Files
train_qnli_42_1779286680/trainer_log.jsonl
ModelHub XC cfa4b7785e 初始化项目,由ModelHub XC社区提供模型
Model: rbelanec/train_qnli_42_1779286680
Source: Original Platform
2026-06-08 05:31:17 +08:00

2377 lines
569 KiB
JSON

{"current_steps": 5, "total_steps": 11784, "loss": 0.8772, "lr": 6.785411365564037e-09, "epoch": 0.0004243041412084182, "percentage": 0.04, "elapsed_time": "0:00:00", "remaining_time": "0:38:31", "throughput": 5087.73, "total_tokens": 4992}
{"current_steps": 10, "total_steps": 11784, "loss": 0.958, "lr": 1.526717557251908e-08, "epoch": 0.0008486082824168364, "percentage": 0.08, "elapsed_time": "0:00:01", "remaining_time": "0:25:54", "throughput": 7223.24, "total_tokens": 9536}
{"current_steps": 15, "total_steps": 11784, "loss": 0.8691, "lr": 2.374893977947413e-08, "epoch": 0.0012729124236252546, "percentage": 0.13, "elapsed_time": "0:00:01", "remaining_time": "0:21:38", "throughput": 8468.76, "total_tokens": 14016}
{"current_steps": 20, "total_steps": 11784, "loss": 0.8723, "lr": 3.223070398642917e-08, "epoch": 0.0016972165648336728, "percentage": 0.17, "elapsed_time": "0:00:02", "remaining_time": "0:19:48", "throughput": 9726.9, "total_tokens": 19648}
{"current_steps": 25, "total_steps": 11784, "loss": 0.8359, "lr": 4.0712468193384224e-08, "epoch": 0.002121520706042091, "percentage": 0.21, "elapsed_time": "0:00:02", "remaining_time": "0:18:28", "throughput": 10511.73, "total_tokens": 24768}
{"current_steps": 30, "total_steps": 11784, "loss": 0.8734, "lr": 4.919423240033927e-08, "epoch": 0.0025458248472505093, "percentage": 0.25, "elapsed_time": "0:00:02", "remaining_time": "0:17:46", "throughput": 11007.6, "total_tokens": 29952}
{"current_steps": 35, "total_steps": 11784, "loss": 0.8972, "lr": 5.767599660729432e-08, "epoch": 0.0029701289884589274, "percentage": 0.3, "elapsed_time": "0:00:03", "remaining_time": "0:17:03", "throughput": 11251.94, "total_tokens": 34304}
{"current_steps": 40, "total_steps": 11784, "loss": 0.8139, "lr": 6.615776081424935e-08, "epoch": 0.0033944331296673455, "percentage": 0.34, "elapsed_time": "0:00:03", "remaining_time": "0:16:34", "throughput": 11618.27, "total_tokens": 39360}
{"current_steps": 45, "total_steps": 11784, "loss": 0.8369, "lr": 7.463952502120441e-08, "epoch": 0.0038187372708757637, "percentage": 0.38, "elapsed_time": "0:00:03", "remaining_time": "0:16:12", "throughput": 11934.21, "total_tokens": 44480}
{"current_steps": 50, "total_steps": 11784, "loss": 0.6877, "lr": 8.312128922815945e-08, "epoch": 0.004243041412084182, "percentage": 0.42, "elapsed_time": "0:00:04", "remaining_time": "0:15:52", "throughput": 12107.61, "total_tokens": 49152}
{"current_steps": 55, "total_steps": 11784, "loss": 0.5185, "lr": 9.16030534351145e-08, "epoch": 0.0046673455532926, "percentage": 0.47, "elapsed_time": "0:00:04", "remaining_time": "0:15:39", "throughput": 12192.19, "total_tokens": 53696}
{"current_steps": 60, "total_steps": 11784, "loss": 0.4927, "lr": 1.0008481764206955e-07, "epoch": 0.0050916496945010185, "percentage": 0.51, "elapsed_time": "0:00:04", "remaining_time": "0:15:25", "throughput": 12361.33, "total_tokens": 58560}
{"current_steps": 65, "total_steps": 11784, "loss": 0.4352, "lr": 1.085665818490246e-07, "epoch": 0.005515953835709436, "percentage": 0.55, "elapsed_time": "0:00:05", "remaining_time": "0:15:16", "throughput": 12550.24, "total_tokens": 63808}
{"current_steps": 70, "total_steps": 11784, "loss": 0.3313, "lr": 1.1704834605597964e-07, "epoch": 0.005940257976917855, "percentage": 0.59, "elapsed_time": "0:00:05", "remaining_time": "0:15:05", "throughput": 12588.78, "total_tokens": 68096}
{"current_steps": 75, "total_steps": 11784, "loss": 0.2376, "lr": 1.2553011026293469e-07, "epoch": 0.006364562118126273, "percentage": 0.64, "elapsed_time": "0:00:05", "remaining_time": "0:14:54", "throughput": 12646.43, "total_tokens": 72448}
{"current_steps": 80, "total_steps": 11784, "loss": 0.2135, "lr": 1.3401187446988974e-07, "epoch": 0.006788866259334691, "percentage": 0.68, "elapsed_time": "0:00:06", "remaining_time": "0:14:50", "throughput": 12867.12, "total_tokens": 78336}
{"current_steps": 85, "total_steps": 11784, "loss": 0.165, "lr": 1.4249363867684477e-07, "epoch": 0.00721317040054311, "percentage": 0.72, "elapsed_time": "0:00:06", "remaining_time": "0:14:43", "throughput": 12946.56, "total_tokens": 83072}
{"current_steps": 90, "total_steps": 11784, "loss": 0.1788, "lr": 1.509754028837998e-07, "epoch": 0.007637474541751527, "percentage": 0.76, "elapsed_time": "0:00:06", "remaining_time": "0:14:39", "throughput": 13022.88, "total_tokens": 88128}
{"current_steps": 95, "total_steps": 11784, "loss": 0.1682, "lr": 1.594571670907549e-07, "epoch": 0.008061778682959946, "percentage": 0.81, "elapsed_time": "0:00:07", "remaining_time": "0:14:33", "throughput": 13091.5, "total_tokens": 92992}
{"current_steps": 100, "total_steps": 11784, "loss": 0.16, "lr": 1.6793893129770992e-07, "epoch": 0.008486082824168364, "percentage": 0.85, "elapsed_time": "0:00:07", "remaining_time": "0:14:29", "throughput": 13184.48, "total_tokens": 98112}
{"current_steps": 105, "total_steps": 11784, "loss": 0.1406, "lr": 1.7642069550466495e-07, "epoch": 0.008910386965376781, "percentage": 0.89, "elapsed_time": "0:00:07", "remaining_time": "0:14:23", "throughput": 13227.15, "total_tokens": 102720}
{"current_steps": 110, "total_steps": 11784, "loss": 0.156, "lr": 1.8490245971162e-07, "epoch": 0.0093346911065852, "percentage": 0.93, "elapsed_time": "0:00:08", "remaining_time": "0:14:19", "throughput": 13281.54, "total_tokens": 107520}
{"current_steps": 115, "total_steps": 11784, "loss": 0.17, "lr": 1.9338422391857507e-07, "epoch": 0.009758995247793618, "percentage": 0.98, "elapsed_time": "0:00:08", "remaining_time": "0:14:14", "throughput": 13308.98, "total_tokens": 112064}
{"current_steps": 120, "total_steps": 11784, "loss": 0.1468, "lr": 2.018659881255301e-07, "epoch": 0.010183299389002037, "percentage": 1.02, "elapsed_time": "0:00:08", "remaining_time": "0:14:11", "throughput": 13381.0, "total_tokens": 117184}
{"current_steps": 125, "total_steps": 11784, "loss": 0.1524, "lr": 2.1034775233248513e-07, "epoch": 0.010607603530210456, "percentage": 1.06, "elapsed_time": "0:00:09", "remaining_time": "0:14:07", "throughput": 13402.86, "total_tokens": 121792}
{"current_steps": 130, "total_steps": 11784, "loss": 0.1493, "lr": 2.188295165394402e-07, "epoch": 0.011031907671418872, "percentage": 1.1, "elapsed_time": "0:00:09", "remaining_time": "0:14:03", "throughput": 13414.26, "total_tokens": 126272}
{"current_steps": 135, "total_steps": 11784, "loss": 0.1492, "lr": 2.2731128074639524e-07, "epoch": 0.011456211812627291, "percentage": 1.15, "elapsed_time": "0:00:09", "remaining_time": "0:14:00", "throughput": 13433.76, "total_tokens": 130880}
{"current_steps": 140, "total_steps": 11784, "loss": 0.152, "lr": 2.3579304495335027e-07, "epoch": 0.01188051595383571, "percentage": 1.19, "elapsed_time": "0:00:10", "remaining_time": "0:13:57", "throughput": 13459.57, "total_tokens": 135552}
{"current_steps": 145, "total_steps": 11784, "loss": 0.1422, "lr": 2.442748091603053e-07, "epoch": 0.012304820095044128, "percentage": 1.23, "elapsed_time": "0:00:10", "remaining_time": "0:13:56", "throughput": 13519.4, "total_tokens": 140928}
{"current_steps": 150, "total_steps": 11784, "loss": 0.1357, "lr": 2.5275657336726036e-07, "epoch": 0.012729124236252547, "percentage": 1.27, "elapsed_time": "0:00:10", "remaining_time": "0:13:55", "throughput": 13568.43, "total_tokens": 146176}
{"current_steps": 155, "total_steps": 11784, "loss": 0.1692, "lr": 2.612383375742154e-07, "epoch": 0.013153428377460964, "percentage": 1.32, "elapsed_time": "0:00:11", "remaining_time": "0:13:54", "throughput": 13639.47, "total_tokens": 151680}
{"current_steps": 160, "total_steps": 11784, "loss": 0.1577, "lr": 2.697201017811705e-07, "epoch": 0.013577732518669382, "percentage": 1.36, "elapsed_time": "0:00:11", "remaining_time": "0:13:52", "throughput": 13660.94, "total_tokens": 156480}
{"current_steps": 165, "total_steps": 11784, "loss": 0.1464, "lr": 2.782018659881255e-07, "epoch": 0.0140020366598778, "percentage": 1.4, "elapsed_time": "0:00:11", "remaining_time": "0:13:49", "throughput": 13665.42, "total_tokens": 161024}
{"current_steps": 170, "total_steps": 11784, "loss": 0.1223, "lr": 2.866836301950806e-07, "epoch": 0.01442634080108622, "percentage": 1.44, "elapsed_time": "0:00:12", "remaining_time": "0:13:47", "throughput": 13682.79, "total_tokens": 165760}
{"current_steps": 175, "total_steps": 11784, "loss": 0.1156, "lr": 2.951653944020356e-07, "epoch": 0.014850644942294636, "percentage": 1.49, "elapsed_time": "0:00:12", "remaining_time": "0:13:44", "throughput": 13669.17, "total_tokens": 169984}
{"current_steps": 180, "total_steps": 11784, "loss": 0.1584, "lr": 3.0364715860899065e-07, "epoch": 0.015274949083503055, "percentage": 1.53, "elapsed_time": "0:00:12", "remaining_time": "0:13:42", "throughput": 13672.25, "total_tokens": 174528}
{"current_steps": 185, "total_steps": 11784, "loss": 0.1117, "lr": 3.121289228159457e-07, "epoch": 0.01569925322471147, "percentage": 1.57, "elapsed_time": "0:00:13", "remaining_time": "0:13:41", "throughput": 13673.53, "total_tokens": 179136}
{"current_steps": 190, "total_steps": 11784, "loss": 0.1283, "lr": 3.206106870229007e-07, "epoch": 0.016123557365919892, "percentage": 1.61, "elapsed_time": "0:00:13", "remaining_time": "0:13:39", "throughput": 13663.61, "total_tokens": 183424}
{"current_steps": 195, "total_steps": 11784, "loss": 0.0957, "lr": 3.2909245122985577e-07, "epoch": 0.01654786150712831, "percentage": 1.65, "elapsed_time": "0:00:13", "remaining_time": "0:13:37", "throughput": 13668.55, "total_tokens": 187968}
{"current_steps": 200, "total_steps": 11784, "loss": 0.1221, "lr": 3.375742154368109e-07, "epoch": 0.01697216564833673, "percentage": 1.7, "elapsed_time": "0:00:14", "remaining_time": "0:13:36", "throughput": 13703.72, "total_tokens": 193152}
{"current_steps": 205, "total_steps": 11784, "loss": 0.1305, "lr": 3.460559796437659e-07, "epoch": 0.017396469789545146, "percentage": 1.74, "elapsed_time": "0:00:14", "remaining_time": "0:13:34", "throughput": 13701.2, "total_tokens": 197632}
{"current_steps": 210, "total_steps": 11784, "loss": 0.0971, "lr": 3.5453774385072094e-07, "epoch": 0.017820773930753563, "percentage": 1.78, "elapsed_time": "0:00:14", "remaining_time": "0:13:33", "throughput": 13712.13, "total_tokens": 202304}
{"current_steps": 215, "total_steps": 11784, "loss": 0.1392, "lr": 3.63019508057676e-07, "epoch": 0.018245078071961983, "percentage": 1.82, "elapsed_time": "0:00:15", "remaining_time": "0:13:31", "throughput": 13726.15, "total_tokens": 207040}
{"current_steps": 220, "total_steps": 11784, "loss": 0.1071, "lr": 3.71501272264631e-07, "epoch": 0.0186693822131704, "percentage": 1.87, "elapsed_time": "0:00:15", "remaining_time": "0:13:31", "throughput": 13770.74, "total_tokens": 212480}
{"current_steps": 225, "total_steps": 11784, "loss": 0.1398, "lr": 3.7998303647158606e-07, "epoch": 0.01909368635437882, "percentage": 1.91, "elapsed_time": "0:00:15", "remaining_time": "0:13:30", "throughput": 13804.01, "total_tokens": 217728}
{"current_steps": 230, "total_steps": 11784, "loss": 0.0853, "lr": 3.8846480067854107e-07, "epoch": 0.019517990495587237, "percentage": 1.95, "elapsed_time": "0:00:16", "remaining_time": "0:13:28", "throughput": 13789.05, "total_tokens": 221888}
{"current_steps": 235, "total_steps": 11784, "loss": 0.0764, "lr": 3.969465648854962e-07, "epoch": 0.019942294636795654, "percentage": 1.99, "elapsed_time": "0:00:16", "remaining_time": "0:13:27", "throughput": 13792.56, "total_tokens": 226496}
{"current_steps": 240, "total_steps": 11784, "loss": 0.1296, "lr": 4.0542832909245124e-07, "epoch": 0.020366598778004074, "percentage": 2.04, "elapsed_time": "0:00:16", "remaining_time": "0:13:25", "throughput": 13782.81, "total_tokens": 230720}
{"current_steps": 245, "total_steps": 11784, "loss": 0.2537, "lr": 4.1391009329940624e-07, "epoch": 0.02079090291921249, "percentage": 2.08, "elapsed_time": "0:00:17", "remaining_time": "0:13:24", "throughput": 13799.01, "total_tokens": 235584}
{"current_steps": 250, "total_steps": 11784, "loss": 0.0764, "lr": 4.223918575063613e-07, "epoch": 0.02121520706042091, "percentage": 2.12, "elapsed_time": "0:00:17", "remaining_time": "0:13:24", "throughput": 13834.27, "total_tokens": 241088}
{"current_steps": 255, "total_steps": 11784, "loss": 0.0627, "lr": 4.3087362171331635e-07, "epoch": 0.021639511201629328, "percentage": 2.16, "elapsed_time": "0:00:17", "remaining_time": "0:13:22", "throughput": 13831.9, "total_tokens": 245568}
{"current_steps": 260, "total_steps": 11784, "loss": 0.0585, "lr": 4.3935538592027136e-07, "epoch": 0.022063815342837745, "percentage": 2.21, "elapsed_time": "0:00:18", "remaining_time": "0:13:21", "throughput": 13839.34, "total_tokens": 250304}
{"current_steps": 265, "total_steps": 11784, "loss": 0.0933, "lr": 4.4783715012722647e-07, "epoch": 0.022488119484046165, "percentage": 2.25, "elapsed_time": "0:00:18", "remaining_time": "0:13:20", "throughput": 13852.83, "total_tokens": 255232}
{"current_steps": 270, "total_steps": 11784, "loss": 0.0946, "lr": 4.5631891433418153e-07, "epoch": 0.022912423625254582, "percentage": 2.29, "elapsed_time": "0:00:18", "remaining_time": "0:13:19", "throughput": 13855.03, "total_tokens": 259840}
{"current_steps": 275, "total_steps": 11784, "loss": 0.081, "lr": 4.6480067854113653e-07, "epoch": 0.023336727766463002, "percentage": 2.33, "elapsed_time": "0:00:19", "remaining_time": "0:13:19", "throughput": 13867.86, "total_tokens": 264768}
{"current_steps": 280, "total_steps": 11784, "loss": 0.1051, "lr": 4.732824427480916e-07, "epoch": 0.02376103190767142, "percentage": 2.38, "elapsed_time": "0:00:19", "remaining_time": "0:13:18", "throughput": 13895.51, "total_tokens": 270016}
{"current_steps": 285, "total_steps": 11784, "loss": 0.0954, "lr": 4.817642069550466e-07, "epoch": 0.024185336048879836, "percentage": 2.42, "elapsed_time": "0:00:19", "remaining_time": "0:13:17", "throughput": 13892.88, "total_tokens": 274496}
{"current_steps": 290, "total_steps": 11784, "loss": 0.0791, "lr": 4.902459711620017e-07, "epoch": 0.024609640190088256, "percentage": 2.46, "elapsed_time": "0:00:20", "remaining_time": "0:13:16", "throughput": 13902.9, "total_tokens": 279296}
{"current_steps": 295, "total_steps": 11784, "loss": 0.077, "lr": 4.987277353689568e-07, "epoch": 0.025033944331296673, "percentage": 2.5, "elapsed_time": "0:00:20", "remaining_time": "0:13:15", "throughput": 13916.03, "total_tokens": 284288}
{"current_steps": 300, "total_steps": 11784, "loss": 0.1016, "lr": 5.072094995759117e-07, "epoch": 0.025458248472505093, "percentage": 2.55, "elapsed_time": "0:00:20", "remaining_time": "0:13:14", "throughput": 13922.61, "total_tokens": 289088}
{"current_steps": 305, "total_steps": 11784, "loss": 0.1201, "lr": 5.156912637828668e-07, "epoch": 0.02588255261371351, "percentage": 2.59, "elapsed_time": "0:00:21", "remaining_time": "0:13:13", "throughput": 13921.05, "total_tokens": 293632}
{"current_steps": 310, "total_steps": 11784, "loss": 0.0812, "lr": 5.241730279898219e-07, "epoch": 0.026306856754921927, "percentage": 2.63, "elapsed_time": "0:00:21", "remaining_time": "0:13:12", "throughput": 13921.78, "total_tokens": 298176}
{"current_steps": 315, "total_steps": 11784, "loss": 0.1464, "lr": 5.326547921967769e-07, "epoch": 0.026731160896130347, "percentage": 2.67, "elapsed_time": "0:00:21", "remaining_time": "0:13:11", "throughput": 13922.8, "total_tokens": 302720}
{"current_steps": 320, "total_steps": 11784, "loss": 0.1395, "lr": 5.411365564037319e-07, "epoch": 0.027155465037338764, "percentage": 2.72, "elapsed_time": "0:00:22", "remaining_time": "0:13:10", "throughput": 13934.71, "total_tokens": 307648}
{"current_steps": 325, "total_steps": 11784, "loss": 0.0854, "lr": 5.49618320610687e-07, "epoch": 0.02757976917854718, "percentage": 2.76, "elapsed_time": "0:00:22", "remaining_time": "0:13:10", "throughput": 13952.48, "total_tokens": 312832}
{"current_steps": 330, "total_steps": 11784, "loss": 0.0932, "lr": 5.581000848176421e-07, "epoch": 0.0280040733197556, "percentage": 2.8, "elapsed_time": "0:00:22", "remaining_time": "0:13:09", "throughput": 13952.26, "total_tokens": 317376}
{"current_steps": 335, "total_steps": 11784, "loss": 0.0609, "lr": 5.66581849024597e-07, "epoch": 0.028428377460964018, "percentage": 2.84, "elapsed_time": "0:00:23", "remaining_time": "0:13:09", "throughput": 13970.84, "total_tokens": 322560}
{"current_steps": 340, "total_steps": 11784, "loss": 0.0641, "lr": 5.750636132315522e-07, "epoch": 0.02885268160217244, "percentage": 2.89, "elapsed_time": "0:00:23", "remaining_time": "0:13:08", "throughput": 13970.35, "total_tokens": 327104}
{"current_steps": 345, "total_steps": 11784, "loss": 0.0712, "lr": 5.835453774385072e-07, "epoch": 0.029276985743380855, "percentage": 2.93, "elapsed_time": "0:00:23", "remaining_time": "0:13:07", "throughput": 13982.46, "total_tokens": 332160}
{"current_steps": 350, "total_steps": 11784, "loss": 0.0986, "lr": 5.920271416454622e-07, "epoch": 0.029701289884589272, "percentage": 2.97, "elapsed_time": "0:00:24", "remaining_time": "0:13:06", "throughput": 13988.07, "total_tokens": 336960}
{"current_steps": 355, "total_steps": 11784, "loss": 0.1444, "lr": 6.005089058524173e-07, "epoch": 0.030125594025797692, "percentage": 3.01, "elapsed_time": "0:00:24", "remaining_time": "0:13:06", "throughput": 13993.35, "total_tokens": 341696}
{"current_steps": 360, "total_steps": 11784, "loss": 0.1736, "lr": 6.089906700593723e-07, "epoch": 0.03054989816700611, "percentage": 3.05, "elapsed_time": "0:00:24", "remaining_time": "0:13:05", "throughput": 14015.1, "total_tokens": 347008}
{"current_steps": 365, "total_steps": 11784, "loss": 0.1123, "lr": 6.174724342663274e-07, "epoch": 0.03097420230821453, "percentage": 3.1, "elapsed_time": "0:00:25", "remaining_time": "0:13:05", "throughput": 14033.99, "total_tokens": 352256}
{"current_steps": 370, "total_steps": 11784, "loss": 0.0541, "lr": 6.259541984732824e-07, "epoch": 0.03139850644942294, "percentage": 3.14, "elapsed_time": "0:00:25", "remaining_time": "0:13:04", "throughput": 14046.93, "total_tokens": 357312}
{"current_steps": 375, "total_steps": 11784, "loss": 0.151, "lr": 6.344359626802375e-07, "epoch": 0.03182281059063136, "percentage": 3.18, "elapsed_time": "0:00:25", "remaining_time": "0:13:03", "throughput": 14040.47, "total_tokens": 361728}
{"current_steps": 380, "total_steps": 11784, "loss": 0.1249, "lr": 6.429177268871925e-07, "epoch": 0.032247114731839784, "percentage": 3.22, "elapsed_time": "0:00:26", "remaining_time": "0:13:03", "throughput": 14047.99, "total_tokens": 366592}
{"current_steps": 385, "total_steps": 11784, "loss": 0.2083, "lr": 6.513994910941476e-07, "epoch": 0.032671418873048204, "percentage": 3.27, "elapsed_time": "0:00:26", "remaining_time": "0:13:02", "throughput": 14053.63, "total_tokens": 371392}
{"current_steps": 390, "total_steps": 11784, "loss": 0.0916, "lr": 6.598812553011026e-07, "epoch": 0.03309572301425662, "percentage": 3.31, "elapsed_time": "0:00:26", "remaining_time": "0:13:02", "throughput": 14069.94, "total_tokens": 376640}
{"current_steps": 395, "total_steps": 11784, "loss": 0.1429, "lr": 6.683630195080576e-07, "epoch": 0.03352002715546504, "percentage": 3.35, "elapsed_time": "0:00:27", "remaining_time": "0:13:01", "throughput": 14075.44, "total_tokens": 381504}
{"current_steps": 400, "total_steps": 11784, "loss": 0.1211, "lr": 6.768447837150128e-07, "epoch": 0.03394433129667346, "percentage": 3.39, "elapsed_time": "0:00:27", "remaining_time": "0:13:00", "throughput": 14068.86, "total_tokens": 385920}
{"current_steps": 405, "total_steps": 11784, "loss": 0.1086, "lr": 6.853265479219677e-07, "epoch": 0.03436863543788187, "percentage": 3.44, "elapsed_time": "0:00:27", "remaining_time": "0:12:59", "throughput": 14060.26, "total_tokens": 390272}
{"current_steps": 410, "total_steps": 11784, "loss": 0.1208, "lr": 6.938083121289228e-07, "epoch": 0.03479293957909029, "percentage": 3.48, "elapsed_time": "0:00:28", "remaining_time": "0:12:59", "throughput": 14091.23, "total_tokens": 396160}
{"current_steps": 415, "total_steps": 11784, "loss": 0.0872, "lr": 7.022900763358778e-07, "epoch": 0.03521724372029871, "percentage": 3.52, "elapsed_time": "0:00:28", "remaining_time": "0:12:59", "throughput": 14089.86, "total_tokens": 400768}
{"current_steps": 420, "total_steps": 11784, "loss": 0.0613, "lr": 7.107718405428329e-07, "epoch": 0.035641547861507125, "percentage": 3.56, "elapsed_time": "0:00:28", "remaining_time": "0:12:58", "throughput": 14090.6, "total_tokens": 405504}
{"current_steps": 425, "total_steps": 11784, "loss": 0.0373, "lr": 7.192536047497879e-07, "epoch": 0.036065852002715545, "percentage": 3.61, "elapsed_time": "0:00:29", "remaining_time": "0:12:57", "throughput": 14092.13, "total_tokens": 410176}
{"current_steps": 430, "total_steps": 11784, "loss": 0.0669, "lr": 7.277353689567429e-07, "epoch": 0.036490156143923966, "percentage": 3.65, "elapsed_time": "0:00:29", "remaining_time": "0:12:57", "throughput": 14098.22, "total_tokens": 415040}
{"current_steps": 435, "total_steps": 11784, "loss": 0.1154, "lr": 7.36217133163698e-07, "epoch": 0.036914460285132386, "percentage": 3.69, "elapsed_time": "0:00:29", "remaining_time": "0:12:56", "throughput": 14106.29, "total_tokens": 419968}
{"current_steps": 440, "total_steps": 11784, "loss": 0.2025, "lr": 7.446988973706531e-07, "epoch": 0.0373387644263408, "percentage": 3.73, "elapsed_time": "0:00:30", "remaining_time": "0:12:56", "throughput": 14110.88, "total_tokens": 424832}
{"current_steps": 445, "total_steps": 11784, "loss": 0.3266, "lr": 7.531806615776081e-07, "epoch": 0.03776306856754922, "percentage": 3.78, "elapsed_time": "0:00:30", "remaining_time": "0:12:57", "throughput": 14164.28, "total_tokens": 432064}
{"current_steps": 450, "total_steps": 11784, "loss": 0.0826, "lr": 7.616624257845632e-07, "epoch": 0.03818737270875764, "percentage": 3.82, "elapsed_time": "0:00:30", "remaining_time": "0:12:56", "throughput": 14174.06, "total_tokens": 437184}
{"current_steps": 455, "total_steps": 11784, "loss": 0.102, "lr": 7.701441899915182e-07, "epoch": 0.03861167684996605, "percentage": 3.86, "elapsed_time": "0:00:31", "remaining_time": "0:12:56", "throughput": 14187.76, "total_tokens": 442432}
{"current_steps": 460, "total_steps": 11784, "loss": 0.0454, "lr": 7.786259541984732e-07, "epoch": 0.039035980991174474, "percentage": 3.9, "elapsed_time": "0:00:31", "remaining_time": "0:12:55", "throughput": 14186.72, "total_tokens": 447040}
{"current_steps": 465, "total_steps": 11784, "loss": 0.1319, "lr": 7.871077184054283e-07, "epoch": 0.039460285132382894, "percentage": 3.95, "elapsed_time": "0:00:31", "remaining_time": "0:12:55", "throughput": 14194.74, "total_tokens": 452032}
{"current_steps": 470, "total_steps": 11784, "loss": 0.0636, "lr": 7.955894826123833e-07, "epoch": 0.03988458927359131, "percentage": 3.99, "elapsed_time": "0:00:32", "remaining_time": "0:12:54", "throughput": 14206.7, "total_tokens": 457344}
{"current_steps": 475, "total_steps": 11784, "loss": 0.1349, "lr": 8.040712468193384e-07, "epoch": 0.04030889341479973, "percentage": 4.03, "elapsed_time": "0:00:32", "remaining_time": "0:12:54", "throughput": 14213.33, "total_tokens": 462336}
{"current_steps": 480, "total_steps": 11784, "loss": 0.0904, "lr": 8.125530110262935e-07, "epoch": 0.04073319755600815, "percentage": 4.07, "elapsed_time": "0:00:32", "remaining_time": "0:12:53", "throughput": 14213.81, "total_tokens": 467072}
{"current_steps": 485, "total_steps": 11784, "loss": 0.0983, "lr": 8.210347752332485e-07, "epoch": 0.04115750169721656, "percentage": 4.12, "elapsed_time": "0:00:33", "remaining_time": "0:12:53", "throughput": 14210.51, "total_tokens": 471616}
{"current_steps": 490, "total_steps": 11784, "loss": 0.0815, "lr": 8.295165394402035e-07, "epoch": 0.04158180583842498, "percentage": 4.16, "elapsed_time": "0:00:33", "remaining_time": "0:12:52", "throughput": 14214.55, "total_tokens": 476480}
{"current_steps": 495, "total_steps": 11784, "loss": 0.0929, "lr": 8.379983036471586e-07, "epoch": 0.0420061099796334, "percentage": 4.2, "elapsed_time": "0:00:33", "remaining_time": "0:12:52", "throughput": 14220.88, "total_tokens": 481536}
{"current_steps": 500, "total_steps": 11784, "loss": 0.1216, "lr": 8.464800678541136e-07, "epoch": 0.04243041412084182, "percentage": 4.24, "elapsed_time": "0:00:34", "remaining_time": "0:12:51", "throughput": 14223.18, "total_tokens": 486336}
{"current_steps": 505, "total_steps": 11784, "loss": 0.1143, "lr": 8.549618320610686e-07, "epoch": 0.042854718262050236, "percentage": 4.29, "elapsed_time": "0:00:34", "remaining_time": "0:12:50", "throughput": 14221.95, "total_tokens": 490944}
{"current_steps": 510, "total_steps": 11784, "loss": 0.0585, "lr": 8.634435962680237e-07, "epoch": 0.043279022403258656, "percentage": 4.33, "elapsed_time": "0:00:34", "remaining_time": "0:12:50", "throughput": 14218.6, "total_tokens": 495488}
{"current_steps": 515, "total_steps": 11784, "loss": 0.1, "lr": 8.719253604749788e-07, "epoch": 0.043703326544467076, "percentage": 4.37, "elapsed_time": "0:00:35", "remaining_time": "0:12:49", "throughput": 14211.52, "total_tokens": 499840}
{"current_steps": 520, "total_steps": 11784, "loss": 0.0818, "lr": 8.804071246819338e-07, "epoch": 0.04412763068567549, "percentage": 4.41, "elapsed_time": "0:00:35", "remaining_time": "0:12:48", "throughput": 14211.93, "total_tokens": 504512}
{"current_steps": 525, "total_steps": 11784, "loss": 0.0705, "lr": 8.888888888888888e-07, "epoch": 0.04455193482688391, "percentage": 4.46, "elapsed_time": "0:00:35", "remaining_time": "0:12:48", "throughput": 14215.54, "total_tokens": 509376}
{"current_steps": 530, "total_steps": 11784, "loss": 0.07, "lr": 8.973706530958439e-07, "epoch": 0.04497623896809233, "percentage": 4.5, "elapsed_time": "0:00:36", "remaining_time": "0:12:47", "throughput": 14210.53, "total_tokens": 513856}
{"current_steps": 535, "total_steps": 11784, "loss": 0.107, "lr": 9.058524173027989e-07, "epoch": 0.045400543109300744, "percentage": 4.54, "elapsed_time": "0:00:36", "remaining_time": "0:12:47", "throughput": 14215.99, "total_tokens": 518976}
{"current_steps": 540, "total_steps": 11784, "loss": 0.0958, "lr": 9.143341815097539e-07, "epoch": 0.045824847250509164, "percentage": 4.58, "elapsed_time": "0:00:36", "remaining_time": "0:12:47", "throughput": 14224.12, "total_tokens": 524160}
{"current_steps": 545, "total_steps": 11784, "loss": 0.1709, "lr": 9.228159457167091e-07, "epoch": 0.046249151391717584, "percentage": 4.62, "elapsed_time": "0:00:37", "remaining_time": "0:12:46", "throughput": 14229.62, "total_tokens": 529152}
{"current_steps": 550, "total_steps": 11784, "loss": 0.1825, "lr": 9.312977099236641e-07, "epoch": 0.046673455532926005, "percentage": 4.67, "elapsed_time": "0:00:37", "remaining_time": "0:12:46", "throughput": 14230.4, "total_tokens": 533824}
{"current_steps": 555, "total_steps": 11784, "loss": 0.0982, "lr": 9.397794741306191e-07, "epoch": 0.04709775967413442, "percentage": 4.71, "elapsed_time": "0:00:37", "remaining_time": "0:12:45", "throughput": 14230.74, "total_tokens": 538560}
{"current_steps": 560, "total_steps": 11784, "loss": 0.1049, "lr": 9.482612383375742e-07, "epoch": 0.04752206381534284, "percentage": 4.75, "elapsed_time": "0:00:38", "remaining_time": "0:12:44", "throughput": 14221.97, "total_tokens": 542784}
{"current_steps": 565, "total_steps": 11784, "loss": 0.1076, "lr": 9.567430025445291e-07, "epoch": 0.04794636795655126, "percentage": 4.79, "elapsed_time": "0:00:38", "remaining_time": "0:12:44", "throughput": 14229.42, "total_tokens": 547840}
{"current_steps": 570, "total_steps": 11784, "loss": 0.0785, "lr": 9.652247667514842e-07, "epoch": 0.04837067209775967, "percentage": 4.84, "elapsed_time": "0:00:38", "remaining_time": "0:12:43", "throughput": 14229.03, "total_tokens": 552448}
{"current_steps": 575, "total_steps": 11784, "loss": 0.1165, "lr": 9.737065309584394e-07, "epoch": 0.04879497623896809, "percentage": 4.88, "elapsed_time": "0:00:39", "remaining_time": "0:12:43", "throughput": 14229.26, "total_tokens": 557120}
{"current_steps": 580, "total_steps": 11784, "loss": 0.1119, "lr": 9.821882951653943e-07, "epoch": 0.04921928038017651, "percentage": 4.92, "elapsed_time": "0:00:39", "remaining_time": "0:12:42", "throughput": 14224.49, "total_tokens": 561536}
