11:16", "throughput": 10177.74, "total_tokens": 49693184}
{"current_steps": 51755, "total_steps": 58920, "loss": 0.0, "lr": 8.877282868095304e-08, "epoch": 4.391972165648337, "percentage": 87.84, "elapsed_time": "1:21:22", "remaining_time": "0:11:15", "throughput": 10177.9, "total_tokens": 49697856}
{"current_steps": 51760, "total_steps": 58920, "loss": 0.0, "lr": 8.865085433828323e-08, "epoch": 4.392396469789545, "percentage": 87.85, "elapsed_time": "1:21:23", "remaining_time": "0:11:15", "throughput": 10178.11, "total_tokens": 49702784}
{"current_steps": 51765, "total_steps": 58920, "loss": 0.0, "lr": 8.85289599632103e-08, "epoch": 4.392820773930754, "percentage": 87.86, "elapsed_time": "1:21:23", "remaining_time": "0:11:15", "throughput": 10178.24, "total_tokens": 49707264}
{"current_steps": 51770, "total_steps": 58920, "loss": 0.0, "lr": 8.840714556643059e-08, "epoch": 4.393245078071962, "percentage": 87.86, "elapsed_time": "1:21:24", "remaining_time": "0:11:14", "throughput": 10178.49, "total_tokens": 49712512}
{"current_steps": 51775, "total_steps": 58920, "loss": 0.0, "lr": 8.828541115863252e-08, "epoch": 4.3936693822131705, "percentage": 87.87, "elapsed_time": "1:21:24", "remaining_time": "0:11:14", "throughput": 10178.75, "total_tokens": 49717824}
{"current_steps": 51780, "total_steps": 58920, "loss": 0.0, "lr": 8.81637567504978e-08, "epoch": 4.3940936863543785, "percentage": 87.88, "elapsed_time": "1:21:24", "remaining_time": "0:11:13", "throughput": 10178.93, "total_tokens": 49722560}
{"current_steps": 51785, "total_steps": 58920, "loss": 0.0, "lr": 8.804218235270133e-08, "epoch": 4.394517990495587, "percentage": 87.89, "elapsed_time": "1:21:25", "remaining_time": "0:11:13", "throughput": 10179.08, "total_tokens": 49727168}
{"current_steps": 51790, "total_steps": 58920, "loss": 0.0, "lr": 8.792068797591068e-08, "epoch": 4.394942294636795, "percentage": 87.9, "elapsed_time": "1:21:25", "remaining_time": "0:11:12", "throughput": 10179.25, "total_tokens": 49731840}
{"current_steps": 51795, "total_steps": 58920, "loss": 0.0, "lr": 8.779927363078654e-08, "epoch": 4.395366598778004, "percentage": 87.91, "elapsed_time": "1:21:25", "remaining_time": "0:11:12", "throughput": 10179.44, "total_tokens": 49736704}
{"current_steps": 51800, "total_steps": 58920, "loss": 0.0, "lr": 8.767793932798262e-08, "epoch": 4.395790902919212, "percentage": 87.92, "elapsed_time": "1:21:26", "remaining_time": "0:11:11", "throughput": 10179.6, "total_tokens": 49741312}
{"current_steps": 51805, "total_steps": 58920, "loss": 0.0, "lr": 8.755668507814585e-08, "epoch": 4.396215207060421, "percentage": 87.92, "elapsed_time": "1:21:26", "remaining_time": "0:11:11", "throughput": 10179.77, "total_tokens": 49745984}
{"current_steps": 51810, "total_steps": 58920, "loss": 0.0, "lr": 8.743551089191537e-08, "epoch": 4.396639511201629, "percentage": 87.93, "elapsed_time": "1:21:27", "remaining_time": "0:11:10", "throughput": 10180.01, "total_tokens": 49751168}
{"current_steps": 51815, "total_steps": 58920, "loss": 0.0, "lr": 8.731441677992424e-08, "epoch": 4.397063815342838, "percentage": 87.94, "elapsed_time": "1:21:27", "remaining_time": "0:11:10", "throughput": 10180.19, "total_tokens": 49755968}
{"current_steps": 51820, "total_steps": 58920, "loss": 0.0, "lr": 8.719340275279763e-08, "epoch": 4.397488119484046, "percentage": 87.95, "elapsed_time": "1:21:27", "remaining_time": "0:11:09", "throughput": 10180.46, "total_tokens": 49761344}
{"current_steps": 51825, "total_steps": 58920, "loss": 0.0, "lr": 8.707246882115415e-08, "epoch": 4.397912423625255, "percentage": 87.96, "elapsed_time": "1:21:28", "remaining_time": "0:11:09", "throughput": 10180.6, "total_tokens": 49765824}
{"current_steps": 51830, "total_steps": 58920, "loss": 0.0, "lr": 8.695161499560566e-08, "epoch": 4.398336727766463, "percentage": 87.97, "elapsed_time": "1:21:28", "remaining_time": "0:11:08", "throughput": 10180.79, "total_tokens": 49770688}
{"current_steps": 51835, "total_steps": 58920, "loss": 0.0, "lr": 8.683084128675621e-08, "epoch": 4.3987610319076715, "percentage": 87.98, "elapsed_time": "1:21:29", "remaining_time": "0:11:08", "throughput": 10180.97, "total_tokens": 49775424}
{"current_steps": 51840, "total_steps": 58920, "loss": 0.0, "lr": 8.671014770520369e-08, "epoch": 4.3991853360488795, "percentage": 87.98, "elapsed_time": "1:21:29", "remaining_time": "0:11:07", "throughput": 10181.15, "total_tokens": 49780224}
{"current_steps": 51845, "total_steps": 58920, "loss": 0.0, "lr": 8.658953426153793e-08, "epoch": 4.399609640190088, "percentage": 87.99, "elapsed_time": "1:21:29", "remaining_time": "0:11:07", "throughput": 10181.36, "total_tokens": 49785152}
{"current_steps": 51850, "total_steps": 58920, "loss": 0.0, "lr": 8.64690009663429e-08, "epoch": 4.400033944331296, "percentage": 88.0, "elapsed_time": "1:21:30", "remaining_time": "0:11:06", "throughput": 10181.56, "total_tokens": 49790080}
{"current_steps": 51855, "total_steps": 58920, "loss": 0.0, "lr": 8.634854783019496e-08, "epoch": 4.400458248472505, "percentage": 88.01, "elapsed_time": "1:21:30", "remaining_time": "0:11:06", "throughput": 10181.68, "total_tokens": 49794432}
{"current_steps": 51860, "total_steps": 58920, "loss": 0.0, "lr": 8.622817486366286e-08, "epoch": 4.400882552613713, "percentage": 88.02, "elapsed_time": "1:21:30", "remaining_time": "0:11:05", "throughput": 10181.87, "total_tokens": 49799296}
{"current_steps": 51865, "total_steps": 58920, "loss": 0.0, "lr": 8.610788207730957e-08, "epoch": 4.401306856754922, "percentage": 88.03, "elapsed_time": "1:21:31", "remaining_time": "0:11:05", "throughput": 10182.1, "total_tokens": 49804416}
{"current_steps": 51870, "total_steps": 58920, "loss": 0.0, "lr": 8.598766948168967e-08, "epoch": 4.40173116089613, "percentage": 88.03, "elapsed_time": "1:21:31", "remaining_time": "0:11:04", "throughput": 10182.35, "total_tokens": 49809600}
{"current_steps": 51875, "total_steps": 58920, "loss": 0.0, "lr": 8.586753708735206e-08, "epoch": 4.402155465037339, "percentage": 88.04, "elapsed_time": "1:21:32", "remaining_time": "0:11:04", "throughput": 10182.48, "total_tokens": 49814080}
{"current_steps": 51880, "total_steps": 58920, "loss": 0.0, "lr": 8.57474849048373e-08, "epoch": 4.402579769178547, "percentage": 88.05, "elapsed_time": "1:21:32", "remaining_time": "0:11:03", "throughput": 10182.64, "total_tokens": 49818688}
{"current_steps": 51885, "total_steps": 58920, "loss": 0.0, "lr": 8.562751294468006e-08, "epoch": 4.403004073319756, "percentage": 88.06, "elapsed_time": "1:21:32", "remaining_time": "0:11:03", "throughput": 10182.76, "total_tokens": 49823104}
{"current_steps": 51890, "total_steps": 58920, "loss": 0.0, "lr": 8.550762121740718e-08, "epoch": 4.403428377460964, "percentage": 88.07, "elapsed_time": "1:21:33", "remaining_time": "0:11:02", "throughput": 10182.95, "total_tokens": 49827968}
{"current_steps": 51895, "total_steps": 58920, "loss": 0.0, "lr": 8.538780973353888e-08, "epoch": 4.403852681602173, "percentage": 88.08, "elapsed_time": "1:21:33", "remaining_time": "0:11:02", "throughput": 10183.13, "total_tokens": 49832704}
{"current_steps": 51900, "total_steps": 58920, "loss": 0.0, "lr": 8.526807850358808e-08, "epoch": 4.404276985743381, "percentage": 88.09, "elapsed_time": "1:21:34", "remaining_time": "0:11:01", "throughput": 10183.24, "total_tokens": 49837056}
{"current_steps": 51905, "total_steps": 58920, "loss": 0.0, "lr": 8.51484275380605e-08, "epoch": 4.404701289884589, "percentage": 88.09, "elapsed_time": "1:21:34", "remaining_time": "0:11:01", "throughput": 10183.36, "total_tokens": 49841472}
{"current_steps": 51910, "total_steps": 58920, "loss": 0.0, "lr": 8.502885684745553e-08, "epoch": 4.405125594025797, "percentage": 88.1, "elapsed_time": "1:21:34", "remaining_time": "0:11:00", "throughput": 10183.62, "total_tokens": 49846656}
{"current_steps": 51915, "total_steps": 58920, "loss": 0.0, "lr": 8.490936644226487e-08, "epoch": 4.405549898167006, "percentage": 88.11, "elapsed_time": "1:21:35", "remaining_time": "0:11:00", "throughput": 10183.82, "total_tokens": 49851584}
{"current_steps": 51920, "total_steps": 58920, "loss": 0.0, "lr": 8.478995633297348e-08, "epoch": 4.405974202308214, "percentage": 88.12, "elapsed_time": "1:21:35", "remaining_time": "0:11:00", "throughput": 10184.02, "total_tokens": 49856448}
{"current_steps": 51925, "total_steps": 58920, "loss": 0.0, "lr": 8.467062653005896e-08, "epoch": 4.406398506449423, "percentage": 88.13, "elapsed_time": "1:21:35", "remaining_time": "0:10:59", "throughput": 10184.16, "total_tokens": 49860928}
{"current_steps": 51930, "total_steps": 58920, "loss": 0.0, "lr": 8.455137704399218e-08, "epoch": 4.406822810590631, "percentage": 88.14, "elapsed_time": "1:21:36", "remaining_time": "0:10:59", "throughput": 10184.29, "total_tokens": 49865344}
{"current_steps": 51935, "total_steps": 58920, "loss": 0.0, "lr": 8.443220788523687e-08, "epoch": 4.40724711473184, "percentage": 88.14, "elapsed_time": "1:21:36", "remaining_time": "0:10:58", "throughput": 10184.52, "total_tokens": 49870400}
{"current_steps": 51940, "total_steps": 58920, "loss": 0.0, "lr": 8.431311906424965e-08, "epoch": 4.407671418873048, "percentage": 88.15, "elapsed_time": "1:21:37", "remaining_time": "0:10:58", "throughput": 10184.73, "total_tokens": 49875392}
{"current_steps": 51945, "total_steps": 58920, "loss": 0.0, "lr": 8.419411059148018e-08, "epoch": 4.408095723014257, "percentage": 88.16, "elapsed_time": "1:21:37", "remaining_time": "0:10:57", "throughput": 10184.88, "total_tokens": 49879936}
{"current_steps": 51950, "total_steps": 58920, "loss": 0.0, "lr": 8.4075182477371e-08, "epoch": 4.408520027155465, "percentage": 88.17, "elapsed_time": "1:21:37", "remaining_time": "0:10:57", "throughput": 10185.16, "total_tokens": 49885376}
{"current_steps": 51955, "total_steps": 58920, "loss": 0.0002, "lr": 8.395633473235764e-08, "epoch": 4.408944331296674, "percentage": 88.18, "elapsed_time": "1:21:38", "remaining_time": "0:10:56", "throughput": 10185.31, "total_tokens": 49889984}
{"current_steps": 51960, "total_steps": 58920, "loss": 0.0, "lr": 8.383756736686853e-08, "epoch": 4.409368635437882, "percentage": 88.19, "elapsed_time": "1:21:38", "remaining_time": "0:10:56", "throughput": 10185.52, "total_tokens": 49894912}
{"current_steps": 51965, "total_steps": 58920, "loss": 0.0, "lr": 8.371888039132513e-08, "epoch": 4.4097929395790905, "percentage": 88.2, "elapsed_time": "1:21:38", "remaining_time": "0:10:55", "throughput": 10185.63, "total_tokens": 49899264}
{"current_steps": 51970, "total_steps": 58920, "loss": 0.0, "lr": 8.360027381614177e-08, "epoch": 4.410217243720298, "percentage": 88.2, "elapsed_time": "1:21:39", "remaining_time": "0:10:55", "throughput": 10185.76, "total_tokens": 49903680}
{"current_steps": 51975, "total_steps": 58920, "loss": 0.0, "lr": 8.348174765172567e-08, "epoch": 4.410641547861507, "percentage": 88.21, "elapsed_time": "1:21:39", "remaining_time": "0:10:54", "throughput": 10185.9, "total_tokens": 49908224}
{"current_steps": 51980, "total_steps": 58920, "loss": 0.0, "lr": 8.336330190847707e-08, "epoch": 4.411065852002715, "percentage": 88.22, "elapsed_time": "1:21:40", "remaining_time": "0:10:54", "throughput": 10186.08, "total_tokens": 49912960}
{"current_steps": 51985, "total_steps": 58920, "loss": 0.0, "lr": 8.324493659678933e-08, "epoch": 4.411490156143924, "percentage": 88.23, "elapsed_time": "1:21:40", "remaining_time": "0:10:53", "throughput": 10186.17, "total_tokens": 49917184}
{"current_steps": 51990, "total_steps": 58920, "loss": 0.0, "lr": 8.312665172704847e-08, "epoch": 4.411914460285132, "percentage": 88.24, "elapsed_time": "1:21:40", "remaining_time": "0:10:53", "throughput": 10186.37, "total_tokens": 49922048}
{"current_steps": 51995, "total_steps": 58920, "loss": 0.0, "lr": 8.300844730963352e-08, "epoch": 4.412338764426341, "percentage": 88.25, "elapsed_time": "1:21:41", "remaining_time": "0:10:52", "throughput": 10186.52, "total_tokens": 49926656}
{"current_steps": 52000, "total_steps": 58920, "loss": 0.0, "lr": 8.289032335491652e-08, "epoch": 4.412763068567549, "percentage": 88.26, "elapsed_time": "1:21:41", "remaining_time": "0:10:52", "throughput": 10186.62, "total_tokens": 49930944}
{"current_steps": 52005, "total_steps": 58920, "loss": 0.0, "lr": 8.277227987326251e-08, "epoch": 4.413187372708758, "percentage": 88.26, "elapsed_time": "1:21:41", "remaining_time": "0:10:51", "throughput": 10186.73, "total_tokens": 49935296}
{"current_steps": 52010, "total_steps": 58920, "loss": 0.0, "lr": 8.265431687502921e-08, "epoch": 4.413611676849966, "percentage": 88.27, "elapsed_time": "1:21:42", "remaining_time": "0:10:51", "throughput": 10186.92, "total_tokens": 49940160}
{"current_steps": 52015, "total_steps": 58920, "loss": 0.0, "lr": 8.253643437056746e-08, "epoch": 4.414035980991175, "percentage": 88.28, "elapsed_time": "1:21:42", "remaining_time": "0:10:50", "throughput": 10187.16, "total_tokens": 49945344}
{"current_steps": 52020, "total_steps": 58920, "loss": 0.0, "lr": 8.241863237022139e-08, "epoch": 4.414460285132383, "percentage": 88.29, "elapsed_time": "1:21:43", "remaining_time": "0:10:50", "throughput": 10187.37, "total_tokens": 49950272}
{"current_steps": 52025, "total_steps": 58920, "loss": 0.0, "lr": 8.230091088432734e-08, "epoch": 4.4148845892735915, "percentage": 88.3, "elapsed_time": "1:21:43", "remaining_time": "0:10:49", "throughput": 10187.49, "total_tokens": 49954688}
{"current_steps": 52030, "total_steps": 58920, "loss": 0.0, "lr": 8.218326992321489e-08, "epoch": 4.4153088934147995, "percentage": 88.31, "elapsed_time": "1:21:43", "remaining_time": "0:10:49", "throughput": 10187.74, "total_tokens": 49959936}
{"current_steps": 52035, "total_steps": 58920, "loss": 0.0, "lr": 8.206570949720681e-08, "epoch": 4.415733197556008, "percentage": 88.31, "elapsed_time": "1:21:44", "remaining_time": "0:10:48", "throughput": 10187.97, "total_tokens": 49965056}
{"current_steps": 52040, "total_steps": 58920, "loss": 0.0, "lr": 8.19482296166184e-08, "epoch": 4.416157501697216, "percentage": 88.32, "elapsed_time": "1:21:44", "remaining_time": "0:10:48", "throughput": 10188.1, "total_tokens": 49969536}
{"current_steps": 52045, "total_steps": 58920, "loss": 0.0, "lr": 8.183083029175852e-08, "epoch": 4.416581805838425, "percentage": 88.33, "elapsed_time": "1:21:45", "remaining_time": "0:10:47", "throughput": 10188.31, "total_tokens": 49974464}
{"current_steps": 52050, "total_steps": 58920, "loss": 0.0, "lr": 8.171351153292782e-08, "epoch": 4.417006109979633, "percentage": 88.34, "elapsed_time": "1:21:45", "remaining_time": "0:10:47", "throughput": 10188.64, "total_tokens": 49980224}
{"current_steps": 52055, "total_steps": 58920, "loss": 0.0, "lr": 8.159627335042152e-08, "epoch": 4.417430414120842, "percentage": 88.35, "elapsed_time": "1:21:45", "remaining_time": "0:10:46", "throughput": 10188.72, "total_tokens": 49984320}
{"current_steps": 52060, "total_steps": 58920, "loss": 0.0, "lr": 8.147911575452593e-08, "epoch": 4.41785471826205, "percentage": 88.36, "elapsed_time": "1:21:46", "remaining_time": "0:10:46", "throughput": 10188.86, "total_tokens": 49988864}
{"current_steps": 52065, "total_steps": 58920, "loss": 0.0, "lr": 8.136203875552172e-08, "epoch": 4.418279022403259, "percentage": 88.37, "elapsed_time": "1:21:46", "remaining_time": "0:10:46", "throughput": 10189.06, "total_tokens": 49993728}
{"current_steps": 52070, "total_steps": 58920, "loss": 0.0, "lr": 8.124504236368212e-08, "epoch": 4.418703326544467, "percentage": 88.37, "elapsed_time": "1:21:47", "remaining_time": "0:10:45", "throughput": 10189.32, "total_tokens": 49999040}
{"current_steps": 52075, "total_steps": 58920, "loss": 0.0, "lr": 8.112812658927259e-08, "epoch": 4.419127630685676, "percentage": 88.38, "elapsed_time": "1:21:47", "remaining_time": "0:10:45", "throughput": 10189.54, "total_tokens": 50004096}
{"current_steps": 52080, "total_steps": 58920, "loss": 0.0, "lr": 8.10112914425527e-08, "epoch": 4.419551934826884, "percentage": 88.39, "elapsed_time": "1:21:47", "remaining_time": "0:10:44", "throughput": 10189.69, "total_tokens": 50008704}
{"current_steps": 52085, "total_steps": 58920, "loss": 0.0, "lr": 8.089453693377368e-08, "epoch": 4.4199762389680926, "percentage": 88.4, "elapsed_time": "1:21:48", "remaining_time": "0:10:44", "throughput": 10189.86, "total_tokens": 50013376}
{"current_steps": 52090, "total_steps": 58920, "loss": 0.0, "lr": 8.077786307318091e-08, "epoch": 4.4204005431093005, "percentage": 88.41, "elapsed_time": "1:21:48", "remaining_time": "0:10:43", "throughput": 10189.99, "total_tokens": 50017856}
{"current_steps": 52095, "total_steps": 58920, "loss": 0.0, "lr": 8.066126987101152e-08, "epoch": 4.420824847250509, "percentage": 88.42, "elapsed_time": "1:21:48", "remaining_time": "0:10:43", "throughput": 10190.19, "total_tokens": 50022720}
{"current_steps": 52100, "total_steps": 58920, "loss": 0.0, "lr": 8.054475733749655e-08, "epoch": 4.421249151391717, "percentage": 88.42, "elapsed_time": "1:21:49", "remaining_time": "0:10:42", "throughput": 10190.4, "total_tokens": 50027648}
{"current_steps": 52105, "total_steps": 58920, "loss": 0.0, "lr": 8.042832548285972e-08, "epoch": 4.421673455532926, "percentage": 88.43, "elapsed_time": "1:21:49", "remaining_time": "0:10:42", "throughput": 10190.59, "total_tokens": 50032512}
{"current_steps": 52110, "total_steps": 58920, "loss": 0.0, "lr": 8.031197431731684e-08, "epoch": 4.422097759674134, "percentage": 88.44, "elapsed_time": "1:21:50", "remaining_time": "0:10:41", "throughput": 10190.69, "total_tokens": 50036800}
{"current_steps": 52115, "total_steps": 58920, "loss": 0.0, "lr": 8.019570385107799e-08, "epoch": 4.422522063815343, "percentage": 88.45, "elapsed_time": "1:21:50", "remaining_time": "0:10:41", "throughput": 10190.84, "total_tokens": 50041344}
{"current_steps": 52120, "total_steps": 58920, "loss": 0.0, "lr": 8.007951409434488e-08, "epoch": 4.422946367956551, "percentage": 88.46, "elapsed_time": "1:21:50", "remaining_time": "0:10:40", "throughput": 10190.93, "total_tokens": 50045568}
{"current_steps": 52125, "total_steps": 58920, "loss": 0.0, "lr": 7.996340505731325e-08, "epoch": 4.42337067209776, "percentage": 88.47, "elapsed_time": "1:21:51", "remaining_time": "0:10:40", "throughput": 10191.06, "total_tokens": 50049984}
{"current_steps": 52130, "total_steps": 58920, "loss": 0.0, "lr": 7.984737675017095e-08, "epoch": 4.423794976238968, "percentage": 88.48, "elapsed_time": "1:21:51", "remaining_time": "0:10:39", "throughput": 10191.25, "total_tokens": 50054784}
{"current_steps": 52135, "total_steps": 58920, "loss": 0.0, "lr": 7.973142918309927e-08, "epoch": 4.424219280380177, "percentage": 88.48, "elapsed_time": "1:21:51", "remaining_time": "0:10:39", "throughput": 10191.41, "total_tokens": 50059392}
{"current_steps": 52140, "total_steps": 58920, "loss": 0.0, "lr": 7.961556236627198e-08, "epoch": 4.424643584521385, "percentage": 88.49, "elapsed_time": "1:21:52", "remaining_time": "0:10:38", "throughput": 10191.6, "total_tokens": 50064256}
{"current_steps": 52145, "total_steps": 58920, "loss": 0.0, "lr": 7.949977630985605e-08, "epoch": 4.425067888662594, "percentage": 88.5, "elapsed_time": "1:21:52", "remaining_time": "0:10:38", "throughput": 10191.88, "total_tokens": 50069696}
{"current_steps": 52150, "total_steps": 58920, "loss": 0.0, "lr": 7.938407102401134e-08, "epoch": 4.425492192803802, "percentage": 88.51, "elapsed_time": "1:21:53", "remaining_time": "0:10:37", "throughput": 10191.99, "total_tokens": 50074048}
{"current_steps": 52155, "total_steps": 58920, "loss": 0.0, "lr": 7.926844651889053e-08, "epoch": 4.42591649694501, "percentage": 88.52, "elapsed_time": "1:21:53", "remaining_time": "0:10:37", "throughput": 10192.18, "total_tokens": 50078912}
{"current_steps": 52160, "total_steps": 58920, "loss": 0.0, "lr": 7.915290280463916e-08, "epoch": 4.426340801086218, "percentage": 88.53, "elapsed_time": "1:21:53", "remaining_time": "0:10:36", "throughput": 10192.38, "total_tokens": 50083776}
{"current_steps": 52165, "total_steps": 58920, "loss": 0.0, "lr": 7.903743989139599e-08, "epoch": 4.426765105227427, "percentage": 88.54, "elapsed_time": "1:21:54", "remaining_time": "0:10:36", "throughput": 10192.55, "total_tokens": 50088512}
{"current_steps": 52170, "total_steps": 58920, "loss": 0.0, "lr": 7.892205778929228e-08, "epoch": 4.427189409368635, "percentage": 88.54, "elapsed_time": "1:21:54", "remaining_time": "0:10:35", "throughput": 10192.67, "total_tokens": 50092928}
{"current_steps": 52175, "total_steps": 58920, "loss": 0.0, "lr": 7.880675650845248e-08, "epoch": 4.427613713509844, "percentage": 88.55, "elapsed_time": "1:21:55", "remaining_time": "0:10:35", "throughput": 10192.97, "total_tokens": 50098560}
{"current_steps": 52180, "total_steps": 58920, "loss": 0.0, "lr": 7.869153605899382e-08, "epoch": 4.428038017651052, "percentage": 88.56, "elapsed_time": "1:21:55", "remaining_time": "0:10:34", "throughput": 10193.25, "total_tokens": 50104000}
{"current_steps": 52185, "total_steps": 58920, "loss": 0.0, "lr": 7.857639645102643e-08, "epoch": 4.428462321792261, "percentage": 88.57, "elapsed_time": "1:21:55", "remaining_time": "0:10:34", "throughput": 10193.38, "total_tokens": 50108480}
{"current_steps": 52190, "total_steps": 58920, "loss": 0.0, "lr": 7.846133769465357e-08, "epoch": 4.428886625933469, "percentage": 88.58, "elapsed_time": "1:21:56", "remaining_time": "0:10:33", "throughput": 10193.56, "total_tokens": 50113280}
{"current_steps": 52195, "total_steps": 58920, "loss": 0.0, "lr": 7.834635979997107e-08, "epoch": 4.429310930074678, "percentage": 88.59, "elapsed_time": "1:21:56", "remaining_time": "0:10:33", "throughput": 10193.71, "total_tokens": 50117824}
{"current_steps": 52200, "total_steps": 58920, "loss": 0.0, "lr": 7.823146277706794e-08, "epoch": 4.429735234215886, "percentage": 88.59, "elapsed_time": "1:21:56", "remaining_time": "0:10:32", "throughput": 10193.92, "total_tokens": 50122816}
{"current_steps": 52205, "total_steps": 58920, "loss": 0.0, "lr": 7.81166466360259e-08, "epoch": 4.430159538357095, "percentage": 88.6, "elapsed_time": "1:21:57", "remaining_time": "0:10:32", "throughput": 10194.05, "total_tokens": 50127296}
{"current_steps": 52210, "total_steps": 58920, "loss": 0.0, "lr": 7.80019113869197e-08, "epoch": 4.430583842498303, "percentage": 88.61, "elapsed_time": "1:21:57", "remaining_time": "0:10:32", "throughput": 10194.19, "total_tokens": 50131840}
{"current_steps": 52215, "total_steps": 58920, "loss": 0.0, "lr": 7.78872570398168e-08, "epoch": 4.4310081466395115, "percentage": 88.62, "elapsed_time": "1:21:58", "remaining_time": "0:10:31", "throughput": 10194.28, "total_tokens": 50136064}
{"current_steps": 52220, "total_steps": 58920, "loss": 0.0, "lr": 7.777268360477796e-08, "epoch": 4.4314324507807195, "percentage": 88.63, "elapsed_time": "1:21:58", "remaining_time": "0:10:31", "throughput": 10194.35, "total_tokens": 50140160}
{"current_steps": 52225, "total_steps": 58920, "loss": 0.0, "lr": 7.765819109185634e-08, "epoch": 4.431856754921928, "percentage": 88.64, "elapsed_time": "1:21:58", "remaining_time": "0:10:30", "throughput": 10194.58, "total_tokens": 50145280}
{"current_steps": 52230, "total_steps": 58920, "loss": 0.0, "lr": 7.754377951109836e-08, "epoch": 4.432281059063136, "percentage": 88.65, "elapsed_time": "1:21:59", "remaining_time": "0:10:30", "throughput": 10194.72, "total_tokens": 50149824}
{"current_steps": 52235, "total_steps": 58920, "loss": 0.0, "lr": 7.742944887254332e-08, "epoch": 4.432705363204345, "percentage": 88.65, "elapsed_time": "1:21:59", "remaining_time": "0:10:29", "throughput": 10194.95, "total_tokens": 50154944}
{"current_steps": 52240, "total_steps": 58920, "loss": 0.0, "lr": 7.731519918622309e-08, "epoch": 4.433129667345553, "percentage": 88.66, "elapsed_time": "1:21:59", "remaining_time": "0:10:29", "throughput": 10195.1, "total_tokens": 50159552}
{"current_steps": 52245, "total_steps": 58920, "loss": 0.0, "lr": 7.720103046216286e-08, "epoch": 4.433553971486762, "percentage": 88.67, "elapsed_time": "1:22:00", "remaining_time": "0:10:28", "throughput": 10195.23, "total_tokens": 50164032}
{"current_steps": 52250, "total_steps": 58920, "loss": 0.0, "lr": 7.708694271038042e-08, "epoch": 4.43397827562797, "percentage": 88.68, "elapsed_time": "1:22:00", "remaining_time": "0:10:28", "throughput": 10195.49, "total_tokens": 50169344}
{"current_steps": 52255, "total_steps": 58920, "loss": 0.0, "lr": 7.697293594088638e-08, "epoch": 4.434402579769179, "percentage": 88.69, "elapsed_time": "1:22:01", "remaining_time": "0:10:27", "throughput": 10195.71, "total_tokens": 50174336}
{"current_steps": 52260, "total_steps": 58920, "loss": 0.0, "lr": 7.685901016368512e-08, "epoch": 4.434826883910387, "percentage": 88.7, "elapsed_time": "1:22:01", "remaining_time": "0:10:27", "throughput": 10195.9, "total_tokens": 50179200}
{"current_steps": 52265, "total_steps": 58920, "loss": 0.0, "lr": 7.674516538877229e-08, "epoch": 4.435251188051596, "percentage": 88.71, "elapsed_time": "1:22:01", "remaining_time": "0:10:26", "throughput": 10196.11, "total_tokens": 50184128}
{"current_steps": 52270, "total_steps": 58920, "loss": 0.0, "lr": 7.663140162613813e-08, "epoch": 4.435675492192804, "percentage": 88.71, "elapsed_time": "1:22:02", "remaining_time": "0:10:26", "throughput": 10196.24, "total_tokens": 50188608}
{"current_steps": 52275, "total_steps": 58920, "loss": 0.0, "lr": 7.651771888576453e-08, "epoch": 4.4360997963340125, "percentage": 88.72, "elapsed_time": "1:22:02", "remaining_time": "0:10:25", "throughput": 10196.37, "total_tokens": 50193024}
{"current_steps": 52280, "total_steps": 58920, "loss": 0.0, "lr": 7.640411717762662e-08, "epoch": 4.4365241004752205, "percentage": 88.73, "elapsed_time": "1:22:03", "remaining_time": "0:10:25", "throughput": 10196.53, "total_tokens": 50197696}
{"current_steps": 52285, "total_steps": 58920, "loss": 0.0, "lr": 7.629059651169323e-08, "epoch": 4.436948404616429, "percentage": 88.74, "elapsed_time": "1:22:03", "remaining_time": "0:10:24", "throughput": 10196.68, "total_tokens": 50202304}
{"current_steps": 52290, "total_steps": 58920, "loss": 0.0, "lr": 7.617715689792458e-08, "epoch": 4.437372708757637, "percentage": 88.75, "elapsed_time": "1:22:03", "remaining_time": "0:10:24", "throughput": 10196.91, "total_tokens": 50207360}
{"current_steps": 52295, "total_steps": 58920, "loss": 0.0, "lr": 7.606379834627541e-08, "epoch": 4.437797012898846, "percentage": 88.76, "elapsed_time": "1:22:04", "remaining_time": "0:10:23", "throughput": 10197.09, "total_tokens": 50212160}
{"current_steps": 52300, "total_steps": 58920, "loss": 0.0, "lr": 7.595052086669162e-08, "epoch": 4.438221317040054, "percentage": 88.76, "elapsed_time": "1:22:04", "remaining_time": "0:10:23", "throughput": 10197.28, "total_tokens": 50216960}
{"current_steps": 52305, "total_steps": 58920, "loss": 0.0, "lr": 7.583732446911373e-08, "epoch": 4.438645621181263, "percentage": 88.77, "elapsed_time": "1:22:04", "remaining_time": "0:10:22", "throughput": 10197.46, "total_tokens": 50221760}
{"current_steps": 52310, "total_steps": 58920, "loss": 0.0, "lr": 7.572420916347355e-08, "epoch": 4.439069925322471, "percentage": 88.78, "elapsed_time": "1:22:05", "remaining_time": "0:10:22", "throughput": 10197.6, "total_tokens": 50226304}
{"current_steps": 52315, "total_steps": 58920, "loss": 0.0, "lr": 7.561117495969715e-08, "epoch": 4.43949422946368, "percentage": 88.79, "elapsed_time": "1:22:05", "remaining_time": "0:10:21", "throughput": 10197.84, "total_tokens": 50231488}
{"current_steps": 52320, "total_steps": 58920, "loss": 0.0, "lr": 7.549822186770283e-08, "epoch": 4.439918533604888, "percentage": 88.8, "elapsed_time": "1:22:06", "remaining_time": "0:10:21", "throughput": 10198.02, "total_tokens": 50236288}
{"current_steps": 52325, "total_steps": 58920, "loss": 0.0, "lr": 7.53853498974013e-08, "epoch": 4.440342837746097, "percentage": 88.81, "elapsed_time": "1:22:06", "remaining_time": "0:10:20", "throughput": 10198.15, "total_tokens": 50240704}
{"current_steps": 52330, "total_steps": 58920, "loss": 0.0, "lr": 7.527255905869734e-08, "epoch": 4.440767141887305, "percentage": 88.82, "elapsed_time": "1:22:06", "remaining_time": "0:10:20", "throughput": 10198.29, "total_tokens": 50245248}
{"current_steps": 52335, "total_steps": 58920, "loss": 0.0, "lr": 7.515984936148734e-08, "epoch": 4.441191446028514, "percentage": 88.82, "elapsed_time": "1:22:07", "remaining_time": "0:10:19", "throughput": 10198.41, "total_tokens": 50249664}
{"current_steps": 52340, "total_steps": 58920, "loss": 0.0, "lr": 7.504722081566151e-08, "epoch": 4.4416157501697215, "percentage": 88.83, "elapsed_time": "1:22:07", "remaining_time": "0:10:19", "throughput": 10198.54, "total_tokens": 50254144}
{"current_steps": 52345, "total_steps": 58920, "loss": 0.0, "lr": 7.49346734311025e-08, "epoch": 4.44204005431093, "percentage": 88.84, "elapsed_time": "1:22:07", "remaining_time": "0:10:18", "throughput": 10198.8, "total_tokens": 50259520}
{"current_steps": 52350, "total_steps": 58920, "loss": 0.0, "lr": 7.482220721768607e-08, "epoch": 4.442464358452138, "percentage": 88.85, "elapsed_time": "1:22:08", "remaining_time": "0:10:18", "throughput": 10199.0, "total_tokens": 50264384}
{"current_steps": 52355, "total_steps": 58920, "loss": 0.0, "lr": 7.470982218528054e-08, "epoch": 4.442888662593347, "percentage": 88.86, "elapsed_time": "1:22:08", "remaining_time": "0:10:18", "throughput": 10199.19, "total_tokens": 50269248}
{"current_steps": 52360, "total_steps": 58920, "loss": 0.0, "lr": 7.459751834374739e-08, "epoch": 4.443312966734555, "percentage": 88.87, "elapsed_time": "1:22:09", "remaining_time": "0:10:17", "throughput": 10199.3, "total_tokens": 50273600}
{"current_steps": 52365, "total_steps": 58920, "loss": 0.0, "lr": 7.448529570294082e-08, "epoch": 4.443737270875764, "percentage": 88.87, "elapsed_time": "1:22:09", "remaining_time": "0:10:17", "throughput": 10199.37, "total_tokens": 50277696}
{"current_steps": 52370, "total_steps": 58920, "loss": 0.0, "lr": 7.437315427270807e-08, "epoch": 4.444161575016972, "percentage": 88.88, "elapsed_time": "1:22:09", "remaining_time": "0:10:16", "throughput": 10199.63, "total_tokens": 50283008}
{"current_steps": 52375, "total_steps": 58920, "loss": 0.0, "lr": 7.426109406288905e-08, "epoch": 4.444585879158181, "percentage": 88.89, "elapsed_time": "1:22:10", "remaining_time": "0:10:16", "throughput": 10199.83, "total_tokens": 50287872}
{"current_steps": 52380, "total_steps": 58920, "loss": 0.0, "lr": 7.414911508331656e-08, "epoch": 4.445010183299389, "percentage": 88.9, "elapsed_time": "1:22:10", "remaining_time": "0:10:15", "throughput": 10200.06, "total_tokens": 50292992}
{"current_steps": 52385, "total_steps": 58920, "loss": 0.0, "lr": 7.403721734381652e-08, "epoch": 4.445434487440598, "percentage": 88.91, "elapsed_time": "1:22:11", "remaining_time": "0:10:15", "throughput": 10200.19, "total_tokens": 50297472}
{"current_steps": 52390, "total_steps": 58920, "loss": 0.0, "lr": 7.39254008542075e-08, "epoch": 4.445858791581806, "percentage": 88.92, "elapsed_time": "1:22:11", "remaining_time": "0:10:14", "throughput": 10200.33, "total_tokens": 50302016}
{"current_steps": 52395, "total_steps": 58920, "loss": 0.0, "lr": 7.381366562430102e-08, "epoch": 4.446283095723015, "percentage": 88.93, "elapsed_time": "1:22:11", "remaining_time": "0:10:14", "throughput": 10200.54, "total_tokens": 50307008}
{"current_steps": 52400, "total_steps": 58920, "loss": 0.0, "lr": 7.370201166390133e-08, "epoch": 4.446707399864223, "percentage": 88.93, "elapsed_time": "1:22:12", "remaining_time": "0:10:13", "throughput": 10200.67, "total_tokens": 50311488}
{"current_steps": 52405, "total_steps": 58920, "loss": 0.0, "lr": 7.35904389828057e-08, "epoch": 4.4471317040054315, "percentage": 88.94, "elapsed_time": "1:22:12", "remaining_time": "0:10:13", "throughput": 10200.75, "total_tokens": 50315648}
{"current_steps": 52410, "total_steps": 58920, "loss": 0.0, "lr": 7.34789475908043e-08, "epoch": 4.447556008146639, "percentage": 88.95, "elapsed_time": "1:22:12", "remaining_time": "0:10:12", "throughput": 10200.91, "total_tokens": 50320256}
{"current_steps": 52415, "total_steps": 58920, "loss": 0.0, "lr": 7.33675374976801e-08, "epoch": 4.447980312287848, "percentage": 88.96, "elapsed_time": "1:22:13", "remaining_time": "0:10:12", "throughput": 10201.05, "total_tokens": 50324800}
{"current_steps": 52420, "total_steps": 58920, "loss": 0.0639, "lr": 7.325620871320881e-08, "epoch": 4.448404616429056, "percentage": 88.97, "elapsed_time": "1:22:13", "remaining_time": "0:10:11", "throughput": 10201.19, "total_tokens": 50329344}
{"current_steps": 52425, "total_steps": 58920, "loss": 0.0, "lr": 7.314496124715929e-08, "epoch": 4.448828920570265, "percentage": 88.98, "elapsed_time": "1:22:14", "remaining_time": "0:10:11", "throughput": 10201.38, "total_tokens": 50334144}
{"current_steps": 52430, "total_steps": 58920, "loss": 0.0, "lr": 7.303379510929297e-08, "epoch": 4.449253224711473, "percentage": 88.99, "elapsed_time": "1:22:14", "remaining_time": "0:10:10", "throughput": 10201.49, "total_tokens": 50338496}
{"current_steps": 52435, "total_steps": 58920, "loss": 0.0, "lr": 7.292271030936436e-08, "epoch": 4.449677528852682, "percentage": 88.99, "elapsed_time": "1:22:14", "remaining_time": "0:10:10", "throughput": 10201.69, "total_tokens": 50343424}
{"current_steps": 52440, "total_steps": 58920, "loss": 0.0, "lr": 7.281170685712068e-08, "epoch": 4.45010183299389, "percentage": 89.0, "elapsed_time": "1:22:15", "remaining_time": "0:10:09", "throughput": 10201.77, "total_tokens": 50347584}
{"current_steps": 52445, "total_steps": 58920, "loss": 0.0, "lr": 7.270078476230213e-08, "epoch": 4.450526137135099, "percentage": 89.01, "elapsed_time": "1:22:15", "remaining_time": "0:10:09", "throughput": 10201.9, "total_tokens": 50352064}
{"current_steps": 52450, "total_steps": 58920, "loss": 0.0, "lr": 7.258994403464169e-08, "epoch": 4.450950441276307, "percentage": 89.02, "elapsed_time": "1:22:15", "remaining_time": "0:10:08", "throughput": 10202.12, "total_tokens": 50357056}
{"current_steps": 52455, "total_steps": 58920, "loss": 0.0, "lr": 7.247918468386538e-08, "epoch": 4.451374745417516, "percentage": 89.03, "elapsed_time": "1:22:16", "remaining_time": "0:10:08", "throughput": 10202.21, "total_tokens": 50361344}
{"current_steps": 52460, "total_steps": 58920, "loss": 0.0, "lr": 7.236850671969175e-08, "epoch": 4.451799049558724, "percentage": 89.04, "elapsed_time": "1:22:16", "remaining_time": "0:10:07", "throughput": 10202.35, "total_tokens": 50365888}
{"current_steps": 52465, "total_steps": 58920, "loss": 0.0, "lr": 7.225791015183247e-08, "epoch": 4.4522233536999325, "percentage": 89.04, "elapsed_time": "1:22:17", "remaining_time": "0:10:07", "throughput": 10202.5, "total_tokens": 50370432}
{"current_steps": 52470, "total_steps": 58920, "loss": 0.0, "lr": 7.214739498999178e-08, "epoch": 4.4526476578411405, "percentage": 89.05, "elapsed_time": "1:22:17", "remaining_time": "0:10:06", "throughput": 10202.59, "total_tokens": 50374720}
{"current_steps": 52475, "total_steps": 58920, "loss": 0.0, "lr": 7.203696124386748e-08, "epoch": 4.453071961982349, "percentage": 89.06, "elapsed_time": "1:22:17", "remaining_time": "0:10:06", "throughput": 10202.73, "total_tokens": 50379264}
{"current_steps": 52480, "total_steps": 58920, "loss": 0.0, "lr": 7.192660892314917e-08, "epoch": 4.453496266123557, "percentage": 89.07, "elapsed_time": "1:22:18", "remaining_time": "0:10:05", "throughput": 10202.86, "total_tokens": 50383680}
{"current_steps": 52485, "total_steps": 58920, "loss": 0.0, "lr": 7.18163380375204e-08, "epoch": 4.453920570264766, "percentage": 89.08, "elapsed_time": "1:22:18", "remaining_time": "0:10:05", "throughput": 10203.03, "total_tokens": 50388416}
{"current_steps": 52490, "total_steps": 58920, "loss": 0.0, "lr": 7.170614859665657e-08, "epoch": 4.454344874405974, "percentage": 89.09, "elapsed_time": "1:22:18", "remaining_time": "0:10:05", "throughput": 10203.16, "total_tokens": 50392832}
{"current_steps": 52495, "total_steps": 58920, "loss": 0.0, "lr": 7.159604061022661e-08, "epoch": 4.454769178547183, "percentage": 89.1, "elapsed_time": "1:22:19", "remaining_time": "0:10:04", "throughput": 10203.35, "total_tokens": 50397696}
{"current_steps": 52500, "total_steps": 58920, "loss": 0.0, "lr": 7.148601408789234e-08, "epoch": 4.455193482688391, "percentage": 89.1, "elapsed_time": "1:22:19", "remaining_time": "0:10:04", "throughput": 10203.55, "total_tokens": 50402624}
{"current_steps": 52505, "total_steps": 58920, "loss": 0.0, "lr": 7.13760690393076e-08, "epoch": 4.4556177868296, "percentage": 89.11, "elapsed_time": "1:22:20", "remaining_time": "0:10:03", "throughput": 10203.67, "total_tokens": 50407040}
{"current_steps": 52510, "total_steps": 58920, "loss": 0.0, "lr": 7.126620547412033e-08, "epoch": 4.456042090970808, "percentage": 89.12, "elapsed_time": "1:22:20", "remaining_time": "0:10:03", "throughput": 10203.83, "total_tokens": 50411712}
{"current_steps": 52515, "total_steps": 58920, "loss": 0.0, "lr": 7.115642340197004e-08, "epoch": 4.456466395112017, "percentage": 89.13, "elapsed_time": "1:22:20", "remaining_time": "0:10:02", "throughput": 10204.08, "total_tokens": 50417024}
{"current_steps": 52520, "total_steps": 58920, "loss": 0.0, "lr": 7.104672283249036e-08, "epoch": 4.456890699253225, "percentage": 89.14, "elapsed_time": "1:22:21", "remaining_time": "0:10:02", "throughput": 10204.24, "total_tokens": 50421696}
{"current_steps": 52525, "total_steps": 58920, "loss": 0.0, "lr": 7.093710377530659e-08, "epoch": 4.4573150033944335, "percentage": 89.15, "elapsed_time": "1:22:21", "remaining_time": "0:10:01", "throughput": 10204.4, "total_tokens": 50426304}
{"current_steps": 52530, "total_steps": 58920, "loss": 0.0, "lr": 7.08275662400375e-08, "epoch": 4.4577393075356415, "percentage": 89.15, "elapsed_time": "1:22:22", "remaining_time": "0:10:01", "throughput": 10204.53, "total_tokens": 50430784}
{"current_steps": 52535, "total_steps": 58920, "loss": 0.0, "lr": 7.071811023629493e-08, "epoch": 4.45816361167685, "percentage": 89.16, "elapsed_time": "1:22:22", "remaining_time": "0:10:00", "throughput": 10204.72, "total_tokens": 50435648}
{"current_steps": 52540, "total_steps": 58920, "loss": 0.0, "lr": 7.060873577368276e-08, "epoch": 4.458587915818058, "percentage": 89.17, "elapsed_time": "1:22:22", "remaining_time": "0:10:00", "throughput": 10204.87, "total_tokens": 50440256}
{"current_steps": 52545, "total_steps": 58920, "loss": 0.0, "lr": 7.049944286179876e-08, "epoch": 4.459012219959266, "percentage": 89.18, "elapsed_time": "1:22:23", "remaining_time": "0:09:59", "throughput": 10205.02, "total_tokens": 50444928}
{"current_steps": 52550, "total_steps": 58920, "loss": 0.0, "lr": 7.039023151023249e-08, "epoch": 4.459436524100475, "percentage": 89.19, "elapsed_time": "1:22:23", "remaining_time": "0:09:59", "throughput": 10205.25, "total_tokens": 50449984}
{"current_steps": 52555, "total_steps": 58920, "loss": 0.0, "lr": 7.028110172856716e-08, "epoch": 4.459860828241684, "percentage": 89.2, "elapsed_time": "1:22:23", "remaining_time": "0:09:58", "throughput": 10205.52, "total_tokens": 50455360}
{"current_steps": 52560, "total_steps": 58920, "loss": 0.0, "lr": 7.017205352637834e-08, "epoch": 4.460285132382892, "percentage": 89.21, "elapsed_time": "1:22:24", "remaining_time": "0:09:58", "throughput": 10205.7, "total_tokens": 50460160}
{"current_steps": 52565, "total_steps": 58920, "loss": 0.0, "lr": 7.006308691323481e-08, "epoch": 4.4607094365241, "percentage": 89.21, "elapsed_time": "1:22:24", "remaining_time": "0:09:57", "throughput": 10205.78, "total_tokens": 50464320}
{"current_steps": 52570, "total_steps": 58920, "loss": 0.0, "lr": 6.995420189869794e-08, "epoch": 4.461133740665309, "percentage": 89.22, "elapsed_time": "1:22:25", "remaining_time": "0:09:57", "throughput": 10205.9, "total_tokens": 50468736}
{"current_steps": 52575, "total_steps": 58920, "loss": 0.0, "lr": 6.984539849232162e-08, "epoch": 4.461558044806518, "percentage": 89.23, "elapsed_time": "1:22:25", "remaining_time": "0:09:56", "throughput": 10206.1, "total_tokens": 50473664}
{"current_steps": 52580, "total_steps": 58920, "loss": 0.0, "lr": 6.973667670365358e-08, "epoch": 4.461982348947726, "percentage": 89.24, "elapsed_time": "1:22:25", "remaining_time": "0:09:56", "throughput": 10206.38, "total_tokens": 50479104}
{"current_steps": 52585, "total_steps": 58920, "loss": 0.0002, "lr": 6.962803654223325e-08, "epoch": 4.462406653088934, "percentage": 89.25, "elapsed_time": "1:22:26", "remaining_time": "0:09:55", "throughput": 10206.49, "total_tokens": 50483456}
{"current_steps": 52590, "total_steps": 58920, "loss": 0.0, "lr": 6.951947801759372e-08, "epoch": 4.462830957230143, "percentage": 89.26, "elapsed_time": "1:22:26", "remaining_time": "0:09:55", "throughput": 10206.64, "total_tokens": 50488064}
{"current_steps": 52595, "total_steps": 58920, "loss": 0.0, "lr": 6.941100113926057e-08, "epoch": 4.463255261371351, "percentage": 89.27, "elapsed_time": "1:22:26", "remaining_time": "0:09:54", "throughput": 10206.8, "total_tokens": 50492736}
{"current_steps": 52600, "total_steps": 58920, "loss": 0.0, "lr": 6.930260591675208e-08, "epoch": 4.463679565512559, "percentage": 89.27, "elapsed_time": "1:22:27", "remaining_time": "0:09:54", "throughput": 10206.95, "total_tokens": 50497344}
{"current_steps": 52605, "total_steps": 58920, "loss": 0.0, "lr": 6.919429235957974e-08, "epoch": 4.464103869653767, "percentage": 89.28, "elapsed_time": "1:22:27", "remaining_time": "0:09:53", "throughput": 10207.1, "total_tokens": 50501952}
{"current_steps": 52610, "total_steps": 58920, "loss": 0.0, "lr": 6.908606047724753e-08, "epoch": 4.464528173794976, "percentage": 89.29, "elapsed_time": "1:22:28", "remaining_time": "0:09:53", "throughput": 10207.25, "total_tokens": 50506496}
{"current_steps": 52615, "total_steps": 58920, "loss": 0.0, "lr": 6.897791027925248e-08, "epoch": 4.464952477936185, "percentage": 89.3, "elapsed_time": "1:22:28", "remaining_time": "0:09:52", "throughput": 10207.41, "total_tokens": 50511168}
{"current_steps": 52620, "total_steps": 58920, "loss": 0.0, "lr": 6.886984177508437e-08, "epoch": 4.465376782077393, "percentage": 89.31, "elapsed_time": "1:22:28", "remaining_time": "0:09:52", "throughput": 10207.58, "total_tokens": 50515968}
{"current_steps": 52625, "total_steps": 58920, "loss": 0.0, "lr": 6.876185497422581e-08, "epoch": 4.465801086218601, "percentage": 89.32, "elapsed_time": "1:22:29", "remaining_time": "0:09:52", "throughput": 10207.76, "total_tokens": 50520768}
{"current_steps": 52630, "total_steps": 58920, "loss": 0.0, "lr": 6.865394988615225e-08, "epoch": 4.46622539035981, "percentage": 89.32, "elapsed_time": "1:22:29", "remaining_time": "0:09:51", "throughput": 10207.99, "total_tokens": 50525888}
{"current_steps": 52635, "total_steps": 58920, "loss": 0.0, "lr": 6.854612652033199e-08, "epoch": 4.466649694501019, "percentage": 89.33, "elapsed_time": "1:22:30", "remaining_time": "0:09:51", "throughput": 10208.16, "total_tokens": 50530560}
{"current_steps": 52640, "total_steps": 58920, "loss": 0.0, "lr": 6.843838488622611e-08, "epoch": 4.467073998642227, "percentage": 89.34, "elapsed_time": "1:22:30", "remaining_time": "0:09:50", "throughput": 10208.32, "total_tokens": 50535296}
{"current_steps": 52645, "total_steps": 58920, "loss": 0.0, "lr": 6.833072499328851e-08, "epoch": 4.467498302783435, "percentage": 89.35, "elapsed_time": "1:22:30", "remaining_time": "0:09:50", "throughput": 10208.6, "total_tokens": 50540672}
{"current_steps": 52650, "total_steps": 58920, "loss": 0.0, "lr": 6.822314685096608e-08, "epoch": 4.467922606924644, "percentage": 89.36, "elapsed_time": "1:22:31", "remaining_time": "0:09:49", "throughput": 10208.79, "total_tokens": 50545536}
{"current_steps": 52655, "total_steps": 58920, "loss": 0.0, "lr": 6.811565046869827e-08, "epoch": 4.4683469110658525, "percentage": 89.37, "elapsed_time": "1:22:31", "remaining_time": "0:09:49", "throughput": 10208.92, "total_tokens": 50549952}
{"current_steps": 52660, "total_steps": 58920, "loss": 0.0, "lr": 6.800823585591764e-08, "epoch": 4.46877121520706, "percentage": 89.38, "elapsed_time": "1:22:31", "remaining_time": "0:09:48", "throughput": 10209.05, "total_tokens": 50554432}
{"current_steps": 52665, "total_steps": 58920, "loss": 0.0, "lr": 6.790090302204943e-08, "epoch": 4.469195519348268, "percentage": 89.38, "elapsed_time": "1:22:32", "remaining_time": "0:09:48", "throughput": 10209.25, "total_tokens": 50559360}
{"current_steps": 52670, "total_steps": 58920, "loss": 0.0, "lr": 6.779365197651155e-08, "epoch": 4.469619823489477, "percentage": 89.39, "elapsed_time": "1:22:32", "remaining_time": "0:09:47", "throughput": 10209.59, "total_tokens": 50565184}
{"current_steps": 52675, "total_steps": 58920, "loss": 0.0, "lr": 6.768648272871502e-08, "epoch": 4.470044127630685, "percentage": 89.4, "elapsed_time": "1:22:33", "remaining_time": "0:09:47", "throughput": 10209.82, "total_tokens": 50570304}
{"current_steps": 52680, "total_steps": 58920, "loss": 0.0, "lr": 6.757939528806356e-08, "epoch": 4.470468431771894, "percentage": 89.41, "elapsed_time": "1:22:33", "remaining_time": "0:09:46", "throughput": 10209.97, "total_tokens": 50574912}
{"current_steps": 52685, "total_steps": 58920, "loss": 0.0, "lr": 6.747238966395352e-08, "epoch": 4.470892735913102, "percentage": 89.42, "elapsed_time": "1:22:33", "remaining_time": "0:09:46", "throughput": 10210.17, "total_tokens": 50579840}
{"current_steps": 52690, "total_steps": 58920, "loss": 0.0, "lr": 6.736546586577462e-08, "epoch": 4.471317040054311, "percentage": 89.43, "elapsed_time": "1:22:34", "remaining_time": "0:09:45", "throughput": 10210.31, "total_tokens": 50584384}
{"current_steps": 52695, "total_steps": 58920, "loss": 0.0, "lr": 6.725862390290881e-08, "epoch": 4.471741344195519, "percentage": 89.43, "elapsed_time": "1:22:34", "remaining_time": "0:09:45", "throughput": 10210.48, "total_tokens": 50589120}
{"current_steps": 52700, "total_steps": 58920, "loss": 0.0, "lr": 6.715186378473104e-08, "epoch": 4.472165648336728, "percentage": 89.44, "elapsed_time": "1:22:35", "remaining_time": "0:09:44", "throughput": 10210.67, "total_tokens": 50593984}
{"current_steps": 52705, "total_steps": 58920, "loss": 0.0, "lr": 6.704518552060923e-08, "epoch": 4.472589952477936, "percentage": 89.45, "elapsed_time": "1:22:35", "remaining_time": "0:09:44", "throughput": 10210.77, "total_tokens": 50598336}
{"current_steps": 52710, "total_steps": 58920, "loss": 0.0, "lr": 6.693858911990369e-08, "epoch": 4.473014256619145, "percentage": 89.46, "elapsed_time": "1:22:35", "remaining_time": "0:09:43", "throughput": 10211.0, "total_tokens": 50603456}
{"current_steps": 52715, "total_steps": 58920, "loss": 0.0, "lr": 6.68320745919686e-08, "epoch": 4.473438560760353, "percentage": 89.47, "elapsed_time": "1:22:36", "remaining_time": "0:09:43", "throughput": 10211.24, "total_tokens": 50608640}
{"current_steps": 52720, "total_steps": 58920, "loss": 0.0, "lr": 6.672564194614937e-08, "epoch": 4.4738628649015615, "percentage": 89.48, "elapsed_time": "1:22:36", "remaining_time": "0:09:42", "throughput": 10211.31, "total_tokens": 50612736}
{"current_steps": 52725, "total_steps": 58920, "loss": 0.0, "lr": 6.661929119178588e-08, "epoch": 4.4742871690427695, "percentage": 89.49, "elapsed_time": "1:22:36", "remaining_time": "0:09:42", "throughput": 10211.48, "total_tokens": 50617472}
{"current_steps": 52730, "total_steps": 58920, "loss": 0.0, "lr": 6.651302233820921e-08, "epoch": 4.474711473183978, "percentage": 89.49, "elapsed_time": "1:22:37", "remaining_time": "0:09:41", "throughput": 10211.62, "total_tokens": 50622016}
{"current_steps": 52735, "total_steps": 58920, "loss": 0.0, "lr": 6.64068353947449e-08, "epoch": 4.475135777325186, "percentage": 89.5, "elapsed_time": "1:22:37", "remaining_time": "0:09:41", "throughput": 10211.8, "total_tokens": 50626816}
{"current_steps": 52740, "total_steps": 58920, "loss": 0.0, "lr": 6.630073037070983e-08, "epoch": 4.475560081466395, "percentage": 89.51, "elapsed_time": "1:22:38", "remaining_time": "0:09:40", "throughput": 10211.9, "total_tokens": 50631104}
{"current_steps": 52745, "total_steps": 58920, "loss": 0.0, "lr": 6.619470727541443e-08, "epoch": 4.475984385607603, "percentage": 89.52, "elapsed_time": "1:22:38", "remaining_time": "0:09:40", "throughput": 10212.06, "total_tokens": 50635776}
{"current_steps": 52750, "total_steps": 58920, "loss": 0.0, "lr": 6.608876611816238e-08, "epoch": 4.476408689748812, "percentage": 89.53, "elapsed_time": "1:22:38", "remaining_time": "0:09:40", "throughput": 10212.18, "total_tokens": 50640192}
{"current_steps": 52755, "total_steps": 58920, "loss": 0.0, "lr": 6.598290690824882e-08, "epoch": 4.47683299389002, "percentage": 89.54, "elapsed_time": "1:22:39", "remaining_time": "0:09:39", "throughput": 10212.34, "total_tokens": 50644928}
{"current_steps": 52760, "total_steps": 58920, "loss": 0.0, "lr": 6.587712965496328e-08, "epoch": 4.477257298031229, "percentage": 89.55, "elapsed_time": "1:22:39", "remaining_time": "0:09:39", "throughput": 10212.44, "total_tokens": 50649216}
{"current_steps": 52765, "total_steps": 58920, "loss": 0.0, "lr": 6.577143436758658e-08, "epoch": 4.477681602172437, "percentage": 89.55, "elapsed_time": "1:22:39", "remaining_time": "0:09:38", "throughput": 10212.56, "total_tokens": 50653632}
{"current_steps": 52770, "total_steps": 58920, "loss": 0.0, "lr": 6.566582105539376e-08, "epoch": 4.478105906313646, "percentage": 89.56, "elapsed_time": "1:22:40", "remaining_time": "0:09:38", "throughput": 10212.76, "total_tokens": 50658560}
{"current_steps": 52775, "total_steps": 58920, "loss": 0.0, "lr": 6.556028972765182e-08, "epoch": 4.478530210454854, "percentage": 89.57, "elapsed_time": "1:22:40", "remaining_time": "0:09:37", "throughput": 10212.86, "total_tokens": 50662912}
{"current_steps": 52780, "total_steps": 58920, "loss": 0.0, "lr": 6.545484039362037e-08, "epoch": 4.4789545145960625, "percentage": 89.58, "elapsed_time": "1:22:41", "remaining_time": "0:09:37", "throughput": 10213.0, "total_tokens": 50667456}
{"current_steps": 52785, "total_steps": 58920, "loss": 0.0, "lr": 6.53494730625529e-08, "epoch": 4.4793788187372705, "percentage": 89.59, "elapsed_time": "1:22:41", "remaining_time": "0:09:36", "throughput": 10213.18, "total_tokens": 50672256}
{"current_steps": 52790, "total_steps": 58920, "loss": 0.0, "lr": 6.524418774369423e-08, "epoch": 4.479803122878479, "percentage": 89.6, "elapsed_time": "1:22:41", "remaining_time": "0:09:36", "throughput": 10213.39, "total_tokens": 50677248}
{"current_steps": 52795, "total_steps": 58920, "loss": 0.0, "lr": 6.51389844462833e-08, "epoch": 4.480227427019687, "percentage": 89.6, "elapsed_time": "1:22:42", "remaining_time": "0:09:35", "throughput": 10213.52, "total_tokens": 50681728}
{"current_steps": 52800, "total_steps": 58920, "loss": 0.0, "lr": 6.503386317955128e-08, "epoch": 4.480651731160896, "percentage": 89.61, "elapsed_time": "1:22:42", "remaining_time": "0:09:35", "throughput": 10213.65, "total_tokens": 50686208}
{"current_steps": 52805, "total_steps": 58920, "loss": 0.0056, "lr": 6.492882395272203e-08, "epoch": 4.481076035302104, "percentage": 89.62, "elapsed_time": "1:22:42", "remaining_time": "0:09:34", "throughput": 10213.82, "total_tokens": 50690944}
{"current_steps": 52810, "total_steps": 58920, "loss": 0.0, "lr": 6.48238667750124e-08, "epoch": 4.481500339443313, "percentage": 89.63, "elapsed_time": "1:22:43", "remaining_time": "0:09:34", "throughput": 10214.0, "total_tokens": 50695808}
{"current_steps": 52815, "total_steps": 58920, "loss": 0.0, "lr": 6.471899165563199e-08, "epoch": 4.481924643584521, "percentage": 89.64, "elapsed_time": "1:22:43", "remaining_time": "0:09:33", "throughput": 10214.12, "total_tokens": 50700224}
{"current_steps": 52820, "total_steps": 58920, "loss": 0.0, "lr": 6.461419860378347e-08, "epoch": 4.48234894772573, "percentage": 89.65, "elapsed_time": "1:22:44", "remaining_time": "0:09:33", "throughput": 10214.31, "total_tokens": 50705152}
{"current_steps": 52825, "total_steps": 58920, "loss": 0.0, "lr": 6.450948762866148e-08, "epoch": 4.482773251866938, "percentage": 89.66, "elapsed_time": "1:22:44", "remaining_time": "0:09:32", "throughput": 10214.51, "total_tokens": 50710016}
{"current_steps": 52830, "total_steps": 58920, "loss": 0.0, "lr": 6.440485873945456e-08, "epoch": 4.483197556008147, "percentage": 89.66, "elapsed_time": "1:22:44", "remaining_time": "0:09:32", "throughput": 10214.69, "total_tokens": 50714816}
{"current_steps": 52835, "total_steps": 58920, "loss": 0.0, "lr": 6.430031194534335e-08, "epoch": 4.483621860149355, "percentage": 89.67, "elapsed_time": "1:22:45", "remaining_time": "0:09:31", "throughput": 10214.85, "total_tokens": 50719488}
{"current_steps": 52840, "total_steps": 58920, "loss": 0.0, "lr": 6.419584725550143e-08, "epoch": 4.484046164290564, "percentage": 89.68, "elapsed_time": "1:22:45", "remaining_time": "0:09:31", "throughput": 10215.07, "total_tokens": 50724608}
{"current_steps": 52845, "total_steps": 58920, "loss": 0.0, "lr": 6.409146467909521e-08, "epoch": 4.4844704684317716, "percentage": 89.69, "elapsed_time": "1:22:46", "remaining_time": "0:09:30", "throughput": 10215.31, "total_tokens": 50729728}
{"current_steps": 52850, "total_steps": 58920, "loss": 0.0, "lr": 6.398716422528383e-08, "epoch": 4.48489477257298, "percentage": 89.7, "elapsed_time": "1:22:46", "remaining_time": "0:09:30", "throughput": 10215.52, "total_tokens": 50734720}
{"current_steps": 52855, "total_steps": 58920, "loss": 0.0, "lr": 6.388294590321929e-08, "epoch": 4.485319076714188, "percentage": 89.71, "elapsed_time": "1:22:46", "remaining_time": "0:09:29", "throughput": 10215.69, "total_tokens": 50739456}
{"current_steps": 52860, "total_steps": 58920, "loss": 0.0, "lr": 6.377880972204653e-08, "epoch": 4.485743380855397, "percentage": 89.71, "elapsed_time": "1:22:47", "remaining_time": "0:09:29", "throughput": 10215.89, "total_tokens": 50744448}
{"current_steps": 52865, "total_steps": 58920, "loss": 0.0, "lr": 6.367475569090297e-08, "epoch": 4.486167684996605, "percentage": 89.72, "elapsed_time": "1:22:47", "remaining_time": "0:09:28", "throughput": 10216.0, "total_tokens": 50748800}
{"current_steps": 52870, "total_steps": 58920, "loss": 0.0, "lr": 6.357078381891889e-08, "epoch": 4.486591989137814, "percentage": 89.73, "elapsed_time": "1:22:47", "remaining_time": "0:09:28", "throughput": 10216.17, "total_tokens": 50753472}
{"current_steps": 52875, "total_steps": 58920, "loss": 0.0, "lr": 6.346689411521766e-08, "epoch": 4.487016293279022, "percentage": 89.74, "elapsed_time": "1:22:48", "remaining_time": "0:09:28", "throughput": 10216.35, "total_tokens": 50758272}
{"current_steps": 52880, "total_steps": 58920, "loss": 0.0, "lr": 6.33630865889152e-08, "epoch": 4.487440597420231, "percentage": 89.75, "elapsed_time": "1:22:48", "remaining_time": "0:09:27", "throughput": 10216.47, "total_tokens": 50762688}
{"current_steps": 52885, "total_steps": 58920, "loss": 0.0, "lr": 6.325936124912013e-08, "epoch": 4.487864901561439, "percentage": 89.76, "elapsed_time": "1:22:49", "remaining_time": "0:09:27", "throughput": 10216.66, "total_tokens": 50767616}
{"current_steps": 52890, "total_steps": 58920, "loss": 0.0, "lr": 6.315571810493392e-08, "epoch": 4.488289205702648, "percentage": 89.77, "elapsed_time": "1:22:49", "remaining_time": "0:09:26", "throughput": 10216.79, "total_tokens": 50772096}
{"current_steps": 52895, "total_steps": 58920, "loss": 0.0, "lr": 6.305215716545109e-08, "epoch": 4.488713509843856, "percentage": 89.77, "elapsed_time": "1:22:49", "remaining_time": "0:09:26", "throughput": 10216.85, "total_tokens": 50776192}
{"current_steps": 52900, "total_steps": 58920, "loss": 0.0, "lr": 6.29486784397586e-08, "epoch": 4.489137813985065, "percentage": 89.78, "elapsed_time": "1:22:50", "remaining_time": "0:09:25", "throughput": 10217.33, "total_tokens": 50782976}
{"current_steps": 52905, "total_steps": 58920, "loss": 0.0, "lr": 6.28452819369364e-08, "epoch": 4.489562118126273, "percentage": 89.79, "elapsed_time": "1:22:50", "remaining_time": "0:09:25", "throughput": 10217.53, "total_tokens": 50787904}
{"current_steps": 52910, "total_steps": 58920, "loss": 0.0, "lr": 6.274196766605711e-08, "epoch": 4.4899864222674815, "percentage": 89.8, "elapsed_time": "1:22:51", "remaining_time": "0:09:24", "throughput": 10217.74, "total_tokens": 50792896}
{"current_steps": 52915, "total_steps": 58920, "loss": 0.0, "lr": 6.263873563618616e-08, "epoch": 4.490410726408689, "percentage": 89.81, "elapsed_time": "1:22:51", "remaining_time": "0:09:24", "throughput": 10217.86, "total_tokens": 50797376}
{"current_steps": 52920, "total_steps": 58920, "loss": 0.0, "lr": 6.253558585638185e-08, "epoch": 4.490835030549898, "percentage": 89.82, "elapsed_time": "1:22:51", "remaining_time": "0:09:23", "throughput": 10217.97, "total_tokens": 50801728}
{"current_steps": 52925, "total_steps": 58920, "loss": 0.0, "lr": 6.243251833569508e-08, "epoch": 4.491259334691106, "percentage": 89.83, "elapsed_time": "1:22:52", "remaining_time": "0:09:23", "throughput": 10218.2, "total_tokens": 50806848}
{"current_steps": 52930, "total_steps": 58920, "loss": 0.0, "lr": 6.232953308317002e-08, "epoch": 4.491683638832315, "percentage": 89.83, "elapsed_time": "1:22:52", "remaining_time": "0:09:22", "throughput": 10218.46, "total_tokens": 50812160}
{"current_steps": 52935, "total_steps": 58920, "loss": 0.0, "lr": 6.222663010784269e-08, "epoch": 4.492107942973523, "percentage": 89.84, "elapsed_time": "1:22:52", "remaining_time": "0:09:22", "throughput": 10218.71, "total_tokens": 50817408}
{"current_steps": 52940, "total_steps": 58920, "loss": 0.0, "lr": 6.212380941874296e-08, "epoch": 4.492532247114732, "percentage": 89.85, "elapsed_time": "1:22:53", "remaining_time": "0:09:21", "throughput": 10218.84, "total_tokens": 50821888}
{"current_steps": 52945, "total_steps": 58920, "loss": 0.0, "lr": 6.202107102489274e-08, "epoch": 4.49295655125594, "percentage": 89.86, "elapsed_time": "1:22:53", "remaining_time": "0:09:21", "throughput": 10218.96, "total_tokens": 50826304}
{"current_steps": 52950, "total_steps": 58920, "loss": 0.0, "lr": 6.191841493530691e-08, "epoch": 4.493380855397149, "percentage": 89.87, "elapsed_time": "1:22:54", "remaining_time": "0:09:20", "throughput": 10219.14, "total_tokens": 50831104}
{"current_steps": 52955, "total_steps": 58920, "loss": 0.0, "lr": 6.18158411589933e-08, "epoch": 4.493805159538357, "percentage": 89.88, "elapsed_time": "1:22:54", "remaining_time": "0:09:20", "throughput": 10219.34, "total_tokens": 50836032}
{"current_steps": 52960, "total_steps": 58920, "loss": 0.0, "lr": 6.171334970495212e-08, "epoch": 4.494229463679566, "percentage": 89.88, "elapsed_time": "1:22:54", "remaining_time": "0:09:19", "throughput": 10219.48, "total_tokens": 50840576}
{"current_steps": 52965, "total_steps": 58920, "loss": 0.0, "lr": 6.161094058217709e-08, "epoch": 4.494653767820774, "percentage": 89.89, "elapsed_time": "1:22:55", "remaining_time": "0:09:19", "throughput": 10219.67, "total_tokens": 50845504}
{"current_steps": 52970, "total_steps": 58920, "loss": 0.0, "lr": 6.150861379965377e-08, "epoch": 4.4950780719619825, "percentage": 89.9, "elapsed_time": "1:22:55", "remaining_time": "0:09:18", "throughput": 10219.87, "total_tokens": 50850432}
{"current_steps": 52975, "total_steps": 58920, "loss": 0.0, "lr": 6.140636936636146e-08, "epoch": 4.4955023761031905, "percentage": 89.91, "elapsed_time": "1:22:56", "remaining_time": "0:09:18", "throughput": 10220.1, "total_tokens": 50855488}
{"current_steps": 52980, "total_steps": 58920, "loss": 0.0, "lr": 6.130420729127117e-08, "epoch": 4.495926680244399, "percentage": 89.92, "elapsed_time": "1:22:56", "remaining_time": "0:09:17", "throughput": 10220.28, "total_tokens": 50860288}
{"current_steps": 52985, "total_steps": 58920, "loss": 0.0, "lr": 6.120212758334764e-08, "epoch": 4.496350984385607, "percentage": 89.93, "elapsed_time": "1:22:56", "remaining_time": "0:09:17", "throughput": 10220.51, "total_tokens": 50865408}
{"current_steps": 52990, "total_steps": 58920, "loss": 0.0, "lr": 6.110013025154815e-08, "epoch": 4.496775288526816, "percentage": 89.94, "elapsed_time": "1:22:57", "remaining_time": "0:09:16", "throughput": 10220.73, "total_tokens": 50870464}
{"current_steps": 52995, "total_steps": 58920, "loss": 0.0, "lr": 6.099821530482196e-08, "epoch": 4.497199592668024, "percentage": 89.94, "elapsed_time": "1:22:57", "remaining_time": "0:09:16", "throughput": 10220.92, "total_tokens": 50875328}
{"current_steps": 53000, "total_steps": 58920, "loss": 0.0, "lr": 6.08963827521124e-08, "epoch": 4.497623896809233, "percentage": 89.95, "elapsed_time": "1:22:57", "remaining_time": "0:09:16", "throughput": 10221.04, "total_tokens": 50879744}
{"current_steps": 53005, "total_steps": 58920, "loss": 0.0, "lr": 6.07946326023544e-08, "epoch": 4.498048200950441, "percentage": 89.96, "elapsed_time": "1:22:58", "remaining_time": "0:09:15", "throughput": 10221.16, "total_tokens": 50884160}
{"current_steps": 53010, "total_steps": 58920, "loss": 0.0, "lr": 6.069296486447661e-08, "epoch": 4.49847250509165, "percentage": 89.97, "elapsed_time": "1:22:58", "remaining_time": "0:09:15", "throughput": 10221.29, "total_tokens": 50888640}
{"current_steps": 53015, "total_steps": 58920, "loss": 0.0, "lr": 6.059137954739957e-08, "epoch": 4.498896809232858, "percentage": 89.98, "elapsed_time": "1:22:59", "remaining_time": "0:09:14", "throughput": 10221.45, "total_tokens": 50893376}
{"current_steps": 53020, "total_steps": 58920, "loss": 0.0, "lr": 6.048987666003746e-08, "epoch": 4.499321113374067, "percentage": 89.99, "elapsed_time": "1:22:59", "remaining_time": "0:09:14", "throughput": 10221.64, "total_tokens": 50898240}
{"current_steps": 53025, "total_steps": 58920, "loss": 0.0, "lr": 6.038845621129663e-08, "epoch": 4.499745417515275, "percentage": 89.99, "elapsed_time": "1:22:59", "remaining_time": "0:09:13", "throughput": 10221.8, "total_tokens": 50902912}
{"current_steps": 53028, "total_steps": 58920, "eval_loss": 0.17595630884170532, "epoch": 4.5, "percentage": 90.0, "elapsed_time": "1:23:16", "remaining_time": "0:09:15", "throughput": 10188.42, "total_tokens": 50906176}
{"current_steps": 53030, "total_steps": 58920, "loss": 0.0, "lr": 6.028711821007604e-08, "epoch": 4.5001697216564835, "percentage": 90.0, "elapsed_time": "1:23:50", "remaining_time": "0:09:18", "throughput": 10119.95, "total_tokens": 50908160}
{"current_steps": 53035, "total_steps": 58920, "loss": 0.0, "lr": 6.018586266526837e-08, "epoch": 4.5005940257976915, "percentage": 90.01, "elapsed_time": "1:23:50", "remaining_time": "0:09:18", "throughput": 10120.12, "total_tokens": 50912832}
{"current_steps": 53040, "total_steps": 58920, "loss": 0.0, "lr": 6.008468958575774e-08, "epoch": 4.5010183299389, "percentage": 90.02, "elapsed_time": "1:23:51", "remaining_time": "0:09:17", "throughput": 10120.27, "total_tokens": 50917440}
{"current_steps": 53045, "total_steps": 58920, "loss": 0.0, "lr": 5.998359898042216e-08, "epoch": 4.501442634080108, "percentage": 90.03, "elapsed_time": "1:23:51", "remaining_time": "0:09:17", "throughput": 10120.41, "total_tokens": 50921920}
{"current_steps": 53050, "total_steps": 58920, "loss": 0.0, "lr": 5.988259085813185e-08, "epoch": 4.501866938221317, "percentage": 90.04, "elapsed_time": "1:23:51", "remaining_time": "0:09:16", "throughput": 10120.63, "total_tokens": 50926976}
{"current_steps": 53055, "total_steps": 58920, "loss": 0.0, "lr": 5.978166522774997e-08, "epoch": 4.502291242362525, "percentage": 90.05, "elapsed_time": "1:23:52", "remaining_time": "0:09:16", "throughput": 10120.76, "total_tokens": 50931456}
{"current_steps": 53060, "total_steps": 58920, "loss": 0.0, "lr": 5.96808220981323e-08, "epoch": 4.502715546503734, "percentage": 90.05, "elapsed_time": "1:23:52", "remaining_time": "0:09:15", "throughput": 10121.06, "total_tokens": 50936960}
{"current_steps": 53065, "total_steps": 58920, "loss": 0.0, "lr": 5.958006147812744e-08, "epoch": 4.503139850644942, "percentage": 90.06, "elapsed_time": "1:23:53", "remaining_time": "0:09:15", "throughput": 10121.21, "total_tokens": 50941632}
{"current_steps": 53070, "total_steps": 58920, "loss": 0.0, "lr": 5.947938337657688e-08, "epoch": 4.503564154786151, "percentage": 90.07, "elapsed_time": "1:23:53", "remaining_time": "0:09:14", "throughput": 10121.35, "total_tokens": 50946176}
{"current_steps": 53075, "total_steps": 58920, "loss": 0.0, "lr": 5.9378787802314644e-08, "epoch": 4.503988458927359, "percentage": 90.08, "elapsed_time": "1:23:53", "remaining_time": "0:09:14", "throughput": 10121.47, "total_tokens": 50950528}
{"current_steps": 53080, "total_steps": 58920, "loss": 0.0, "lr": 5.927827476416769e-08, "epoch": 4.504412763068568, "percentage": 90.09, "elapsed_time": "1:23:54", "remaining_time": "0:09:13", "throughput": 10121.61, "total_tokens": 50955072}
{"current_steps": 53085, "total_steps": 58920, "loss": 0.0, "lr": 5.917784427095562e-08, "epoch": 4.504837067209776, "percentage": 90.1, "elapsed_time": "1:23:54", "remaining_time": "0:09:13", "throughput": 10121.81, "total_tokens": 50960064}
{"current_steps": 53090, "total_steps": 58920, "loss": 0.0, "lr": 5.907749633149095e-08, "epoch": 4.505261371350985, "percentage": 90.11, "elapsed_time": "1:23:55", "remaining_time": "0:09:12", "throughput": 10122.13, "total_tokens": 50965760}
{"current_steps": 53095, "total_steps": 58920, "loss": 0.0, "lr": 5.8977230954578735e-08, "epoch": 4.505685675492193, "percentage": 90.11, "elapsed_time": "1:23:55", "remaining_time": "0:09:12", "throughput": 10122.31, "total_tokens": 50970560}
{"current_steps": 53100, "total_steps": 58920, "loss": 0.0264, "lr": 5.8877048149017064e-08, "epoch": 4.506109979633401, "percentage": 90.12, "elapsed_time": "1:23:55", "remaining_time": "0:09:11", "throughput": 10122.51, "total_tokens": 50975488}
{"current_steps": 53105, "total_steps": 58920, "loss": 0.0, "lr": 5.8776947923596444e-08, "epoch": 4.506534283774609, "percentage": 90.13, "elapsed_time": "1:23:56", "remaining_time": "0:09:11", "throughput": 10122.65, "total_tokens": 50980032}
{"current_steps": 53110, "total_steps": 58920, "loss": 0.0, "lr": 5.86769302871003e-08, "epoch": 4.506958587915818, "percentage": 90.14, "elapsed_time": "1:23:56", "remaining_time": "0:09:10", "throughput": 10122.9, "total_tokens": 50985344}
{"current_steps": 53115, "total_steps": 58920, "loss": 0.0, "lr": 5.857699524830495e-08, "epoch": 4.507382892057026, "percentage": 90.15, "elapsed_time": "1:23:57", "remaining_time": "0:09:10", "throughput": 10123.1, "total_tokens": 50990208}
{"current_steps": 53120, "total_steps": 58920, "loss": 0.0, "lr": 5.8477142815979264e-08, "epoch": 4.507807196198235, "percentage": 90.16, "elapsed_time": "1:23:57", "remaining_time": "0:09:10", "throughput": 10123.18, "total_tokens": 50994368}
{"current_steps": 53125, "total_steps": 58920, "loss": 0.0, "lr": 5.837737299888501e-08, "epoch": 4.508231500339443, "percentage": 90.16, "elapsed_time": "1:23:57", "remaining_time": "0:09:09", "throughput": 10123.31, "total_tokens": 50998848}
{"current_steps": 53130, "total_steps": 58920, "loss": 0.0, "lr": 5.827768580577641e-08, "epoch": 4.508655804480652, "percentage": 90.17, "elapsed_time": "1:23:58", "remaining_time": "0:09:09", "throughput": 10123.5, "total_tokens": 51003648}
{"current_steps": 53135, "total_steps": 58920, "loss": 0.0, "lr": 5.817808124540091e-08, "epoch": 4.50908010862186, "percentage": 90.18, "elapsed_time": "1:23:58", "remaining_time": "0:09:08", "throughput": 10123.7, "total_tokens": 51008576}
{"current_steps": 53140, "total_steps": 58920, "loss": 0.0278, "lr": 5.8078559326498414e-08, "epoch": 4.509504412763069, "percentage": 90.19, "elapsed_time": "1:23:58", "remaining_time": "0:09:08", "throughput": 10123.83, "total_tokens": 51012992}
{"current_steps": 53145, "total_steps": 58920, "loss": 0.0, "lr": 5.797912005780148e-08, "epoch": 4.509928716904277, "percentage": 90.2, "elapsed_time": "1:23:59", "remaining_time": "0:09:07", "throughput": 10124.05, "total_tokens": 51018048}
{"current_steps": 53150, "total_steps": 58920, "loss": 0.0, "lr": 5.7879763448035576e-08, "epoch": 4.510353021045486, "percentage": 90.21, "elapsed_time": "1:23:59", "remaining_time": "0:09:07", "throughput": 10124.29, "total_tokens": 51023232}
{"current_steps": 53155, "total_steps": 58920, "loss": 0.0, "lr": 5.778048950591885e-08, "epoch": 4.510777325186694, "percentage": 90.22, "elapsed_time": "1:24:00", "remaining_time": "0:09:06", "throughput": 10124.41, "total_tokens": 51027648}
{"current_steps": 53160, "total_steps": 58920, "loss": 0.0, "lr": 5.7681298240162436e-08, "epoch": 4.5112016293279025, "percentage": 90.22, "elapsed_time": "1:24:00", "remaining_time": "0:09:06", "throughput": 10124.62, "total_tokens": 51032640}
{"current_steps": 53165, "total_steps": 58920, "loss": 0.0, "lr": 5.758218965946981e-08, "epoch": 4.5116259334691104, "percentage": 90.23, "elapsed_time": "1:24:00", "remaining_time": "0:09:05", "throughput": 10124.77, "total_tokens": 51037184}
{"current_steps": 53170, "total_steps": 58920, "loss": 0.0, "lr": 5.748316377253748e-08, "epoch": 4.512050237610319, "percentage": 90.24, "elapsed_time": "1:24:01", "remaining_time": "0:09:05", "throughput": 10124.92, "total_tokens": 51041792}
{"current_steps": 53175, "total_steps": 58920, "loss": 0.0, "lr": 5.738422058805437e-08, "epoch": 4.512474541751527, "percentage": 90.25, "elapsed_time": "1:24:01", "remaining_time": "0:09:04", "throughput": 10125.23, "total_tokens": 51047424}
{"current_steps": 53180, "total_steps": 58920, "loss": 0.0, "lr": 5.7285360114702974e-08, "epoch": 4.512898845892736, "percentage": 90.26, "elapsed_time": "1:24:01", "remaining_time": "0:09:04", "throughput": 10125.35, "total_tokens": 51051840}
{"current_steps": 53185, "total_steps": 58920, "loss": 0.0, "lr": 5.718658236115725e-08, "epoch": 4.513323150033944, "percentage": 90.27, "elapsed_time": "1:24:02", "remaining_time": "0:09:03", "throughput": 10125.46, "total_tokens": 51056192}
{"current_steps": 53190, "total_steps": 58920, "loss": 0.0, "lr": 5.708788733608527e-08, "epoch": 4.513747454175153, "percentage": 90.27, "elapsed_time": "1:24:02", "remaining_time": "0:09:03", "throughput": 10125.56, "total_tokens": 51060480}
{"current_steps": 53195, "total_steps": 58920, "loss": 0.0, "lr": 5.6989275048146544e-08, "epoch": 4.514171758316361, "percentage": 90.28, "elapsed_time": "1:24:03", "remaining_time": "0:09:02", "throughput": 10125.74, "total_tokens": 51065216}
{"current_steps": 53200, "total_steps": 58920, "loss": 0.0, "lr": 5.6890745505994154e-08, "epoch": 4.51459606245757, "percentage": 90.29, "elapsed_time": "1:24:03", "remaining_time": "0:09:02", "throughput": 10125.89, "total_tokens": 51069824}
{"current_steps": 53205, "total_steps": 58920, "loss": 0.0, "lr": 5.679229871827396e-08, "epoch": 4.515020366598778, "percentage": 90.3, "elapsed_time": "1:24:03", "remaining_time": "0:09:01", "throughput": 10126.1, "total_tokens": 51074816}
{"current_steps": 53210, "total_steps": 58920, "loss": 0.0, "lr": 5.6693934693623935e-08, "epoch": 4.515444670739987, "percentage": 90.31, "elapsed_time": "1:24:04", "remaining_time": "0:09:01", "throughput": 10126.26, "total_tokens": 51079488}
{"current_steps": 53215, "total_steps": 58920, "loss": 0.0, "lr": 5.659565344067552e-08, "epoch": 4.515868974881195, "percentage": 90.32, "elapsed_time": "1:24:04", "remaining_time": "0:09:00", "throughput": 10126.39, "total_tokens": 51083968}
{"current_steps": 53220, "total_steps": 58920, "loss": 0.0, "lr": 5.6497454968052136e-08, "epoch": 4.5162932790224035, "percentage": 90.33, "elapsed_time": "1:24:05", "remaining_time": "0:09:00", "throughput": 10126.58, "total_tokens": 51088832}
{"current_steps": 53225, "total_steps": 58920, "loss": 0.0, "lr": 5.6399339284370904e-08, "epoch": 4.5167175831636115, "percentage": 90.33, "elapsed_time": "1:24:05", "remaining_time": "0:08:59", "throughput": 10126.78, "total_tokens": 51093760}
{"current_steps": 53230, "total_steps": 58920, "loss": 0.0, "lr": 5.6301306398240376e-08, "epoch": 4.51714188730482, "percentage": 90.34, "elapsed_time": "1:24:05", "remaining_time": "0:08:59", "throughput": 10126.85, "total_tokens": 51097856}
{"current_steps": 53235, "total_steps": 58920, "loss": 0.0, "lr": 5.620335631826334e-08, "epoch": 4.517566191446028, "percentage": 90.35, "elapsed_time": "1:24:06", "remaining_time": "0:08:58", "throughput": 10126.98, "total_tokens": 51102272}
{"current_steps": 53240, "total_steps": 58920, "loss": 0.0, "lr": 5.610548905303425e-08, "epoch": 4.517990495587237, "percentage": 90.36, "elapsed_time": "1:24:06", "remaining_time": "0:08:58", "throughput": 10127.11, "total_tokens": 51106752}
{"current_steps": 53245, "total_steps": 58920, "loss": 0.0, "lr": 5.600770461114024e-08, "epoch": 4.518414799728445, "percentage": 90.37, "elapsed_time": "1:24:06", "remaining_time": "0:08:57", "throughput": 10127.34, "total_tokens": 51111808}
{"current_steps": 53250, "total_steps": 58920, "loss": 0.0, "lr": 5.591000300116222e-08, "epoch": 4.518839103869654, "percentage": 90.38, "elapsed_time": "1:24:07", "remaining_time": "0:08:57", "throughput": 10127.51, "total_tokens": 51116480}
{"current_steps": 53255, "total_steps": 58920, "loss": 0.0, "lr": 5.581238423167256e-08, "epoch": 4.519263408010862, "percentage": 90.39, "elapsed_time": "1:24:07", "remaining_time": "0:08:56", "throughput": 10127.69, "total_tokens": 51121216}
{"current_steps": 53260, "total_steps": 58920, "loss": 0.0, "lr": 5.57148483112373e-08, "epoch": 4.519687712152071, "percentage": 90.39, "elapsed_time": "1:24:08", "remaining_time": "0:08:56", "throughput": 10127.82, "total_tokens": 51125696}
{"current_steps": 53265, "total_steps": 58920, "loss": 0.0, "lr": 5.56173952484148e-08, "epoch": 4.520112016293279, "percentage": 90.4, "elapsed_time": "1:24:08", "remaining_time": "0:08:55", "throughput": 10127.98, "total_tokens": 51130304}
{"current_steps": 53270, "total_steps": 58920, "loss": 0.0, "lr": 5.5520025051756236e-08, "epoch": 4.520536320434488, "percentage": 90.41, "elapsed_time": "1:24:08", "remaining_time": "0:08:55", "throughput": 10128.22, "total_tokens": 51135488}
{"current_steps": 53275, "total_steps": 58920, "loss": 0.0, "lr": 5.542273772980544e-08, "epoch": 4.520960624575696, "percentage": 90.42, "elapsed_time": "1:24:09", "remaining_time": "0:08:55", "throughput": 10128.61, "total_tokens": 51141568}
{"current_steps": 53280, "total_steps": 58920, "loss": 0.0, "lr": 5.53255332910989e-08, "epoch": 4.521384928716905, "percentage": 90.43, "elapsed_time": "1:24:09", "remaining_time": "0:08:54", "throughput": 10128.78, "total_tokens": 51146240}
{"current_steps": 53285, "total_steps": 58920, "loss": 0.0, "lr": 5.522841174416615e-08, "epoch": 4.5218092328581125, "percentage": 90.44, "elapsed_time": "1:24:09", "remaining_time": "0:08:54", "throughput": 10129.04, "total_tokens": 51151616}
{"current_steps": 53290, "total_steps": 58920, "loss": 0.0, "lr": 5.513137309752924e-08, "epoch": 4.522233536999321, "percentage": 90.44, "elapsed_time": "1:24:10", "remaining_time": "0:08:53", "throughput": 10129.3, "total_tokens": 51156864}
{"current_steps": 53295, "total_steps": 58920, "loss": 0.0, "lr": 5.5034417359702823e-08, "epoch": 4.522657841140529, "percentage": 90.45, "elapsed_time": "1:24:10", "remaining_time": "0:08:53", "throughput": 10129.55, "total_tokens": 51162112}
{"current_steps": 53300, "total_steps": 58920, "loss": 0.0, "lr": 5.4937544539194525e-08, "epoch": 4.523082145281738, "percentage": 90.46, "elapsed_time": "1:24:11", "remaining_time": "0:08:52", "throughput": 10129.84, "total_tokens": 51167616}
{"current_steps": 53305, "total_steps": 58920, "loss": 0.0, "lr": 5.484075464450455e-08, "epoch": 4.523506449422946, "percentage": 90.47, "elapsed_time": "1:24:11", "remaining_time": "0:08:52", "throughput": 10130.0, "total_tokens": 51172288}
{"current_steps": 53310, "total_steps": 58920, "loss": 0.0, "lr": 5.4744047684125994e-08, "epoch": 4.523930753564155, "percentage": 90.48, "elapsed_time": "1:24:11", "remaining_time": "0:08:51", "throughput": 10130.2, "total_tokens": 51177216}
{"current_steps": 53315, "total_steps": 58920, "loss": 0.0, "lr": 5.464742366654429e-08, "epoch": 4.524355057705363, "percentage": 90.49, "elapsed_time": "1:24:12", "remaining_time": "0:08:51", "throughput": 10130.35, "total_tokens": 51181888}
{"current_steps": 53320, "total_steps": 58920, "loss": 0.0, "lr": 5.455088260023799e-08, "epoch": 4.524779361846572, "percentage": 90.5, "elapsed_time": "1:24:12", "remaining_time": "0:08:50", "throughput": 10130.49, "total_tokens": 51186432}
{"current_steps": 53325, "total_steps": 58920, "loss": 0.0, "lr": 5.4454424493678206e-08, "epoch": 4.52520366598778, "percentage": 90.5, "elapsed_time": "1:24:13", "remaining_time": "0:08:50", "throughput": 10130.74, "total_tokens": 51191616}
{"current_steps": 53330, "total_steps": 58920, "loss": 0.0, "lr": 5.435804935532884e-08, "epoch": 4.525627970128989, "percentage": 90.51, "elapsed_time": "1:24:13", "remaining_time": "0:08:49", "throughput": 10130.9, "total_tokens": 51196288}
{"current_steps": 53335, "total_steps": 58920, "loss": 0.0, "lr": 5.426175719364634e-08, "epoch": 4.526052274270197, "percentage": 90.52, "elapsed_time": "1:24:13", "remaining_time": "0:08:49", "throughput": 10131.16, "total_tokens": 51201600}
{"current_steps": 53340, "total_steps": 58920, "loss": 0.0, "lr": 5.416554801708017e-08, "epoch": 4.526476578411406, "percentage": 90.53, "elapsed_time": "1:24:14", "remaining_time": "0:08:48", "throughput": 10131.36, "total_tokens": 51206528}
{"current_steps": 53345, "total_steps": 58920, "loss": 0.0, "lr": 5.406942183407215e-08, "epoch": 4.526900882552614, "percentage": 90.54, "elapsed_time": "1:24:14", "remaining_time": "0:08:48", "throughput": 10131.54, "total_tokens": 51211328}
{"current_steps": 53350, "total_steps": 58920, "loss": 0.0, "lr": 5.397337865305718e-08, "epoch": 4.5273251866938224, "percentage": 90.55, "elapsed_time": "1:24:15", "remaining_time": "0:08:47", "throughput": 10131.69, "total_tokens": 51216000}
{"current_steps": 53355, "total_steps": 58920, "loss": 0.0, "lr": 5.387741848246252e-08, "epoch": 4.52774949083503, "percentage": 90.55, "elapsed_time": "1:24:15", "remaining_time": "0:08:47", "throughput": 10131.86, "total_tokens": 51220736}
{"current_steps": 53360, "total_steps": 58920, "loss": 0.0, "lr": 5.3781541330708557e-08, "epoch": 4.528173794976239, "percentage": 90.56, "elapsed_time": "1:24:15", "remaining_time": "0:08:46", "throughput": 10132.04, "total_tokens": 51225600}
{"current_steps": 53365, "total_steps": 58920, "loss": 0.0, "lr": 5.3685747206207885e-08, "epoch": 4.528598099117447, "percentage": 90.57, "elapsed_time": "1:24:16", "remaining_time": "0:08:46", "throughput": 10132.51, "total_tokens": 51232384}
{"current_steps": 53370, "total_steps": 58920, "loss": 0.0, "lr": 5.3590036117366345e-08, "epoch": 4.529022403258656, "percentage": 90.58, "elapsed_time": "1:24:16", "remaining_time": "0:08:45", "throughput": 10132.63, "total_tokens": 51236800}
{"current_steps": 53375, "total_steps": 58920, "loss": 0.0, "lr": 5.3494408072582095e-08, "epoch": 4.529446707399864, "percentage": 90.59, "elapsed_time": "1:24:17", "remaining_time": "0:08:45", "throughput": 10132.8, "total_tokens": 51241600}
{"current_steps": 53380, "total_steps": 58920, "loss": 0.0, "lr": 5.3398863080246214e-08, "epoch": 4.529871011541073, "percentage": 90.6, "elapsed_time": "1:24:17", "remaining_time": "0:08:44", "throughput": 10133.03, "total_tokens": 51246720}
{"current_steps": 53385, "total_steps": 58920, "loss": 0.0, "lr": 5.330340114874243e-08, "epoch": 4.530295315682281, "percentage": 90.61, "elapsed_time": "1:24:17", "remaining_time": "0:08:44", "throughput": 10133.16, "total_tokens": 51251136}
{"current_steps": 53390, "total_steps": 58920, "loss": 0.0, "lr": 5.320802228644694e-08, "epoch": 4.53071961982349, "percentage": 90.61, "elapsed_time": "1:24:18", "remaining_time": "0:08:43", "throughput": 10133.28, "total_tokens": 51255552}
{"current_steps": 53395, "total_steps": 58920, "loss": 0.0, "lr": 5.311272650172949e-08, "epoch": 4.531143923964698, "percentage": 90.62, "elapsed_time": "1:24:18", "remaining_time": "0:08:43", "throughput": 10133.44, "total_tokens": 51260288}
{"current_steps": 53400, "total_steps": 58920, "loss": 0.0, "lr": 5.301751380295116e-08, "epoch": 4.531568228105907, "percentage": 90.63, "elapsed_time": "1:24:18", "remaining_time": "0:08:42", "throughput": 10133.58, "total_tokens": 51264832}
{"current_steps": 53405, "total_steps": 58920, "loss": 0.0, "lr": 5.292238419846728e-08, "epoch": 4.531992532247115, "percentage": 90.64, "elapsed_time": "1:24:19", "remaining_time": "0:08:42", "throughput": 10133.84, "total_tokens": 51270208}
{"current_steps": 53410, "total_steps": 58920, "loss": 0.0, "lr": 5.282733769662473e-08, "epoch": 4.5324168363883235, "percentage": 90.65, "elapsed_time": "1:24:19", "remaining_time": "0:08:41", "throughput": 10134.06, "total_tokens": 51275264}
{"current_steps": 53415, "total_steps": 58920, "loss": 0.0, "lr": 5.273237430576327e-08, "epoch": 4.5328411405295315, "percentage": 90.66, "elapsed_time": "1:24:20", "remaining_time": "0:08:41", "throughput": 10134.24, "total_tokens": 51280064}
{"current_steps": 53420, "total_steps": 58920, "loss": 0.0, "lr": 5.263749403421625e-08, "epoch": 4.53326544467074, "percentage": 90.67, "elapsed_time": "1:24:20", "remaining_time": "0:08:41", "throughput": 10134.38, "total_tokens": 51284672}
{"current_steps": 53425, "total_steps": 58920, "loss": 0.0, "lr": 5.254269689030832e-08, "epoch": 4.533689748811948, "percentage": 90.67, "elapsed_time": "1:24:20", "remaining_time": "0:08:40", "throughput": 10134.47, "total_tokens": 51288960}
{"current_steps": 53430, "total_steps": 58920, "loss": 0.0, "lr": 5.24479828823583e-08, "epoch": 4.534114052953157, "percentage": 90.68, "elapsed_time": "1:24:21", "remaining_time": "0:08:40", "throughput": 10134.66, "total_tokens": 51293888}
{"current_steps": 53435, "total_steps": 58920, "loss": 0.0, "lr": 5.23533520186763e-08, "epoch": 4.534538357094365, "percentage": 90.69, "elapsed_time": "1:24:21", "remaining_time": "0:08:39", "throughput": 10134.97, "total_tokens": 51299584}
{"current_steps": 53440, "total_steps": 58920, "loss": 0.0, "lr": 5.225880430756657e-08, "epoch": 4.534962661235574, "percentage": 90.7, "elapsed_time": "1:24:22", "remaining_time": "0:08:39", "throughput": 10135.11, "total_tokens": 51304256}
{"current_steps": 53445, "total_steps": 58920, "loss": 0.0, "lr": 5.21643397573247e-08, "epoch": 4.535386965376782, "percentage": 90.71, "elapsed_time": "1:24:22", "remaining_time": "0:08:38", "throughput": 10135.32, "total_tokens": 51309376}
{"current_steps": 53450, "total_steps": 58920, "loss": 0.0, "lr": 5.206995837623984e-08, "epoch": 4.535811269517991, "percentage": 90.72, "elapsed_time": "1:24:22", "remaining_time": "0:08:38", "throughput": 10135.49, "total_tokens": 51314176}
{"current_steps": 53455, "total_steps": 58920, "loss": 0.0, "lr": 5.1975660172593914e-08, "epoch": 4.536235573659199, "percentage": 90.72, "elapsed_time": "1:24:23", "remaining_time": "0:08:37", "throughput": 10135.73, "total_tokens": 51319424}
{"current_steps": 53460, "total_steps": 58920, "loss": 0.0, "lr": 5.188144515466064e-08, "epoch": 4.536659877800408, "percentage": 90.73, "elapsed_time": "1:24:23", "remaining_time": "0:08:37", "throughput": 10135.79, "total_tokens": 51323520}
{"current_steps": 53465, "total_steps": 58920, "loss": 0.0, "lr": 5.178731333070774e-08, "epoch": 4.537084181941616, "percentage": 90.74, "elapsed_time": "1:24:23", "remaining_time": "0:08:36", "throughput": 10135.9, "total_tokens": 51328000}
{"current_steps": 53470, "total_steps": 58920, "loss": 0.0, "lr": 5.169326470899427e-08, "epoch": 4.5375084860828245, "percentage": 90.75, "elapsed_time": "1:24:24", "remaining_time": "0:08:36", "throughput": 10136.08, "total_tokens": 51332864}
{"current_steps": 53475, "total_steps": 58920, "loss": 0.0, "lr": 5.1599299297773066e-08, "epoch": 4.5379327902240325, "percentage": 90.76, "elapsed_time": "1:24:24", "remaining_time": "0:08:35", "throughput": 10136.32, "total_tokens": 51338112}
{"current_steps": 53480, "total_steps": 58920, "loss": 0.0, "lr": 5.150541710528922e-08, "epoch": 4.538357094365241, "percentage": 90.77, "elapsed_time": "1:24:25", "remaining_time": "0:08:35", "throughput": 10136.48, "total_tokens": 51342912}
{"current_steps": 53485, "total_steps": 58920, "loss": 0.0, "lr": 5.1411618139780455e-08, "epoch": 4.538781398506449, "percentage": 90.78, "elapsed_time": "1:24:25", "remaining_time": "0:08:34", "throughput": 10136.67, "total_tokens": 51347776}
{"current_steps": 53490, "total_steps": 58920, "loss": 0.0, "lr": 5.131790240947753e-08, "epoch": 4.539205702647658, "percentage": 90.78, "elapsed_time": "1:24:25", "remaining_time": "0:08:34", "throughput": 10136.76, "total_tokens": 51352064}
{"current_steps": 53495, "total_steps": 58920, "loss": 0.0, "lr": 5.122426992260309e-08, "epoch": 4.539630006788866, "percentage": 90.79, "elapsed_time": "1:24:26", "remaining_time": "0:08:33", "throughput": 10136.91, "total_tokens": 51356672}
{"current_steps": 53500, "total_steps": 58920, "loss": 0.0, "lr": 5.1130720687373675e-08, "epoch": 4.540054310930075, "percentage": 90.8, "elapsed_time": "1:24:26", "remaining_time": "0:08:33", "throughput": 10137.04, "total_tokens": 51361216}
{"current_steps": 53505, "total_steps": 58920, "loss": 0.0, "lr": 5.10372547119976e-08, "epoch": 4.540478615071283, "percentage": 90.81, "elapsed_time": "1:24:27", "remaining_time": "0:08:32", "throughput": 10137.19, "total_tokens": 51365888}
{"current_steps": 53510, "total_steps": 58920, "loss": 0.0, "lr": 5.0943872004676206e-08, "epoch": 4.540902919212492, "percentage": 90.82, "elapsed_time": "1:24:27", "remaining_time": "0:08:32", "throughput": 10137.53, "total_tokens": 51371776}
{"current_steps": 53515, "total_steps": 58920, "loss": 0.0, "lr": 5.085057257360348e-08, "epoch": 4.5413272233537, "percentage": 90.83, "elapsed_time": "1:24:27", "remaining_time": "0:08:31", "throughput": 10137.61, "total_tokens": 51375872}
{"current_steps": 53520, "total_steps": 58920, "loss": 0.0, "lr": 5.0757356426966105e-08, "epoch": 4.541751527494909, "percentage": 90.84, "elapsed_time": "1:24:28", "remaining_time": "0:08:31", "throughput": 10137.72, "total_tokens": 51380288}
{"current_steps": 53525, "total_steps": 58920, "loss": 0.0, "lr": 5.066422357294353e-08, "epoch": 4.542175831636117, "percentage": 90.84, "elapsed_time": "1:24:28", "remaining_time": "0:08:30", "throughput": 10137.89, "total_tokens": 51385024}
{"current_steps": 53530, "total_steps": 58920, "loss": 0.0, "lr": 5.0571174019707677e-08, "epoch": 4.542600135777326, "percentage": 90.85, "elapsed_time": "1:24:28", "remaining_time": "0:08:30", "throughput": 10138.0, "total_tokens": 51389376}
{"current_steps": 53535, "total_steps": 58920, "loss": 0.0, "lr": 5.0478207775423445e-08, "epoch": 4.5430244399185336, "percentage": 90.86, "elapsed_time": "1:24:29", "remaining_time": "0:08:29", "throughput": 10138.09, "total_tokens": 51393728}
{"current_steps": 53540, "total_steps": 58920, "loss": 0.0, "lr": 5.038532484824831e-08, "epoch": 4.5434487440597415, "percentage": 90.87, "elapsed_time": "1:24:29", "remaining_time": "0:08:29", "throughput": 10138.27, "total_tokens": 51398528}
{"current_steps": 53545, "total_steps": 58920, "loss": 0.0, "lr": 5.029252524633232e-08, "epoch": 4.54387304820095, "percentage": 90.88, "elapsed_time": "1:24:30", "remaining_time": "0:08:28", "throughput": 10138.5, "total_tokens": 51403648}