{"current_steps": 585, "total_steps": 11784, "loss": 0.0704, "lr": 9.906700593723493e-07, "epoch": 0.049643584521384926, "percentage": 4.96, "elapsed_time": "0:00:39", "remaining_time": "0:12:42", "throughput": 14225.69, "total_tokens": 566336}
{"current_steps": 590, "total_steps": 11784, "loss": 0.0929, "lr": 9.991518235793044e-07, "epoch": 0.050067888662593346, "percentage": 5.01, "elapsed_time": "0:00:40", "remaining_time": "0:12:41", "throughput": 14227.18, "total_tokens": 571072}
{"current_steps": 590, "total_steps": 11784, "eval_loss": 0.08071617037057877, "epoch": 0.050067888662593346, "percentage": 5.01, "elapsed_time": "0:00:55", "remaining_time": "0:17:39", "throughput": 10228.84, "total_tokens": 571072}
{"current_steps": 595, "total_steps": 11784, "loss": 0.0317, "lr": 1.0076335877862595e-06, "epoch": 0.050492192803801766, "percentage": 5.05, "elapsed_time": "0:01:43", "remaining_time": "0:32:29", "throughput": 5558.41, "total_tokens": 576192}
{"current_steps": 600, "total_steps": 11784, "loss": 0.1199, "lr": 1.0161153519932147e-06, "epoch": 0.05091649694501019, "percentage": 5.09, "elapsed_time": "0:01:43", "remaining_time": "0:32:18", "throughput": 5586.21, "total_tokens": 580928}
{"current_steps": 605, "total_steps": 11784, "loss": 0.1215, "lr": 1.0245971162001696e-06, "epoch": 0.0513408010862186, "percentage": 5.13, "elapsed_time": "0:01:44", "remaining_time": "0:32:07", "throughput": 5614.47, "total_tokens": 585728}
{"current_steps": 610, "total_steps": 11784, "loss": 0.0926, "lr": 1.0330788804071246e-06, "epoch": 0.05176510522742702, "percentage": 5.18, "elapsed_time": "0:01:44", "remaining_time": "0:31:57", "throughput": 5646.62, "total_tokens": 591040}
{"current_steps": 615, "total_steps": 11784, "loss": 0.1686, "lr": 1.0415606446140797e-06, "epoch": 0.05218940936863544, "percentage": 5.22, "elapsed_time": "0:01:44", "remaining_time": "0:31:46", "throughput": 5672.42, "total_tokens": 595584}
{"current_steps": 620, "total_steps": 11784, "loss": 0.1433, "lr": 1.0500424088210348e-06, "epoch": 0.052613713509843854, "percentage": 5.26, "elapsed_time": "0:01:45", "remaining_time": "0:31:36", "throughput": 5700.08, "total_tokens": 600384}
{"current_steps": 625, "total_steps": 11784, "loss": 0.058, "lr": 1.0585241730279896e-06, "epoch": 0.053038017651052274, "percentage": 5.3, "elapsed_time": "0:01:45", "remaining_time": "0:31:26", "throughput": 5727.97, "total_tokens": 605248}
{"current_steps": 630, "total_steps": 11784, "loss": 0.0805, "lr": 1.0670059372349449e-06, "epoch": 0.053462321792260695, "percentage": 5.35, "elapsed_time": "0:01:45", "remaining_time": "0:31:16", "throughput": 5753.59, "total_tokens": 609856}
{"current_steps": 635, "total_steps": 11784, "loss": 0.0443, "lr": 1.0754877014419e-06, "epoch": 0.05388662593346911, "percentage": 5.39, "elapsed_time": "0:01:46", "remaining_time": "0:31:06", "throughput": 5783.56, "total_tokens": 614976}
{"current_steps": 640, "total_steps": 11784, "loss": 0.0862, "lr": 1.083969465648855e-06, "epoch": 0.05431093007467753, "percentage": 5.43, "elapsed_time": "0:01:46", "remaining_time": "0:30:57", "throughput": 5809.5, "total_tokens": 619648}
{"current_steps": 645, "total_steps": 11784, "loss": 0.0478, "lr": 1.09245122985581e-06, "epoch": 0.05473523421588595, "percentage": 5.47, "elapsed_time": "0:01:47", "remaining_time": "0:30:47", "throughput": 5840.05, "total_tokens": 624896}
{"current_steps": 650, "total_steps": 11784, "loss": 0.1452, "lr": 1.1009329940627649e-06, "epoch": 0.05515953835709436, "percentage": 5.52, "elapsed_time": "0:01:47", "remaining_time": "0:30:38", "throughput": 5866.32, "total_tokens": 629632}
{"current_steps": 655, "total_steps": 11784, "loss": 0.0974, "lr": 1.10941475826972e-06, "epoch": 0.05558384249830278, "percentage": 5.56, "elapsed_time": "0:01:47", "remaining_time": "0:30:29", "throughput": 5894.25, "total_tokens": 634624}
{"current_steps": 660, "total_steps": 11784, "loss": 0.0974, "lr": 1.1178965224766752e-06, "epoch": 0.0560081466395112, "percentage": 5.6, "elapsed_time": "0:01:48", "remaining_time": "0:30:20", "throughput": 5919.91, "total_tokens": 639360}
{"current_steps": 665, "total_steps": 11784, "loss": 0.038, "lr": 1.1263782866836303e-06, "epoch": 0.05643245078071962, "percentage": 5.64, "elapsed_time": "0:01:48", "remaining_time": "0:30:11", "throughput": 5944.99, "total_tokens": 644032}
{"current_steps": 670, "total_steps": 11784, "loss": 0.0969, "lr": 1.1348600508905853e-06, "epoch": 0.056856754921928036, "percentage": 5.69, "elapsed_time": "0:01:48", "remaining_time": "0:30:02", "throughput": 5966.36, "total_tokens": 648256}
{"current_steps": 675, "total_steps": 11784, "loss": 0.1091, "lr": 1.1433418150975402e-06, "epoch": 0.05728105906313646, "percentage": 5.73, "elapsed_time": "0:01:48", "remaining_time": "0:29:53", "throughput": 5992.28, "total_tokens": 653056}
{"current_steps": 680, "total_steps": 11784, "loss": 0.0743, "lr": 1.1518235793044952e-06, "epoch": 0.05770536320434488, "percentage": 5.77, "elapsed_time": "0:01:49", "remaining_time": "0:29:44", "throughput": 6016.63, "total_tokens": 657664}
{"current_steps": 685, "total_steps": 11784, "loss": 0.0379, "lr": 1.1603053435114503e-06, "epoch": 0.05812966734555329, "percentage": 5.81, "elapsed_time": "0:01:49", "remaining_time": "0:29:36", "throughput": 6038.61, "total_tokens": 662016}
{"current_steps": 690, "total_steps": 11784, "loss": 0.1067, "lr": 1.1687871077184053e-06, "epoch": 0.05855397148676171, "percentage": 5.86, "elapsed_time": "0:01:49", "remaining_time": "0:29:27", "throughput": 6060.17, "total_tokens": 666368}
{"current_steps": 695, "total_steps": 11784, "loss": 0.1044, "lr": 1.1772688719253606e-06, "epoch": 0.05897827562797013, "percentage": 5.9, "elapsed_time": "0:01:50", "remaining_time": "0:29:19", "throughput": 6088.71, "total_tokens": 671616}
{"current_steps": 700, "total_steps": 11784, "loss": 0.0405, "lr": 1.1857506361323155e-06, "epoch": 0.059402579769178544, "percentage": 5.94, "elapsed_time": "0:01:50", "remaining_time": "0:29:11", "throughput": 6112.62, "total_tokens": 676288}
{"current_steps": 705, "total_steps": 11784, "loss": 0.0789, "lr": 1.1942324003392705e-06, "epoch": 0.059826883910386965, "percentage": 5.98, "elapsed_time": "0:01:50", "remaining_time": "0:29:03", "throughput": 6136.24, "total_tokens": 680960}
{"current_steps": 710, "total_steps": 11784, "loss": 0.0686, "lr": 1.2027141645462256e-06, "epoch": 0.060251188051595385, "percentage": 6.03, "elapsed_time": "0:01:51", "remaining_time": "0:28:56", "throughput": 6158.19, "total_tokens": 685440}
{"current_steps": 715, "total_steps": 11784, "loss": 0.1027, "lr": 1.2111959287531806e-06, "epoch": 0.060675492192803805, "percentage": 6.07, "elapsed_time": "0:01:51", "remaining_time": "0:28:48", "throughput": 6183.16, "total_tokens": 690304}
{"current_steps": 720, "total_steps": 11784, "loss": 0.0782, "lr": 1.2196776929601355e-06, "epoch": 0.06109979633401222, "percentage": 6.11, "elapsed_time": "0:01:51", "remaining_time": "0:28:40", "throughput": 6207.24, "total_tokens": 695040}
{"current_steps": 725, "total_steps": 11784, "loss": 0.0291, "lr": 1.2281594571670907e-06, "epoch": 0.06152410047522064, "percentage": 6.15, "elapsed_time": "0:01:52", "remaining_time": "0:28:33", "throughput": 6228.44, "total_tokens": 699456}
{"current_steps": 730, "total_steps": 11784, "loss": 0.1563, "lr": 1.2366412213740458e-06, "epoch": 0.06194840461642906, "percentage": 6.19, "elapsed_time": "0:01:52", "remaining_time": "0:28:25", "throughput": 6250.99, "total_tokens": 704064}
{"current_steps": 735, "total_steps": 11784, "loss": 0.0311, "lr": 1.2451229855810009e-06, "epoch": 0.06237270875763747, "percentage": 6.24, "elapsed_time": "0:01:52", "remaining_time": "0:28:18", "throughput": 6272.56, "total_tokens": 708544}
{"current_steps": 740, "total_steps": 11784, "loss": 0.2106, "lr": 1.253604749787956e-06, "epoch": 0.06279701289884589, "percentage": 6.28, "elapsed_time": "0:01:53", "remaining_time": "0:28:10", "throughput": 6294.26, "total_tokens": 713088}
{"current_steps": 745, "total_steps": 11784, "loss": 0.1061, "lr": 1.2620865139949108e-06, "epoch": 0.0632213170400543, "percentage": 6.32, "elapsed_time": "0:01:53", "remaining_time": "0:28:03", "throughput": 6318.93, "total_tokens": 718016}
{"current_steps": 750, "total_steps": 11784, "loss": 0.042, "lr": 1.2705682782018658e-06, "epoch": 0.06364562118126273, "percentage": 6.36, "elapsed_time": "0:01:53", "remaining_time": "0:27:56", "throughput": 6342.0, "total_tokens": 722752}
{"current_steps": 755, "total_steps": 11784, "loss": 0.0744, "lr": 1.279050042408821e-06, "epoch": 0.06406992532247115, "percentage": 6.41, "elapsed_time": "0:01:54", "remaining_time": "0:27:49", "throughput": 6367.84, "total_tokens": 727872}
{"current_steps": 760, "total_steps": 11784, "loss": 0.1042, "lr": 1.2875318066157761e-06, "epoch": 0.06449422946367957, "percentage": 6.45, "elapsed_time": "0:01:54", "remaining_time": "0:27:42", "throughput": 6389.8, "total_tokens": 732480}
{"current_steps": 765, "total_steps": 11784, "loss": 0.0475, "lr": 1.2960135708227312e-06, "epoch": 0.06491853360488799, "percentage": 6.49, "elapsed_time": "0:01:54", "remaining_time": "0:27:35", "throughput": 6408.55, "total_tokens": 736704}
{"current_steps": 770, "total_steps": 11784, "loss": 0.0575, "lr": 1.304495335029686e-06, "epoch": 0.06534283774609641, "percentage": 6.53, "elapsed_time": "0:01:55", "remaining_time": "0:27:29", "throughput": 6441.48, "total_tokens": 742848}
{"current_steps": 775, "total_steps": 11784, "loss": 0.1154, "lr": 1.3129770992366411e-06, "epoch": 0.06576714188730481, "percentage": 6.58, "elapsed_time": "0:01:55", "remaining_time": "0:27:22", "throughput": 6459.82, "total_tokens": 747072}
{"current_steps": 780, "total_steps": 11784, "loss": 0.0311, "lr": 1.3214588634435962e-06, "epoch": 0.06619144602851323, "percentage": 6.62, "elapsed_time": "0:01:55", "remaining_time": "0:27:16", "throughput": 6482.11, "total_tokens": 751808}
{"current_steps": 785, "total_steps": 11784, "loss": 0.0878, "lr": 1.3299406276505512e-06, "epoch": 0.06661575016972165, "percentage": 6.66, "elapsed_time": "0:01:56", "remaining_time": "0:27:09", "throughput": 6505.95, "total_tokens": 756800}
{"current_steps": 790, "total_steps": 11784, "loss": 0.1431, "lr": 1.3384223918575063e-06, "epoch": 0.06704005431093008, "percentage": 6.7, "elapsed_time": "0:01:56", "remaining_time": "0:27:03", "throughput": 6528.21, "total_tokens": 761536}
{"current_steps": 795, "total_steps": 11784, "loss": 0.1062, "lr": 1.3469041560644613e-06, "epoch": 0.0674643584521385, "percentage": 6.75, "elapsed_time": "0:01:56", "remaining_time": "0:26:56", "throughput": 6546.68, "total_tokens": 765824}
{"current_steps": 800, "total_steps": 11784, "loss": 0.3519, "lr": 1.3553859202714164e-06, "epoch": 0.06788866259334692, "percentage": 6.79, "elapsed_time": "0:01:57", "remaining_time": "0:26:50", "throughput": 6566.18, "total_tokens": 770240}
{"current_steps": 805, "total_steps": 11784, "loss": 0.1262, "lr": 1.3638676844783715e-06, "epoch": 0.06831296673455534, "percentage": 6.83, "elapsed_time": "0:01:57", "remaining_time": "0:26:44", "throughput": 6591.0, "total_tokens": 775424}
{"current_steps": 810, "total_steps": 11784, "loss": 0.061, "lr": 1.3723494486853265e-06, "epoch": 0.06873727087576374, "percentage": 6.87, "elapsed_time": "0:01:57", "remaining_time": "0:26:38", "throughput": 6610.5, "total_tokens": 779904}
{"current_steps": 815, "total_steps": 11784, "loss": 0.0747, "lr": 1.3808312128922814e-06, "epoch": 0.06916157501697216, "percentage": 6.92, "elapsed_time": "0:01:58", "remaining_time": "0:26:32", "throughput": 6631.16, "total_tokens": 784512}
{"current_steps": 820, "total_steps": 11784, "loss": 0.078, "lr": 1.3893129770992366e-06, "epoch": 0.06958587915818058, "percentage": 6.96, "elapsed_time": "0:01:58", "remaining_time": "0:26:26", "throughput": 6653.79, "total_tokens": 789440}
{"current_steps": 825, "total_steps": 11784, "loss": 0.1098, "lr": 1.3977947413061917e-06, "epoch": 0.070010183299389, "percentage": 7.0, "elapsed_time": "0:01:58", "remaining_time": "0:26:20", "throughput": 6675.56, "total_tokens": 794240}
{"current_steps": 830, "total_steps": 11784, "loss": 0.139, "lr": 1.4062765055131467e-06, "epoch": 0.07043448744059742, "percentage": 7.04, "elapsed_time": "0:01:59", "remaining_time": "0:26:14", "throughput": 6693.91, "total_tokens": 798592}
{"current_steps": 835, "total_steps": 11784, "loss": 0.1213, "lr": 1.4147582697201018e-06, "epoch": 0.07085879158180584, "percentage": 7.09, "elapsed_time": "0:01:59", "remaining_time": "0:26:08", "throughput": 6718.06, "total_tokens": 803776}
{"current_steps": 840, "total_steps": 11784, "loss": 0.0552, "lr": 1.4232400339270566e-06, "epoch": 0.07128309572301425, "percentage": 7.13, "elapsed_time": "0:01:59", "remaining_time": "0:26:03", "throughput": 6743.12, "total_tokens": 809088}
{"current_steps": 845, "total_steps": 11784, "loss": 0.0523, "lr": 1.4317217981340117e-06, "epoch": 0.07170739986422267, "percentage": 7.17, "elapsed_time": "0:02:00", "remaining_time": "0:25:57", "throughput": 6763.99, "total_tokens": 813824}
{"current_steps": 850, "total_steps": 11784, "loss": 0.0617, "lr": 1.440203562340967e-06, "epoch": 0.07213170400543109, "percentage": 7.21, "elapsed_time": "0:02:00", "remaining_time": "0:25:51", "throughput": 6782.42, "total_tokens": 818240}
{"current_steps": 855, "total_steps": 11784, "loss": 0.1225, "lr": 1.448685326547922e-06, "epoch": 0.07255600814663951, "percentage": 7.26, "elapsed_time": "0:02:00", "remaining_time": "0:25:46", "throughput": 6798.81, "total_tokens": 822400}
{"current_steps": 860, "total_steps": 11784, "loss": 0.1247, "lr": 1.457167090754877e-06, "epoch": 0.07298031228784793, "percentage": 7.3, "elapsed_time": "0:02:01", "remaining_time": "0:25:40", "throughput": 6820.58, "total_tokens": 827328}
{"current_steps": 865, "total_steps": 11784, "loss": 0.1375, "lr": 1.465648854961832e-06, "epoch": 0.07340461642905635, "percentage": 7.34, "elapsed_time": "0:02:01", "remaining_time": "0:25:35", "throughput": 6842.66, "total_tokens": 832320}
{"current_steps": 870, "total_steps": 11784, "loss": 0.0976, "lr": 1.474130619168787e-06, "epoch": 0.07382892057026477, "percentage": 7.38, "elapsed_time": "0:02:01", "remaining_time": "0:25:30", "throughput": 6864.64, "total_tokens": 837376}
{"current_steps": 875, "total_steps": 11784, "loss": 0.0646, "lr": 1.482612383375742e-06, "epoch": 0.07425322471147318, "percentage": 7.43, "elapsed_time": "0:02:02", "remaining_time": "0:25:25", "throughput": 6890.63, "total_tokens": 843008}
{"current_steps": 880, "total_steps": 11784, "loss": 0.1057, "lr": 1.491094147582697e-06, "epoch": 0.0746775288526816, "percentage": 7.47, "elapsed_time": "0:02:02", "remaining_time": "0:25:20", "throughput": 6910.11, "total_tokens": 847680}
{"current_steps": 885, "total_steps": 11784, "loss": 0.0703, "lr": 1.4995759117896522e-06, "epoch": 0.07510183299389002, "percentage": 7.51, "elapsed_time": "0:02:03", "remaining_time": "0:25:14", "throughput": 6929.08, "total_tokens": 852288}
{"current_steps": 890, "total_steps": 11784, "loss": 0.0832, "lr": 1.5080576759966072e-06, "epoch": 0.07552613713509844, "percentage": 7.55, "elapsed_time": "0:02:03", "remaining_time": "0:25:09", "throughput": 6950.65, "total_tokens": 857280}
{"current_steps": 895, "total_steps": 11784, "loss": 0.0415, "lr": 1.5165394402035623e-06, "epoch": 0.07595044127630686, "percentage": 7.6, "elapsed_time": "0:02:03", "remaining_time": "0:25:04", "throughput": 6970.53, "total_tokens": 862080}
{"current_steps": 900, "total_steps": 11784, "loss": 0.1667, "lr": 1.5250212044105173e-06, "epoch": 0.07637474541751528, "percentage": 7.64, "elapsed_time": "0:02:03", "remaining_time": "0:24:59", "throughput": 6988.95, "total_tokens": 866624}
{"current_steps": 905, "total_steps": 11784, "loss": 0.0798, "lr": 1.5335029686174724e-06, "epoch": 0.07679904955872369, "percentage": 7.68, "elapsed_time": "0:02:04", "remaining_time": "0:24:54", "throughput": 7008.39, "total_tokens": 871360}
{"current_steps": 910, "total_steps": 11784, "loss": 0.1418, "lr": 1.5419847328244272e-06, "epoch": 0.0772233536999321, "percentage": 7.72, "elapsed_time": "0:02:04", "remaining_time": "0:24:50", "throughput": 7037.77, "total_tokens": 877632}
{"current_steps": 915, "total_steps": 11784, "loss": 0.0659, "lr": 1.5504664970313825e-06, "epoch": 0.07764765784114053, "percentage": 7.76, "elapsed_time": "0:02:05", "remaining_time": "0:24:45", "throughput": 7051.66, "total_tokens": 881600}
{"current_steps": 920, "total_steps": 11784, "loss": 0.0591, "lr": 1.5589482612383376e-06, "epoch": 0.07807196198234895, "percentage": 7.81, "elapsed_time": "0:02:05", "remaining_time": "0:24:40", "throughput": 7071.3, "total_tokens": 886400}
{"current_steps": 925, "total_steps": 11784, "loss": 0.0906, "lr": 1.5674300254452926e-06, "epoch": 0.07849626612355737, "percentage": 7.85, "elapsed_time": "0:02:05", "remaining_time": "0:24:35", "throughput": 7088.17, "total_tokens": 890880}
{"current_steps": 930, "total_steps": 11784, "loss": 0.076, "lr": 1.5759117896522477e-06, "epoch": 0.07892057026476579, "percentage": 7.89, "elapsed_time": "0:02:06", "remaining_time": "0:24:30", "throughput": 7107.92, "total_tokens": 895744}
{"current_steps": 935, "total_steps": 11784, "loss": 0.1215, "lr": 1.5843935538592025e-06, "epoch": 0.07934487440597421, "percentage": 7.93, "elapsed_time": "0:02:06", "remaining_time": "0:24:26", "throughput": 7124.84, "total_tokens": 900224}
{"current_steps": 940, "total_steps": 11784, "loss": 0.0687, "lr": 1.5928753180661576e-06, "epoch": 0.07976917854718261, "percentage": 7.98, "elapsed_time": "0:02:06", "remaining_time": "0:24:21", "throughput": 7145.43, "total_tokens": 905280}
{"current_steps": 945, "total_steps": 11784, "loss": 0.0859, "lr": 1.6013570822731128e-06, "epoch": 0.08019348268839104, "percentage": 8.02, "elapsed_time": "0:02:07", "remaining_time": "0:24:17", "throughput": 7166.31, "total_tokens": 910336}
{"current_steps": 950, "total_steps": 11784, "loss": 0.0632, "lr": 1.609838846480068e-06, "epoch": 0.08061778682959946, "percentage": 8.06, "elapsed_time": "0:02:07", "remaining_time": "0:24:12", "throughput": 7189.26, "total_tokens": 915776}
{"current_steps": 955, "total_steps": 11784, "loss": 0.0857, "lr": 1.618320610687023e-06, "epoch": 0.08104209097080788, "percentage": 8.1, "elapsed_time": "0:02:07", "remaining_time": "0:24:08", "throughput": 7207.46, "total_tokens": 920512}
{"current_steps": 960, "total_steps": 11784, "loss": 0.1331, "lr": 1.6268023748939778e-06, "epoch": 0.0814663951120163, "percentage": 8.15, "elapsed_time": "0:02:08", "remaining_time": "0:24:03", "throughput": 7223.94, "total_tokens": 924992}
{"current_steps": 965, "total_steps": 11784, "loss": 0.1138, "lr": 1.6352841391009329e-06, "epoch": 0.08189069925322472, "percentage": 8.19, "elapsed_time": "0:02:08", "remaining_time": "0:23:59", "throughput": 7242.45, "total_tokens": 929792}
{"current_steps": 970, "total_steps": 11784, "loss": 0.1123, "lr": 1.643765903307888e-06, "epoch": 0.08231500339443312, "percentage": 8.23, "elapsed_time": "0:02:08", "remaining_time": "0:23:54", "throughput": 7258.27, "total_tokens": 934208}
{"current_steps": 975, "total_steps": 11784, "loss": 0.0767, "lr": 1.652247667514843e-06, "epoch": 0.08273930753564154, "percentage": 8.27, "elapsed_time": "0:02:09", "remaining_time": "0:23:50", "throughput": 7274.01, "total_tokens": 938624}
{"current_steps": 980, "total_steps": 11784, "loss": 0.0286, "lr": 1.660729431721798e-06, "epoch": 0.08316361167684996, "percentage": 8.32, "elapsed_time": "0:02:09", "remaining_time": "0:23:46", "throughput": 7290.47, "total_tokens": 943168}
{"current_steps": 985, "total_steps": 11784, "loss": 0.0942, "lr": 1.669211195928753e-06, "epoch": 0.08358791581805838, "percentage": 8.36, "elapsed_time": "0:02:09", "remaining_time": "0:23:42", "throughput": 7309.21, "total_tokens": 948032}
{"current_steps": 990, "total_steps": 11784, "loss": 0.0874, "lr": 1.6776929601357082e-06, "epoch": 0.0840122199592668, "percentage": 8.4, "elapsed_time": "0:02:10", "remaining_time": "0:23:38", "throughput": 7335.87, "total_tokens": 954176}
{"current_steps": 995, "total_steps": 11784, "loss": 0.0855, "lr": 1.6861747243426632e-06, "epoch": 0.08443652410047522, "percentage": 8.44, "elapsed_time": "0:02:10", "remaining_time": "0:23:33", "throughput": 7353.48, "total_tokens": 958912}
{"current_steps": 1000, "total_steps": 11784, "loss": 0.1609, "lr": 1.6946564885496183e-06, "epoch": 0.08486082824168364, "percentage": 8.49, "elapsed_time": "0:02:10", "remaining_time": "0:23:29", "throughput": 7368.25, "total_tokens": 963264}
{"current_steps": 1005, "total_steps": 11784, "loss": 0.0747, "lr": 1.7031382527565731e-06, "epoch": 0.08528513238289205, "percentage": 8.53, "elapsed_time": "0:02:11", "remaining_time": "0:23:25", "throughput": 7387.3, "total_tokens": 968256}
{"current_steps": 1010, "total_steps": 11784, "loss": 0.1322, "lr": 1.7116200169635284e-06, "epoch": 0.08570943652410047, "percentage": 8.57, "elapsed_time": "0:02:11", "remaining_time": "0:23:21", "throughput": 7401.92, "total_tokens": 972608}
{"current_steps": 1015, "total_steps": 11784, "loss": 0.0859, "lr": 1.7201017811704834e-06, "epoch": 0.08613374066530889, "percentage": 8.61, "elapsed_time": "0:02:11", "remaining_time": "0:23:17", "throughput": 7422.31, "total_tokens": 977856}
{"current_steps": 1020, "total_steps": 11784, "loss": 0.0987, "lr": 1.7285835453774385e-06, "epoch": 0.08655804480651731, "percentage": 8.66, "elapsed_time": "0:02:12", "remaining_time": "0:23:13", "throughput": 7440.24, "total_tokens": 982720}
{"current_steps": 1025, "total_steps": 11784, "loss": 0.1228, "lr": 1.7370653095843936e-06, "epoch": 0.08698234894772573, "percentage": 8.7, "elapsed_time": "0:02:12", "remaining_time": "0:23:09", "throughput": 7457.84, "total_tokens": 987584}
{"current_steps": 1030, "total_steps": 11784, "loss": 0.082, "lr": 1.7455470737913484e-06, "epoch": 0.08740665308893415, "percentage": 8.74, "elapsed_time": "0:02:12", "remaining_time": "0:23:06", "throughput": 7475.61, "total_tokens": 992448}
{"current_steps": 1035, "total_steps": 11784, "loss": 0.1068, "lr": 1.7540288379983035e-06, "epoch": 0.08783095723014257, "percentage": 8.78, "elapsed_time": "0:02:13", "remaining_time": "0:23:02", "throughput": 7492.6, "total_tokens": 997184}
{"current_steps": 1040, "total_steps": 11784, "loss": 0.0649, "lr": 1.7625106022052587e-06, "epoch": 0.08825526137135098, "percentage": 8.83, "elapsed_time": "0:02:13", "remaining_time": "0:22:58", "throughput": 7512.38, "total_tokens": 1002432}
{"current_steps": 1045, "total_steps": 11784, "loss": 0.0748, "lr": 1.7709923664122138e-06, "epoch": 0.0886795655125594, "percentage": 8.87, "elapsed_time": "0:02:13", "remaining_time": "0:22:54", "throughput": 7529.95, "total_tokens": 1007360}
{"current_steps": 1050, "total_steps": 11784, "loss": 0.0598, "lr": 1.7794741306191686e-06, "epoch": 0.08910386965376782, "percentage": 8.91, "elapsed_time": "0:02:14", "remaining_time": "0:22:51", "throughput": 7545.17, "total_tokens": 1011968}
{"current_steps": 1055, "total_steps": 11784, "loss": 0.0976, "lr": 1.7879558948261237e-06, "epoch": 0.08952817379497624, "percentage": 8.95, "elapsed_time": "0:02:14", "remaining_time": "0:22:47", "throughput": 7562.64, "total_tokens": 1016896}
{"current_steps": 1060, "total_steps": 11784, "loss": 0.1005, "lr": 1.7964376590330787e-06, "epoch": 0.08995247793618466, "percentage": 9.0, "elapsed_time": "0:02:14", "remaining_time": "0:22:43", "throughput": 7581.0, "total_tokens": 1021952}
{"current_steps": 1065, "total_steps": 11784, "loss": 0.1977, "lr": 1.8049194232400338e-06, "epoch": 0.09037678207739308, "percentage": 9.04, "elapsed_time": "0:02:15", "remaining_time": "0:22:40", "throughput": 7596.22, "total_tokens": 1026560}
{"current_steps": 1070, "total_steps": 11784, "loss": 0.0821, "lr": 1.813401187446989e-06, "epoch": 0.09080108621860149, "percentage": 9.08, "elapsed_time": "0:02:15", "remaining_time": "0:22:36", "throughput": 7612.78, "total_tokens": 1031360}
{"current_steps": 1075, "total_steps": 11784, "loss": 0.1014, "lr": 1.821882951653944e-06, "epoch": 0.09122539035980991, "percentage": 9.12, "elapsed_time": "0:02:15", "remaining_time": "0:22:33", "throughput": 7631.25, "total_tokens": 1036480}
{"current_steps": 1080, "total_steps": 11784, "loss": 0.0861, "lr": 1.830364715860899e-06, "epoch": 0.09164969450101833, "percentage": 9.16, "elapsed_time": "0:02:16", "remaining_time": "0:22:29", "throughput": 7646.08, "total_tokens": 1041024}
{"current_steps": 1085, "total_steps": 11784, "loss": 0.0588, "lr": 1.838846480067854e-06, "epoch": 0.09207399864222675, "percentage": 9.21, "elapsed_time": "0:02:16", "remaining_time": "0:22:25", "throughput": 7659.19, "total_tokens": 1045312}
{"current_steps": 1090, "total_steps": 11784, "loss": 0.0759, "lr": 1.847328244274809e-06, "epoch": 0.09249830278343517, "percentage": 9.25, "elapsed_time": "0:02:16", "remaining_time": "0:22:22", "throughput": 7676.21, "total_tokens": 1050240}
{"current_steps": 1095, "total_steps": 11784, "loss": 0.09, "lr": 1.8558100084817641e-06, "epoch": 0.09292260692464359, "percentage": 9.29, "elapsed_time": "0:02:17", "remaining_time": "0:22:19", "throughput": 7696.44, "total_tokens": 1055744}
{"current_steps": 1100, "total_steps": 11784, "loss": 0.073, "lr": 1.864291772688719e-06, "epoch": 0.09334691106585201, "percentage": 9.33, "elapsed_time": "0:02:17", "remaining_time": "0:22:15", "throughput": 7711.27, "total_tokens": 1060352}
{"current_steps": 1105, "total_steps": 11784, "loss": 0.1046, "lr": 1.8727735368956743e-06, "epoch": 0.09377121520706042, "percentage": 9.38, "elapsed_time": "0:02:17", "remaining_time": "0:22:12", "throughput": 7729.03, "total_tokens": 1065472}
{"current_steps": 1110, "total_steps": 11784, "loss": 0.0767, "lr": 1.8812553011026293e-06, "epoch": 0.09419551934826884, "percentage": 9.42, "elapsed_time": "0:02:18", "remaining_time": "0:22:08", "throughput": 7744.45, "total_tokens": 1070144}
{"current_steps": 1115, "total_steps": 11784, "loss": 0.0741, "lr": 1.8897370653095844e-06, "epoch": 0.09461982348947726, "percentage": 9.46, "elapsed_time": "0:02:18", "remaining_time": "0:22:05", "throughput": 7758.86, "total_tokens": 1074688}
{"current_steps": 1120, "total_steps": 11784, "loss": 0.0479, "lr": 1.8982188295165394e-06, "epoch": 0.09504412763068568, "percentage": 9.5, "elapsed_time": "0:02:18", "remaining_time": "0:22:01", "throughput": 7771.78, "total_tokens": 1079040}
{"current_steps": 1125, "total_steps": 11784, "loss": 0.0952, "lr": 1.9067005937234943e-06, "epoch": 0.0954684317718941, "percentage": 9.55, "elapsed_time": "0:02:19", "remaining_time": "0:21:58", "throughput": 7785.03, "total_tokens": 1083456}
{"current_steps": 1130, "total_steps": 11784, "loss": 0.1757, "lr": 1.9151823579304493e-06, "epoch": 0.09589273591310252, "percentage": 9.59, "elapsed_time": "0:02:19", "remaining_time": "0:21:55", "throughput": 7799.64, "total_tokens": 1088064}
{"current_steps": 1135, "total_steps": 11784, "loss": 0.0502, "lr": 1.9236641221374044e-06, "epoch": 0.09631704005431092, "percentage": 9.63, "elapsed_time": "0:02:19", "remaining_time": "0:21:51", "throughput": 7813.47, "total_tokens": 1092544}
{"current_steps": 1140, "total_steps": 11784, "loss": 0.0995, "lr": 1.9321458863443595e-06, "epoch": 0.09674134419551934, "percentage": 9.67, "elapsed_time": "0:02:20", "remaining_time": "0:21:48", "throughput": 7831.43, "total_tokens": 1097792}
{"current_steps": 1145, "total_steps": 11784, "loss": 0.1066, "lr": 1.9406276505513145e-06, "epoch": 0.09716564833672776, "percentage": 9.72, "elapsed_time": "0:02:20", "remaining_time": "0:21:45", "throughput": 7848.96, "total_tokens": 1102912}
{"current_steps": 1150, "total_steps": 11784, "loss": 0.0254, "lr": 1.9491094147582696e-06, "epoch": 0.09758995247793618, "percentage": 9.76, "elapsed_time": "0:02:20", "remaining_time": "0:21:42", "throughput": 7865.12, "total_tokens": 1107840}
{"current_steps": 1155, "total_steps": 11784, "loss": 0.1516, "lr": 1.9575911789652246e-06, "epoch": 0.0980142566191446, "percentage": 9.8, "elapsed_time": "0:02:21", "remaining_time": "0:21:39", "throughput": 7879.36, "total_tokens": 1112448}
{"current_steps": 1160, "total_steps": 11784, "loss": 0.1223, "lr": 1.9660729431721797e-06, "epoch": 0.09843856076035302, "percentage": 9.84, "elapsed_time": "0:02:21", "remaining_time": "0:21:36", "throughput": 7894.37, "total_tokens": 1117248}