{"current_steps": 53550, "total_steps": 58920, "loss": 0.0, "lr": 5.019980897781828e-08, "epoch": 4.544297352342159, "percentage": 90.89, "elapsed_time": "1:24:30", "remaining_time": "0:08:28", "throughput": 10138.6, "total_tokens": 51408000}
{"current_steps": 53555, "total_steps": 58920, "loss": 0.0, "lr": 5.0107176050841806e-08, "epoch": 4.544721656483367, "percentage": 90.89, "elapsed_time": "1:24:30", "remaining_time": "0:08:27", "throughput": 10138.77, "total_tokens": 51412736}
{"current_steps": 53560, "total_steps": 58920, "loss": 0.0, "lr": 5.001462647353105e-08, "epoch": 4.545145960624575, "percentage": 90.9, "elapsed_time": "1:24:31", "remaining_time": "0:08:27", "throughput": 10138.97, "total_tokens": 51417728}
{"current_steps": 53565, "total_steps": 58920, "loss": 0.0, "lr": 4.9922160254006976e-08, "epoch": 4.545570264765784, "percentage": 90.91, "elapsed_time": "1:24:31", "remaining_time": "0:08:27", "throughput": 10139.1, "total_tokens": 51422208}
{"current_steps": 53570, "total_steps": 58920, "loss": 0.0, "lr": 4.982977740038308e-08, "epoch": 4.545994568906993, "percentage": 90.92, "elapsed_time": "1:24:32", "remaining_time": "0:08:26", "throughput": 10139.26, "total_tokens": 51426944}
{"current_steps": 53575, "total_steps": 58920, "loss": 0.0, "lr": 4.9737477920765545e-08, "epoch": 4.546418873048201, "percentage": 90.93, "elapsed_time": "1:24:32", "remaining_time": "0:08:26", "throughput": 10139.49, "total_tokens": 51432064}
{"current_steps": 53580, "total_steps": 58920, "loss": 0.0, "lr": 4.9645261823253456e-08, "epoch": 4.546843177189409, "percentage": 90.94, "elapsed_time": "1:24:32", "remaining_time": "0:08:25", "throughput": 10139.59, "total_tokens": 51436352}
{"current_steps": 53585, "total_steps": 58920, "loss": 0.0, "lr": 4.9553129115938454e-08, "epoch": 4.547267481330618, "percentage": 90.95, "elapsed_time": "1:24:33", "remaining_time": "0:08:25", "throughput": 10139.7, "total_tokens": 51440704}
{"current_steps": 53590, "total_steps": 58920, "loss": 0.0, "lr": 4.9461079806904726e-08, "epoch": 4.547691785471827, "percentage": 90.95, "elapsed_time": "1:24:33", "remaining_time": "0:08:24", "throughput": 10139.93, "total_tokens": 51445824}
{"current_steps": 53595, "total_steps": 58920, "loss": 0.0, "lr": 4.936911390422937e-08, "epoch": 4.548116089613035, "percentage": 90.96, "elapsed_time": "1:24:33", "remaining_time": "0:08:24", "throughput": 10140.13, "total_tokens": 51450752}
{"current_steps": 53600, "total_steps": 58920, "loss": 0.0, "lr": 4.927723141598206e-08, "epoch": 4.548540393754243, "percentage": 90.97, "elapsed_time": "1:24:34", "remaining_time": "0:08:23", "throughput": 10140.33, "total_tokens": 51455680}
{"current_steps": 53605, "total_steps": 58920, "loss": 0.0, "lr": 4.9185432350224875e-08, "epoch": 4.548964697895451, "percentage": 90.98, "elapsed_time": "1:24:34", "remaining_time": "0:08:23", "throughput": 10140.5, "total_tokens": 51460416}
{"current_steps": 53610, "total_steps": 58920, "loss": 0.0, "lr": 4.90937167150135e-08, "epoch": 4.54938900203666, "percentage": 90.99, "elapsed_time": "1:24:35", "remaining_time": "0:08:22", "throughput": 10140.77, "total_tokens": 51465792}
{"current_steps": 53615, "total_steps": 58920, "loss": 0.0, "lr": 4.900208451839505e-08, "epoch": 4.549813306177868, "percentage": 91.0, "elapsed_time": "1:24:35", "remaining_time": "0:08:22", "throughput": 10140.91, "total_tokens": 51470400}
{"current_steps": 53620, "total_steps": 58920, "loss": 0.0, "lr": 4.89105357684102e-08, "epoch": 4.550237610319076, "percentage": 91.0, "elapsed_time": "1:24:35", "remaining_time": "0:08:21", "throughput": 10141.06, "total_tokens": 51474944}
{"current_steps": 53625, "total_steps": 58920, "loss": 0.0, "lr": 4.881907047309186e-08, "epoch": 4.550661914460285, "percentage": 91.01, "elapsed_time": "1:24:36", "remaining_time": "0:08:21", "throughput": 10141.27, "total_tokens": 51480000}
{"current_steps": 53630, "total_steps": 58920, "loss": 0.0, "lr": 4.872768864046572e-08, "epoch": 4.551086218601494, "percentage": 91.02, "elapsed_time": "1:24:36", "remaining_time": "0:08:20", "throughput": 10141.44, "total_tokens": 51484736}
{"current_steps": 53635, "total_steps": 58920, "loss": 0.0, "lr": 4.86363902785506e-08, "epoch": 4.551510522742702, "percentage": 91.03, "elapsed_time": "1:24:37", "remaining_time": "0:08:20", "throughput": 10141.61, "total_tokens": 51489408}
{"current_steps": 53640, "total_steps": 58920, "loss": 0.0, "lr": 4.854517539535718e-08, "epoch": 4.55193482688391, "percentage": 91.04, "elapsed_time": "1:24:37", "remaining_time": "0:08:19", "throughput": 10141.71, "total_tokens": 51493696}
{"current_steps": 53645, "total_steps": 58920, "loss": 0.0, "lr": 4.8454043998889526e-08, "epoch": 4.552359131025119, "percentage": 91.05, "elapsed_time": "1:24:37", "remaining_time": "0:08:19", "throughput": 10141.93, "total_tokens": 51498752}
{"current_steps": 53650, "total_steps": 58920, "loss": 0.0, "lr": 4.836299609714378e-08, "epoch": 4.552783435166328, "percentage": 91.06, "elapsed_time": "1:24:38", "remaining_time": "0:08:18", "throughput": 10142.21, "total_tokens": 51504192}
{"current_steps": 53655, "total_steps": 58920, "loss": 0.0, "lr": 4.8272031698109564e-08, "epoch": 4.553207739307536, "percentage": 91.06, "elapsed_time": "1:24:38", "remaining_time": "0:08:18", "throughput": 10142.42, "total_tokens": 51509184}
{"current_steps": 53660, "total_steps": 58920, "loss": 0.0, "lr": 4.818115080976826e-08, "epoch": 4.553632043448744, "percentage": 91.07, "elapsed_time": "1:24:38", "remaining_time": "0:08:17", "throughput": 10142.55, "total_tokens": 51513664}
{"current_steps": 53665, "total_steps": 58920, "loss": 0.0, "lr": 4.809035344009416e-08, "epoch": 4.5540563475899525, "percentage": 91.08, "elapsed_time": "1:24:39", "remaining_time": "0:08:17", "throughput": 10142.72, "total_tokens": 51518336}
{"current_steps": 53670, "total_steps": 58920, "loss": 0.0, "lr": 4.799963959705511e-08, "epoch": 4.554480651731161, "percentage": 91.09, "elapsed_time": "1:24:39", "remaining_time": "0:08:16", "throughput": 10142.98, "total_tokens": 51523712}
{"current_steps": 53675, "total_steps": 58920, "loss": 0.0, "lr": 4.790900928861019e-08, "epoch": 4.554904955872369, "percentage": 91.1, "elapsed_time": "1:24:40", "remaining_time": "0:08:16", "throughput": 10143.14, "total_tokens": 51528384}
{"current_steps": 53680, "total_steps": 58920, "loss": 0.0, "lr": 4.7818462522712376e-08, "epoch": 4.555329260013577, "percentage": 91.11, "elapsed_time": "1:24:40", "remaining_time": "0:08:15", "throughput": 10143.26, "total_tokens": 51532800}
{"current_steps": 53685, "total_steps": 58920, "loss": 0.0, "lr": 4.7727999307306424e-08, "epoch": 4.555753564154786, "percentage": 91.12, "elapsed_time": "1:24:40", "remaining_time": "0:08:15", "throughput": 10143.57, "total_tokens": 51538432}
{"current_steps": 53690, "total_steps": 58920, "loss": 0.0001, "lr": 4.763761965033053e-08, "epoch": 4.556177868295995, "percentage": 91.12, "elapsed_time": "1:24:41", "remaining_time": "0:08:14", "throughput": 10143.75, "total_tokens": 51543232}
{"current_steps": 53695, "total_steps": 58920, "loss": 0.0, "lr": 4.754732355971514e-08, "epoch": 4.556602172437203, "percentage": 91.13, "elapsed_time": "1:24:41", "remaining_time": "0:08:14", "throughput": 10143.88, "total_tokens": 51547712}
{"current_steps": 53700, "total_steps": 58920, "loss": 0.0, "lr": 4.7457111043383014e-08, "epoch": 4.557026476578411, "percentage": 91.14, "elapsed_time": "1:24:42", "remaining_time": "0:08:14", "throughput": 10144.16, "total_tokens": 51553152}
{"current_steps": 53705, "total_steps": 58920, "loss": 0.0, "lr": 4.73669821092505e-08, "epoch": 4.55745078071962, "percentage": 91.15, "elapsed_time": "1:24:42", "remaining_time": "0:08:13", "throughput": 10144.27, "total_tokens": 51557440}
{"current_steps": 53710, "total_steps": 58920, "loss": 0.0, "lr": 4.727693676522559e-08, "epoch": 4.557875084860829, "percentage": 91.16, "elapsed_time": "1:24:42", "remaining_time": "0:08:13", "throughput": 10144.5, "total_tokens": 51562624}
{"current_steps": 53715, "total_steps": 58920, "loss": 0.0, "lr": 4.718697501920987e-08, "epoch": 4.558299389002037, "percentage": 91.17, "elapsed_time": "1:24:43", "remaining_time": "0:08:12", "throughput": 10144.72, "total_tokens": 51567680}
{"current_steps": 53720, "total_steps": 58920, "loss": 0.0, "lr": 4.709709687909691e-08, "epoch": 4.558723693143245, "percentage": 91.17, "elapsed_time": "1:24:43", "remaining_time": "0:08:12", "throughput": 10144.82, "total_tokens": 51571968}
{"current_steps": 53725, "total_steps": 58920, "loss": 0.0, "lr": 4.7007302352773283e-08, "epoch": 4.5591479972844535, "percentage": 91.18, "elapsed_time": "1:24:43", "remaining_time": "0:08:11", "throughput": 10145.08, "total_tokens": 51577344}
{"current_steps": 53730, "total_steps": 58920, "loss": 0.0, "lr": 4.691759144811813e-08, "epoch": 4.559572301425662, "percentage": 91.19, "elapsed_time": "1:24:44", "remaining_time": "0:08:11", "throughput": 10145.29, "total_tokens": 51582336}
{"current_steps": 53735, "total_steps": 58920, "loss": 0.0, "lr": 4.682796417300317e-08, "epoch": 4.55999660556687, "percentage": 91.2, "elapsed_time": "1:24:44", "remaining_time": "0:08:10", "throughput": 10145.45, "total_tokens": 51586944}
{"current_steps": 53740, "total_steps": 58920, "loss": 0.0, "lr": 4.6738420535293085e-08, "epoch": 4.560420909708078, "percentage": 91.21, "elapsed_time": "1:24:45", "remaining_time": "0:08:10", "throughput": 10145.59, "total_tokens": 51591552}
{"current_steps": 53745, "total_steps": 58920, "loss": 0.0, "lr": 4.664896054284462e-08, "epoch": 4.560845213849287, "percentage": 91.22, "elapsed_time": "1:24:45", "remaining_time": "0:08:09", "throughput": 10145.76, "total_tokens": 51596224}
{"current_steps": 53750, "total_steps": 58920, "loss": 0.0, "lr": 4.655958420350803e-08, "epoch": 4.561269517990496, "percentage": 91.23, "elapsed_time": "1:24:45", "remaining_time": "0:08:09", "throughput": 10146.02, "total_tokens": 51601472}
{"current_steps": 53755, "total_steps": 58920, "loss": 0.0, "lr": 4.647029152512538e-08, "epoch": 4.561693822131704, "percentage": 91.23, "elapsed_time": "1:24:46", "remaining_time": "0:08:08", "throughput": 10146.12, "total_tokens": 51605824}
{"current_steps": 53760, "total_steps": 58920, "loss": 0.0, "lr": 4.6381082515532075e-08, "epoch": 4.562118126272912, "percentage": 91.24, "elapsed_time": "1:24:46", "remaining_time": "0:08:08", "throughput": 10146.21, "total_tokens": 51610048}
{"current_steps": 53765, "total_steps": 58920, "loss": 0.0, "lr": 4.629195718255563e-08, "epoch": 4.562542430414121, "percentage": 91.25, "elapsed_time": "1:24:47", "remaining_time": "0:08:07", "throughput": 10146.38, "total_tokens": 51614784}
{"current_steps": 53770, "total_steps": 58920, "loss": 0.0, "lr": 4.6202915534016676e-08, "epoch": 4.56296673455533, "percentage": 91.26, "elapsed_time": "1:24:47", "remaining_time": "0:08:07", "throughput": 10146.55, "total_tokens": 51619456}
{"current_steps": 53775, "total_steps": 58920, "loss": 0.0, "lr": 4.611395757772818e-08, "epoch": 4.563391038696538, "percentage": 91.27, "elapsed_time": "1:24:47", "remaining_time": "0:08:06", "throughput": 10146.78, "total_tokens": 51624576}
{"current_steps": 53780, "total_steps": 58920, "loss": 0.0, "lr": 4.602508332149591e-08, "epoch": 4.563815342837746, "percentage": 91.28, "elapsed_time": "1:24:48", "remaining_time": "0:08:06", "throughput": 10146.9, "total_tokens": 51629056}
{"current_steps": 53785, "total_steps": 58920, "loss": 0.0, "lr": 4.593629277311828e-08, "epoch": 4.564239646978955, "percentage": 91.28, "elapsed_time": "1:24:48", "remaining_time": "0:08:05", "throughput": 10147.19, "total_tokens": 51634624}
{"current_steps": 53790, "total_steps": 58920, "loss": 0.0, "lr": 4.58475859403864e-08, "epoch": 4.564663951120163, "percentage": 91.29, "elapsed_time": "1:24:48", "remaining_time": "0:08:05", "throughput": 10147.24, "total_tokens": 51638592}
{"current_steps": 53795, "total_steps": 58920, "loss": 0.0, "lr": 4.575896283108383e-08, "epoch": 4.565088255261371, "percentage": 91.3, "elapsed_time": "1:24:49", "remaining_time": "0:08:04", "throughput": 10147.43, "total_tokens": 51643456}
{"current_steps": 53800, "total_steps": 58920, "loss": 0.0, "lr": 4.5670423452987e-08, "epoch": 4.565512559402579, "percentage": 91.31, "elapsed_time": "1:24:49", "remaining_time": "0:08:04", "throughput": 10147.59, "total_tokens": 51648128}
{"current_steps": 53805, "total_steps": 58920, "loss": 0.0, "lr": 4.558196781386492e-08, "epoch": 4.565936863543788, "percentage": 91.32, "elapsed_time": "1:24:50", "remaining_time": "0:08:03", "throughput": 10147.74, "total_tokens": 51652800}
{"current_steps": 53810, "total_steps": 58920, "loss": 0.0, "lr": 4.5493595921479166e-08, "epoch": 4.566361167684996, "percentage": 91.33, "elapsed_time": "1:24:50", "remaining_time": "0:08:03", "throughput": 10148.12, "total_tokens": 51658944}
{"current_steps": 53815, "total_steps": 58920, "loss": 0.0, "lr": 4.5405307783584314e-08, "epoch": 4.566785471826205, "percentage": 91.34, "elapsed_time": "1:24:50", "remaining_time": "0:08:02", "throughput": 10148.25, "total_tokens": 51663424}
{"current_steps": 53820, "total_steps": 58920, "loss": 0.0, "lr": 4.531710340792705e-08, "epoch": 4.567209775967413, "percentage": 91.34, "elapsed_time": "1:24:51", "remaining_time": "0:08:02", "throughput": 10148.45, "total_tokens": 51668352}
{"current_steps": 53825, "total_steps": 58920, "loss": 0.0, "lr": 4.5228982802247075e-08, "epoch": 4.567634080108622, "percentage": 91.35, "elapsed_time": "1:24:51", "remaining_time": "0:08:01", "throughput": 10148.7, "total_tokens": 51673600}
{"current_steps": 53830, "total_steps": 58920, "loss": 0.0, "lr": 4.5140945974276645e-08, "epoch": 4.56805838424983, "percentage": 91.36, "elapsed_time": "1:24:52", "remaining_time": "0:08:01", "throughput": 10148.83, "total_tokens": 51678080}
{"current_steps": 53835, "total_steps": 58920, "loss": 0.0, "lr": 4.5052992931740805e-08, "epoch": 4.568482688391039, "percentage": 91.37, "elapsed_time": "1:24:52", "remaining_time": "0:08:01", "throughput": 10148.98, "total_tokens": 51682688}
{"current_steps": 53840, "total_steps": 58920, "loss": 0.0, "lr": 4.496512368235694e-08, "epoch": 4.568906992532247, "percentage": 91.38, "elapsed_time": "1:24:52", "remaining_time": "0:08:00", "throughput": 10149.18, "total_tokens": 51687616}
{"current_steps": 53845, "total_steps": 58920, "loss": 0.0, "lr": 4.487733823383522e-08, "epoch": 4.569331296673456, "percentage": 91.39, "elapsed_time": "1:24:53", "remaining_time": "0:08:00", "throughput": 10149.9, "total_tokens": 51696256}
{"current_steps": 53850, "total_steps": 58920, "loss": 0.0, "lr": 4.478963659387891e-08, "epoch": 4.569755600814664, "percentage": 91.4, "elapsed_time": "1:24:53", "remaining_time": "0:07:59", "throughput": 10150.1, "total_tokens": 51701120}
{"current_steps": 53855, "total_steps": 58920, "loss": 0.0, "lr": 4.470201877018287e-08, "epoch": 4.5701799049558725, "percentage": 91.4, "elapsed_time": "1:24:54", "remaining_time": "0:07:59", "throughput": 10150.26, "total_tokens": 51705792}
{"current_steps": 53860, "total_steps": 58920, "loss": 0.0, "lr": 4.4614484770435944e-08, "epoch": 4.57060420909708, "percentage": 91.41, "elapsed_time": "1:24:54", "remaining_time": "0:07:58", "throughput": 10150.37, "total_tokens": 51710144}
{"current_steps": 53865, "total_steps": 58920, "loss": 0.0, "lr": 4.4527034602318435e-08, "epoch": 4.571028513238289, "percentage": 91.42, "elapsed_time": "1:24:54", "remaining_time": "0:07:58", "throughput": 10150.51, "total_tokens": 51714752}
{"current_steps": 53870, "total_steps": 58920, "loss": 0.0, "lr": 4.4439668273503874e-08, "epoch": 4.571452817379497, "percentage": 91.43, "elapsed_time": "1:24:55", "remaining_time": "0:07:57", "throughput": 10150.65, "total_tokens": 51719360}
{"current_steps": 53875, "total_steps": 58920, "loss": 0.0, "lr": 4.435238579165845e-08, "epoch": 4.571877121520706, "percentage": 91.44, "elapsed_time": "1:24:55", "remaining_time": "0:07:57", "throughput": 10150.85, "total_tokens": 51724288}
{"current_steps": 53880, "total_steps": 58920, "loss": 0.0, "lr": 4.426518716444061e-08, "epoch": 4.572301425661914, "percentage": 91.45, "elapsed_time": "1:24:55", "remaining_time": "0:07:56", "throughput": 10150.95, "total_tokens": 51728576}
{"current_steps": 53885, "total_steps": 58920, "loss": 0.0, "lr": 4.417807239950222e-08, "epoch": 4.572725729803123, "percentage": 91.45, "elapsed_time": "1:24:56", "remaining_time": "0:07:56", "throughput": 10151.14, "total_tokens": 51733440}
{"current_steps": 53890, "total_steps": 58920, "loss": 0.0, "lr": 4.4091041504486726e-08, "epoch": 4.573150033944331, "percentage": 91.46, "elapsed_time": "1:24:56", "remaining_time": "0:07:55", "throughput": 10151.39, "total_tokens": 51738624}
{"current_steps": 53895, "total_steps": 58920, "loss": 0.0, "lr": 4.400409448703135e-08, "epoch": 4.57357433808554, "percentage": 91.47, "elapsed_time": "1:24:57", "remaining_time": "0:07:55", "throughput": 10151.55, "total_tokens": 51743296}
{"current_steps": 53900, "total_steps": 58920, "loss": 0.0, "lr": 4.3917231354764774e-08, "epoch": 4.573998642226748, "percentage": 91.48, "elapsed_time": "1:24:57", "remaining_time": "0:07:54", "throughput": 10151.69, "total_tokens": 51747840}
{"current_steps": 53905, "total_steps": 58920, "loss": 0.0, "lr": 4.3830452115309336e-08, "epoch": 4.574422946367957, "percentage": 91.49, "elapsed_time": "1:24:57", "remaining_time": "0:07:54", "throughput": 10151.96, "total_tokens": 51753216}
{"current_steps": 53910, "total_steps": 58920, "loss": 0.0, "lr": 4.3743756776279616e-08, "epoch": 4.574847250509165, "percentage": 91.5, "elapsed_time": "1:24:58", "remaining_time": "0:07:53", "throughput": 10152.17, "total_tokens": 51758208}
{"current_steps": 53915, "total_steps": 58920, "loss": 0.0, "lr": 4.3657145345282534e-08, "epoch": 4.5752715546503735, "percentage": 91.51, "elapsed_time": "1:24:58", "remaining_time": "0:07:53", "throughput": 10152.24, "total_tokens": 51762368}
{"current_steps": 53920, "total_steps": 58920, "loss": 0.0, "lr": 4.3570617829918224e-08, "epoch": 4.5756958587915815, "percentage": 91.51, "elapsed_time": "1:24:59", "remaining_time": "0:07:52", "throughput": 10152.46, "total_tokens": 51767424}
{"current_steps": 53925, "total_steps": 58920, "loss": 0.0, "lr": 4.3484174237778834e-08, "epoch": 4.57612016293279, "percentage": 91.52, "elapsed_time": "1:24:59", "remaining_time": "0:07:52", "throughput": 10152.57, "total_tokens": 51771776}
{"current_steps": 53930, "total_steps": 58920, "loss": 0.016, "lr": 4.339781457644975e-08, "epoch": 4.576544467073998, "percentage": 91.53, "elapsed_time": "1:24:59", "remaining_time": "0:07:51", "throughput": 10152.76, "total_tokens": 51776640}
{"current_steps": 53935, "total_steps": 58920, "loss": 0.0, "lr": 4.331153885350869e-08, "epoch": 4.576968771215207, "percentage": 91.54, "elapsed_time": "1:25:00", "remaining_time": "0:07:51", "throughput": 10152.94, "total_tokens": 51781440}
{"current_steps": 53940, "total_steps": 58920, "loss": 0.0, "lr": 4.322534707652592e-08, "epoch": 4.577393075356415, "percentage": 91.55, "elapsed_time": "1:25:00", "remaining_time": "0:07:50", "throughput": 10152.56, "total_tokens": 51786048}
{"current_steps": 53945, "total_steps": 58920, "loss": 0.0, "lr": 4.313923925306473e-08, "epoch": 4.577817379497624, "percentage": 91.56, "elapsed_time": "1:25:01", "remaining_time": "0:07:50", "throughput": 10152.76, "total_tokens": 51790976}
{"current_steps": 53950, "total_steps": 58920, "loss": 0.0, "lr": 4.3053215390680183e-08, "epoch": 4.578241683638832, "percentage": 91.56, "elapsed_time": "1:25:01", "remaining_time": "0:07:49", "throughput": 10152.92, "total_tokens": 51795712}
{"current_steps": 53955, "total_steps": 58920, "loss": 0.0, "lr": 4.296727549692136e-08, "epoch": 4.578665987780041, "percentage": 91.57, "elapsed_time": "1:25:01", "remaining_time": "0:07:49", "throughput": 10153.14, "total_tokens": 51800768}
{"current_steps": 53960, "total_steps": 58920, "loss": 0.0, "lr": 4.288141957932834e-08, "epoch": 4.579090291921249, "percentage": 91.58, "elapsed_time": "1:25:02", "remaining_time": "0:07:49", "throughput": 10153.44, "total_tokens": 51806400}
{"current_steps": 53965, "total_steps": 58920, "loss": 0.0, "lr": 4.2795647645435306e-08, "epoch": 4.579514596062458, "percentage": 91.59, "elapsed_time": "1:25:02", "remaining_time": "0:07:48", "throughput": 10153.63, "total_tokens": 51811264}
{"current_steps": 53970, "total_steps": 58920, "loss": 0.0, "lr": 4.270995970276825e-08, "epoch": 4.579938900203666, "percentage": 91.6, "elapsed_time": "1:25:03", "remaining_time": "0:07:48", "throughput": 10153.85, "total_tokens": 51816320}
{"current_steps": 53975, "total_steps": 58920, "loss": 0.0, "lr": 4.2624355758845934e-08, "epoch": 4.5803632043448745, "percentage": 91.61, "elapsed_time": "1:25:03", "remaining_time": "0:07:47", "throughput": 10154.05, "total_tokens": 51821248}
{"current_steps": 53980, "total_steps": 58920, "loss": 0.0, "lr": 4.2538835821179786e-08, "epoch": 4.5807875084860825, "percentage": 91.62, "elapsed_time": "1:25:03", "remaining_time": "0:07:47", "throughput": 10154.26, "total_tokens": 51826240}
{"current_steps": 53985, "total_steps": 58920, "loss": 0.0, "lr": 4.2453399897273814e-08, "epoch": 4.581211812627291, "percentage": 91.62, "elapsed_time": "1:25:04", "remaining_time": "0:07:46", "throughput": 10154.46, "total_tokens": 51831232}
{"current_steps": 53990, "total_steps": 58920, "loss": 0.0, "lr": 4.23680479946249e-08, "epoch": 4.581636116768499, "percentage": 91.63, "elapsed_time": "1:25:04", "remaining_time": "0:07:46", "throughput": 10154.64, "total_tokens": 51836096}
{"current_steps": 53995, "total_steps": 58920, "loss": 0.0, "lr": 4.2282780120722284e-08, "epoch": 4.582060420909708, "percentage": 91.64, "elapsed_time": "1:25:05", "remaining_time": "0:07:45", "throughput": 10154.78, "total_tokens": 51840704}
{"current_steps": 54000, "total_steps": 58920, "loss": 0.0, "lr": 4.2197596283047754e-08, "epoch": 4.582484725050916, "percentage": 91.65, "elapsed_time": "1:25:05", "remaining_time": "0:07:45", "throughput": 10154.98, "total_tokens": 51845696}
{"current_steps": 54005, "total_steps": 58920, "loss": 0.0, "lr": 4.211249648907611e-08, "epoch": 4.582909029192125, "percentage": 91.66, "elapsed_time": "1:25:05", "remaining_time": "0:07:44", "throughput": 10155.19, "total_tokens": 51850752}
{"current_steps": 54010, "total_steps": 58920, "loss": 0.0, "lr": 4.202748074627449e-08, "epoch": 4.583333333333333, "percentage": 91.67, "elapsed_time": "1:25:06", "remaining_time": "0:07:44", "throughput": 10155.35, "total_tokens": 51855424}
{"current_steps": 54015, "total_steps": 58920, "loss": 0.0, "lr": 4.194254906210271e-08, "epoch": 4.583757637474542, "percentage": 91.68, "elapsed_time": "1:25:06", "remaining_time": "0:07:43", "throughput": 10155.61, "total_tokens": 51860864}
{"current_steps": 54020, "total_steps": 58920, "loss": 0.0, "lr": 4.1857701444013126e-08, "epoch": 4.58418194161575, "percentage": 91.68, "elapsed_time": "1:25:06", "remaining_time": "0:07:43", "throughput": 10155.72, "total_tokens": 51865216}
{"current_steps": 54025, "total_steps": 58920, "loss": 0.0, "lr": 4.17729378994508e-08, "epoch": 4.584606245756959, "percentage": 91.69, "elapsed_time": "1:25:07", "remaining_time": "0:07:42", "throughput": 10156.39, "total_tokens": 51873600}
{"current_steps": 54030, "total_steps": 58920, "loss": 0.0, "lr": 4.168825843585366e-08, "epoch": 4.585030549898167, "percentage": 91.7, "elapsed_time": "1:25:07", "remaining_time": "0:07:42", "throughput": 10156.71, "total_tokens": 51879360}
{"current_steps": 54035, "total_steps": 58920, "loss": 0.0, "lr": 4.160366306065177e-08, "epoch": 4.585454854039376, "percentage": 91.71, "elapsed_time": "1:25:08", "remaining_time": "0:07:41", "throughput": 10156.9, "total_tokens": 51884224}
{"current_steps": 54040, "total_steps": 58920, "loss": 0.0, "lr": 4.151915178126819e-08, "epoch": 4.585879158180584, "percentage": 91.72, "elapsed_time": "1:25:08", "remaining_time": "0:07:41", "throughput": 10157.06, "total_tokens": 51888896}
{"current_steps": 54045, "total_steps": 58920, "loss": 0.0, "lr": 4.143472460511854e-08, "epoch": 4.586303462321792, "percentage": 91.73, "elapsed_time": "1:25:09", "remaining_time": "0:07:40", "throughput": 10157.23, "total_tokens": 51893632}
{"current_steps": 54050, "total_steps": 58920, "loss": 0.0, "lr": 4.135038153961079e-08, "epoch": 4.586727766463, "percentage": 91.73, "elapsed_time": "1:25:09", "remaining_time": "0:07:40", "throughput": 10157.45, "total_tokens": 51898752}
{"current_steps": 54055, "total_steps": 58920, "loss": 0.0, "lr": 4.1266122592146016e-08, "epoch": 4.587152070604209, "percentage": 91.74, "elapsed_time": "1:25:09", "remaining_time": "0:07:39", "throughput": 10157.7, "total_tokens": 51904064}
{"current_steps": 54060, "total_steps": 58920, "loss": 0.0, "lr": 4.11819477701173e-08, "epoch": 4.587576374745417, "percentage": 91.75, "elapsed_time": "1:25:10", "remaining_time": "0:07:39", "throughput": 10157.77, "total_tokens": 51908160}
{"current_steps": 54065, "total_steps": 58920, "loss": 0.0, "lr": 4.109785708091107e-08, "epoch": 4.588000678886626, "percentage": 91.76, "elapsed_time": "1:25:10", "remaining_time": "0:07:38", "throughput": 10158.05, "total_tokens": 51913728}
{"current_steps": 54070, "total_steps": 58920, "loss": 0.0, "lr": 4.1013850531905646e-08, "epoch": 4.588424983027834, "percentage": 91.77, "elapsed_time": "1:25:10", "remaining_time": "0:07:38", "throughput": 10158.19, "total_tokens": 51918272}
{"current_steps": 54075, "total_steps": 58920, "loss": 0.0, "lr": 4.092992813047247e-08, "epoch": 4.588849287169043, "percentage": 91.78, "elapsed_time": "1:25:11", "remaining_time": "0:07:37", "throughput": 10158.52, "total_tokens": 51924096}
{"current_steps": 54080, "total_steps": 58920, "loss": 0.0, "lr": 4.084608988397542e-08, "epoch": 4.589273591310251, "percentage": 91.79, "elapsed_time": "1:25:11", "remaining_time": "0:07:37", "throughput": 10158.79, "total_tokens": 51929600}
{"current_steps": 54085, "total_steps": 58920, "loss": 0.0, "lr": 4.076233579977095e-08, "epoch": 4.58969789545146, "percentage": 91.79, "elapsed_time": "1:25:12", "remaining_time": "0:07:37", "throughput": 10159.0, "total_tokens": 51934720}
{"current_steps": 54090, "total_steps": 58920, "loss": 0.0, "lr": 4.0678665885208185e-08, "epoch": 4.590122199592668, "percentage": 91.8, "elapsed_time": "1:25:12", "remaining_time": "0:07:36", "throughput": 10159.15, "total_tokens": 51939264}
{"current_steps": 54095, "total_steps": 58920, "loss": 0.0, "lr": 4.05950801476288e-08, "epoch": 4.590546503733877, "percentage": 91.81, "elapsed_time": "1:25:12", "remaining_time": "0:07:36", "throughput": 10159.42, "total_tokens": 51944704}
{"current_steps": 54100, "total_steps": 58920, "loss": 0.0, "lr": 4.051157859436738e-08, "epoch": 4.590970807875085, "percentage": 91.82, "elapsed_time": "1:25:13", "remaining_time": "0:07:35", "throughput": 10159.53, "total_tokens": 51949120}
{"current_steps": 54105, "total_steps": 58920, "loss": 0.0, "lr": 4.042816123275061e-08, "epoch": 4.5913951120162935, "percentage": 91.83, "elapsed_time": "1:25:13", "remaining_time": "0:07:35", "throughput": 10159.65, "total_tokens": 51953536}
{"current_steps": 54110, "total_steps": 58920, "loss": 0.0, "lr": 4.0344828070098316e-08, "epoch": 4.591819416157501, "percentage": 91.84, "elapsed_time": "1:25:14", "remaining_time": "0:07:34", "throughput": 10159.92, "total_tokens": 51958976}
{"current_steps": 54115, "total_steps": 58920, "loss": 0.0, "lr": 4.0261579113722413e-08, "epoch": 4.59224372029871, "percentage": 91.84, "elapsed_time": "1:25:14", "remaining_time": "0:07:34", "throughput": 10160.07, "total_tokens": 51963584}
{"current_steps": 54120, "total_steps": 58920, "loss": 0.0, "lr": 4.017841437092773e-08, "epoch": 4.592668024439918, "percentage": 91.85, "elapsed_time": "1:25:14", "remaining_time": "0:07:33", "throughput": 10160.26, "total_tokens": 51968448}
{"current_steps": 54125, "total_steps": 58920, "loss": 0.0, "lr": 4.009533384901198e-08, "epoch": 4.593092328581127, "percentage": 91.86, "elapsed_time": "1:25:15", "remaining_time": "0:07:33", "throughput": 10160.35, "total_tokens": 51972736}
{"current_steps": 54130, "total_steps": 58920, "loss": 0.0, "lr": 4.001233755526467e-08, "epoch": 4.593516632722335, "percentage": 91.87, "elapsed_time": "1:25:15", "remaining_time": "0:07:32", "throughput": 10160.49, "total_tokens": 51977280}
{"current_steps": 54135, "total_steps": 58920, "loss": 0.0, "lr": 3.992942549696898e-08, "epoch": 4.593940936863544, "percentage": 91.88, "elapsed_time": "1:25:16", "remaining_time": "0:07:32", "throughput": 10160.61, "total_tokens": 51981760}
{"current_steps": 54140, "total_steps": 58920, "loss": 0.0, "lr": 3.984659768139975e-08, "epoch": 4.594365241004752, "percentage": 91.89, "elapsed_time": "1:25:16", "remaining_time": "0:07:31", "throughput": 10160.78, "total_tokens": 51986496}
{"current_steps": 54145, "total_steps": 58920, "loss": 0.0, "lr": 3.9763854115825056e-08, "epoch": 4.594789545145961, "percentage": 91.9, "elapsed_time": "1:25:16", "remaining_time": "0:07:31", "throughput": 10160.95, "total_tokens": 51991296}
{"current_steps": 54150, "total_steps": 58920, "loss": 0.0, "lr": 3.9681194807505095e-08, "epoch": 4.595213849287169, "percentage": 91.9, "elapsed_time": "1:25:17", "remaining_time": "0:07:30", "throughput": 10161.14, "total_tokens": 51996160}
{"current_steps": 54155, "total_steps": 58920, "loss": 0.0, "lr": 3.959861976369316e-08, "epoch": 4.595638153428378, "percentage": 91.91, "elapsed_time": "1:25:17", "remaining_time": "0:07:30", "throughput": 10161.44, "total_tokens": 52001792}
{"current_steps": 54160, "total_steps": 58920, "loss": 0.0, "lr": 3.951612899163492e-08, "epoch": 4.596062457569586, "percentage": 91.92, "elapsed_time": "1:25:17", "remaining_time": "0:07:29", "throughput": 10161.79, "total_tokens": 52007744}
{"current_steps": 54165, "total_steps": 58920, "loss": 0.0, "lr": 3.9433722498568356e-08, "epoch": 4.5964867617107945, "percentage": 91.93, "elapsed_time": "1:25:18", "remaining_time": "0:07:29", "throughput": 10162.14, "total_tokens": 52013760}
{"current_steps": 54170, "total_steps": 58920, "loss": 0.0, "lr": 3.935140029172479e-08, "epoch": 4.5969110658520025, "percentage": 91.94, "elapsed_time": "1:25:18", "remaining_time": "0:07:28", "throughput": 10162.28, "total_tokens": 52018304}
{"current_steps": 54175, "total_steps": 58920, "loss": 0.0, "lr": 3.926916237832711e-08, "epoch": 4.597335369993211, "percentage": 91.95, "elapsed_time": "1:25:19", "remaining_time": "0:07:28", "throughput": 10162.54, "total_tokens": 52023616}
{"current_steps": 54180, "total_steps": 58920, "loss": 0.0, "lr": 3.9187008765592e-08, "epoch": 4.597759674134419, "percentage": 91.96, "elapsed_time": "1:25:19", "remaining_time": "0:07:27", "throughput": 10162.81, "total_tokens": 52028992}
{"current_steps": 54185, "total_steps": 58920, "loss": 0.0, "lr": 3.910493946072768e-08, "epoch": 4.598183978275628, "percentage": 91.96, "elapsed_time": "1:25:19", "remaining_time": "0:07:27", "throughput": 10163.13, "total_tokens": 52034752}
{"current_steps": 54190, "total_steps": 58920, "loss": 0.0, "lr": 3.902295447093573e-08, "epoch": 4.598608282416836, "percentage": 91.97, "elapsed_time": "1:25:20", "remaining_time": "0:07:26", "throughput": 10163.27, "total_tokens": 52039360}
{"current_steps": 54195, "total_steps": 58920, "loss": 0.0, "lr": 3.894105380340995e-08, "epoch": 4.599032586558045, "percentage": 91.98, "elapsed_time": "1:25:20", "remaining_time": "0:07:26", "throughput": 10163.32, "total_tokens": 52043328}
{"current_steps": 54200, "total_steps": 58920, "loss": 0.0, "lr": 3.8859237465336816e-08, "epoch": 4.599456890699253, "percentage": 91.99, "elapsed_time": "1:25:21", "remaining_time": "0:07:25", "throughput": 10163.44, "total_tokens": 52047744}
{"current_steps": 54205, "total_steps": 58920, "loss": 0.0, "lr": 3.877750546389536e-08, "epoch": 4.599881194840462, "percentage": 92.0, "elapsed_time": "1:25:21", "remaining_time": "0:07:25", "throughput": 10163.58, "total_tokens": 52052288}
{"current_steps": 54210, "total_steps": 58920, "loss": 0.0, "lr": 3.869585780625728e-08, "epoch": 4.60030549898167, "percentage": 92.01, "elapsed_time": "1:25:21", "remaining_time": "0:07:25", "throughput": 10163.73, "total_tokens": 52056896}
{"current_steps": 54215, "total_steps": 58920, "loss": 0.0, "lr": 3.861429449958697e-08, "epoch": 4.600729803122879, "percentage": 92.01, "elapsed_time": "1:25:22", "remaining_time": "0:07:24", "throughput": 10163.86, "total_tokens": 52061440}
{"current_steps": 54220, "total_steps": 58920, "loss": 0.0, "lr": 3.853281555104126e-08, "epoch": 4.601154107264087, "percentage": 92.02, "elapsed_time": "1:25:22", "remaining_time": "0:07:24", "throughput": 10164.12, "total_tokens": 52066752}
{"current_steps": 54225, "total_steps": 58920, "loss": 0.0, "lr": 3.8451420967769546e-08, "epoch": 4.6015784114052956, "percentage": 92.03, "elapsed_time": "1:25:22", "remaining_time": "0:07:23", "throughput": 10164.29, "total_tokens": 52071552}
{"current_steps": 54230, "total_steps": 58920, "loss": 0.0, "lr": 3.8370110756914095e-08, "epoch": 4.6020027155465035, "percentage": 92.04, "elapsed_time": "1:25:23", "remaining_time": "0:07:23", "throughput": 10164.44, "total_tokens": 52076096}
{"current_steps": 54235, "total_steps": 58920, "loss": 0.0, "lr": 3.828888492560933e-08, "epoch": 4.602427019687712, "percentage": 92.05, "elapsed_time": "1:25:23", "remaining_time": "0:07:22", "throughput": 10164.66, "total_tokens": 52081216}
{"current_steps": 54240, "total_steps": 58920, "loss": 0.0, "lr": 3.820774348098277e-08, "epoch": 4.60285132382892, "percentage": 92.06, "elapsed_time": "1:25:24", "remaining_time": "0:07:22", "throughput": 10164.98, "total_tokens": 52087040}
{"current_steps": 54245, "total_steps": 58920, "loss": 0.0122, "lr": 3.8126686430154155e-08, "epoch": 4.603275627970129, "percentage": 92.07, "elapsed_time": "1:25:24", "remaining_time": "0:07:21", "throughput": 10165.11, "total_tokens": 52091520}
{"current_steps": 54250, "total_steps": 58920, "loss": 0.0, "lr": 3.804571378023602e-08, "epoch": 4.603699932111337, "percentage": 92.07, "elapsed_time": "1:25:24", "remaining_time": "0:07:21", "throughput": 10165.31, "total_tokens": 52096448}
{"current_steps": 54255, "total_steps": 58920, "loss": 0.0, "lr": 3.7964825538333355e-08, "epoch": 4.604124236252546, "percentage": 92.08, "elapsed_time": "1:25:25", "remaining_time": "0:07:20", "throughput": 10165.45, "total_tokens": 52100992}
{"current_steps": 54260, "total_steps": 58920, "loss": 0.0, "lr": 3.7884021711543814e-08, "epoch": 4.604548540393754, "percentage": 92.09, "elapsed_time": "1:25:25", "remaining_time": "0:07:20", "throughput": 10165.54, "total_tokens": 52105216}
{"current_steps": 54265, "total_steps": 58920, "loss": 0.0, "lr": 3.780330230695761e-08, "epoch": 4.604972844534963, "percentage": 92.1, "elapsed_time": "1:25:26", "remaining_time": "0:07:19", "throughput": 10165.75, "total_tokens": 52110144}
{"current_steps": 54270, "total_steps": 58920, "loss": 0.0, "lr": 3.7722667331657745e-08, "epoch": 4.605397148676171, "percentage": 92.11, "elapsed_time": "1:25:26", "remaining_time": "0:07:19", "throughput": 10165.92, "total_tokens": 52114944}
{"current_steps": 54275, "total_steps": 58920, "loss": 0.0, "lr": 3.7642116792719445e-08, "epoch": 4.60582145281738, "percentage": 92.12, "elapsed_time": "1:25:26", "remaining_time": "0:07:18", "throughput": 10166.12, "total_tokens": 52119872}
{"current_steps": 54280, "total_steps": 58920, "loss": 0.0, "lr": 3.756165069721085e-08, "epoch": 4.606245756958588, "percentage": 92.12, "elapsed_time": "1:25:27", "remaining_time": "0:07:18", "throughput": 10166.23, "total_tokens": 52124224}
{"current_steps": 54285, "total_steps": 58920, "loss": 0.0, "lr": 3.748126905219251e-08, "epoch": 4.606670061099797, "percentage": 92.13, "elapsed_time": "1:25:27", "remaining_time": "0:07:17", "throughput": 10166.41, "total_tokens": 52129024}
{"current_steps": 54290, "total_steps": 58920, "loss": 0.0, "lr": 3.740097186471769e-08, "epoch": 4.607094365241005, "percentage": 92.14, "elapsed_time": "1:25:27", "remaining_time": "0:07:17", "throughput": 10166.66, "total_tokens": 52134272}
{"current_steps": 54295, "total_steps": 58920, "loss": 0.0, "lr": 3.732075914183219e-08, "epoch": 4.607518669382213, "percentage": 92.15, "elapsed_time": "1:25:28", "remaining_time": "0:07:16", "throughput": 10166.88, "total_tokens": 52139392}
{"current_steps": 54300, "total_steps": 58920, "loss": 0.0, "lr": 3.7240630890574276e-08, "epoch": 4.607942973523421, "percentage": 92.16, "elapsed_time": "1:25:28", "remaining_time": "0:07:16", "throughput": 10166.98, "total_tokens": 52143680}
{"current_steps": 54305, "total_steps": 58920, "loss": 0.0, "lr": 3.7160587117974876e-08, "epoch": 4.60836727766463, "percentage": 92.17, "elapsed_time": "1:25:29", "remaining_time": "0:07:15", "throughput": 10167.12, "total_tokens": 52148224}
{"current_steps": 54310, "total_steps": 58920, "loss": 0.0, "lr": 3.70806278310577e-08, "epoch": 4.608791581805838, "percentage": 92.18, "elapsed_time": "1:25:29", "remaining_time": "0:07:15", "throughput": 10167.19, "total_tokens": 52152320}
{"current_steps": 54315, "total_steps": 58920, "loss": 0.0, "lr": 3.700075303683892e-08, "epoch": 4.609215885947047, "percentage": 92.18, "elapsed_time": "1:25:29", "remaining_time": "0:07:14", "throughput": 10167.38, "total_tokens": 52157248}
{"current_steps": 54320, "total_steps": 58920, "loss": 0.0, "lr": 3.6920962742327034e-08, "epoch": 4.609640190088255, "percentage": 92.19, "elapsed_time": "1:25:30", "remaining_time": "0:07:14", "throughput": 10167.61, "total_tokens": 52162368}
{"current_steps": 54325, "total_steps": 58920, "loss": 0.0, "lr": 3.684125695452367e-08, "epoch": 4.610064494229464, "percentage": 92.2, "elapsed_time": "1:25:30", "remaining_time": "0:07:13", "throughput": 10167.77, "total_tokens": 52167040}
{"current_steps": 54330, "total_steps": 58920, "loss": 0.0, "lr": 3.676163568042234e-08, "epoch": 4.610488798370672, "percentage": 92.21, "elapsed_time": "1:25:31", "remaining_time": "0:07:13", "throughput": 10167.94, "total_tokens": 52171776}
{"current_steps": 54335, "total_steps": 58920, "loss": 0.0, "lr": 3.668209892700969e-08, "epoch": 4.610913102511881, "percentage": 92.22, "elapsed_time": "1:25:31", "remaining_time": "0:07:13", "throughput": 10168.11, "total_tokens": 52176448}
{"current_steps": 54340, "total_steps": 58920, "loss": 0.0, "lr": 3.6602646701265115e-08, "epoch": 4.611337406653089, "percentage": 92.23, "elapsed_time": "1:25:31", "remaining_time": "0:07:12", "throughput": 10168.26, "total_tokens": 52181056}
{"current_steps": 54345, "total_steps": 58920, "loss": 0.0, "lr": 3.652327901015961e-08, "epoch": 4.611761710794298, "percentage": 92.24, "elapsed_time": "1:25:32", "remaining_time": "0:07:12", "throughput": 10168.49, "total_tokens": 52186240}
{"current_steps": 54350, "total_steps": 58920, "loss": 0.0, "lr": 3.644399586065805e-08, "epoch": 4.612186014935506, "percentage": 92.24, "elapsed_time": "1:25:32", "remaining_time": "0:07:11", "throughput": 10168.77, "total_tokens": 52191680}
{"current_steps": 54355, "total_steps": 58920, "loss": 0.0, "lr": 3.636479725971664e-08, "epoch": 4.6126103190767145, "percentage": 92.25, "elapsed_time": "1:25:32", "remaining_time": "0:07:11", "throughput": 10168.95, "total_tokens": 52196544}
{"current_steps": 54360, "total_steps": 58920, "loss": 0.0, "lr": 3.628568321428538e-08, "epoch": 4.6130346232179225, "percentage": 92.26, "elapsed_time": "1:25:33", "remaining_time": "0:07:10", "throughput": 10169.14, "total_tokens": 52201408}
{"current_steps": 54365, "total_steps": 58920, "loss": 0.0, "lr": 3.6206653731305827e-08, "epoch": 4.613458927359131, "percentage": 92.27, "elapsed_time": "1:25:33", "remaining_time": "0:07:10", "throughput": 10169.34, "total_tokens": 52206336}
{"current_steps": 54370, "total_steps": 58920, "loss": 0.0, "lr": 3.612770881771254e-08, "epoch": 4.613883231500339, "percentage": 92.28, "elapsed_time": "1:25:34", "remaining_time": "0:07:09", "throughput": 10169.51, "total_tokens": 52211136}
{"current_steps": 54375, "total_steps": 58920, "loss": 0.0, "lr": 3.604884848043299e-08, "epoch": 4.614307535641548, "percentage": 92.29, "elapsed_time": "1:25:34", "remaining_time": "0:07:09", "throughput": 10169.69, "total_tokens": 52215936}
{"current_steps": 54380, "total_steps": 58920, "loss": 0.0, "lr": 3.59700727263863e-08, "epoch": 4.614731839782756, "percentage": 92.29, "elapsed_time": "1:25:34", "remaining_time": "0:07:08", "throughput": 10169.9, "total_tokens": 52220928}
{"current_steps": 54385, "total_steps": 58920, "loss": 0.0, "lr": 3.58913815624855e-08, "epoch": 4.615156143923965, "percentage": 92.3, "elapsed_time": "1:25:35", "remaining_time": "0:07:08", "throughput": 10170.09, "total_tokens": 52225792}
{"current_steps": 54390, "total_steps": 58920, "loss": 0.0, "lr": 3.581277499563473e-08, "epoch": 4.615580448065173, "percentage": 92.31, "elapsed_time": "1:25:35", "remaining_time": "0:07:07", "throughput": 10170.22, "total_tokens": 52230336}
{"current_steps": 54395, "total_steps": 58920, "loss": 0.0, "lr": 3.573425303273192e-08, "epoch": 4.616004752206382, "percentage": 92.32, "elapsed_time": "1:25:35", "remaining_time": "0:07:07", "throughput": 10170.35, "total_tokens": 52234816}
{"current_steps": 54400, "total_steps": 58920, "loss": 0.0, "lr": 3.5655815680667e-08, "epoch": 4.61642905634759, "percentage": 92.33, "elapsed_time": "1:25:36", "remaining_time": "0:07:06", "throughput": 10170.52, "total_tokens": 52239488}
{"current_steps": 54405, "total_steps": 58920, "loss": 0.0, "lr": 3.557746294632247e-08, "epoch": 4.616853360488799, "percentage": 92.34, "elapsed_time": "1:25:36", "remaining_time": "0:07:06", "throughput": 10170.67, "total_tokens": 52244096}
{"current_steps": 54410, "total_steps": 58920, "loss": 0.0, "lr": 3.54991948365736e-08, "epoch": 4.617277664630007, "percentage": 92.35, "elapsed_time": "1:25:37", "remaining_time": "0:07:05", "throughput": 10170.85, "total_tokens": 52248896}
{"current_steps": 54415, "total_steps": 58920, "loss": 0.0, "lr": 3.54210113582879e-08, "epoch": 4.6177019687712155, "percentage": 92.35, "elapsed_time": "1:25:37", "remaining_time": "0:07:05", "throughput": 10170.93, "total_tokens": 52253056}
{"current_steps": 54420, "total_steps": 58920, "loss": 0.0, "lr": 3.534291251832588e-08, "epoch": 4.6181262729124235, "percentage": 92.36, "elapsed_time": "1:25:37", "remaining_time": "0:07:04", "throughput": 10171.15, "total_tokens": 52258176}
{"current_steps": 54425, "total_steps": 58920, "loss": 0.0, "lr": 3.526489832354051e-08, "epoch": 4.618550577053632, "percentage": 92.37, "elapsed_time": "1:25:38", "remaining_time": "0:07:04", "throughput": 10171.21, "total_tokens": 52262208}
{"current_steps": 54430, "total_steps": 58920, "loss": 0.0, "lr": 3.5186968780777096e-08, "epoch": 4.61897488119484, "percentage": 92.38, "elapsed_time": "1:25:38", "remaining_time": "0:07:03", "throughput": 10171.45, "total_tokens": 52267392}
{"current_steps": 54435, "total_steps": 58920, "loss": 0.0, "lr": 3.5109123896873706e-08, "epoch": 4.619399185336049, "percentage": 92.39, "elapsed_time": "1:25:39", "remaining_time": "0:07:03", "throughput": 10171.58, "total_tokens": 52271872}
{"current_steps": 54440, "total_steps": 58920, "loss": 0.0, "lr": 3.5031363678661e-08, "epoch": 4.619823489477257, "percentage": 92.4, "elapsed_time": "1:25:39", "remaining_time": "0:07:02", "throughput": 10171.78, "total_tokens": 52276800}
{"current_steps": 54445, "total_steps": 58920, "loss": 0.0, "lr": 3.495368813296218e-08, "epoch": 4.620247793618466, "percentage": 92.4, "elapsed_time": "1:25:39", "remaining_time": "0:07:02", "throughput": 10171.9, "total_tokens": 52281216}
{"current_steps": 54450, "total_steps": 58920, "loss": 0.0, "lr": 3.4876097266592796e-08, "epoch": 4.620672097759674, "percentage": 92.41, "elapsed_time": "1:25:40", "remaining_time": "0:07:01", "throughput": 10172.01, "total_tokens": 52285568}
{"current_steps": 54455, "total_steps": 58920, "loss": 0.0, "lr": 3.4798591086361406e-08, "epoch": 4.621096401900883, "percentage": 92.42, "elapsed_time": "1:25:40", "remaining_time": "0:07:01", "throughput": 10172.15, "total_tokens": 52290176}
{"current_steps": 54460, "total_steps": 58920, "loss": 0.0, "lr": 3.472116959906879e-08, "epoch": 4.621520706042091, "percentage": 92.43, "elapsed_time": "1:25:40", "remaining_time": "0:07:01", "throughput": 10172.39, "total_tokens": 52295360}
{"current_steps": 54465, "total_steps": 58920, "loss": 0.0, "lr": 3.464383281150851e-08, "epoch": 4.6219450101833, "percentage": 92.44, "elapsed_time": "1:25:41", "remaining_time": "0:07:00", "throughput": 10172.52, "total_tokens": 52299840}
{"current_steps": 54470, "total_steps": 58920, "loss": 0.0, "lr": 3.4566580730466364e-08, "epoch": 4.622369314324508, "percentage": 92.45, "elapsed_time": "1:25:41", "remaining_time": "0:07:00", "throughput": 10172.7, "total_tokens": 52304704}
{"current_steps": 54475, "total_steps": 58920, "loss": 0.0, "lr": 3.4489413362721155e-08, "epoch": 4.622793618465717, "percentage": 92.46, "elapsed_time": "1:25:42", "remaining_time": "0:06:59", "throughput": 10172.81, "total_tokens": 52309056}
{"current_steps": 54480, "total_steps": 58920, "loss": 0.0, "lr": 3.44123307150439e-08, "epoch": 4.6232179226069245, "percentage": 92.46, "elapsed_time": "1:25:42", "remaining_time": "0:06:59", "throughput": 10172.94, "total_tokens": 52313472}
{"current_steps": 54485, "total_steps": 58920, "loss": 0.0, "lr": 3.433533279419842e-08, "epoch": 4.623642226748133, "percentage": 92.47, "elapsed_time": "1:25:42", "remaining_time": "0:06:58", "throughput": 10173.07, "total_tokens": 52317952}
{"current_steps": 54490, "total_steps": 58920, "loss": 0.0, "lr": 3.425841960694098e-08, "epoch": 4.624066530889341, "percentage": 92.48, "elapsed_time": "1:25:43", "remaining_time": "0:06:58", "throughput": 10173.31, "total_tokens": 52323200}
{"current_steps": 54495, "total_steps": 58920, "loss": 0.0, "lr": 3.418159116002039e-08, "epoch": 4.62449083503055, "percentage": 92.49, "elapsed_time": "1:25:43", "remaining_time": "0:06:57", "throughput": 10173.49, "total_tokens": 52328000}
{"current_steps": 54500, "total_steps": 58920, "loss": 0.0, "lr": 3.410484746017805e-08, "epoch": 4.624915139171758, "percentage": 92.5, "elapsed_time": "1:25:43", "remaining_time": "0:06:57", "throughput": 10173.66, "total_tokens": 52332736}
{"current_steps": 54505, "total_steps": 58920, "loss": 0.0, "lr": 3.4028188514148125e-08, "epoch": 4.625339443312967, "percentage": 92.51, "elapsed_time": "1:25:44", "remaining_time": "0:06:56", "throughput": 10173.81, "total_tokens": 52337408}
{"current_steps": 54510, "total_steps": 58920, "loss": 0.0, "lr": 3.39516143286569e-08, "epoch": 4.625763747454175, "percentage": 92.52, "elapsed_time": "1:25:44", "remaining_time": "0:06:56", "throughput": 10173.95, "total_tokens": 52341952}
{"current_steps": 54515, "total_steps": 58920, "loss": 0.0, "lr": 3.387512491042366e-08, "epoch": 4.626188051595384, "percentage": 92.52, "elapsed_time": "1:25:45", "remaining_time": "0:06:55", "throughput": 10174.08, "total_tokens": 52346432}
{"current_steps": 54520, "total_steps": 58920, "loss": 0.0, "lr": 3.379872026616004e-08, "epoch": 4.626612355736592, "percentage": 92.53, "elapsed_time": "1:25:45", "remaining_time": "0:06:55", "throughput": 10174.23, "total_tokens": 52351040}
{"current_steps": 54525, "total_steps": 58920, "loss": 0.0, "lr": 3.372240040257024e-08, "epoch": 4.627036659877801, "percentage": 92.54, "elapsed_time": "1:25:45", "remaining_time": "0:06:54", "throughput": 10174.41, "total_tokens": 52355840}
{"current_steps": 54530, "total_steps": 58920, "loss": 0.0, "lr": 3.3646165326351225e-08, "epoch": 4.627460964019009, "percentage": 92.55, "elapsed_time": "1:25:46", "remaining_time": "0:06:54", "throughput": 10174.59, "total_tokens": 52360640}
{"current_steps": 54535, "total_steps": 58920, "loss": 0.0, "lr": 3.357001504419199e-08, "epoch": 4.627885268160218, "percentage": 92.56, "elapsed_time": "1:25:46", "remaining_time": "0:06:53", "throughput": 10174.83, "total_tokens": 52365888}
{"current_steps": 54540, "total_steps": 58920, "loss": 0.0, "lr": 3.3493949562774734e-08, "epoch": 4.628309572301426, "percentage": 92.57, "elapsed_time": "1:25:46", "remaining_time": "0:06:53", "throughput": 10175.04, "total_tokens": 52370880}
{"current_steps": 54545, "total_steps": 58920, "loss": 0.0032, "lr": 3.341796888877391e-08, "epoch": 4.6287338764426345, "percentage": 92.57, "elapsed_time": "1:25:47", "remaining_time": "0:06:52", "throughput": 10175.25, "total_tokens": 52375936}
{"current_steps": 54550, "total_steps": 58920, "loss": 0.0, "lr": 3.334207302885628e-08, "epoch": 4.629158180583842, "percentage": 92.58, "elapsed_time": "1:25:47", "remaining_time": "0:06:52", "throughput": 10175.49, "total_tokens": 52381120}
{"current_steps": 54555, "total_steps": 58920, "loss": 0.0, "lr": 3.3266261989681854e-08, "epoch": 4.629582484725051, "percentage": 92.59, "elapsed_time": "1:25:48", "remaining_time": "0:06:51", "throughput": 10175.65, "total_tokens": 52385792}
{"current_steps": 54560, "total_steps": 58920, "loss": 0.0507, "lr": 3.319053577790243e-08, "epoch": 4.630006788866259, "percentage": 92.6, "elapsed_time": "1:25:48", "remaining_time": "0:06:51", "throughput": 10175.85, "total_tokens": 52390784}
{"current_steps": 54565, "total_steps": 58920, "loss": 0.0, "lr": 3.3114894400163016e-08, "epoch": 4.630431093007468, "percentage": 92.61, "elapsed_time": "1:25:48", "remaining_time": "0:06:50", "throughput": 10176.05, "total_tokens": 52395776}
{"current_steps": 54570, "total_steps": 58920, "loss": 0.0, "lr": 3.303933786310043e-08, "epoch": 4.630855397148676, "percentage": 92.62, "elapsed_time": "1:25:49", "remaining_time": "0:06:50", "throughput": 10176.22, "total_tokens": 52400512}
{"current_steps": 54575, "total_steps": 58920, "loss": 0.0, "lr": 3.2963866173345015e-08, "epoch": 4.631279701289885, "percentage": 92.63, "elapsed_time": "1:25:49", "remaining_time": "0:06:49", "throughput": 10176.37, "total_tokens": 52405120}
{"current_steps": 54580, "total_steps": 58920, "loss": 0.0, "lr": 3.2888479337518814e-08, "epoch": 4.631704005431093, "percentage": 92.63, "elapsed_time": "1:25:50", "remaining_time": "0:06:49", "throughput": 10176.47, "total_tokens": 52409408}
{"current_steps": 54585, "total_steps": 58920, "loss": 0.0, "lr": 3.281317736223654e-08, "epoch": 4.632128309572302, "percentage": 92.64, "elapsed_time": "1:25:50", "remaining_time": "0:06:49", "throughput": 10176.69, "total_tokens": 52414464}
{"current_steps": 54590, "total_steps": 58920, "loss": 0.0, "lr": 3.2737960254106356e-08, "epoch": 4.63255261371351, "percentage": 92.65, "elapsed_time": "1:25:50", "remaining_time": "0:06:48", "throughput": 10176.89, "total_tokens": 52419456}
{"current_steps": 54595, "total_steps": 58920, "loss": 0.0, "lr": 3.266282801972753e-08, "epoch": 4.632976917854718, "percentage": 92.66, "elapsed_time": "1:25:51", "remaining_time": "0:06:48", "throughput": 10177.04, "total_tokens": 52424064}
{"current_steps": 54600, "total_steps": 58920, "loss": 0.0, "lr": 3.2587780665693235e-08, "epoch": 4.633401221995927, "percentage": 92.67, "elapsed_time": "1:25:51", "remaining_time": "0:06:47", "throughput": 10177.09, "total_tokens": 52428096}
{"current_steps": 54605, "total_steps": 58920, "loss": 0.0, "lr": 3.251281819858809e-08, "epoch": 4.6338255261371355, "percentage": 92.68, "elapsed_time": "1:25:51", "remaining_time": "0:06:47", "throughput": 10177.29, "total_tokens": 52433024}
{"current_steps": 54610, "total_steps": 58920, "loss": 0.0, "lr": 3.2437940624990165e-08, "epoch": 4.6342498302783435, "percentage": 92.68, "elapsed_time": "1:25:52", "remaining_time": "0:06:46", "throughput": 10177.53, "total_tokens": 52438208}
{"current_steps": 54615, "total_steps": 58920, "loss": 0.0, "lr": 3.2363147951469774e-08, "epoch": 4.6346741344195515, "percentage": 92.69, "elapsed_time": "1:25:52", "remaining_time": "0:06:46", "throughput": 10177.72, "total_tokens": 52443072}
{"current_steps": 54620, "total_steps": 58920, "loss": 0.0, "lr": 3.2288440184589204e-08, "epoch": 4.63509843856076, "percentage": 92.7, "elapsed_time": "1:25:53", "remaining_time": "0:06:45", "throughput": 10177.9, "total_tokens": 52447872}
{"current_steps": 54625, "total_steps": 58920, "loss": 0.0, "lr": 3.221381733090445e-08, "epoch": 4.635522742701969, "percentage": 92.71, "elapsed_time": "1:25:53", "remaining_time": "0:06:45", "throughput": 10178.12, "total_tokens": 52452992}
{"current_steps": 54630, "total_steps": 58920, "loss": 0.0, "lr": 3.2139279396962706e-08, "epoch": 4.635947046843177, "percentage": 92.72, "elapsed_time": "1:25:53", "remaining_time": "0:06:44", "throughput": 10178.32, "total_tokens": 52457984}
{"current_steps": 54635, "total_steps": 58920, "loss": 0.0, "lr": 3.206482638930485e-08, "epoch": 4.636371350984385, "percentage": 92.73, "elapsed_time": "1:25:54", "remaining_time": "0:06:44", "throughput": 10178.46, "total_tokens": 52462528}
{"current_steps": 54640, "total_steps": 58920, "loss": 0.0, "lr": 3.19904583144639e-08, "epoch": 4.636795655125594, "percentage": 92.74, "elapsed_time": "1:25:54", "remaining_time": "0:06:43", "throughput": 10178.63, "total_tokens": 52467200}
{"current_steps": 54645, "total_steps": 58920, "loss": 0.0, "lr": 3.191617517896506e-08, "epoch": 4.637219959266803, "percentage": 92.74, "elapsed_time": "1:25:55", "remaining_time": "0:06:43", "throughput": 10178.81, "total_tokens": 52472064}
{"current_steps": 54650, "total_steps": 58920, "loss": 0.0, "lr": 3.184197698932678e-08, "epoch": 4.637644263408011, "percentage": 92.75, "elapsed_time": "1:25:55", "remaining_time": "0:06:42", "throughput": 10179.01, "total_tokens": 52476992}
{"current_steps": 54655, "total_steps": 58920, "loss": 0.0, "lr": 3.176786375205931e-08, "epoch": 4.638068567549219, "percentage": 92.76, "elapsed_time": "1:25:55", "remaining_time": "0:06:42", "throughput": 10179.22, "total_tokens": 52482048}
{"current_steps": 54660, "total_steps": 58920, "loss": 0.0, "lr": 3.169383547366622e-08, "epoch": 4.638492871690428, "percentage": 92.77, "elapsed_time": "1:25:56", "remaining_time": "0:06:41", "throughput": 10179.46, "total_tokens": 52487296}
{"current_steps": 54665, "total_steps": 58920, "loss": 0.0, "lr": 3.161989216064287e-08, "epoch": 4.6389171758316365, "percentage": 92.78, "elapsed_time": "1:25:56", "remaining_time": "0:06:41", "throughput": 10179.71, "total_tokens": 52492608}
{"current_steps": 54670, "total_steps": 58920, "loss": 0.0, "lr": 3.1546033819477626e-08, "epoch": 4.6393414799728445, "percentage": 92.79, "elapsed_time": "1:25:56", "remaining_time": "0:06:40", "throughput": 10179.86, "total_tokens": 52497216}
{"current_steps": 54675, "total_steps": 58920, "loss": 0.0, "lr": 3.147226045665141e-08, "epoch": 4.6397657841140525, "percentage": 92.8, "elapsed_time": "1:25:57", "remaining_time": "0:06:40", "throughput": 10180.03, "total_tokens": 52501952}
{"current_steps": 54680, "total_steps": 58920, "loss": 0.0, "lr": 3.13985720786375e-08, "epoch": 4.640190088255261, "percentage": 92.8, "elapsed_time": "1:25:57", "remaining_time": "0:06:39", "throughput": 10180.13, "total_tokens": 52506240}
{"current_steps": 54685, "total_steps": 58920, "loss": 0.0, "lr": 3.132496869190171e-08, "epoch": 4.64061439239647, "percentage": 92.81, "elapsed_time": "1:25:58", "remaining_time": "0:06:39", "throughput": 10180.29, "total_tokens": 52510976}
{"current_steps": 54690, "total_steps": 58920, "loss": 0.0, "lr": 3.1251450302902546e-08, "epoch": 4.641038696537678, "percentage": 92.82, "elapsed_time": "1:25:58", "remaining_time": "0:06:38", "throughput": 10180.44, "total_tokens": 52515584}
{"current_steps": 54695, "total_steps": 58920, "loss": 0.0, "lr": 3.1178016918090966e-08, "epoch": 4.641463000678886, "percentage": 92.83, "elapsed_time": "1:25:58", "remaining_time": "0:06:38", "throughput": 10181.14, "total_tokens": 52524160}
{"current_steps": 54700, "total_steps": 58920, "loss": 0.0, "lr": 3.1104668543910474e-08, "epoch": 4.641887304820095, "percentage": 92.84, "elapsed_time": "1:25:59", "remaining_time": "0:06:38", "throughput": 10181.31, "total_tokens": 52528896}
{"current_steps": 54705, "total_steps": 58920, "loss": 0.0, "lr": 3.1031405186797144e-08, "epoch": 4.642311608961304, "percentage": 92.85, "elapsed_time": "1:25:59", "remaining_time": "0:06:37", "throughput": 10181.5, "total_tokens": 52533824}
{"current_steps": 54710, "total_steps": 58920, "loss": 0.0, "lr": 3.0958226853179506e-08, "epoch": 4.642735913102512, "percentage": 92.85, "elapsed_time": "1:26:00", "remaining_time": "0:06:37", "throughput": 10181.7, "total_tokens": 52538816}
{"current_steps": 54715, "total_steps": 58920, "loss": 0.0, "lr": 3.088513354947886e-08, "epoch": 4.64316021724372, "percentage": 92.86, "elapsed_time": "1:26:00", "remaining_time": "0:06:36", "throughput": 10181.92, "total_tokens": 52543872}
{"current_steps": 54720, "total_steps": 58920, "loss": 0.0, "lr": 3.0812125282108745e-08, "epoch": 4.643584521384929, "percentage": 92.87, "elapsed_time": "1:26:00", "remaining_time": "0:06:36", "throughput": 10182.15, "total_tokens": 52549120}
{"current_steps": 54725, "total_steps": 58920, "loss": 0.0, "lr": 3.073920205747538e-08, "epoch": 4.644008825526138, "percentage": 92.88, "elapsed_time": "1:26:01", "remaining_time": "0:06:35", "throughput": 10182.37, "total_tokens": 52554240}
{"current_steps": 54730, "total_steps": 58920, "loss": 0.0, "lr": 3.066636388197741e-08, "epoch": 4.644433129667346, "percentage": 92.89, "elapsed_time": "1:26:01", "remaining_time": "0:06:35", "throughput": 10182.51, "total_tokens": 52558784}
{"current_steps": 54735, "total_steps": 58920, "loss": 0.0, "lr": 3.0593610762006394e-08, "epoch": 4.6448574338085535, "percentage": 92.9, "elapsed_time": "1:26:02", "remaining_time": "0:06:34", "throughput": 10182.68, "total_tokens": 52563520}
{"current_steps": 54740, "total_steps": 58920, "loss": 0.0, "lr": 3.052094270394601e-08, "epoch": 4.645281737949762, "percentage": 92.91, "elapsed_time": "1:26:02", "remaining_time": "0:06:34", "throughput": 10182.85, "total_tokens": 52568256}
{"current_steps": 54745, "total_steps": 58920, "loss": 0.0, "lr": 3.044835971417259e-08, "epoch": 4.645706042090971, "percentage": 92.91, "elapsed_time": "1:26:02", "remaining_time": "0:06:33", "throughput": 10183.01, "total_tokens": 52572928}
{"current_steps": 54750, "total_steps": 58920, "loss": 0.0, "lr": 3.0375861799054935e-08, "epoch": 4.646130346232179, "percentage": 92.92, "elapsed_time": "1:26:03", "remaining_time": "0:06:33", "throughput": 10183.11, "total_tokens": 52577280}
{"current_steps": 54755, "total_steps": 58920, "loss": 0.0, "lr": 3.030344896495474e-08, "epoch": 4.646554650373387, "percentage": 92.93, "elapsed_time": "1:26:03", "remaining_time": "0:06:32", "throughput": 10183.46, "total_tokens": 52583296}
{"current_steps": 54760, "total_steps": 58920, "loss": 0.0, "lr": 3.02311212182258e-08, "epoch": 4.646978954514596, "percentage": 92.94, "elapsed_time": "1:26:03", "remaining_time": "0:06:32", "throughput": 10183.6, "total_tokens": 52587840}
{"current_steps": 54765, "total_steps": 58920, "loss": 0.0, "lr": 3.0158878565214484e-08, "epoch": 4.647403258655805, "percentage": 92.95, "elapsed_time": "1:26:04", "remaining_time": "0:06:31", "throughput": 10183.78, "total_tokens": 52592640}
{"current_steps": 54770, "total_steps": 58920, "loss": 0.0, "lr": 3.008672101226018e-08, "epoch": 4.647827562797013, "percentage": 92.96, "elapsed_time": "1:26:04", "remaining_time": "0:06:31", "throughput": 10183.99, "total_tokens": 52597696}
{"current_steps": 54775, "total_steps": 58920, "loss": 0.0, "lr": 3.001464856569413e-08, "epoch": 4.648251866938221, "percentage": 92.97, "elapsed_time": "1:26:05", "remaining_time": "0:06:30", "throughput": 10184.12, "total_tokens": 52602240}
{"current_steps": 54780, "total_steps": 58920, "loss": 0.0, "lr": 2.994266123184064e-08, "epoch": 4.64867617107943, "percentage": 92.97, "elapsed_time": "1:26:05", "remaining_time": "0:06:30", "throughput": 10184.34, "total_tokens": 52607296}
{"current_steps": 54785, "total_steps": 58920, "loss": 0.0, "lr": 2.9870759017016186e-08, "epoch": 4.649100475220639, "percentage": 92.98, "elapsed_time": "1:26:05", "remaining_time": "0:06:29", "throughput": 10184.5, "total_tokens": 52611968}
{"current_steps": 54790, "total_steps": 58920, "loss": 0.0, "lr": 2.9798941927530074e-08, "epoch": 4.649524779361847, "percentage": 92.99, "elapsed_time": "1:26:06", "remaining_time": "0:06:29", "throughput": 10184.65, "total_tokens": 52616576}
{"current_steps": 54795, "total_steps": 58920, "loss": 0.0, "lr": 2.9727209969683807e-08, "epoch": 4.649949083503055, "percentage": 93.0, "elapsed_time": "1:26:06", "remaining_time": "0:06:28", "throughput": 10184.97, "total_tokens": 52622336}
{"current_steps": 54800, "total_steps": 58920, "loss": 0.0, "lr": 2.9655563149771688e-08, "epoch": 4.6503733876442634, "percentage": 93.01, "elapsed_time": "1:26:07", "remaining_time": "0:06:28", "throughput": 10185.18, "total_tokens": 52627264}
{"current_steps": 54805, "total_steps": 58920, "loss": 0.0, "lr": 2.9584001474080578e-08, "epoch": 4.650797691785472, "percentage": 93.02, "elapsed_time": "1:26:07", "remaining_time": "0:06:27", "throughput": 10185.35, "total_tokens": 52632064}
{"current_steps": 54810, "total_steps": 58920, "loss": 0.0, "lr": 2.951252494888956e-08, "epoch": 4.65122199592668, "percentage": 93.02, "elapsed_time": "1:26:07", "remaining_time": "0:06:27", "throughput": 10185.45, "total_tokens": 52636352}
{"current_steps": 54815, "total_steps": 58920, "loss": 0.0, "lr": 2.9441133580470734e-08, "epoch": 4.651646300067888, "percentage": 93.03, "elapsed_time": "1:26:08", "remaining_time": "0:06:27", "throughput": 10185.63, "total_tokens": 52641152}
{"current_steps": 54820, "total_steps": 58920, "loss": 0.0, "lr": 2.9369827375087976e-08, "epoch": 4.652070604209097, "percentage": 93.04, "elapsed_time": "1:26:08", "remaining_time": "0:06:26", "throughput": 10185.75, "total_tokens": 52645568}
{"current_steps": 54825, "total_steps": 58920, "loss": 0.0, "lr": 2.929860633899861e-08, "epoch": 4.652494908350306, "percentage": 93.05, "elapsed_time": "1:26:08", "remaining_time": "0:06:26", "throughput": 10185.94, "total_tokens": 52650432}
{"current_steps": 54830, "total_steps": 58920, "loss": 0.0, "lr": 2.9227470478451866e-08, "epoch": 4.652919212491514, "percentage": 93.06, "elapsed_time": "1:26:09", "remaining_time": "0:06:25", "throughput": 10186.16, "total_tokens": 52655488}
{"current_steps": 54835, "total_steps": 58920, "loss": 0.0, "lr": 2.9156419799689524e-08, "epoch": 4.653343516632722, "percentage": 93.07, "elapsed_time": "1:26:09", "remaining_time": "0:06:25", "throughput": 10186.33, "total_tokens": 52660288}
{"current_steps": 54840, "total_steps": 58920, "loss": 0.0, "lr": 2.9085454308946266e-08, "epoch": 4.653767820773931, "percentage": 93.08, "elapsed_time": "1:26:10", "remaining_time": "0:06:24", "throughput": 10186.48, "total_tokens": 52664960}
{"current_steps": 54845, "total_steps": 58920, "loss": 0.0, "lr": 2.9014574012448666e-08, "epoch": 4.654192124915139, "percentage": 93.08, "elapsed_time": "1:26:10", "remaining_time": "0:06:24", "throughput": 10186.6, "total_tokens": 52669376}
{"current_steps": 54850, "total_steps": 58920, "loss": 0.0, "lr": 2.8943778916416638e-08, "epoch": 4.654616429056348, "percentage": 93.09, "elapsed_time": "1:26:10", "remaining_time": "0:06:23", "throughput": 10186.74, "total_tokens": 52673984}
{"current_steps": 54855, "total_steps": 58920, "loss": 0.0, "lr": 2.887306902706199e-08, "epoch": 4.655040733197556, "percentage": 93.1, "elapsed_time": "1:26:11", "remaining_time": "0:06:23", "throughput": 10186.93, "total_tokens": 52678912}
{"current_steps": 54860, "total_steps": 58920, "loss": 0.0, "lr": 2.8802444350589317e-08, "epoch": 4.6554650373387645, "percentage": 93.11, "elapsed_time": "1:26:11", "remaining_time": "0:06:22", "throughput": 10187.08, "total_tokens": 52683520}
{"current_steps": 54865, "total_steps": 58920, "loss": 0.0, "lr": 2.8731904893195768e-08, "epoch": 4.6558893414799725, "percentage": 93.12, "elapsed_time": "1:26:11", "remaining_time": "0:06:22", "throughput": 10187.27, "total_tokens": 52688448}
{"current_steps": 54870, "total_steps": 58920, "loss": 0.0, "lr": 2.8661450661070618e-08, "epoch": 4.656313645621181, "percentage": 93.13, "elapsed_time": "1:26:12", "remaining_time": "0:06:21", "throughput": 10187.41, "total_tokens": 52692992}
{"current_steps": 54875, "total_steps": 58920, "loss": 0.0, "lr": 2.8591081660396365e-08, "epoch": 4.656737949762389, "percentage": 93.13, "elapsed_time": "1:26:12", "remaining_time": "0:06:21", "throughput": 10187.57, "total_tokens": 52697664}
{"current_steps": 54880, "total_steps": 58920, "loss": 0.0, "lr": 2.8520797897347183e-08, "epoch": 4.657162253903598, "percentage": 93.14, "elapsed_time": "1:26:13", "remaining_time": "0:06:20", "throughput": 10187.69, "total_tokens": 52702080}
{"current_steps": 54885, "total_steps": 58920, "loss": 0.0, "lr": 2.845059937809058e-08, "epoch": 4.657586558044806, "percentage": 93.15, "elapsed_time": "1:26:13", "remaining_time": "0:06:20", "throughput": 10187.83, "total_tokens": 52706624}
{"current_steps": 54890, "total_steps": 58920, "loss": 0.0, "lr": 2.8380486108786185e-08, "epoch": 4.658010862186015, "percentage": 93.16, "elapsed_time": "1:26:13", "remaining_time": "0:06:19", "throughput": 10188.05, "total_tokens": 52711680}
{"current_steps": 54895, "total_steps": 58920, "loss": 0.0, "lr": 2.8310458095586077e-08, "epoch": 4.658435166327223, "percentage": 93.17, "elapsed_time": "1:26:14", "remaining_time": "0:06:19", "throughput": 10188.24, "total_tokens": 52716608}
{"current_steps": 54900, "total_steps": 58920, "loss": 0.0, "lr": 2.8240515344635007e-08, "epoch": 4.658859470468432, "percentage": 93.18, "elapsed_time": "1:26:14", "remaining_time": "0:06:18", "throughput": 10188.54, "total_tokens": 52722240}
{"current_steps": 54905, "total_steps": 58920, "loss": 0.0, "lr": 2.817065786207018e-08, "epoch": 4.65928377460964, "percentage": 93.19, "elapsed_time": "1:26:15", "remaining_time": "0:06:18", "throughput": 10188.72, "total_tokens": 52727104}
{"current_steps": 54910, "total_steps": 58920, "loss": 0.0, "lr": 2.8100885654021357e-08, "epoch": 4.659708078750849, "percentage": 93.19, "elapsed_time": "1:26:15", "remaining_time": "0:06:17", "throughput": 10188.87, "total_tokens": 52731712}
{"current_steps": 54915, "total_steps": 58920, "loss": 0.0, "lr": 2.803119872661075e-08, "epoch": 4.660132382892057, "percentage": 93.2, "elapsed_time": "1:26:15", "remaining_time": "0:06:17", "throughput": 10189.14, "total_tokens": 52737216}
{"current_steps": 54920, "total_steps": 58920, "loss": 0.0, "lr": 2.7961597085953247e-08, "epoch": 4.6605566870332655, "percentage": 93.21, "elapsed_time": "1:26:16", "remaining_time": "0:06:16", "throughput": 10189.27, "total_tokens": 52741760}
{"current_steps": 54925, "total_steps": 58920, "loss": 0.0, "lr": 2.7892080738156075e-08, "epoch": 4.6609809911744735, "percentage": 93.22, "elapsed_time": "1:26:16", "remaining_time": "0:06:16", "throughput": 10189.4, "total_tokens": 52746304}
{"current_steps": 54930, "total_steps": 58920, "loss": 0.0, "lr": 2.7822649689319023e-08, "epoch": 4.661405295315682, "percentage": 93.23, "elapsed_time": "1:26:16", "remaining_time": "0:06:16", "throughput": 10189.6, "total_tokens": 52751296}
{"current_steps": 54935, "total_steps": 58920, "loss": 0.0, "lr": 2.7753303945534324e-08, "epoch": 4.66182959945689, "percentage": 93.24, "elapsed_time": "1:26:17", "remaining_time": "0:06:15", "throughput": 10189.79, "total_tokens": 52756224}
{"current_steps": 54940, "total_steps": 58920, "loss": 0.0, "lr": 2.7684043512887e-08, "epoch": 4.662253903598099, "percentage": 93.25, "elapsed_time": "1:26:17", "remaining_time": "0:06:15", "throughput": 10190.0, "total_tokens": 52761216}
{"current_steps": 54945, "total_steps": 58920, "loss": 0.0, "lr": 2.7614868397454415e-08, "epoch": 4.662678207739307, "percentage": 93.25, "elapsed_time": "1:26:18", "remaining_time": "0:06:14", "throughput": 10190.22, "total_tokens": 52766336}
{"current_steps": 54950, "total_steps": 58920, "loss": 0.0, "lr": 2.754577860530627e-08, "epoch": 4.663102511880516, "percentage": 93.26, "elapsed_time": "1:26:18", "remaining_time": "0:06:14", "throughput": 10190.38, "total_tokens": 52771136}
{"current_steps": 54955, "total_steps": 58920, "loss": 0.0, "lr": 2.747677414250493e-08, "epoch": 4.663526816021724, "percentage": 93.27, "elapsed_time": "1:26:18", "remaining_time": "0:06:13", "throughput": 10190.55, "total_tokens": 52775936}
{"current_steps": 54960, "total_steps": 58920, "loss": 0.0, "lr": 2.7407855015105453e-08, "epoch": 4.663951120162933, "percentage": 93.28, "elapsed_time": "1:26:19", "remaining_time": "0:06:13", "throughput": 10190.77, "total_tokens": 52781184}
{"current_steps": 54965, "total_steps": 58920, "loss": 0.0, "lr": 2.7339021229155212e-08, "epoch": 4.664375424304141, "percentage": 93.29, "elapsed_time": "1:26:19", "remaining_time": "0:06:12", "throughput": 10190.9, "total_tokens": 52785792}
{"current_steps": 54970, "total_steps": 58920, "loss": 0.0, "lr": 2.727027279069405e-08, "epoch": 4.66479972844535, "percentage": 93.3, "elapsed_time": "1:26:20", "remaining_time": "0:06:12", "throughput": 10191.04, "total_tokens": 52790464}
{"current_steps": 54975, "total_steps": 58920, "loss": 0.0, "lr": 2.720160970575436e-08, "epoch": 4.665224032586558, "percentage": 93.3, "elapsed_time": "1:26:20", "remaining_time": "0:06:11", "throughput": 10191.23, "total_tokens": 52795392}
{"current_steps": 54980, "total_steps": 58920, "loss": 0.0, "lr": 2.71330319803611e-08, "epoch": 4.665648336727767, "percentage": 93.31, "elapsed_time": "1:26:20", "remaining_time": "0:06:11", "throughput": 10191.35, "total_tokens": 52799808}
{"current_steps": 54985, "total_steps": 58920, "loss": 0.0, "lr": 2.7064539620532012e-08, "epoch": 4.6660726408689746, "percentage": 93.32, "elapsed_time": "1:26:21", "remaining_time": "0:06:10", "throughput": 10191.46, "total_tokens": 52804224}
{"current_steps": 54990, "total_steps": 58920, "loss": 0.0, "lr": 2.6996132632276625e-08, "epoch": 4.666496945010183, "percentage": 93.33, "elapsed_time": "1:26:21", "remaining_time": "0:06:10", "throughput": 10191.62, "total_tokens": 52808896}
{"current_steps": 54995, "total_steps": 58920, "loss": 0.0, "lr": 2.692781102159758e-08, "epoch": 4.666921249151391, "percentage": 93.34, "elapsed_time": "1:26:21", "remaining_time": "0:06:09", "throughput": 10191.71, "total_tokens": 52813184}
{"current_steps": 55000, "total_steps": 58920, "loss": 0.0, "lr": 2.685957479448997e-08, "epoch": 4.6673455532926, "percentage": 93.35, "elapsed_time": "1:26:22", "remaining_time": "0:06:09", "throughput": 10191.88, "total_tokens": 52817920}
{"current_steps": 55005, "total_steps": 58920, "loss": 0.0, "lr": 2.6791423956941005e-08, "epoch": 4.667769857433808, "percentage": 93.36, "elapsed_time": "1:26:22", "remaining_time": "0:06:08", "throughput": 10192.0, "total_tokens": 52822400}
{"current_steps": 55010, "total_steps": 58920, "loss": 0.0, "lr": 2.6723358514930905e-08, "epoch": 4.668194161575017, "percentage": 93.36, "elapsed_time": "1:26:23", "remaining_time": "0:06:08", "throughput": 10192.24, "total_tokens": 52827584}
{"current_steps": 55015, "total_steps": 58920, "loss": 0.0, "lr": 2.6655378474432e-08, "epoch": 4.668618465716225, "percentage": 93.37, "elapsed_time": "1:26:23", "remaining_time": "0:06:07", "throughput": 10192.32, "total_tokens": 52831808}
{"current_steps": 55020, "total_steps": 58920, "loss": 0.0, "lr": 2.658748384140963e-08, "epoch": 4.669042769857434, "percentage": 93.38, "elapsed_time": "1:26:23", "remaining_time": "0:06:07", "throughput": 10192.49, "total_tokens": 52836608}
{"current_steps": 55025, "total_steps": 58920, "loss": 0.0, "lr": 2.651967462182081e-08, "epoch": 4.669467073998642, "percentage": 93.39, "elapsed_time": "1:26:24", "remaining_time": "0:06:06", "throughput": 10192.57, "total_tokens": 52840768}
{"current_steps": 55030, "total_steps": 58920, "loss": 0.0, "lr": 2.6451950821615998e-08, "epoch": 4.669891378139851, "percentage": 93.4, "elapsed_time": "1:26:24", "remaining_time": "0:06:06", "throughput": 10192.77, "total_tokens": 52845696}
{"current_steps": 55035, "total_steps": 58920, "loss": 0.0, "lr": 2.6384312446737333e-08, "epoch": 4.670315682281059, "percentage": 93.41, "elapsed_time": "1:26:24", "remaining_time": "0:06:06", "throughput": 10192.86, "total_tokens": 52849920}
{"current_steps": 55040, "total_steps": 58920, "loss": 0.0, "lr": 2.6316759503120067e-08, "epoch": 4.670739986422268, "percentage": 93.41, "elapsed_time": "1:26:25", "remaining_time": "0:06:05", "throughput": 10193.02, "total_tokens": 52854656}
{"current_steps": 55045, "total_steps": 58920, "loss": 0.0, "lr": 2.624929199669179e-08, "epoch": 4.671164290563476, "percentage": 93.42, "elapsed_time": "1:26:25", "remaining_time": "0:06:05", "throughput": 10193.12, "total_tokens": 52859008}
{"current_steps": 55050, "total_steps": 58920, "loss": 0.0, "lr": 2.6181909933372326e-08, "epoch": 4.6715885947046845, "percentage": 93.43, "elapsed_time": "1:26:26", "remaining_time": "0:06:04", "throughput": 10193.26, "total_tokens": 52863552}
{"current_steps": 55055, "total_steps": 58920, "loss": 0.0, "lr": 2.6114613319074497e-08, "epoch": 4.672012898845892, "percentage": 93.44, "elapsed_time": "1:26:26", "remaining_time": "0:06:04", "throughput": 10193.4, "total_tokens": 52868096}
{"current_steps": 55060, "total_steps": 58920, "loss": 0.0, "lr": 2.6047402159702914e-08, "epoch": 4.672437202987101, "percentage": 93.45, "elapsed_time": "1:26:26", "remaining_time": "0:06:03", "throughput": 10193.52, "total_tokens": 52872576}
{"current_steps": 55065, "total_steps": 58920, "loss": 0.0, "lr": 2.5980276461155415e-08, "epoch": 4.672861507128309, "percentage": 93.46, "elapsed_time": "1:26:27", "remaining_time": "0:06:03", "throughput": 10193.69, "total_tokens": 52877376}
{"current_steps": 55070, "total_steps": 58920, "loss": 0.0, "lr": 2.5913236229321956e-08, "epoch": 4.673285811269518, "percentage": 93.47, "elapsed_time": "1:26:27", "remaining_time": "0:06:02", "throughput": 10193.9, "total_tokens": 52882432}
{"current_steps": 55075, "total_steps": 58920, "loss": 0.0, "lr": 2.5846281470085163e-08, "epoch": 4.673710115410726, "percentage": 93.47, "elapsed_time": "1:26:28", "remaining_time": "0:06:02", "throughput": 10194.14, "total_tokens": 52887872}
{"current_steps": 55080, "total_steps": 58920, "loss": 0.0, "lr": 2.5779412189320117e-08, "epoch": 4.674134419551935, "percentage": 93.48, "elapsed_time": "1:26:28", "remaining_time": "0:06:01", "throughput": 10194.33, "total_tokens": 52892736}
{"current_steps": 55085, "total_steps": 58920, "loss": 0.0, "lr": 2.571262839289401e-08, "epoch": 4.674558723693143, "percentage": 93.49, "elapsed_time": "1:26:28", "remaining_time": "0:06:01", "throughput": 10194.53, "total_tokens": 52897664}
{"current_steps": 55090, "total_steps": 58920, "loss": 0.0, "lr": 2.5645930086667267e-08, "epoch": 4.674983027834352, "percentage": 93.5, "elapsed_time": "1:26:29", "remaining_time": "0:06:00", "throughput": 10194.67, "total_tokens": 52902272}
{"current_steps": 55095, "total_steps": 58920, "loss": 0.0003, "lr": 2.5579317276492097e-08, "epoch": 4.67540733197556, "percentage": 93.51, "elapsed_time": "1:26:29", "remaining_time": "0:06:00", "throughput": 10194.82, "total_tokens": 52906880}
{"current_steps": 55100, "total_steps": 58920, "loss": 0.0, "lr": 2.5512789968213822e-08, "epoch": 4.675831636116769, "percentage": 93.52, "elapsed_time": "1:26:29", "remaining_time": "0:05:59", "throughput": 10195.06, "total_tokens": 52912128}
{"current_steps": 55105, "total_steps": 58920, "loss": 0.0, "lr": 2.5446348167669884e-08, "epoch": 4.676255940257977, "percentage": 93.53, "elapsed_time": "1:26:30", "remaining_time": "0:05:59", "throughput": 10195.27, "total_tokens": 52917120}
{"current_steps": 55110, "total_steps": 58920, "loss": 0.0, "lr": 2.5379991880690175e-08, "epoch": 4.6766802443991855, "percentage": 93.53, "elapsed_time": "1:26:30", "remaining_time": "0:05:58", "throughput": 10195.48, "total_tokens": 52922240}
{"current_steps": 55115, "total_steps": 58920, "loss": 0.0, "lr": 2.5313721113097376e-08, "epoch": 4.6771045485403935, "percentage": 93.54, "elapsed_time": "1:26:31", "remaining_time": "0:05:58", "throughput": 10195.66, "total_tokens": 52927040}
{"current_steps": 55120, "total_steps": 58920, "loss": 0.0, "lr": 2.5247535870706492e-08, "epoch": 4.677528852681602, "percentage": 93.55, "elapsed_time": "1:26:31", "remaining_time": "0:05:57", "throughput": 10195.83, "total_tokens": 52931904}
{"current_steps": 55125, "total_steps": 58920, "loss": 0.0, "lr": 2.5181436159324997e-08, "epoch": 4.67795315682281, "percentage": 93.56, "elapsed_time": "1:26:31", "remaining_time": "0:05:57", "throughput": 10196.01, "total_tokens": 52936832}
{"current_steps": 55130, "total_steps": 58920, "loss": 0.0, "lr": 2.5115421984752916e-08, "epoch": 4.678377460964019, "percentage": 93.57, "elapsed_time": "1:26:32", "remaining_time": "0:05:56", "throughput": 10196.14, "total_tokens": 52941376}
{"current_steps": 55135, "total_steps": 58920, "loss": 0.0, "lr": 2.5049493352782724e-08, "epoch": 4.678801765105227, "percentage": 93.58, "elapsed_time": "1:26:32", "remaining_time": "0:05:56", "throughput": 10196.25, "total_tokens": 52945792}
{"current_steps": 55140, "total_steps": 58920, "loss": 0.0, "lr": 2.4983650269199463e-08, "epoch": 4.679226069246436, "percentage": 93.58, "elapsed_time": "1:26:33", "remaining_time": "0:05:55", "throughput": 10196.37, "total_tokens": 52950208}
{"current_steps": 55145, "total_steps": 58920, "loss": 0.0, "lr": 2.491789273978062e-08, "epoch": 4.679650373387644, "percentage": 93.59, "elapsed_time": "1:26:33", "remaining_time": "0:05:55", "throughput": 10196.44, "total_tokens": 52954368}
{"current_steps": 55150, "total_steps": 58920, "loss": 0.0, "lr": 2.485222077029614e-08, "epoch": 4.680074677528853, "percentage": 93.6, "elapsed_time": "1:26:33", "remaining_time": "0:05:55", "throughput": 10196.71, "total_tokens": 52959872}
{"current_steps": 55155, "total_steps": 58920, "loss": 0.0, "lr": 2.4786634366508517e-08, "epoch": 4.680498981670061, "percentage": 93.61, "elapsed_time": "1:26:34", "remaining_time": "0:05:54", "throughput": 10196.87, "total_tokens": 52964544}
{"current_steps": 55160, "total_steps": 58920, "loss": 0.0, "lr": 2.472113353417282e-08, "epoch": 4.68092328581127, "percentage": 93.62, "elapsed_time": "1:26:34", "remaining_time": "0:05:54", "throughput": 10197.01, "total_tokens": 52969152}
{"current_steps": 55165, "total_steps": 58920, "loss": 0.0, "lr": 2.4655718279036342e-08, "epoch": 4.681347589952478, "percentage": 93.63, "elapsed_time": "1:26:34", "remaining_time": "0:05:53", "throughput": 10197.23, "total_tokens": 52974464}
{"current_steps": 55170, "total_steps": 58920, "loss": 0.0, "lr": 2.459038860683915e-08, "epoch": 4.6817718940936865, "percentage": 93.64, "elapsed_time": "1:26:35", "remaining_time": "0:05:53", "throughput": 10197.42, "total_tokens": 52979328}
{"current_steps": 55175, "total_steps": 58920, "loss": 0.0, "lr": 2.4525144523313666e-08, "epoch": 4.6821961982348945, "percentage": 93.64, "elapsed_time": "1:26:35", "remaining_time": "0:05:52", "throughput": 10197.57, "total_tokens": 52984000}
{"current_steps": 55180, "total_steps": 58920, "loss": 0.0, "lr": 2.4459986034184755e-08, "epoch": 4.682620502376103, "percentage": 93.65, "elapsed_time": "1:26:36", "remaining_time": "0:05:52", "throughput": 10197.65, "total_tokens": 52988224}
{"current_steps": 55185, "total_steps": 58920, "loss": 0.0, "lr": 2.439491314516995e-08, "epoch": 4.683044806517311, "percentage": 93.66, "elapsed_time": "1:26:36", "remaining_time": "0:05:51", "throughput": 10197.82, "total_tokens": 52992960}
{"current_steps": 55190, "total_steps": 58920, "loss": 0.0, "lr": 2.4329925861979128e-08, "epoch": 4.68346911065852, "percentage": 93.67, "elapsed_time": "1:26:36", "remaining_time": "0:05:51", "throughput": 10198.01, "total_tokens": 52997888}
{"current_steps": 55195, "total_steps": 58920, "loss": 0.0, "lr": 2.426502419031451e-08, "epoch": 4.683893414799728, "percentage": 93.68, "elapsed_time": "1:26:37", "remaining_time": "0:05:50", "throughput": 10198.25, "total_tokens": 53003264}
{"current_steps": 55200, "total_steps": 58920, "loss": 0.0, "lr": 2.4200208135871313e-08, "epoch": 4.684317718940937, "percentage": 93.69, "elapsed_time": "1:26:37", "remaining_time": "0:05:50", "throughput": 10198.39, "total_tokens": 53007872}
{"current_steps": 55205, "total_steps": 58920, "loss": 0.0, "lr": 2.413547770433677e-08, "epoch": 4.684742023082145, "percentage": 93.69, "elapsed_time": "1:26:38", "remaining_time": "0:05:49", "throughput": 10198.65, "total_tokens": 53013184}
{"current_steps": 55210, "total_steps": 58920, "loss": 0.0, "lr": 2.407083290139056e-08, "epoch": 4.685166327223354, "percentage": 93.7, "elapsed_time": "1:26:38", "remaining_time": "0:05:49", "throughput": 10198.77, "total_tokens": 53017664}
{"current_steps": 55215, "total_steps": 58920, "loss": 0.0, "lr": 2.400627373270536e-08, "epoch": 4.685590631364562, "percentage": 93.71, "elapsed_time": "1:26:38", "remaining_time": "0:05:48", "throughput": 10198.85, "total_tokens": 53021824}
{"current_steps": 55220, "total_steps": 58920, "loss": 0.0, "lr": 2.394180020394565e-08, "epoch": 4.686014935505771, "percentage": 93.72, "elapsed_time": "1:26:39", "remaining_time": "0:05:48", "throughput": 10199.11, "total_tokens": 53027264}
{"current_steps": 55225, "total_steps": 58920, "loss": 0.0, "lr": 2.387741232076901e-08, "epoch": 4.686439239646979, "percentage": 93.73, "elapsed_time": "1:26:39", "remaining_time": "0:05:47", "throughput": 10199.27, "total_tokens": 53031936}
{"current_steps": 55230, "total_steps": 58920, "loss": 0.0, "lr": 2.381311008882514e-08, "epoch": 4.686863543788188, "percentage": 93.74, "elapsed_time": "1:26:39", "remaining_time": "0:05:47", "throughput": 10199.45, "total_tokens": 53036800}
{"current_steps": 55235, "total_steps": 58920, "loss": 0.0, "lr": 2.3748893513756418e-08, "epoch": 4.687287847929396, "percentage": 93.75, "elapsed_time": "1:26:40", "remaining_time": "0:05:46", "throughput": 10199.6, "total_tokens": 53041472}
{"current_steps": 55240, "total_steps": 58920, "loss": 0.0, "lr": 2.368476260119745e-08, "epoch": 4.687712152070604, "percentage": 93.75, "elapsed_time": "1:26:40", "remaining_time": "0:05:46", "throughput": 10199.73, "total_tokens": 53045952}
{"current_steps": 55245, "total_steps": 58920, "loss": 0.0, "lr": 2.3620717356775733e-08, "epoch": 4.688136456211812, "percentage": 93.76, "elapsed_time": "1:26:41", "remaining_time": "0:05:45", "throughput": 10199.83, "total_tokens": 53050304}
{"current_steps": 55250, "total_steps": 58920, "loss": 0.0, "lr": 2.355675778611077e-08, "epoch": 4.688560760353021, "percentage": 93.77, "elapsed_time": "1:26:41", "remaining_time": "0:05:45", "throughput": 10199.99, "total_tokens": 53054976}
{"current_steps": 55255, "total_steps": 58920, "loss": 0.0, "lr": 2.349288389481474e-08, "epoch": 4.688985064494229, "percentage": 93.78, "elapsed_time": "1:26:41", "remaining_time": "0:05:45", "throughput": 10200.19, "total_tokens": 53059968}
{"current_steps": 55260, "total_steps": 58920, "loss": 0.0, "lr": 2.3429095688492717e-08, "epoch": 4.689409368635438, "percentage": 93.79, "elapsed_time": "1:26:42", "remaining_time": "0:05:44", "throughput": 10200.35, "total_tokens": 53064640}
{"current_steps": 55265, "total_steps": 58920, "loss": 0.0, "lr": 2.3365393172741554e-08, "epoch": 4.689833672776646, "percentage": 93.8, "elapsed_time": "1:26:42", "remaining_time": "0:05:44", "throughput": 10200.52, "total_tokens": 53069504}
{"current_steps": 55270, "total_steps": 58920, "loss": 0.0, "lr": 2.3301776353151115e-08, "epoch": 4.690257976917855, "percentage": 93.81, "elapsed_time": "1:26:43", "remaining_time": "0:05:43", "throughput": 10200.68, "total_tokens": 53074432}
{"current_steps": 55275, "total_steps": 58920, "loss": 0.0, "lr": 2.3238245235303266e-08, "epoch": 4.690682281059063, "percentage": 93.81, "elapsed_time": "1:26:43", "remaining_time": "0:05:43", "throughput": 10200.83, "total_tokens": 53079040}
{"current_steps": 55280, "total_steps": 58920, "loss": 0.0, "lr": 2.3174799824772885e-08, "epoch": 4.691106585200272, "percentage": 93.82, "elapsed_time": "1:26:43", "remaining_time": "0:05:42", "throughput": 10200.95, "total_tokens": 53083456}
{"current_steps": 55285, "total_steps": 58920, "loss": 0.0, "lr": 2.3111440127127068e-08, "epoch": 4.69153088934148, "percentage": 93.83, "elapsed_time": "1:26:44", "remaining_time": "0:05:42", "throughput": 10201.09, "total_tokens": 53088064}
{"current_steps": 55290, "total_steps": 58920, "loss": 0.0, "lr": 2.3048166147925264e-08, "epoch": 4.691955193482689, "percentage": 93.84, "elapsed_time": "1:26:44", "remaining_time": "0:05:41", "throughput": 10201.25, "total_tokens": 53092800}
{"current_steps": 55295, "total_steps": 58920, "loss": 0.0, "lr": 2.2984977892719694e-08, "epoch": 4.692379497623897, "percentage": 93.85, "elapsed_time": "1:26:44", "remaining_time": "0:05:41", "throughput": 10201.42, "total_tokens": 53097536}
{"current_steps": 55300, "total_steps": 58920, "loss": 0.0, "lr": 2.2921875367054698e-08, "epoch": 4.6928038017651055, "percentage": 93.86, "elapsed_time": "1:26:45", "remaining_time": "0:05:40", "throughput": 10201.59, "total_tokens": 53102400}
{"current_steps": 55305, "total_steps": 58920, "loss": 0.0, "lr": 2.285885857646752e-08, "epoch": 4.6932281059063135, "percentage": 93.86, "elapsed_time": "1:26:45", "remaining_time": "0:05:40", "throughput": 10201.78, "total_tokens": 53107392}
{"current_steps": 55310, "total_steps": 58920, "loss": 0.0, "lr": 2.27959275264874e-08, "epoch": 4.693652410047522, "percentage": 93.87, "elapsed_time": "1:26:46", "remaining_time": "0:05:39", "throughput": 10202.05, "total_tokens": 53112832}
{"current_steps": 55315, "total_steps": 58920, "loss": 0.0, "lr": 2.273308222263659e-08, "epoch": 4.69407671418873, "percentage": 93.88, "elapsed_time": "1:26:46", "remaining_time": "0:05:39", "throughput": 10202.17, "total_tokens": 53117248}
{"current_steps": 55320, "total_steps": 58920, "loss": 0.0, "lr": 2.267032267042934e-08, "epoch": 4.694501018329939, "percentage": 93.89, "elapsed_time": "1:26:46", "remaining_time": "0:05:38", "throughput": 10202.33, "total_tokens": 53121984}
{"current_steps": 55325, "total_steps": 58920, "loss": 0.0493, "lr": 2.2607648875372698e-08, "epoch": 4.694925322471147, "percentage": 93.9, "elapsed_time": "1:26:47", "remaining_time": "0:05:38", "throughput": 10202.53, "total_tokens": 53126976}
{"current_steps": 55330, "total_steps": 58920, "loss": 0.0, "lr": 2.2545060842966035e-08, "epoch": 4.695349626612356, "percentage": 93.91, "elapsed_time": "1:26:47", "remaining_time": "0:05:37", "throughput": 10202.73, "total_tokens": 53131904}
{"current_steps": 55335, "total_steps": 58920, "loss": 0.0, "lr": 2.248255857870107e-08, "epoch": 4.695773930753564, "percentage": 93.92, "elapsed_time": "1:26:47", "remaining_time": "0:05:37", "throughput": 10202.83, "total_tokens": 53136256}
{"current_steps": 55340, "total_steps": 58920, "loss": 0.0, "lr": 2.2420142088062423e-08, "epoch": 4.696198234894773, "percentage": 93.92, "elapsed_time": "1:26:48", "remaining_time": "0:05:36", "throughput": 10202.96, "total_tokens": 53140800}