{"current_steps": 1165, "total_steps": 11784, "loss": 0.089, "lr": 1.9745547073791347e-06, "epoch": 0.09886286490156145, "percentage": 9.89, "elapsed_time": "0:02:21", "remaining_time": "0:21:33", "throughput": 7909.14, "total_tokens": 1121984}
{"current_steps": 1170, "total_steps": 11784, "loss": 0.0988, "lr": 1.98303647158609e-06, "epoch": 0.09928716904276985, "percentage": 9.93, "elapsed_time": "0:02:22", "remaining_time": "0:21:30", "throughput": 7925.64, "total_tokens": 1127040}
{"current_steps": 1175, "total_steps": 11784, "loss": 0.0578, "lr": 1.991518235793045e-06, "epoch": 0.09971147318397827, "percentage": 9.97, "elapsed_time": "0:02:22", "remaining_time": "0:21:26", "throughput": 7941.13, "total_tokens": 1131904}
{"current_steps": 1180, "total_steps": 11784, "loss": 0.1054, "lr": 2e-06, "epoch": 0.10013577732518669, "percentage": 10.01, "elapsed_time": "0:02:22", "remaining_time": "0:21:23", "throughput": 7954.32, "total_tokens": 1136384}
{"current_steps": 1180, "total_steps": 11784, "eval_loss": 0.07076410949230194, "epoch": 0.10013577732518669, "percentage": 10.01, "elapsed_time": "0:02:38", "remaining_time": "0:23:45", "throughput": 7163.83, "total_tokens": 1136384}
{"current_steps": 1185, "total_steps": 11784, "loss": 0.0543, "lr": 1.999998903046209e-06, "epoch": 0.10056008146639511, "percentage": 10.06, "elapsed_time": "0:03:25", "remaining_time": "0:30:38", "throughput": 5549.27, "total_tokens": 1140864}
{"current_steps": 1190, "total_steps": 11784, "loss": 0.1416, "lr": 1.999995612187243e-06, "epoch": 0.10098438560760353, "percentage": 10.1, "elapsed_time": "0:03:25", "remaining_time": "0:30:33", "throughput": 5562.43, "total_tokens": 1145408}
{"current_steps": 1195, "total_steps": 11784, "loss": 0.1497, "lr": 1.9999901274303226e-06, "epoch": 0.10140868974881195, "percentage": 10.14, "elapsed_time": "0:03:26", "remaining_time": "0:30:27", "throughput": 5577.56, "total_tokens": 1150400}
{"current_steps": 1200, "total_steps": 11784, "loss": 0.1094, "lr": 1.9999824487874795e-06, "epoch": 0.10183299389002037, "percentage": 10.18, "elapsed_time": "0:03:26", "remaining_time": "0:30:22", "throughput": 5590.36, "total_tokens": 1154880}
{"current_steps": 1205, "total_steps": 11784, "loss": 0.1046, "lr": 1.999972576275561e-06, "epoch": 0.10225729803122878, "percentage": 10.23, "elapsed_time": "0:03:26", "remaining_time": "0:30:16", "throughput": 5604.03, "total_tokens": 1159552}
{"current_steps": 1210, "total_steps": 11784, "loss": 0.0262, "lr": 1.999960509916226e-06, "epoch": 0.1026816021724372, "percentage": 10.27, "elapsed_time": "0:03:27", "remaining_time": "0:30:11", "throughput": 5620.01, "total_tokens": 1164800}
{"current_steps": 1215, "total_steps": 11784, "loss": 0.0621, "lr": 1.9999462497359463e-06, "epoch": 0.10310590631364562, "percentage": 10.31, "elapsed_time": "0:03:27", "remaining_time": "0:30:05", "throughput": 5637.12, "total_tokens": 1170304}
{"current_steps": 1220, "total_steps": 11784, "loss": 0.0834, "lr": 1.999929795766009e-06, "epoch": 0.10353021045485404, "percentage": 10.35, "elapsed_time": "0:03:27", "remaining_time": "0:30:00", "throughput": 5650.95, "total_tokens": 1175040}
{"current_steps": 1225, "total_steps": 11784, "loss": 0.0045, "lr": 1.999911148042511e-06, "epoch": 0.10395451459606246, "percentage": 10.4, "elapsed_time": "0:03:28", "remaining_time": "0:29:55", "throughput": 5666.88, "total_tokens": 1180288}
{"current_steps": 1230, "total_steps": 11784, "loss": 0.097, "lr": 1.999890306606365e-06, "epoch": 0.10437881873727088, "percentage": 10.44, "elapsed_time": "0:03:28", "remaining_time": "0:29:49", "throughput": 5680.81, "total_tokens": 1185088}
{"current_steps": 1235, "total_steps": 11784, "loss": 0.0987, "lr": 1.9998672715032944e-06, "epoch": 0.10480312287847929, "percentage": 10.48, "elapsed_time": "0:03:28", "remaining_time": "0:29:44", "throughput": 5693.17, "total_tokens": 1189504}
{"current_steps": 1240, "total_steps": 11784, "loss": 0.1065, "lr": 1.999842042783836e-06, "epoch": 0.10522742701968771, "percentage": 10.52, "elapsed_time": "0:03:29", "remaining_time": "0:29:39", "throughput": 5707.04, "total_tokens": 1194304}
{"current_steps": 1245, "total_steps": 11784, "loss": 0.0156, "lr": 1.99981462050334e-06, "epoch": 0.10565173116089613, "percentage": 10.57, "elapsed_time": "0:03:29", "remaining_time": "0:29:34", "throughput": 5720.28, "total_tokens": 1198976}
{"current_steps": 1250, "total_steps": 11784, "loss": 0.0797, "lr": 1.999785004721968e-06, "epoch": 0.10607603530210455, "percentage": 10.61, "elapsed_time": "0:03:29", "remaining_time": "0:29:29", "throughput": 5732.92, "total_tokens": 1203520}
{"current_steps": 1255, "total_steps": 11784, "loss": 0.0947, "lr": 1.9997531955046936e-06, "epoch": 0.10650033944331297, "percentage": 10.65, "elapsed_time": "0:03:30", "remaining_time": "0:29:23", "throughput": 5744.51, "total_tokens": 1207808}
{"current_steps": 1260, "total_steps": 11784, "loss": 0.0938, "lr": 1.9997191929213044e-06, "epoch": 0.10692464358452139, "percentage": 10.69, "elapsed_time": "0:03:30", "remaining_time": "0:29:19", "throughput": 5759.73, "total_tokens": 1212992}
{"current_steps": 1265, "total_steps": 11784, "loss": 0.1488, "lr": 1.999682997046398e-06, "epoch": 0.10734894772572981, "percentage": 10.73, "elapsed_time": "0:03:30", "remaining_time": "0:29:13", "throughput": 5771.49, "total_tokens": 1217344}
{"current_steps": 1270, "total_steps": 11784, "loss": 0.0821, "lr": 1.9996446079593855e-06, "epoch": 0.10777325186693822, "percentage": 10.78, "elapsed_time": "0:03:31", "remaining_time": "0:29:08", "throughput": 5784.93, "total_tokens": 1222080}
{"current_steps": 1275, "total_steps": 11784, "loss": 0.1393, "lr": 1.999604025744489e-06, "epoch": 0.10819755600814664, "percentage": 10.82, "elapsed_time": "0:03:31", "remaining_time": "0:29:03", "throughput": 5797.92, "total_tokens": 1226752}
{"current_steps": 1280, "total_steps": 11784, "loss": 0.1702, "lr": 1.9995612504907414e-06, "epoch": 0.10862186014935506, "percentage": 10.86, "elapsed_time": "0:03:31", "remaining_time": "0:28:59", "throughput": 5812.39, "total_tokens": 1231808}
{"current_steps": 1285, "total_steps": 11784, "loss": 0.1218, "lr": 1.999516282291988e-06, "epoch": 0.10904616429056348, "percentage": 10.9, "elapsed_time": "0:03:32", "remaining_time": "0:28:54", "throughput": 5824.86, "total_tokens": 1236352}
{"current_steps": 1290, "total_steps": 11784, "loss": 0.0983, "lr": 1.9994691212468853e-06, "epoch": 0.1094704684317719, "percentage": 10.95, "elapsed_time": "0:03:32", "remaining_time": "0:28:49", "throughput": 5838.11, "total_tokens": 1241088}
{"current_steps": 1295, "total_steps": 11784, "loss": 0.0506, "lr": 1.9994197674588997e-06, "epoch": 0.10989477257298032, "percentage": 10.99, "elapsed_time": "0:03:32", "remaining_time": "0:28:44", "throughput": 5853.3, "total_tokens": 1246336}
{"current_steps": 1300, "total_steps": 11784, "loss": 0.1021, "lr": 1.999368221036309e-06, "epoch": 0.11031907671418872, "percentage": 11.03, "elapsed_time": "0:03:33", "remaining_time": "0:28:39", "throughput": 5868.82, "total_tokens": 1251648}
{"current_steps": 1305, "total_steps": 11784, "loss": 0.0848, "lr": 1.9993144820922015e-06, "epoch": 0.11074338085539714, "percentage": 11.07, "elapsed_time": "0:03:33", "remaining_time": "0:28:35", "throughput": 5882.1, "total_tokens": 1256448}
{"current_steps": 1310, "total_steps": 11784, "loss": 0.096, "lr": 1.9992585507444757e-06, "epoch": 0.11116768499660556, "percentage": 11.12, "elapsed_time": "0:03:33", "remaining_time": "0:28:30", "throughput": 5895.06, "total_tokens": 1261184}
{"current_steps": 1315, "total_steps": 11784, "loss": 0.1, "lr": 1.999200427115839e-06, "epoch": 0.11159198913781398, "percentage": 11.16, "elapsed_time": "0:03:34", "remaining_time": "0:28:25", "throughput": 5909.56, "total_tokens": 1266304}
{"current_steps": 1320, "total_steps": 11784, "loss": 0.0415, "lr": 1.99914011133381e-06, "epoch": 0.1120162932790224, "percentage": 11.2, "elapsed_time": "0:03:34", "remaining_time": "0:28:21", "throughput": 5921.61, "total_tokens": 1270848}
{"current_steps": 1325, "total_steps": 11784, "loss": 0.0318, "lr": 1.999077603530716e-06, "epoch": 0.11244059742023083, "percentage": 11.24, "elapsed_time": "0:03:34", "remaining_time": "0:28:16", "throughput": 5934.9, "total_tokens": 1275712}
{"current_steps": 1330, "total_steps": 11784, "loss": 0.0425, "lr": 1.999012903843693e-06, "epoch": 0.11286490156143925, "percentage": 11.29, "elapsed_time": "0:03:35", "remaining_time": "0:28:12", "throughput": 5945.86, "total_tokens": 1280000}
{"current_steps": 1335, "total_steps": 11784, "loss": 0.0826, "lr": 1.9989460124146854e-06, "epoch": 0.11328920570264765, "percentage": 11.33, "elapsed_time": "0:03:35", "remaining_time": "0:28:07", "throughput": 5961.5, "total_tokens": 1285440}
{"current_steps": 1340, "total_steps": 11784, "loss": 0.0835, "lr": 1.998876929390448e-06, "epoch": 0.11371350984385607, "percentage": 11.37, "elapsed_time": "0:03:35", "remaining_time": "0:28:03", "throughput": 5974.19, "total_tokens": 1290176}
{"current_steps": 1345, "total_steps": 11784, "loss": 0.108, "lr": 1.9988056549225423e-06, "epoch": 0.11413781398506449, "percentage": 11.41, "elapsed_time": "0:03:36", "remaining_time": "0:27:58", "throughput": 5986.76, "total_tokens": 1294912}
{"current_steps": 1350, "total_steps": 11784, "loss": 0.0703, "lr": 1.9987321891673375e-06, "epoch": 0.11456211812627291, "percentage": 11.46, "elapsed_time": "0:03:36", "remaining_time": "0:27:54", "throughput": 5997.36, "total_tokens": 1299136}
{"current_steps": 1355, "total_steps": 11784, "loss": 0.1112, "lr": 1.9986565322860116e-06, "epoch": 0.11498642226748133, "percentage": 11.5, "elapsed_time": "0:03:36", "remaining_time": "0:27:49", "throughput": 6010.21, "total_tokens": 1303936}
{"current_steps": 1360, "total_steps": 11784, "loss": 0.045, "lr": 1.9985786844445474e-06, "epoch": 0.11541072640868975, "percentage": 11.54, "elapsed_time": "0:03:37", "remaining_time": "0:27:45", "throughput": 6023.86, "total_tokens": 1308928}
{"current_steps": 1365, "total_steps": 11784, "loss": 0.0518, "lr": 1.9984986458137366e-06, "epoch": 0.11583503054989816, "percentage": 11.58, "elapsed_time": "0:03:37", "remaining_time": "0:27:41", "throughput": 6036.62, "total_tokens": 1313728}
{"current_steps": 1370, "total_steps": 11784, "loss": 0.062, "lr": 1.998416416569177e-06, "epoch": 0.11625933469110658, "percentage": 11.63, "elapsed_time": "0:03:37", "remaining_time": "0:27:36", "throughput": 6048.82, "total_tokens": 1318400}
{"current_steps": 1375, "total_steps": 11784, "loss": 0.0946, "lr": 1.9983319968912714e-06, "epoch": 0.116683638832315, "percentage": 11.67, "elapsed_time": "0:03:38", "remaining_time": "0:27:32", "throughput": 6059.82, "total_tokens": 1322752}
{"current_steps": 1380, "total_steps": 11784, "loss": 0.0354, "lr": 1.9982453869652286e-06, "epoch": 0.11710794297352342, "percentage": 11.71, "elapsed_time": "0:03:38", "remaining_time": "0:27:28", "throughput": 6072.63, "total_tokens": 1327552}
{"current_steps": 1385, "total_steps": 11784, "loss": 0.084, "lr": 1.9981565869810637e-06, "epoch": 0.11753224711473184, "percentage": 11.75, "elapsed_time": "0:03:38", "remaining_time": "0:27:23", "throughput": 6082.95, "total_tokens": 1331776}
{"current_steps": 1390, "total_steps": 11784, "loss": 0.0591, "lr": 1.998065597133594e-06, "epoch": 0.11795655125594026, "percentage": 11.8, "elapsed_time": "0:03:39", "remaining_time": "0:27:19", "throughput": 6093.81, "total_tokens": 1336128}
{"current_steps": 1395, "total_steps": 11784, "loss": 0.1068, "lr": 1.9979724176224447e-06, "epoch": 0.11838085539714868, "percentage": 11.84, "elapsed_time": "0:03:39", "remaining_time": "0:27:15", "throughput": 6105.87, "total_tokens": 1340800}
{"current_steps": 1400, "total_steps": 11784, "loss": 0.0982, "lr": 1.997877048652042e-06, "epoch": 0.11880515953835709, "percentage": 11.88, "elapsed_time": "0:03:39", "remaining_time": "0:27:11", "throughput": 6117.61, "total_tokens": 1345408}
{"current_steps": 1405, "total_steps": 11784, "loss": 0.12, "lr": 1.9977794904316163e-06, "epoch": 0.11922946367956551, "percentage": 11.92, "elapsed_time": "0:03:40", "remaining_time": "0:27:07", "throughput": 6130.12, "total_tokens": 1350208}
{"current_steps": 1410, "total_steps": 11784, "loss": 0.0689, "lr": 1.9976797431752023e-06, "epoch": 0.11965376782077393, "percentage": 11.97, "elapsed_time": "0:03:40", "remaining_time": "0:27:02", "throughput": 6141.13, "total_tokens": 1354624}
{"current_steps": 1415, "total_steps": 11784, "loss": 0.0574, "lr": 1.9975778071016357e-06, "epoch": 0.12007807196198235, "percentage": 12.01, "elapsed_time": "0:03:40", "remaining_time": "0:26:58", "throughput": 6152.79, "total_tokens": 1359232}
{"current_steps": 1420, "total_steps": 11784, "loss": 0.0794, "lr": 1.997473682434555e-06, "epoch": 0.12050237610319077, "percentage": 12.05, "elapsed_time": "0:03:41", "remaining_time": "0:26:54", "throughput": 6164.78, "total_tokens": 1363904}
{"current_steps": 1425, "total_steps": 11784, "loss": 0.0577, "lr": 1.9973673694023998e-06, "epoch": 0.12092668024439919, "percentage": 12.09, "elapsed_time": "0:03:41", "remaining_time": "0:26:50", "throughput": 6176.19, "total_tokens": 1368448}
{"current_steps": 1430, "total_steps": 11784, "loss": 0.099, "lr": 1.997258868238411e-06, "epoch": 0.12135098438560761, "percentage": 12.14, "elapsed_time": "0:03:41", "remaining_time": "0:26:46", "throughput": 6187.08, "total_tokens": 1372864}
{"current_steps": 1435, "total_steps": 11784, "loss": 0.0979, "lr": 1.997148179180631e-06, "epoch": 0.12177528852681602, "percentage": 12.18, "elapsed_time": "0:03:42", "remaining_time": "0:26:42", "throughput": 6200.39, "total_tokens": 1377920}
{"current_steps": 1440, "total_steps": 11784, "loss": 0.0951, "lr": 1.9970353024719003e-06, "epoch": 0.12219959266802444, "percentage": 12.22, "elapsed_time": "0:03:42", "remaining_time": "0:26:38", "throughput": 6211.7, "total_tokens": 1382464}
{"current_steps": 1445, "total_steps": 11784, "loss": 0.065, "lr": 1.9969202383598605e-06, "epoch": 0.12262389680923286, "percentage": 12.26, "elapsed_time": "0:03:42", "remaining_time": "0:26:34", "throughput": 6223.2, "total_tokens": 1387072}
{"current_steps": 1450, "total_steps": 11784, "loss": 0.0363, "lr": 1.996802987096952e-06, "epoch": 0.12304820095044128, "percentage": 12.3, "elapsed_time": "0:03:43", "remaining_time": "0:26:30", "throughput": 6233.92, "total_tokens": 1391488}
{"current_steps": 1455, "total_steps": 11784, "loss": 0.1148, "lr": 1.9966835489404123e-06, "epoch": 0.1234725050916497, "percentage": 12.35, "elapsed_time": "0:03:43", "remaining_time": "0:26:27", "throughput": 6250.5, "total_tokens": 1397440}
{"current_steps": 1460, "total_steps": 11784, "loss": 0.0559, "lr": 1.996561924152278e-06, "epoch": 0.12389680923285812, "percentage": 12.39, "elapsed_time": "0:03:43", "remaining_time": "0:26:23", "throughput": 6261.86, "total_tokens": 1402048}
{"current_steps": 1465, "total_steps": 11784, "loss": 0.0275, "lr": 1.996438112999383e-06, "epoch": 0.12432111337406652, "percentage": 12.43, "elapsed_time": "0:03:44", "remaining_time": "0:26:19", "throughput": 6273.79, "total_tokens": 1406784}
{"current_steps": 1470, "total_steps": 11784, "loss": 0.1324, "lr": 1.9963121157533573e-06, "epoch": 0.12474541751527495, "percentage": 12.47, "elapsed_time": "0:03:44", "remaining_time": "0:26:15", "throughput": 6284.81, "total_tokens": 1411328}
{"current_steps": 1475, "total_steps": 11784, "loss": 0.1638, "lr": 1.9961839326906272e-06, "epoch": 0.12516972165648338, "percentage": 12.52, "elapsed_time": "0:03:44", "remaining_time": "0:26:11", "throughput": 6296.09, "total_tokens": 1415936}
{"current_steps": 1480, "total_steps": 11784, "loss": 0.1479, "lr": 1.9960535640924146e-06, "epoch": 0.12559402579769177, "percentage": 12.56, "elapsed_time": "0:03:45", "remaining_time": "0:26:08", "throughput": 6310.02, "total_tokens": 1421248}
{"current_steps": 1485, "total_steps": 11784, "loss": 0.0392, "lr": 1.995921010244736e-06, "epoch": 0.1260183299389002, "percentage": 12.6, "elapsed_time": "0:03:45", "remaining_time": "0:26:04", "throughput": 6320.77, "total_tokens": 1425728}
{"current_steps": 1490, "total_steps": 11784, "loss": 0.0857, "lr": 1.9957862714384025e-06, "epoch": 0.1264426340801086, "percentage": 12.64, "elapsed_time": "0:03:45", "remaining_time": "0:26:00", "throughput": 6335.25, "total_tokens": 1431296}
{"current_steps": 1495, "total_steps": 11784, "loss": 0.0819, "lr": 1.9956493479690188e-06, "epoch": 0.12686693822131703, "percentage": 12.69, "elapsed_time": "0:03:46", "remaining_time": "0:25:57", "throughput": 6347.37, "total_tokens": 1436160}
{"current_steps": 1500, "total_steps": 11784, "loss": 0.1003, "lr": 1.9955102401369814e-06, "epoch": 0.12729124236252545, "percentage": 12.73, "elapsed_time": "0:03:46", "remaining_time": "0:25:53", "throughput": 6359.24, "total_tokens": 1440960}
{"current_steps": 1505, "total_steps": 11784, "loss": 0.0611, "lr": 1.9953689482474806e-06, "epoch": 0.12771554650373387, "percentage": 12.77, "elapsed_time": "0:03:46", "remaining_time": "0:25:49", "throughput": 6371.05, "total_tokens": 1445760}
{"current_steps": 1510, "total_steps": 11784, "loss": 0.0144, "lr": 1.995225472610498e-06, "epoch": 0.1281398506449423, "percentage": 12.81, "elapsed_time": "0:03:47", "remaining_time": "0:25:46", "throughput": 6383.33, "total_tokens": 1450688}
{"current_steps": 1515, "total_steps": 11784, "loss": 0.1675, "lr": 1.9950798135408057e-06, "epoch": 0.12856415478615071, "percentage": 12.86, "elapsed_time": "0:03:47", "remaining_time": "0:25:42", "throughput": 6395.36, "total_tokens": 1455552}
{"current_steps": 1520, "total_steps": 11784, "loss": 0.0808, "lr": 1.994931971357966e-06, "epoch": 0.12898845892735913, "percentage": 12.9, "elapsed_time": "0:03:47", "remaining_time": "0:25:39", "throughput": 6407.35, "total_tokens": 1460416}
{"current_steps": 1525, "total_steps": 11784, "loss": 0.0717, "lr": 1.9947819463863316e-06, "epoch": 0.12941276306856755, "percentage": 12.94, "elapsed_time": "0:03:48", "remaining_time": "0:25:35", "throughput": 6423.43, "total_tokens": 1466432}
{"current_steps": 1530, "total_steps": 11784, "loss": 0.0989, "lr": 1.9946297389550432e-06, "epoch": 0.12983706720977597, "percentage": 12.98, "elapsed_time": "0:03:48", "remaining_time": "0:25:32", "throughput": 6435.15, "total_tokens": 1471232}
{"current_steps": 1535, "total_steps": 11784, "loss": 0.0587, "lr": 1.9944753493980292e-06, "epoch": 0.1302613713509844, "percentage": 13.03, "elapsed_time": "0:03:48", "remaining_time": "0:25:28", "throughput": 6447.27, "total_tokens": 1476160}
{"current_steps": 1540, "total_steps": 11784, "loss": 0.0755, "lr": 1.9943187780540062e-06, "epoch": 0.13068567549219282, "percentage": 13.07, "elapsed_time": "0:03:49", "remaining_time": "0:25:25", "throughput": 6459.49, "total_tokens": 1481152}
{"current_steps": 1545, "total_steps": 11784, "loss": 0.1668, "lr": 1.994160025266478e-06, "epoch": 0.13110997963340124, "percentage": 13.11, "elapsed_time": "0:03:49", "remaining_time": "0:25:21", "throughput": 6472.42, "total_tokens": 1486336}
{"current_steps": 1550, "total_steps": 11784, "loss": 0.0588, "lr": 1.9939990913837327e-06, "epoch": 0.13153428377460963, "percentage": 13.15, "elapsed_time": "0:03:49", "remaining_time": "0:25:18", "throughput": 6484.4, "total_tokens": 1491264}
{"current_steps": 1555, "total_steps": 11784, "loss": 0.0672, "lr": 1.993835976758845e-06, "epoch": 0.13195858791581805, "percentage": 13.2, "elapsed_time": "0:03:50", "remaining_time": "0:25:14", "throughput": 6494.34, "total_tokens": 1495680}
{"current_steps": 1560, "total_steps": 11784, "loss": 0.1687, "lr": 1.993670681749673e-06, "epoch": 0.13238289205702647, "percentage": 13.24, "elapsed_time": "0:03:50", "remaining_time": "0:25:11", "throughput": 6509.18, "total_tokens": 1501376}
{"current_steps": 1565, "total_steps": 11784, "loss": 0.1089, "lr": 1.9935032067188587e-06, "epoch": 0.1328071961982349, "percentage": 13.28, "elapsed_time": "0:03:50", "remaining_time": "0:25:08", "throughput": 6520.65, "total_tokens": 1506176}
{"current_steps": 1570, "total_steps": 11784, "loss": 0.0749, "lr": 1.993333552033827e-06, "epoch": 0.1332315003394433, "percentage": 13.32, "elapsed_time": "0:03:51", "remaining_time": "0:25:05", "throughput": 6535.15, "total_tokens": 1511808}
{"current_steps": 1575, "total_steps": 11784, "loss": 0.0406, "lr": 1.9931617180667844e-06, "epoch": 0.13365580448065173, "percentage": 13.37, "elapsed_time": "0:03:51", "remaining_time": "0:25:01", "throughput": 6546.4, "total_tokens": 1516608}
{"current_steps": 1580, "total_steps": 11784, "loss": 0.0988, "lr": 1.992987705194719e-06, "epoch": 0.13408010862186015, "percentage": 13.41, "elapsed_time": "0:03:51", "remaining_time": "0:24:58", "throughput": 6557.28, "total_tokens": 1521280}
{"current_steps": 1585, "total_steps": 11784, "loss": 0.0683, "lr": 1.9928115137993983e-06, "epoch": 0.13450441276306857, "percentage": 13.45, "elapsed_time": "0:03:52", "remaining_time": "0:24:54", "throughput": 6568.55, "total_tokens": 1526080}
{"current_steps": 1590, "total_steps": 11784, "loss": 0.0429, "lr": 1.9926331442673703e-06, "epoch": 0.134928716904277, "percentage": 13.49, "elapsed_time": "0:03:52", "remaining_time": "0:24:51", "throughput": 6580.05, "total_tokens": 1530944}
{"current_steps": 1595, "total_steps": 11784, "loss": 0.1098, "lr": 1.992452596989962e-06, "epoch": 0.1353530210454854, "percentage": 13.54, "elapsed_time": "0:03:53", "remaining_time": "0:24:48", "throughput": 6593.12, "total_tokens": 1536256}
{"current_steps": 1600, "total_steps": 11784, "loss": 0.0842, "lr": 1.9922698723632763e-06, "epoch": 0.13577732518669383, "percentage": 13.58, "elapsed_time": "0:03:53", "remaining_time": "0:24:45", "throughput": 6603.56, "total_tokens": 1540864}
{"current_steps": 1605, "total_steps": 11784, "loss": 0.077, "lr": 1.992084970788195e-06, "epoch": 0.13620162932790225, "percentage": 13.62, "elapsed_time": "0:03:53", "remaining_time": "0:24:42", "throughput": 6613.79, "total_tokens": 1545536}
{"current_steps": 1610, "total_steps": 11784, "loss": 0.1246, "lr": 1.991897892670375e-06, "epoch": 0.13662593346911067, "percentage": 13.66, "elapsed_time": "0:03:54", "remaining_time": "0:24:38", "throughput": 6624.21, "total_tokens": 1550144}
{"current_steps": 1615, "total_steps": 11784, "loss": 0.0509, "lr": 1.9917086384202475e-06, "epoch": 0.13705023761031906, "percentage": 13.71, "elapsed_time": "0:03:54", "remaining_time": "0:24:35", "throughput": 6634.06, "total_tokens": 1554624}
{"current_steps": 1620, "total_steps": 11784, "loss": 0.1169, "lr": 1.9915172084530195e-06, "epoch": 0.13747454175152748, "percentage": 13.75, "elapsed_time": "0:03:54", "remaining_time": "0:24:32", "throughput": 6644.12, "total_tokens": 1559168}
{"current_steps": 1625, "total_steps": 11784, "loss": 0.0867, "lr": 1.9913236031886707e-06, "epoch": 0.1378988458927359, "percentage": 13.79, "elapsed_time": "0:03:55", "remaining_time": "0:24:29", "throughput": 6655.41, "total_tokens": 1564032}
{"current_steps": 1630, "total_steps": 11784, "loss": 0.0813, "lr": 1.9911278230519533e-06, "epoch": 0.13832315003394433, "percentage": 13.83, "elapsed_time": "0:03:55", "remaining_time": "0:24:25", "throughput": 6666.75, "total_tokens": 1568896}
{"current_steps": 1635, "total_steps": 11784, "loss": 0.0779, "lr": 1.9909298684723905e-06, "epoch": 0.13874745417515275, "percentage": 13.87, "elapsed_time": "0:03:55", "remaining_time": "0:24:22", "throughput": 6678.34, "total_tokens": 1573888}
{"current_steps": 1640, "total_steps": 11784, "loss": 0.0649, "lr": 1.9907297398842764e-06, "epoch": 0.13917175831636117, "percentage": 13.92, "elapsed_time": "0:03:55", "remaining_time": "0:24:19", "throughput": 6688.6, "total_tokens": 1578496}
{"current_steps": 1645, "total_steps": 11784, "loss": 0.0418, "lr": 1.9905274377266744e-06, "epoch": 0.1395960624575696, "percentage": 13.96, "elapsed_time": "0:03:56", "remaining_time": "0:24:16", "throughput": 6698.8, "total_tokens": 1583104}
{"current_steps": 1650, "total_steps": 11784, "loss": 0.1031, "lr": 1.9903229624434174e-06, "epoch": 0.140020366598778, "percentage": 14.0, "elapsed_time": "0:03:56", "remaining_time": "0:24:13", "throughput": 6708.7, "total_tokens": 1587648}
{"current_steps": 1655, "total_steps": 11784, "loss": 0.1513, "lr": 1.9901163144831047e-06, "epoch": 0.14044467073998643, "percentage": 14.04, "elapsed_time": "0:03:57", "remaining_time": "0:24:10", "throughput": 6722.24, "total_tokens": 1593216}
{"current_steps": 1660, "total_steps": 11784, "loss": 0.0057, "lr": 1.989907494299103e-06, "epoch": 0.14086897488119485, "percentage": 14.09, "elapsed_time": "0:03:57", "remaining_time": "0:24:07", "throughput": 6733.76, "total_tokens": 1598208}
{"current_steps": 1665, "total_steps": 11784, "loss": 0.0057, "lr": 1.989696502349545e-06, "epoch": 0.14129327902240327, "percentage": 14.13, "elapsed_time": "0:03:57", "remaining_time": "0:24:04", "throughput": 6743.43, "total_tokens": 1602688}
{"current_steps": 1670, "total_steps": 11784, "loss": 0.1691, "lr": 1.9894833390973266e-06, "epoch": 0.1417175831636117, "percentage": 14.17, "elapsed_time": "0:03:57", "remaining_time": "0:24:01", "throughput": 6751.57, "total_tokens": 1606784}
{"current_steps": 1675, "total_steps": 11784, "loss": 0.1757, "lr": 1.9892680050101085e-06, "epoch": 0.1421418873048201, "percentage": 14.21, "elapsed_time": "0:03:58", "remaining_time": "0:23:58", "throughput": 6762.33, "total_tokens": 1611584}
{"current_steps": 1680, "total_steps": 11784, "loss": 0.094, "lr": 1.9890505005603146e-06, "epoch": 0.1425661914460285, "percentage": 14.26, "elapsed_time": "0:03:58", "remaining_time": "0:23:55", "throughput": 6773.74, "total_tokens": 1616576}
{"current_steps": 1685, "total_steps": 11784, "loss": 0.0994, "lr": 1.9888308262251284e-06, "epoch": 0.14299049558723692, "percentage": 14.3, "elapsed_time": "0:03:58", "remaining_time": "0:23:52", "throughput": 6784.63, "total_tokens": 1621440}
{"current_steps": 1690, "total_steps": 11784, "loss": 0.071, "lr": 1.9886089824864956e-06, "epoch": 0.14341479972844534, "percentage": 14.34, "elapsed_time": "0:03:59", "remaining_time": "0:23:49", "throughput": 6795.72, "total_tokens": 1626368}
{"current_steps": 1695, "total_steps": 11784, "loss": 0.0566, "lr": 1.9883849698311213e-06, "epoch": 0.14383910386965376, "percentage": 14.38, "elapsed_time": "0:03:59", "remaining_time": "0:23:46", "throughput": 6804.77, "total_tokens": 1630784}
{"current_steps": 1700, "total_steps": 11784, "loss": 0.0815, "lr": 1.988158788750468e-06, "epoch": 0.14426340801086218, "percentage": 14.43, "elapsed_time": "0:03:59", "remaining_time": "0:23:43", "throughput": 6815.96, "total_tokens": 1635776}
{"current_steps": 1705, "total_steps": 11784, "loss": 0.0967, "lr": 1.9879304397407566e-06, "epoch": 0.1446877121520706, "percentage": 14.47, "elapsed_time": "0:04:00", "remaining_time": "0:23:40", "throughput": 6826.13, "total_tokens": 1640448}
{"current_steps": 1710, "total_steps": 11784, "loss": 0.0206, "lr": 1.987699923302963e-06, "epoch": 0.14511201629327902, "percentage": 14.51, "elapsed_time": "0:04:00", "remaining_time": "0:23:37", "throughput": 6837.14, "total_tokens": 1645440}
{"current_steps": 1715, "total_steps": 11784, "loss": 0.0811, "lr": 1.9874672399428195e-06, "epoch": 0.14553632043448744, "percentage": 14.55, "elapsed_time": "0:04:00", "remaining_time": "0:23:34", "throughput": 6846.67, "total_tokens": 1649984}
{"current_steps": 1720, "total_steps": 11784, "loss": 0.1235, "lr": 1.9872323901708116e-06, "epoch": 0.14596062457569586, "percentage": 14.6, "elapsed_time": "0:04:01", "remaining_time": "0:23:32", "throughput": 6856.83, "total_tokens": 1654720}
{"current_steps": 1725, "total_steps": 11784, "loss": 0.1061, "lr": 1.9869953745021785e-06, "epoch": 0.14638492871690428, "percentage": 14.64, "elapsed_time": "0:04:01", "remaining_time": "0:23:29", "throughput": 6867.69, "total_tokens": 1659648}
{"current_steps": 1730, "total_steps": 11784, "loss": 0.0567, "lr": 1.9867561934569103e-06, "epoch": 0.1468092328581127, "percentage": 14.68, "elapsed_time": "0:04:02", "remaining_time": "0:23:26", "throughput": 6879.57, "total_tokens": 1664896}
{"current_steps": 1735, "total_steps": 11784, "loss": 0.0482, "lr": 1.9865148475597475e-06, "epoch": 0.14723353699932112, "percentage": 14.72, "elapsed_time": "0:04:02", "remaining_time": "0:23:23", "throughput": 6889.46, "total_tokens": 1669568}