{"current_steps": 55345, "total_steps": 58920, "loss": 0.0, "lr": 2.2357811376526702e-08, "epoch": 4.696622539035981, "percentage": 93.93, "elapsed_time": "1:26:48", "remaining_time": "0:05:36", "throughput": 10203.12, "total_tokens": 53145536}
{"current_steps": 55350, "total_steps": 58920, "loss": 0.0, "lr": 2.2295566449563207e-08, "epoch": 4.69704684317719, "percentage": 93.94, "elapsed_time": "1:26:49", "remaining_time": "0:05:35", "throughput": 10203.34, "total_tokens": 53150720}
{"current_steps": 55355, "total_steps": 58920, "loss": 0.0, "lr": 2.22334073126339e-08, "epoch": 4.697471147318398, "percentage": 93.95, "elapsed_time": "1:26:49", "remaining_time": "0:05:35", "throughput": 10203.47, "total_tokens": 53155200}
{"current_steps": 55360, "total_steps": 58920, "loss": 0.0, "lr": 2.217133397119275e-08, "epoch": 4.6978954514596065, "percentage": 93.96, "elapsed_time": "1:26:49", "remaining_time": "0:05:35", "throughput": 10203.62, "total_tokens": 53159872}
{"current_steps": 55365, "total_steps": 58920, "loss": 0.0, "lr": 2.2109346430686737e-08, "epoch": 4.6983197556008145, "percentage": 93.97, "elapsed_time": "1:26:50", "remaining_time": "0:05:34", "throughput": 10203.74, "total_tokens": 53164288}
{"current_steps": 55370, "total_steps": 58920, "loss": 0.0, "lr": 2.204744469655484e-08, "epoch": 4.698744059742023, "percentage": 93.97, "elapsed_time": "1:26:50", "remaining_time": "0:05:34", "throughput": 10203.83, "total_tokens": 53168576}
{"current_steps": 55375, "total_steps": 58920, "loss": 0.0, "lr": 2.1985628774228715e-08, "epoch": 4.699168363883231, "percentage": 93.98, "elapsed_time": "1:26:51", "remaining_time": "0:05:33", "throughput": 10203.97, "total_tokens": 53173312}
{"current_steps": 55380, "total_steps": 58920, "loss": 0.0, "lr": 2.192389866913269e-08, "epoch": 4.69959266802444, "percentage": 93.99, "elapsed_time": "1:26:51", "remaining_time": "0:05:33", "throughput": 10204.08, "total_tokens": 53177728}
{"current_steps": 55385, "total_steps": 58920, "loss": 0.0, "lr": 2.186225438668321e-08, "epoch": 4.700016972165648, "percentage": 94.0, "elapsed_time": "1:26:51", "remaining_time": "0:05:32", "throughput": 10204.23, "total_tokens": 53182336}
{"current_steps": 55390, "total_steps": 58920, "loss": 0.0, "lr": 2.180069593228928e-08, "epoch": 4.700441276306857, "percentage": 94.01, "elapsed_time": "1:26:52", "remaining_time": "0:05:32", "throughput": 10204.44, "total_tokens": 53187328}
{"current_steps": 55395, "total_steps": 58920, "loss": 0.0, "lr": 2.1739223311352584e-08, "epoch": 4.700865580448065, "percentage": 94.02, "elapsed_time": "1:26:52", "remaining_time": "0:05:31", "throughput": 10204.59, "total_tokens": 53192000}
{"current_steps": 55400, "total_steps": 58920, "loss": 0.0, "lr": 2.1677836529267023e-08, "epoch": 4.701289884589274, "percentage": 94.03, "elapsed_time": "1:26:52", "remaining_time": "0:05:31", "throughput": 10204.77, "total_tokens": 53196864}
{"current_steps": 55405, "total_steps": 58920, "loss": 0.0, "lr": 2.161653559141907e-08, "epoch": 4.701714188730482, "percentage": 94.03, "elapsed_time": "1:26:53", "remaining_time": "0:05:30", "throughput": 10204.92, "total_tokens": 53201472}
{"current_steps": 55410, "total_steps": 58920, "loss": 0.0, "lr": 2.1555320503187648e-08, "epoch": 4.702138492871691, "percentage": 94.04, "elapsed_time": "1:26:53", "remaining_time": "0:05:30", "throughput": 10205.04, "total_tokens": 53205952}
{"current_steps": 55415, "total_steps": 58920, "loss": 0.0, "lr": 2.1494191269944227e-08, "epoch": 4.702562797012899, "percentage": 94.05, "elapsed_time": "1:26:54", "remaining_time": "0:05:29", "throughput": 10205.21, "total_tokens": 53210752}
{"current_steps": 55420, "total_steps": 58920, "loss": 0.0, "lr": 2.143314789705264e-08, "epoch": 4.702987101154108, "percentage": 94.06, "elapsed_time": "1:26:54", "remaining_time": "0:05:29", "throughput": 10205.37, "total_tokens": 53215552}
{"current_steps": 55425, "total_steps": 58920, "loss": 0.0, "lr": 2.137219038986926e-08, "epoch": 4.7034114052953155, "percentage": 94.07, "elapsed_time": "1:26:54", "remaining_time": "0:05:28", "throughput": 10205.48, "total_tokens": 53219904}
{"current_steps": 55430, "total_steps": 58920, "loss": 0.0479, "lr": 2.1311318753742813e-08, "epoch": 4.703835709436524, "percentage": 94.08, "elapsed_time": "1:26:55", "remaining_time": "0:05:28", "throughput": 10205.6, "total_tokens": 53224448}
{"current_steps": 55435, "total_steps": 58920, "loss": 0.0, "lr": 2.1250532994014693e-08, "epoch": 4.704260013577732, "percentage": 94.09, "elapsed_time": "1:26:55", "remaining_time": "0:05:27", "throughput": 10205.76, "total_tokens": 53229184}
{"current_steps": 55440, "total_steps": 58920, "loss": 0.0, "lr": 2.1189833116018407e-08, "epoch": 4.704684317718941, "percentage": 94.09, "elapsed_time": "1:26:55", "remaining_time": "0:05:27", "throughput": 10205.89, "total_tokens": 53233728}
{"current_steps": 55445, "total_steps": 58920, "loss": 0.0, "lr": 2.1129219125080254e-08, "epoch": 4.705108621860149, "percentage": 94.1, "elapsed_time": "1:26:56", "remaining_time": "0:05:26", "throughput": 10205.97, "total_tokens": 53237952}
{"current_steps": 55450, "total_steps": 58920, "loss": 0.0, "lr": 2.1068691026519092e-08, "epoch": 4.705532926001358, "percentage": 94.11, "elapsed_time": "1:26:56", "remaining_time": "0:05:26", "throughput": 10206.15, "total_tokens": 53242816}
{"current_steps": 55455, "total_steps": 58920, "loss": 0.0, "lr": 2.100824882564578e-08, "epoch": 4.705957230142566, "percentage": 94.12, "elapsed_time": "1:26:57", "remaining_time": "0:05:25", "throughput": 10206.43, "total_tokens": 53248320}
{"current_steps": 55460, "total_steps": 58920, "loss": 0.0, "lr": 2.0947892527764076e-08, "epoch": 4.706381534283775, "percentage": 94.13, "elapsed_time": "1:26:57", "remaining_time": "0:05:25", "throughput": 10206.56, "total_tokens": 53252864}
{"current_steps": 55465, "total_steps": 58920, "loss": 0.0, "lr": 2.0887622138169857e-08, "epoch": 4.706805838424983, "percentage": 94.14, "elapsed_time": "1:26:57", "remaining_time": "0:05:25", "throughput": 10206.85, "total_tokens": 53258560}
{"current_steps": 55470, "total_steps": 58920, "loss": 0.0, "lr": 2.082743766215167e-08, "epoch": 4.707230142566192, "percentage": 94.14, "elapsed_time": "1:26:58", "remaining_time": "0:05:24", "throughput": 10206.97, "total_tokens": 53262976}
{"current_steps": 55475, "total_steps": 58920, "loss": 0.0, "lr": 2.0767339104990732e-08, "epoch": 4.7076544467074, "percentage": 94.15, "elapsed_time": "1:26:58", "remaining_time": "0:05:24", "throughput": 10207.18, "total_tokens": 53268032}
{"current_steps": 55480, "total_steps": 58920, "loss": 0.0, "lr": 2.070732647196005e-08, "epoch": 4.708078750848609, "percentage": 94.16, "elapsed_time": "1:26:59", "remaining_time": "0:05:23", "throughput": 10207.33, "total_tokens": 53272704}
{"current_steps": 55485, "total_steps": 58920, "loss": 0.0, "lr": 2.064739976832597e-08, "epoch": 4.708503054989817, "percentage": 94.17, "elapsed_time": "1:26:59", "remaining_time": "0:05:23", "throughput": 10207.46, "total_tokens": 53277184}
{"current_steps": 55490, "total_steps": 58920, "loss": 0.0, "lr": 2.058755899934639e-08, "epoch": 4.7089273591310254, "percentage": 94.18, "elapsed_time": "1:26:59", "remaining_time": "0:05:22", "throughput": 10207.71, "total_tokens": 53282432}
{"current_steps": 55495, "total_steps": 58920, "loss": 0.0, "lr": 2.0527804170272556e-08, "epoch": 4.709351663272233, "percentage": 94.19, "elapsed_time": "1:27:00", "remaining_time": "0:05:22", "throughput": 10207.8, "total_tokens": 53286720}
{"current_steps": 55500, "total_steps": 58920, "loss": 0.0, "lr": 2.04681352863475e-08, "epoch": 4.709775967413442, "percentage": 94.2, "elapsed_time": "1:27:00", "remaining_time": "0:05:21", "throughput": 10207.92, "total_tokens": 53291200}
{"current_steps": 55505, "total_steps": 58920, "loss": 0.0, "lr": 2.0408552352806806e-08, "epoch": 4.71020027155465, "percentage": 94.2, "elapsed_time": "1:27:00", "remaining_time": "0:05:21", "throughput": 10208.13, "total_tokens": 53296256}
{"current_steps": 55510, "total_steps": 58920, "loss": 0.0, "lr": 2.0349055374879078e-08, "epoch": 4.710624575695859, "percentage": 94.21, "elapsed_time": "1:27:01", "remaining_time": "0:05:20", "throughput": 10208.26, "total_tokens": 53300800}
{"current_steps": 55515, "total_steps": 58920, "loss": 0.0, "lr": 2.0289644357784574e-08, "epoch": 4.711048879837067, "percentage": 94.22, "elapsed_time": "1:27:01", "remaining_time": "0:05:20", "throughput": 10208.4, "total_tokens": 53305408}
{"current_steps": 55520, "total_steps": 58920, "loss": 0.0, "lr": 2.023031930673669e-08, "epoch": 4.711473183978276, "percentage": 94.23, "elapsed_time": "1:27:02", "remaining_time": "0:05:19", "throughput": 10208.57, "total_tokens": 53310144}
{"current_steps": 55525, "total_steps": 58920, "loss": 0.0, "lr": 2.0171080226940695e-08, "epoch": 4.711897488119484, "percentage": 94.24, "elapsed_time": "1:27:02", "remaining_time": "0:05:19", "throughput": 10208.71, "total_tokens": 53314752}
{"current_steps": 55530, "total_steps": 58920, "loss": 0.0, "lr": 2.0111927123594774e-08, "epoch": 4.712321792260693, "percentage": 94.25, "elapsed_time": "1:27:02", "remaining_time": "0:05:18", "throughput": 10208.88, "total_tokens": 53319488}
{"current_steps": 55535, "total_steps": 58920, "loss": 0.0, "lr": 2.0052860001889548e-08, "epoch": 4.712746096401901, "percentage": 94.25, "elapsed_time": "1:27:03", "remaining_time": "0:05:18", "throughput": 10209.17, "total_tokens": 53325120}
{"current_steps": 55540, "total_steps": 58920, "loss": 0.0, "lr": 1.999387886700754e-08, "epoch": 4.71317040054311, "percentage": 94.26, "elapsed_time": "1:27:03", "remaining_time": "0:05:17", "throughput": 10209.58, "total_tokens": 53331648}
{"current_steps": 55545, "total_steps": 58920, "loss": 0.0, "lr": 1.993498372412461e-08, "epoch": 4.713594704684318, "percentage": 94.27, "elapsed_time": "1:27:04", "remaining_time": "0:05:17", "throughput": 10209.73, "total_tokens": 53336256}
{"current_steps": 55550, "total_steps": 58920, "loss": 0.0, "lr": 1.9876174578408066e-08, "epoch": 4.7140190088255265, "percentage": 94.28, "elapsed_time": "1:27:04", "remaining_time": "0:05:16", "throughput": 10209.83, "total_tokens": 53340608}
{"current_steps": 55555, "total_steps": 58920, "loss": 0.0, "lr": 1.9817451435018674e-08, "epoch": 4.7144433129667345, "percentage": 94.29, "elapsed_time": "1:27:04", "remaining_time": "0:05:16", "throughput": 10209.98, "total_tokens": 53345216}
{"current_steps": 55560, "total_steps": 58920, "loss": 0.0, "lr": 1.9758814299108862e-08, "epoch": 4.714867617107943, "percentage": 94.3, "elapsed_time": "1:27:05", "remaining_time": "0:05:15", "throughput": 10210.1, "total_tokens": 53349632}
{"current_steps": 55565, "total_steps": 58920, "loss": 0.0, "lr": 1.9700263175824074e-08, "epoch": 4.715291921249151, "percentage": 94.31, "elapsed_time": "1:27:05", "remaining_time": "0:05:15", "throughput": 10210.32, "total_tokens": 53354752}
{"current_steps": 55570, "total_steps": 58920, "loss": 0.0, "lr": 1.9641798070301753e-08, "epoch": 4.71571622539036, "percentage": 94.31, "elapsed_time": "1:27:05", "remaining_time": "0:05:15", "throughput": 10210.46, "total_tokens": 53359360}
{"current_steps": 55575, "total_steps": 58920, "loss": 0.0, "lr": 1.9583418987672016e-08, "epoch": 4.716140529531568, "percentage": 94.32, "elapsed_time": "1:27:06", "remaining_time": "0:05:14", "throughput": 10210.58, "total_tokens": 53363840}
{"current_steps": 55580, "total_steps": 58920, "loss": 0.0, "lr": 1.952512593305766e-08, "epoch": 4.716564833672777, "percentage": 94.33, "elapsed_time": "1:27:06", "remaining_time": "0:05:14", "throughput": 10210.74, "total_tokens": 53368576}
{"current_steps": 55585, "total_steps": 58920, "loss": 0.0, "lr": 1.9466918911573372e-08, "epoch": 4.716989137813985, "percentage": 94.34, "elapsed_time": "1:27:07", "remaining_time": "0:05:13", "throughput": 10210.9, "total_tokens": 53373312}
{"current_steps": 55590, "total_steps": 58920, "loss": 0.0, "lr": 1.9408797928326835e-08, "epoch": 4.717413441955194, "percentage": 94.35, "elapsed_time": "1:27:07", "remaining_time": "0:05:13", "throughput": 10211.05, "total_tokens": 53377984}
{"current_steps": 55595, "total_steps": 58920, "loss": 0.0, "lr": 1.9350762988417757e-08, "epoch": 4.717837746096402, "percentage": 94.36, "elapsed_time": "1:27:07", "remaining_time": "0:05:12", "throughput": 10211.18, "total_tokens": 53382528}
{"current_steps": 55600, "total_steps": 58920, "loss": 0.0, "lr": 1.9292814096938725e-08, "epoch": 4.718262050237611, "percentage": 94.37, "elapsed_time": "1:27:08", "remaining_time": "0:05:12", "throughput": 10211.3, "total_tokens": 53387008}
{"current_steps": 55605, "total_steps": 58920, "loss": 0.0, "lr": 1.9234951258974342e-08, "epoch": 4.718686354378819, "percentage": 94.37, "elapsed_time": "1:27:08", "remaining_time": "0:05:11", "throughput": 10211.48, "total_tokens": 53391872}
{"current_steps": 55610, "total_steps": 58920, "loss": 0.0, "lr": 1.9177174479602098e-08, "epoch": 4.7191106585200275, "percentage": 94.38, "elapsed_time": "1:27:08", "remaining_time": "0:05:11", "throughput": 10211.61, "total_tokens": 53396352}
{"current_steps": 55615, "total_steps": 58920, "loss": 0.0, "lr": 1.9119483763891385e-08, "epoch": 4.7195349626612355, "percentage": 94.39, "elapsed_time": "1:27:09", "remaining_time": "0:05:10", "throughput": 10211.71, "total_tokens": 53400704}
{"current_steps": 55620, "total_steps": 58920, "loss": 0.0, "lr": 1.90618791169046e-08, "epoch": 4.719959266802444, "percentage": 94.4, "elapsed_time": "1:27:09", "remaining_time": "0:05:10", "throughput": 10211.92, "total_tokens": 53405760}
{"current_steps": 55625, "total_steps": 58920, "loss": 0.0, "lr": 1.9004360543696253e-08, "epoch": 4.720383570943652, "percentage": 94.41, "elapsed_time": "1:27:10", "remaining_time": "0:05:09", "throughput": 10212.13, "total_tokens": 53410880}
{"current_steps": 55630, "total_steps": 58920, "loss": 0.0, "lr": 1.8946928049313303e-08, "epoch": 4.720807875084861, "percentage": 94.42, "elapsed_time": "1:27:10", "remaining_time": "0:05:09", "throughput": 10212.28, "total_tokens": 53415488}
{"current_steps": 55635, "total_steps": 58920, "loss": 0.0, "lr": 1.8889581638795394e-08, "epoch": 4.721232179226069, "percentage": 94.42, "elapsed_time": "1:27:10", "remaining_time": "0:05:08", "throughput": 10212.37, "total_tokens": 53419776}
{"current_steps": 55640, "total_steps": 58920, "loss": 0.0, "lr": 1.8832321317174494e-08, "epoch": 4.721656483367278, "percentage": 94.43, "elapsed_time": "1:27:11", "remaining_time": "0:05:08", "throughput": 10212.55, "total_tokens": 53424704}
{"current_steps": 55645, "total_steps": 58920, "loss": 0.0, "lr": 1.8775147089474808e-08, "epoch": 4.722080787508486, "percentage": 94.44, "elapsed_time": "1:27:11", "remaining_time": "0:05:07", "throughput": 10212.71, "total_tokens": 53429440}
{"current_steps": 55650, "total_steps": 58920, "loss": 0.0, "lr": 1.8718058960713323e-08, "epoch": 4.722505091649694, "percentage": 94.45, "elapsed_time": "1:27:12", "remaining_time": "0:05:07", "throughput": 10212.92, "total_tokens": 53434560}
{"current_steps": 55655, "total_steps": 58920, "loss": 0.0, "lr": 1.8661056935899256e-08, "epoch": 4.722929395790903, "percentage": 94.46, "elapsed_time": "1:27:12", "remaining_time": "0:05:06", "throughput": 10213.09, "total_tokens": 53439296}
{"current_steps": 55660, "total_steps": 58920, "loss": 0.0, "lr": 1.860414102003427e-08, "epoch": 4.723353699932112, "percentage": 94.47, "elapsed_time": "1:27:12", "remaining_time": "0:05:06", "throughput": 10213.25, "total_tokens": 53444032}
{"current_steps": 55665, "total_steps": 58920, "loss": 0.0, "lr": 1.8547311218112592e-08, "epoch": 4.72377800407332, "percentage": 94.48, "elapsed_time": "1:27:13", "remaining_time": "0:05:06", "throughput": 10213.49, "total_tokens": 53449344}
{"current_steps": 55670, "total_steps": 58920, "loss": 0.0, "lr": 1.8490567535120904e-08, "epoch": 4.724202308214528, "percentage": 94.48, "elapsed_time": "1:27:13", "remaining_time": "0:05:05", "throughput": 10213.57, "total_tokens": 53453504}
{"current_steps": 55675, "total_steps": 58920, "loss": 0.0, "lr": 1.843390997603822e-08, "epoch": 4.7246266123557366, "percentage": 94.49, "elapsed_time": "1:27:13", "remaining_time": "0:05:05", "throughput": 10213.72, "total_tokens": 53458176}
{"current_steps": 55680, "total_steps": 58920, "loss": 0.0, "lr": 1.8377338545835898e-08, "epoch": 4.725050916496945, "percentage": 94.5, "elapsed_time": "1:27:14", "remaining_time": "0:05:04", "throughput": 10213.9, "total_tokens": 53463040}
{"current_steps": 55685, "total_steps": 58920, "loss": 0.0, "lr": 1.8320853249477962e-08, "epoch": 4.725475220638153, "percentage": 94.51, "elapsed_time": "1:27:14", "remaining_time": "0:05:04", "throughput": 10214.04, "total_tokens": 53467584}
{"current_steps": 55690, "total_steps": 58920, "loss": 0.0, "lr": 1.826445409192101e-08, "epoch": 4.725899524779361, "percentage": 94.52, "elapsed_time": "1:27:15", "remaining_time": "0:05:03", "throughput": 10214.23, "total_tokens": 53472512}
{"current_steps": 55695, "total_steps": 58920, "loss": 0.0, "lr": 1.8208141078113413e-08, "epoch": 4.72632382892057, "percentage": 94.53, "elapsed_time": "1:27:15", "remaining_time": "0:05:03", "throughput": 10214.41, "total_tokens": 53477376}
{"current_steps": 55700, "total_steps": 58920, "loss": 0.0, "lr": 1.815191421299689e-08, "epoch": 4.726748133061779, "percentage": 94.53, "elapsed_time": "1:27:15", "remaining_time": "0:05:02", "throughput": 10214.59, "total_tokens": 53482176}
{"current_steps": 55705, "total_steps": 58920, "loss": 0.0, "lr": 1.809577350150493e-08, "epoch": 4.727172437202987, "percentage": 94.54, "elapsed_time": "1:27:16", "remaining_time": "0:05:02", "throughput": 10214.7, "total_tokens": 53486592}
{"current_steps": 55710, "total_steps": 58920, "loss": 0.0264, "lr": 1.8039718948563598e-08, "epoch": 4.727596741344195, "percentage": 94.55, "elapsed_time": "1:27:16", "remaining_time": "0:05:01", "throughput": 10214.85, "total_tokens": 53491264}
{"current_steps": 55715, "total_steps": 58920, "loss": 0.0, "lr": 1.7983750559091625e-08, "epoch": 4.728021045485404, "percentage": 94.56, "elapsed_time": "1:27:16", "remaining_time": "0:05:01", "throughput": 10214.98, "total_tokens": 53495744}
{"current_steps": 55720, "total_steps": 58920, "loss": 0.0, "lr": 1.7927868337999863e-08, "epoch": 4.728445349626613, "percentage": 94.57, "elapsed_time": "1:27:17", "remaining_time": "0:05:00", "throughput": 10215.14, "total_tokens": 53500480}
{"current_steps": 55725, "total_steps": 58920, "loss": 0.0342, "lr": 1.7872072290192164e-08, "epoch": 4.728869653767821, "percentage": 94.58, "elapsed_time": "1:27:17", "remaining_time": "0:05:00", "throughput": 10215.26, "total_tokens": 53504896}
{"current_steps": 55730, "total_steps": 58920, "loss": 0.0, "lr": 1.7816362420563947e-08, "epoch": 4.729293957909029, "percentage": 94.59, "elapsed_time": "1:27:18", "remaining_time": "0:04:59", "throughput": 10215.37, "total_tokens": 53509312}
{"current_steps": 55735, "total_steps": 58920, "loss": 0.0, "lr": 1.7760738734003854e-08, "epoch": 4.729718262050238, "percentage": 94.59, "elapsed_time": "1:27:18", "remaining_time": "0:04:59", "throughput": 10215.52, "total_tokens": 53513984}
{"current_steps": 55740, "total_steps": 58920, "loss": 0.0, "lr": 1.770520123539254e-08, "epoch": 4.7301425661914465, "percentage": 94.6, "elapsed_time": "1:27:18", "remaining_time": "0:04:58", "throughput": 10215.74, "total_tokens": 53519040}
{"current_steps": 55745, "total_steps": 58920, "loss": 0.0, "lr": 1.764974992960322e-08, "epoch": 4.730566870332654, "percentage": 94.61, "elapsed_time": "1:27:19", "remaining_time": "0:04:58", "throughput": 10215.84, "total_tokens": 53523392}
{"current_steps": 55750, "total_steps": 58920, "loss": 0.0, "lr": 1.7594384821501775e-08, "epoch": 4.730991174473862, "percentage": 94.62, "elapsed_time": "1:27:19", "remaining_time": "0:04:57", "throughput": 10216.06, "total_tokens": 53528512}
{"current_steps": 55755, "total_steps": 58920, "loss": 0.0, "lr": 1.7539105915945873e-08, "epoch": 4.731415478615071, "percentage": 94.63, "elapsed_time": "1:27:20", "remaining_time": "0:04:57", "throughput": 10216.19, "total_tokens": 53533056}
{"current_steps": 55760, "total_steps": 58920, "loss": 0.0, "lr": 1.7483913217786416e-08, "epoch": 4.73183978275628, "percentage": 94.64, "elapsed_time": "1:27:20", "remaining_time": "0:04:56", "throughput": 10216.38, "total_tokens": 53537984}
{"current_steps": 55765, "total_steps": 58920, "loss": 0.0, "lr": 1.7428806731866087e-08, "epoch": 4.732264086897488, "percentage": 94.65, "elapsed_time": "1:27:20", "remaining_time": "0:04:56", "throughput": 10216.52, "total_tokens": 53542528}
{"current_steps": 55770, "total_steps": 58920, "loss": 0.0, "lr": 1.7373786463020458e-08, "epoch": 4.732688391038696, "percentage": 94.65, "elapsed_time": "1:27:21", "remaining_time": "0:04:56", "throughput": 10216.77, "total_tokens": 53547904}
{"current_steps": 55775, "total_steps": 58920, "loss": 0.0, "lr": 1.7318852416077334e-08, "epoch": 4.733112695179905, "percentage": 94.66, "elapsed_time": "1:27:21", "remaining_time": "0:04:55", "throughput": 10216.95, "total_tokens": 53552768}
{"current_steps": 55780, "total_steps": 58920, "loss": 0.0, "lr": 1.7264004595856973e-08, "epoch": 4.733536999321114, "percentage": 94.67, "elapsed_time": "1:27:21", "remaining_time": "0:04:55", "throughput": 10217.09, "total_tokens": 53557312}
{"current_steps": 55785, "total_steps": 58920, "loss": 0.0, "lr": 1.720924300717208e-08, "epoch": 4.733961303462322, "percentage": 94.68, "elapsed_time": "1:27:22", "remaining_time": "0:04:54", "throughput": 10217.17, "total_tokens": 53561536}
{"current_steps": 55790, "total_steps": 58920, "loss": 0.0, "lr": 1.715456765482759e-08, "epoch": 4.73438560760353, "percentage": 94.69, "elapsed_time": "1:27:22", "remaining_time": "0:04:54", "throughput": 10217.3, "total_tokens": 53566016}
{"current_steps": 55795, "total_steps": 58920, "loss": 0.0, "lr": 1.709997854362144e-08, "epoch": 4.734809911744739, "percentage": 94.7, "elapsed_time": "1:27:23", "remaining_time": "0:04:53", "throughput": 10217.47, "total_tokens": 53570816}
{"current_steps": 55800, "total_steps": 58920, "loss": 0.0, "lr": 1.7045475678343246e-08, "epoch": 4.7352342158859475, "percentage": 94.7, "elapsed_time": "1:27:23", "remaining_time": "0:04:53", "throughput": 10217.76, "total_tokens": 53576448}
{"current_steps": 55805, "total_steps": 58920, "loss": 0.0, "lr": 1.6991059063775736e-08, "epoch": 4.7356585200271555, "percentage": 94.71, "elapsed_time": "1:27:23", "remaining_time": "0:04:52", "throughput": 10217.85, "total_tokens": 53580736}
{"current_steps": 55810, "total_steps": 58920, "loss": 0.0, "lr": 1.6936728704693647e-08, "epoch": 4.7360828241683635, "percentage": 94.72, "elapsed_time": "1:27:24", "remaining_time": "0:04:52", "throughput": 10218.03, "total_tokens": 53585664}
{"current_steps": 55815, "total_steps": 58920, "loss": 0.0, "lr": 1.6882484605864278e-08, "epoch": 4.736507128309572, "percentage": 94.73, "elapsed_time": "1:27:24", "remaining_time": "0:04:51", "throughput": 10218.28, "total_tokens": 53590976}
{"current_steps": 55820, "total_steps": 58920, "loss": 0.0, "lr": 1.6828326772047263e-08, "epoch": 4.736931432450781, "percentage": 94.74, "elapsed_time": "1:27:25", "remaining_time": "0:04:51", "throughput": 10218.46, "total_tokens": 53595904}
{"current_steps": 55825, "total_steps": 58920, "loss": 0.0, "lr": 1.6774255207994913e-08, "epoch": 4.737355736591989, "percentage": 94.75, "elapsed_time": "1:27:25", "remaining_time": "0:04:50", "throughput": 10218.61, "total_tokens": 53600512}
{"current_steps": 55830, "total_steps": 58920, "loss": 0.0, "lr": 1.6720269918451768e-08, "epoch": 4.737780040733197, "percentage": 94.76, "elapsed_time": "1:27:25", "remaining_time": "0:04:50", "throughput": 10218.74, "total_tokens": 53605056}
{"current_steps": 55835, "total_steps": 58920, "loss": 0.0, "lr": 1.6666370908154816e-08, "epoch": 4.738204344874406, "percentage": 94.76, "elapsed_time": "1:27:26", "remaining_time": "0:04:49", "throughput": 10218.91, "total_tokens": 53609856}
{"current_steps": 55840, "total_steps": 58920, "loss": 0.0, "lr": 1.6612558181833492e-08, "epoch": 4.738628649015615, "percentage": 94.77, "elapsed_time": "1:27:26", "remaining_time": "0:04:49", "throughput": 10219.08, "total_tokens": 53614656}
{"current_steps": 55845, "total_steps": 58920, "loss": 0.0, "lr": 1.655883174420969e-08, "epoch": 4.739052953156823, "percentage": 94.78, "elapsed_time": "1:27:26", "remaining_time": "0:04:48", "throughput": 10219.39, "total_tokens": 53620480}
{"current_steps": 55850, "total_steps": 58920, "loss": 0.0, "lr": 1.6505191599997746e-08, "epoch": 4.739477257298031, "percentage": 94.79, "elapsed_time": "1:27:27", "remaining_time": "0:04:48", "throughput": 10219.59, "total_tokens": 53625408}
{"current_steps": 55855, "total_steps": 58920, "loss": 0.0, "lr": 1.6451637753904236e-08, "epoch": 4.73990156143924, "percentage": 94.8, "elapsed_time": "1:27:27", "remaining_time": "0:04:47", "throughput": 10219.67, "total_tokens": 53629632}
{"current_steps": 55860, "total_steps": 58920, "loss": 0.0, "lr": 1.6398170210628504e-08, "epoch": 4.7403258655804485, "percentage": 94.81, "elapsed_time": "1:27:28", "remaining_time": "0:04:47", "throughput": 10219.88, "total_tokens": 53634688}
{"current_steps": 55865, "total_steps": 58920, "loss": 0.0, "lr": 1.634478897486202e-08, "epoch": 4.7407501697216565, "percentage": 94.82, "elapsed_time": "1:27:28", "remaining_time": "0:04:47", "throughput": 10219.98, "total_tokens": 53639040}
{"current_steps": 55870, "total_steps": 58920, "loss": 0.0, "lr": 1.6291494051288936e-08, "epoch": 4.7411744738628645, "percentage": 94.82, "elapsed_time": "1:27:28", "remaining_time": "0:04:46", "throughput": 10220.26, "total_tokens": 53644608}
{"current_steps": 55875, "total_steps": 58920, "loss": 0.0, "lr": 1.6238285444585496e-08, "epoch": 4.741598778004073, "percentage": 94.83, "elapsed_time": "1:27:29", "remaining_time": "0:04:46", "throughput": 10220.41, "total_tokens": 53649216}
{"current_steps": 55880, "total_steps": 58920, "loss": 0.0, "lr": 1.6185163159420645e-08, "epoch": 4.742023082145282, "percentage": 94.84, "elapsed_time": "1:27:29", "remaining_time": "0:04:45", "throughput": 10220.55, "total_tokens": 53653888}
{"current_steps": 55885, "total_steps": 58920, "loss": 0.0322, "lr": 1.6132127200455647e-08, "epoch": 4.74244738628649, "percentage": 94.85, "elapsed_time": "1:27:29", "remaining_time": "0:04:45", "throughput": 10220.65, "total_tokens": 53658176}
{"current_steps": 55890, "total_steps": 58920, "loss": 0.0, "lr": 1.6079177572344227e-08, "epoch": 4.742871690427698, "percentage": 94.86, "elapsed_time": "1:27:30", "remaining_time": "0:04:44", "throughput": 10220.83, "total_tokens": 53663040}
{"current_steps": 55895, "total_steps": 58920, "loss": 0.0, "lr": 1.6026314279732665e-08, "epoch": 4.743295994568907, "percentage": 94.87, "elapsed_time": "1:27:30", "remaining_time": "0:04:44", "throughput": 10221.13, "total_tokens": 53668736}
{"current_steps": 55900, "total_steps": 58920, "loss": 0.0, "lr": 1.5973537327259255e-08, "epoch": 4.743720298710115, "percentage": 94.87, "elapsed_time": "1:27:31", "remaining_time": "0:04:43", "throughput": 10221.27, "total_tokens": 53673344}
{"current_steps": 55905, "total_steps": 58920, "loss": 0.0, "lr": 1.592084671955529e-08, "epoch": 4.744144602851324, "percentage": 94.88, "elapsed_time": "1:27:31", "remaining_time": "0:04:43", "throughput": 10221.5, "total_tokens": 53678528}
{"current_steps": 55910, "total_steps": 58920, "loss": 0.0, "lr": 1.5868242461243964e-08, "epoch": 4.744568906992532, "percentage": 94.89, "elapsed_time": "1:27:31", "remaining_time": "0:04:42", "throughput": 10221.82, "total_tokens": 53684352}
{"current_steps": 55915, "total_steps": 58920, "loss": 0.0, "lr": 1.5815724556941135e-08, "epoch": 4.744993211133741, "percentage": 94.9, "elapsed_time": "1:27:32", "remaining_time": "0:04:42", "throughput": 10222.07, "total_tokens": 53689728}
{"current_steps": 55920, "total_steps": 58920, "loss": 0.0, "lr": 1.576329301125512e-08, "epoch": 4.745417515274949, "percentage": 94.91, "elapsed_time": "1:27:32", "remaining_time": "0:04:41", "throughput": 10222.29, "total_tokens": 53694912}
{"current_steps": 55925, "total_steps": 58920, "loss": 0.0, "lr": 1.5710947828786568e-08, "epoch": 4.745841819416158, "percentage": 94.92, "elapsed_time": "1:27:33", "remaining_time": "0:04:41", "throughput": 10222.46, "total_tokens": 53699712}
{"current_steps": 55930, "total_steps": 58920, "loss": 0.0, "lr": 1.5658689014128478e-08, "epoch": 4.7462661235573655, "percentage": 94.93, "elapsed_time": "1:27:33", "remaining_time": "0:04:40", "throughput": 10222.61, "total_tokens": 53704384}
{"current_steps": 55935, "total_steps": 58920, "loss": 0.0, "lr": 1.5606516571866512e-08, "epoch": 4.746690427698574, "percentage": 94.93, "elapsed_time": "1:27:33", "remaining_time": "0:04:40", "throughput": 10222.73, "total_tokens": 53708864}
{"current_steps": 55940, "total_steps": 58920, "loss": 0.0, "lr": 1.5554430506578787e-08, "epoch": 4.747114731839782, "percentage": 94.94, "elapsed_time": "1:27:34", "remaining_time": "0:04:39", "throughput": 10223.04, "total_tokens": 53714624}
{"current_steps": 55945, "total_steps": 58920, "loss": 0.0, "lr": 1.5502430822835198e-08, "epoch": 4.747539035980991, "percentage": 94.95, "elapsed_time": "1:27:34", "remaining_time": "0:04:39", "throughput": 10223.23, "total_tokens": 53719552}
{"current_steps": 55950, "total_steps": 58920, "loss": 0.0, "lr": 1.5450517525198993e-08, "epoch": 4.747963340122199, "percentage": 94.96, "elapsed_time": "1:27:35", "remaining_time": "0:04:38", "throughput": 10223.39, "total_tokens": 53724288}
{"current_steps": 55955, "total_steps": 58920, "loss": 0.0, "lr": 1.5398690618225074e-08, "epoch": 4.748387644263408, "percentage": 94.97, "elapsed_time": "1:27:35", "remaining_time": "0:04:38", "throughput": 10223.52, "total_tokens": 53728832}
{"current_steps": 55960, "total_steps": 58920, "loss": 0.0, "lr": 1.5346950106461032e-08, "epoch": 4.748811948404616, "percentage": 94.98, "elapsed_time": "1:27:35", "remaining_time": "0:04:38", "throughput": 10223.64, "total_tokens": 53733248}
{"current_steps": 55965, "total_steps": 58920, "loss": 0.0, "lr": 1.5295295994447233e-08, "epoch": 4.749236252545825, "percentage": 94.98, "elapsed_time": "1:27:36", "remaining_time": "0:04:37", "throughput": 10223.78, "total_tokens": 53737856}
{"current_steps": 55970, "total_steps": 58920, "loss": 0.0, "lr": 1.524372828671583e-08, "epoch": 4.749660556687033, "percentage": 94.99, "elapsed_time": "1:27:36", "remaining_time": "0:04:37", "throughput": 10223.97, "total_tokens": 53742784}
{"current_steps": 55974, "total_steps": 58920, "eval_loss": 0.17533057928085327, "epoch": 4.75, "percentage": 95.0, "elapsed_time": "1:27:53", "remaining_time": "0:04:37", "throughput": 10192.32, "total_tokens": 53746240}
{"current_steps": 55975, "total_steps": 58920, "loss": 0.0, "lr": 1.519224698779198e-08, "epoch": 4.750084860828242, "percentage": 95.0, "elapsed_time": "1:28:28", "remaining_time": "0:04:39", "throughput": 10124.04, "total_tokens": 53747072}
{"current_steps": 55980, "total_steps": 58920, "loss": 0.0, "lr": 1.5140852102192625e-08, "epoch": 4.75050916496945, "percentage": 95.01, "elapsed_time": "1:28:29", "remaining_time": "0:04:38", "throughput": 10124.11, "total_tokens": 53751232}
{"current_steps": 55985, "total_steps": 58920, "loss": 0.0, "lr": 1.5089543634427824e-08, "epoch": 4.750933469110659, "percentage": 95.02, "elapsed_time": "1:28:29", "remaining_time": "0:04:38", "throughput": 10124.39, "total_tokens": 53756736}
{"current_steps": 55990, "total_steps": 58920, "loss": 0.0, "lr": 1.5038321588999535e-08, "epoch": 4.751357773251867, "percentage": 95.03, "elapsed_time": "1:28:30", "remaining_time": "0:04:37", "throughput": 10124.6, "total_tokens": 53761856}
{"current_steps": 55995, "total_steps": 58920, "loss": 0.0, "lr": 1.498718597040227e-08, "epoch": 4.7517820773930755, "percentage": 95.04, "elapsed_time": "1:28:30", "remaining_time": "0:04:37", "throughput": 10124.81, "total_tokens": 53766848}
{"current_steps": 56000, "total_steps": 58920, "loss": 0.0, "lr": 1.4936136783123222e-08, "epoch": 4.752206381534283, "percentage": 95.04, "elapsed_time": "1:28:30", "remaining_time": "0:04:36", "throughput": 10124.94, "total_tokens": 53771392}
{"current_steps": 56005, "total_steps": 58920, "loss": 0.0, "lr": 1.4885174031641468e-08, "epoch": 4.752630685675492, "percentage": 95.05, "elapsed_time": "1:28:31", "remaining_time": "0:04:36", "throughput": 10125.07, "total_tokens": 53775872}
{"current_steps": 56010, "total_steps": 58920, "loss": 0.0, "lr": 1.4834297720429101e-08, "epoch": 4.7530549898167, "percentage": 95.06, "elapsed_time": "1:28:31", "remaining_time": "0:04:35", "throughput": 10125.32, "total_tokens": 53781184}
{"current_steps": 56015, "total_steps": 58920, "loss": 0.0, "lr": 1.4783507853949883e-08, "epoch": 4.753479293957909, "percentage": 95.07, "elapsed_time": "1:28:31", "remaining_time": "0:04:35", "throughput": 10125.53, "total_tokens": 53786240}
{"current_steps": 56020, "total_steps": 58920, "loss": 0.0, "lr": 1.4732804436661028e-08, "epoch": 4.753903598099117, "percentage": 95.08, "elapsed_time": "1:28:32", "remaining_time": "0:04:35", "throughput": 10125.68, "total_tokens": 53790848}
{"current_steps": 56025, "total_steps": 58920, "loss": 0.0, "lr": 1.4682187473011198e-08, "epoch": 4.754327902240326, "percentage": 95.09, "elapsed_time": "1:28:32", "remaining_time": "0:04:34", "throughput": 10125.97, "total_tokens": 53796480}
{"current_steps": 56030, "total_steps": 58920, "loss": 0.0, "lr": 1.4631656967441842e-08, "epoch": 4.754752206381534, "percentage": 95.1, "elapsed_time": "1:28:33", "remaining_time": "0:04:34", "throughput": 10126.17, "total_tokens": 53801472}
{"current_steps": 56035, "total_steps": 58920, "loss": 0.0, "lr": 1.4581212924387076e-08, "epoch": 4.755176510522743, "percentage": 95.1, "elapsed_time": "1:28:33", "remaining_time": "0:04:33", "throughput": 10126.29, "total_tokens": 53805952}
{"current_steps": 56040, "total_steps": 58920, "loss": 0.0, "lr": 1.4530855348272919e-08, "epoch": 4.755600814663951, "percentage": 95.11, "elapsed_time": "1:28:33", "remaining_time": "0:04:33", "throughput": 10126.51, "total_tokens": 53811008}
{"current_steps": 56045, "total_steps": 58920, "loss": 0.0, "lr": 1.4480584243518279e-08, "epoch": 4.75602511880516, "percentage": 95.12, "elapsed_time": "1:28:34", "remaining_time": "0:04:32", "throughput": 10126.74, "total_tokens": 53816128}
{"current_steps": 56050, "total_steps": 58920, "loss": 0.0, "lr": 1.4430399614534183e-08, "epoch": 4.756449422946368, "percentage": 95.13, "elapsed_time": "1:28:34", "remaining_time": "0:04:32", "throughput": 10126.91, "total_tokens": 53820992}
{"current_steps": 56055, "total_steps": 58920, "loss": 0.0, "lr": 1.4380301465723998e-08, "epoch": 4.7568737270875765, "percentage": 95.14, "elapsed_time": "1:28:35", "remaining_time": "0:04:31", "throughput": 10127.07, "total_tokens": 53825664}
{"current_steps": 56060, "total_steps": 58920, "loss": 0.0, "lr": 1.4330289801483874e-08, "epoch": 4.7572980312287845, "percentage": 95.15, "elapsed_time": "1:28:35", "remaining_time": "0:04:31", "throughput": 10127.26, "total_tokens": 53830528}
{"current_steps": 56065, "total_steps": 58920, "loss": 0.0005, "lr": 1.4280364626202079e-08, "epoch": 4.757722335369993, "percentage": 95.15, "elapsed_time": "1:28:35", "remaining_time": "0:04:30", "throughput": 10127.44, "total_tokens": 53835328}
{"current_steps": 56070, "total_steps": 58920, "loss": 0.0, "lr": 1.4230525944259441e-08, "epoch": 4.758146639511201, "percentage": 95.16, "elapsed_time": "1:28:36", "remaining_time": "0:04:30", "throughput": 10127.51, "total_tokens": 53839424}
{"current_steps": 56075, "total_steps": 58920, "loss": 0.0, "lr": 1.4180773760028908e-08, "epoch": 4.75857094365241, "percentage": 95.17, "elapsed_time": "1:28:36", "remaining_time": "0:04:29", "throughput": 10127.68, "total_tokens": 53844224}
{"current_steps": 56080, "total_steps": 58920, "loss": 0.0, "lr": 1.4131108077876319e-08, "epoch": 4.758995247793618, "percentage": 95.18, "elapsed_time": "1:28:36", "remaining_time": "0:04:29", "throughput": 10127.71, "total_tokens": 53848128}
{"current_steps": 56085, "total_steps": 58920, "loss": 0.0, "lr": 1.4081528902159412e-08, "epoch": 4.759419551934827, "percentage": 95.19, "elapsed_time": "1:28:37", "remaining_time": "0:04:28", "throughput": 10127.91, "total_tokens": 53853120}
{"current_steps": 56090, "total_steps": 58920, "loss": 0.0, "lr": 1.4032036237228706e-08, "epoch": 4.759843856076035, "percentage": 95.2, "elapsed_time": "1:28:37", "remaining_time": "0:04:28", "throughput": 10128.12, "total_tokens": 53858176}
{"current_steps": 56095, "total_steps": 58920, "loss": 0.0, "lr": 1.3982630087427061e-08, "epoch": 4.760268160217244, "percentage": 95.21, "elapsed_time": "1:28:38", "remaining_time": "0:04:27", "throughput": 10128.25, "total_tokens": 53862720}
{"current_steps": 56100, "total_steps": 58920, "loss": 0.0, "lr": 1.3933310457089676e-08, "epoch": 4.760692464358452, "percentage": 95.21, "elapsed_time": "1:28:38", "remaining_time": "0:04:27", "throughput": 10128.45, "total_tokens": 53867712}
{"current_steps": 56105, "total_steps": 58920, "loss": 0.0, "lr": 1.3884077350543977e-08, "epoch": 4.761116768499661, "percentage": 95.22, "elapsed_time": "1:28:38", "remaining_time": "0:04:26", "throughput": 10128.57, "total_tokens": 53872128}
{"current_steps": 56110, "total_steps": 58920, "loss": 0.0, "lr": 1.3834930772110175e-08, "epoch": 4.761541072640869, "percentage": 95.23, "elapsed_time": "1:28:39", "remaining_time": "0:04:26", "throughput": 10128.73, "total_tokens": 53876800}
{"current_steps": 56115, "total_steps": 58920, "loss": 0.0, "lr": 1.3785870726100712e-08, "epoch": 4.7619653767820775, "percentage": 95.24, "elapsed_time": "1:28:39", "remaining_time": "0:04:25", "throughput": 10128.92, "total_tokens": 53881728}
{"current_steps": 56120, "total_steps": 58920, "loss": 0.0, "lr": 1.3736897216820365e-08, "epoch": 4.7623896809232855, "percentage": 95.25, "elapsed_time": "1:28:39", "remaining_time": "0:04:25", "throughput": 10129.01, "total_tokens": 53886016}
{"current_steps": 56125, "total_steps": 58920, "loss": 0.0, "lr": 1.3688010248566361e-08, "epoch": 4.762813985064494, "percentage": 95.26, "elapsed_time": "1:28:40", "remaining_time": "0:04:24", "throughput": 10129.19, "total_tokens": 53890880}
{"current_steps": 56130, "total_steps": 58920, "loss": 0.0, "lr": 1.3639209825628495e-08, "epoch": 4.763238289205702, "percentage": 95.26, "elapsed_time": "1:28:40", "remaining_time": "0:04:24", "throughput": 10129.35, "total_tokens": 53895552}
{"current_steps": 56135, "total_steps": 58920, "loss": 0.0, "lr": 1.3590495952288671e-08, "epoch": 4.763662593346911, "percentage": 95.27, "elapsed_time": "1:28:41", "remaining_time": "0:04:23", "throughput": 10129.52, "total_tokens": 53900352}
{"current_steps": 56140, "total_steps": 58920, "loss": 0.0, "lr": 1.3541868632821363e-08, "epoch": 4.764086897488119, "percentage": 95.28, "elapsed_time": "1:28:41", "remaining_time": "0:04:23", "throughput": 10129.73, "total_tokens": 53905408}
{"current_steps": 56145, "total_steps": 58920, "loss": 0.0, "lr": 1.3493327871493487e-08, "epoch": 4.764511201629328, "percentage": 95.29, "elapsed_time": "1:28:41", "remaining_time": "0:04:23", "throughput": 10129.88, "total_tokens": 53910080}
{"current_steps": 56150, "total_steps": 58920, "loss": 0.0, "lr": 1.3444873672564305e-08, "epoch": 4.764935505770536, "percentage": 95.3, "elapsed_time": "1:28:42", "remaining_time": "0:04:22", "throughput": 10129.99, "total_tokens": 53914496}
{"current_steps": 56155, "total_steps": 58920, "loss": 0.0, "lr": 1.3396506040285639e-08, "epoch": 4.765359809911745, "percentage": 95.31, "elapsed_time": "1:28:42", "remaining_time": "0:04:22", "throughput": 10130.22, "total_tokens": 53919744}
{"current_steps": 56160, "total_steps": 58920, "loss": 0.0, "lr": 1.3348224978901313e-08, "epoch": 4.765784114052953, "percentage": 95.32, "elapsed_time": "1:28:43", "remaining_time": "0:04:21", "throughput": 10130.44, "total_tokens": 53924864}
{"current_steps": 56165, "total_steps": 58920, "loss": 0.0, "lr": 1.3300030492648052e-08, "epoch": 4.766208418194162, "percentage": 95.32, "elapsed_time": "1:28:43", "remaining_time": "0:04:21", "throughput": 10130.6, "total_tokens": 53929664}
{"current_steps": 56170, "total_steps": 58920, "loss": 0.0, "lr": 1.3251922585754693e-08, "epoch": 4.76663272233537, "percentage": 95.33, "elapsed_time": "1:28:43", "remaining_time": "0:04:20", "throughput": 10130.78, "total_tokens": 53934528}
{"current_steps": 56175, "total_steps": 58920, "loss": 0.0, "lr": 1.3203901262442308e-08, "epoch": 4.767057026476579, "percentage": 95.34, "elapsed_time": "1:28:44", "remaining_time": "0:04:20", "throughput": 10130.89, "total_tokens": 53938880}
{"current_steps": 56180, "total_steps": 58920, "loss": 0.0, "lr": 1.3155966526924967e-08, "epoch": 4.767481330617787, "percentage": 95.35, "elapsed_time": "1:28:44", "remaining_time": "0:04:19", "throughput": 10130.98, "total_tokens": 53943168}
{"current_steps": 56185, "total_steps": 58920, "loss": 0.0, "lr": 1.3108118383408418e-08, "epoch": 4.767905634758995, "percentage": 95.36, "elapsed_time": "1:28:44", "remaining_time": "0:04:19", "throughput": 10131.26, "total_tokens": 53948736}
{"current_steps": 56190, "total_steps": 58920, "loss": 0.0, "lr": 1.3060356836091413e-08, "epoch": 4.768329938900203, "percentage": 95.37, "elapsed_time": "1:28:45", "remaining_time": "0:04:18", "throughput": 10131.38, "total_tokens": 53953152}
{"current_steps": 56195, "total_steps": 58920, "loss": 0.0, "lr": 1.3012681889164711e-08, "epoch": 4.768754243041412, "percentage": 95.38, "elapsed_time": "1:28:45", "remaining_time": "0:04:18", "throughput": 10131.61, "total_tokens": 53958400}
{"current_steps": 56200, "total_steps": 58920, "loss": 0.0, "lr": 1.2965093546811634e-08, "epoch": 4.76917854718262, "percentage": 95.38, "elapsed_time": "1:28:46", "remaining_time": "0:04:17", "throughput": 10131.71, "total_tokens": 53962752}
{"current_steps": 56205, "total_steps": 58920, "loss": 0.0, "lr": 1.2917591813208062e-08, "epoch": 4.769602851323829, "percentage": 95.39, "elapsed_time": "1:28:46", "remaining_time": "0:04:17", "throughput": 10131.82, "total_tokens": 53967168}
{"current_steps": 56210, "total_steps": 58920, "loss": 0.0, "lr": 1.2870176692521773e-08, "epoch": 4.770027155465037, "percentage": 95.4, "elapsed_time": "1:28:46", "remaining_time": "0:04:16", "throughput": 10132.02, "total_tokens": 53972160}
{"current_steps": 56215, "total_steps": 58920, "loss": 0.0, "lr": 1.282284818891366e-08, "epoch": 4.770451459606246, "percentage": 95.41, "elapsed_time": "1:28:47", "remaining_time": "0:04:16", "throughput": 10132.23, "total_tokens": 53977216}
{"current_steps": 56220, "total_steps": 58920, "loss": 0.0, "lr": 1.277560630653629e-08, "epoch": 4.770875763747454, "percentage": 95.42, "elapsed_time": "1:28:47", "remaining_time": "0:04:15", "throughput": 10132.34, "total_tokens": 53981696}
{"current_steps": 56225, "total_steps": 58920, "loss": 0.0, "lr": 1.2728451049535238e-08, "epoch": 4.771300067888663, "percentage": 95.43, "elapsed_time": "1:28:48", "remaining_time": "0:04:15", "throughput": 10132.47, "total_tokens": 53986176}
{"current_steps": 56230, "total_steps": 58920, "loss": 0.0, "lr": 1.268138242204797e-08, "epoch": 4.771724372029871, "percentage": 95.43, "elapsed_time": "1:28:48", "remaining_time": "0:04:14", "throughput": 10132.63, "total_tokens": 53990912}
{"current_steps": 56235, "total_steps": 58920, "loss": 0.0, "lr": 1.2634400428204739e-08, "epoch": 4.77214867617108, "percentage": 95.44, "elapsed_time": "1:28:48", "remaining_time": "0:04:14", "throughput": 10132.77, "total_tokens": 53995520}
{"current_steps": 56240, "total_steps": 58920, "loss": 0.0, "lr": 1.2587505072127914e-08, "epoch": 4.772572980312288, "percentage": 95.45, "elapsed_time": "1:28:49", "remaining_time": "0:04:13", "throughput": 10132.89, "total_tokens": 54000064}
{"current_steps": 56245, "total_steps": 58920, "loss": 0.0, "lr": 1.2540696357932534e-08, "epoch": 4.7729972844534965, "percentage": 95.46, "elapsed_time": "1:28:49", "remaining_time": "0:04:13", "throughput": 10133.01, "total_tokens": 54004480}
{"current_steps": 56250, "total_steps": 58920, "loss": 0.0, "lr": 1.2493974289725984e-08, "epoch": 4.7734215885947044, "percentage": 95.47, "elapsed_time": "1:28:49", "remaining_time": "0:04:12", "throughput": 10133.14, "total_tokens": 54009088}
{"current_steps": 56255, "total_steps": 58920, "loss": 0.0, "lr": 1.2447338871607649e-08, "epoch": 4.773845892735913, "percentage": 95.48, "elapsed_time": "1:28:50", "remaining_time": "0:04:12", "throughput": 10133.43, "total_tokens": 54014656}
{"current_steps": 56260, "total_steps": 58920, "loss": 0.0, "lr": 1.2400790107669811e-08, "epoch": 4.774270196877121, "percentage": 95.49, "elapsed_time": "1:28:50", "remaining_time": "0:04:12", "throughput": 10133.55, "total_tokens": 54019136}
{"current_steps": 56265, "total_steps": 58920, "loss": 0.0, "lr": 1.2354328001996872e-08, "epoch": 4.77469450101833, "percentage": 95.49, "elapsed_time": "1:28:51", "remaining_time": "0:04:11", "throughput": 10133.72, "total_tokens": 54023936}
{"current_steps": 56270, "total_steps": 58920, "loss": 0.0, "lr": 1.2307952558665902e-08, "epoch": 4.775118805159538, "percentage": 95.5, "elapsed_time": "1:28:51", "remaining_time": "0:04:11", "throughput": 10133.85, "total_tokens": 54028480}
{"current_steps": 56275, "total_steps": 58920, "loss": 0.0, "lr": 1.226166378174598e-08, "epoch": 4.775543109300747, "percentage": 95.51, "elapsed_time": "1:28:51", "remaining_time": "0:04:10", "throughput": 10134.01, "total_tokens": 54033152}
{"current_steps": 56280, "total_steps": 58920, "loss": 0.0, "lr": 1.2215461675298855e-08, "epoch": 4.775967413441955, "percentage": 95.52, "elapsed_time": "1:28:52", "remaining_time": "0:04:10", "throughput": 10134.12, "total_tokens": 54037568}
{"current_steps": 56285, "total_steps": 58920, "loss": 0.0, "lr": 1.2169346243378509e-08, "epoch": 4.776391717583164, "percentage": 95.53, "elapsed_time": "1:28:52", "remaining_time": "0:04:09", "throughput": 10134.27, "total_tokens": 54042240}
{"current_steps": 56290, "total_steps": 58920, "loss": 0.0, "lr": 1.2123317490031593e-08, "epoch": 4.776816021724372, "percentage": 95.54, "elapsed_time": "1:28:53", "remaining_time": "0:04:09", "throughput": 10134.43, "total_tokens": 54046976}
{"current_steps": 56295, "total_steps": 58920, "loss": 0.0, "lr": 1.2077375419296764e-08, "epoch": 4.777240325865581, "percentage": 95.54, "elapsed_time": "1:28:53", "remaining_time": "0:04:08", "throughput": 10134.54, "total_tokens": 54051392}
{"current_steps": 56300, "total_steps": 58920, "loss": 0.0, "lr": 1.2031520035205468e-08, "epoch": 4.777664630006789, "percentage": 95.55, "elapsed_time": "1:28:53", "remaining_time": "0:04:08", "throughput": 10134.71, "total_tokens": 54056320}
{"current_steps": 56305, "total_steps": 58920, "loss": 0.0, "lr": 1.1985751341781147e-08, "epoch": 4.7780889341479975, "percentage": 95.56, "elapsed_time": "1:28:54", "remaining_time": "0:04:07", "throughput": 10134.81, "total_tokens": 54060608}
{"current_steps": 56310, "total_steps": 58920, "loss": 0.0, "lr": 1.1940069343040037e-08, "epoch": 4.7785132382892055, "percentage": 95.57, "elapsed_time": "1:28:54", "remaining_time": "0:04:07", "throughput": 10134.97, "total_tokens": 54065344}
{"current_steps": 56315, "total_steps": 58920, "loss": 0.0, "lr": 1.1894474042990377e-08, "epoch": 4.778937542430414, "percentage": 95.58, "elapsed_time": "1:28:54", "remaining_time": "0:04:06", "throughput": 10135.17, "total_tokens": 54070400}
{"current_steps": 56320, "total_steps": 58920, "loss": 0.0, "lr": 1.1848965445633074e-08, "epoch": 4.779361846571622, "percentage": 95.59, "elapsed_time": "1:28:55", "remaining_time": "0:04:06", "throughput": 10135.3, "total_tokens": 54074944}
{"current_steps": 56325, "total_steps": 58920, "loss": 0.0, "lr": 1.1803543554961382e-08, "epoch": 4.779786150712831, "percentage": 95.6, "elapsed_time": "1:28:55", "remaining_time": "0:04:05", "throughput": 10135.46, "total_tokens": 54079744}
{"current_steps": 56330, "total_steps": 58920, "loss": 0.0, "lr": 1.1758208374960888e-08, "epoch": 4.780210454854039, "percentage": 95.6, "elapsed_time": "1:28:56", "remaining_time": "0:04:05", "throughput": 10135.63, "total_tokens": 54084544}
{"current_steps": 56335, "total_steps": 58920, "loss": 0.0, "lr": 1.1712959909609522e-08, "epoch": 4.780634758995248, "percentage": 95.61, "elapsed_time": "1:28:56", "remaining_time": "0:04:04", "throughput": 10135.75, "total_tokens": 54088960}
{"current_steps": 56340, "total_steps": 58920, "loss": 0.0, "lr": 1.1667798162877773e-08, "epoch": 4.781059063136456, "percentage": 95.62, "elapsed_time": "1:28:56", "remaining_time": "0:04:04", "throughput": 10136.03, "total_tokens": 54094464}
{"current_steps": 56345, "total_steps": 58920, "loss": 0.0, "lr": 1.1622723138728363e-08, "epoch": 4.781483367277665, "percentage": 95.63, "elapsed_time": "1:28:57", "remaining_time": "0:04:03", "throughput": 10136.31, "total_tokens": 54100096}
{"current_steps": 56350, "total_steps": 58920, "loss": 0.0, "lr": 1.157773484111646e-08, "epoch": 4.781907671418873, "percentage": 95.64, "elapsed_time": "1:28:57", "remaining_time": "0:04:03", "throughput": 10136.48, "total_tokens": 54104896}
{"current_steps": 56355, "total_steps": 58920, "loss": 0.0, "lr": 1.1532833273989684e-08, "epoch": 4.782331975560082, "percentage": 95.65, "elapsed_time": "1:28:58", "remaining_time": "0:04:02", "throughput": 10136.64, "total_tokens": 54109632}
{"current_steps": 56360, "total_steps": 58920, "loss": 0.0, "lr": 1.1488018441287884e-08, "epoch": 4.78275627970129, "percentage": 95.66, "elapsed_time": "1:28:58", "remaining_time": "0:04:02", "throughput": 10136.81, "total_tokens": 54114432}
{"current_steps": 56365, "total_steps": 58920, "loss": 0.0, "lr": 1.1443290346943468e-08, "epoch": 4.783180583842499, "percentage": 95.66, "elapsed_time": "1:28:58", "remaining_time": "0:04:02", "throughput": 10137.01, "total_tokens": 54119488}
{"current_steps": 56370, "total_steps": 58920, "loss": 0.0, "lr": 1.1398648994881189e-08, "epoch": 4.7836048879837065, "percentage": 95.67, "elapsed_time": "1:28:59", "remaining_time": "0:04:01", "throughput": 10137.23, "total_tokens": 54124608}
{"current_steps": 56375, "total_steps": 58920, "loss": 0.0, "lr": 1.1354094389018132e-08, "epoch": 4.784029192124915, "percentage": 95.68, "elapsed_time": "1:28:59", "remaining_time": "0:04:01", "throughput": 10137.35, "total_tokens": 54129088}
{"current_steps": 56380, "total_steps": 58920, "loss": 0.0, "lr": 1.130962653326384e-08, "epoch": 4.784453496266123, "percentage": 95.69, "elapsed_time": "1:28:59", "remaining_time": "0:04:00", "throughput": 10137.47, "total_tokens": 54133504}
{"current_steps": 56385, "total_steps": 58920, "loss": 0.0, "lr": 1.1265245431520077e-08, "epoch": 4.784877800407332, "percentage": 95.7, "elapsed_time": "1:29:00", "remaining_time": "0:04:00", "throughput": 10137.68, "total_tokens": 54138560}
{"current_steps": 56390, "total_steps": 58920, "loss": 0.0, "lr": 1.1220951087681174e-08, "epoch": 4.78530210454854, "percentage": 95.71, "elapsed_time": "1:29:00", "remaining_time": "0:03:59", "throughput": 10137.84, "total_tokens": 54143296}
{"current_steps": 56395, "total_steps": 58920, "loss": 0.0, "lr": 1.1176743505634024e-08, "epoch": 4.785726408689749, "percentage": 95.71, "elapsed_time": "1:29:01", "remaining_time": "0:03:59", "throughput": 10138.04, "total_tokens": 54148288}
{"current_steps": 56400, "total_steps": 58920, "loss": 0.0, "lr": 1.1132622689257298e-08, "epoch": 4.786150712830957, "percentage": 95.72, "elapsed_time": "1:29:01", "remaining_time": "0:03:58", "throughput": 10138.23, "total_tokens": 54153216}
{"current_steps": 56405, "total_steps": 58920, "loss": 0.0, "lr": 1.1088588642422792e-08, "epoch": 4.786575016972166, "percentage": 95.73, "elapsed_time": "1:29:01", "remaining_time": "0:03:58", "throughput": 10138.47, "total_tokens": 54158464}
{"current_steps": 56410, "total_steps": 58920, "loss": 0.0, "lr": 1.1044641368994078e-08, "epoch": 4.786999321113374, "percentage": 95.74, "elapsed_time": "1:29:02", "remaining_time": "0:03:57", "throughput": 10138.61, "total_tokens": 54163008}
{"current_steps": 56415, "total_steps": 58920, "loss": 0.0, "lr": 1.100078087282752e-08, "epoch": 4.787423625254583, "percentage": 95.75, "elapsed_time": "1:29:02", "remaining_time": "0:03:57", "throughput": 10138.78, "total_tokens": 54167808}
{"current_steps": 56420, "total_steps": 58920, "loss": 0.0, "lr": 1.0957007157771703e-08, "epoch": 4.787847929395791, "percentage": 95.76, "elapsed_time": "1:29:03", "remaining_time": "0:03:56", "throughput": 10138.97, "total_tokens": 54172800}
{"current_steps": 56425, "total_steps": 58920, "loss": 0.0, "lr": 1.0913320227667555e-08, "epoch": 4.788272233537, "percentage": 95.77, "elapsed_time": "1:29:03", "remaining_time": "0:03:56", "throughput": 10139.05, "total_tokens": 54177024}
{"current_steps": 56430, "total_steps": 58920, "loss": 0.0, "lr": 1.0869720086348455e-08, "epoch": 4.788696537678208, "percentage": 95.77, "elapsed_time": "1:29:03", "remaining_time": "0:03:55", "throughput": 10139.28, "total_tokens": 54182272}
{"current_steps": 56435, "total_steps": 58920, "loss": 0.0, "lr": 1.082620673764023e-08, "epoch": 4.789120841819416, "percentage": 95.78, "elapsed_time": "1:29:04", "remaining_time": "0:03:55", "throughput": 10139.38, "total_tokens": 54186688}
{"current_steps": 56440, "total_steps": 58920, "loss": 0.0, "lr": 1.078278018536094e-08, "epoch": 4.789545145960624, "percentage": 95.79, "elapsed_time": "1:29:04", "remaining_time": "0:03:54", "throughput": 10139.62, "total_tokens": 54192000}
{"current_steps": 56445, "total_steps": 58920, "loss": 0.0, "lr": 1.0739440433321089e-08, "epoch": 4.789969450101833, "percentage": 95.8, "elapsed_time": "1:29:04", "remaining_time": "0:03:54", "throughput": 10139.74, "total_tokens": 54196480}
{"current_steps": 56450, "total_steps": 58920, "loss": 0.0, "lr": 1.0696187485323638e-08, "epoch": 4.790393754243041, "percentage": 95.81, "elapsed_time": "1:29:05", "remaining_time": "0:03:53", "throughput": 10139.9, "total_tokens": 54201280}
{"current_steps": 56455, "total_steps": 58920, "loss": 0.0, "lr": 1.0653021345163993e-08, "epoch": 4.79081805838425, "percentage": 95.82, "elapsed_time": "1:29:05", "remaining_time": "0:03:53", "throughput": 10140.03, "total_tokens": 54205824}
{"current_steps": 56460, "total_steps": 58920, "loss": 0.0, "lr": 1.0609942016629459e-08, "epoch": 4.791242362525458, "percentage": 95.82, "elapsed_time": "1:29:06", "remaining_time": "0:03:52", "throughput": 10140.17, "total_tokens": 54210496}
{"current_steps": 56465, "total_steps": 58920, "loss": 0.0, "lr": 1.0566949503500566e-08, "epoch": 4.791666666666667, "percentage": 95.83, "elapsed_time": "1:29:06", "remaining_time": "0:03:52", "throughput": 10140.31, "total_tokens": 54215104}
{"current_steps": 56470, "total_steps": 58920, "loss": 0.0, "lr": 1.052404380954941e-08, "epoch": 4.792090970807875, "percentage": 95.84, "elapsed_time": "1:29:06", "remaining_time": "0:03:51", "throughput": 10140.53, "total_tokens": 54220288}
{"current_steps": 56475, "total_steps": 58920, "loss": 0.0, "lr": 1.0481224938540866e-08, "epoch": 4.792515274949084, "percentage": 95.85, "elapsed_time": "1:29:07", "remaining_time": "0:03:51", "throughput": 10140.72, "total_tokens": 54225344}
{"current_steps": 56480, "total_steps": 58920, "loss": 0.0, "lr": 1.0438492894232265e-08, "epoch": 4.792939579090292, "percentage": 95.86, "elapsed_time": "1:29:07", "remaining_time": "0:03:51", "throughput": 10140.95, "total_tokens": 54230464}
{"current_steps": 56485, "total_steps": 58920, "loss": 0.0, "lr": 1.039584768037316e-08, "epoch": 4.793363883231501, "percentage": 95.87, "elapsed_time": "1:29:08", "remaining_time": "0:03:50", "throughput": 10141.06, "total_tokens": 54234944}
{"current_steps": 56490, "total_steps": 58920, "loss": 0.0, "lr": 1.0353289300705447e-08, "epoch": 4.793788187372709, "percentage": 95.88, "elapsed_time": "1:29:08", "remaining_time": "0:03:50", "throughput": 10141.33, "total_tokens": 54240512}
{"current_steps": 56495, "total_steps": 58920, "loss": 0.0, "lr": 1.0310817758963474e-08, "epoch": 4.7942124915139175, "percentage": 95.88, "elapsed_time": "1:29:08", "remaining_time": "0:03:49", "throughput": 10141.53, "total_tokens": 54245504}
{"current_steps": 56500, "total_steps": 58920, "loss": 0.0, "lr": 1.0268433058874038e-08, "epoch": 4.7946367956551255, "percentage": 95.89, "elapsed_time": "1:29:09", "remaining_time": "0:03:49", "throughput": 10141.73, "total_tokens": 54250560}
{"current_steps": 56505, "total_steps": 58920, "loss": 0.0, "lr": 1.022613520415605e-08, "epoch": 4.795061099796334, "percentage": 95.9, "elapsed_time": "1:29:09", "remaining_time": "0:03:48", "throughput": 10141.86, "total_tokens": 54255232}
{"current_steps": 56510, "total_steps": 58920, "loss": 0.0, "lr": 1.018392419852121e-08, "epoch": 4.795485403937542, "percentage": 95.91, "elapsed_time": "1:29:10", "remaining_time": "0:03:48", "throughput": 10141.95, "total_tokens": 54259520}
{"current_steps": 56515, "total_steps": 58920, "loss": 0.0, "lr": 1.0141800045673332e-08, "epoch": 4.795909708078751, "percentage": 95.92, "elapsed_time": "1:29:10", "remaining_time": "0:03:47", "throughput": 10142.06, "total_tokens": 54264000}
{"current_steps": 56520, "total_steps": 58920, "loss": 0.0, "lr": 1.0099762749308572e-08, "epoch": 4.796334012219959, "percentage": 95.93, "elapsed_time": "1:29:10", "remaining_time": "0:03:47", "throughput": 10142.3, "total_tokens": 54269312}
{"current_steps": 56525, "total_steps": 58920, "loss": 0.0, "lr": 1.0057812313115643e-08, "epoch": 4.796758316361168, "percentage": 95.94, "elapsed_time": "1:29:11", "remaining_time": "0:03:46", "throughput": 10142.42, "total_tokens": 54273856}
{"current_steps": 56530, "total_steps": 58920, "loss": 0.0, "lr": 1.0015948740775604e-08, "epoch": 4.797182620502376, "percentage": 95.94, "elapsed_time": "1:29:11", "remaining_time": "0:03:46", "throughput": 10142.65, "total_tokens": 54279104}
{"current_steps": 56535, "total_steps": 58920, "loss": 0.0, "lr": 9.974172035961625e-09, "epoch": 4.797606924643585, "percentage": 95.95, "elapsed_time": "1:29:11", "remaining_time": "0:03:45", "throughput": 10142.81, "total_tokens": 54283840}
{"current_steps": 56540, "total_steps": 58920, "loss": 0.0, "lr": 9.932482202339554e-09, "epoch": 4.798031228784793, "percentage": 95.96, "elapsed_time": "1:29:12", "remaining_time": "0:03:45", "throughput": 10143.01, "total_tokens": 54288896}
{"current_steps": 56545, "total_steps": 58920, "loss": 0.0, "lr": 9.890879243567684e-09, "epoch": 4.798455532926002, "percentage": 95.97, "elapsed_time": "1:29:12", "remaining_time": "0:03:44", "throughput": 10143.17, "total_tokens": 54293632}
{"current_steps": 56550, "total_steps": 58920, "loss": 0.0, "lr": 9.849363163296209e-09, "epoch": 4.79887983706721, "percentage": 95.98, "elapsed_time": "1:29:13", "remaining_time": "0:03:44", "throughput": 10143.36, "total_tokens": 54298624}
{"current_steps": 56555, "total_steps": 58920, "loss": 0.0, "lr": 9.807933965168324e-09, "epoch": 4.7993041412084185, "percentage": 95.99, "elapsed_time": "1:29:13", "remaining_time": "0:03:43", "throughput": 10143.5, "total_tokens": 54303168}
{"current_steps": 56560, "total_steps": 58920, "loss": 0.0, "lr": 9.766591652819123e-09, "epoch": 4.7997284453496265, "percentage": 95.99, "elapsed_time": "1:29:13", "remaining_time": "0:03:43", "throughput": 10143.63, "total_tokens": 54307776}
{"current_steps": 56565, "total_steps": 58920, "loss": 0.0, "lr": 9.725336229876257e-09, "epoch": 4.800152749490835, "percentage": 96.0, "elapsed_time": "1:29:14", "remaining_time": "0:03:42", "throughput": 10143.82, "total_tokens": 54312704}
{"current_steps": 56570, "total_steps": 58920, "loss": 0.0, "lr": 9.684167699959723e-09, "epoch": 4.800577053632043, "percentage": 96.01, "elapsed_time": "1:29:14", "remaining_time": "0:03:42", "throughput": 10144.03, "total_tokens": 54317760}
{"current_steps": 56575, "total_steps": 58920, "loss": 0.0, "lr": 9.643086066682072e-09, "epoch": 4.801001357773252, "percentage": 96.02, "elapsed_time": "1:29:15", "remaining_time": "0:03:41", "throughput": 10144.2, "total_tokens": 54322560}
{"current_steps": 56580, "total_steps": 58920, "loss": 0.0, "lr": 9.602091333647866e-09, "epoch": 4.80142566191446, "percentage": 96.03, "elapsed_time": "1:29:15", "remaining_time": "0:03:41", "throughput": 10144.44, "total_tokens": 54327872}
{"current_steps": 56585, "total_steps": 58920, "loss": 0.0178, "lr": 9.56118350445434e-09, "epoch": 4.801849966055669, "percentage": 96.04, "elapsed_time": "1:29:15", "remaining_time": "0:03:41", "throughput": 10144.61, "total_tokens": 54332672}
{"current_steps": 56590, "total_steps": 58920, "loss": 0.0, "lr": 9.520362582691065e-09, "epoch": 4.802274270196877, "percentage": 96.05, "elapsed_time": "1:29:16", "remaining_time": "0:03:40", "throughput": 10144.84, "total_tokens": 54337856}
{"current_steps": 56595, "total_steps": 58920, "loss": 0.0, "lr": 9.479628571939734e-09, "epoch": 4.802698574338086, "percentage": 96.05, "elapsed_time": "1:29:16", "remaining_time": "0:03:40", "throughput": 10145.01, "total_tokens": 54342656}
{"current_steps": 56600, "total_steps": 58920, "loss": 0.0, "lr": 9.438981475774821e-09, "epoch": 4.803122878479294, "percentage": 96.06, "elapsed_time": "1:29:16", "remaining_time": "0:03:39", "throughput": 10145.25, "total_tokens": 54347904}
{"current_steps": 56605, "total_steps": 58920, "loss": 0.0, "lr": 9.398421297762803e-09, "epoch": 4.803547182620503, "percentage": 96.07, "elapsed_time": "1:29:17", "remaining_time": "0:03:39", "throughput": 10145.36, "total_tokens": 54352256}
{"current_steps": 56610, "total_steps": 58920, "loss": 0.0, "lr": 9.357948041462837e-09, "epoch": 4.803971486761711, "percentage": 96.08, "elapsed_time": "1:29:17", "remaining_time": "0:03:38", "throughput": 10145.5, "total_tokens": 54356864}
{"current_steps": 56615, "total_steps": 58920, "loss": 0.0, "lr": 9.317561710426192e-09, "epoch": 4.80439579090292, "percentage": 96.09, "elapsed_time": "1:29:18", "remaining_time": "0:03:38", "throughput": 10145.63, "total_tokens": 54361536}
{"current_steps": 56620, "total_steps": 58920, "loss": 0.0, "lr": 9.277262308196698e-09, "epoch": 4.8048200950441275, "percentage": 96.1, "elapsed_time": "1:29:18", "remaining_time": "0:03:37", "throughput": 10145.79, "total_tokens": 54366208}
{"current_steps": 56625, "total_steps": 58920, "loss": 0.0, "lr": 9.237049838310529e-09, "epoch": 4.805244399185336, "percentage": 96.1, "elapsed_time": "1:29:18", "remaining_time": "0:03:37", "throughput": 10145.99, "total_tokens": 54371200}
{"current_steps": 56630, "total_steps": 58920, "loss": 0.0, "lr": 9.196924304295973e-09, "epoch": 4.805668703326544, "percentage": 96.11, "elapsed_time": "1:29:19", "remaining_time": "0:03:36", "throughput": 10146.31, "total_tokens": 54377024}
{"current_steps": 56635, "total_steps": 58920, "loss": 0.0, "lr": 9.156885709674101e-09, "epoch": 4.806093007467753, "percentage": 96.12, "elapsed_time": "1:29:19", "remaining_time": "0:03:36", "throughput": 10146.43, "total_tokens": 54381440}
{"current_steps": 56640, "total_steps": 58920, "loss": 0.0, "lr": 9.11693405795788e-09, "epoch": 4.806517311608961, "percentage": 96.13, "elapsed_time": "1:29:20", "remaining_time": "0:03:35", "throughput": 10146.59, "total_tokens": 54386112}
{"current_steps": 56645, "total_steps": 58920, "loss": 0.0, "lr": 9.077069352653399e-09, "epoch": 4.80694161575017, "percentage": 96.14, "elapsed_time": "1:29:20", "remaining_time": "0:03:35", "throughput": 10147.33, "total_tokens": 54395136}
{"current_steps": 56650, "total_steps": 58920, "loss": 0.0, "lr": 9.03729159725819e-09, "epoch": 4.807365919891378, "percentage": 96.15, "elapsed_time": "1:29:20", "remaining_time": "0:03:34", "throughput": 10147.53, "total_tokens": 54400128}
{"current_steps": 56655, "total_steps": 58920, "loss": 0.0, "lr": 8.997600795262904e-09, "epoch": 4.807790224032587, "percentage": 96.16, "elapsed_time": "1:29:21", "remaining_time": "0:03:34", "throughput": 10147.67, "total_tokens": 54404736}
{"current_steps": 56660, "total_steps": 58920, "loss": 0.0, "lr": 8.957996950150093e-09, "epoch": 4.808214528173795, "percentage": 96.16, "elapsed_time": "1:29:21", "remaining_time": "0:03:33", "throughput": 10147.86, "total_tokens": 54409600}
{"current_steps": 56665, "total_steps": 58920, "loss": 0.0, "lr": 8.918480065394863e-09, "epoch": 4.808638832315004, "percentage": 96.17, "elapsed_time": "1:29:22", "remaining_time": "0:03:33", "throughput": 10148.02, "total_tokens": 54414272}
{"current_steps": 56670, "total_steps": 58920, "loss": 0.0, "lr": 8.879050144464883e-09, "epoch": 4.809063136456212, "percentage": 96.18, "elapsed_time": "1:29:22", "remaining_time": "0:03:32", "throughput": 10148.11, "total_tokens": 54418560}
{"current_steps": 56675, "total_steps": 58920, "loss": 0.0, "lr": 8.839707190819611e-09, "epoch": 4.809487440597421, "percentage": 96.19, "elapsed_time": "1:29:22", "remaining_time": "0:03:32", "throughput": 10148.24, "total_tokens": 54423040}
{"current_steps": 56680, "total_steps": 58920, "loss": 0.0, "lr": 8.80045120791162e-09, "epoch": 4.809911744738629, "percentage": 96.2, "elapsed_time": "1:29:23", "remaining_time": "0:03:31", "throughput": 10148.42, "total_tokens": 54427840}
{"current_steps": 56685, "total_steps": 58920, "loss": 0.0, "lr": 8.76128219918526e-09, "epoch": 4.810336048879837, "percentage": 96.21, "elapsed_time": "1:29:23", "remaining_time": "0:03:31", "throughput": 10148.6, "total_tokens": 54432768}
{"current_steps": 56690, "total_steps": 58920, "loss": 0.0292, "lr": 8.722200168077564e-09, "epoch": 4.810760353021045, "percentage": 96.22, "elapsed_time": "1:29:23", "remaining_time": "0:03:31", "throughput": 10148.75, "total_tokens": 54437440}
{"current_steps": 56695, "total_steps": 58920, "loss": 0.008, "lr": 8.683205118017789e-09, "epoch": 4.811184657162254, "percentage": 96.22, "elapsed_time": "1:29:24", "remaining_time": "0:03:30", "throughput": 10148.91, "total_tokens": 54442048}
{"current_steps": 56700, "total_steps": 58920, "loss": 0.0, "lr": 8.64429705242753e-09, "epoch": 4.811608961303462, "percentage": 96.23, "elapsed_time": "1:29:24", "remaining_time": "0:03:30", "throughput": 10149.09, "total_tokens": 54446976}
{"current_steps": 56705, "total_steps": 58920, "loss": 0.0, "lr": 8.605475974721166e-09, "epoch": 4.81203326544467, "percentage": 96.24, "elapsed_time": "1:29:25", "remaining_time": "0:03:29", "throughput": 10149.29, "total_tokens": 54451904}
{"current_steps": 56710, "total_steps": 58920, "loss": 0.0, "lr": 8.566741888304641e-09, "epoch": 4.812457569585879, "percentage": 96.25, "elapsed_time": "1:29:25", "remaining_time": "0:03:29", "throughput": 10149.48, "total_tokens": 54456832}
{"current_steps": 56715, "total_steps": 58920, "loss": 0.0, "lr": 8.528094796577124e-09, "epoch": 4.812881873727088, "percentage": 96.26, "elapsed_time": "1:29:25", "remaining_time": "0:03:28", "throughput": 10149.72, "total_tokens": 54462080}
{"current_steps": 56720, "total_steps": 58920, "loss": 0.0, "lr": 8.489534702929458e-09, "epoch": 4.813306177868296, "percentage": 96.27, "elapsed_time": "1:29:26", "remaining_time": "0:03:28", "throughput": 10149.85, "total_tokens": 54466560}
{"current_steps": 56725, "total_steps": 58920, "loss": 0.0, "lr": 8.451061610745381e-09, "epoch": 4.813730482009504, "percentage": 96.27, "elapsed_time": "1:29:26", "remaining_time": "0:03:27", "throughput": 10149.96, "total_tokens": 54470976}
{"current_steps": 56730, "total_steps": 58920, "loss": 0.0, "lr": 8.412675523400637e-09, "epoch": 4.814154786150713, "percentage": 96.28, "elapsed_time": "1:29:26", "remaining_time": "0:03:27", "throughput": 10150.11, "total_tokens": 54475584}
{"current_steps": 56735, "total_steps": 58920, "loss": 0.0, "lr": 8.374376444263421e-09, "epoch": 4.814579090291922, "percentage": 96.29, "elapsed_time": "1:29:27", "remaining_time": "0:03:26", "throughput": 10150.32, "total_tokens": 54480640}
{"current_steps": 56740, "total_steps": 58920, "loss": 0.0, "lr": 8.336164376694599e-09, "epoch": 4.81500339443313, "percentage": 96.3, "elapsed_time": "1:29:27", "remaining_time": "0:03:26", "throughput": 10150.48, "total_tokens": 54485376}
{"current_steps": 56745, "total_steps": 58920, "loss": 0.0, "lr": 8.298039324046824e-09, "epoch": 4.815427698574338, "percentage": 96.31, "elapsed_time": "1:29:28", "remaining_time": "0:03:25", "throughput": 10150.66, "total_tokens": 54490240}
{"current_steps": 56750, "total_steps": 58920, "loss": 0.0, "lr": 8.260001289665642e-09, "epoch": 4.8158520027155465, "percentage": 96.32, "elapsed_time": "1:29:28", "remaining_time": "0:03:25", "throughput": 10150.75, "total_tokens": 54494528}
{"current_steps": 56755, "total_steps": 58920, "loss": 0.0568, "lr": 8.222050276888715e-09, "epoch": 4.816276306856755, "percentage": 96.33, "elapsed_time": "1:29:28", "remaining_time": "0:03:24", "throughput": 10151.06, "total_tokens": 54500224}
{"current_steps": 56760, "total_steps": 58920, "loss": 0.0, "lr": 8.184186289045936e-09, "epoch": 4.816700610997963, "percentage": 96.33, "elapsed_time": "1:29:29", "remaining_time": "0:03:24", "throughput": 10151.18, "total_tokens": 54504640}
{"current_steps": 56765, "total_steps": 58920, "loss": 0.0, "lr": 8.14640932945998e-09, "epoch": 4.817124915139171, "percentage": 96.34, "elapsed_time": "1:29:29", "remaining_time": "0:03:23", "throughput": 10151.37, "total_tokens": 54509568}
{"current_steps": 56770, "total_steps": 58920, "loss": 0.0, "lr": 8.10871940144553e-09, "epoch": 4.81754921928038, "percentage": 96.35, "elapsed_time": "1:29:30", "remaining_time": "0:03:23", "throughput": 10151.5, "total_tokens": 54514112}
{"current_steps": 56775, "total_steps": 58920, "loss": 0.0, "lr": 8.071116508309716e-09, "epoch": 4.817973523421589, "percentage": 96.36, "elapsed_time": "1:29:30", "remaining_time": "0:03:22", "throughput": 10151.58, "total_tokens": 54518336}
{"current_steps": 56780, "total_steps": 58920, "loss": 0.0, "lr": 8.033600653352123e-09, "epoch": 4.818397827562797, "percentage": 96.37, "elapsed_time": "1:29:30", "remaining_time": "0:03:22", "throughput": 10151.93, "total_tokens": 54524352}
{"current_steps": 56785, "total_steps": 58920, "loss": 0.0, "lr": 7.996171839864563e-09, "epoch": 4.818822131704005, "percentage": 96.38, "elapsed_time": "1:29:31", "remaining_time": "0:03:21", "throughput": 10152.07, "total_tokens": 54528960}
{"current_steps": 56790, "total_steps": 58920, "loss": 0.0, "lr": 7.958830071131295e-09, "epoch": 4.819246435845214, "percentage": 96.38, "elapsed_time": "1:29:31", "remaining_time": "0:03:21", "throughput": 10152.18, "total_tokens": 54533312}
{"current_steps": 56795, "total_steps": 58920, "loss": 0.0, "lr": 7.921575350429033e-09, "epoch": 4.819670739986423, "percentage": 96.39, "elapsed_time": "1:29:31", "remaining_time": "0:03:20", "throughput": 10152.47, "total_tokens": 54539008}
{"current_steps": 56800, "total_steps": 58920, "loss": 0.0, "lr": 7.884407681026494e-09, "epoch": 4.820095044127631, "percentage": 96.4, "elapsed_time": "1:29:32", "remaining_time": "0:03:20", "throughput": 10152.72, "total_tokens": 54544320}
{"current_steps": 56805, "total_steps": 58920, "loss": 0.0, "lr": 7.847327066185294e-09, "epoch": 4.820519348268839, "percentage": 96.41, "elapsed_time": "1:29:32", "remaining_time": "0:03:20", "throughput": 10152.86, "total_tokens": 54548864}
{"current_steps": 56810, "total_steps": 58920, "loss": 0.0, "lr": 7.81033350915894e-09, "epoch": 4.8209436524100475, "percentage": 96.42, "elapsed_time": "1:29:33", "remaining_time": "0:03:19", "throughput": 10152.97, "total_tokens": 54553216}
{"current_steps": 56815, "total_steps": 58920, "loss": 0.0, "lr": 7.773427013193501e-09, "epoch": 4.821367956551256, "percentage": 96.43, "elapsed_time": "1:29:33", "remaining_time": "0:03:19", "throughput": 10153.16, "total_tokens": 54558144}
{"current_steps": 56820, "total_steps": 58920, "loss": 0.0, "lr": 7.736607581527388e-09, "epoch": 4.821792260692464, "percentage": 96.44, "elapsed_time": "1:29:33", "remaining_time": "0:03:18", "throughput": 10153.4, "total_tokens": 54563392}
{"current_steps": 56825, "total_steps": 58920, "loss": 0.0, "lr": 7.699875217391571e-09, "epoch": 4.822216564833672, "percentage": 96.44, "elapsed_time": "1:29:34", "remaining_time": "0:03:18", "throughput": 10153.64, "total_tokens": 54568640}
{"current_steps": 56830, "total_steps": 58920, "loss": 0.0, "lr": 7.663229924008918e-09, "epoch": 4.822640868974881, "percentage": 96.45, "elapsed_time": "1:29:34", "remaining_time": "0:03:17", "throughput": 10153.82, "total_tokens": 54573504}
{"current_steps": 56835, "total_steps": 58920, "loss": 0.0, "lr": 7.626671704594967e-09, "epoch": 4.82306517311609, "percentage": 96.46, "elapsed_time": "1:29:35", "remaining_time": "0:03:17", "throughput": 10153.99, "total_tokens": 54578304}
{"current_steps": 56840, "total_steps": 58920, "loss": 0.0, "lr": 7.590200562357707e-09, "epoch": 4.823489477257298, "percentage": 96.47, "elapsed_time": "1:29:35", "remaining_time": "0:03:16", "throughput": 10154.14, "total_tokens": 54582976}
{"current_steps": 56845, "total_steps": 58920, "loss": 0.0, "lr": 7.553816500497245e-09, "epoch": 4.823913781398506, "percentage": 96.48, "elapsed_time": "1:29:35", "remaining_time": "0:03:16", "throughput": 10154.3, "total_tokens": 54587648}
{"current_steps": 56850, "total_steps": 58920, "loss": 0.0, "lr": 7.517519522206139e-09, "epoch": 4.824338085539715, "percentage": 96.49, "elapsed_time": "1:29:36", "remaining_time": "0:03:15", "throughput": 10154.45, "total_tokens": 54592320}
{"current_steps": 56855, "total_steps": 58920, "loss": 0.0, "lr": 7.481309630669397e-09, "epoch": 4.824762389680924, "percentage": 96.5, "elapsed_time": "1:29:36", "remaining_time": "0:03:15", "throughput": 10154.59, "total_tokens": 54596928}
{"current_steps": 56860, "total_steps": 58920, "loss": 0.0, "lr": 7.445186829064254e-09, "epoch": 4.825186693822132, "percentage": 96.5, "elapsed_time": "1:29:36", "remaining_time": "0:03:14", "throughput": 10154.82, "total_tokens": 54602048}
{"current_steps": 56865, "total_steps": 58920, "loss": 0.0, "lr": 7.409151120560286e-09, "epoch": 4.82561099796334, "percentage": 96.51, "elapsed_time": "1:29:37", "remaining_time": "0:03:14", "throughput": 10154.96, "total_tokens": 54606656}
{"current_steps": 56870, "total_steps": 58920, "loss": 0.0, "lr": 7.373202508319631e-09, "epoch": 4.826035302104549, "percentage": 96.52, "elapsed_time": "1:29:37", "remaining_time": "0:03:13", "throughput": 10155.18, "total_tokens": 54611776}
{"current_steps": 56875, "total_steps": 58920, "loss": 0.0, "lr": 7.337340995496654e-09, "epoch": 4.826459606245757, "percentage": 96.53, "elapsed_time": "1:29:38", "remaining_time": "0:03:13", "throughput": 10155.36, "total_tokens": 54616576}
{"current_steps": 56880, "total_steps": 58920, "loss": 0.0, "lr": 7.301566585237839e-09, "epoch": 4.826883910386965, "percentage": 96.54, "elapsed_time": "1:29:38", "remaining_time": "0:03:12", "throughput": 10155.55, "total_tokens": 54621504}
{"current_steps": 56885, "total_steps": 58920, "loss": 0.0, "lr": 7.265879280682674e-09, "epoch": 4.827308214528173, "percentage": 96.55, "elapsed_time": "1:29:38", "remaining_time": "0:03:12", "throughput": 10155.72, "total_tokens": 54626368}
{"current_steps": 56890, "total_steps": 58920, "loss": 0.0, "lr": 7.2302790849620985e-09, "epoch": 4.827732518669382, "percentage": 96.55, "elapsed_time": "1:29:39", "remaining_time": "0:03:11", "throughput": 10155.82, "total_tokens": 54630656}
{"current_steps": 56895, "total_steps": 58920, "loss": 0.0, "lr": 7.194766001200392e-09, "epoch": 4.828156822810591, "percentage": 96.56, "elapsed_time": "1:29:39", "remaining_time": "0:03:11", "throughput": 10156.04, "total_tokens": 54635776}
{"current_steps": 56900, "total_steps": 58920, "loss": 0.0, "lr": 7.159340032513283e-09, "epoch": 4.828581126951799, "percentage": 96.57, "elapsed_time": "1:29:40", "remaining_time": "0:03:10", "throughput": 10156.29, "total_tokens": 54641152}
{"current_steps": 56905, "total_steps": 58920, "loss": 0.0, "lr": 7.124001182009509e-09, "epoch": 4.829005431093007, "percentage": 96.58, "elapsed_time": "1:29:40", "remaining_time": "0:03:10", "throughput": 10156.48, "total_tokens": 54646080}
{"current_steps": 56910, "total_steps": 58920, "loss": 0.0, "lr": 7.088749452789811e-09, "epoch": 4.829429735234216, "percentage": 96.59, "elapsed_time": "1:29:40", "remaining_time": "0:03:10", "throughput": 10156.62, "total_tokens": 54650688}
{"current_steps": 56915, "total_steps": 58920, "loss": 0.0, "lr": 7.053584847947603e-09, "epoch": 4.829854039375425, "percentage": 96.6, "elapsed_time": "1:29:41", "remaining_time": "0:03:09", "throughput": 10156.91, "total_tokens": 54656384}
{"current_steps": 56920, "total_steps": 58920, "loss": 0.0, "lr": 7.018507370568194e-09, "epoch": 4.830278343516633, "percentage": 96.61, "elapsed_time": "1:29:41", "remaining_time": "0:03:09", "throughput": 10157.07, "total_tokens": 54661056}
{"current_steps": 56925, "total_steps": 58920, "loss": 0.0, "lr": 6.983517023729568e-09, "epoch": 4.830702647657841, "percentage": 96.61, "elapsed_time": "1:29:41", "remaining_time": "0:03:08", "throughput": 10157.26, "total_tokens": 54665984}
{"current_steps": 56930, "total_steps": 58920, "loss": 0.0, "lr": 6.948613810502268e-09, "epoch": 4.83112695179905, "percentage": 96.62, "elapsed_time": "1:29:42", "remaining_time": "0:03:08", "throughput": 10157.44, "total_tokens": 54670784}
{"current_steps": 56935, "total_steps": 58920, "loss": 0.0, "lr": 6.913797733948512e-09, "epoch": 4.8315512559402585, "percentage": 96.63, "elapsed_time": "1:29:42", "remaining_time": "0:03:07", "throughput": 10157.6, "total_tokens": 54675520}
{"current_steps": 56940, "total_steps": 58920, "loss": 0.0, "lr": 6.879068797123522e-09, "epoch": 4.8319755600814664, "percentage": 96.64, "elapsed_time": "1:29:43", "remaining_time": "0:03:07", "throughput": 10157.89, "total_tokens": 54681216}
{"current_steps": 56945, "total_steps": 58920, "loss": 0.0, "lr": 6.8444270030745265e-09, "epoch": 4.832399864222674, "percentage": 96.65, "elapsed_time": "1:29:43", "remaining_time": "0:03:06", "throughput": 10158.06, "total_tokens": 54685952}
{"current_steps": 56950, "total_steps": 58920, "loss": 0.0, "lr": 6.809872354841429e-09, "epoch": 4.832824168363883, "percentage": 96.66, "elapsed_time": "1:29:43", "remaining_time": "0:03:06", "throughput": 10158.21, "total_tokens": 54690624}
{"current_steps": 56955, "total_steps": 58920, "loss": 0.0, "lr": 6.775404855456024e-09, "epoch": 4.833248472505091, "percentage": 96.66, "elapsed_time": "1:29:44", "remaining_time": "0:03:05", "throughput": 10158.33, "total_tokens": 54695104}
{"current_steps": 56960, "total_steps": 58920, "loss": 0.0, "lr": 6.741024507942894e-09, "epoch": 4.8336727766463, "percentage": 96.67, "elapsed_time": "1:29:44", "remaining_time": "0:03:05", "throughput": 10158.5, "total_tokens": 54699904}
{"current_steps": 56965, "total_steps": 58920, "loss": 0.0, "lr": 6.706731315318737e-09, "epoch": 4.834097080787508, "percentage": 96.68, "elapsed_time": "1:29:45", "remaining_time": "0:03:04", "throughput": 10158.78, "total_tokens": 54705408}
{"current_steps": 56970, "total_steps": 58920, "loss": 0.0, "lr": 6.672525280592589e-09, "epoch": 4.834521384928717, "percentage": 96.69, "elapsed_time": "1:29:45", "remaining_time": "0:03:04", "throughput": 10159.01, "total_tokens": 54710592}
{"current_steps": 56975, "total_steps": 58920, "loss": 0.0, "lr": 6.63840640676594e-09, "epoch": 4.834945689069925, "percentage": 96.7, "elapsed_time": "1:29:45", "remaining_time": "0:03:03", "throughput": 10159.26, "total_tokens": 54715968}
{"current_steps": 56980, "total_steps": 58920, "loss": 0.0, "lr": 6.604374696832615e-09, "epoch": 4.835369993211134, "percentage": 96.71, "elapsed_time": "1:29:46", "remaining_time": "0:03:03", "throughput": 10159.49, "total_tokens": 54721152}
{"current_steps": 56985, "total_steps": 58920, "loss": 0.0, "lr": 6.570430153778783e-09, "epoch": 4.835794297352342, "percentage": 96.72, "elapsed_time": "1:29:46", "remaining_time": "0:03:02", "throughput": 10159.64, "total_tokens": 54725824}
{"current_steps": 56990, "total_steps": 58920, "loss": 0.0, "lr": 6.53657278058295e-09, "epoch": 4.836218601493551, "percentage": 96.72, "elapsed_time": "1:29:46", "remaining_time": "0:03:02", "throughput": 10159.85, "total_tokens": 54730816}
{"current_steps": 56995, "total_steps": 58920, "loss": 0.0, "lr": 6.50280258021596e-09, "epoch": 4.836642905634759, "percentage": 96.73, "elapsed_time": "1:29:47", "remaining_time": "0:03:01", "throughput": 10160.06, "total_tokens": 54735872}
{"current_steps": 57000, "total_steps": 58920, "loss": 0.0, "lr": 6.469119555641e-09, "epoch": 4.8370672097759675, "percentage": 96.74, "elapsed_time": "1:29:47", "remaining_time": "0:03:01", "throughput": 10160.2, "total_tokens": 54740416}
{"current_steps": 57005, "total_steps": 58920, "loss": 0.0, "lr": 6.4355237098137064e-09, "epoch": 4.8374915139171755, "percentage": 96.75, "elapsed_time": "1:29:48", "remaining_time": "0:03:01", "throughput": 10160.35, "total_tokens": 54745024}
{"current_steps": 57010, "total_steps": 58920, "loss": 0.0, "lr": 6.402015045681941e-09, "epoch": 4.837915818058384, "percentage": 96.76, "elapsed_time": "1:29:48", "remaining_time": "0:03:00", "throughput": 10160.49, "total_tokens": 54749632}
{"current_steps": 57015, "total_steps": 58920, "loss": 0.0, "lr": 6.3685935661860205e-09, "epoch": 4.838340122199592, "percentage": 96.77, "elapsed_time": "1:29:48", "remaining_time": "0:03:00", "throughput": 10160.61, "total_tokens": 54754048}
{"current_steps": 57020, "total_steps": 58920, "loss": 0.0, "lr": 6.335259274258487e-09, "epoch": 4.838764426340801, "percentage": 96.78, "elapsed_time": "1:29:49", "remaining_time": "0:02:59", "throughput": 10160.75, "total_tokens": 54758656}
{"current_steps": 57025, "total_steps": 58920, "loss": 0.0, "lr": 6.302012172824334e-09, "epoch": 4.839188730482009, "percentage": 96.78, "elapsed_time": "1:29:49", "remaining_time": "0:02:59", "throughput": 10160.89, "total_tokens": 54763200}
{"current_steps": 57030, "total_steps": 58920, "loss": 0.0, "lr": 6.268852264800895e-09, "epoch": 4.839613034623218, "percentage": 96.79, "elapsed_time": "1:29:50", "remaining_time": "0:02:58", "throughput": 10161.13, "total_tokens": 54768512}
{"current_steps": 57035, "total_steps": 58920, "loss": 0.0, "lr": 6.235779553097731e-09, "epoch": 4.840037338764426, "percentage": 96.8, "elapsed_time": "1:29:50", "remaining_time": "0:02:58", "throughput": 10161.33, "total_tokens": 54773504}
{"current_steps": 57040, "total_steps": 58920, "loss": 0.0, "lr": 6.202794040617077e-09, "epoch": 4.840461642905635, "percentage": 96.81, "elapsed_time": "1:29:50", "remaining_time": "0:02:57", "throughput": 10161.43, "total_tokens": 54777856}
{"current_steps": 57045, "total_steps": 58920, "loss": 0.0, "lr": 6.169895730253172e-09, "epoch": 4.840885947046843, "percentage": 96.82, "elapsed_time": "1:29:51", "remaining_time": "0:02:57", "throughput": 10161.64, "total_tokens": 54782912}
{"current_steps": 57050, "total_steps": 58920, "loss": 0.0, "lr": 6.137084624892597e-09, "epoch": 4.841310251188052, "percentage": 96.83, "elapsed_time": "1:29:51", "remaining_time": "0:02:56", "throughput": 10161.76, "total_tokens": 54787392}
{"current_steps": 57055, "total_steps": 58920, "loss": 0.0, "lr": 6.104360727414604e-09, "epoch": 4.84173455532926, "percentage": 96.83, "elapsed_time": "1:29:51", "remaining_time": "0:02:56", "throughput": 10161.94, "total_tokens": 54792256}
{"current_steps": 57060, "total_steps": 58920, "loss": 0.0, "lr": 6.071724040690451e-09, "epoch": 4.8421588594704685, "percentage": 96.84, "elapsed_time": "1:29:52", "remaining_time": "0:02:55", "throughput": 10162.07, "total_tokens": 54796800}
{"current_steps": 57065, "total_steps": 58920, "loss": 0.0, "lr": 6.03917456758396e-09, "epoch": 4.8425831636116765, "percentage": 96.85, "elapsed_time": "1:29:52", "remaining_time": "0:02:55", "throughput": 10162.18, "total_tokens": 54801216}
{"current_steps": 57070, "total_steps": 58920, "loss": 0.0, "lr": 6.006712310951179e-09, "epoch": 4.843007467752885, "percentage": 96.86, "elapsed_time": "1:29:53", "remaining_time": "0:02:54", "throughput": 10162.34, "total_tokens": 54805952}
{"current_steps": 57075, "total_steps": 58920, "loss": 0.0, "lr": 5.974337273640717e-09, "epoch": 4.843431771894093, "percentage": 96.87, "elapsed_time": "1:29:53", "remaining_time": "0:02:54", "throughput": 10162.44, "total_tokens": 54810240}
{"current_steps": 57080, "total_steps": 58920, "loss": 0.0, "lr": 5.9420494584930815e-09, "epoch": 4.843856076035302, "percentage": 96.88, "elapsed_time": "1:29:53", "remaining_time": "0:02:53", "throughput": 10162.6, "total_tokens": 54814976}
{"current_steps": 57085, "total_steps": 58920, "loss": 0.0, "lr": 5.909848868341782e-09, "epoch": 4.84428038017651, "percentage": 96.89, "elapsed_time": "1:29:54", "remaining_time": "0:02:53", "throughput": 10162.84, "total_tokens": 54820224}
{"current_steps": 57090, "total_steps": 58920, "loss": 0.0, "lr": 5.877735506012005e-09, "epoch": 4.844704684317719, "percentage": 96.89, "elapsed_time": "1:29:54", "remaining_time": "0:02:52", "throughput": 10162.93, "total_tokens": 54824448}
{"current_steps": 57095, "total_steps": 58920, "loss": 0.0, "lr": 5.8457093743216055e-09, "epoch": 4.845128988458927, "percentage": 96.9, "elapsed_time": "1:29:54", "remaining_time": "0:02:52", "throughput": 10163.16, "total_tokens": 54829632}
{"current_steps": 57100, "total_steps": 58920, "loss": 0.0, "lr": 5.813770476080893e-09, "epoch": 4.845553292600136, "percentage": 96.91, "elapsed_time": "1:29:55", "remaining_time": "0:02:51", "throughput": 10163.22, "total_tokens": 54833664}
{"current_steps": 57105, "total_steps": 58920, "loss": 0.0, "lr": 5.78191881409218e-09, "epoch": 4.845977596741344, "percentage": 96.92, "elapsed_time": "1:29:55", "remaining_time": "0:02:51", "throughput": 10163.4, "total_tokens": 54838464}
{"current_steps": 57110, "total_steps": 58920, "loss": 0.0, "lr": 5.750154391150674e-09, "epoch": 4.846401900882553, "percentage": 96.93, "elapsed_time": "1:29:56", "remaining_time": "0:02:51", "throughput": 10163.5, "total_tokens": 54842752}
{"current_steps": 57115, "total_steps": 58920, "loss": 0.0, "lr": 5.71847721004326e-09, "epoch": 4.846826205023761, "percentage": 96.94, "elapsed_time": "1:29:56", "remaining_time": "0:02:50", "throughput": 10163.65, "total_tokens": 54847424}
{"current_steps": 57120, "total_steps": 58920, "loss": 0.0, "lr": 5.686887273549712e-09, "epoch": 4.84725050916497, "percentage": 96.95, "elapsed_time": "1:29:56", "remaining_time": "0:02:50", "throughput": 10163.86, "total_tokens": 54852480}
{"current_steps": 57125, "total_steps": 58920, "loss": 0.0, "lr": 5.655384584441925e-09, "epoch": 4.8476748133061776, "percentage": 96.95, "elapsed_time": "1:29:57", "remaining_time": "0:02:49", "throughput": 10164.07, "total_tokens": 54857536}
{"current_steps": 57130, "total_steps": 58920, "loss": 0.0, "lr": 5.623969145483909e-09, "epoch": 4.848099117447386, "percentage": 96.96, "elapsed_time": "1:29:57", "remaining_time": "0:02:49", "throughput": 10164.31, "total_tokens": 54862784}