{"current_steps": 1740, "total_steps": 11784, "loss": 0.0588, "lr": 1.986271337340182e-06, "epoch": 0.14765784114052954, "percentage": 14.77, "elapsed_time": "0:04:02", "remaining_time": "0:23:20", "throughput": 6899.95, "total_tokens": 1674432}
{"current_steps": 1745, "total_steps": 11784, "loss": 0.0265, "lr": 1.9860256633324513e-06, "epoch": 0.14808214528173794, "percentage": 14.81, "elapsed_time": "0:04:02", "remaining_time": "0:23:17", "throughput": 6908.34, "total_tokens": 1678720}
{"current_steps": 1750, "total_steps": 11784, "loss": 0.0692, "lr": 1.9857778260755426e-06, "epoch": 0.14850644942294636, "percentage": 14.85, "elapsed_time": "0:04:03", "remaining_time": "0:23:15", "throughput": 6919.77, "total_tokens": 1683904}
{"current_steps": 1755, "total_steps": 11784, "loss": 0.0717, "lr": 1.9855278261131876e-06, "epoch": 0.14893075356415478, "percentage": 14.89, "elapsed_time": "0:04:03", "remaining_time": "0:23:12", "throughput": 6931.03, "total_tokens": 1689024}
{"current_steps": 1760, "total_steps": 11784, "loss": 0.0851, "lr": 1.985275663993863e-06, "epoch": 0.1493550577053632, "percentage": 14.94, "elapsed_time": "0:04:04", "remaining_time": "0:23:09", "throughput": 6940.51, "total_tokens": 1693632}
{"current_steps": 1765, "total_steps": 11784, "loss": 0.0532, "lr": 1.9850213402707888e-06, "epoch": 0.14977936184657162, "percentage": 14.98, "elapsed_time": "0:04:04", "remaining_time": "0:23:07", "throughput": 6949.95, "total_tokens": 1698304}
{"current_steps": 1770, "total_steps": 11784, "loss": 0.1201, "lr": 1.9847648555019286e-06, "epoch": 0.15020366598778004, "percentage": 15.02, "elapsed_time": "0:04:04", "remaining_time": "0:23:04", "throughput": 6962.22, "total_tokens": 1703808}
{"current_steps": 1770, "total_steps": 11784, "eval_loss": 0.0835869163274765, "epoch": 0.15020366598778004, "percentage": 15.02, "elapsed_time": "0:04:20", "remaining_time": "0:24:35", "throughput": 6533.39, "total_tokens": 1703808}
{"current_steps": 1775, "total_steps": 11784, "loss": 0.0634, "lr": 1.9845062102499858e-06, "epoch": 0.15062797012898846, "percentage": 15.06, "elapsed_time": "0:04:47", "remaining_time": "0:27:00", "throughput": 5946.61, "total_tokens": 1708992}
{"current_steps": 1780, "total_steps": 11784, "loss": 0.0769, "lr": 1.9842454050824043e-06, "epoch": 0.15105227427019688, "percentage": 15.11, "elapsed_time": "0:04:47", "remaining_time": "0:26:57", "throughput": 5955.87, "total_tokens": 1713600}
{"current_steps": 1785, "total_steps": 11784, "loss": 0.0963, "lr": 1.9839824405713663e-06, "epoch": 0.1514765784114053, "percentage": 15.15, "elapsed_time": "0:04:48", "remaining_time": "0:26:53", "throughput": 5965.1, "total_tokens": 1718208}
{"current_steps": 1790, "total_steps": 11784, "loss": 0.1394, "lr": 1.983717317293792e-06, "epoch": 0.15190088255261372, "percentage": 15.19, "elapsed_time": "0:04:48", "remaining_time": "0:26:50", "throughput": 5973.51, "total_tokens": 1722560}
{"current_steps": 1795, "total_steps": 11784, "loss": 0.0263, "lr": 1.983450035831337e-06, "epoch": 0.15232518669382214, "percentage": 15.23, "elapsed_time": "0:04:48", "remaining_time": "0:26:46", "throughput": 5983.09, "total_tokens": 1727296}
{"current_steps": 1800, "total_steps": 11784, "loss": 0.0809, "lr": 1.983180596770392e-06, "epoch": 0.15274949083503056, "percentage": 15.27, "elapsed_time": "0:04:49", "remaining_time": "0:26:43", "throughput": 5994.36, "total_tokens": 1732608}
{"current_steps": 1805, "total_steps": 11784, "loss": 0.0569, "lr": 1.982909000702082e-06, "epoch": 0.15317379497623898, "percentage": 15.32, "elapsed_time": "0:04:49", "remaining_time": "0:26:39", "throughput": 6003.66, "total_tokens": 1737280}
{"current_steps": 1810, "total_steps": 11784, "loss": 0.0948, "lr": 1.982635248222264e-06, "epoch": 0.15359809911744737, "percentage": 15.36, "elapsed_time": "0:04:49", "remaining_time": "0:26:36", "throughput": 6011.41, "total_tokens": 1741440}
{"current_steps": 1815, "total_steps": 11784, "loss": 0.0485, "lr": 1.982359339931524e-06, "epoch": 0.1540224032586558, "percentage": 15.4, "elapsed_time": "0:04:50", "remaining_time": "0:26:32", "throughput": 6020.94, "total_tokens": 1746176}
{"current_steps": 1820, "total_steps": 11784, "loss": 0.1267, "lr": 1.9820812764351804e-06, "epoch": 0.1544467073998642, "percentage": 15.44, "elapsed_time": "0:04:50", "remaining_time": "0:26:29", "throughput": 6032.65, "total_tokens": 1751680}
{"current_steps": 1825, "total_steps": 11784, "loss": 0.0524, "lr": 1.981801058343279e-06, "epoch": 0.15487101154107263, "percentage": 15.49, "elapsed_time": "0:04:50", "remaining_time": "0:26:26", "throughput": 6041.99, "total_tokens": 1756416}
{"current_steps": 1830, "total_steps": 11784, "loss": 0.0919, "lr": 1.981518686270592e-06, "epoch": 0.15529531568228105, "percentage": 15.53, "elapsed_time": "0:04:51", "remaining_time": "0:26:23", "throughput": 6050.78, "total_tokens": 1760960}
{"current_steps": 1835, "total_steps": 11784, "loss": 0.0884, "lr": 1.9812341608366183e-06, "epoch": 0.15571961982348947, "percentage": 15.57, "elapsed_time": "0:04:51", "remaining_time": "0:26:19", "throughput": 6061.69, "total_tokens": 1766208}
{"current_steps": 1840, "total_steps": 11784, "loss": 0.0528, "lr": 1.980947482665579e-06, "epoch": 0.1561439239646979, "percentage": 15.61, "elapsed_time": "0:04:51", "remaining_time": "0:26:16", "throughput": 6072.01, "total_tokens": 1771264}
{"current_steps": 1845, "total_steps": 11784, "loss": 0.15, "lr": 1.980658652386421e-06, "epoch": 0.15656822810590632, "percentage": 15.66, "elapsed_time": "0:04:52", "remaining_time": "0:26:13", "throughput": 6081.92, "total_tokens": 1776192}
{"current_steps": 1850, "total_steps": 11784, "loss": 0.0842, "lr": 1.9803676706328102e-06, "epoch": 0.15699253224711474, "percentage": 15.7, "elapsed_time": "0:04:52", "remaining_time": "0:26:09", "throughput": 6091.49, "total_tokens": 1780992}
{"current_steps": 1855, "total_steps": 11784, "loss": 0.0473, "lr": 1.980074538043134e-06, "epoch": 0.15741683638832316, "percentage": 15.74, "elapsed_time": "0:04:52", "remaining_time": "0:26:06", "throughput": 6099.81, "total_tokens": 1785408}
{"current_steps": 1860, "total_steps": 11784, "loss": 0.1532, "lr": 1.9797792552604985e-06, "epoch": 0.15784114052953158, "percentage": 15.78, "elapsed_time": "0:04:53", "remaining_time": "0:26:03", "throughput": 6109.25, "total_tokens": 1790208}
{"current_steps": 1865, "total_steps": 11784, "loss": 0.0137, "lr": 1.9794818229327266e-06, "epoch": 0.15826544467074, "percentage": 15.83, "elapsed_time": "0:04:53", "remaining_time": "0:26:00", "throughput": 6119.45, "total_tokens": 1795264}
{"current_steps": 1870, "total_steps": 11784, "loss": 0.0572, "lr": 1.9791822417123576e-06, "epoch": 0.15868974881194842, "percentage": 15.87, "elapsed_time": "0:04:53", "remaining_time": "0:25:57", "throughput": 6128.9, "total_tokens": 1800064}
{"current_steps": 1875, "total_steps": 11784, "loss": 0.05, "lr": 1.9788805122566445e-06, "epoch": 0.1591140529531568, "percentage": 15.91, "elapsed_time": "0:04:54", "remaining_time": "0:25:53", "throughput": 6137.75, "total_tokens": 1804672}
{"current_steps": 1880, "total_steps": 11784, "loss": 0.1075, "lr": 1.9785766352275538e-06, "epoch": 0.15953835709436523, "percentage": 15.95, "elapsed_time": "0:04:54", "remaining_time": "0:25:50", "throughput": 6146.9, "total_tokens": 1809408}
{"current_steps": 1885, "total_steps": 11784, "loss": 0.1561, "lr": 1.9782706112917643e-06, "epoch": 0.15996266123557365, "percentage": 16.0, "elapsed_time": "0:04:54", "remaining_time": "0:25:47", "throughput": 6155.06, "total_tokens": 1813824}
{"current_steps": 1890, "total_steps": 11784, "loss": 0.0392, "lr": 1.977962441120664e-06, "epoch": 0.16038696537678207, "percentage": 16.04, "elapsed_time": "0:04:55", "remaining_time": "0:25:44", "throughput": 6162.99, "total_tokens": 1818176}
{"current_steps": 1895, "total_steps": 11784, "loss": 0.0622, "lr": 1.9776521253903492e-06, "epoch": 0.1608112695179905, "percentage": 16.08, "elapsed_time": "0:04:55", "remaining_time": "0:25:41", "throughput": 6171.76, "total_tokens": 1822784}
{"current_steps": 1900, "total_steps": 11784, "loss": 0.1414, "lr": 1.9773396647816246e-06, "epoch": 0.1612355736591989, "percentage": 16.12, "elapsed_time": "0:04:55", "remaining_time": "0:25:38", "throughput": 6180.91, "total_tokens": 1827520}
{"current_steps": 1905, "total_steps": 11784, "loss": 0.0911, "lr": 1.97702505998e-06, "epoch": 0.16165987780040733, "percentage": 16.17, "elapsed_time": "0:04:55", "remaining_time": "0:25:35", "throughput": 6190.07, "total_tokens": 1832256}
{"current_steps": 1910, "total_steps": 11784, "loss": 0.0821, "lr": 1.976708311675688e-06, "epoch": 0.16208418194161575, "percentage": 16.21, "elapsed_time": "0:04:56", "remaining_time": "0:25:31", "throughput": 6198.79, "total_tokens": 1836864}
{"current_steps": 1915, "total_steps": 11784, "loss": 0.0317, "lr": 1.976389420563607e-06, "epoch": 0.16250848608282417, "percentage": 16.25, "elapsed_time": "0:04:56", "remaining_time": "0:25:28", "throughput": 6206.91, "total_tokens": 1841280}
{"current_steps": 1920, "total_steps": 11784, "loss": 0.0848, "lr": 1.9760683873433734e-06, "epoch": 0.1629327902240326, "percentage": 16.29, "elapsed_time": "0:04:56", "remaining_time": "0:25:25", "throughput": 6216.16, "total_tokens": 1846080}
{"current_steps": 1925, "total_steps": 11784, "loss": 0.0373, "lr": 1.9757452127193043e-06, "epoch": 0.163357094365241, "percentage": 16.34, "elapsed_time": "0:04:57", "remaining_time": "0:25:22", "throughput": 6225.27, "total_tokens": 1850816}
{"current_steps": 1930, "total_steps": 11784, "loss": 0.0922, "lr": 1.9754198974004156e-06, "epoch": 0.16378139850644943, "percentage": 16.38, "elapsed_time": "0:04:57", "remaining_time": "0:25:19", "throughput": 6233.27, "total_tokens": 1855232}
{"current_steps": 1935, "total_steps": 11784, "loss": 0.0689, "lr": 1.975092442100419e-06, "epoch": 0.16420570264765785, "percentage": 16.42, "elapsed_time": "0:04:57", "remaining_time": "0:25:16", "throughput": 6242.81, "total_tokens": 1860160}
{"current_steps": 1940, "total_steps": 11784, "loss": 0.0229, "lr": 1.9747628475377204e-06, "epoch": 0.16463000678886625, "percentage": 16.46, "elapsed_time": "0:04:58", "remaining_time": "0:25:13", "throughput": 6252.16, "total_tokens": 1865024}
{"current_steps": 1945, "total_steps": 11784, "loss": 0.0846, "lr": 1.9744311144354208e-06, "epoch": 0.16505431093007467, "percentage": 16.51, "elapsed_time": "0:04:58", "remaining_time": "0:25:10", "throughput": 6261.47, "total_tokens": 1869888}
{"current_steps": 1950, "total_steps": 11784, "loss": 0.1164, "lr": 1.9740972435213112e-06, "epoch": 0.16547861507128309, "percentage": 16.55, "elapsed_time": "0:04:58", "remaining_time": "0:25:07", "throughput": 6270.33, "total_tokens": 1874624}
{"current_steps": 1955, "total_steps": 11784, "loss": 0.066, "lr": 1.973761235527874e-06, "epoch": 0.1659029192124915, "percentage": 16.59, "elapsed_time": "0:04:59", "remaining_time": "0:25:04", "throughput": 6278.66, "total_tokens": 1879168}
{"current_steps": 1960, "total_steps": 11784, "loss": 0.1811, "lr": 1.9734230911922795e-06, "epoch": 0.16632722335369993, "percentage": 16.63, "elapsed_time": "0:04:59", "remaining_time": "0:25:01", "throughput": 6288.09, "total_tokens": 1884096}
{"current_steps": 1965, "total_steps": 11784, "loss": 0.0921, "lr": 1.9730828112563852e-06, "epoch": 0.16675152749490835, "percentage": 16.68, "elapsed_time": "0:04:59", "remaining_time": "0:24:58", "throughput": 6296.91, "total_tokens": 1888832}
{"current_steps": 1970, "total_steps": 11784, "loss": 0.0428, "lr": 1.972740396466734e-06, "epoch": 0.16717583163611677, "percentage": 16.72, "elapsed_time": "0:05:00", "remaining_time": "0:24:55", "throughput": 6306.11, "total_tokens": 1893696}
{"current_steps": 1975, "total_steps": 11784, "loss": 0.0128, "lr": 1.972395847574552e-06, "epoch": 0.1676001357773252, "percentage": 16.76, "elapsed_time": "0:05:00", "remaining_time": "0:24:53", "throughput": 6314.11, "total_tokens": 1898176}
{"current_steps": 1980, "total_steps": 11784, "loss": 0.092, "lr": 1.972049165335747e-06, "epoch": 0.1680244399185336, "percentage": 16.8, "elapsed_time": "0:05:00", "remaining_time": "0:24:50", "throughput": 6322.38, "total_tokens": 1902720}
{"current_steps": 1985, "total_steps": 11784, "loss": 0.0494, "lr": 1.9717003505109094e-06, "epoch": 0.16844874405974203, "percentage": 16.84, "elapsed_time": "0:05:01", "remaining_time": "0:24:47", "throughput": 6331.3, "total_tokens": 1907520}
{"current_steps": 1990, "total_steps": 11784, "loss": 0.0955, "lr": 1.9713494038653054e-06, "epoch": 0.16887304820095045, "percentage": 16.89, "elapsed_time": "0:05:01", "remaining_time": "0:24:44", "throughput": 6339.31, "total_tokens": 1912000}
{"current_steps": 1995, "total_steps": 11784, "loss": 0.0437, "lr": 1.97099632616888e-06, "epoch": 0.16929735234215887, "percentage": 16.93, "elapsed_time": "0:05:01", "remaining_time": "0:24:41", "throughput": 6346.5, "total_tokens": 1916224}
{"current_steps": 2000, "total_steps": 11784, "loss": 0.0532, "lr": 1.9706411181962534e-06, "epoch": 0.1697216564833673, "percentage": 16.97, "elapsed_time": "0:05:02", "remaining_time": "0:24:38", "throughput": 6355.04, "total_tokens": 1920896}
{"current_steps": 2005, "total_steps": 11784, "loss": 0.0502, "lr": 1.970283780726718e-06, "epoch": 0.1701459606245757, "percentage": 17.01, "elapsed_time": "0:05:02", "remaining_time": "0:24:35", "throughput": 6362.85, "total_tokens": 1925312}
{"current_steps": 2010, "total_steps": 11784, "loss": 0.095, "lr": 1.9699243145442397e-06, "epoch": 0.1705702647657841, "percentage": 17.06, "elapsed_time": "0:05:02", "remaining_time": "0:24:32", "throughput": 6371.16, "total_tokens": 1929920}
{"current_steps": 2015, "total_steps": 11784, "loss": 0.0817, "lr": 1.9695627204374544e-06, "epoch": 0.17099456890699252, "percentage": 17.1, "elapsed_time": "0:05:03", "remaining_time": "0:24:30", "throughput": 6379.98, "total_tokens": 1934720}
{"current_steps": 2020, "total_steps": 11784, "loss": 0.0332, "lr": 1.969198999199666e-06, "epoch": 0.17141887304820094, "percentage": 17.14, "elapsed_time": "0:05:03", "remaining_time": "0:24:27", "throughput": 6389.09, "total_tokens": 1939584}
{"current_steps": 2025, "total_steps": 11784, "loss": 0.125, "lr": 1.968833151628845e-06, "epoch": 0.17184317718940936, "percentage": 17.18, "elapsed_time": "0:05:03", "remaining_time": "0:24:24", "throughput": 6398.43, "total_tokens": 1944576}
{"current_steps": 2030, "total_steps": 11784, "loss": 0.1032, "lr": 1.968465178527628e-06, "epoch": 0.17226748133061778, "percentage": 17.23, "elapsed_time": "0:05:04", "remaining_time": "0:24:21", "throughput": 6405.93, "total_tokens": 1948928}
{"current_steps": 2035, "total_steps": 11784, "loss": 0.0727, "lr": 1.9680950807033124e-06, "epoch": 0.1726917854718262, "percentage": 17.27, "elapsed_time": "0:05:04", "remaining_time": "0:24:19", "throughput": 6414.32, "total_tokens": 1953600}
{"current_steps": 2040, "total_steps": 11784, "loss": 0.0892, "lr": 1.96772285896786e-06, "epoch": 0.17311608961303462, "percentage": 17.31, "elapsed_time": "0:05:04", "remaining_time": "0:24:16", "throughput": 6423.66, "total_tokens": 1958592}
{"current_steps": 2045, "total_steps": 11784, "loss": 0.042, "lr": 1.9673485141378904e-06, "epoch": 0.17354039375424304, "percentage": 17.35, "elapsed_time": "0:05:05", "remaining_time": "0:24:13", "throughput": 6430.56, "total_tokens": 1962752}
{"current_steps": 2050, "total_steps": 11784, "loss": 0.1337, "lr": 1.9669720470346817e-06, "epoch": 0.17396469789545146, "percentage": 17.4, "elapsed_time": "0:05:05", "remaining_time": "0:24:10", "throughput": 6438.92, "total_tokens": 1967424}
{"current_steps": 2055, "total_steps": 11784, "loss": 0.0393, "lr": 1.966593458484168e-06, "epoch": 0.17438900203665988, "percentage": 17.44, "elapsed_time": "0:05:05", "remaining_time": "0:24:08", "throughput": 6449.11, "total_tokens": 1972736}
{"current_steps": 2060, "total_steps": 11784, "loss": 0.0351, "lr": 1.9662127493169367e-06, "epoch": 0.1748133061778683, "percentage": 17.48, "elapsed_time": "0:05:06", "remaining_time": "0:24:05", "throughput": 6457.37, "total_tokens": 1977408}
{"current_steps": 2065, "total_steps": 11784, "loss": 0.044, "lr": 1.96582992036823e-06, "epoch": 0.17523761031907673, "percentage": 17.52, "elapsed_time": "0:05:06", "remaining_time": "0:24:02", "throughput": 6465.5, "total_tokens": 1982016}
{"current_steps": 2070, "total_steps": 11784, "loss": 0.114, "lr": 1.9654449724779387e-06, "epoch": 0.17566191446028515, "percentage": 17.57, "elapsed_time": "0:05:06", "remaining_time": "0:24:00", "throughput": 6475.71, "total_tokens": 1987392}
{"current_steps": 2075, "total_steps": 11784, "loss": 0.0802, "lr": 1.965057906490602e-06, "epoch": 0.17608621860149354, "percentage": 17.61, "elapsed_time": "0:05:07", "remaining_time": "0:23:57", "throughput": 6483.88, "total_tokens": 1992064}
{"current_steps": 2080, "total_steps": 11784, "loss": 0.0644, "lr": 1.964668723255408e-06, "epoch": 0.17651052274270196, "percentage": 17.65, "elapsed_time": "0:05:07", "remaining_time": "0:23:54", "throughput": 6493.15, "total_tokens": 1997120}
{"current_steps": 2085, "total_steps": 11784, "loss": 0.0501, "lr": 1.964277423626188e-06, "epoch": 0.17693482688391038, "percentage": 17.69, "elapsed_time": "0:05:07", "remaining_time": "0:23:52", "throughput": 6501.07, "total_tokens": 2001664}
{"current_steps": 2090, "total_steps": 11784, "loss": 0.0941, "lr": 1.9638840084614178e-06, "epoch": 0.1773591310251188, "percentage": 17.74, "elapsed_time": "0:05:08", "remaining_time": "0:23:49", "throughput": 6509.3, "total_tokens": 2006336}
{"current_steps": 2095, "total_steps": 11784, "loss": 0.0483, "lr": 1.963488478624214e-06, "epoch": 0.17778343516632722, "percentage": 17.78, "elapsed_time": "0:05:08", "remaining_time": "0:23:47", "throughput": 6518.16, "total_tokens": 2011264}
{"current_steps": 2100, "total_steps": 11784, "loss": 0.0896, "lr": 1.9630908349823315e-06, "epoch": 0.17820773930753564, "percentage": 17.82, "elapsed_time": "0:05:08", "remaining_time": "0:23:44", "throughput": 6525.64, "total_tokens": 2015680}
{"current_steps": 2105, "total_steps": 11784, "loss": 0.1457, "lr": 1.9626910784081647e-06, "epoch": 0.17863204344874406, "percentage": 17.86, "elapsed_time": "0:05:09", "remaining_time": "0:23:41", "throughput": 6533.75, "total_tokens": 2020352}
{"current_steps": 2110, "total_steps": 11784, "loss": 0.0603, "lr": 1.9622892097787426e-06, "epoch": 0.17905634758995248, "percentage": 17.91, "elapsed_time": "0:05:09", "remaining_time": "0:23:39", "throughput": 6541.31, "total_tokens": 2024832}
{"current_steps": 2115, "total_steps": 11784, "loss": 0.0261, "lr": 1.961885229975727e-06, "epoch": 0.1794806517311609, "percentage": 17.95, "elapsed_time": "0:05:09", "remaining_time": "0:23:36", "throughput": 6548.54, "total_tokens": 2029184}
{"current_steps": 2120, "total_steps": 11784, "loss": 0.0787, "lr": 1.9614791398854133e-06, "epoch": 0.17990495587236932, "percentage": 17.99, "elapsed_time": "0:05:10", "remaining_time": "0:23:34", "throughput": 6557.18, "total_tokens": 2034048}
{"current_steps": 2125, "total_steps": 11784, "loss": 0.0453, "lr": 1.9610709403987244e-06, "epoch": 0.18032926001357774, "percentage": 18.03, "elapsed_time": "0:05:10", "remaining_time": "0:23:31", "throughput": 6566.63, "total_tokens": 2039232}
{"current_steps": 2130, "total_steps": 11784, "loss": 0.0774, "lr": 1.9606606324112134e-06, "epoch": 0.18075356415478616, "percentage": 18.08, "elapsed_time": "0:05:10", "remaining_time": "0:23:28", "throughput": 6574.21, "total_tokens": 2043712}
{"current_steps": 2135, "total_steps": 11784, "loss": 0.1347, "lr": 1.9602482168230576e-06, "epoch": 0.18117786829599458, "percentage": 18.12, "elapsed_time": "0:05:11", "remaining_time": "0:23:26", "throughput": 6582.78, "total_tokens": 2048576}
{"current_steps": 2140, "total_steps": 11784, "loss": 0.071, "lr": 1.9598336945390584e-06, "epoch": 0.18160217243720297, "percentage": 18.16, "elapsed_time": "0:05:11", "remaining_time": "0:23:23", "throughput": 6591.36, "total_tokens": 2053440}
{"current_steps": 2145, "total_steps": 11784, "loss": 0.0639, "lr": 1.95941706646864e-06, "epoch": 0.1820264765784114, "percentage": 18.2, "elapsed_time": "0:05:11", "remaining_time": "0:23:21", "throughput": 6599.86, "total_tokens": 2058304}
{"current_steps": 2150, "total_steps": 11784, "loss": 0.0581, "lr": 1.9589983335258457e-06, "epoch": 0.18245078071961982, "percentage": 18.25, "elapsed_time": "0:05:12", "remaining_time": "0:23:18", "throughput": 6607.17, "total_tokens": 2062720}
{"current_steps": 2155, "total_steps": 11784, "loss": 0.0886, "lr": 1.9585774966293365e-06, "epoch": 0.18287508486082824, "percentage": 18.29, "elapsed_time": "0:05:12", "remaining_time": "0:23:16", "throughput": 6614.86, "total_tokens": 2067264}
{"current_steps": 2160, "total_steps": 11784, "loss": 0.0804, "lr": 1.95815455670239e-06, "epoch": 0.18329938900203666, "percentage": 18.33, "elapsed_time": "0:05:12", "remaining_time": "0:23:13", "throughput": 6622.35, "total_tokens": 2071744}
{"current_steps": 2165, "total_steps": 11784, "loss": 0.0776, "lr": 1.957729514672897e-06, "epoch": 0.18372369314324508, "percentage": 18.37, "elapsed_time": "0:05:13", "remaining_time": "0:23:11", "throughput": 6630.17, "total_tokens": 2076352}
{"current_steps": 2170, "total_steps": 11784, "loss": 0.0654, "lr": 1.957302371473361e-06, "epoch": 0.1841479972844535, "percentage": 18.41, "elapsed_time": "0:05:13", "remaining_time": "0:23:08", "throughput": 6638.21, "total_tokens": 2081088}
{"current_steps": 2175, "total_steps": 11784, "loss": 0.0651, "lr": 1.9568731280408945e-06, "epoch": 0.18457230142566192, "percentage": 18.46, "elapsed_time": "0:05:13", "remaining_time": "0:23:06", "throughput": 6646.05, "total_tokens": 2085760}
{"current_steps": 2180, "total_steps": 11784, "loss": 0.0981, "lr": 1.956441785317217e-06, "epoch": 0.18499660556687034, "percentage": 18.5, "elapsed_time": "0:05:14", "remaining_time": "0:23:04", "throughput": 6654.36, "total_tokens": 2090624}
{"current_steps": 2185, "total_steps": 11784, "loss": 0.0606, "lr": 1.9560083442486565e-06, "epoch": 0.18542090970807876, "percentage": 18.54, "elapsed_time": "0:05:14", "remaining_time": "0:23:01", "throughput": 6663.94, "total_tokens": 2095936}
{"current_steps": 2190, "total_steps": 11784, "loss": 0.081, "lr": 1.955572805786141e-06, "epoch": 0.18584521384928718, "percentage": 18.58, "elapsed_time": "0:05:14", "remaining_time": "0:22:59", "throughput": 6671.74, "total_tokens": 2100608}
{"current_steps": 2195, "total_steps": 11784, "loss": 0.0897, "lr": 1.9551351708852015e-06, "epoch": 0.1862695179904956, "percentage": 18.63, "elapsed_time": "0:05:15", "remaining_time": "0:22:56", "throughput": 6681.11, "total_tokens": 2105856}
{"current_steps": 2200, "total_steps": 11784, "loss": 0.0448, "lr": 1.9546954405059697e-06, "epoch": 0.18669382213170402, "percentage": 18.67, "elapsed_time": "0:05:15", "remaining_time": "0:22:54", "throughput": 6688.81, "total_tokens": 2110464}
{"current_steps": 2205, "total_steps": 11784, "loss": 0.1086, "lr": 1.954253615613173e-06, "epoch": 0.1871181262729124, "percentage": 18.71, "elapsed_time": "0:05:15", "remaining_time": "0:22:52", "throughput": 6697.97, "total_tokens": 2115648}
{"current_steps": 2210, "total_steps": 11784, "loss": 0.043, "lr": 1.9538096971761343e-06, "epoch": 0.18754243041412083, "percentage": 18.75, "elapsed_time": "0:05:16", "remaining_time": "0:22:49", "throughput": 6705.54, "total_tokens": 2120256}
{"current_steps": 2215, "total_steps": 11784, "loss": 0.1077, "lr": 1.9533636861687696e-06, "epoch": 0.18796673455532925, "percentage": 18.8, "elapsed_time": "0:05:16", "remaining_time": "0:22:47", "throughput": 6712.6, "total_tokens": 2124672}
{"current_steps": 2220, "total_steps": 11784, "loss": 0.0675, "lr": 1.9529155835695855e-06, "epoch": 0.18839103869653767, "percentage": 18.84, "elapsed_time": "0:05:16", "remaining_time": "0:22:45", "throughput": 6720.22, "total_tokens": 2129344}
{"current_steps": 2225, "total_steps": 11784, "loss": 0.0677, "lr": 1.952465390361678e-06, "epoch": 0.1888153428377461, "percentage": 18.88, "elapsed_time": "0:05:17", "remaining_time": "0:22:42", "throughput": 6728.78, "total_tokens": 2134336}
{"current_steps": 2230, "total_steps": 11784, "loss": 0.0558, "lr": 1.95201310753273e-06, "epoch": 0.1892396469789545, "percentage": 18.92, "elapsed_time": "0:05:17", "remaining_time": "0:22:40", "throughput": 6737.66, "total_tokens": 2139456}
{"current_steps": 2235, "total_steps": 11784, "loss": 0.1059, "lr": 1.9515587360750068e-06, "epoch": 0.18966395112016293, "percentage": 18.97, "elapsed_time": "0:05:17", "remaining_time": "0:22:38", "throughput": 6746.69, "total_tokens": 2144640}
{"current_steps": 2240, "total_steps": 11784, "loss": 0.1091, "lr": 1.9511022769853586e-06, "epoch": 0.19008825526137135, "percentage": 19.01, "elapsed_time": "0:05:18", "remaining_time": "0:22:35", "throughput": 6755.62, "total_tokens": 2149760}
{"current_steps": 2245, "total_steps": 11784, "loss": 0.1657, "lr": 1.9506437312652144e-06, "epoch": 0.19051255940257977, "percentage": 19.05, "elapsed_time": "0:05:18", "remaining_time": "0:22:33", "throughput": 6765.3, "total_tokens": 2155200}
{"current_steps": 2250, "total_steps": 11784, "loss": 0.1252, "lr": 1.9501830999205806e-06, "epoch": 0.1909368635437882, "percentage": 19.09, "elapsed_time": "0:05:18", "remaining_time": "0:22:31", "throughput": 6772.91, "total_tokens": 2159872}
{"current_steps": 2255, "total_steps": 11784, "loss": 0.0864, "lr": 1.9497203839620398e-06, "epoch": 0.1913611676849966, "percentage": 19.14, "elapsed_time": "0:05:19", "remaining_time": "0:22:28", "throughput": 6780.58, "total_tokens": 2164544}
{"current_steps": 2260, "total_steps": 11784, "loss": 0.0384, "lr": 1.9492555844047483e-06, "epoch": 0.19178547182620503, "percentage": 19.18, "elapsed_time": "0:05:19", "remaining_time": "0:22:26", "throughput": 6789.9, "total_tokens": 2169856}
{"current_steps": 2265, "total_steps": 11784, "loss": 0.0385, "lr": 1.9487887022684334e-06, "epoch": 0.19220977596741345, "percentage": 19.22, "elapsed_time": "0:05:19", "remaining_time": "0:22:24", "throughput": 6797.11, "total_tokens": 2174400}
{"current_steps": 2270, "total_steps": 11784, "loss": 0.0915, "lr": 1.9483197385773913e-06, "epoch": 0.19263408010862185, "percentage": 19.26, "elapsed_time": "0:05:20", "remaining_time": "0:22:22", "throughput": 6804.98, "total_tokens": 2179200}
{"current_steps": 2275, "total_steps": 11784, "loss": 0.0774, "lr": 1.947848694360485e-06, "epoch": 0.19305838424983027, "percentage": 19.31, "elapsed_time": "0:05:20", "remaining_time": "0:22:19", "throughput": 6814.82, "total_tokens": 2184768}
{"current_steps": 2280, "total_steps": 11784, "loss": 0.0947, "lr": 1.947375570651142e-06, "epoch": 0.1934826883910387, "percentage": 19.35, "elapsed_time": "0:05:20", "remaining_time": "0:22:17", "throughput": 6823.33, "total_tokens": 2189824}
{"current_steps": 2285, "total_steps": 11784, "loss": 0.0549, "lr": 1.9469003684873514e-06, "epoch": 0.1939069925322471, "percentage": 19.39, "elapsed_time": "0:05:21", "remaining_time": "0:22:15", "throughput": 6831.43, "total_tokens": 2194752}
{"current_steps": 2290, "total_steps": 11784, "loss": 0.1116, "lr": 1.946423088911664e-06, "epoch": 0.19433129667345553, "percentage": 19.43, "elapsed_time": "0:05:21", "remaining_time": "0:22:13", "throughput": 6839.25, "total_tokens": 2199552}
{"current_steps": 2295, "total_steps": 11784, "loss": 0.1976, "lr": 1.9459437329711865e-06, "epoch": 0.19475560081466395, "percentage": 19.48, "elapsed_time": "0:05:21", "remaining_time": "0:22:11", "throughput": 6846.84, "total_tokens": 2204288}
{"current_steps": 2300, "total_steps": 11784, "loss": 0.0683, "lr": 1.945462301717581e-06, "epoch": 0.19517990495587237, "percentage": 19.52, "elapsed_time": "0:05:22", "remaining_time": "0:22:08", "throughput": 6855.25, "total_tokens": 2209344}
{"current_steps": 2305, "total_steps": 11784, "loss": 0.0837, "lr": 1.944978796207064e-06, "epoch": 0.1956042090970808, "percentage": 19.56, "elapsed_time": "0:05:22", "remaining_time": "0:22:06", "throughput": 6863.19, "total_tokens": 2214208}
{"current_steps": 2310, "total_steps": 11784, "loss": 0.0974, "lr": 1.9444932175004017e-06, "epoch": 0.1960285132382892, "percentage": 19.6, "elapsed_time": "0:05:22", "remaining_time": "0:22:04", "throughput": 6869.95, "total_tokens": 2218624}