{"current_steps": 57135, "total_steps": 58920, "loss": 0.0, "lr": 5.592640959432571e-09, "epoch": 4.848523421588594, "percentage": 96.97, "elapsed_time": "1:29:57", "remaining_time": "0:02:48", "throughput": 10164.44, "total_tokens": 54867328}
{"current_steps": 57140, "total_steps": 58920, "loss": 0.0, "lr": 5.561400029036601e-09, "epoch": 4.848947725729803, "percentage": 96.98, "elapsed_time": "1:29:58", "remaining_time": "0:02:48", "throughput": 10164.59, "total_tokens": 54871936}
{"current_steps": 57145, "total_steps": 58920, "loss": 0.0, "lr": 5.53024635703736e-09, "epoch": 4.849372029871011, "percentage": 96.99, "elapsed_time": "1:29:58", "remaining_time": "0:02:47", "throughput": 10164.78, "total_tokens": 54876864}
{"current_steps": 57150, "total_steps": 58920, "loss": 0.0, "lr": 5.499179946168553e-09, "epoch": 4.84979633401222, "percentage": 97.0, "elapsed_time": "1:29:59", "remaining_time": "0:02:47", "throughput": 10165.01, "total_tokens": 54882112}
{"current_steps": 57155, "total_steps": 58920, "loss": 0.0, "lr": 5.468200799155998e-09, "epoch": 4.850220638153428, "percentage": 97.0, "elapsed_time": "1:29:59", "remaining_time": "0:02:46", "throughput": 10165.23, "total_tokens": 54887232}
{"current_steps": 57160, "total_steps": 58920, "loss": 0.0, "lr": 5.437308918718075e-09, "epoch": 4.850644942294637, "percentage": 97.01, "elapsed_time": "1:29:59", "remaining_time": "0:02:46", "throughput": 10165.4, "total_tokens": 54892032}
{"current_steps": 57165, "total_steps": 58920, "loss": 0.0, "lr": 5.406504307565507e-09, "epoch": 4.851069246435845, "percentage": 97.02, "elapsed_time": "1:30:00", "remaining_time": "0:02:45", "throughput": 10165.53, "total_tokens": 54896576}
{"current_steps": 57170, "total_steps": 58920, "loss": 0.0, "lr": 5.375786968401241e-09, "epoch": 4.851493550577054, "percentage": 97.03, "elapsed_time": "1:30:00", "remaining_time": "0:02:45", "throughput": 10165.71, "total_tokens": 54901376}
{"current_steps": 57175, "total_steps": 58920, "loss": 0.0, "lr": 5.345156903920567e-09, "epoch": 4.851917854718262, "percentage": 97.04, "elapsed_time": "1:30:01", "remaining_time": "0:02:44", "throughput": 10165.91, "total_tokens": 54906368}
{"current_steps": 57180, "total_steps": 58920, "loss": 0.0, "lr": 5.314614116811111e-09, "epoch": 4.852342158859471, "percentage": 97.05, "elapsed_time": "1:30:01", "remaining_time": "0:02:44", "throughput": 10166.07, "total_tokens": 54911168}
{"current_steps": 57185, "total_steps": 58920, "loss": 0.0, "lr": 5.2841586097530646e-09, "epoch": 4.852766463000679, "percentage": 97.06, "elapsed_time": "1:30:01", "remaining_time": "0:02:43", "throughput": 10166.34, "total_tokens": 54916672}
{"current_steps": 57190, "total_steps": 58920, "loss": 0.0, "lr": 5.253790385418622e-09, "epoch": 4.8531907671418875, "percentage": 97.06, "elapsed_time": "1:30:02", "remaining_time": "0:02:43", "throughput": 10166.52, "total_tokens": 54921600}
{"current_steps": 57195, "total_steps": 58920, "loss": 0.0, "lr": 5.223509446472651e-09, "epoch": 4.853615071283095, "percentage": 97.07, "elapsed_time": "1:30:02", "remaining_time": "0:02:42", "throughput": 10166.7, "total_tokens": 54926464}
{"current_steps": 57200, "total_steps": 58920, "loss": 0.0, "lr": 5.193315795572029e-09, "epoch": 4.854039375424304, "percentage": 97.08, "elapsed_time": "1:30:02", "remaining_time": "0:02:42", "throughput": 10166.8, "total_tokens": 54930752}
{"current_steps": 57205, "total_steps": 58920, "loss": 0.0522, "lr": 5.163209435366189e-09, "epoch": 4.854463679565512, "percentage": 97.09, "elapsed_time": "1:30:03", "remaining_time": "0:02:41", "throughput": 10166.94, "total_tokens": 54935360}
{"current_steps": 57210, "total_steps": 58920, "loss": 0.0, "lr": 5.133190368496909e-09, "epoch": 4.854887983706721, "percentage": 97.1, "elapsed_time": "1:30:03", "remaining_time": "0:02:41", "throughput": 10167.14, "total_tokens": 54940416}
{"current_steps": 57215, "total_steps": 58920, "loss": 0.0, "lr": 5.1032585975981926e-09, "epoch": 4.855312287847929, "percentage": 97.11, "elapsed_time": "1:30:04", "remaining_time": "0:02:41", "throughput": 10167.19, "total_tokens": 54944448}
{"current_steps": 57220, "total_steps": 58920, "loss": 0.0, "lr": 5.073414125296493e-09, "epoch": 4.855736591989138, "percentage": 97.11, "elapsed_time": "1:30:04", "remaining_time": "0:02:40", "throughput": 10167.4, "total_tokens": 54949440}
{"current_steps": 57225, "total_steps": 58920, "loss": 0.0, "lr": 5.043656954210607e-09, "epoch": 4.856160896130346, "percentage": 97.12, "elapsed_time": "1:30:04", "remaining_time": "0:02:40", "throughput": 10167.63, "total_tokens": 54954688}
{"current_steps": 57230, "total_steps": 58920, "loss": 0.0, "lr": 5.013987086951444e-09, "epoch": 4.856585200271555, "percentage": 97.13, "elapsed_time": "1:30:05", "remaining_time": "0:02:39", "throughput": 10167.73, "total_tokens": 54959040}
{"current_steps": 57235, "total_steps": 58920, "loss": 0.0, "lr": 4.984404526122587e-09, "epoch": 4.857009504412763, "percentage": 97.14, "elapsed_time": "1:30:05", "remaining_time": "0:02:39", "throughput": 10167.98, "total_tokens": 54964416}
{"current_steps": 57240, "total_steps": 58920, "loss": 0.0, "lr": 4.954909274319741e-09, "epoch": 4.857433808553972, "percentage": 97.15, "elapsed_time": "1:30:06", "remaining_time": "0:02:38", "throughput": 10168.07, "total_tokens": 54968704}
{"current_steps": 57245, "total_steps": 58920, "loss": 0.0, "lr": 4.925501334130944e-09, "epoch": 4.85785811269518, "percentage": 97.16, "elapsed_time": "1:30:06", "remaining_time": "0:02:38", "throughput": 10168.15, "total_tokens": 54972928}
{"current_steps": 57250, "total_steps": 58920, "loss": 0.0, "lr": 4.896180708136799e-09, "epoch": 4.8582824168363885, "percentage": 97.17, "elapsed_time": "1:30:06", "remaining_time": "0:02:37", "throughput": 10168.29, "total_tokens": 54977536}
{"current_steps": 57255, "total_steps": 58920, "loss": 0.0, "lr": 4.866947398909915e-09, "epoch": 4.8587067209775965, "percentage": 97.17, "elapsed_time": "1:30:07", "remaining_time": "0:02:37", "throughput": 10168.46, "total_tokens": 54982272}
{"current_steps": 57260, "total_steps": 58920, "loss": 0.0, "lr": 4.837801409015574e-09, "epoch": 4.859131025118805, "percentage": 97.18, "elapsed_time": "1:30:07", "remaining_time": "0:02:36", "throughput": 10168.59, "total_tokens": 54986816}
{"current_steps": 57265, "total_steps": 58920, "loss": 0.0, "lr": 4.808742741011062e-09, "epoch": 4.859555329260013, "percentage": 97.19, "elapsed_time": "1:30:07", "remaining_time": "0:02:36", "throughput": 10168.72, "total_tokens": 54991360}
{"current_steps": 57270, "total_steps": 58920, "loss": 0.0, "lr": 4.779771397446231e-09, "epoch": 4.859979633401222, "percentage": 97.2, "elapsed_time": "1:30:08", "remaining_time": "0:02:35", "throughput": 10168.9, "total_tokens": 54996224}
{"current_steps": 57275, "total_steps": 58920, "loss": 0.0, "lr": 4.750887380863266e-09, "epoch": 4.86040393754243, "percentage": 97.21, "elapsed_time": "1:30:08", "remaining_time": "0:02:35", "throughput": 10169.05, "total_tokens": 55000832}
{"current_steps": 57280, "total_steps": 58920, "loss": 0.0, "lr": 4.722090693796588e-09, "epoch": 4.860828241683639, "percentage": 97.22, "elapsed_time": "1:30:09", "remaining_time": "0:02:34", "throughput": 10169.18, "total_tokens": 55005376}
{"current_steps": 57285, "total_steps": 58920, "loss": 0.0, "lr": 4.6933813387730616e-09, "epoch": 4.861252545824847, "percentage": 97.23, "elapsed_time": "1:30:09", "remaining_time": "0:02:34", "throughput": 10169.38, "total_tokens": 55010304}
{"current_steps": 57290, "total_steps": 58920, "loss": 0.0, "lr": 4.664759318311784e-09, "epoch": 4.861676849966056, "percentage": 97.23, "elapsed_time": "1:30:09", "remaining_time": "0:02:33", "throughput": 10169.45, "total_tokens": 55014464}
{"current_steps": 57295, "total_steps": 58920, "loss": 0.0, "lr": 4.6362246349241906e-09, "epoch": 4.862101154107264, "percentage": 97.24, "elapsed_time": "1:30:10", "remaining_time": "0:02:33", "throughput": 10169.63, "total_tokens": 55019264}
{"current_steps": 57300, "total_steps": 58920, "loss": 0.0, "lr": 4.607777291114168e-09, "epoch": 4.862525458248473, "percentage": 97.25, "elapsed_time": "1:30:10", "remaining_time": "0:02:32", "throughput": 10169.73, "total_tokens": 55023616}
{"current_steps": 57305, "total_steps": 58920, "loss": 0.0, "lr": 4.5794172893778295e-09, "epoch": 4.862949762389681, "percentage": 97.26, "elapsed_time": "1:30:10", "remaining_time": "0:02:32", "throughput": 10169.86, "total_tokens": 55028096}
{"current_steps": 57310, "total_steps": 58920, "loss": 0.0, "lr": 4.55114463220363e-09, "epoch": 4.8633740665308896, "percentage": 97.27, "elapsed_time": "1:30:11", "remaining_time": "0:02:32", "throughput": 10170.02, "total_tokens": 55032832}
{"current_steps": 57315, "total_steps": 58920, "loss": 0.0, "lr": 4.522959322072473e-09, "epoch": 4.8637983706720975, "percentage": 97.28, "elapsed_time": "1:30:11", "remaining_time": "0:02:31", "throughput": 10170.15, "total_tokens": 55037376}
{"current_steps": 57320, "total_steps": 58920, "loss": 0.0, "lr": 4.494861361457492e-09, "epoch": 4.864222674813306, "percentage": 97.28, "elapsed_time": "1:30:12", "remaining_time": "0:02:31", "throughput": 10170.32, "total_tokens": 55042176}
{"current_steps": 57325, "total_steps": 58920, "loss": 0.0, "lr": 4.466850752824158e-09, "epoch": 4.864646978954514, "percentage": 97.29, "elapsed_time": "1:30:12", "remaining_time": "0:02:30", "throughput": 10170.54, "total_tokens": 55047296}
{"current_steps": 57330, "total_steps": 58920, "loss": 0.0, "lr": 4.438927498630285e-09, "epoch": 4.865071283095723, "percentage": 97.3, "elapsed_time": "1:30:12", "remaining_time": "0:02:30", "throughput": 10170.72, "total_tokens": 55052160}
{"current_steps": 57335, "total_steps": 58920, "loss": 0.0, "lr": 4.411091601326023e-09, "epoch": 4.865495587236931, "percentage": 97.31, "elapsed_time": "1:30:13", "remaining_time": "0:02:29", "throughput": 10170.86, "total_tokens": 55056768}
{"current_steps": 57340, "total_steps": 58920, "loss": 0.0, "lr": 4.383343063354084e-09, "epoch": 4.86591989137814, "percentage": 97.32, "elapsed_time": "1:30:13", "remaining_time": "0:02:29", "throughput": 10171.08, "total_tokens": 55061888}
{"current_steps": 57345, "total_steps": 58920, "loss": 0.0, "lr": 4.355681887148966e-09, "epoch": 4.866344195519348, "percentage": 97.33, "elapsed_time": "1:30:13", "remaining_time": "0:02:28", "throughput": 10171.24, "total_tokens": 55066560}
{"current_steps": 57350, "total_steps": 58920, "loss": 0.0, "lr": 4.32810807513806e-09, "epoch": 4.866768499660557, "percentage": 97.34, "elapsed_time": "1:30:14", "remaining_time": "0:02:28", "throughput": 10171.34, "total_tokens": 55070912}
{"current_steps": 57355, "total_steps": 58920, "loss": 0.0, "lr": 4.300621629740764e-09, "epoch": 4.867192803801765, "percentage": 97.34, "elapsed_time": "1:30:14", "remaining_time": "0:02:27", "throughput": 10171.46, "total_tokens": 55075392}
{"current_steps": 57360, "total_steps": 58920, "loss": 0.0, "lr": 4.273222553369038e-09, "epoch": 4.867617107942974, "percentage": 97.35, "elapsed_time": "1:30:15", "remaining_time": "0:02:27", "throughput": 10171.63, "total_tokens": 55080128}
{"current_steps": 57365, "total_steps": 58920, "loss": 0.0, "lr": 4.245910848426959e-09, "epoch": 4.868041412084182, "percentage": 97.36, "elapsed_time": "1:30:15", "remaining_time": "0:02:26", "throughput": 10171.87, "total_tokens": 55085504}
{"current_steps": 57370, "total_steps": 58920, "loss": 0.0, "lr": 4.2186865173110545e-09, "epoch": 4.868465716225391, "percentage": 97.37, "elapsed_time": "1:30:15", "remaining_time": "0:02:26", "throughput": 10172.01, "total_tokens": 55090112}
{"current_steps": 57375, "total_steps": 58920, "loss": 0.0, "lr": 4.191549562410191e-09, "epoch": 4.868890020366599, "percentage": 97.38, "elapsed_time": "1:30:16", "remaining_time": "0:02:25", "throughput": 10172.19, "total_tokens": 55094976}
{"current_steps": 57380, "total_steps": 58920, "loss": 0.0, "lr": 4.1644999861053524e-09, "epoch": 4.869314324507807, "percentage": 97.39, "elapsed_time": "1:30:16", "remaining_time": "0:02:25", "throughput": 10172.37, "total_tokens": 55099776}
{"current_steps": 57385, "total_steps": 58920, "loss": 0.0, "lr": 4.137537790770307e-09, "epoch": 4.869738628649015, "percentage": 97.39, "elapsed_time": "1:30:16", "remaining_time": "0:02:24", "throughput": 10172.55, "total_tokens": 55104640}
{"current_steps": 57390, "total_steps": 58920, "loss": 0.0, "lr": 4.110662978770718e-09, "epoch": 4.870162932790224, "percentage": 97.4, "elapsed_time": "1:30:17", "remaining_time": "0:02:24", "throughput": 10172.79, "total_tokens": 55109952}
{"current_steps": 57395, "total_steps": 58920, "loss": 0.0, "lr": 4.083875552464922e-09, "epoch": 4.870587236931432, "percentage": 97.41, "elapsed_time": "1:30:17", "remaining_time": "0:02:23", "throughput": 10172.96, "total_tokens": 55114752}
{"current_steps": 57400, "total_steps": 58920, "loss": 0.0, "lr": 4.057175514203149e-09, "epoch": 4.871011541072641, "percentage": 97.42, "elapsed_time": "1:30:18", "remaining_time": "0:02:23", "throughput": 10173.12, "total_tokens": 55119488}
{"current_steps": 57405, "total_steps": 58920, "loss": 0.0, "lr": 4.030562866328524e-09, "epoch": 4.871435845213849, "percentage": 97.43, "elapsed_time": "1:30:18", "remaining_time": "0:02:23", "throughput": 10173.3, "total_tokens": 55124416}
{"current_steps": 57410, "total_steps": 58920, "loss": 0.0, "lr": 4.004037611175959e-09, "epoch": 4.871860149355058, "percentage": 97.44, "elapsed_time": "1:30:18", "remaining_time": "0:02:22", "throughput": 10173.51, "total_tokens": 55129472}
{"current_steps": 57415, "total_steps": 58920, "loss": 0.0, "lr": 3.977599751073146e-09, "epoch": 4.872284453496266, "percentage": 97.45, "elapsed_time": "1:30:19", "remaining_time": "0:02:22", "throughput": 10173.63, "total_tokens": 55133888}
{"current_steps": 57420, "total_steps": 58920, "loss": 0.0, "lr": 3.951249288339786e-09, "epoch": 4.872708757637475, "percentage": 97.45, "elapsed_time": "1:30:19", "remaining_time": "0:02:21", "throughput": 10173.78, "total_tokens": 55138560}
{"current_steps": 57425, "total_steps": 58920, "loss": 0.0, "lr": 3.924986225288141e-09, "epoch": 4.873133061778683, "percentage": 97.46, "elapsed_time": "1:30:20", "remaining_time": "0:02:21", "throughput": 10173.9, "total_tokens": 55143040}
{"current_steps": 57430, "total_steps": 58920, "loss": 0.0, "lr": 3.898810564222588e-09, "epoch": 4.873557365919892, "percentage": 97.47, "elapsed_time": "1:30:20", "remaining_time": "0:02:20", "throughput": 10174.11, "total_tokens": 55148096}
{"current_steps": 57435, "total_steps": 58920, "loss": 0.0, "lr": 3.872722307439957e-09, "epoch": 4.8739816700611, "percentage": 97.48, "elapsed_time": "1:30:20", "remaining_time": "0:02:20", "throughput": 10174.24, "total_tokens": 55152640}
{"current_steps": 57440, "total_steps": 58920, "loss": 0.0, "lr": 3.846721457229529e-09, "epoch": 4.8744059742023085, "percentage": 97.49, "elapsed_time": "1:30:21", "remaining_time": "0:02:19", "throughput": 10174.44, "total_tokens": 55157632}
{"current_steps": 57445, "total_steps": 58920, "loss": 0.0, "lr": 3.820808015872701e-09, "epoch": 4.8748302783435165, "percentage": 97.5, "elapsed_time": "1:30:21", "remaining_time": "0:02:19", "throughput": 10174.52, "total_tokens": 55161856}
{"current_steps": 57450, "total_steps": 58920, "loss": 0.0, "lr": 3.794981985643209e-09, "epoch": 4.875254582484725, "percentage": 97.51, "elapsed_time": "1:30:21", "remaining_time": "0:02:18", "throughput": 10174.67, "total_tokens": 55166528}
{"current_steps": 57455, "total_steps": 58920, "loss": 0.0, "lr": 3.76924336880724e-09, "epoch": 4.875678886625933, "percentage": 97.51, "elapsed_time": "1:30:22", "remaining_time": "0:02:18", "throughput": 10174.82, "total_tokens": 55171200}
{"current_steps": 57460, "total_steps": 58920, "loss": 0.0, "lr": 3.743592167623321e-09, "epoch": 4.876103190767142, "percentage": 97.52, "elapsed_time": "1:30:22", "remaining_time": "0:02:17", "throughput": 10174.99, "total_tokens": 55176064}
{"current_steps": 57465, "total_steps": 58920, "loss": 0.0, "lr": 3.71802838434232e-09, "epoch": 4.87652749490835, "percentage": 97.53, "elapsed_time": "1:30:23", "remaining_time": "0:02:17", "throughput": 10175.09, "total_tokens": 55180416}
{"current_steps": 57470, "total_steps": 58920, "loss": 0.0, "lr": 3.692552021207107e-09, "epoch": 4.876951799049559, "percentage": 97.54, "elapsed_time": "1:30:23", "remaining_time": "0:02:16", "throughput": 10175.42, "total_tokens": 55186368}
{"current_steps": 57475, "total_steps": 58920, "loss": 0.0, "lr": 3.6671630804534505e-09, "epoch": 4.877376103190767, "percentage": 97.55, "elapsed_time": "1:30:23", "remaining_time": "0:02:16", "throughput": 10175.59, "total_tokens": 55191232}
{"current_steps": 57480, "total_steps": 58920, "loss": 0.0, "lr": 3.6418615643089013e-09, "epoch": 4.877800407331976, "percentage": 97.56, "elapsed_time": "1:30:24", "remaining_time": "0:02:15", "throughput": 10175.77, "total_tokens": 55196096}
{"current_steps": 57485, "total_steps": 58920, "loss": 0.0, "lr": 3.6166474749936836e-09, "epoch": 4.878224711473184, "percentage": 97.56, "elapsed_time": "1:30:24", "remaining_time": "0:02:15", "throughput": 10175.92, "total_tokens": 55200704}
{"current_steps": 57490, "total_steps": 58920, "loss": 0.0, "lr": 3.5915208147202504e-09, "epoch": 4.878649015614393, "percentage": 97.57, "elapsed_time": "1:30:25", "remaining_time": "0:02:14", "throughput": 10176.01, "total_tokens": 55204992}
{"current_steps": 57495, "total_steps": 58920, "loss": 0.0, "lr": 3.5664815856932818e-09, "epoch": 4.879073319755601, "percentage": 97.58, "elapsed_time": "1:30:25", "remaining_time": "0:02:14", "throughput": 10176.28, "total_tokens": 55210496}
{"current_steps": 57500, "total_steps": 58920, "loss": 0.0, "lr": 3.5415297901099095e-09, "epoch": 4.8794976238968095, "percentage": 97.59, "elapsed_time": "1:30:25", "remaining_time": "0:02:13", "throughput": 10176.47, "total_tokens": 55215488}
{"current_steps": 57505, "total_steps": 58920, "loss": 0.0, "lr": 3.5166654301597155e-09, "epoch": 4.8799219280380175, "percentage": 97.6, "elapsed_time": "1:30:26", "remaining_time": "0:02:13", "throughput": 10176.65, "total_tokens": 55220352}
{"current_steps": 57510, "total_steps": 58920, "loss": 0.0, "lr": 3.4918885080242876e-09, "epoch": 4.880346232179226, "percentage": 97.61, "elapsed_time": "1:30:26", "remaining_time": "0:02:13", "throughput": 10176.83, "total_tokens": 55225280}
{"current_steps": 57515, "total_steps": 58920, "loss": 0.0, "lr": 3.4671990258777762e-09, "epoch": 4.880770536320434, "percentage": 97.62, "elapsed_time": "1:30:26", "remaining_time": "0:02:12", "throughput": 10177.02, "total_tokens": 55230208}
{"current_steps": 57520, "total_steps": 58920, "loss": 0.0, "lr": 3.4425969858865587e-09, "epoch": 4.881194840461643, "percentage": 97.62, "elapsed_time": "1:30:27", "remaining_time": "0:02:12", "throughput": 10177.16, "total_tokens": 55234816}
{"current_steps": 57525, "total_steps": 58920, "loss": 0.0, "lr": 3.4180823902093536e-09, "epoch": 4.881619144602851, "percentage": 97.63, "elapsed_time": "1:30:27", "remaining_time": "0:02:11", "throughput": 10177.34, "total_tokens": 55239744}
{"current_steps": 57530, "total_steps": 58920, "loss": 0.0, "lr": 3.3936552409974395e-09, "epoch": 4.88204344874406, "percentage": 97.64, "elapsed_time": "1:30:28", "remaining_time": "0:02:11", "throughput": 10177.42, "total_tokens": 55243904}
{"current_steps": 57535, "total_steps": 58920, "loss": 0.0, "lr": 3.36931554039388e-09, "epoch": 4.882467752885268, "percentage": 97.65, "elapsed_time": "1:30:28", "remaining_time": "0:02:10", "throughput": 10177.57, "total_tokens": 55248576}
{"current_steps": 57540, "total_steps": 58920, "loss": 0.0, "lr": 3.3450632905346333e-09, "epoch": 4.882892057026477, "percentage": 97.66, "elapsed_time": "1:30:28", "remaining_time": "0:02:10", "throughput": 10177.73, "total_tokens": 55253248}
{"current_steps": 57545, "total_steps": 58920, "loss": 0.0, "lr": 3.3208984935476636e-09, "epoch": 4.883316361167685, "percentage": 97.67, "elapsed_time": "1:30:29", "remaining_time": "0:02:09", "throughput": 10177.98, "total_tokens": 55258624}
{"current_steps": 57550, "total_steps": 58920, "loss": 0.0, "lr": 3.296821151553386e-09, "epoch": 4.883740665308894, "percentage": 97.67, "elapsed_time": "1:30:29", "remaining_time": "0:02:09", "throughput": 10178.15, "total_tokens": 55263424}
{"current_steps": 57555, "total_steps": 58920, "loss": 0.0, "lr": 3.272831266664444e-09, "epoch": 4.884164969450102, "percentage": 97.68, "elapsed_time": "1:30:29", "remaining_time": "0:02:08", "throughput": 10178.24, "total_tokens": 55267712}
{"current_steps": 57560, "total_steps": 58920, "loss": 0.0, "lr": 3.2489288409858207e-09, "epoch": 4.884589273591311, "percentage": 97.69, "elapsed_time": "1:30:30", "remaining_time": "0:02:08", "throughput": 10178.44, "total_tokens": 55272704}
{"current_steps": 57565, "total_steps": 58920, "loss": 0.0, "lr": 3.22511387661506e-09, "epoch": 4.8850135777325185, "percentage": 97.7, "elapsed_time": "1:30:30", "remaining_time": "0:02:07", "throughput": 10178.57, "total_tokens": 55277248}
{"current_steps": 57570, "total_steps": 58920, "loss": 0.0, "lr": 3.2013863756416013e-09, "epoch": 4.885437881873727, "percentage": 97.71, "elapsed_time": "1:30:31", "remaining_time": "0:02:07", "throughput": 10178.71, "total_tokens": 55281920}
{"current_steps": 57575, "total_steps": 58920, "loss": 0.0, "lr": 3.177746340147669e-09, "epoch": 4.885862186014935, "percentage": 97.72, "elapsed_time": "1:30:31", "remaining_time": "0:02:06", "throughput": 10178.87, "total_tokens": 55286656}
{"current_steps": 57580, "total_steps": 58920, "loss": 0.0, "lr": 3.154193772207381e-09, "epoch": 4.886286490156144, "percentage": 97.73, "elapsed_time": "1:30:31", "remaining_time": "0:02:06", "throughput": 10179.03, "total_tokens": 55291328}
{"current_steps": 57585, "total_steps": 58920, "loss": 0.0, "lr": 3.130728673887528e-09, "epoch": 4.886710794297352, "percentage": 97.73, "elapsed_time": "1:30:32", "remaining_time": "0:02:05", "throughput": 10179.12, "total_tokens": 55295616}
{"current_steps": 57590, "total_steps": 58920, "loss": 0.0, "lr": 3.107351047247131e-09, "epoch": 4.887135098438561, "percentage": 97.74, "elapsed_time": "1:30:32", "remaining_time": "0:02:05", "throughput": 10179.28, "total_tokens": 55300352}
{"current_steps": 57595, "total_steps": 58920, "loss": 0.0001, "lr": 3.084060894337326e-09, "epoch": 4.887559402579769, "percentage": 97.75, "elapsed_time": "1:30:33", "remaining_time": "0:02:04", "throughput": 10179.4, "total_tokens": 55304832}
{"current_steps": 57600, "total_steps": 58920, "loss": 0.0, "lr": 3.0608582172018114e-09, "epoch": 4.887983706720978, "percentage": 97.76, "elapsed_time": "1:30:33", "remaining_time": "0:02:04", "throughput": 10179.56, "total_tokens": 55309632}
{"current_steps": 57605, "total_steps": 58920, "loss": 0.0, "lr": 3.0377430178766262e-09, "epoch": 4.888408010862186, "percentage": 97.77, "elapsed_time": "1:30:33", "remaining_time": "0:02:04", "throughput": 10179.7, "total_tokens": 55314240}
{"current_steps": 57610, "total_steps": 58920, "loss": 0.0, "lr": 3.014715298389925e-09, "epoch": 4.888832315003395, "percentage": 97.78, "elapsed_time": "1:30:34", "remaining_time": "0:02:03", "throughput": 10179.8, "total_tokens": 55318592}
{"current_steps": 57615, "total_steps": 58920, "loss": 0.0, "lr": 2.9917750607623136e-09, "epoch": 4.889256619144603, "percentage": 97.79, "elapsed_time": "1:30:34", "remaining_time": "0:02:03", "throughput": 10179.96, "total_tokens": 55323264}
{"current_steps": 57620, "total_steps": 58920, "loss": 0.0, "lr": 2.9689223070068493e-09, "epoch": 4.889680923285812, "percentage": 97.79, "elapsed_time": "1:30:34", "remaining_time": "0:02:02", "throughput": 10180.14, "total_tokens": 55328192}
{"current_steps": 57625, "total_steps": 58920, "loss": 0.0, "lr": 2.9461570391287047e-09, "epoch": 4.89010522742702, "percentage": 97.8, "elapsed_time": "1:30:35", "remaining_time": "0:02:02", "throughput": 10180.27, "total_tokens": 55332736}
{"current_steps": 57630, "total_steps": 58920, "loss": 0.0, "lr": 2.9234792591252833e-09, "epoch": 4.8905295315682284, "percentage": 97.81, "elapsed_time": "1:30:35", "remaining_time": "0:02:01", "throughput": 10180.41, "total_tokens": 55337408}
{"current_steps": 57635, "total_steps": 58920, "loss": 0.0, "lr": 2.90088896898677e-09, "epoch": 4.890953835709436, "percentage": 97.82, "elapsed_time": "1:30:36", "remaining_time": "0:02:01", "throughput": 10180.57, "total_tokens": 55342208}
{"current_steps": 57640, "total_steps": 58920, "loss": 0.0, "lr": 2.878386170695135e-09, "epoch": 4.891378139850645, "percentage": 97.83, "elapsed_time": "1:30:36", "remaining_time": "0:02:00", "throughput": 10180.7, "total_tokens": 55346752}
{"current_steps": 57645, "total_steps": 58920, "loss": 0.0, "lr": 2.8559708662251327e-09, "epoch": 4.891802443991853, "percentage": 97.84, "elapsed_time": "1:30:36", "remaining_time": "0:02:00", "throughput": 10180.82, "total_tokens": 55351232}
{"current_steps": 57650, "total_steps": 58920, "loss": 0.0, "lr": 2.833643057543411e-09, "epoch": 4.892226748133062, "percentage": 97.84, "elapsed_time": "1:30:37", "remaining_time": "0:01:59", "throughput": 10180.98, "total_tokens": 55355968}
{"current_steps": 57655, "total_steps": 58920, "loss": 0.0, "lr": 2.811402746609293e-09, "epoch": 4.89265105227427, "percentage": 97.85, "elapsed_time": "1:30:37", "remaining_time": "0:01:59", "throughput": 10181.17, "total_tokens": 55360960}
{"current_steps": 57660, "total_steps": 58920, "loss": 0.0, "lr": 2.789249935374216e-09, "epoch": 4.893075356415479, "percentage": 97.86, "elapsed_time": "1:30:37", "remaining_time": "0:01:58", "throughput": 10181.35, "total_tokens": 55365824}
{"current_steps": 57665, "total_steps": 58920, "loss": 0.0, "lr": 2.767184625782071e-09, "epoch": 4.893499660556687, "percentage": 97.87, "elapsed_time": "1:30:38", "remaining_time": "0:01:58", "throughput": 10181.46, "total_tokens": 55370240}
{"current_steps": 57670, "total_steps": 58920, "loss": 0.0, "lr": 2.7452068197690857e-09, "epoch": 4.893923964697896, "percentage": 97.88, "elapsed_time": "1:30:38", "remaining_time": "0:01:57", "throughput": 10181.64, "total_tokens": 55375168}
{"current_steps": 57675, "total_steps": 58920, "loss": 0.0, "lr": 2.7233165192634964e-09, "epoch": 4.894348268839104, "percentage": 97.89, "elapsed_time": "1:30:39", "remaining_time": "0:01:57", "throughput": 10181.83, "total_tokens": 55380160}
{"current_steps": 57680, "total_steps": 58920, "loss": 0.0, "lr": 2.701513726186211e-09, "epoch": 4.894772572980313, "percentage": 97.9, "elapsed_time": "1:30:39", "remaining_time": "0:01:56", "throughput": 10181.93, "total_tokens": 55384448}
{"current_steps": 57685, "total_steps": 58920, "loss": 0.0, "lr": 2.679798442450476e-09, "epoch": 4.895196877121521, "percentage": 97.9, "elapsed_time": "1:30:39", "remaining_time": "0:01:56", "throughput": 10182.09, "total_tokens": 55389184}
{"current_steps": 57690, "total_steps": 58920, "loss": 0.0, "lr": 2.6581706699615456e-09, "epoch": 4.8956211812627295, "percentage": 97.91, "elapsed_time": "1:30:40", "remaining_time": "0:01:55", "throughput": 10182.29, "total_tokens": 55394176}
{"current_steps": 57695, "total_steps": 58920, "loss": 0.0, "lr": 2.6366304106172353e-09, "epoch": 4.8960454854039375, "percentage": 97.92, "elapsed_time": "1:30:40", "remaining_time": "0:01:55", "throughput": 10182.66, "total_tokens": 55400512}
{"current_steps": 57700, "total_steps": 58920, "loss": 0.0, "lr": 2.6151776663076997e-09, "epoch": 4.896469789545146, "percentage": 97.93, "elapsed_time": "1:30:41", "remaining_time": "0:01:55", "throughput": 10182.82, "total_tokens": 55405248}
{"current_steps": 57705, "total_steps": 58920, "loss": 0.0, "lr": 2.5938124389152104e-09, "epoch": 4.896894093686354, "percentage": 97.94, "elapsed_time": "1:30:41", "remaining_time": "0:01:54", "throughput": 10182.96, "total_tokens": 55409856}
{"current_steps": 57710, "total_steps": 58920, "loss": 0.0, "lr": 2.572534730314602e-09, "epoch": 4.897318397827563, "percentage": 97.95, "elapsed_time": "1:30:41", "remaining_time": "0:01:54", "throughput": 10183.15, "total_tokens": 55414848}
{"current_steps": 57715, "total_steps": 58920, "loss": 0.0, "lr": 2.5513445423728242e-09, "epoch": 4.897742701968771, "percentage": 97.95, "elapsed_time": "1:30:42", "remaining_time": "0:01:53", "throughput": 10183.25, "total_tokens": 55419136}
{"current_steps": 57720, "total_steps": 58920, "loss": 0.0, "lr": 2.5302418769493904e-09, "epoch": 4.89816700610998, "percentage": 97.96, "elapsed_time": "1:30:42", "remaining_time": "0:01:53", "throughput": 10183.35, "total_tokens": 55423488}
{"current_steps": 57725, "total_steps": 58920, "loss": 0.0, "lr": 2.5092267358958197e-09, "epoch": 4.898591310251188, "percentage": 97.97, "elapsed_time": "1:30:42", "remaining_time": "0:01:52", "throughput": 10183.51, "total_tokens": 55428224}
{"current_steps": 57730, "total_steps": 58920, "loss": 0.0, "lr": 2.488299121056192e-09, "epoch": 4.899015614392397, "percentage": 97.98, "elapsed_time": "1:30:43", "remaining_time": "0:01:52", "throughput": 10183.73, "total_tokens": 55433472}
{"current_steps": 57735, "total_steps": 58920, "loss": 0.0, "lr": 2.4674590342668165e-09, "epoch": 4.899439918533605, "percentage": 97.99, "elapsed_time": "1:30:43", "remaining_time": "0:01:51", "throughput": 10183.95, "total_tokens": 55438592}
{"current_steps": 57740, "total_steps": 58920, "loss": 0.0, "lr": 2.446706477356231e-09, "epoch": 4.899864222674813, "percentage": 98.0, "elapsed_time": "1:30:44", "remaining_time": "0:01:51", "throughput": 10184.15, "total_tokens": 55443648}
{"current_steps": 57745, "total_steps": 58920, "loss": 0.0, "lr": 2.426041452145644e-09, "epoch": 4.900288526816022, "percentage": 98.01, "elapsed_time": "1:30:44", "remaining_time": "0:01:50", "throughput": 10184.29, "total_tokens": 55448256}
{"current_steps": 57750, "total_steps": 58920, "loss": 0.0, "lr": 2.405463960448051e-09, "epoch": 4.9007128309572305, "percentage": 98.01, "elapsed_time": "1:30:44", "remaining_time": "0:01:50", "throughput": 10184.39, "total_tokens": 55452544}
{"current_steps": 57755, "total_steps": 58920, "loss": 0.0, "lr": 2.38497400406934e-09, "epoch": 4.9011371350984385, "percentage": 98.02, "elapsed_time": "1:30:45", "remaining_time": "0:01:49", "throughput": 10184.57, "total_tokens": 55457408}
{"current_steps": 57760, "total_steps": 58920, "loss": 0.0, "lr": 2.3645715848072956e-09, "epoch": 4.9015614392396465, "percentage": 98.03, "elapsed_time": "1:30:45", "remaining_time": "0:01:49", "throughput": 10184.8, "total_tokens": 55462656}
{"current_steps": 57765, "total_steps": 58920, "loss": 0.0, "lr": 2.3442567044520413e-09, "epoch": 4.901985743380855, "percentage": 98.04, "elapsed_time": "1:30:46", "remaining_time": "0:01:48", "throughput": 10184.89, "total_tokens": 55466944}
{"current_steps": 57770, "total_steps": 58920, "loss": 0.0, "lr": 2.3240293647862618e-09, "epoch": 4.902410047522064, "percentage": 98.05, "elapsed_time": "1:30:46", "remaining_time": "0:01:48", "throughput": 10185.0, "total_tokens": 55471360}
{"current_steps": 57775, "total_steps": 58920, "loss": 0.0, "lr": 2.3038895675847603e-09, "epoch": 4.902834351663272, "percentage": 98.06, "elapsed_time": "1:30:46", "remaining_time": "0:01:47", "throughput": 10185.17, "total_tokens": 55476160}
{"current_steps": 57780, "total_steps": 58920, "loss": 0.0, "lr": 2.2838373146149003e-09, "epoch": 4.90325865580448, "percentage": 98.07, "elapsed_time": "1:30:47", "remaining_time": "0:01:47", "throughput": 10185.3, "total_tokens": 55480768}
{"current_steps": 57785, "total_steps": 58920, "loss": 0.0, "lr": 2.2638726076360524e-09, "epoch": 4.903682959945689, "percentage": 98.07, "elapsed_time": "1:30:47", "remaining_time": "0:01:46", "throughput": 10185.39, "total_tokens": 55484992}
{"current_steps": 57790, "total_steps": 58920, "loss": 0.0, "lr": 2.243995448400038e-09, "epoch": 4.904107264086898, "percentage": 98.08, "elapsed_time": "1:30:47", "remaining_time": "0:01:46", "throughput": 10185.56, "total_tokens": 55489856}
{"current_steps": 57795, "total_steps": 58920, "loss": 0.0, "lr": 2.2242058386510167e-09, "epoch": 4.904531568228106, "percentage": 98.09, "elapsed_time": "1:30:48", "remaining_time": "0:01:46", "throughput": 10185.73, "total_tokens": 55494656}
{"current_steps": 57800, "total_steps": 58920, "loss": 0.0, "lr": 2.2045037801254885e-09, "epoch": 4.904955872369314, "percentage": 98.1, "elapsed_time": "1:30:48", "remaining_time": "0:01:45", "throughput": 10185.95, "total_tokens": 55499904}
{"current_steps": 57805, "total_steps": 58920, "loss": 0.0, "lr": 2.1848892745522927e-09, "epoch": 4.905380176510523, "percentage": 98.11, "elapsed_time": "1:30:49", "remaining_time": "0:01:45", "throughput": 10186.1, "total_tokens": 55504576}
{"current_steps": 57810, "total_steps": 58920, "loss": 0.0, "lr": 2.1653623236523867e-09, "epoch": 4.905804480651732, "percentage": 98.12, "elapsed_time": "1:30:49", "remaining_time": "0:01:44", "throughput": 10186.27, "total_tokens": 55509376}
{"current_steps": 57815, "total_steps": 58920, "loss": 0.0, "lr": 2.1459229291392875e-09, "epoch": 4.90622878479294, "percentage": 98.12, "elapsed_time": "1:30:49", "remaining_time": "0:01:44", "throughput": 10186.47, "total_tokens": 55514432}
{"current_steps": 57820, "total_steps": 58920, "loss": 0.0, "lr": 2.126571092718743e-09, "epoch": 4.9066530889341475, "percentage": 98.13, "elapsed_time": "1:30:50", "remaining_time": "0:01:43", "throughput": 10186.59, "total_tokens": 55518976}
{"current_steps": 57825, "total_steps": 58920, "loss": 0.0, "lr": 2.1073068160887275e-09, "epoch": 4.907077393075356, "percentage": 98.14, "elapsed_time": "1:30:50", "remaining_time": "0:01:43", "throughput": 10186.76, "total_tokens": 55523776}
{"current_steps": 57830, "total_steps": 58920, "loss": 0.0, "lr": 2.0881301009396668e-09, "epoch": 4.907501697216565, "percentage": 98.15, "elapsed_time": "1:30:50", "remaining_time": "0:01:42", "throughput": 10186.93, "total_tokens": 55528576}
{"current_steps": 57835, "total_steps": 58920, "loss": 0.0, "lr": 2.069040948954326e-09, "epoch": 4.907926001357773, "percentage": 98.16, "elapsed_time": "1:30:51", "remaining_time": "0:01:42", "throughput": 10187.13, "total_tokens": 55533632}
{"current_steps": 57840, "total_steps": 58920, "loss": 0.0, "lr": 2.0500393618075875e-09, "epoch": 4.908350305498981, "percentage": 98.17, "elapsed_time": "1:30:51", "remaining_time": "0:01:41", "throughput": 10187.23, "total_tokens": 55537920}
{"current_steps": 57845, "total_steps": 58920, "loss": 0.0, "lr": 2.031125341166673e-09, "epoch": 4.90877460964019, "percentage": 98.18, "elapsed_time": "1:30:52", "remaining_time": "0:01:41", "throughput": 10187.37, "total_tokens": 55542528}
{"current_steps": 57850, "total_steps": 58920, "loss": 0.0, "lr": 2.012298888691588e-09, "epoch": 4.909198913781399, "percentage": 98.18, "elapsed_time": "1:30:52", "remaining_time": "0:01:40", "throughput": 10187.67, "total_tokens": 55548352}
{"current_steps": 57855, "total_steps": 58920, "loss": 0.0, "lr": 1.9935600060339007e-09, "epoch": 4.909623217922607, "percentage": 98.19, "elapsed_time": "1:30:52", "remaining_time": "0:01:40", "throughput": 10187.95, "total_tokens": 55553920}
{"current_steps": 57860, "total_steps": 58920, "loss": 0.0, "lr": 1.9749086948380734e-09, "epoch": 4.910047522063815, "percentage": 98.2, "elapsed_time": "1:30:53", "remaining_time": "0:01:39", "throughput": 10188.12, "total_tokens": 55558784}
{"current_steps": 57865, "total_steps": 58920, "loss": 0.0, "lr": 1.9563449567406855e-09, "epoch": 4.910471826205024, "percentage": 98.21, "elapsed_time": "1:30:53", "remaining_time": "0:01:39", "throughput": 10188.2, "total_tokens": 55563008}
{"current_steps": 57870, "total_steps": 58920, "loss": 0.0, "lr": 1.937868793370545e-09, "epoch": 4.910896130346233, "percentage": 98.22, "elapsed_time": "1:30:54", "remaining_time": "0:01:38", "throughput": 10188.32, "total_tokens": 55567488}
{"current_steps": 57875, "total_steps": 58920, "loss": 0.0, "lr": 1.919480206348911e-09, "epoch": 4.911320434487441, "percentage": 98.23, "elapsed_time": "1:30:54", "remaining_time": "0:01:38", "throughput": 10188.45, "total_tokens": 55572032}
{"current_steps": 57880, "total_steps": 58920, "loss": 0.0, "lr": 1.901179197289382e-09, "epoch": 4.911744738628649, "percentage": 98.23, "elapsed_time": "1:30:54", "remaining_time": "0:01:38", "throughput": 10188.56, "total_tokens": 55576448}
{"current_steps": 57885, "total_steps": 58920, "loss": 0.0, "lr": 1.882965767797784e-09, "epoch": 4.912169042769857, "percentage": 98.24, "elapsed_time": "1:30:55", "remaining_time": "0:01:37", "throughput": 10188.75, "total_tokens": 55581440}
{"current_steps": 57890, "total_steps": 58920, "loss": 0.0, "lr": 1.864839919472283e-09, "epoch": 4.912593346911066, "percentage": 98.25, "elapsed_time": "1:30:55", "remaining_time": "0:01:37", "throughput": 10188.95, "total_tokens": 55586432}
{"current_steps": 57895, "total_steps": 58920, "loss": 0.0, "lr": 1.8468016539032738e-09, "epoch": 4.913017651052274, "percentage": 98.26, "elapsed_time": "1:30:55", "remaining_time": "0:01:36", "throughput": 10189.12, "total_tokens": 55591296}
{"current_steps": 57900, "total_steps": 58920, "loss": 0.0, "lr": 1.8288509726736013e-09, "epoch": 4.913441955193482, "percentage": 98.27, "elapsed_time": "1:30:56", "remaining_time": "0:01:36", "throughput": 10189.36, "total_tokens": 55596544}
{"current_steps": 57905, "total_steps": 58920, "loss": 0.0, "lr": 1.8109878773583388e-09, "epoch": 4.913866259334691, "percentage": 98.28, "elapsed_time": "1:30:56", "remaining_time": "0:01:35", "throughput": 10189.54, "total_tokens": 55601408}
{"current_steps": 57910, "total_steps": 58920, "loss": 0.0, "lr": 1.79321236952501e-09, "epoch": 4.9142905634759, "percentage": 98.29, "elapsed_time": "1:30:57", "remaining_time": "0:01:35", "throughput": 10189.65, "total_tokens": 55605824}
{"current_steps": 57915, "total_steps": 58920, "loss": 0.0, "lr": 1.7755244507332568e-09, "epoch": 4.914714867617108, "percentage": 98.29, "elapsed_time": "1:30:57", "remaining_time": "0:01:34", "throughput": 10189.82, "total_tokens": 55610688}
{"current_steps": 57920, "total_steps": 58920, "loss": 0.0, "lr": 1.7579241225350594e-09, "epoch": 4.915139171758316, "percentage": 98.3, "elapsed_time": "1:30:57", "remaining_time": "0:01:34", "throughput": 10189.99, "total_tokens": 55615488}
{"current_steps": 57925, "total_steps": 58920, "loss": 0.0, "lr": 1.7404113864749603e-09, "epoch": 4.915563475899525, "percentage": 98.31, "elapsed_time": "1:30:58", "remaining_time": "0:01:33", "throughput": 10190.14, "total_tokens": 55620288}
{"current_steps": 57930, "total_steps": 58920, "loss": 0.0, "lr": 1.7229862440896193e-09, "epoch": 4.915987780040734, "percentage": 98.32, "elapsed_time": "1:30:58", "remaining_time": "0:01:33", "throughput": 10190.3, "total_tokens": 55625024}
{"current_steps": 57935, "total_steps": 58920, "loss": 0.0, "lr": 1.7056486969079242e-09, "epoch": 4.916412084181942, "percentage": 98.33, "elapsed_time": "1:30:59", "remaining_time": "0:01:32", "throughput": 10190.67, "total_tokens": 55631360}
{"current_steps": 57940, "total_steps": 58920, "loss": 0.0, "lr": 1.688398746451214e-09, "epoch": 4.91683638832315, "percentage": 98.34, "elapsed_time": "1:30:59", "remaining_time": "0:01:32", "throughput": 10190.87, "total_tokens": 55636416}
{"current_steps": 57945, "total_steps": 58920, "loss": 0.0, "lr": 1.6712363942331664e-09, "epoch": 4.9172606924643585, "percentage": 98.35, "elapsed_time": "1:30:59", "remaining_time": "0:01:31", "throughput": 10191.01, "total_tokens": 55641024}
{"current_steps": 57950, "total_steps": 58920, "loss": 0.0, "lr": 1.6541616417595772e-09, "epoch": 4.917684996605567, "percentage": 98.35, "elapsed_time": "1:31:00", "remaining_time": "0:01:31", "throughput": 10191.21, "total_tokens": 55646144}
{"current_steps": 57955, "total_steps": 58920, "loss": 0.0, "lr": 1.6371744905289142e-09, "epoch": 4.918109300746775, "percentage": 98.36, "elapsed_time": "1:31:00", "remaining_time": "0:01:30", "throughput": 10191.44, "total_tokens": 55651392}
{"current_steps": 57960, "total_steps": 58920, "loss": 0.0, "lr": 1.6202749420315408e-09, "epoch": 4.918533604887983, "percentage": 98.37, "elapsed_time": "1:31:00", "remaining_time": "0:01:30", "throughput": 10191.57, "total_tokens": 55655936}
{"current_steps": 57965, "total_steps": 58920, "loss": 0.0, "lr": 1.6034629977503821e-09, "epoch": 4.918957909029192, "percentage": 98.38, "elapsed_time": "1:31:01", "remaining_time": "0:01:29", "throughput": 10191.68, "total_tokens": 55660288}
{"current_steps": 57970, "total_steps": 58920, "loss": 0.0, "lr": 1.5867386591607023e-09, "epoch": 4.919382213170401, "percentage": 98.39, "elapsed_time": "1:31:01", "remaining_time": "0:01:29", "throughput": 10191.79, "total_tokens": 55664704}
{"current_steps": 57975, "total_steps": 58920, "loss": 0.0, "lr": 1.5701019277299942e-09, "epoch": 4.919806517311609, "percentage": 98.4, "elapsed_time": "1:31:02", "remaining_time": "0:01:29", "throughput": 10191.98, "total_tokens": 55669696}
{"current_steps": 57980, "total_steps": 58920, "loss": 0.0, "lr": 1.5535528049179791e-09, "epoch": 4.920230821452817, "percentage": 98.4, "elapsed_time": "1:31:02", "remaining_time": "0:01:28", "throughput": 10192.07, "total_tokens": 55673984}
{"current_steps": 57985, "total_steps": 58920, "loss": 0.0, "lr": 1.5370912921768286e-09, "epoch": 4.920655125594026, "percentage": 98.41, "elapsed_time": "1:31:02", "remaining_time": "0:01:28", "throughput": 10192.27, "total_tokens": 55679040}
{"current_steps": 57990, "total_steps": 58920, "loss": 0.0, "lr": 1.520717390950943e-09, "epoch": 4.921079429735235, "percentage": 98.42, "elapsed_time": "1:31:03", "remaining_time": "0:01:27", "throughput": 10192.47, "total_tokens": 55684032}
{"current_steps": 57995, "total_steps": 58920, "loss": 0.0, "lr": 1.5044311026771728e-09, "epoch": 4.921503733876443, "percentage": 98.43, "elapsed_time": "1:31:03", "remaining_time": "0:01:27", "throughput": 10192.74, "total_tokens": 55689536}
{"current_steps": 58000, "total_steps": 58920, "loss": 0.0, "lr": 1.488232428784375e-09, "epoch": 4.921928038017651, "percentage": 98.44, "elapsed_time": "1:31:04", "remaining_time": "0:01:26", "throughput": 10192.84, "total_tokens": 55693888}
{"current_steps": 58005, "total_steps": 58920, "loss": 0.0, "lr": 1.4721213706941904e-09, "epoch": 4.9223523421588595, "percentage": 98.45, "elapsed_time": "1:31:04", "remaining_time": "0:01:26", "throughput": 10192.99, "total_tokens": 55698560}
{"current_steps": 58010, "total_steps": 58920, "loss": 0.0, "lr": 1.456097929820266e-09, "epoch": 4.9227766463000675, "percentage": 98.46, "elapsed_time": "1:31:04", "remaining_time": "0:01:25", "throughput": 10193.27, "total_tokens": 55704192}
{"current_steps": 58015, "total_steps": 58920, "loss": 0.0, "lr": 1.4401621075683657e-09, "epoch": 4.923200950441276, "percentage": 98.46, "elapsed_time": "1:31:05", "remaining_time": "0:01:25", "throughput": 10193.43, "total_tokens": 55708992}
{"current_steps": 58020, "total_steps": 58920, "loss": 0.0, "lr": 1.4243139053370378e-09, "epoch": 4.923625254582484, "percentage": 98.47, "elapsed_time": "1:31:05", "remaining_time": "0:01:24", "throughput": 10193.6, "total_tokens": 55713792}
{"current_steps": 58025, "total_steps": 58920, "loss": 0.0, "lr": 1.4085533245167258e-09, "epoch": 4.924049558723693, "percentage": 98.48, "elapsed_time": "1:31:05", "remaining_time": "0:01:24", "throughput": 10193.69, "total_tokens": 55718080}
{"current_steps": 58030, "total_steps": 58920, "loss": 0.0, "lr": 1.3928803664906563e-09, "epoch": 4.924473862864901, "percentage": 98.49, "elapsed_time": "1:31:06", "remaining_time": "0:01:23", "throughput": 10193.83, "total_tokens": 55722688}
{"current_steps": 58035, "total_steps": 58920, "loss": 0.0, "lr": 1.3772950326337296e-09, "epoch": 4.92489816700611, "percentage": 98.5, "elapsed_time": "1:31:06", "remaining_time": "0:01:23", "throughput": 10194.03, "total_tokens": 55727744}
{"current_steps": 58040, "total_steps": 58920, "loss": 0.0, "lr": 1.3617973243136293e-09, "epoch": 4.925322471147318, "percentage": 98.51, "elapsed_time": "1:31:07", "remaining_time": "0:01:22", "throughput": 10194.19, "total_tokens": 55732544}
{"current_steps": 58045, "total_steps": 58920, "loss": 0.0, "lr": 1.3463872428902678e-09, "epoch": 4.925746775288527, "percentage": 98.51, "elapsed_time": "1:31:07", "remaining_time": "0:01:22", "throughput": 10194.35, "total_tokens": 55737216}
{"current_steps": 58050, "total_steps": 58920, "loss": 0.0, "lr": 1.3310647897158967e-09, "epoch": 4.926171079429735, "percentage": 98.52, "elapsed_time": "1:31:07", "remaining_time": "0:01:21", "throughput": 10194.49, "total_tokens": 55741888}
{"current_steps": 58055, "total_steps": 58920, "loss": 0.0, "lr": 1.3158299661347739e-09, "epoch": 4.926595383570944, "percentage": 98.53, "elapsed_time": "1:31:08", "remaining_time": "0:01:21", "throughput": 10194.67, "total_tokens": 55746816}
{"current_steps": 58060, "total_steps": 58920, "loss": 0.0, "lr": 1.300682773483941e-09, "epoch": 4.927019687712152, "percentage": 98.54, "elapsed_time": "1:31:08", "remaining_time": "0:01:21", "throughput": 10194.8, "total_tokens": 55751360}
{"current_steps": 58065, "total_steps": 58920, "loss": 0.0, "lr": 1.285623213092335e-09, "epoch": 4.927443991853361, "percentage": 98.55, "elapsed_time": "1:31:08", "remaining_time": "0:01:20", "throughput": 10194.91, "total_tokens": 55755776}
{"current_steps": 58070, "total_steps": 58920, "loss": 0.0, "lr": 1.2706512862814545e-09, "epoch": 4.9278682959945685, "percentage": 98.56, "elapsed_time": "1:31:09", "remaining_time": "0:01:20", "throughput": 10195.08, "total_tokens": 55760576}
{"current_steps": 58075, "total_steps": 58920, "loss": 0.0, "lr": 1.2557669943650262e-09, "epoch": 4.928292600135777, "percentage": 98.57, "elapsed_time": "1:31:09", "remaining_time": "0:01:19", "throughput": 10195.22, "total_tokens": 55765184}
{"current_steps": 58080, "total_steps": 58920, "loss": 0.0, "lr": 1.2409703386491166e-09, "epoch": 4.928716904276985, "percentage": 98.57, "elapsed_time": "1:31:10", "remaining_time": "0:01:19", "throughput": 10195.49, "total_tokens": 55770752}
{"current_steps": 58085, "total_steps": 58920, "loss": 0.0, "lr": 1.2262613204321315e-09, "epoch": 4.929141208418194, "percentage": 98.58, "elapsed_time": "1:31:10", "remaining_time": "0:01:18", "throughput": 10195.67, "total_tokens": 55775616}
{"current_steps": 58090, "total_steps": 58920, "loss": 0.0, "lr": 1.211639941004594e-09, "epoch": 4.929565512559402, "percentage": 98.59, "elapsed_time": "1:31:10", "remaining_time": "0:01:18", "throughput": 10195.82, "total_tokens": 55780352}
{"current_steps": 58095, "total_steps": 58920, "loss": 0.0, "lr": 1.1971062016494782e-09, "epoch": 4.929989816700611, "percentage": 98.6, "elapsed_time": "1:31:11", "remaining_time": "0:01:17", "throughput": 10195.98, "total_tokens": 55785152}
{"current_steps": 58100, "total_steps": 58920, "loss": 0.0, "lr": 1.182660103642208e-09, "epoch": 4.930414120841819, "percentage": 98.61, "elapsed_time": "1:31:11", "remaining_time": "0:01:17", "throughput": 10196.1, "total_tokens": 55789568}
{"current_steps": 58105, "total_steps": 58920, "loss": 0.0, "lr": 1.1683016482502139e-09, "epoch": 4.930838424983028, "percentage": 98.62, "elapsed_time": "1:31:12", "remaining_time": "0:01:16", "throughput": 10196.28, "total_tokens": 55794496}
{"current_steps": 58110, "total_steps": 58920, "loss": 0.0, "lr": 1.1540308367335994e-09, "epoch": 4.931262729124236, "percentage": 98.63, "elapsed_time": "1:31:12", "remaining_time": "0:01:16", "throughput": 10196.44, "total_tokens": 55799232}
{"current_steps": 58115, "total_steps": 58920, "loss": 0.0, "lr": 1.1398476703443626e-09, "epoch": 4.931687033265445, "percentage": 98.63, "elapsed_time": "1:31:12", "remaining_time": "0:01:15", "throughput": 10196.59, "total_tokens": 55803968}
{"current_steps": 58120, "total_steps": 58920, "loss": 0.0, "lr": 1.125752150327175e-09, "epoch": 4.932111337406653, "percentage": 98.64, "elapsed_time": "1:31:13", "remaining_time": "0:01:15", "throughput": 10196.7, "total_tokens": 55808448}
{"current_steps": 58125, "total_steps": 58920, "loss": 0.0, "lr": 1.1117442779188247e-09, "epoch": 4.932535641547862, "percentage": 98.65, "elapsed_time": "1:31:13", "remaining_time": "0:01:14", "throughput": 10196.92, "total_tokens": 55813632}
{"current_steps": 58130, "total_steps": 58920, "loss": 0.0, "lr": 1.0978240543483285e-09, "epoch": 4.93295994568907, "percentage": 98.66, "elapsed_time": "1:31:13", "remaining_time": "0:01:14", "throughput": 10196.98, "total_tokens": 55817728}
{"current_steps": 58135, "total_steps": 58920, "loss": 0.0, "lr": 1.0839914808373763e-09, "epoch": 4.9333842498302785, "percentage": 98.67, "elapsed_time": "1:31:14", "remaining_time": "0:01:13", "throughput": 10197.21, "total_tokens": 55823040}
{"current_steps": 58140, "total_steps": 58920, "loss": 0.0, "lr": 1.0702465585995523e-09, "epoch": 4.933808553971486, "percentage": 98.68, "elapsed_time": "1:31:14", "remaining_time": "0:01:13", "throughput": 10197.43, "total_tokens": 55828224}
{"current_steps": 58145, "total_steps": 58920, "loss": 0.0, "lr": 1.0565892888410032e-09, "epoch": 4.934232858112695, "percentage": 98.68, "elapsed_time": "1:31:15", "remaining_time": "0:01:12", "throughput": 10197.56, "total_tokens": 55832768}
{"current_steps": 58150, "total_steps": 58920, "loss": 0.0, "lr": 1.0430196727599927e-09, "epoch": 4.934657162253903, "percentage": 98.69, "elapsed_time": "1:31:15", "remaining_time": "0:01:12", "throughput": 10197.73, "total_tokens": 55837632}
{"current_steps": 58155, "total_steps": 58920, "loss": 0.0, "lr": 1.0295377115473458e-09, "epoch": 4.935081466395112, "percentage": 98.7, "elapsed_time": "1:31:15", "remaining_time": "0:01:12", "throughput": 10197.95, "total_tokens": 55842816}
{"current_steps": 58160, "total_steps": 58920, "loss": 0.0, "lr": 1.0161434063860054e-09, "epoch": 4.93550577053632, "percentage": 98.71, "elapsed_time": "1:31:16", "remaining_time": "0:01:11", "throughput": 10198.03, "total_tokens": 55847040}
{"current_steps": 58165, "total_steps": 58920, "loss": 0.0, "lr": 1.002836758451253e-09, "epoch": 4.935930074677529, "percentage": 98.72, "elapsed_time": "1:31:16", "remaining_time": "0:01:11", "throughput": 10198.21, "total_tokens": 55851968}
{"current_steps": 58170, "total_steps": 58920, "loss": 0.0, "lr": 9.89617768910711e-10, "epoch": 4.936354378818737, "percentage": 98.73, "elapsed_time": "1:31:17", "remaining_time": "0:01:10", "throughput": 10198.34, "total_tokens": 55856512}
{"current_steps": 58175, "total_steps": 58920, "loss": 0.0, "lr": 9.7648643892434e-10, "epoch": 4.936778682959946, "percentage": 98.74, "elapsed_time": "1:31:17", "remaining_time": "0:01:10", "throughput": 10198.6, "total_tokens": 55862016}
{"current_steps": 58180, "total_steps": 58920, "loss": 0.0, "lr": 9.634427696442183e-10, "epoch": 4.937202987101154, "percentage": 98.74, "elapsed_time": "1:31:17", "remaining_time": "0:01:09", "throughput": 10198.85, "total_tokens": 55867456}
{"current_steps": 58185, "total_steps": 58920, "loss": 0.0, "lr": 9.50486762215097e-10, "epoch": 4.937627291242363, "percentage": 98.75, "elapsed_time": "1:31:18", "remaining_time": "0:01:09", "throughput": 10198.97, "total_tokens": 55871936}
{"current_steps": 58190, "total_steps": 58920, "loss": 0.0, "lr": 9.376184177736224e-10, "epoch": 4.938051595383571, "percentage": 98.76, "elapsed_time": "1:31:18", "remaining_time": "0:01:08", "throughput": 10199.14, "total_tokens": 55876800}
{"current_steps": 58195, "total_steps": 58920, "loss": 0.0, "lr": 9.248377374491134e-10, "epoch": 4.9384758995247795, "percentage": 98.77, "elapsed_time": "1:31:18", "remaining_time": "0:01:08", "throughput": 10199.24, "total_tokens": 55881216}
{"current_steps": 58200, "total_steps": 58920, "loss": 0.0, "lr": 9.121447223628953e-10, "epoch": 4.9389002036659875, "percentage": 98.78, "elapsed_time": "1:31:19", "remaining_time": "0:01:07", "throughput": 10199.4, "total_tokens": 55885952}
{"current_steps": 58205, "total_steps": 58920, "loss": 0.0, "lr": 8.995393736287438e-10, "epoch": 4.939324507807196, "percentage": 98.79, "elapsed_time": "1:31:19", "remaining_time": "0:01:07", "throughput": 10199.59, "total_tokens": 55890944}
{"current_steps": 58210, "total_steps": 58920, "loss": 0.0, "lr": 8.87021692352885e-10, "epoch": 4.939748811948404, "percentage": 98.79, "elapsed_time": "1:31:20", "remaining_time": "0:01:06", "throughput": 10199.73, "total_tokens": 55895488}
{"current_steps": 58215, "total_steps": 58920, "loss": 0.0, "lr": 8.745916796334407e-10, "epoch": 4.940173116089613, "percentage": 98.8, "elapsed_time": "1:31:20", "remaining_time": "0:01:06", "throughput": 10199.91, "total_tokens": 55900416}
{"current_steps": 58220, "total_steps": 58920, "loss": 0.0, "lr": 8.62249336561316e-10, "epoch": 4.940597420230821, "percentage": 98.81, "elapsed_time": "1:31:20", "remaining_time": "0:01:05", "throughput": 10200.24, "total_tokens": 55906432}
{"current_steps": 58225, "total_steps": 58920, "loss": 0.0, "lr": 8.499946642195333e-10, "epoch": 4.94102172437203, "percentage": 98.82, "elapsed_time": "1:31:21", "remaining_time": "0:01:05", "throughput": 10200.52, "total_tokens": 55912128}
{"current_steps": 58230, "total_steps": 58920, "loss": 0.0, "lr": 8.378276636832326e-10, "epoch": 4.941446028513238, "percentage": 98.83, "elapsed_time": "1:31:21", "remaining_time": "0:01:04", "throughput": 10200.63, "total_tokens": 55916544}
{"current_steps": 58235, "total_steps": 58920, "loss": 0.0, "lr": 8.257483360200046e-10, "epoch": 4.941870332654447, "percentage": 98.84, "elapsed_time": "1:31:22", "remaining_time": "0:01:04", "throughput": 10200.77, "total_tokens": 55921152}
{"current_steps": 58240, "total_steps": 58920, "loss": 0.0, "lr": 8.13756682290001e-10, "epoch": 4.942294636795655, "percentage": 98.85, "elapsed_time": "1:31:22", "remaining_time": "0:01:04", "throughput": 10200.93, "total_tokens": 55925888}
{"current_steps": 58245, "total_steps": 58920, "loss": 0.0, "lr": 8.018527035452693e-10, "epoch": 4.942718940936864, "percentage": 98.85, "elapsed_time": "1:31:22", "remaining_time": "0:01:03", "throughput": 10201.16, "total_tokens": 55931200}
{"current_steps": 58250, "total_steps": 58920, "loss": 0.0, "lr": 7.900364008303073e-10, "epoch": 4.943143245078072, "percentage": 98.86, "elapsed_time": "1:31:23", "remaining_time": "0:01:03", "throughput": 10201.37, "total_tokens": 55936256}
{"current_steps": 58255, "total_steps": 58920, "loss": 0.0, "lr": 7.783077751820633e-10, "epoch": 4.9435675492192805, "percentage": 98.87, "elapsed_time": "1:31:23", "remaining_time": "0:01:02", "throughput": 10201.54, "total_tokens": 55941120}
{"current_steps": 58260, "total_steps": 58920, "loss": 0.0, "lr": 7.666668276296028e-10, "epoch": 4.9439918533604885, "percentage": 98.88, "elapsed_time": "1:31:23", "remaining_time": "0:01:02", "throughput": 10201.66, "total_tokens": 55945600}
{"current_steps": 58265, "total_steps": 58920, "loss": 0.0, "lr": 7.551135591944424e-10, "epoch": 4.944416157501697, "percentage": 98.89, "elapsed_time": "1:31:24", "remaining_time": "0:01:01", "throughput": 10201.79, "total_tokens": 55950144}
{"current_steps": 58270, "total_steps": 58920, "loss": 0.0, "lr": 7.436479708903265e-10, "epoch": 4.944840461642905, "percentage": 98.9, "elapsed_time": "1:31:24", "remaining_time": "0:01:01", "throughput": 10201.95, "total_tokens": 55955008}
{"current_steps": 58275, "total_steps": 58920, "loss": 0.0, "lr": 7.322700637232282e-10, "epoch": 4.945264765784114, "percentage": 98.91, "elapsed_time": "1:31:25", "remaining_time": "0:01:00", "throughput": 10202.21, "total_tokens": 55960512}
{"current_steps": 58280, "total_steps": 58920, "loss": 0.0, "lr": 7.209798386915711e-10, "epoch": 4.945689069925322, "percentage": 98.91, "elapsed_time": "1:31:25", "remaining_time": "0:01:00", "throughput": 10202.34, "total_tokens": 55965120}
{"current_steps": 58285, "total_steps": 58920, "loss": 0.0, "lr": 7.097772967861182e-10, "epoch": 4.946113374066531, "percentage": 98.92, "elapsed_time": "1:31:25", "remaining_time": "0:00:59", "throughput": 10202.46, "total_tokens": 55969600}
{"current_steps": 58290, "total_steps": 58920, "loss": 0.0, "lr": 6.98662438989861e-10, "epoch": 4.946537678207739, "percentage": 98.93, "elapsed_time": "1:31:26", "remaining_time": "0:00:59", "throughput": 10202.56, "total_tokens": 55973952}
{"current_steps": 58295, "total_steps": 58920, "loss": 0.0, "lr": 6.876352662779083e-10, "epoch": 4.946961982348948, "percentage": 98.94, "elapsed_time": "1:31:26", "remaining_time": "0:00:58", "throughput": 10202.71, "total_tokens": 55978624}
{"current_steps": 58300, "total_steps": 58920, "loss": 0.0, "lr": 6.766957796179307e-10, "epoch": 4.947386286490156, "percentage": 98.95, "elapsed_time": "1:31:27", "remaining_time": "0:00:58", "throughput": 10202.9, "total_tokens": 55983616}
{"current_steps": 58305, "total_steps": 58920, "loss": 0.0, "lr": 6.658439799699378e-10, "epoch": 4.947810590631365, "percentage": 98.96, "elapsed_time": "1:31:27", "remaining_time": "0:00:57", "throughput": 10203.07, "total_tokens": 55988416}
{"current_steps": 58310, "total_steps": 58920, "loss": 0.0, "lr": 6.550798682859459e-10, "epoch": 4.948234894772573, "percentage": 98.96, "elapsed_time": "1:31:27", "remaining_time": "0:00:57", "throughput": 10203.32, "total_tokens": 55993856}
{"current_steps": 58315, "total_steps": 58920, "loss": 0.0179, "lr": 6.44403445510755e-10, "epoch": 4.948659198913782, "percentage": 98.97, "elapsed_time": "1:31:28", "remaining_time": "0:00:56", "throughput": 10203.45, "total_tokens": 55998400}
{"current_steps": 58320, "total_steps": 58920, "loss": 0.0, "lr": 6.338147125808379e-10, "epoch": 4.94908350305499, "percentage": 98.98, "elapsed_time": "1:31:28", "remaining_time": "0:00:56", "throughput": 10203.59, "total_tokens": 56003008}
{"current_steps": 58325, "total_steps": 58920, "loss": 0.0, "lr": 6.233136704255626e-10, "epoch": 4.949507807196198, "percentage": 98.99, "elapsed_time": "1:31:28", "remaining_time": "0:00:55", "throughput": 10203.73, "total_tokens": 56007680}
{"current_steps": 58330, "total_steps": 58920, "loss": 0.0, "lr": 6.12900319966192e-10, "epoch": 4.949932111337406, "percentage": 99.0, "elapsed_time": "1:31:29", "remaining_time": "0:00:55", "throughput": 10203.95, "total_tokens": 56012864}
{"current_steps": 58335, "total_steps": 58920, "loss": 0.0, "lr": 6.025746621166616e-10, "epoch": 4.950356415478615, "percentage": 99.01, "elapsed_time": "1:31:29", "remaining_time": "0:00:55", "throughput": 10204.13, "total_tokens": 56017728}
{"current_steps": 58340, "total_steps": 58920, "loss": 0.0, "lr": 5.923366977828026e-10, "epoch": 4.950780719619823, "percentage": 99.02, "elapsed_time": "1:31:30", "remaining_time": "0:00:54", "throughput": 10204.3, "total_tokens": 56022528}
{"current_steps": 58345, "total_steps": 58920, "loss": 0.0, "lr": 5.821864278631183e-10, "epoch": 4.951205023761032, "percentage": 99.02, "elapsed_time": "1:31:30", "remaining_time": "0:00:54", "throughput": 10204.52, "total_tokens": 56027776}
{"current_steps": 58350, "total_steps": 58920, "loss": 0.0, "lr": 5.721238532482298e-10, "epoch": 4.95162932790224, "percentage": 99.03, "elapsed_time": "1:31:30", "remaining_time": "0:00:53", "throughput": 10204.66, "total_tokens": 56032384}
{"current_steps": 58355, "total_steps": 58920, "loss": 0.0, "lr": 5.621489748209862e-10, "epoch": 4.952053632043449, "percentage": 99.04, "elapsed_time": "1:31:31", "remaining_time": "0:00:53", "throughput": 10204.84, "total_tokens": 56037312}
{"current_steps": 58360, "total_steps": 58920, "loss": 0.0, "lr": 5.522617934566875e-10, "epoch": 4.952477936184657, "percentage": 99.05, "elapsed_time": "1:31:31", "remaining_time": "0:00:52", "throughput": 10204.93, "total_tokens": 56041600}
{"current_steps": 58365, "total_steps": 58920, "loss": 0.0, "lr": 5.42462310022973e-10, "epoch": 4.952902240325866, "percentage": 99.06, "elapsed_time": "1:31:31", "remaining_time": "0:00:52", "throughput": 10205.08, "total_tokens": 56046272}
{"current_steps": 58370, "total_steps": 58920, "loss": 0.0, "lr": 5.327505253795994e-10, "epoch": 4.953326544467074, "percentage": 99.07, "elapsed_time": "1:31:32", "remaining_time": "0:00:51", "throughput": 10205.33, "total_tokens": 56051712}
{"current_steps": 58375, "total_steps": 58920, "loss": 0.0, "lr": 5.231264403788849e-10, "epoch": 4.953750848608283, "percentage": 99.08, "elapsed_time": "1:31:32", "remaining_time": "0:00:51", "throughput": 10205.48, "total_tokens": 56056448}
{"current_steps": 58380, "total_steps": 58920, "loss": 0.0, "lr": 5.13590055865154e-10, "epoch": 4.954175152749491, "percentage": 99.08, "elapsed_time": "1:31:33", "remaining_time": "0:00:50", "throughput": 10205.61, "total_tokens": 56060992}
{"current_steps": 58385, "total_steps": 58920, "loss": 0.0, "lr": 5.04141372675293e-10, "epoch": 4.9545994568906995, "percentage": 99.09, "elapsed_time": "1:31:33", "remaining_time": "0:00:50", "throughput": 10205.82, "total_tokens": 56066112}
{"current_steps": 58390, "total_steps": 58920, "loss": 0.0, "lr": 4.947803916384164e-10, "epoch": 4.9550237610319074, "percentage": 99.1, "elapsed_time": "1:31:33", "remaining_time": "0:00:49", "throughput": 10205.99, "total_tokens": 56070976}
{"current_steps": 58395, "total_steps": 58920, "loss": 0.0, "lr": 4.855071135757561e-10, "epoch": 4.955448065173116, "percentage": 99.11, "elapsed_time": "1:31:34", "remaining_time": "0:00:49", "throughput": 10206.19, "total_tokens": 56076096}
{"current_steps": 58400, "total_steps": 58920, "loss": 0.0, "lr": 4.763215393012165e-10, "epoch": 4.955872369314324, "percentage": 99.12, "elapsed_time": "1:31:34", "remaining_time": "0:00:48", "throughput": 10206.3, "total_tokens": 56080512}
{"current_steps": 58405, "total_steps": 58920, "loss": 0.0, "lr": 4.672236696205978e-10, "epoch": 4.956296673455533, "percentage": 99.13, "elapsed_time": "1:31:35", "remaining_time": "0:00:48", "throughput": 10206.43, "total_tokens": 56085056}
{"current_steps": 58410, "total_steps": 58920, "loss": 0.0, "lr": 4.5821350533237214e-10, "epoch": 4.956720977596741, "percentage": 99.13, "elapsed_time": "1:31:35", "remaining_time": "0:00:47", "throughput": 10206.55, "total_tokens": 56089536}
{"current_steps": 58415, "total_steps": 58920, "loss": 0.0, "lr": 4.492910472271294e-10, "epoch": 4.95714528173795, "percentage": 99.14, "elapsed_time": "1:31:35", "remaining_time": "0:00:47", "throughput": 10206.66, "total_tokens": 56093952}
{"current_steps": 58420, "total_steps": 58920, "loss": 0.0, "lr": 4.4045629608757685e-10, "epoch": 4.957569585879158, "percentage": 99.15, "elapsed_time": "1:31:36", "remaining_time": "0:00:47", "throughput": 10206.8, "total_tokens": 56098624}
{"current_steps": 58425, "total_steps": 58920, "loss": 0.0, "lr": 4.3170925268920524e-10, "epoch": 4.957993890020367, "percentage": 99.16, "elapsed_time": "1:31:36", "remaining_time": "0:00:46", "throughput": 10207.01, "total_tokens": 56103808}
{"current_steps": 58430, "total_steps": 58920, "loss": 0.0, "lr": 4.230499177994007e-10, "epoch": 4.958418194161575, "percentage": 99.17, "elapsed_time": "1:31:36", "remaining_time": "0:00:46", "throughput": 10207.17, "total_tokens": 56108608}
{"current_steps": 58435, "total_steps": 58920, "loss": 0.0, "lr": 4.144782921779999e-10, "epoch": 4.958842498302784, "percentage": 99.18, "elapsed_time": "1:31:37", "remaining_time": "0:00:45", "throughput": 10207.39, "total_tokens": 56113792}
{"current_steps": 58440, "total_steps": 58920, "loss": 0.0, "lr": 4.059943765771789e-10, "epoch": 4.959266802443992, "percentage": 99.19, "elapsed_time": "1:31:37", "remaining_time": "0:00:45", "throughput": 10207.63, "total_tokens": 56119168}
{"current_steps": 58445, "total_steps": 58920, "loss": 0.0, "lr": 3.9759817174123134e-10, "epoch": 4.9596911065852005, "percentage": 99.19, "elapsed_time": "1:31:38", "remaining_time": "0:00:44", "throughput": 10207.88, "total_tokens": 56124608}
{"current_steps": 58450, "total_steps": 58920, "loss": 0.0, "lr": 3.8928967840712314e-10, "epoch": 4.9601154107264085, "percentage": 99.2, "elapsed_time": "1:31:38", "remaining_time": "0:00:44", "throughput": 10208.01, "total_tokens": 56129216}
{"current_steps": 58455, "total_steps": 58920, "loss": 0.0, "lr": 3.8106889730371574e-10, "epoch": 4.960539714867617, "percentage": 99.21, "elapsed_time": "1:31:38", "remaining_time": "0:00:43", "throughput": 10208.15, "total_tokens": 56133760}
{"current_steps": 58460, "total_steps": 58920, "loss": 0.0, "lr": 3.72935829152321e-10, "epoch": 4.960964019008825, "percentage": 99.22, "elapsed_time": "1:31:39", "remaining_time": "0:00:43", "throughput": 10208.28, "total_tokens": 56138368}
{"current_steps": 58465, "total_steps": 58920, "loss": 0.0, "lr": 3.6489047466681244e-10, "epoch": 4.961388323150034, "percentage": 99.23, "elapsed_time": "1:31:39", "remaining_time": "0:00:42", "throughput": 10208.42, "total_tokens": 56142976}
{"current_steps": 58470, "total_steps": 58920, "loss": 0.0, "lr": 3.569328345528477e-10, "epoch": 4.961812627291242, "percentage": 99.24, "elapsed_time": "1:31:40", "remaining_time": "0:00:42", "throughput": 10208.6, "total_tokens": 56147904}
{"current_steps": 58475, "total_steps": 58920, "loss": 0.0, "lr": 3.490629095089792e-10, "epoch": 4.962236931432451, "percentage": 99.24, "elapsed_time": "1:31:40", "remaining_time": "0:00:41", "throughput": 10208.8, "total_tokens": 56152960}
{"current_steps": 58480, "total_steps": 58920, "loss": 0.0, "lr": 3.4128070022554356e-10, "epoch": 4.962661235573659, "percentage": 99.25, "elapsed_time": "1:31:40", "remaining_time": "0:00:41", "throughput": 10208.92, "total_tokens": 56157440}
{"current_steps": 58485, "total_steps": 58920, "loss": 0.0, "lr": 3.3358620738543894e-10, "epoch": 4.963085539714868, "percentage": 99.26, "elapsed_time": "1:31:41", "remaining_time": "0:00:40", "throughput": 10209.1, "total_tokens": 56162368}
{"current_steps": 58490, "total_steps": 58920, "loss": 0.0, "lr": 3.2597943166390305e-10, "epoch": 4.963509843856076, "percentage": 99.27, "elapsed_time": "1:31:41", "remaining_time": "0:00:40", "throughput": 10209.22, "total_tokens": 56166848}
{"current_steps": 58495, "total_steps": 58920, "loss": 0.0, "lr": 3.1846037372829094e-10, "epoch": 4.963934147997285, "percentage": 99.28, "elapsed_time": "1:31:41", "remaining_time": "0:00:39", "throughput": 10209.43, "total_tokens": 56171968}
{"current_steps": 58500, "total_steps": 58920, "loss": 0.0, "lr": 3.1102903423851914e-10, "epoch": 4.964358452138493, "percentage": 99.29, "elapsed_time": "1:31:42", "remaining_time": "0:00:39", "throughput": 10209.55, "total_tokens": 56176448}
{"current_steps": 58505, "total_steps": 58920, "loss": 0.0, "lr": 3.036854138466216e-10, "epoch": 4.964782756279702, "percentage": 99.3, "elapsed_time": "1:31:42", "remaining_time": "0:00:39", "throughput": 10209.71, "total_tokens": 56181248}
{"current_steps": 58510, "total_steps": 58920, "loss": 0.0, "lr": 2.964295131968608e-10, "epoch": 4.9652070604209095, "percentage": 99.3, "elapsed_time": "1:31:43", "remaining_time": "0:00:38", "throughput": 10209.93, "total_tokens": 56186496}
{"current_steps": 58515, "total_steps": 58920, "loss": 0.0, "lr": 2.892613329260607e-10, "epoch": 4.965631364562118, "percentage": 99.31, "elapsed_time": "1:31:43", "remaining_time": "0:00:38", "throughput": 10210.1, "total_tokens": 56191424}
{"current_steps": 58520, "total_steps": 58920, "loss": 0.0, "lr": 2.821808736630515e-10, "epoch": 4.966055668703326, "percentage": 99.32, "elapsed_time": "1:31:43", "remaining_time": "0:00:37", "throughput": 10210.25, "total_tokens": 56196160}
{"current_steps": 58525, "total_steps": 58920, "loss": 0.0, "lr": 2.751881360292252e-10, "epoch": 4.966479972844535, "percentage": 99.33, "elapsed_time": "1:31:44", "remaining_time": "0:00:37", "throughput": 10210.38, "total_tokens": 56200704}
{"current_steps": 58530, "total_steps": 58920, "loss": 0.0, "lr": 2.682831206382019e-10, "epoch": 4.966904276985743, "percentage": 99.34, "elapsed_time": "1:31:44", "remaining_time": "0:00:36", "throughput": 10210.51, "total_tokens": 56205248}
{"current_steps": 58535, "total_steps": 58920, "loss": 0.0, "lr": 2.614658280958304e-10, "epoch": 4.967328581126952, "percentage": 99.35, "elapsed_time": "1:31:45", "remaining_time": "0:00:36", "throughput": 10210.59, "total_tokens": 56209536}
{"current_steps": 58540, "total_steps": 58920, "loss": 0.0, "lr": 2.547362590001878e-10, "epoch": 4.96775288526816, "percentage": 99.36, "elapsed_time": "1:31:45", "remaining_time": "0:00:35", "throughput": 10210.72, "total_tokens": 56214144}
{"current_steps": 58545, "total_steps": 58920, "loss": 0.0, "lr": 2.480944139420238e-10, "epoch": 4.968177189409369, "percentage": 99.36, "elapsed_time": "1:31:45", "remaining_time": "0:00:35", "throughput": 10210.92, "total_tokens": 56219200}
{"current_steps": 58550, "total_steps": 58920, "loss": 0.0, "lr": 2.4154029350387237e-10, "epoch": 4.968601493550577, "percentage": 99.37, "elapsed_time": "1:31:46", "remaining_time": "0:00:34", "throughput": 10211.05, "total_tokens": 56223744}
{"current_steps": 58555, "total_steps": 58920, "loss": 0.0, "lr": 2.3507389826094013e-10, "epoch": 4.969025797691786, "percentage": 99.38, "elapsed_time": "1:31:46", "remaining_time": "0:00:34", "throughput": 10211.23, "total_tokens": 56228608}
{"current_steps": 58560, "total_steps": 58920, "loss": 0.0, "lr": 2.2869522878066205e-10, "epoch": 4.969450101832994, "percentage": 99.39, "elapsed_time": "1:31:46", "remaining_time": "0:00:33", "throughput": 10211.37, "total_tokens": 56233280}
{"current_steps": 58565, "total_steps": 58920, "loss": 0.0, "lr": 2.2240428562281255e-10, "epoch": 4.969874405974203, "percentage": 99.4, "elapsed_time": "1:31:47", "remaining_time": "0:00:33", "throughput": 10211.53, "total_tokens": 56238016}
{"current_steps": 58570, "total_steps": 58920, "loss": 0.0, "lr": 2.162010693391725e-10, "epoch": 4.970298710115411, "percentage": 99.41, "elapsed_time": "1:31:47", "remaining_time": "0:00:32", "throughput": 10211.65, "total_tokens": 56242496}
{"current_steps": 58575, "total_steps": 58920, "loss": 0.0, "lr": 2.1008558047419522e-10, "epoch": 4.970723014256619, "percentage": 99.41, "elapsed_time": "1:31:48", "remaining_time": "0:00:32", "throughput": 10211.81, "total_tokens": 56247296}
{"current_steps": 58580, "total_steps": 58920, "loss": 0.0, "lr": 2.0405781956456259e-10, "epoch": 4.971147318397827, "percentage": 99.42, "elapsed_time": "1:31:48", "remaining_time": "0:00:31", "throughput": 10211.92, "total_tokens": 56251712}
{"current_steps": 58585, "total_steps": 58920, "loss": 0.0, "lr": 1.9811778713907378e-10, "epoch": 4.971571622539036, "percentage": 99.43, "elapsed_time": "1:31:48", "remaining_time": "0:00:31", "throughput": 10212.07, "total_tokens": 56256512}
{"current_steps": 58590, "total_steps": 58920, "loss": 0.0, "lr": 1.9226548371897855e-10, "epoch": 4.971995926680244, "percentage": 99.44, "elapsed_time": "1:31:49", "remaining_time": "0:00:31", "throughput": 10212.13, "total_tokens": 56260608}
{"current_steps": 58595, "total_steps": 58920, "loss": 0.0, "lr": 1.8650090981775502e-10, "epoch": 4.972420230821453, "percentage": 99.45, "elapsed_time": "1:31:49", "remaining_time": "0:00:30", "throughput": 10212.26, "total_tokens": 56265152}
{"current_steps": 58600, "total_steps": 58920, "loss": 0.0, "lr": 1.808240659412208e-10, "epoch": 4.972844534962661, "percentage": 99.46, "elapsed_time": "1:31:49", "remaining_time": "0:00:30", "throughput": 10212.49, "total_tokens": 56270464}
{"current_steps": 58605, "total_steps": 58920, "loss": 0.0, "lr": 1.7523495258764398e-10, "epoch": 4.97326883910387, "percentage": 99.47, "elapsed_time": "1:31:50", "remaining_time": "0:00:29", "throughput": 10212.57, "total_tokens": 56274624}
{"current_steps": 58610, "total_steps": 58920, "loss": 0.0, "lr": 1.6973357024729906e-10, "epoch": 4.973693143245078, "percentage": 99.47, "elapsed_time": "1:31:50", "remaining_time": "0:00:29", "throughput": 10212.73, "total_tokens": 56279424}
{"current_steps": 58615, "total_steps": 58920, "loss": 0.0, "lr": 1.6431991940302203e-10, "epoch": 4.974117447386287, "percentage": 99.48, "elapsed_time": "1:31:51", "remaining_time": "0:00:28", "throughput": 10212.89, "total_tokens": 56284224}
{"current_steps": 58620, "total_steps": 58920, "loss": 0.0, "lr": 1.589940005297663e-10, "epoch": 4.974541751527495, "percentage": 99.49, "elapsed_time": "1:31:51", "remaining_time": "0:00:28", "throughput": 10213.0, "total_tokens": 56288704}
{"current_steps": 58625, "total_steps": 58920, "loss": 0.0, "lr": 1.5375581409482475e-10, "epoch": 4.974966055668704, "percentage": 99.5, "elapsed_time": "1:31:51", "remaining_time": "0:00:27", "throughput": 10213.1, "total_tokens": 56293056}
{"current_steps": 58630, "total_steps": 58920, "loss": 0.0, "lr": 1.486053605578297e-10, "epoch": 4.975390359809912, "percentage": 99.51, "elapsed_time": "1:31:52", "remaining_time": "0:00:27", "throughput": 10213.19, "total_tokens": 56297344}
{"current_steps": 58635, "total_steps": 58920, "loss": 0.0, "lr": 1.4354264037086395e-10, "epoch": 4.9758146639511205, "percentage": 99.52, "elapsed_time": "1:31:52", "remaining_time": "0:00:26", "throughput": 10213.37, "total_tokens": 56302336}
{"current_steps": 58640, "total_steps": 58920, "loss": 0.0, "lr": 1.3856765397801674e-10, "epoch": 4.9762389680923285, "percentage": 99.52, "elapsed_time": "1:31:52", "remaining_time": "0:00:26", "throughput": 10213.5, "total_tokens": 56306880}
{"current_steps": 58645, "total_steps": 58920, "loss": 0.0, "lr": 1.3368040181593875e-10, "epoch": 4.976663272233537, "percentage": 99.53, "elapsed_time": "1:31:53", "remaining_time": "0:00:25", "throughput": 10213.58, "total_tokens": 56311040}
{"current_steps": 58650, "total_steps": 58920, "loss": 0.0, "lr": 1.2888088431328715e-10, "epoch": 4.977087576374745, "percentage": 99.54, "elapsed_time": "1:31:53", "remaining_time": "0:00:25", "throughput": 10213.7, "total_tokens": 56315648}
{"current_steps": 58655, "total_steps": 58920, "loss": 0.0, "lr": 1.241691018913915e-10, "epoch": 4.977511880515954, "percentage": 99.55, "elapsed_time": "1:31:54", "remaining_time": "0:00:24", "throughput": 10213.88, "total_tokens": 56320448}
{"current_steps": 58660, "total_steps": 58920, "loss": 0.0, "lr": 1.1954505496369893e-10, "epoch": 4.977936184657162, "percentage": 99.56, "elapsed_time": "1:31:54", "remaining_time": "0:00:24", "throughput": 10213.96, "total_tokens": 56324672}
{"current_steps": 58665, "total_steps": 58920, "loss": 0.0, "lr": 1.1500874393577387e-10, "epoch": 4.978360488798371, "percentage": 99.57, "elapsed_time": "1:31:54", "remaining_time": "0:00:23", "throughput": 10214.21, "total_tokens": 56330176}
{"current_steps": 58670, "total_steps": 58920, "loss": 0.0, "lr": 1.105601692057423e-10, "epoch": 4.978784792939579, "percentage": 99.58, "elapsed_time": "1:31:55", "remaining_time": "0:00:23", "throughput": 10214.38, "total_tokens": 56335040}
{"current_steps": 58675, "total_steps": 58920, "loss": 0.0, "lr": 1.0619933116395862e-10, "epoch": 4.979209097080788, "percentage": 99.58, "elapsed_time": "1:31:55", "remaining_time": "0:00:23", "throughput": 10214.46, "total_tokens": 56339264}
{"current_steps": 58680, "total_steps": 58920, "loss": 0.0, "lr": 1.0192623019311675e-10, "epoch": 4.979633401221996, "percentage": 99.59, "elapsed_time": "1:31:56", "remaining_time": "0:00:22", "throughput": 10214.59, "total_tokens": 56343808}
{"current_steps": 58685, "total_steps": 58920, "loss": 0.0, "lr": 9.774086666813897e-11, "epoch": 4.980057705363205, "percentage": 99.6, "elapsed_time": "1:31:56", "remaining_time": "0:00:22", "throughput": 10214.75, "total_tokens": 56348672}
{"current_steps": 58690, "total_steps": 58920, "loss": 0.0, "lr": 9.364324095628706e-11, "epoch": 4.980482009504413, "percentage": 99.61, "elapsed_time": "1:31:56", "remaining_time": "0:00:21", "throughput": 10214.95, "total_tokens": 56353728}
{"current_steps": 58695, "total_steps": 58920, "loss": 0.0, "lr": 8.963335341705125e-11, "epoch": 4.9809063136456215, "percentage": 99.62, "elapsed_time": "1:31:57", "remaining_time": "0:00:21", "throughput": 10215.04, "total_tokens": 56358016}
{"current_steps": 58700, "total_steps": 58920, "loss": 0.0, "lr": 8.571120440237223e-11, "epoch": 4.9813306177868295, "percentage": 99.63, "elapsed_time": "1:31:57", "remaining_time": "0:00:20", "throughput": 10215.14, "total_tokens": 56362432}
{"current_steps": 58705, "total_steps": 58920, "loss": 0.0, "lr": 8.187679425630811e-11, "epoch": 4.981754921928038, "percentage": 99.64, "elapsed_time": "1:31:57", "remaining_time": "0:00:20", "throughput": 10215.37, "total_tokens": 56367680}
{"current_steps": 58710, "total_steps": 58920, "loss": 0.0, "lr": 7.813012331547852e-11, "epoch": 4.982179226069246, "percentage": 99.64, "elapsed_time": "1:31:58", "remaining_time": "0:00:19", "throughput": 10215.48, "total_tokens": 56372096}
{"current_steps": 58715, "total_steps": 58920, "loss": 0.0, "lr": 7.447119190839845e-11, "epoch": 4.982603530210455, "percentage": 99.65, "elapsed_time": "1:31:58", "remaining_time": "0:00:19", "throughput": 10215.59, "total_tokens": 56376512}
{"current_steps": 58720, "total_steps": 58920, "loss": 0.0, "lr": 7.090000035625543e-11, "epoch": 4.983027834351663, "percentage": 99.66, "elapsed_time": "1:31:59", "remaining_time": "0:00:18", "throughput": 10215.79, "total_tokens": 56381568}
{"current_steps": 58725, "total_steps": 58920, "loss": 0.0, "lr": 6.741654897246541e-11, "epoch": 4.983452138492872, "percentage": 99.67, "elapsed_time": "1:31:59", "remaining_time": "0:00:18", "throughput": 10216.05, "total_tokens": 56387072}
{"current_steps": 58730, "total_steps": 58920, "loss": 0.0, "lr": 6.402083806267278e-11, "epoch": 4.98387644263408, "percentage": 99.68, "elapsed_time": "1:31:59", "remaining_time": "0:00:17", "throughput": 10216.15, "total_tokens": 56391424}
{"current_steps": 58735, "total_steps": 58920, "loss": 0.0, "lr": 6.071286792475039e-11, "epoch": 4.984300746775289, "percentage": 99.69, "elapsed_time": "1:32:00", "remaining_time": "0:00:17", "throughput": 10216.3, "total_tokens": 56396096}
{"current_steps": 58740, "total_steps": 58920, "loss": 0.0, "lr": 5.7492638848910535e-11, "epoch": 4.984725050916497, "percentage": 99.69, "elapsed_time": "1:32:00", "remaining_time": "0:00:16", "throughput": 10216.48, "total_tokens": 56401024}
{"current_steps": 58745, "total_steps": 58920, "loss": 0.0, "lr": 5.436015111792702e-11, "epoch": 4.985149355057706, "percentage": 99.7, "elapsed_time": "1:32:00", "remaining_time": "0:00:16", "throughput": 10216.67, "total_tokens": 56406080}
{"current_steps": 58750, "total_steps": 58920, "loss": 0.0, "lr": 5.131540500658005e-11, "epoch": 4.985573659198914, "percentage": 99.71, "elapsed_time": "1:32:01", "remaining_time": "0:00:15", "throughput": 10217.0, "total_tokens": 56412096}
{"current_steps": 58755, "total_steps": 58920, "loss": 0.0, "lr": 4.835840078187825e-11, "epoch": 4.985997963340123, "percentage": 99.72, "elapsed_time": "1:32:01", "remaining_time": "0:00:15", "throughput": 10217.16, "total_tokens": 56416832}
{"current_steps": 58760, "total_steps": 58920, "loss": 0.0, "lr": 4.548913870350279e-11, "epoch": 4.9864222674813306, "percentage": 99.73, "elapsed_time": "1:32:02", "remaining_time": "0:00:15", "throughput": 10217.23, "total_tokens": 56421056}
{"current_steps": 58765, "total_steps": 58920, "loss": 0.0, "lr": 4.270761902314124e-11, "epoch": 4.986846571622539, "percentage": 99.74, "elapsed_time": "1:32:02", "remaining_time": "0:00:14", "throughput": 10217.42, "total_tokens": 56426112}
{"current_steps": 58770, "total_steps": 58920, "loss": 0.0, "lr": 4.001384198482061e-11, "epoch": 4.987270875763747, "percentage": 99.75, "elapsed_time": "1:32:02", "remaining_time": "0:00:14", "throughput": 10217.53, "total_tokens": 56430528}
{"current_steps": 58775, "total_steps": 58920, "loss": 0.0, "lr": 3.7407807824907375e-11, "epoch": 4.987695179904956, "percentage": 99.75, "elapsed_time": "1:32:03", "remaining_time": "0:00:13", "throughput": 10217.64, "total_tokens": 56434944}
{"current_steps": 58780, "total_steps": 58920, "loss": 0.0, "lr": 3.488951677221852e-11, "epoch": 4.988119484046164, "percentage": 99.76, "elapsed_time": "1:32:03", "remaining_time": "0:00:13", "throughput": 10217.77, "total_tokens": 56439488}
{"current_steps": 58785, "total_steps": 58920, "loss": 0.0, "lr": 3.245896904757739e-11, "epoch": 4.988543788187373, "percentage": 99.77, "elapsed_time": "1:32:04", "remaining_time": "0:00:12", "throughput": 10217.92, "total_tokens": 56444224}
{"current_steps": 58790, "total_steps": 58920, "loss": 0.0, "lr": 3.011616486425783e-11, "epoch": 4.988968092328581, "percentage": 99.78, "elapsed_time": "1:32:04", "remaining_time": "0:00:12", "throughput": 10218.11, "total_tokens": 56449152}
{"current_steps": 58795, "total_steps": 58920, "loss": 0.0, "lr": 2.786110442787315e-11, "epoch": 4.989392396469789, "percentage": 99.79, "elapsed_time": "1:32:04", "remaining_time": "0:00:11", "throughput": 10218.32, "total_tokens": 56454336}
{"current_steps": 58800, "total_steps": 58920, "loss": 0.0, "lr": 2.5693787936265087e-11, "epoch": 4.989816700610998, "percentage": 99.8, "elapsed_time": "1:32:05", "remaining_time": "0:00:11", "throughput": 10218.5, "total_tokens": 56459264}
{"current_steps": 58805, "total_steps": 58920, "loss": 0.0, "lr": 2.3614215579614848e-11, "epoch": 4.990241004752207, "percentage": 99.8, "elapsed_time": "1:32:05", "remaining_time": "0:00:10", "throughput": 10218.7, "total_tokens": 56464384}
{"current_steps": 58810, "total_steps": 58920, "loss": 0.0, "lr": 2.162238754055412e-11, "epoch": 4.990665308893415, "percentage": 99.81, "elapsed_time": "1:32:05", "remaining_time": "0:00:10", "throughput": 10218.89, "total_tokens": 56469376}
{"current_steps": 58815, "total_steps": 58920, "loss": 0.0, "lr": 1.9718303993609963e-11, "epoch": 4.991089613034623, "percentage": 99.82, "elapsed_time": "1:32:06", "remaining_time": "0:00:09", "throughput": 10219.03, "total_tokens": 56474048}
{"current_steps": 58820, "total_steps": 58920, "loss": 0.0, "lr": 1.7901965105981965e-11, "epoch": 4.991513917175832, "percentage": 99.83, "elapsed_time": "1:32:06", "remaining_time": "0:00:09", "throughput": 10219.11, "total_tokens": 56478272}
{"current_steps": 58825, "total_steps": 58920, "loss": 0.0, "lr": 1.6173371036987127e-11, "epoch": 4.9919382213170405, "percentage": 99.84, "elapsed_time": "1:32:07", "remaining_time": "0:00:08", "throughput": 10219.24, "total_tokens": 56482880}
{"current_steps": 58830, "total_steps": 58920, "loss": 0.0, "lr": 1.4532521938503961e-11, "epoch": 4.992362525458248, "percentage": 99.85, "elapsed_time": "1:32:07", "remaining_time": "0:00:08", "throughput": 10219.66, "total_tokens": 56489536}
{"current_steps": 58835, "total_steps": 58920, "loss": 0.0, "lr": 1.2979417954195326e-11, "epoch": 4.992786829599456, "percentage": 99.86, "elapsed_time": "1:32:07", "remaining_time": "0:00:07", "throughput": 10219.74, "total_tokens": 56493824}
{"current_steps": 58840, "total_steps": 58920, "loss": 0.0, "lr": 1.1514059220618654e-11, "epoch": 4.993211133740665, "percentage": 99.86, "elapsed_time": "1:32:08", "remaining_time": "0:00:07", "throughput": 10219.93, "total_tokens": 56498880}
{"current_steps": 58845, "total_steps": 58920, "loss": 0.0, "lr": 1.013644586622675e-11, "epoch": 4.993635437881874, "percentage": 99.87, "elapsed_time": "1:32:08", "remaining_time": "0:00:07", "throughput": 10220.11, "total_tokens": 56503808}
{"current_steps": 58850, "total_steps": 58920, "loss": 0.0, "lr": 8.846578011811878e-12, "epoch": 4.994059742023082, "percentage": 99.88, "elapsed_time": "1:32:09", "remaining_time": "0:00:06", "throughput": 10220.3, "total_tokens": 56508864}
{"current_steps": 58855, "total_steps": 58920, "loss": 0.0, "lr": 7.644455770727809e-12, "epoch": 4.99448404616429, "percentage": 99.89, "elapsed_time": "1:32:09", "remaining_time": "0:00:06", "throughput": 10220.42, "total_tokens": 56513344}
{"current_steps": 58860, "total_steps": 58920, "loss": 0.0, "lr": 6.5300792484457304e-12, "epoch": 4.994908350305499, "percentage": 99.9, "elapsed_time": "1:32:09", "remaining_time": "0:00:05", "throughput": 10220.54, "total_tokens": 56517888}
{"current_steps": 58865, "total_steps": 58920, "loss": 0.0, "lr": 5.503448542554245e-12, "epoch": 4.995332654446708, "percentage": 99.91, "elapsed_time": "1:32:10", "remaining_time": "0:00:05", "throughput": 10220.67, "total_tokens": 56522432}
{"current_steps": 58870, "total_steps": 58920, "loss": 0.0, "lr": 4.564563743314487e-12, "epoch": 4.995756958587916, "percentage": 99.92, "elapsed_time": "1:32:10", "remaining_time": "0:00:04", "throughput": 10220.83, "total_tokens": 56527232}
{"current_steps": 58875, "total_steps": 58920, "loss": 0.0, "lr": 3.713424933105003e-12, "epoch": 4.996181262729124, "percentage": 99.92, "elapsed_time": "1:32:10", "remaining_time": "0:00:04", "throughput": 10221.05, "total_tokens": 56532480}
{"current_steps": 58880, "total_steps": 58920, "loss": 0.0, "lr": 2.9500321866438028e-12, "epoch": 4.996605566870333, "percentage": 99.93, "elapsed_time": "1:32:11", "remaining_time": "0:00:03", "throughput": 10221.16, "total_tokens": 56536960}
{"current_steps": 58885, "total_steps": 58920, "loss": 0.0, "lr": 2.2743855706552906e-12, "epoch": 4.9970298710115415, "percentage": 99.94, "elapsed_time": "1:32:11", "remaining_time": "0:00:03", "throughput": 10221.31, "total_tokens": 56541696}
{"current_steps": 58890, "total_steps": 58920, "loss": 0.0, "lr": 1.6864851447584427e-12, "epoch": 4.9974541751527495, "percentage": 99.95, "elapsed_time": "1:32:12", "remaining_time": "0:00:02", "throughput": 10221.43, "total_tokens": 56546176}
{"current_steps": 58895, "total_steps": 58920, "loss": 0.0, "lr": 1.1863309603565852e-12, "epoch": 4.9978784792939575, "percentage": 99.96, "elapsed_time": "1:32:12", "remaining_time": "0:00:02", "throughput": 10221.59, "total_tokens": 56550912}
{"current_steps": 58900, "total_steps": 58920, "loss": 0.0, "lr": 7.739230613035274e-13, "epoch": 4.998302783435166, "percentage": 99.97, "elapsed_time": "1:32:12", "remaining_time": "0:00:01", "throughput": 10221.79, "total_tokens": 56556032}
{"current_steps": 58905, "total_steps": 58920, "loss": 0.0, "lr": 4.4926148401458477e-13, "epoch": 4.998727087576375, "percentage": 99.97, "elapsed_time": "1:32:13", "remaining_time": "0:00:01", "throughput": 10221.95, "total_tokens": 56560768}
{"current_steps": 58910, "total_steps": 58920, "loss": 0.0, "lr": 2.1234625668942186e-13, "epoch": 4.999151391717583, "percentage": 99.98, "elapsed_time": "1:32:13", "remaining_time": "0:00:00", "throughput": 10222.12, "total_tokens": 56565568}
{"current_steps": 58915, "total_steps": 58920, "loss": 0.0, "lr": 6.317740020023166e-14, "epoch": 4.999575695858791, "percentage": 99.99, "elapsed_time": "1:32:14", "remaining_time": "0:00:00", "throughput": 10222.21, "total_tokens": 56569984}
{"current_steps": 58920, "total_steps": 58920, "loss": 0.0, "lr": 1.7549277586681455e-15, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "1:32:14", "remaining_time": "0:00:00", "throughput": 10222.23, "total_tokens": 56574368}
{"current_steps": 58920, "total_steps": 58920, "eval_loss": 0.17537885904312134, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "1:32:30", "remaining_time": "0:00:00", "throughput": 10191.96, "total_tokens": 56574368}
{"current_steps": 58920, "total_steps": 58920, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "1:33:22", "remaining_time": "0:00:00", "throughput": 10098.44, "total_tokens": 56574368}