{"current_steps": 2315, "total_steps": 11784, "loss": 0.0717, "lr": 1.9440055666629087e-06, "epoch": 0.19645281737949763, "percentage": 19.65, "elapsed_time": "0:05:23", "remaining_time": "0:22:02", "throughput": 6878.83, "total_tokens": 2223872}
{"current_steps": 2320, "total_steps": 11784, "loss": 0.0729, "lr": 1.943515844764446e-06, "epoch": 0.19687712152070605, "percentage": 19.69, "elapsed_time": "0:05:23", "remaining_time": "0:22:00", "throughput": 6884.98, "total_tokens": 2228096}
{"current_steps": 2325, "total_steps": 11784, "loss": 0.1151, "lr": 1.943024052879418e-06, "epoch": 0.19730142566191447, "percentage": 19.73, "elapsed_time": "0:05:23", "remaining_time": "0:21:57", "throughput": 6891.29, "total_tokens": 2232384}
{"current_steps": 2330, "total_steps": 11784, "loss": 0.0336, "lr": 1.9425301920867703e-06, "epoch": 0.1977257298031229, "percentage": 19.77, "elapsed_time": "0:05:24", "remaining_time": "0:21:55", "throughput": 6898.91, "total_tokens": 2237184}
{"current_steps": 2335, "total_steps": 11784, "loss": 0.1116, "lr": 1.942034263469989e-06, "epoch": 0.19815003394433128, "percentage": 19.82, "elapsed_time": "0:05:24", "remaining_time": "0:21:53", "throughput": 6906.67, "total_tokens": 2242048}
{"current_steps": 2340, "total_steps": 11784, "loss": 0.0395, "lr": 1.941536268117095e-06, "epoch": 0.1985743380855397, "percentage": 19.86, "elapsed_time": "0:05:24", "remaining_time": "0:21:51", "throughput": 6915.03, "total_tokens": 2247104}
{"current_steps": 2345, "total_steps": 11784, "loss": 0.089, "lr": 1.9410362071206436e-06, "epoch": 0.19899864222674812, "percentage": 19.9, "elapsed_time": "0:05:25", "remaining_time": "0:21:49", "throughput": 6922.54, "total_tokens": 2251840}
{"current_steps": 2350, "total_steps": 11784, "loss": 0.1879, "lr": 1.9405340815777232e-06, "epoch": 0.19942294636795654, "percentage": 19.94, "elapsed_time": "0:05:25", "remaining_time": "0:21:47", "throughput": 6930.73, "total_tokens": 2256832}
{"current_steps": 2355, "total_steps": 11784, "loss": 0.0277, "lr": 1.9400298925899505e-06, "epoch": 0.19984725050916496, "percentage": 19.98, "elapsed_time": "0:05:25", "remaining_time": "0:21:45", "throughput": 6937.03, "total_tokens": 2261120}
{"current_steps": 2360, "total_steps": 11784, "loss": 0.1436, "lr": 1.939523641263469e-06, "epoch": 0.20027155465037338, "percentage": 20.03, "elapsed_time": "0:05:26", "remaining_time": "0:21:42", "throughput": 6946.07, "total_tokens": 2266496}
{"current_steps": 2360, "total_steps": 11784, "eval_loss": 0.0887659341096878, "epoch": 0.20027155465037338, "percentage": 20.03, "elapsed_time": "0:05:42", "remaining_time": "0:22:46", "throughput": 6621.92, "total_tokens": 2266496}
{"current_steps": 2365, "total_steps": 11784, "loss": 0.0249, "lr": 1.9390153287089485e-06, "epoch": 0.2006958587915818, "percentage": 20.07, "elapsed_time": "0:06:13", "remaining_time": "0:24:47", "throughput": 6079.46, "total_tokens": 2271040}
{"current_steps": 2370, "total_steps": 11784, "loss": 0.1026, "lr": 1.938504956041579e-06, "epoch": 0.20112016293279023, "percentage": 20.11, "elapsed_time": "0:06:13", "remaining_time": "0:24:45", "throughput": 6087.47, "total_tokens": 2276096}
{"current_steps": 2375, "total_steps": 11784, "loss": 0.0498, "lr": 1.937992524381071e-06, "epoch": 0.20154446707399865, "percentage": 20.15, "elapsed_time": "0:06:14", "remaining_time": "0:24:42", "throughput": 6093.17, "total_tokens": 2280192}
{"current_steps": 2380, "total_steps": 11784, "loss": 0.0528, "lr": 1.9374780348516525e-06, "epoch": 0.20196877121520707, "percentage": 20.2, "elapsed_time": "0:06:14", "remaining_time": "0:24:39", "throughput": 6099.85, "total_tokens": 2284672}
{"current_steps": 2385, "total_steps": 11784, "loss": 0.1108, "lr": 1.9369614885820657e-06, "epoch": 0.20239307535641549, "percentage": 20.24, "elapsed_time": "0:06:14", "remaining_time": "0:24:37", "throughput": 6107.72, "total_tokens": 2289664}
{"current_steps": 2390, "total_steps": 11784, "loss": 0.0978, "lr": 1.9364428867055655e-06, "epoch": 0.2028173794976239, "percentage": 20.28, "elapsed_time": "0:06:15", "remaining_time": "0:24:34", "throughput": 6116.28, "total_tokens": 2294976}
{"current_steps": 2395, "total_steps": 11784, "loss": 0.0427, "lr": 1.935922230359916e-06, "epoch": 0.20324168363883233, "percentage": 20.32, "elapsed_time": "0:06:15", "remaining_time": "0:24:32", "throughput": 6123.23, "total_tokens": 2299584}
{"current_steps": 2400, "total_steps": 11784, "loss": 0.067, "lr": 1.9353995206873898e-06, "epoch": 0.20366598778004075, "percentage": 20.37, "elapsed_time": "0:06:15", "remaining_time": "0:24:29", "throughput": 6130.43, "total_tokens": 2304320}
{"current_steps": 2405, "total_steps": 11784, "loss": 0.1673, "lr": 1.9348747588347637e-06, "epoch": 0.20409029192124914, "percentage": 20.41, "elapsed_time": "0:06:16", "remaining_time": "0:24:27", "throughput": 6137.38, "total_tokens": 2308928}
{"current_steps": 2410, "total_steps": 11784, "loss": 0.0387, "lr": 1.9343479459533157e-06, "epoch": 0.20451459606245756, "percentage": 20.45, "elapsed_time": "0:06:16", "remaining_time": "0:24:24", "throughput": 6143.66, "total_tokens": 2313280}
{"current_steps": 2415, "total_steps": 11784, "loss": 0.1093, "lr": 1.933819083198826e-06, "epoch": 0.20493890020366598, "percentage": 20.49, "elapsed_time": "0:06:16", "remaining_time": "0:24:22", "throughput": 6151.73, "total_tokens": 2318400}
{"current_steps": 2420, "total_steps": 11784, "loss": 0.0704, "lr": 1.9332881717315694e-06, "epoch": 0.2053632043448744, "percentage": 20.54, "elapsed_time": "0:06:17", "remaining_time": "0:24:19", "throughput": 6160.2, "total_tokens": 2323712}
{"current_steps": 2425, "total_steps": 11784, "loss": 0.0282, "lr": 1.9327552127163172e-06, "epoch": 0.20578750848608282, "percentage": 20.58, "elapsed_time": "0:06:17", "remaining_time": "0:24:17", "throughput": 6165.99, "total_tokens": 2327936}
{"current_steps": 2430, "total_steps": 11784, "loss": 0.0612, "lr": 1.932220207322332e-06, "epoch": 0.20621181262729124, "percentage": 20.62, "elapsed_time": "0:06:17", "remaining_time": "0:24:14", "throughput": 6172.07, "total_tokens": 2332224}
{"current_steps": 2435, "total_steps": 11784, "loss": 0.0718, "lr": 1.931683156723366e-06, "epoch": 0.20663611676849966, "percentage": 20.66, "elapsed_time": "0:06:18", "remaining_time": "0:24:12", "throughput": 6178.6, "total_tokens": 2336704}
{"current_steps": 2440, "total_steps": 11784, "loss": 0.0876, "lr": 1.9311440620976595e-06, "epoch": 0.20706042090970808, "percentage": 20.71, "elapsed_time": "0:06:18", "remaining_time": "0:24:09", "throughput": 6186.74, "total_tokens": 2341888}
{"current_steps": 2445, "total_steps": 11784, "loss": 0.0747, "lr": 1.930602924627935e-06, "epoch": 0.2074847250509165, "percentage": 20.75, "elapsed_time": "0:06:18", "remaining_time": "0:24:07", "throughput": 6193.38, "total_tokens": 2346432}
{"current_steps": 2450, "total_steps": 11784, "loss": 0.0499, "lr": 1.930059745501399e-06, "epoch": 0.20790902919212492, "percentage": 20.79, "elapsed_time": "0:06:19", "remaining_time": "0:24:04", "throughput": 6199.25, "total_tokens": 2350656}
{"current_steps": 2455, "total_steps": 11784, "loss": 0.0438, "lr": 1.9295145259097362e-06, "epoch": 0.20833333333333334, "percentage": 20.83, "elapsed_time": "0:06:19", "remaining_time": "0:24:02", "throughput": 6206.31, "total_tokens": 2355392}
{"current_steps": 2460, "total_steps": 11784, "loss": 0.0241, "lr": 1.9289672670491076e-06, "epoch": 0.20875763747454176, "percentage": 20.88, "elapsed_time": "0:06:19", "remaining_time": "0:23:59", "throughput": 6213.79, "total_tokens": 2360320}
{"current_steps": 2465, "total_steps": 11784, "loss": 0.0112, "lr": 1.928417970120149e-06, "epoch": 0.20918194161575018, "percentage": 20.92, "elapsed_time": "0:06:20", "remaining_time": "0:23:57", "throughput": 6221.03, "total_tokens": 2365120}
{"current_steps": 2470, "total_steps": 11784, "loss": 0.1338, "lr": 1.9278666363279664e-06, "epoch": 0.20960624575695858, "percentage": 20.96, "elapsed_time": "0:06:20", "remaining_time": "0:23:54", "throughput": 6228.18, "total_tokens": 2369920}
{"current_steps": 2475, "total_steps": 11784, "loss": 0.0943, "lr": 1.9273132668821363e-06, "epoch": 0.210030549898167, "percentage": 21.0, "elapsed_time": "0:06:20", "remaining_time": "0:23:52", "throughput": 6235.6, "total_tokens": 2374848}
{"current_steps": 2480, "total_steps": 11784, "loss": 0.0583, "lr": 1.926757862996699e-06, "epoch": 0.21045485403937542, "percentage": 21.05, "elapsed_time": "0:06:21", "remaining_time": "0:23:50", "throughput": 6243.6, "total_tokens": 2380032}
{"current_steps": 2485, "total_steps": 11784, "loss": 0.1324, "lr": 1.92620042589016e-06, "epoch": 0.21087915818058384, "percentage": 21.09, "elapsed_time": "0:06:21", "remaining_time": "0:23:47", "throughput": 6250.44, "total_tokens": 2384704}
{"current_steps": 2490, "total_steps": 11784, "loss": 0.0661, "lr": 1.9256409567854847e-06, "epoch": 0.21130346232179226, "percentage": 21.13, "elapsed_time": "0:06:21", "remaining_time": "0:23:45", "throughput": 6257.75, "total_tokens": 2389568}
{"current_steps": 2495, "total_steps": 11784, "loss": 0.1469, "lr": 1.9250794569100963e-06, "epoch": 0.21172776646300068, "percentage": 21.17, "elapsed_time": "0:06:22", "remaining_time": "0:23:42", "throughput": 6265.28, "total_tokens": 2394560}
{"current_steps": 2500, "total_steps": 11784, "loss": 0.0676, "lr": 1.9245159274958737e-06, "epoch": 0.2121520706042091, "percentage": 21.22, "elapsed_time": "0:06:22", "remaining_time": "0:23:40", "throughput": 6272.1, "total_tokens": 2399232}
{"current_steps": 2505, "total_steps": 11784, "loss": 0.1362, "lr": 1.9239503697791487e-06, "epoch": 0.21257637474541752, "percentage": 21.26, "elapsed_time": "0:06:22", "remaining_time": "0:23:38", "throughput": 6279.2, "total_tokens": 2404032}
{"current_steps": 2510, "total_steps": 11784, "loss": 0.0744, "lr": 1.9233827850007024e-06, "epoch": 0.21300067888662594, "percentage": 21.3, "elapsed_time": "0:06:23", "remaining_time": "0:23:35", "throughput": 6285.7, "total_tokens": 2408576}
{"current_steps": 2515, "total_steps": 11784, "loss": 0.0727, "lr": 1.9228131744057633e-06, "epoch": 0.21342498302783436, "percentage": 21.34, "elapsed_time": "0:06:23", "remaining_time": "0:23:33", "throughput": 6292.88, "total_tokens": 2413440}
{"current_steps": 2520, "total_steps": 11784, "loss": 0.0503, "lr": 1.922241539244005e-06, "epoch": 0.21384928716904278, "percentage": 21.38, "elapsed_time": "0:06:23", "remaining_time": "0:23:31", "throughput": 6298.64, "total_tokens": 2417664}
{"current_steps": 2525, "total_steps": 11784, "loss": 0.0807, "lr": 1.921667880769541e-06, "epoch": 0.2142735913102512, "percentage": 21.43, "elapsed_time": "0:06:24", "remaining_time": "0:23:28", "throughput": 6305.7, "total_tokens": 2422464}
{"current_steps": 2530, "total_steps": 11784, "loss": 0.039, "lr": 1.921092200240926e-06, "epoch": 0.21469789545145962, "percentage": 21.47, "elapsed_time": "0:06:24", "remaining_time": "0:23:26", "throughput": 6312.58, "total_tokens": 2427200}
{"current_steps": 2535, "total_steps": 11784, "loss": 0.0421, "lr": 1.9205144989211495e-06, "epoch": 0.215122199592668, "percentage": 21.51, "elapsed_time": "0:06:24", "remaining_time": "0:23:24", "throughput": 6318.72, "total_tokens": 2431616}
{"current_steps": 2540, "total_steps": 11784, "loss": 0.0555, "lr": 1.919934778077635e-06, "epoch": 0.21554650373387643, "percentage": 21.55, "elapsed_time": "0:06:25", "remaining_time": "0:23:21", "throughput": 6325.55, "total_tokens": 2436352}
{"current_steps": 2545, "total_steps": 11784, "loss": 0.0429, "lr": 1.9193530389822362e-06, "epoch": 0.21597080787508485, "percentage": 21.6, "elapsed_time": "0:06:25", "remaining_time": "0:23:19", "throughput": 6331.52, "total_tokens": 2440704}
{"current_steps": 2550, "total_steps": 11784, "loss": 0.0246, "lr": 1.918769282911235e-06, "epoch": 0.21639511201629327, "percentage": 21.64, "elapsed_time": "0:06:25", "remaining_time": "0:23:17", "throughput": 6340.2, "total_tokens": 2446272}
{"current_steps": 2555, "total_steps": 11784, "loss": 0.0731, "lr": 1.9181835111453383e-06, "epoch": 0.2168194161575017, "percentage": 21.68, "elapsed_time": "0:06:26", "remaining_time": "0:23:14", "throughput": 6345.82, "total_tokens": 2450496}
{"current_steps": 2560, "total_steps": 11784, "loss": 0.0483, "lr": 1.9175957249696755e-06, "epoch": 0.2172437202987101, "percentage": 21.72, "elapsed_time": "0:06:26", "remaining_time": "0:23:12", "throughput": 6353.06, "total_tokens": 2455424}
{"current_steps": 2565, "total_steps": 11784, "loss": 0.0535, "lr": 1.9170059256737946e-06, "epoch": 0.21766802443991853, "percentage": 21.77, "elapsed_time": "0:06:26", "remaining_time": "0:23:10", "throughput": 6360.28, "total_tokens": 2460352}
{"current_steps": 2570, "total_steps": 11784, "loss": 0.1311, "lr": 1.9164141145516613e-06, "epoch": 0.21809232858112695, "percentage": 21.81, "elapsed_time": "0:06:27", "remaining_time": "0:23:08", "throughput": 6366.66, "total_tokens": 2464896}
{"current_steps": 2575, "total_steps": 11784, "loss": 0.1178, "lr": 1.915820292901654e-06, "epoch": 0.21851663272233537, "percentage": 21.85, "elapsed_time": "0:06:27", "remaining_time": "0:23:05", "throughput": 6373.85, "total_tokens": 2469824}
{"current_steps": 2580, "total_steps": 11784, "loss": 0.1612, "lr": 1.915224462026563e-06, "epoch": 0.2189409368635438, "percentage": 21.89, "elapsed_time": "0:06:27", "remaining_time": "0:23:03", "throughput": 6379.74, "total_tokens": 2474176}
{"current_steps": 2585, "total_steps": 11784, "loss": 0.1505, "lr": 1.9146266232335854e-06, "epoch": 0.21936524100475221, "percentage": 21.94, "elapsed_time": "0:06:28", "remaining_time": "0:23:01", "throughput": 6387.25, "total_tokens": 2479232}
{"current_steps": 2590, "total_steps": 11784, "loss": 0.1221, "lr": 1.914026777834325e-06, "epoch": 0.21978954514596064, "percentage": 21.98, "elapsed_time": "0:06:28", "remaining_time": "0:22:59", "throughput": 6393.23, "total_tokens": 2483648}
{"current_steps": 2595, "total_steps": 11784, "loss": 0.0517, "lr": 1.9134249271447872e-06, "epoch": 0.22021384928716906, "percentage": 22.02, "elapsed_time": "0:06:28", "remaining_time": "0:22:56", "throughput": 6399.19, "total_tokens": 2488064}
{"current_steps": 2600, "total_steps": 11784, "loss": 0.0604, "lr": 1.9128210724853765e-06, "epoch": 0.22063815342837745, "percentage": 22.06, "elapsed_time": "0:06:29", "remaining_time": "0:22:54", "throughput": 6406.73, "total_tokens": 2493184}
{"current_steps": 2605, "total_steps": 11784, "loss": 0.094, "lr": 1.912215215180894e-06, "epoch": 0.22106245756958587, "percentage": 22.11, "elapsed_time": "0:06:29", "remaining_time": "0:22:52", "throughput": 6413.64, "total_tokens": 2498048}
{"current_steps": 2610, "total_steps": 11784, "loss": 0.1097, "lr": 1.9116073565605347e-06, "epoch": 0.2214867617107943, "percentage": 22.15, "elapsed_time": "0:06:29", "remaining_time": "0:22:50", "throughput": 6423.12, "total_tokens": 2504064}
{"current_steps": 2615, "total_steps": 11784, "loss": 0.0698, "lr": 1.9109974979578847e-06, "epoch": 0.2219110658520027, "percentage": 22.19, "elapsed_time": "0:06:30", "remaining_time": "0:22:48", "throughput": 6429.81, "total_tokens": 2508800}
{"current_steps": 2620, "total_steps": 11784, "loss": 0.0328, "lr": 1.9103856407109172e-06, "epoch": 0.22233536999321113, "percentage": 22.23, "elapsed_time": "0:06:30", "remaining_time": "0:22:45", "throughput": 6435.88, "total_tokens": 2513280}
{"current_steps": 2625, "total_steps": 11784, "loss": 0.0484, "lr": 1.9097717861619907e-06, "epoch": 0.22275967413441955, "percentage": 22.28, "elapsed_time": "0:06:30", "remaining_time": "0:22:43", "throughput": 6442.68, "total_tokens": 2518080}
{"current_steps": 2630, "total_steps": 11784, "loss": 0.0655, "lr": 1.9091559356578445e-06, "epoch": 0.22318397827562797, "percentage": 22.32, "elapsed_time": "0:06:31", "remaining_time": "0:22:41", "throughput": 6449.05, "total_tokens": 2522688}
{"current_steps": 2635, "total_steps": 11784, "loss": 0.0933, "lr": 1.9085380905495985e-06, "epoch": 0.2236082824168364, "percentage": 22.36, "elapsed_time": "0:06:31", "remaining_time": "0:22:39", "throughput": 6454.81, "total_tokens": 2527040}
{"current_steps": 2640, "total_steps": 11784, "loss": 0.0743, "lr": 1.9079182521927475e-06, "epoch": 0.2240325865580448, "percentage": 22.4, "elapsed_time": "0:06:31", "remaining_time": "0:22:37", "throughput": 6460.98, "total_tokens": 2531584}
{"current_steps": 2645, "total_steps": 11784, "loss": 0.1144, "lr": 1.9072964219471594e-06, "epoch": 0.22445689069925323, "percentage": 22.45, "elapsed_time": "0:06:32", "remaining_time": "0:22:35", "throughput": 6467.62, "total_tokens": 2536384}
{"current_steps": 2650, "total_steps": 11784, "loss": 0.0821, "lr": 1.9066726011770724e-06, "epoch": 0.22488119484046165, "percentage": 22.49, "elapsed_time": "0:06:32", "remaining_time": "0:22:32", "throughput": 6473.41, "total_tokens": 2540800}
{"current_steps": 2655, "total_steps": 11784, "loss": 0.02, "lr": 1.906046791251092e-06, "epoch": 0.22530549898167007, "percentage": 22.53, "elapsed_time": "0:06:32", "remaining_time": "0:22:30", "throughput": 6480.1, "total_tokens": 2545600}
{"current_steps": 2660, "total_steps": 11784, "loss": 0.1331, "lr": 1.9054189935421868e-06, "epoch": 0.2257298031228785, "percentage": 22.57, "elapsed_time": "0:06:33", "remaining_time": "0:22:28", "throughput": 6487.13, "total_tokens": 2550528}
{"current_steps": 2665, "total_steps": 11784, "loss": 0.0412, "lr": 1.9047892094276871e-06, "epoch": 0.22615410726408688, "percentage": 22.62, "elapsed_time": "0:06:33", "remaining_time": "0:22:26", "throughput": 6493.89, "total_tokens": 2555328}
{"current_steps": 2670, "total_steps": 11784, "loss": 0.0844, "lr": 1.9041574402892813e-06, "epoch": 0.2265784114052953, "percentage": 22.66, "elapsed_time": "0:06:33", "remaining_time": "0:22:24", "throughput": 6501.03, "total_tokens": 2560320}
{"current_steps": 2675, "total_steps": 11784, "loss": 0.0467, "lr": 1.903523687513012e-06, "epoch": 0.22700271554650372, "percentage": 22.7, "elapsed_time": "0:06:34", "remaining_time": "0:22:22", "throughput": 6507.03, "total_tokens": 2564800}
{"current_steps": 2680, "total_steps": 11784, "loss": 0.0676, "lr": 1.902887952489275e-06, "epoch": 0.22742701968771215, "percentage": 22.74, "elapsed_time": "0:06:34", "remaining_time": "0:22:20", "throughput": 6513.8, "total_tokens": 2569664}
{"current_steps": 2685, "total_steps": 11784, "loss": 0.0301, "lr": 1.9022502366128132e-06, "epoch": 0.22785132382892057, "percentage": 22.79, "elapsed_time": "0:06:34", "remaining_time": "0:22:18", "throughput": 6520.74, "total_tokens": 2574592}
{"current_steps": 2690, "total_steps": 11784, "loss": 0.1049, "lr": 1.9016105412827173e-06, "epoch": 0.22827562797012899, "percentage": 22.83, "elapsed_time": "0:06:35", "remaining_time": "0:22:15", "throughput": 6527.26, "total_tokens": 2579328}
{"current_steps": 2695, "total_steps": 11784, "loss": 0.0181, "lr": 1.9009688679024189e-06, "epoch": 0.2286999321113374, "percentage": 22.87, "elapsed_time": "0:06:35", "remaining_time": "0:22:13", "throughput": 6535.54, "total_tokens": 2584896}
{"current_steps": 2700, "total_steps": 11784, "loss": 0.1308, "lr": 1.9003252178796907e-06, "epoch": 0.22912423625254583, "percentage": 22.91, "elapsed_time": "0:06:35", "remaining_time": "0:22:11", "throughput": 6541.76, "total_tokens": 2589504}
{"current_steps": 2705, "total_steps": 11784, "loss": 0.0851, "lr": 1.8996795926266412e-06, "epoch": 0.22954854039375425, "percentage": 22.95, "elapsed_time": "0:06:36", "remaining_time": "0:22:09", "throughput": 6548.34, "total_tokens": 2594304}
{"current_steps": 2710, "total_steps": 11784, "loss": 0.0292, "lr": 1.899031993559712e-06, "epoch": 0.22997284453496267, "percentage": 23.0, "elapsed_time": "0:06:36", "remaining_time": "0:22:07", "throughput": 6554.2, "total_tokens": 2598784}
{"current_steps": 2715, "total_steps": 11784, "loss": 0.0709, "lr": 1.8983824220996764e-06, "epoch": 0.2303971486761711, "percentage": 23.04, "elapsed_time": "0:06:36", "remaining_time": "0:22:05", "throughput": 6561.04, "total_tokens": 2603712}
{"current_steps": 2720, "total_steps": 11784, "loss": 0.0578, "lr": 1.8977308796716338e-06, "epoch": 0.2308214528173795, "percentage": 23.08, "elapsed_time": "0:06:37", "remaining_time": "0:22:03", "throughput": 6567.22, "total_tokens": 2608320}
{"current_steps": 2725, "total_steps": 11784, "loss": 0.0302, "lr": 1.897077367705008e-06, "epoch": 0.23124575695858793, "percentage": 23.12, "elapsed_time": "0:06:37", "remaining_time": "0:22:01", "throughput": 6574.05, "total_tokens": 2613248}
{"current_steps": 2730, "total_steps": 11784, "loss": 0.0637, "lr": 1.896421887633544e-06, "epoch": 0.23167006109979632, "percentage": 23.17, "elapsed_time": "0:06:37", "remaining_time": "0:21:59", "throughput": 6579.65, "total_tokens": 2617664}
{"current_steps": 2735, "total_steps": 11784, "loss": 0.0716, "lr": 1.8957644408953044e-06, "epoch": 0.23209436524100474, "percentage": 23.21, "elapsed_time": "0:06:38", "remaining_time": "0:21:57", "throughput": 6585.13, "total_tokens": 2622016}
{"current_steps": 2740, "total_steps": 11784, "loss": 0.0438, "lr": 1.8951050289326664e-06, "epoch": 0.23251866938221316, "percentage": 23.25, "elapsed_time": "0:06:38", "remaining_time": "0:21:55", "throughput": 6590.71, "total_tokens": 2626368}
{"current_steps": 2745, "total_steps": 11784, "loss": 0.032, "lr": 1.8944436531923193e-06, "epoch": 0.23294297352342158, "percentage": 23.29, "elapsed_time": "0:06:38", "remaining_time": "0:21:53", "throughput": 6596.23, "total_tokens": 2630720}
{"current_steps": 2750, "total_steps": 11784, "loss": 0.1554, "lr": 1.8937803151252603e-06, "epoch": 0.23336727766463, "percentage": 23.34, "elapsed_time": "0:06:39", "remaining_time": "0:21:51", "throughput": 6602.57, "total_tokens": 2635456}
{"current_steps": 2755, "total_steps": 11784, "loss": 0.1055, "lr": 1.8931150161867915e-06, "epoch": 0.23379158180583842, "percentage": 23.38, "elapsed_time": "0:06:39", "remaining_time": "0:21:49", "throughput": 6607.96, "total_tokens": 2639744}
{"current_steps": 2760, "total_steps": 11784, "loss": 0.0627, "lr": 1.8924477578365177e-06, "epoch": 0.23421588594704684, "percentage": 23.42, "elapsed_time": "0:06:39", "remaining_time": "0:21:47", "throughput": 6613.04, "total_tokens": 2643904}
{"current_steps": 2765, "total_steps": 11784, "loss": 0.0403, "lr": 1.8917785415383415e-06, "epoch": 0.23464019008825526, "percentage": 23.46, "elapsed_time": "0:06:40", "remaining_time": "0:21:45", "throughput": 6619.64, "total_tokens": 2648768}
{"current_steps": 2770, "total_steps": 11784, "loss": 0.0271, "lr": 1.8911073687604622e-06, "epoch": 0.23506449422946368, "percentage": 23.51, "elapsed_time": "0:06:40", "remaining_time": "0:21:43", "throughput": 6626.9, "total_tokens": 2653952}
{"current_steps": 2775, "total_steps": 11784, "loss": 0.0031, "lr": 1.8904342409753703e-06, "epoch": 0.2354887983706721, "percentage": 23.55, "elapsed_time": "0:06:40", "remaining_time": "0:21:41", "throughput": 6632.58, "total_tokens": 2658432}
{"current_steps": 2780, "total_steps": 11784, "loss": 0.054, "lr": 1.8897591596598464e-06, "epoch": 0.23591310251188052, "percentage": 23.59, "elapsed_time": "0:06:41", "remaining_time": "0:21:39", "throughput": 6638.89, "total_tokens": 2663168}
{"current_steps": 2785, "total_steps": 11784, "loss": 0.1288, "lr": 1.8890821262949564e-06, "epoch": 0.23633740665308894, "percentage": 23.63, "elapsed_time": "0:06:41", "remaining_time": "0:21:37", "throughput": 6645.53, "total_tokens": 2668096}
{"current_steps": 2790, "total_steps": 11784, "loss": 0.1241, "lr": 1.8884031423660488e-06, "epoch": 0.23676171079429736, "percentage": 23.68, "elapsed_time": "0:06:41", "remaining_time": "0:21:35", "throughput": 6651.28, "total_tokens": 2672576}
{"current_steps": 2795, "total_steps": 11784, "loss": 0.0832, "lr": 1.8877222093627517e-06, "epoch": 0.23718601493550576, "percentage": 23.72, "elapsed_time": "0:06:42", "remaining_time": "0:21:33", "throughput": 6659.66, "total_tokens": 2678336}
{"current_steps": 2800, "total_steps": 11784, "loss": 0.1352, "lr": 1.8870393287789694e-06, "epoch": 0.23761031907671418, "percentage": 23.76, "elapsed_time": "0:06:42", "remaining_time": "0:21:31", "throughput": 6668.45, "total_tokens": 2684288}
{"current_steps": 2805, "total_steps": 11784, "loss": 0.0542, "lr": 1.8863545021128781e-06, "epoch": 0.2380346232179226, "percentage": 23.8, "elapsed_time": "0:06:42", "remaining_time": "0:21:29", "throughput": 6673.97, "total_tokens": 2688704}
{"current_steps": 2810, "total_steps": 11784, "loss": 0.0608, "lr": 1.885667730866925e-06, "epoch": 0.23845892735913102, "percentage": 23.85, "elapsed_time": "0:06:43", "remaining_time": "0:21:27", "throughput": 6679.41, "total_tokens": 2693056}
{"current_steps": 2815, "total_steps": 11784, "loss": 0.0844, "lr": 1.884979016547822e-06, "epoch": 0.23888323150033944, "percentage": 23.89, "elapsed_time": "0:06:43", "remaining_time": "0:21:25", "throughput": 6684.52, "total_tokens": 2697280}
{"current_steps": 2820, "total_steps": 11784, "loss": 0.0769, "lr": 1.8842883606665457e-06, "epoch": 0.23930753564154786, "percentage": 23.93, "elapsed_time": "0:06:43", "remaining_time": "0:21:23", "throughput": 6689.44, "total_tokens": 2701440}
{"current_steps": 2825, "total_steps": 11784, "loss": 0.0935, "lr": 1.88359576473833e-06, "epoch": 0.23973183978275628, "percentage": 23.97, "elapsed_time": "0:06:44", "remaining_time": "0:21:21", "throughput": 6697.88, "total_tokens": 2707264}
{"current_steps": 2830, "total_steps": 11784, "loss": 0.1271, "lr": 1.8829012302826674e-06, "epoch": 0.2401561439239647, "percentage": 24.02, "elapsed_time": "0:06:44", "remaining_time": "0:21:19", "throughput": 6703.38, "total_tokens": 2711680}
{"current_steps": 2835, "total_steps": 11784, "loss": 0.0232, "lr": 1.8822047588233017e-06, "epoch": 0.24058044806517312, "percentage": 24.06, "elapsed_time": "0:06:44", "remaining_time": "0:21:17", "throughput": 6709.41, "total_tokens": 2716352}
{"current_steps": 2840, "total_steps": 11784, "loss": 0.0673, "lr": 1.881506351888227e-06, "epoch": 0.24100475220638154, "percentage": 24.1, "elapsed_time": "0:06:45", "remaining_time": "0:21:16", "throughput": 6715.42, "total_tokens": 2721024}
{"current_steps": 2845, "total_steps": 11784, "loss": 0.0675, "lr": 1.8808060110096839e-06, "epoch": 0.24142905634758996, "percentage": 24.14, "elapsed_time": "0:06:45", "remaining_time": "0:21:14", "throughput": 6721.4, "total_tokens": 2725696}
{"current_steps": 2850, "total_steps": 11784, "loss": 0.0625, "lr": 1.8801037377241553e-06, "epoch": 0.24185336048879838, "percentage": 24.19, "elapsed_time": "0:06:45", "remaining_time": "0:21:12", "throughput": 6729.42, "total_tokens": 2731328}
{"current_steps": 2855, "total_steps": 11784, "loss": 0.115, "lr": 1.879399533572364e-06, "epoch": 0.2422776646300068, "percentage": 24.23, "elapsed_time": "0:06:46", "remaining_time": "0:21:10", "throughput": 6735.82, "total_tokens": 2736192}
{"current_steps": 2860, "total_steps": 11784, "loss": 0.0828, "lr": 1.8786934000992688e-06, "epoch": 0.24270196877121522, "percentage": 24.27, "elapsed_time": "0:06:46", "remaining_time": "0:21:08", "throughput": 6741.17, "total_tokens": 2740544}
{"current_steps": 2865, "total_steps": 11784, "loss": 0.0668, "lr": 1.877985338854061e-06, "epoch": 0.2431262729124236, "percentage": 24.31, "elapsed_time": "0:06:46", "remaining_time": "0:21:06", "throughput": 6747.66, "total_tokens": 2745472}
{"current_steps": 2870, "total_steps": 11784, "loss": 0.0126, "lr": 1.877275351390162e-06, "epoch": 0.24355057705363203, "percentage": 24.36, "elapsed_time": "0:06:47", "remaining_time": "0:21:04", "throughput": 6754.48, "total_tokens": 2750528}
{"current_steps": 2875, "total_steps": 11784, "loss": 0.0341, "lr": 1.8765634392652183e-06, "epoch": 0.24397488119484045, "percentage": 24.4, "elapsed_time": "0:06:47", "remaining_time": "0:21:02", "throughput": 6760.69, "total_tokens": 2755328}
{"current_steps": 2880, "total_steps": 11784, "loss": 0.0878, "lr": 1.8758496040410998e-06, "epoch": 0.24439918533604887, "percentage": 24.44, "elapsed_time": "0:06:47", "remaining_time": "0:21:01", "throughput": 6766.86, "total_tokens": 2760128}
{"current_steps": 2885, "total_steps": 11784, "loss": 0.0316, "lr": 1.8751338472838942e-06, "epoch": 0.2448234894772573, "percentage": 24.48, "elapsed_time": "0:06:48", "remaining_time": "0:20:59", "throughput": 6773.12, "total_tokens": 2764992}
{"current_steps": 2890, "total_steps": 11784, "loss": 0.0563, "lr": 1.8744161705639065e-06, "epoch": 0.24524779361846571, "percentage": 24.52, "elapsed_time": "0:06:48", "remaining_time": "0:20:57", "throughput": 6778.5, "total_tokens": 2769408}
{"current_steps": 2895, "total_steps": 11784, "loss": 0.0999, "lr": 1.8736965754556526e-06, "epoch": 0.24567209775967414, "percentage": 24.57, "elapsed_time": "0:06:48", "remaining_time": "0:20:55", "throughput": 6784.91, "total_tokens": 2774336}
{"current_steps": 2900, "total_steps": 11784, "loss": 0.1851, "lr": 1.8729750635378578e-06, "epoch": 0.24609640190088256, "percentage": 24.61, "elapsed_time": "0:06:49", "remaining_time": "0:20:53", "throughput": 6791.06, "total_tokens": 2779136}
{"current_steps": 2905, "total_steps": 11784, "loss": 0.0546, "lr": 1.872251636393453e-06, "epoch": 0.24652070604209098, "percentage": 24.65, "elapsed_time": "0:06:49", "remaining_time": "0:20:51", "throughput": 6797.94, "total_tokens": 2784256}
{"current_steps": 2910, "total_steps": 11784, "loss": 0.1097, "lr": 1.8715262956095694e-06, "epoch": 0.2469450101832994, "percentage": 24.69, "elapsed_time": "0:06:49", "remaining_time": "0:20:49", "throughput": 6803.69, "total_tokens": 2788864}
{"current_steps": 2915, "total_steps": 11784, "loss": 0.0549, "lr": 1.8707990427775386e-06, "epoch": 0.24736931432450782, "percentage": 24.74, "elapsed_time": "0:06:50", "remaining_time": "0:20:48", "throughput": 6808.76, "total_tokens": 2793152}
{"current_steps": 2920, "total_steps": 11784, "loss": 0.0782, "lr": 1.870069879492886e-06, "epoch": 0.24779361846571624, "percentage": 24.78, "elapsed_time": "0:06:50", "remaining_time": "0:20:46", "throughput": 6815.31, "total_tokens": 2798144}
{"current_steps": 2925, "total_steps": 11784, "loss": 0.0769, "lr": 1.869338807355328e-06, "epoch": 0.24821792260692466, "percentage": 24.82, "elapsed_time": "0:06:50", "remaining_time": "0:20:44", "throughput": 6821.78, "total_tokens": 2803136}
{"current_steps": 2930, "total_steps": 11784, "loss": 0.0514, "lr": 1.8686058279687699e-06, "epoch": 0.24864222674813305, "percentage": 24.86, "elapsed_time": "0:06:51", "remaining_time": "0:20:42", "throughput": 6827.51, "total_tokens": 2807744}
{"current_steps": 2935, "total_steps": 11784, "loss": 0.038, "lr": 1.8678709429413e-06, "epoch": 0.24906653088934147, "percentage": 24.91, "elapsed_time": "0:06:51", "remaining_time": "0:20:40", "throughput": 6834.29, "total_tokens": 2812928}
{"current_steps": 2940, "total_steps": 11784, "loss": 0.0578, "lr": 1.867134153885189e-06, "epoch": 0.2494908350305499, "percentage": 24.95, "elapsed_time": "0:06:51", "remaining_time": "0:20:39", "throughput": 6839.84, "total_tokens": 2817536}
{"current_steps": 2945, "total_steps": 11784, "loss": 0.0818, "lr": 1.8663954624168832e-06, "epoch": 0.2499151391717583, "percentage": 24.99, "elapsed_time": "0:06:52", "remaining_time": "0:20:37", "throughput": 6846.82, "total_tokens": 2822784}
{"current_steps": 2950, "total_steps": 11784, "loss": 0.0749, "lr": 1.8656548701570039e-06, "epoch": 0.25033944331296676, "percentage": 25.03, "elapsed_time": "0:06:52", "remaining_time": "0:20:35", "throughput": 6852.35, "total_tokens": 2827328}
{"current_steps": 2950, "total_steps": 11784, "eval_loss": 0.07611989974975586, "epoch": 0.25033944331296676, "percentage": 25.03, "elapsed_time": "0:07:08", "remaining_time": "0:21:23", "throughput": 6598.04, "total_tokens": 2827328}
{"current_steps": 2955, "total_steps": 11784, "loss": 0.0738, "lr": 1.864912378730342e-06, "epoch": 0.2507637474541752, "percentage": 25.08, "elapsed_time": "0:07:34", "remaining_time": "0:22:39", "throughput": 6225.05, "total_tokens": 2832128}
{"current_steps": 2960, "total_steps": 11784, "loss": 0.149, "lr": 1.8641679897658551e-06, "epoch": 0.25118805159538354, "percentage": 25.12, "elapsed_time": "0:07:35", "remaining_time": "0:22:37", "throughput": 6232.76, "total_tokens": 2837824}
{"current_steps": 2965, "total_steps": 11784, "loss": 0.063, "lr": 1.8634217048966633e-06, "epoch": 0.25161235573659196, "percentage": 25.16, "elapsed_time": "0:07:35", "remaining_time": "0:22:35", "throughput": 6238.01, "total_tokens": 2842240}
{"current_steps": 2970, "total_steps": 11784, "loss": 0.0512, "lr": 1.8626735257600475e-06, "epoch": 0.2520366598778004, "percentage": 25.2, "elapsed_time": "0:07:35", "remaining_time": "0:22:33", "throughput": 6243.64, "total_tokens": 2846848}
{"current_steps": 2975, "total_steps": 11784, "loss": 0.0923, "lr": 1.8619234539974429e-06, "epoch": 0.2524609640190088, "percentage": 25.25, "elapsed_time": "0:07:36", "remaining_time": "0:22:31", "throughput": 6249.07, "total_tokens": 2851392}
{"current_steps": 2980, "total_steps": 11784, "loss": 0.0373, "lr": 1.8611714912544376e-06, "epoch": 0.2528852681602172, "percentage": 25.29, "elapsed_time": "0:07:36", "remaining_time": "0:22:29", "throughput": 6254.02, "total_tokens": 2855680}
{"current_steps": 2985, "total_steps": 11784, "loss": 0.0624, "lr": 1.860417639180769e-06, "epoch": 0.25330957230142565, "percentage": 25.33, "elapsed_time": "0:07:36", "remaining_time": "0:22:26", "throughput": 6260.09, "total_tokens": 2860544}
{"current_steps": 2990, "total_steps": 11784, "loss": 0.0577, "lr": 1.8596618994303183e-06, "epoch": 0.25373387644263407, "percentage": 25.37, "elapsed_time": "0:07:37", "remaining_time": "0:22:24", "throughput": 6265.64, "total_tokens": 2865152}
{"current_steps": 2995, "total_steps": 11784, "loss": 0.066, "lr": 1.858904273661109e-06, "epoch": 0.2541581805838425, "percentage": 25.42, "elapsed_time": "0:07:37", "remaining_time": "0:22:22", "throughput": 6271.93, "total_tokens": 2870144}
{"current_steps": 3000, "total_steps": 11784, "loss": 0.0492, "lr": 1.8581447635353019e-06, "epoch": 0.2545824847250509, "percentage": 25.46, "elapsed_time": "0:07:37", "remaining_time": "0:22:20", "throughput": 6278.33, "total_tokens": 2875200}
{"current_steps": 3005, "total_steps": 11784, "loss": 0.1037, "lr": 1.8573833707191918e-06, "epoch": 0.2550067888662593, "percentage": 25.5, "elapsed_time": "0:07:38", "remaining_time": "0:22:18", "throughput": 6284.59, "total_tokens": 2880192}
{"current_steps": 3010, "total_steps": 11784, "loss": 0.1198, "lr": 1.8566200968832044e-06, "epoch": 0.25543109300746775, "percentage": 25.54, "elapsed_time": "0:07:38", "remaining_time": "0:22:16", "throughput": 6290.17, "total_tokens": 2884800}
{"current_steps": 3015, "total_steps": 11784, "loss": 0.0739, "lr": 1.855854943701892e-06, "epoch": 0.25585539714867617, "percentage": 25.59, "elapsed_time": "0:07:38", "remaining_time": "0:22:14", "throughput": 6297.18, "total_tokens": 2890176}
{"current_steps": 3020, "total_steps": 11784, "loss": 0.1248, "lr": 1.85508791285393e-06, "epoch": 0.2562797012898846, "percentage": 25.63, "elapsed_time": "0:07:39", "remaining_time": "0:22:12", "throughput": 6303.16, "total_tokens": 2895040}
{"current_steps": 3025, "total_steps": 11784, "loss": 0.0693, "lr": 1.8543190060221125e-06, "epoch": 0.256704005431093, "percentage": 25.67, "elapsed_time": "0:07:39", "remaining_time": "0:22:10", "throughput": 6308.94, "total_tokens": 2899776}
{"current_steps": 3030, "total_steps": 11784, "loss": 0.0601, "lr": 1.853548224893351e-06, "epoch": 0.25712830957230143, "percentage": 25.71, "elapsed_time": "0:07:39", "remaining_time": "0:22:08", "throughput": 6313.9, "total_tokens": 2904064}
{"current_steps": 3035, "total_steps": 11784, "loss": 0.0395, "lr": 1.8527755711586678e-06, "epoch": 0.25755261371350985, "percentage": 25.76, "elapsed_time": "0:07:40", "remaining_time": "0:22:06", "throughput": 6319.68, "total_tokens": 2908800}
{"current_steps": 3040, "total_steps": 11784, "loss": 0.0432, "lr": 1.8520010465131935e-06, "epoch": 0.25797691785471827, "percentage": 25.8, "elapsed_time": "0:07:40", "remaining_time": "0:22:04", "throughput": 6324.84, "total_tokens": 2913216}
{"current_steps": 3045, "total_steps": 11784, "loss": 0.0755, "lr": 1.8512246526561636e-06, "epoch": 0.2584012219959267, "percentage": 25.84, "elapsed_time": "0:07:40", "remaining_time": "0:22:02", "throughput": 6329.72, "total_tokens": 2917504}
{"current_steps": 3050, "total_steps": 11784, "loss": 0.1289, "lr": 1.8504463912909149e-06, "epoch": 0.2588255261371351, "percentage": 25.88, "elapsed_time": "0:07:41", "remaining_time": "0:22:00", "throughput": 6336.42, "total_tokens": 2922752}
{"current_steps": 3055, "total_steps": 11784, "loss": 0.0354, "lr": 1.8496662641248807e-06, "epoch": 0.25924983027834353, "percentage": 25.92, "elapsed_time": "0:07:41", "remaining_time": "0:21:58", "throughput": 6343.08, "total_tokens": 2928000}
{"current_steps": 3060, "total_steps": 11784, "loss": 0.0658, "lr": 1.8488842728695874e-06, "epoch": 0.25967413441955195, "percentage": 25.97, "elapsed_time": "0:07:41", "remaining_time": "0:21:56", "throughput": 6348.82, "total_tokens": 2932736}
{"current_steps": 3065, "total_steps": 11784, "loss": 0.1191, "lr": 1.8481004192406525e-06, "epoch": 0.26009843856076037, "percentage": 26.01, "elapsed_time": "0:07:42", "remaining_time": "0:21:55", "throughput": 6354.85, "total_tokens": 2937664}
{"current_steps": 3070, "total_steps": 11784, "loss": 0.1139, "lr": 1.8473147049577773e-06, "epoch": 0.2605227427019688, "percentage": 26.05, "elapsed_time": "0:07:42", "remaining_time": "0:21:53", "throughput": 6361.27, "total_tokens": 2942784}
{"current_steps": 3075, "total_steps": 11784, "loss": 0.1196, "lr": 1.8465271317447474e-06, "epoch": 0.2609470468431772, "percentage": 26.09, "elapsed_time": "0:07:42", "remaining_time": "0:21:51", "throughput": 6367.55, "total_tokens": 2947840}
{"current_steps": 3080, "total_steps": 11784, "loss": 0.0741, "lr": 1.845737701329425e-06, "epoch": 0.26137135098438563, "percentage": 26.14, "elapsed_time": "0:07:43", "remaining_time": "0:21:49", "throughput": 6372.99, "total_tokens": 2952448}
{"current_steps": 3085, "total_steps": 11784, "loss": 0.0241, "lr": 1.8449464154437475e-06, "epoch": 0.26179565512559405, "percentage": 26.18, "elapsed_time": "0:07:43", "remaining_time": "0:21:47", "throughput": 6378.49, "total_tokens": 2957120}
{"current_steps": 3090, "total_steps": 11784, "loss": 0.1096, "lr": 1.8441532758237233e-06, "epoch": 0.26221995926680247, "percentage": 26.22, "elapsed_time": "0:07:43", "remaining_time": "0:21:45", "throughput": 6383.91, "total_tokens": 2961728}
{"current_steps": 3095, "total_steps": 11784, "loss": 0.0875, "lr": 1.8433582842094273e-06, "epoch": 0.26264426340801084, "percentage": 26.26, "elapsed_time": "0:07:44", "remaining_time": "0:21:43", "throughput": 6389.07, "total_tokens": 2966208}
{"current_steps": 3100, "total_steps": 11784, "loss": 0.0347, "lr": 1.8425614423449974e-06, "epoch": 0.26306856754921926, "percentage": 26.31, "elapsed_time": "0:07:44", "remaining_time": "0:21:41", "throughput": 6397.15, "total_tokens": 2972288}
{"current_steps": 3105, "total_steps": 11784, "loss": 0.0902, "lr": 1.8417627519786313e-06, "epoch": 0.2634928716904277, "percentage": 26.35, "elapsed_time": "0:07:44", "remaining_time": "0:21:39", "throughput": 6401.83, "total_tokens": 2976512}
{"current_steps": 3110, "total_steps": 11784, "loss": 0.0626, "lr": 1.840962214862582e-06, "epoch": 0.2639171758316361, "percentage": 26.39, "elapsed_time": "0:07:45", "remaining_time": "0:21:37", "throughput": 6407.44, "total_tokens": 2981248}
{"current_steps": 3115, "total_steps": 11784, "loss": 0.0862, "lr": 1.8401598327531533e-06, "epoch": 0.2643414799728445, "percentage": 26.43, "elapsed_time": "0:07:45", "remaining_time": "0:21:35", "throughput": 6412.6, "total_tokens": 2985728}
{"current_steps": 3120, "total_steps": 11784, "loss": 0.0586, "lr": 1.839355607410698e-06, "epoch": 0.26476578411405294, "percentage": 26.48, "elapsed_time": "0:07:45", "remaining_time": "0:21:33", "throughput": 6417.44, "total_tokens": 2990144}
{"current_steps": 3125, "total_steps": 11784, "loss": 0.0669, "lr": 1.8385495405996119e-06, "epoch": 0.26519008825526136, "percentage": 26.52, "elapsed_time": "0:07:46", "remaining_time": "0:21:31", "throughput": 6422.41, "total_tokens": 2994560}
{"current_steps": 3130, "total_steps": 11784, "loss": 0.0625, "lr": 1.8377416340883312e-06, "epoch": 0.2656143923964698, "percentage": 26.56, "elapsed_time": "0:07:46", "remaining_time": "0:21:30", "throughput": 6428.34, "total_tokens": 2999488}
{"current_steps": 3135, "total_steps": 11784, "loss": 0.0634, "lr": 1.836931889649328e-06, "epoch": 0.2660386965376782, "percentage": 26.6, "elapsed_time": "0:07:46", "remaining_time": "0:21:28", "throughput": 6433.68, "total_tokens": 3004096}
{"current_steps": 3140, "total_steps": 11784, "loss": 0.1258, "lr": 1.8361203090591068e-06, "epoch": 0.2664630006788866, "percentage": 26.65, "elapsed_time": "0:07:47", "remaining_time": "0:21:26", "throughput": 6438.65, "total_tokens": 3008512}
{"current_steps": 3145, "total_steps": 11784, "loss": 0.0708, "lr": 1.8353068940982006e-06, "epoch": 0.26688730482009504, "percentage": 26.69, "elapsed_time": "0:07:47", "remaining_time": "0:21:24", "throughput": 6444.68, "total_tokens": 3013504}
{"current_steps": 3150, "total_steps": 11784, "loss": 0.0164, "lr": 1.8344916465511664e-06, "epoch": 0.26731160896130346, "percentage": 26.73, "elapsed_time": "0:07:47", "remaining_time": "0:21:22", "throughput": 6450.01, "total_tokens": 3018112}
{"current_steps": 3155, "total_steps": 11784, "loss": 0.1132, "lr": 1.833674568206582e-06, "epoch": 0.2677359131025119, "percentage": 26.77, "elapsed_time": "0:07:48", "remaining_time": "0:21:20", "throughput": 6456.12, "total_tokens": 3023168}
{"current_steps": 3160, "total_steps": 11784, "loss": 0.0723, "lr": 1.832855660857042e-06, "epoch": 0.2681602172437203, "percentage": 26.82, "elapsed_time": "0:07:48", "remaining_time": "0:21:18", "throughput": 6461.54, "total_tokens": 3027840}
{"current_steps": 3165, "total_steps": 11784, "loss": 0.1293, "lr": 1.8320349262991532e-06, "epoch": 0.2685845213849287, "percentage": 26.86, "elapsed_time": "0:07:48", "remaining_time": "0:21:17", "throughput": 6469.93, "total_tokens": 3034176}
{"current_steps": 3170, "total_steps": 11784, "loss": 0.063, "lr": 1.8312123663335316e-06, "epoch": 0.26900882552613714, "percentage": 26.9, "elapsed_time": "0:07:49", "remaining_time": "0:21:15", "throughput": 6474.59, "total_tokens": 3038464}
{"current_steps": 3175, "total_steps": 11784, "loss": 0.0748, "lr": 1.8303879827647974e-06, "epoch": 0.26943312966734556, "percentage": 26.94, "elapsed_time": "0:07:49", "remaining_time": "0:21:13", "throughput": 6479.59, "total_tokens": 3042944}
{"current_steps": 3180, "total_steps": 11784, "loss": 0.0582, "lr": 1.8295617774015724e-06, "epoch": 0.269857433808554, "percentage": 26.99, "elapsed_time": "0:07:49", "remaining_time": "0:21:11", "throughput": 6485.67, "total_tokens": 3048000}
{"current_steps": 3185, "total_steps": 11784, "loss": 0.0863, "lr": 1.8287337520564744e-06, "epoch": 0.2702817379497624, "percentage": 27.03, "elapsed_time": "0:07:50", "remaining_time": "0:21:09", "throughput": 6491.74, "total_tokens": 3053056}
{"current_steps": 3190, "total_steps": 11784, "loss": 0.1082, "lr": 1.8279039085461148e-06, "epoch": 0.2707060420909708, "percentage": 27.07, "elapsed_time": "0:07:50", "remaining_time": "0:21:07", "throughput": 6497.2, "total_tokens": 3057792}
{"current_steps": 3195, "total_steps": 11784, "loss": 0.1442, "lr": 1.8270722486910933e-06, "epoch": 0.27113034623217924, "percentage": 27.11, "elapsed_time": "0:07:50", "remaining_time": "0:21:06", "throughput": 6503.17, "total_tokens": 3062784}
{"current_steps": 3200, "total_steps": 11784, "loss": 0.1048, "lr": 1.8262387743159948e-06, "epoch": 0.27155465037338766, "percentage": 27.16, "elapsed_time": "0:07:51", "remaining_time": "0:21:04", "throughput": 6509.02, "total_tokens": 3067712}
{"current_steps": 3205, "total_steps": 11784, "loss": 0.0471, "lr": 1.8254034872493853e-06, "epoch": 0.2719789545145961, "percentage": 27.2, "elapsed_time": "0:07:51", "remaining_time": "0:21:02", "throughput": 6513.63, "total_tokens": 3072000}
{"current_steps": 3210, "total_steps": 11784, "loss": 0.0572, "lr": 1.8245663893238072e-06, "epoch": 0.2724032586558045, "percentage": 27.24, "elapsed_time": "0:07:51", "remaining_time": "0:21:00", "throughput": 6518.49, "total_tokens": 3076416}
{"current_steps": 3215, "total_steps": 11784, "loss": 0.0936, "lr": 1.823727482375776e-06, "epoch": 0.2728275627970129, "percentage": 27.28, "elapsed_time": "0:07:52", "remaining_time": "0:20:58", "throughput": 6525.01, "total_tokens": 3081792}
{"current_steps": 3220, "total_steps": 11784, "loss": 0.1179, "lr": 1.8228867682457762e-06, "epoch": 0.27325186693822134, "percentage": 27.33, "elapsed_time": "0:07:52", "remaining_time": "0:20:57", "throughput": 6530.65, "total_tokens": 3086656}
{"current_steps": 3225, "total_steps": 11784, "loss": 0.0912, "lr": 1.8220442487782565e-06, "epoch": 0.2736761710794297, "percentage": 27.37, "elapsed_time": "0:07:52", "remaining_time": "0:20:55", "throughput": 6536.0, "total_tokens": 3091328}
{"current_steps": 3230, "total_steps": 11784, "loss": 0.0176, "lr": 1.8211999258216273e-06, "epoch": 0.27410047522063813, "percentage": 27.41, "elapsed_time": "0:07:53", "remaining_time": "0:20:53", "throughput": 6542.17, "total_tokens": 3096448}
{"current_steps": 3235, "total_steps": 11784, "loss": 0.0774, "lr": 1.8203538012282548e-06, "epoch": 0.27452477936184655, "percentage": 27.45, "elapsed_time": "0:07:53", "remaining_time": "0:20:51", "throughput": 6549.77, "total_tokens": 3102400}
{"current_steps": 3240, "total_steps": 11784, "loss": 0.0535, "lr": 1.8195058768544583e-06, "epoch": 0.27494908350305497, "percentage": 27.49, "elapsed_time": "0:07:53", "remaining_time": "0:20:49", "throughput": 6554.96, "total_tokens": 3107008}
{"current_steps": 3245, "total_steps": 11784, "loss": 0.0291, "lr": 1.8186561545605052e-06, "epoch": 0.2753733876442634, "percentage": 27.54, "elapsed_time": "0:07:54", "remaining_time": "0:20:48", "throughput": 6560.59, "total_tokens": 3111872}
{"current_steps": 3250, "total_steps": 11784, "loss": 0.0274, "lr": 1.8178046362106083e-06, "epoch": 0.2757976917854718, "percentage": 27.58, "elapsed_time": "0:07:54", "remaining_time": "0:20:46", "throughput": 6565.83, "total_tokens": 3116544}
{"current_steps": 3255, "total_steps": 11784, "loss": 0.1035, "lr": 1.8169513236729195e-06, "epoch": 0.27622199592668023, "percentage": 27.62, "elapsed_time": "0:07:54", "remaining_time": "0:20:44", "throughput": 6570.69, "total_tokens": 3121024}
{"current_steps": 3260, "total_steps": 11784, "loss": 0.0561, "lr": 1.8160962188195278e-06, "epoch": 0.27664630006788865, "percentage": 27.66, "elapsed_time": "0:07:55", "remaining_time": "0:20:42", "throughput": 6575.92, "total_tokens": 3125696}
{"current_steps": 3265, "total_steps": 11784, "loss": 0.0989, "lr": 1.8152393235264545e-06, "epoch": 0.27707060420909707, "percentage": 27.71, "elapsed_time": "0:07:55", "remaining_time": "0:20:41", "throughput": 6581.86, "total_tokens": 3130752}
{"current_steps": 3270, "total_steps": 11784, "loss": 0.0991, "lr": 1.8143806396736486e-06, "epoch": 0.2774949083503055, "percentage": 27.75, "elapsed_time": "0:07:55", "remaining_time": "0:20:39", "throughput": 6586.94, "total_tokens": 3135360}
{"current_steps": 3275, "total_steps": 11784, "loss": 0.1135, "lr": 1.813520169144983e-06, "epoch": 0.2779192124915139, "percentage": 27.79, "elapsed_time": "0:07:56", "remaining_time": "0:20:37", "throughput": 6592.13, "total_tokens": 3140032}
{"current_steps": 3280, "total_steps": 11784, "loss": 0.0532, "lr": 1.8126579138282501e-06, "epoch": 0.27834351663272233, "percentage": 27.83, "elapsed_time": "0:07:56", "remaining_time": "0:20:35", "throughput": 6597.77, "total_tokens": 3144960}
{"current_steps": 3285, "total_steps": 11784, "loss": 0.065, "lr": 1.8117938756151592e-06, "epoch": 0.27876782077393075, "percentage": 27.88, "elapsed_time": "0:07:57", "remaining_time": "0:20:34", "throughput": 6603.64, "total_tokens": 3150016}
{"current_steps": 3290, "total_steps": 11784, "loss": 0.1384, "lr": 1.8109280564013297e-06, "epoch": 0.2791921249151392, "percentage": 27.92, "elapsed_time": "0:07:57", "remaining_time": "0:20:32", "throughput": 6609.72, "total_tokens": 3155200}
{"current_steps": 3295, "total_steps": 11784, "loss": 0.0494, "lr": 1.8100604580862898e-06, "epoch": 0.2796164290563476, "percentage": 27.96, "elapsed_time": "0:07:57", "remaining_time": "0:20:30", "throughput": 6615.16, "total_tokens": 3160000}
{"current_steps": 3300, "total_steps": 11784, "loss": 0.0524, "lr": 1.8091910825734686e-06, "epoch": 0.280040733197556, "percentage": 28.0, "elapsed_time": "0:07:58", "remaining_time": "0:20:28", "throughput": 6620.33, "total_tokens": 3164672}
{"current_steps": 3305, "total_steps": 11784, "loss": 0.052, "lr": 1.808319931770197e-06, "epoch": 0.28046503733876443, "percentage": 28.05, "elapsed_time": "0:07:58", "remaining_time": "0:20:27", "throughput": 6625.16, "total_tokens": 3169152}
{"current_steps": 3310, "total_steps": 11784, "loss": 0.0446, "lr": 1.8074470075876983e-06, "epoch": 0.28088934147997285, "percentage": 28.09, "elapsed_time": "0:07:58", "remaining_time": "0:20:25", "throughput": 6630.5, "total_tokens": 3173888}
{"current_steps": 3315, "total_steps": 11784, "loss": 0.0326, "lr": 1.8065723119410884e-06, "epoch": 0.2813136456211813, "percentage": 28.13, "elapsed_time": "0:07:59", "remaining_time": "0:20:23", "throughput": 6636.55, "total_tokens": 3179072}
{"current_steps": 3320, "total_steps": 11784, "loss": 0.0651, "lr": 1.8056958467493678e-06, "epoch": 0.2817379497623897, "percentage": 28.17, "elapsed_time": "0:07:59", "remaining_time": "0:20:22", "throughput": 6641.39, "total_tokens": 3183552}
{"current_steps": 3325, "total_steps": 11784, "loss": 0.0082, "lr": 1.8048176139354207e-06, "epoch": 0.2821622539035981, "percentage": 28.22, "elapsed_time": "0:07:59", "remaining_time": "0:20:21", "throughput": 6641.81, "total_tokens": 3187968}
{"current_steps": 3330, "total_steps": 11784, "loss": 0.1037, "lr": 1.8039376154260086e-06, "epoch": 0.28258655804480654, "percentage": 28.26, "elapsed_time": "0:08:00", "remaining_time": "0:20:19", "throughput": 6647.05, "total_tokens": 3192704}
{"current_steps": 3335, "total_steps": 11784, "loss": 0.0991, "lr": 1.803055853151767e-06, "epoch": 0.28301086218601496, "percentage": 28.3, "elapsed_time": "0:08:00", "remaining_time": "0:20:17", "throughput": 6652.9, "total_tokens": 3197760}
{"current_steps": 3340, "total_steps": 11784, "loss": 0.0358, "lr": 1.8021723290472007e-06, "epoch": 0.2834351663272234, "percentage": 28.34, "elapsed_time": "0:08:00", "remaining_time": "0:20:16", "throughput": 6657.84, "total_tokens": 3202368}
{"current_steps": 3345, "total_steps": 11784, "loss": 0.1846, "lr": 1.8012870450506798e-06, "epoch": 0.2838594704684318, "percentage": 28.39, "elapsed_time": "0:08:01", "remaining_time": "0:20:14", "throughput": 6663.6, "total_tokens": 3207360}
{"current_steps": 3350, "total_steps": 11784, "loss": 0.0893, "lr": 1.800400003104436e-06, "epoch": 0.2842837746096402, "percentage": 28.43, "elapsed_time": "0:08:01", "remaining_time": "0:20:12", "throughput": 6671.39, "total_tokens": 3213632}
{"current_steps": 3355, "total_steps": 11784, "loss": 0.0597, "lr": 1.799511205154557e-06, "epoch": 0.2847080787508486, "percentage": 28.47, "elapsed_time": "0:08:02", "remaining_time": "0:20:11", "throughput": 6677.96, "total_tokens": 3219136}
{"current_steps": 3360, "total_steps": 11784, "loss": 0.0728, "lr": 1.7986206531509835e-06, "epoch": 0.285132382892057, "percentage": 28.51, "elapsed_time": "0:08:02", "remaining_time": "0:20:09", "throughput": 6685.31, "total_tokens": 3225088}
{"current_steps": 3365, "total_steps": 11784, "loss": 0.0789, "lr": 1.7977283490475043e-06, "epoch": 0.2855566870332654, "percentage": 28.56, "elapsed_time": "0:08:02", "remaining_time": "0:20:07", "throughput": 6689.9, "total_tokens": 3229504}
{"current_steps": 3370, "total_steps": 11784, "loss": 0.0618, "lr": 1.796834294801752e-06, "epoch": 0.28598099117447384, "percentage": 28.6, "elapsed_time": "0:08:03", "remaining_time": "0:20:06", "throughput": 6695.34, "total_tokens": 3234368}
{"current_steps": 3375, "total_steps": 11784, "loss": 0.082, "lr": 1.7959384923751993e-06, "epoch": 0.28640529531568226, "percentage": 28.64, "elapsed_time": "0:08:03", "remaining_time": "0:20:04", "throughput": 6700.78, "total_tokens": 3239232}
{"current_steps": 3380, "total_steps": 11784, "loss": 0.064, "lr": 1.7950409437331535e-06, "epoch": 0.2868295994568907, "percentage": 28.68, "elapsed_time": "0:08:03", "remaining_time": "0:20:02", "throughput": 6706.52, "total_tokens": 3244288}
{"current_steps": 3385, "total_steps": 11784, "loss": 0.1214, "lr": 1.7941416508447534e-06, "epoch": 0.2872539035980991, "percentage": 28.73, "elapsed_time": "0:08:04", "remaining_time": "0:20:01", "throughput": 6710.99, "total_tokens": 3248640}
{"current_steps": 3390, "total_steps": 11784, "loss": 0.0186, "lr": 1.7932406156829649e-06, "epoch": 0.2876782077393075, "percentage": 28.77, "elapsed_time": "0:08:04", "remaining_time": "0:19:59", "throughput": 6716.28, "total_tokens": 3253440}
{"current_steps": 3395, "total_steps": 11784, "loss": 0.0676, "lr": 1.7923378402245756e-06, "epoch": 0.28810251188051594, "percentage": 28.81, "elapsed_time": "0:08:04", "remaining_time": "0:19:57", "throughput": 6721.2, "total_tokens": 3258048}
{"current_steps": 3400, "total_steps": 11784, "loss": 0.0332, "lr": 1.7914333264501913e-06, "epoch": 0.28852681602172436, "percentage": 28.85, "elapsed_time": "0:08:05", "remaining_time": "0:19:56", "throughput": 6726.56, "total_tokens": 3262912}
{"current_steps": 3405, "total_steps": 11784, "loss": 0.0887, "lr": 1.790527076344232e-06, "epoch": 0.2889511201629328, "percentage": 28.9, "elapsed_time": "0:08:05", "remaining_time": "0:19:54", "throughput": 6731.96, "total_tokens": 3267776}
{"current_steps": 3410, "total_steps": 11784, "loss": 0.0464, "lr": 1.7896190918949266e-06, "epoch": 0.2893754243041412, "percentage": 28.94, "elapsed_time": "0:08:05", "remaining_time": "0:19:52", "throughput": 6736.94, "total_tokens": 3272448}
{"current_steps": 3415, "total_steps": 11784, "loss": 0.07, "lr": 1.7887093750943088e-06, "epoch": 0.2897997284453496, "percentage": 28.98, "elapsed_time": "0:08:06", "remaining_time": "0:19:51", "throughput": 6741.83, "total_tokens": 3277056}
{"current_steps": 3420, "total_steps": 11784, "loss": 0.0767, "lr": 1.7877979279382131e-06, "epoch": 0.29022403258655805, "percentage": 29.02, "elapsed_time": "0:08:06", "remaining_time": "0:19:49", "throughput": 6747.37, "total_tokens": 3282048}
{"current_steps": 3425, "total_steps": 11784, "loss": 0.0967, "lr": 1.7868847524262708e-06, "epoch": 0.29064833672776647, "percentage": 29.06, "elapsed_time": "0:08:06", "remaining_time": "0:19:47", "throughput": 6751.63, "total_tokens": 3286336}
{"current_steps": 3430, "total_steps": 11784, "loss": 0.0277, "lr": 1.7859698505619043e-06, "epoch": 0.2910726408689749, "percentage": 29.11, "elapsed_time": "0:08:07", "remaining_time": "0:19:46", "throughput": 6756.41, "total_tokens": 3290880}
{"current_steps": 3435, "total_steps": 11784, "loss": 0.0378, "lr": 1.7850532243523238e-06, "epoch": 0.2914969450101833, "percentage": 29.15, "elapsed_time": "0:08:07", "remaining_time": "0:19:44", "throughput": 6761.02, "total_tokens": 3295360}
{"current_steps": 3440, "total_steps": 11784, "loss": 0.0274, "lr": 1.7841348758085224e-06, "epoch": 0.2919212491513917, "percentage": 29.19, "elapsed_time": "0:08:07", "remaining_time": "0:19:43", "throughput": 6765.65, "total_tokens": 3299840}
{"current_steps": 3445, "total_steps": 11784, "loss": 0.0298, "lr": 1.7832148069452719e-06, "epoch": 0.29234555329260015, "percentage": 29.23, "elapsed_time": "0:08:08", "remaining_time": "0:19:41", "throughput": 6770.46, "total_tokens": 3304448}
{"current_steps": 3450, "total_steps": 11784, "loss": 0.1044, "lr": 1.7822930197811186e-06, "epoch": 0.29276985743380857, "percentage": 29.28, "elapsed_time": "0:08:08", "remaining_time": "0:19:39", "throughput": 6775.06, "total_tokens": 3308928}
{"current_steps": 3455, "total_steps": 11784, "loss": 0.1, "lr": 1.781369516338378e-06, "epoch": 0.293194161575017, "percentage": 29.32, "elapsed_time": "0:08:08", "remaining_time": "0:19:38", "throughput": 6779.64, "total_tokens": 3313408}
{"current_steps": 3460, "total_steps": 11784, "loss": 0.0865, "lr": 1.7804442986431317e-06, "epoch": 0.2936184657162254, "percentage": 29.36, "elapsed_time": "0:08:09", "remaining_time": "0:19:36", "throughput": 6784.62, "total_tokens": 3318080}
{"current_steps": 3465, "total_steps": 11784, "loss": 0.0947, "lr": 1.7795173687252213e-06, "epoch": 0.29404276985743383, "percentage": 29.4, "elapsed_time": "0:08:09", "remaining_time": "0:19:34", "throughput": 6790.18, "total_tokens": 3323136}
{"current_steps": 3470, "total_steps": 11784, "loss": 0.0454, "lr": 1.778588728618246e-06, "epoch": 0.29446707399864225, "percentage": 29.45, "elapsed_time": "0:08:09", "remaining_time": "0:19:33", "throughput": 6795.29, "total_tokens": 3327936}
{"current_steps": 3475, "total_steps": 11784, "loss": 0.0718, "lr": 1.777658380359556e-06, "epoch": 0.29489137813985067, "percentage": 29.49, "elapsed_time": "0:08:10", "remaining_time": "0:19:31", "throughput": 6800.59, "total_tokens": 3332864}
{"current_steps": 3480, "total_steps": 11784, "loss": 0.0759, "lr": 1.7767263259902494e-06, "epoch": 0.2953156822810591, "percentage": 29.53, "elapsed_time": "0:08:10", "remaining_time": "0:19:30", "throughput": 6806.35, "total_tokens": 3338048}
{"current_steps": 3485, "total_steps": 11784, "loss": 0.1356, "lr": 1.7757925675551672e-06, "epoch": 0.2957399864222675, "percentage": 29.57, "elapsed_time": "0:08:10", "remaining_time": "0:19:28", "throughput": 6811.86, "total_tokens": 3343104}
{"current_steps": 3490, "total_steps": 11784, "loss": 0.0701, "lr": 1.7748571071028898e-06, "epoch": 0.2961642905634759, "percentage": 29.62, "elapsed_time": "0:08:11", "remaining_time": "0:19:27", "throughput": 6816.58, "total_tokens": 3347712}
{"current_steps": 3495, "total_steps": 11784, "loss": 0.0489, "lr": 1.7739199466857301e-06, "epoch": 0.2965885947046843, "percentage": 29.66, "elapsed_time": "0:08:11", "remaining_time": "0:19:25", "throughput": 6820.75, "total_tokens": 3352000}
{"current_steps": 3500, "total_steps": 11784, "loss": 0.0291, "lr": 1.772981088359732e-06, "epoch": 0.2970128988458927, "percentage": 29.7, "elapsed_time": "0:08:11", "remaining_time": "0:19:23", "throughput": 6825.25, "total_tokens": 3356480}
{"current_steps": 3505, "total_steps": 11784, "loss": 0.0997, "lr": 1.7720405341846636e-06, "epoch": 0.29743720298710113, "percentage": 29.74, "elapsed_time": "0:08:12", "remaining_time": "0:19:22", "throughput": 6830.75, "total_tokens": 3361536}
{"current_steps": 3510, "total_steps": 11784, "loss": 0.0796, "lr": 1.771098286224014e-06, "epoch": 0.29786150712830956, "percentage": 29.79, "elapsed_time": "0:08:12", "remaining_time": "0:19:20", "throughput": 6837.4, "total_tokens": 3367296}
{"current_steps": 3515, "total_steps": 11784, "loss": 0.0678, "lr": 1.7701543465449884e-06, "epoch": 0.298285811269518, "percentage": 29.83, "elapsed_time": "0:08:12", "remaining_time": "0:19:19", "throughput": 6842.43, "total_tokens": 3372096}
{"current_steps": 3520, "total_steps": 11784, "loss": 0.0632, "lr": 1.7692087172185026e-06, "epoch": 0.2987101154107264, "percentage": 29.87, "elapsed_time": "0:08:13", "remaining_time": "0:19:17", "throughput": 6846.53, "total_tokens": 3376384}
{"current_steps": 3525, "total_steps": 11784, "loss": 0.0409, "lr": 1.7682614003191805e-06, "epoch": 0.2991344195519348, "percentage": 29.91, "elapsed_time": "0:08:13", "remaining_time": "0:19:16", "throughput": 6851.99, "total_tokens": 3381504}
{"current_steps": 3530, "total_steps": 11784, "loss": 0.0469, "lr": 1.7673123979253475e-06, "epoch": 0.29955872369314324, "percentage": 29.96, "elapsed_time": "0:08:13", "remaining_time": "0:19:14", "throughput": 6856.62, "total_tokens": 3386112}
{"current_steps": 3535, "total_steps": 11784, "loss": 0.05, "lr": 1.7663617121190271e-06, "epoch": 0.29998302783435166, "percentage": 30.0, "elapsed_time": "0:08:14", "remaining_time": "0:19:13", "throughput": 6868.48, "total_tokens": 3395072}
{"current_steps": 3540, "total_steps": 11784, "loss": 0.0141, "lr": 1.7654093449859367e-06, "epoch": 0.3004073319755601, "percentage": 30.04, "elapsed_time": "0:08:14", "remaining_time": "0:19:11", "throughput": 6873.36, "total_tokens": 3399808}
{"current_steps": 3540, "total_steps": 11784, "eval_loss": 0.08620841801166534, "epoch": 0.3004073319755601, "percentage": 30.04, "elapsed_time": "0:08:30", "remaining_time": "0:19:49", "throughput": 6658.39, "total_tokens": 3399808}
{"current_steps": 3545, "total_steps": 11784, "loss": 0.0416, "lr": 1.764455298615481e-06, "epoch": 0.3008316361167685, "percentage": 30.08, "elapsed_time": "0:09:11", "remaining_time": "0:21:20", "throughput": 6177.14, "total_tokens": 3404544}
{"current_steps": 3550, "total_steps": 11784, "loss": 0.1003, "lr": 1.7634995751007499e-06, "epoch": 0.3012559402579769, "percentage": 30.13, "elapsed_time": "0:09:11", "remaining_time": "0:21:19", "throughput": 6181.39, "total_tokens": 3408896}
{"current_steps": 3555, "total_steps": 11784, "loss": 0.0709, "lr": 1.7625421765385124e-06, "epoch": 0.30168024439918534, "percentage": 30.17, "elapsed_time": "0:09:11", "remaining_time": "0:21:17", "throughput": 6186.54, "total_tokens": 3413824}
{"current_steps": 3560, "total_steps": 11784, "loss": 0.097, "lr": 1.7615831050292127e-06, "epoch": 0.30210454854039376, "percentage": 30.21, "elapsed_time": "0:09:12", "remaining_time": "0:21:15", "throughput": 6190.87, "total_tokens": 3418240}
{"current_steps": 3565, "total_steps": 11784, "loss": 0.1312, "lr": 1.760622362676965e-06, "epoch": 0.3025288526816022, "percentage": 30.25, "elapsed_time": "0:09:12", "remaining_time": "0:21:13", "throughput": 6196.04, "total_tokens": 3423168}
{"current_steps": 3570, "total_steps": 11784, "loss": 0.0642, "lr": 1.7596599515895486e-06, "epoch": 0.3029531568228106, "percentage": 30.3, "elapsed_time": "0:09:12", "remaining_time": "0:21:11", "throughput": 6201.38, "total_tokens": 3428224}
{"current_steps": 3575, "total_steps": 11784, "loss": 0.0485, "lr": 1.7586958738784055e-06, "epoch": 0.303377460964019, "percentage": 30.34, "elapsed_time": "0:09:13", "remaining_time": "0:21:10", "throughput": 6206.11, "total_tokens": 3432896}
{"current_steps": 3580, "total_steps": 11784, "loss": 0.1002, "lr": 1.7577301316586323e-06, "epoch": 0.30380176510522744, "percentage": 30.38, "elapsed_time": "0:09:13", "remaining_time": "0:21:08", "throughput": 6210.93, "total_tokens": 3437632}
{"current_steps": 3585, "total_steps": 11784, "loss": 0.061, "lr": 1.7567627270489787e-06, "epoch": 0.30422606924643586, "percentage": 30.42, "elapsed_time": "0:09:13", "remaining_time": "0:21:06", "throughput": 6215.34, "total_tokens": 3442112}
{"current_steps": 3590, "total_steps": 11784, "loss": 0.0435, "lr": 1.7557936621718406e-06, "epoch": 0.3046503733876443, "percentage": 30.47, "elapsed_time": "0:09:14", "remaining_time": "0:21:04", "throughput": 6222.05, "total_tokens": 3448064}
{"current_steps": 3595, "total_steps": 11784, "loss": 0.1354, "lr": 1.754822939153257e-06, "epoch": 0.3050746775288527, "percentage": 30.51, "elapsed_time": "0:09:14", "remaining_time": "0:21:03", "throughput": 6226.87, "total_tokens": 3452800}
{"current_steps": 3600, "total_steps": 11784, "loss": 0.1403, "lr": 1.7538505601229043e-06, "epoch": 0.3054989816700611, "percentage": 30.55, "elapsed_time": "0:09:14", "remaining_time": "0:21:01", "throughput": 6232.17, "total_tokens": 3457856}
{"current_steps": 3605, "total_steps": 11784, "loss": 0.036, "lr": 1.7528765272140927e-06, "epoch": 0.30592328581126954, "percentage": 30.59, "elapsed_time": "0:09:15", "remaining_time": "0:20:59", "throughput": 6237.16, "total_tokens": 3462720}
{"current_steps": 3610, "total_steps": 11784, "loss": 0.1049, "lr": 1.7519008425637597e-06, "epoch": 0.30634758995247796, "percentage": 30.63, "elapsed_time": "0:09:15", "remaining_time": "0:20:57", "throughput": 6241.64, "total_tokens": 3467264}
{"current_steps": 3615, "total_steps": 11784, "loss": 0.0713, "lr": 1.7509235083124679e-06, "epoch": 0.3067718940936864, "percentage": 30.68, "elapsed_time": "0:09:15", "remaining_time": "0:20:56", "throughput": 6247.72, "total_tokens": 3472832}
{"current_steps": 3620, "total_steps": 11784, "loss": 0.061, "lr": 1.749944526604398e-06, "epoch": 0.30719619823489475, "percentage": 30.72, "elapsed_time": "0:09:16", "remaining_time": "0:20:54", "throughput": 6253.23, "total_tokens": 3478016}
{"current_steps": 3625, "total_steps": 11784, "loss": 0.0438, "lr": 1.7489638995873453e-06, "epoch": 0.30762050237610317, "percentage": 30.76, "elapsed_time": "0:09:16", "remaining_time": "0:20:52", "throughput": 6257.92, "total_tokens": 3482688}
{"current_steps": 3630, "total_steps": 11784, "loss": 0.0193, "lr": 1.7479816294127149e-06, "epoch": 0.3080448065173116, "percentage": 30.8, "elapsed_time": "0:09:16", "remaining_time": "0:20:50", "throughput": 6262.48, "total_tokens": 3487296}
{"current_steps": 3635, "total_steps": 11784, "loss": 0.0555, "lr": 1.746997718235517e-06, "epoch": 0.30846911065852, "percentage": 30.85, "elapsed_time": "0:09:17", "remaining_time": "0:20:49", "throughput": 6266.76, "total_tokens": 3491712}
{"current_steps": 3640, "total_steps": 11784, "loss": 0.0876, "lr": 1.7460121682143616e-06, "epoch": 0.3088934147997284, "percentage": 30.89, "elapsed_time": "0:09:17", "remaining_time": "0:20:47", "throughput": 6271.21, "total_tokens": 3496256}
{"current_steps": 3645, "total_steps": 11784, "loss": 0.1017, "lr": 1.7450249815114545e-06, "epoch": 0.30931771894093685, "percentage": 30.93, "elapsed_time": "0:09:17", "remaining_time": "0:20:45", "throughput": 6275.49, "total_tokens": 3500672}
{"current_steps": 3650, "total_steps": 11784, "loss": 0.0117, "lr": 1.744036160292592e-06, "epoch": 0.30974202308214527, "percentage": 30.97, "elapsed_time": "0:09:18", "remaining_time": "0:20:43", "throughput": 6280.49, "total_tokens": 3505536}
{"current_steps": 3655, "total_steps": 11784, "loss": 0.0618, "lr": 1.7430457067271563e-06, "epoch": 0.3101663272233537, "percentage": 31.02, "elapsed_time": "0:09:18", "remaining_time": "0:20:42", "throughput": 6285.4, "total_tokens": 3510400}
{"current_steps": 3660, "total_steps": 11784, "loss": 0.03, "lr": 1.742053622988111e-06, "epoch": 0.3105906313645621, "percentage": 31.06, "elapsed_time": "0:09:18", "remaining_time": "0:20:40", "throughput": 6289.76, "total_tokens": 3514880}
{"current_steps": 3665, "total_steps": 11784, "loss": 0.1128, "lr": 1.7410599112519969e-06, "epoch": 0.31101493550577053, "percentage": 31.1, "elapsed_time": "0:09:19", "remaining_time": "0:20:38", "throughput": 6295.2, "total_tokens": 3520192}
{"current_steps": 3670, "total_steps": 11784, "loss": 0.0743, "lr": 1.7400645736989246e-06, "epoch": 0.31143923964697895, "percentage": 31.14, "elapsed_time": "0:09:19", "remaining_time": "0:20:37", "throughput": 6299.32, "total_tokens": 3524544}
{"current_steps": 3675, "total_steps": 11784, "loss": 0.0105, "lr": 1.7390676125125733e-06, "epoch": 0.31186354378818737, "percentage": 31.19, "elapsed_time": "0:09:19", "remaining_time": "0:20:35", "throughput": 6303.45, "total_tokens": 3528896}
{"current_steps": 3680, "total_steps": 11784, "loss": 0.0761, "lr": 1.7380690298801836e-06, "epoch": 0.3122878479293958, "percentage": 31.23, "elapsed_time": "0:09:20", "remaining_time": "0:20:33", "throughput": 6308.07, "total_tokens": 3533568}
{"current_steps": 3685, "total_steps": 11784, "loss": 0.0437, "lr": 1.7370688279925538e-06, "epoch": 0.3127121520706042, "percentage": 31.27, "elapsed_time": "0:09:20", "remaining_time": "0:20:31", "throughput": 6313.88, "total_tokens": 3539008}
{"current_steps": 3690, "total_steps": 11784, "loss": 0.0234, "lr": 1.736067009044034e-06, "epoch": 0.31313645621181263, "percentage": 31.31, "elapsed_time": "0:09:20", "remaining_time": "0:20:30", "throughput": 6319.69, "total_tokens": 3544448}
{"current_steps": 3695, "total_steps": 11784, "loss": 0.1307, "lr": 1.7350635752325222e-06, "epoch": 0.31356076035302105, "percentage": 31.36, "elapsed_time": "0:09:21", "remaining_time": "0:20:28", "throughput": 6324.42, "total_tokens": 3549184}
{"current_steps": 3700, "total_steps": 11784, "loss": 0.0346, "lr": 1.7340585287594603e-06, "epoch": 0.31398506449422947, "percentage": 31.4, "elapsed_time": "0:09:21", "remaining_time": "0:20:26", "throughput": 6329.51, "total_tokens": 3554176}
{"current_steps": 3705, "total_steps": 11784, "loss": 0.0626, "lr": 1.733051871829826e-06, "epoch": 0.3144093686354379, "percentage": 31.44, "elapsed_time": "0:09:21", "remaining_time": "0:20:25", "throughput": 6333.92, "total_tokens": 3558720}
{"current_steps": 3710, "total_steps": 11784, "loss": 0.0735, "lr": 1.7320436066521333e-06, "epoch": 0.3148336727766463, "percentage": 31.48, "elapsed_time": "0:09:22", "remaining_time": "0:20:23", "throughput": 6338.92, "total_tokens": 3563648}
{"current_steps": 3715, "total_steps": 11784, "loss": 0.0464, "lr": 1.7310337354384214e-06, "epoch": 0.31525797691785473, "percentage": 31.53, "elapsed_time": "0:09:22", "remaining_time": "0:20:21", "throughput": 6344.05, "total_tokens": 3568704}
{"current_steps": 3720, "total_steps": 11784, "loss": 0.0382, "lr": 1.7300222604042552e-06, "epoch": 0.31568228105906315, "percentage": 31.57, "elapsed_time": "0:09:22", "remaining_time": "0:20:20", "throughput": 6348.34, "total_tokens": 3573184}
{"current_steps": 3725, "total_steps": 11784, "loss": 0.0764, "lr": 1.7290091837687172e-06, "epoch": 0.3161065852002716, "percentage": 31.61, "elapsed_time": "0:09:23", "remaining_time": "0:20:18", "throughput": 6353.77, "total_tokens": 3578432}
{"current_steps": 3730, "total_steps": 11784, "loss": 0.0116, "lr": 1.7279945077544036e-06, "epoch": 0.31653088934148, "percentage": 31.65, "elapsed_time": "0:09:23", "remaining_time": "0:20:16", "throughput": 6357.97, "total_tokens": 3582848}
{"current_steps": 3735, "total_steps": 11784, "loss": 0.0319, "lr": 1.7269782345874203e-06, "epoch": 0.3169551934826884, "percentage": 31.7, "elapsed_time": "0:09:23", "remaining_time": "0:20:15", "throughput": 6363.0, "total_tokens": 3587840}
{"current_steps": 3740, "total_steps": 11784, "loss": 0.1165, "lr": 1.7259603664973766e-06, "epoch": 0.31737949762389683, "percentage": 31.74, "elapsed_time": "0:09:24", "remaining_time": "0:20:13", "throughput": 6367.58, "total_tokens": 3592576}
{"current_steps": 3745, "total_steps": 11784, "loss": 0.1014, "lr": 1.7249409057173806e-06, "epoch": 0.31780380176510525, "percentage": 31.78, "elapsed_time": "0:09:24", "remaining_time": "0:20:11", "throughput": 6372.3, "total_tokens": 3597376}
{"current_steps": 3750, "total_steps": 11784, "loss": 0.0935, "lr": 1.7239198544840354e-06, "epoch": 0.3182281059063136, "percentage": 31.82, "elapsed_time": "0:09:24", "remaining_time": "0:20:10", "throughput": 6376.34, "total_tokens": 3601728}
{"current_steps": 3755, "total_steps": 11784, "loss": 0.1359, "lr": 1.7228972150374332e-06, "epoch": 0.31865241004752204, "percentage": 31.87, "elapsed_time": "0:09:25", "remaining_time": "0:20:08", "throughput": 6381.13, "total_tokens": 3606592}
{"current_steps": 3760, "total_steps": 11784, "loss": 0.0588, "lr": 1.7218729896211504e-06, "epoch": 0.31907671418873046, "percentage": 31.91, "elapsed_time": "0:09:25", "remaining_time": "0:20:06", "throughput": 6385.75, "total_tokens": 3611328}
{"current_steps": 3765, "total_steps": 11784, "loss": 0.0536, "lr": 1.7208471804822425e-06, "epoch": 0.3195010183299389, "percentage": 31.95, "elapsed_time": "0:09:25", "remaining_time": "0:20:05", "throughput": 6390.3, "total_tokens": 3616000}
{"current_steps": 3770, "total_steps": 11784, "loss": 0.0302, "lr": 1.71981978987124e-06, "epoch": 0.3199253224711473, "percentage": 31.99, "elapsed_time": "0:09:26", "remaining_time": "0:20:03", "throughput": 6394.22, "total_tokens": 3620288}
{"current_steps": 3775, "total_steps": 11784, "loss": 0.0396, "lr": 1.7187908200421432e-06, "epoch": 0.3203496266123557, "percentage": 32.03, "elapsed_time": "0:09:26", "remaining_time": "0:20:01", "throughput": 6398.32, "total_tokens": 3624704}
{"current_steps": 3780, "total_steps": 11784, "loss": 0.0919, "lr": 1.717760273252417e-06, "epoch": 0.32077393075356414, "percentage": 32.08, "elapsed_time": "0:09:26", "remaining_time": "0:20:00", "throughput": 6401.84, "total_tokens": 3628736}
{"current_steps": 3785, "total_steps": 11784, "loss": 0.0607, "lr": 1.7167281517629854e-06, "epoch": 0.32119823489477256, "percentage": 32.12, "elapsed_time": "0:09:27", "remaining_time": "0:19:58", "throughput": 6406.71, "total_tokens": 3633664}
{"current_steps": 3790, "total_steps": 11784, "loss": 0.0758, "lr": 1.7156944578382277e-06, "epoch": 0.321622539035981, "percentage": 32.16, "elapsed_time": "0:09:27", "remaining_time": "0:19:56", "throughput": 6411.28, "total_tokens": 3638400}
{"current_steps": 3795, "total_steps": 11784, "loss": 0.0976, "lr": 1.7146591937459732e-06, "epoch": 0.3220468431771894, "percentage": 32.2, "elapsed_time": "0:09:27", "remaining_time": "0:19:55", "throughput": 6415.99, "total_tokens": 3643200}
{"current_steps": 3800, "total_steps": 11784, "loss": 0.1564, "lr": 1.713622361757495e-06, "epoch": 0.3224711473183978, "percentage": 32.25, "elapsed_time": "0:09:28", "remaining_time": "0:19:53", "throughput": 6420.2, "total_tokens": 3647680}
{"current_steps": 3805, "total_steps": 11784, "loss": 0.0291, "lr": 1.712583964147507e-06, "epoch": 0.32289545145960624, "percentage": 32.29, "elapsed_time": "0:09:28", "remaining_time": "0:19:52", "throughput": 6425.79, "total_tokens": 3653120}
{"current_steps": 3810, "total_steps": 11784, "loss": 0.1444, "lr": 1.7115440031941572e-06, "epoch": 0.32331975560081466, "percentage": 32.33, "elapsed_time": "0:09:28", "remaining_time": "0:19:50", "throughput": 6430.29, "total_tokens": 3657856}
{"current_steps": 3815, "total_steps": 11784, "loss": 0.0922, "lr": 1.7105024811790248e-06, "epoch": 0.3237440597420231, "percentage": 32.37, "elapsed_time": "0:09:29", "remaining_time": "0:19:48", "throughput": 6434.99, "total_tokens": 3662656}
{"current_steps": 3820, "total_steps": 11784, "loss": 0.0862, "lr": 1.7094594003871116e-06, "epoch": 0.3241683638832315, "percentage": 32.42, "elapsed_time": "0:09:29", "remaining_time": "0:19:47", "throughput": 6440.6, "total_tokens": 3668096}
{"current_steps": 3825, "total_steps": 11784, "loss": 0.0375, "lr": 1.7084147631068415e-06, "epoch": 0.3245926680244399, "percentage": 32.46, "elapsed_time": "0:09:29", "remaining_time": "0:19:45", "throughput": 6445.78, "total_tokens": 3673280}
{"current_steps": 3830, "total_steps": 11784, "loss": 0.084, "lr": 1.7073685716300517e-06, "epoch": 0.32501697216564834, "percentage": 32.5, "elapsed_time": "0:09:30", "remaining_time": "0:19:44", "throughput": 6449.99, "total_tokens": 3677824}
{"current_steps": 3835, "total_steps": 11784, "loss": 0.0866, "lr": 1.7063208282519894e-06, "epoch": 0.32544127630685676, "percentage": 32.54, "elapsed_time": "0:09:30", "remaining_time": "0:19:42", "throughput": 6454.64, "total_tokens": 3682624}
{"current_steps": 3840, "total_steps": 11784, "loss": 0.0973, "lr": 1.7052715352713074e-06, "epoch": 0.3258655804480652, "percentage": 32.59, "elapsed_time": "0:09:30", "remaining_time": "0:19:40", "throughput": 6459.09, "total_tokens": 3687296}
{"current_steps": 3845, "total_steps": 11784, "loss": 0.0854, "lr": 1.7042206949900568e-06, "epoch": 0.3262898845892736, "percentage": 32.63, "elapsed_time": "0:09:31", "remaining_time": "0:19:39", "throughput": 6464.14, "total_tokens": 3692352}
{"current_steps": 3850, "total_steps": 11784, "loss": 0.0305, "lr": 1.703168309713684e-06, "epoch": 0.326714188730482, "percentage": 32.67, "elapsed_time": "0:09:31", "remaining_time": "0:19:37", "throughput": 6469.24, "total_tokens": 3697472}
{"current_steps": 3855, "total_steps": 11784, "loss": 0.0659, "lr": 1.7021143817510262e-06, "epoch": 0.32713849287169044, "percentage": 32.71, "elapsed_time": "0:09:31", "remaining_time": "0:19:36", "throughput": 6474.23, "total_tokens": 3702528}
{"current_steps": 3860, "total_steps": 11784, "loss": 0.1094, "lr": 1.7010589134143025e-06, "epoch": 0.32756279701289887, "percentage": 32.76, "elapsed_time": "0:09:32", "remaining_time": "0:19:34", "throughput": 6477.65, "total_tokens": 3706560}
{"current_steps": 3865, "total_steps": 11784, "loss": 0.067, "lr": 1.7000019070191138e-06, "epoch": 0.3279871011541073, "percentage": 32.8, "elapsed_time": "0:09:32", "remaining_time": "0:19:33", "throughput": 6481.9, "total_tokens": 3711104}
{"current_steps": 3870, "total_steps": 11784, "loss": 0.0876, "lr": 1.698943364884434e-06, "epoch": 0.3284114052953157, "percentage": 32.84, "elapsed_time": "0:09:32", "remaining_time": "0:19:31", "throughput": 6486.2, "total_tokens": 3715712}
{"current_steps": 3875, "total_steps": 11784, "loss": 0.0276, "lr": 1.697883289332607e-06, "epoch": 0.3288357094365241, "percentage": 32.88, "elapsed_time": "0:09:33", "remaining_time": "0:19:29", "throughput": 6491.43, "total_tokens": 3720960}
{"current_steps": 3880, "total_steps": 11784, "loss": 0.0555, "lr": 1.6968216826893405e-06, "epoch": 0.3292600135777325, "percentage": 32.93, "elapsed_time": "0:09:33", "remaining_time": "0:19:28", "throughput": 6495.63, "total_tokens": 3725504}
{"current_steps": 3885, "total_steps": 11784, "loss": 0.0693, "lr": 1.6957585472837014e-06, "epoch": 0.3296843177189409, "percentage": 32.97, "elapsed_time": "0:09:33", "remaining_time": "0:19:26", "throughput": 6499.53, "total_tokens": 3729856}
{"current_steps": 3890, "total_steps": 11784, "loss": 0.1188, "lr": 1.6946938854481103e-06, "epoch": 0.33010862186014933, "percentage": 33.01, "elapsed_time": "0:09:34", "remaining_time": "0:19:25", "throughput": 6504.63, "total_tokens": 3735040}
{"current_steps": 3895, "total_steps": 11784, "loss": 0.0129, "lr": 1.6936276995183371e-06, "epoch": 0.33053292600135775, "percentage": 33.05, "elapsed_time": "0:09:34", "remaining_time": "0:19:23", "throughput": 6509.86, "total_tokens": 3740288}
{"current_steps": 3900, "total_steps": 11784, "loss": 0.0761, "lr": 1.6925599918334954e-06, "epoch": 0.33095723014256617, "percentage": 33.1, "elapsed_time": "0:09:34", "remaining_time": "0:19:22", "throughput": 6514.18, "total_tokens": 3744960}
{"current_steps": 3905, "total_steps": 11784, "loss": 0.0783, "lr": 1.6914907647360367e-06, "epoch": 0.3313815342837746, "percentage": 33.14, "elapsed_time": "0:09:35", "remaining_time": "0:19:20", "throughput": 6517.71, "total_tokens": 3749120}
{"current_steps": 3910, "total_steps": 11784, "loss": 0.0857, "lr": 1.6904200205717467e-06, "epoch": 0.331805838424983, "percentage": 33.18, "elapsed_time": "0:09:35", "remaining_time": "0:19:19", "throughput": 6522.31, "total_tokens": 3753984}
{"current_steps": 3915, "total_steps": 11784, "loss": 0.0364, "lr": 1.689347761689739e-06, "epoch": 0.33223014256619143, "percentage": 33.22, "elapsed_time": "0:09:35", "remaining_time": "0:19:17", "throughput": 6526.27, "total_tokens": 3758464}
{"current_steps": 3920, "total_steps": 11784, "loss": 0.0956, "lr": 1.6882739904424507e-06, "epoch": 0.33265444670739985, "percentage": 33.27, "elapsed_time": "0:09:36", "remaining_time": "0:19:15", "throughput": 6529.81, "total_tokens": 3762624}
{"current_steps": 3925, "total_steps": 11784, "loss": 0.1428, "lr": 1.6871987091856366e-06, "epoch": 0.3330787508486083, "percentage": 33.31, "elapsed_time": "0:09:36", "remaining_time": "0:19:14", "throughput": 6534.62, "total_tokens": 3767616}
{"current_steps": 3930, "total_steps": 11784, "loss": 0.0047, "lr": 1.6861219202783644e-06, "epoch": 0.3335030549898167, "percentage": 33.35, "elapsed_time": "0:09:36", "remaining_time": "0:19:12", "throughput": 6539.83, "total_tokens": 3772864}
{"current_steps": 3935, "total_steps": 11784, "loss": 0.0992, "lr": 1.6850436260830093e-06, "epoch": 0.3339273591310251, "percentage": 33.39, "elapsed_time": "0:09:37", "remaining_time": "0:19:11", "throughput": 6544.43, "total_tokens": 3777728}
{"current_steps": 3940, "total_steps": 11784, "loss": 0.0653, "lr": 1.683963828965249e-06, "epoch": 0.33435166327223353, "percentage": 33.44, "elapsed_time": "0:09:37", "remaining_time": "0:19:09", "throughput": 6549.45, "total_tokens": 3782912}
{"current_steps": 3945, "total_steps": 11784, "loss": 0.0656, "lr": 1.6828825312940592e-06, "epoch": 0.33477596741344195, "percentage": 33.48, "elapsed_time": "0:09:37", "remaining_time": "0:19:08", "throughput": 6554.55, "total_tokens": 3788160}
{"current_steps": 3950, "total_steps": 11784, "loss": 0.0815, "lr": 1.6817997354417066e-06, "epoch": 0.3352002715546504, "percentage": 33.52, "elapsed_time": "0:09:38", "remaining_time": "0:19:06", "throughput": 6558.28, "total_tokens": 3792448}
{"current_steps": 3955, "total_steps": 11784, "loss": 0.0654, "lr": 1.6807154437837453e-06, "epoch": 0.3356245756958588, "percentage": 33.56, "elapsed_time": "0:09:38", "remaining_time": "0:19:05", "throughput": 6562.92, "total_tokens": 3797376}
{"current_steps": 3960, "total_steps": 11784, "loss": 0.0956, "lr": 1.6796296586990108e-06, "epoch": 0.3360488798370672, "percentage": 33.6, "elapsed_time": "0:09:38", "remaining_time": "0:19:03", "throughput": 6567.89, "total_tokens": 3802496}
{"current_steps": 3965, "total_steps": 11784, "loss": 0.0604, "lr": 1.6785423825696156e-06, "epoch": 0.33647318397827564, "percentage": 33.65, "elapsed_time": "0:09:39", "remaining_time": "0:19:02", "throughput": 6571.77, "total_tokens": 3806912}
{"current_steps": 3970, "total_steps": 11784, "loss": 0.042, "lr": 1.6774536177809426e-06, "epoch": 0.33689748811948406, "percentage": 33.69, "elapsed_time": "0:09:39", "remaining_time": "0:19:00", "throughput": 6576.14, "total_tokens": 3811648}
{"current_steps": 3975, "total_steps": 11784, "loss": 0.0873, "lr": 1.6763633667216416e-06, "epoch": 0.3373217922606925, "percentage": 33.73, "elapsed_time": "0:09:39", "remaining_time": "0:18:59", "throughput": 6581.42, "total_tokens": 3817024}
{"current_steps": 3980, "total_steps": 11784, "loss": 0.0224, "lr": 1.6752716317836226e-06, "epoch": 0.3377460964019009, "percentage": 33.77, "elapsed_time": "0:09:40", "remaining_time": "0:18:57", "throughput": 6585.28, "total_tokens": 3821440}
{"current_steps": 3985, "total_steps": 11784, "loss": 0.0261, "lr": 1.6741784153620508e-06, "epoch": 0.3381704005431093, "percentage": 33.82, "elapsed_time": "0:09:40", "remaining_time": "0:18:56", "throughput": 6589.37, "total_tokens": 3825984}
{"current_steps": 3990, "total_steps": 11784, "loss": 0.057, "lr": 1.6730837198553422e-06, "epoch": 0.33859470468431774, "percentage": 33.86, "elapsed_time": "0:09:40", "remaining_time": "0:18:54", "throughput": 6594.28, "total_tokens": 3831104}
{"current_steps": 3995, "total_steps": 11784, "loss": 0.083, "lr": 1.6719875476651577e-06, "epoch": 0.33901900882552616, "percentage": 33.9, "elapsed_time": "0:09:41", "remaining_time": "0:18:53", "throughput": 6599.05, "total_tokens": 3836160}
{"current_steps": 4000, "total_steps": 11784, "loss": 0.099, "lr": 1.6708899011963978e-06, "epoch": 0.3394433129667346, "percentage": 33.94, "elapsed_time": "0:09:41", "remaining_time": "0:18:51", "throughput": 6602.97, "total_tokens": 3840640}
{"current_steps": 4005, "total_steps": 11784, "loss": 0.0456, "lr": 1.6697907828571966e-06, "epoch": 0.339867617107943, "percentage": 33.99, "elapsed_time": "0:09:41", "remaining_time": "0:18:50", "throughput": 6607.37, "total_tokens": 3845440}
{"current_steps": 4010, "total_steps": 11784, "loss": 0.1105, "lr": 1.6686901950589193e-06, "epoch": 0.3402919212491514, "percentage": 34.03, "elapsed_time": "0:09:42", "remaining_time": "0:18:48", "throughput": 6611.94, "total_tokens": 3850368}
{"current_steps": 4015, "total_steps": 11784, "loss": 0.0449, "lr": 1.6675881402161536e-06, "epoch": 0.3407162253903598, "percentage": 34.07, "elapsed_time": "0:09:42", "remaining_time": "0:18:47", "throughput": 6616.55, "total_tokens": 3855296}
{"current_steps": 4020, "total_steps": 11784, "loss": 0.073, "lr": 1.6664846207467054e-06, "epoch": 0.3411405295315682, "percentage": 34.11, "elapsed_time": "0:09:43", "remaining_time": "0:18:45", "throughput": 6620.28, "total_tokens": 3859648}
{"current_steps": 4025, "total_steps": 11784, "loss": 0.0364, "lr": 1.665379639071595e-06, "epoch": 0.3415648336727766, "percentage": 34.16, "elapsed_time": "0:09:43", "remaining_time": "0:18:44", "throughput": 6624.79, "total_tokens": 3864512}
{"current_steps": 4030, "total_steps": 11784, "loss": 0.0528, "lr": 1.6642731976150492e-06, "epoch": 0.34198913781398504, "percentage": 34.2, "elapsed_time": "0:09:43", "remaining_time": "0:18:43", "throughput": 6628.38, "total_tokens": 3868800}
{"current_steps": 4035, "total_steps": 11784, "loss": 0.059, "lr": 1.6631652988044995e-06, "epoch": 0.34241344195519346, "percentage": 34.24, "elapsed_time": "0:09:44", "remaining_time": "0:18:41", "throughput": 6632.83, "total_tokens": 3873664}
{"current_steps": 4040, "total_steps": 11784, "loss": 0.0991, "lr": 1.6620559450705728e-06, "epoch": 0.3428377460964019, "percentage": 34.28, "elapsed_time": "0:09:44", "remaining_time": "0:18:40", "throughput": 6637.25, "total_tokens": 3878528}
{"current_steps": 4045, "total_steps": 11784, "loss": 0.0806, "lr": 1.6609451388470885e-06, "epoch": 0.3432620502376103, "percentage": 34.33, "elapsed_time": "0:09:44", "remaining_time": "0:18:38", "throughput": 6641.32, "total_tokens": 3883136}
{"current_steps": 4050, "total_steps": 11784, "loss": 0.095, "lr": 1.6598328825710533e-06, "epoch": 0.3436863543788187, "percentage": 34.37, "elapsed_time": "0:09:45", "remaining_time": "0:18:37", "throughput": 6646.32, "total_tokens": 3888384}
{"current_steps": 4055, "total_steps": 11784, "loss": 0.0117, "lr": 1.6587191786826543e-06, "epoch": 0.34411065852002715, "percentage": 34.41, "elapsed_time": "0:09:45", "remaining_time": "0:18:35", "throughput": 6650.49, "total_tokens": 3893056}
{"current_steps": 4060, "total_steps": 11784, "loss": 0.0724, "lr": 1.6576040296252553e-06, "epoch": 0.34453496266123557, "percentage": 34.45, "elapsed_time": "0:09:45", "remaining_time": "0:18:34", "throughput": 6654.49, "total_tokens": 3897600}
{"current_steps": 4065, "total_steps": 11784, "loss": 0.1141, "lr": 1.65648743784539e-06, "epoch": 0.344959266802444, "percentage": 34.5, "elapsed_time": "0:09:46", "remaining_time": "0:18:32", "throughput": 6658.39, "total_tokens": 3902080}
{"current_steps": 4070, "total_steps": 11784, "loss": 0.061, "lr": 1.6553694057927573e-06, "epoch": 0.3453835709436524, "percentage": 34.54, "elapsed_time": "0:09:46", "remaining_time": "0:18:31", "throughput": 6662.75, "total_tokens": 3906880}
{"current_steps": 4075, "total_steps": 11784, "loss": 0.1306, "lr": 1.654249935920217e-06, "epoch": 0.3458078750848608, "percentage": 34.58, "elapsed_time": "0:09:46", "remaining_time": "0:18:29", "throughput": 6666.14, "total_tokens": 3911040}
{"current_steps": 4080, "total_steps": 11784, "loss": 0.0689, "lr": 1.6531290306837817e-06, "epoch": 0.34623217922606925, "percentage": 34.62, "elapsed_time": "0:09:47", "remaining_time": "0:18:28", "throughput": 6670.33, "total_tokens": 3915712}
{"current_steps": 4085, "total_steps": 11784, "loss": 0.0916, "lr": 1.6520066925426143e-06, "epoch": 0.34665648336727767, "percentage": 34.67, "elapsed_time": "0:09:47", "remaining_time": "0:18:27", "throughput": 6673.8, "total_tokens": 3919936}
{"current_steps": 4090, "total_steps": 11784, "loss": 0.1051, "lr": 1.650882923959021e-06, "epoch": 0.3470807875084861, "percentage": 34.71, "elapsed_time": "0:09:47", "remaining_time": "0:18:25", "throughput": 6677.81, "total_tokens": 3924480}
{"current_steps": 4095, "total_steps": 11784, "loss": 0.1395, "lr": 1.649757727398446e-06, "epoch": 0.3475050916496945, "percentage": 34.75, "elapsed_time": "0:09:48", "remaining_time": "0:18:24", "throughput": 6682.83, "total_tokens": 3929728}
{"current_steps": 4100, "total_steps": 11784, "loss": 0.0495, "lr": 1.6486311053294669e-06, "epoch": 0.34792939579090293, "percentage": 34.79, "elapsed_time": "0:09:48", "remaining_time": "0:18:22", "throughput": 6686.49, "total_tokens": 3934080}
{"current_steps": 4105, "total_steps": 11784, "loss": 0.0759, "lr": 1.6475030602237876e-06, "epoch": 0.34835369993211135, "percentage": 34.84, "elapsed_time": "0:09:48", "remaining_time": "0:18:21", "throughput": 6690.46, "total_tokens": 3938624}
{"current_steps": 4110, "total_steps": 11784, "loss": 0.0924, "lr": 1.646373594556236e-06, "epoch": 0.34877800407331977, "percentage": 34.88, "elapsed_time": "0:09:49", "remaining_time": "0:18:19", "throughput": 6696.16, "total_tokens": 3944448}
{"current_steps": 4115, "total_steps": 11784, "loss": 0.0257, "lr": 1.6452427108047542e-06, "epoch": 0.3492023082145282, "percentage": 34.92, "elapsed_time": "0:09:49", "remaining_time": "0:18:18", "throughput": 6700.36, "total_tokens": 3949184}
{"current_steps": 4120, "total_steps": 11784, "loss": 0.0649, "lr": 1.6441104114503977e-06, "epoch": 0.3496266123557366, "percentage": 34.96, "elapsed_time": "0:09:49", "remaining_time": "0:18:17", "throughput": 6704.21, "total_tokens": 3953664}
{"current_steps": 4125, "total_steps": 11784, "loss": 0.0585, "lr": 1.642976698977326e-06, "epoch": 0.35005091649694503, "percentage": 35.01, "elapsed_time": "0:09:50", "remaining_time": "0:18:15", "throughput": 6708.35, "total_tokens": 3958336}
{"current_steps": 4130, "total_steps": 11784, "loss": 0.0051, "lr": 1.6418415758727995e-06, "epoch": 0.35047522063815345, "percentage": 35.05, "elapsed_time": "0:09:50", "remaining_time": "0:18:14", "throughput": 6713.29, "total_tokens": 3963584}
{"current_steps": 4130, "total_steps": 11784, "eval_loss": 0.07100464403629303, "epoch": 0.35047522063815345, "percentage": 35.05, "elapsed_time": "0:10:06", "remaining_time": "0:18:43", "throughput": 6536.85, "total_tokens": 3963584}
{"current_steps": 4135, "total_steps": 11784, "loss": 0.0893, "lr": 1.6407050446271738e-06, "epoch": 0.35089952477936187, "percentage": 35.09, "elapsed_time": "0:10:37", "remaining_time": "0:19:38", "throughput": 6228.46, "total_tokens": 3968896}
{"current_steps": 4140, "total_steps": 11784, "loss": 0.1264, "lr": 1.6395671077338928e-06, "epoch": 0.3513238289205703, "percentage": 35.13, "elapsed_time": "0:10:37", "remaining_time": "0:19:37", "throughput": 6232.35, "total_tokens": 3973440}
{"current_steps": 4145, "total_steps": 11784, "loss": 0.0501, "lr": 1.6384277676894855e-06, "epoch": 0.35174813306177866, "percentage": 35.17, "elapsed_time": "0:10:37", "remaining_time": "0:19:35", "throughput": 6236.54, "total_tokens": 3978176}
{"current_steps": 4150, "total_steps": 11784, "loss": 0.0844, "lr": 1.6372870269935583e-06, "epoch": 0.3521724372029871, "percentage": 35.22, "elapsed_time": "0:10:38", "remaining_time": "0:19:34", "throughput": 6241.32, "total_tokens": 3983360}
{"current_steps": 4155, "total_steps": 11784, "loss": 0.0303, "lr": 1.6361448881487912e-06, "epoch": 0.3525967413441955, "percentage": 35.26, "elapsed_time": "0:10:38", "remaining_time": "0:19:32", "throughput": 6244.78, "total_tokens": 3987584}
{"current_steps": 4160, "total_steps": 11784, "loss": 0.0368, "lr": 1.6350013536609307e-06, "epoch": 0.3530210454854039, "percentage": 35.3, "elapsed_time": "0:10:38", "remaining_time": "0:19:30", "throughput": 6249.26, "total_tokens": 3992576}
{"current_steps": 4165, "total_steps": 11784, "loss": 0.0488, "lr": 1.6338564260387861e-06, "epoch": 0.35344534962661234, "percentage": 35.34, "elapsed_time": "0:10:39", "remaining_time": "0:19:29", "throughput": 6254.07, "total_tokens": 3997824}
{"current_steps": 4170, "total_steps": 11784, "loss": 0.1147, "lr": 1.6327101077942228e-06, "epoch": 0.35386965376782076, "percentage": 35.39, "elapsed_time": "0:10:39", "remaining_time": "0:19:27", "throughput": 6257.52, "total_tokens": 4002048}
{"current_steps": 4175, "total_steps": 11784, "loss": 0.0454, "lr": 1.631562401442157e-06, "epoch": 0.3542939579090292, "percentage": 35.43, "elapsed_time": "0:10:39", "remaining_time": "0:19:26", "throughput": 6261.5, "total_tokens": 4006656}
{"current_steps": 4180, "total_steps": 11784, "loss": 0.0978, "lr": 1.6304133095005505e-06, "epoch": 0.3547182620502376, "percentage": 35.47, "elapsed_time": "0:10:40", "remaining_time": "0:19:24", "throughput": 6265.25, "total_tokens": 4011136}
{"current_steps": 4185, "total_steps": 11784, "loss": 0.0658, "lr": 1.6292628344904048e-06, "epoch": 0.355142566191446, "percentage": 35.51, "elapsed_time": "0:10:40", "remaining_time": "0:19:23", "throughput": 6269.3, "total_tokens": 4015808}
{"current_steps": 4190, "total_steps": 11784, "loss": 0.0771, "lr": 1.628110978935756e-06, "epoch": 0.35556687033265444, "percentage": 35.56, "elapsed_time": "0:10:40", "remaining_time": "0:19:21", "throughput": 6273.36, "total_tokens": 4020480}
{"current_steps": 4195, "total_steps": 11784, "loss": 0.0722, "lr": 1.626957745363668e-06, "epoch": 0.35599117447386286, "percentage": 35.6, "elapsed_time": "0:10:41", "remaining_time": "0:19:19", "throughput": 6277.32, "total_tokens": 4025088}
{"current_steps": 4200, "total_steps": 11784, "loss": 0.0513, "lr": 1.6258031363042291e-06, "epoch": 0.3564154786150713, "percentage": 35.64, "elapsed_time": "0:10:41", "remaining_time": "0:19:18", "throughput": 6282.05, "total_tokens": 4030272}
{"current_steps": 4205, "total_steps": 11784, "loss": 0.0864, "lr": 1.624647154290545e-06, "epoch": 0.3568397827562797, "percentage": 35.68, "elapsed_time": "0:10:41", "remaining_time": "0:19:16", "throughput": 6286.25, "total_tokens": 4035072}
{"current_steps": 4210, "total_steps": 11784, "loss": 0.0615, "lr": 1.6234898018587336e-06, "epoch": 0.3572640868974881, "percentage": 35.73, "elapsed_time": "0:10:42", "remaining_time": "0:19:15", "throughput": 6289.91, "total_tokens": 4039488}
{"current_steps": 4215, "total_steps": 11784, "loss": 0.1352, "lr": 1.6223310815479186e-06, "epoch": 0.35768839103869654, "percentage": 35.77, "elapsed_time": "0:10:42", "remaining_time": "0:19:13", "throughput": 6294.39, "total_tokens": 4044480}
{"current_steps": 4220, "total_steps": 11784, "loss": 0.0714, "lr": 1.6211709959002255e-06, "epoch": 0.35811269517990496, "percentage": 35.81, "elapsed_time": "0:10:42", "remaining_time": "0:19:12", "throughput": 6297.92, "total_tokens": 4048768}
{"current_steps": 4225, "total_steps": 11784, "loss": 0.0638, "lr": 1.620009547460775e-06, "epoch": 0.3585369993211134, "percentage": 35.85, "elapsed_time": "0:10:43", "remaining_time": "0:19:10", "throughput": 6302.01, "total_tokens": 4053504}
{"current_steps": 4230, "total_steps": 11784, "loss": 0.0221, "lr": 1.6188467387776779e-06, "epoch": 0.3589613034623218, "percentage": 35.9, "elapsed_time": "0:10:43", "remaining_time": "0:19:09", "throughput": 6305.6, "total_tokens": 4057856}
{"current_steps": 4235, "total_steps": 11784, "loss": 0.0434, "lr": 1.6176825724020286e-06, "epoch": 0.3593856076035302, "percentage": 35.94, "elapsed_time": "0:10:43", "remaining_time": "0:19:07", "throughput": 6309.97, "total_tokens": 4062784}
{"current_steps": 4240, "total_steps": 11784, "loss": 0.0282, "lr": 1.6165170508879007e-06, "epoch": 0.35980991174473864, "percentage": 35.98, "elapsed_time": "0:10:44", "remaining_time": "0:19:06", "throughput": 6313.81, "total_tokens": 4067328}
{"current_steps": 4245, "total_steps": 11784, "loss": 0.0755, "lr": 1.6153501767923408e-06, "epoch": 0.36023421588594706, "percentage": 36.02, "elapsed_time": "0:10:44", "remaining_time": "0:19:04", "throughput": 6318.78, "total_tokens": 4072704}
{"current_steps": 4250, "total_steps": 11784, "loss": 0.1098, "lr": 1.6141819526753626e-06, "epoch": 0.3606585200271555, "percentage": 36.07, "elapsed_time": "0:10:44", "remaining_time": "0:19:03", "throughput": 6322.95, "total_tokens": 4077504}
{"current_steps": 4255, "total_steps": 11784, "loss": 0.1086, "lr": 1.613012381099942e-06, "epoch": 0.3610828241683639, "percentage": 36.11, "elapsed_time": "0:10:45", "remaining_time": "0:19:01", "throughput": 6327.04, "total_tokens": 4082240}
{"current_steps": 4260, "total_steps": 11784, "loss": 0.0658, "lr": 1.6118414646320111e-06, "epoch": 0.3615071283095723, "percentage": 36.15, "elapsed_time": "0:10:45", "remaining_time": "0:19:00", "throughput": 6330.14, "total_tokens": 4086272}
{"current_steps": 4265, "total_steps": 11784, "loss": 0.0744, "lr": 1.6106692058404518e-06, "epoch": 0.36193143245078074, "percentage": 36.19, "elapsed_time": "0:10:45", "remaining_time": "0:18:58", "throughput": 6334.05, "total_tokens": 4090880}
{"current_steps": 4270, "total_steps": 11784, "loss": 0.0715, "lr": 1.6094956072970924e-06, "epoch": 0.36235573659198916, "percentage": 36.24, "elapsed_time": "0:10:46", "remaining_time": "0:18:57", "throughput": 6338.01, "total_tokens": 4095552}
{"current_steps": 4275, "total_steps": 11784, "loss": 0.0807, "lr": 1.608320671576699e-06, "epoch": 0.36278004073319753, "percentage": 36.28, "elapsed_time": "0:10:46", "remaining_time": "0:18:55", "throughput": 6342.18, "total_tokens": 4100352}
{"current_steps": 4280, "total_steps": 11784, "loss": 0.052, "lr": 1.6071444012569723e-06, "epoch": 0.36320434487440595, "percentage": 36.32, "elapsed_time": "0:10:46", "remaining_time": "0:18:54", "throughput": 6345.74, "total_tokens": 4104704}
{"current_steps": 4285, "total_steps": 11784, "loss": 0.1166, "lr": 1.6059667989185405e-06, "epoch": 0.36362864901561437, "percentage": 36.36, "elapsed_time": "0:10:47", "remaining_time": "0:18:52", "throughput": 6349.69, "total_tokens": 4109376}
{"current_steps": 4290, "total_steps": 11784, "loss": 0.0883, "lr": 1.6047878671449544e-06, "epoch": 0.3640529531568228, "percentage": 36.41, "elapsed_time": "0:10:47", "remaining_time": "0:18:51", "throughput": 6354.27, "total_tokens": 4114496}
{"current_steps": 4295, "total_steps": 11784, "loss": 0.0369, "lr": 1.6036076085226812e-06, "epoch": 0.3644772572980312, "percentage": 36.45, "elapsed_time": "0:10:47", "remaining_time": "0:18:49", "throughput": 6358.72, "total_tokens": 4119552}
{"current_steps": 4300, "total_steps": 11784, "loss": 0.0301, "lr": 1.6024260256410995e-06, "epoch": 0.36490156143923963, "percentage": 36.49, "elapsed_time": "0:10:48", "remaining_time": "0:18:48", "throughput": 6362.87, "total_tokens": 4124352}
{"current_steps": 4305, "total_steps": 11784, "loss": 0.0234, "lr": 1.601243121092493e-06, "epoch": 0.36532586558044805, "percentage": 36.53, "elapsed_time": "0:10:48", "remaining_time": "0:18:46", "throughput": 6367.01, "total_tokens": 4129152}
{"current_steps": 4310, "total_steps": 11784, "loss": 0.0369, "lr": 1.6000588974720443e-06, "epoch": 0.36575016972165647, "percentage": 36.58, "elapsed_time": "0:10:48", "remaining_time": "0:18:45", "throughput": 6371.36, "total_tokens": 4134144}
{"current_steps": 4315, "total_steps": 11784, "loss": 0.1336, "lr": 1.5988733573778314e-06, "epoch": 0.3661744738628649, "percentage": 36.62, "elapsed_time": "0:10:49", "remaining_time": "0:18:43", "throughput": 6375.28, "total_tokens": 4138816}
{"current_steps": 4320, "total_steps": 11784, "loss": 0.1023, "lr": 1.597686503410819e-06, "epoch": 0.3665987780040733, "percentage": 36.66, "elapsed_time": "0:10:49", "remaining_time": "0:18:42", "throughput": 6379.48, "total_tokens": 4143680}
{"current_steps": 4325, "total_steps": 11784, "loss": 0.0953, "lr": 1.596498338174856e-06, "epoch": 0.36702308214528173, "percentage": 36.7, "elapsed_time": "0:10:49", "remaining_time": "0:18:40", "throughput": 6384.43, "total_tokens": 4149120}
{"current_steps": 4330, "total_steps": 11784, "loss": 0.0331, "lr": 1.595308864276666e-06, "epoch": 0.36744738628649015, "percentage": 36.74, "elapsed_time": "0:10:50", "remaining_time": "0:18:39", "throughput": 6389.16, "total_tokens": 4154432}
{"current_steps": 4335, "total_steps": 11784, "loss": 0.0485, "lr": 1.5941180843258452e-06, "epoch": 0.36787169042769857, "percentage": 36.79, "elapsed_time": "0:10:50", "remaining_time": "0:18:37", "throughput": 6393.43, "total_tokens": 4159360}
{"current_steps": 4340, "total_steps": 11784, "loss": 0.0196, "lr": 1.5929260009348551e-06, "epoch": 0.368295994568907, "percentage": 36.83, "elapsed_time": "0:10:50", "remaining_time": "0:18:36", "throughput": 6396.61, "total_tokens": 4163520}
{"current_steps": 4345, "total_steps": 11784, "loss": 0.1079, "lr": 1.5917326167190163e-06, "epoch": 0.3687202987101154, "percentage": 36.87, "elapsed_time": "0:10:51", "remaining_time": "0:18:34", "throughput": 6401.13, "total_tokens": 4168640}
{"current_steps": 4350, "total_steps": 11784, "loss": 0.1585, "lr": 1.5905379342965033e-06, "epoch": 0.36914460285132383, "percentage": 36.91, "elapsed_time": "0:10:51", "remaining_time": "0:18:33", "throughput": 6405.0, "total_tokens": 4173312}
{"current_steps": 4355, "total_steps": 11784, "loss": 0.1323, "lr": 1.589341956288339e-06, "epoch": 0.36956890699253225, "percentage": 36.96, "elapsed_time": "0:10:51", "remaining_time": "0:18:32", "throughput": 6408.47, "total_tokens": 4177664}
{"current_steps": 4360, "total_steps": 11784, "loss": 0.0261, "lr": 1.5881446853183888e-06, "epoch": 0.3699932111337407, "percentage": 37.0, "elapsed_time": "0:10:52", "remaining_time": "0:18:30", "throughput": 6411.9, "total_tokens": 4182016}
{"current_steps": 4365, "total_steps": 11784, "loss": 0.0039, "lr": 1.586946124013354e-06, "epoch": 0.3704175152749491, "percentage": 37.04, "elapsed_time": "0:10:52", "remaining_time": "0:18:29", "throughput": 6415.7, "total_tokens": 4186624}
{"current_steps": 4370, "total_steps": 11784, "loss": 0.0708, "lr": 1.585746275002768e-06, "epoch": 0.3708418194161575, "percentage": 37.08, "elapsed_time": "0:10:52", "remaining_time": "0:18:27", "throughput": 6420.4, "total_tokens": 4191936}
{"current_steps": 4375, "total_steps": 11784, "loss": 0.087, "lr": 1.5845451409189887e-06, "epoch": 0.37126612355736593, "percentage": 37.13, "elapsed_time": "0:10:53", "remaining_time": "0:18:26", "throughput": 6423.95, "total_tokens": 4196352}
{"current_steps": 4380, "total_steps": 11784, "loss": 0.0648, "lr": 1.5833427243971927e-06, "epoch": 0.37169042769857435, "percentage": 37.17, "elapsed_time": "0:10:53", "remaining_time": "0:18:24", "throughput": 6427.73, "total_tokens": 4200960}
{"current_steps": 4385, "total_steps": 11784, "loss": 0.0723, "lr": 1.582139028075371e-06, "epoch": 0.3721147318397828, "percentage": 37.21, "elapsed_time": "0:10:53", "remaining_time": "0:18:23", "throughput": 6432.33, "total_tokens": 4206208}
{"current_steps": 4390, "total_steps": 11784, "loss": 0.0497, "lr": 1.580934054594322e-06, "epoch": 0.3725390359809912, "percentage": 37.25, "elapsed_time": "0:10:54", "remaining_time": "0:18:21", "throughput": 6435.95, "total_tokens": 4210688}
{"current_steps": 4395, "total_steps": 11784, "loss": 0.0667, "lr": 1.5797278065976463e-06, "epoch": 0.3729633401221996, "percentage": 37.3, "elapsed_time": "0:10:54", "remaining_time": "0:18:20", "throughput": 6439.9, "total_tokens": 4215424}
{"current_steps": 4400, "total_steps": 11784, "loss": 0.0108, "lr": 1.5785202867317407e-06, "epoch": 0.37338764426340804, "percentage": 37.34, "elapsed_time": "0:10:54", "remaining_time": "0:18:19", "throughput": 6443.9, "total_tokens": 4220160}
{"current_steps": 4405, "total_steps": 11784, "loss": 0.1083, "lr": 1.5773114976457915e-06, "epoch": 0.37381194840461646, "percentage": 37.38, "elapsed_time": "0:10:55", "remaining_time": "0:18:17", "throughput": 6447.78, "total_tokens": 4224832}
{"current_steps": 4410, "total_steps": 11784, "loss": 0.0833, "lr": 1.576101441991771e-06, "epoch": 0.3742362525458248, "percentage": 37.42, "elapsed_time": "0:10:55", "remaining_time": "0:18:16", "throughput": 6452.89, "total_tokens": 4230464}
{"current_steps": 4415, "total_steps": 11784, "loss": 0.0739, "lr": 1.574890122424429e-06, "epoch": 0.37466055668703324, "percentage": 37.47, "elapsed_time": "0:10:55", "remaining_time": "0:18:14", "throughput": 6456.34, "total_tokens": 4234816}
{"current_steps": 4420, "total_steps": 11784, "loss": 0.1099, "lr": 1.573677541601289e-06, "epoch": 0.37508486082824166, "percentage": 37.51, "elapsed_time": "0:10:56", "remaining_time": "0:18:13", "throughput": 6460.02, "total_tokens": 4239424}
{"current_steps": 4425, "total_steps": 11784, "loss": 0.0576, "lr": 1.5724637021826409e-06, "epoch": 0.3755091649694501, "percentage": 37.55, "elapsed_time": "0:10:56", "remaining_time": "0:18:11", "throughput": 6463.92, "total_tokens": 4244160}
{"current_steps": 4430, "total_steps": 11784, "loss": 0.0613, "lr": 1.5712486068315367e-06, "epoch": 0.3759334691106585, "percentage": 37.59, "elapsed_time": "0:10:56", "remaining_time": "0:18:10", "throughput": 6467.07, "total_tokens": 4248320}
{"current_steps": 4435, "total_steps": 11784, "loss": 0.0184, "lr": 1.5700322582137826e-06, "epoch": 0.3763577732518669, "percentage": 37.64, "elapsed_time": "0:10:57", "remaining_time": "0:18:09", "throughput": 6470.49, "total_tokens": 4252672}
{"current_steps": 4440, "total_steps": 11784, "loss": 0.0768, "lr": 1.5688146589979358e-06, "epoch": 0.37678207739307534, "percentage": 37.68, "elapsed_time": "0:10:57", "remaining_time": "0:18:07", "throughput": 6474.21, "total_tokens": 4257280}
{"current_steps": 4445, "total_steps": 11784, "loss": 0.0366, "lr": 1.5675958118552962e-06, "epoch": 0.37720638153428376, "percentage": 37.72, "elapsed_time": "0:10:57", "remaining_time": "0:18:06", "throughput": 6478.84, "total_tokens": 4262592}
{"current_steps": 4450, "total_steps": 11784, "loss": 0.0796, "lr": 1.5663757194599013e-06, "epoch": 0.3776306856754922, "percentage": 37.76, "elapsed_time": "0:10:58", "remaining_time": "0:18:04", "throughput": 6483.36, "total_tokens": 4267840}
{"current_steps": 4455, "total_steps": 11784, "loss": 0.0535, "lr": 1.5651543844885216e-06, "epoch": 0.3780549898167006, "percentage": 37.81, "elapsed_time": "0:10:58", "remaining_time": "0:18:03", "throughput": 6487.22, "total_tokens": 4272576}
{"current_steps": 4460, "total_steps": 11784, "loss": 0.0441, "lr": 1.5639318096206533e-06, "epoch": 0.378479293957909, "percentage": 37.85, "elapsed_time": "0:10:58", "remaining_time": "0:18:02", "throughput": 6491.45, "total_tokens": 4277568}
{"current_steps": 4465, "total_steps": 11784, "loss": 0.0889, "lr": 1.562707997538512e-06, "epoch": 0.37890359809911744, "percentage": 37.89, "elapsed_time": "0:10:59", "remaining_time": "0:18:00", "throughput": 6496.08, "total_tokens": 4282880}
{"current_steps": 4470, "total_steps": 11784, "loss": 0.087, "lr": 1.5614829509270288e-06, "epoch": 0.37932790224032586, "percentage": 37.93, "elapsed_time": "0:10:59", "remaining_time": "0:17:59", "throughput": 6499.49, "total_tokens": 4287296}
{"current_steps": 4475, "total_steps": 11784, "loss": 0.0615, "lr": 1.5602566724738426e-06, "epoch": 0.3797522063815343, "percentage": 37.98, "elapsed_time": "0:10:59", "remaining_time": "0:17:57", "throughput": 6502.94, "total_tokens": 4291712}
{"current_steps": 4480, "total_steps": 11784, "loss": 0.0883, "lr": 1.5590291648692952e-06, "epoch": 0.3801765105227427, "percentage": 38.02, "elapsed_time": "0:11:00", "remaining_time": "0:17:56", "throughput": 6507.61, "total_tokens": 4297088}
{"current_steps": 4485, "total_steps": 11784, "loss": 0.0393, "lr": 1.5578004308064245e-06, "epoch": 0.3806008146639511, "percentage": 38.06, "elapsed_time": "0:11:00", "remaining_time": "0:17:55", "throughput": 6512.72, "total_tokens": 4302784}
{"current_steps": 4490, "total_steps": 11784, "loss": 0.0433, "lr": 1.55657047298096e-06, "epoch": 0.38102511880515955, "percentage": 38.1, "elapsed_time": "0:11:01", "remaining_time": "0:17:53", "throughput": 6516.69, "total_tokens": 4307584}
{"current_steps": 4495, "total_steps": 11784, "loss": 0.0148, "lr": 1.5553392940913148e-06, "epoch": 0.38144942294636797, "percentage": 38.14, "elapsed_time": "0:11:01", "remaining_time": "0:17:52", "throughput": 6520.24, "total_tokens": 4312064}
{"current_steps": 4500, "total_steps": 11784, "loss": 0.0059, "lr": 1.554106896838582e-06, "epoch": 0.3818737270875764, "percentage": 38.19, "elapsed_time": "0:11:01", "remaining_time": "0:17:51", "throughput": 6523.94, "total_tokens": 4316672}
{"current_steps": 4505, "total_steps": 11784, "loss": 0.0332, "lr": 1.5528732839265272e-06, "epoch": 0.3822980312287848, "percentage": 38.23, "elapsed_time": "0:11:01", "remaining_time": "0:17:49", "throughput": 6527.39, "total_tokens": 4321088}
{"current_steps": 4510, "total_steps": 11784, "loss": 0.0341, "lr": 1.5516384580615832e-06, "epoch": 0.3827223353699932, "percentage": 38.27, "elapsed_time": "0:11:02", "remaining_time": "0:17:48", "throughput": 6531.75, "total_tokens": 4326208}
{"current_steps": 4515, "total_steps": 11784, "loss": 0.0553, "lr": 1.5504024219528437e-06, "epoch": 0.38314663951120165, "percentage": 38.31, "elapsed_time": "0:11:02", "remaining_time": "0:17:46", "throughput": 6535.68, "total_tokens": 4331008}
{"current_steps": 4520, "total_steps": 11784, "loss": 0.019, "lr": 1.5491651783120578e-06, "epoch": 0.38357094365241007, "percentage": 38.36, "elapsed_time": "0:11:03", "remaining_time": "0:17:45", "throughput": 6539.79, "total_tokens": 4335936}
{"current_steps": 4525, "total_steps": 11784, "loss": 0.0442, "lr": 1.5479267298536238e-06, "epoch": 0.3839952477936185, "percentage": 38.4, "elapsed_time": "0:11:03", "remaining_time": "0:17:44", "throughput": 6543.53, "total_tokens": 4340608}
{"current_steps": 4530, "total_steps": 11784, "loss": 0.0841, "lr": 1.5466870792945828e-06, "epoch": 0.3844195519348269, "percentage": 38.44, "elapsed_time": "0:11:03", "remaining_time": "0:17:42", "throughput": 6547.38, "total_tokens": 4345344}
{"current_steps": 4535, "total_steps": 11784, "loss": 0.1063, "lr": 1.545446229354614e-06, "epoch": 0.38484385607603533, "percentage": 38.48, "elapsed_time": "0:11:04", "remaining_time": "0:17:41", "throughput": 6553.27, "total_tokens": 4351680}
{"current_steps": 4540, "total_steps": 11784, "loss": 0.12, "lr": 1.5442041827560272e-06, "epoch": 0.3852681602172437, "percentage": 38.53, "elapsed_time": "0:11:04", "remaining_time": "0:17:40", "throughput": 6556.57, "total_tokens": 4356032}
{"current_steps": 4545, "total_steps": 11784, "loss": 0.0567, "lr": 1.542960942223758e-06, "epoch": 0.3856924643584521, "percentage": 38.57, "elapsed_time": "0:11:04", "remaining_time": "0:17:38", "throughput": 6560.15, "total_tokens": 4360576}
{"current_steps": 4550, "total_steps": 11784, "loss": 0.1224, "lr": 1.541716510485361e-06, "epoch": 0.38611676849966053, "percentage": 38.61, "elapsed_time": "0:11:05", "remaining_time": "0:17:37", "throughput": 6564.09, "total_tokens": 4365376}
{"current_steps": 4555, "total_steps": 11784, "loss": 0.015, "lr": 1.5404708902710048e-06, "epoch": 0.38654107264086895, "percentage": 38.65, "elapsed_time": "0:11:05", "remaining_time": "0:17:35", "throughput": 6568.25, "total_tokens": 4370368}
{"current_steps": 4560, "total_steps": 11784, "loss": 0.0918, "lr": 1.5392240843134648e-06, "epoch": 0.3869653767820774, "percentage": 38.7, "elapsed_time": "0:11:05", "remaining_time": "0:17:34", "throughput": 6572.56, "total_tokens": 4375488}
{"current_steps": 4565, "total_steps": 11784, "loss": 0.1303, "lr": 1.5379760953481178e-06, "epoch": 0.3873896809232858, "percentage": 38.74, "elapsed_time": "0:11:06", "remaining_time": "0:17:33", "throughput": 6576.58, "total_tokens": 4380352}
{"current_steps": 4570, "total_steps": 11784, "loss": 0.0735, "lr": 1.5367269261129367e-06, "epoch": 0.3878139850644942, "percentage": 38.78, "elapsed_time": "0:11:06", "remaining_time": "0:17:31", "throughput": 6581.12, "total_tokens": 4385664}
{"current_steps": 4575, "total_steps": 11784, "loss": 0.1257, "lr": 1.5354765793484831e-06, "epoch": 0.38823828920570264, "percentage": 38.82, "elapsed_time": "0:11:06", "remaining_time": "0:17:30", "throughput": 6585.08, "total_tokens": 4390528}
{"current_steps": 4580, "total_steps": 11784, "loss": 0.0082, "lr": 1.5342250577979023e-06, "epoch": 0.38866259334691106, "percentage": 38.87, "elapsed_time": "0:11:07", "remaining_time": "0:17:29", "throughput": 6588.71, "total_tokens": 4395136}
{"current_steps": 4585, "total_steps": 11784, "loss": 0.0835, "lr": 1.532972364206917e-06, "epoch": 0.3890868974881195, "percentage": 38.91, "elapsed_time": "0:11:07", "remaining_time": "0:17:27", "throughput": 6593.03, "total_tokens": 4400320}
{"current_steps": 4590, "total_steps": 11784, "loss": 0.0612, "lr": 1.5317185013238209e-06, "epoch": 0.3895112016293279, "percentage": 38.95, "elapsed_time": "0:11:07", "remaining_time": "0:17:26", "throughput": 6596.81, "total_tokens": 4405056}
{"current_steps": 4595, "total_steps": 11784, "loss": 0.0862, "lr": 1.5304634718994738e-06, "epoch": 0.3899355057705363, "percentage": 38.99, "elapsed_time": "0:11:08", "remaining_time": "0:17:25", "throughput": 6601.62, "total_tokens": 4410624}
{"current_steps": 4600, "total_steps": 11784, "loss": 0.0614, "lr": 1.5292072786872938e-06, "epoch": 0.39035980991174474, "percentage": 39.04, "elapsed_time": "0:11:08", "remaining_time": "0:17:23", "throughput": 6605.5, "total_tokens": 4415424}
{"current_steps": 4605, "total_steps": 11784, "loss": 0.0369, "lr": 1.527949924443253e-06, "epoch": 0.39078411405295316, "percentage": 39.08, "elapsed_time": "0:11:08", "remaining_time": "0:17:22", "throughput": 6609.35, "total_tokens": 4420224}
{"current_steps": 4610, "total_steps": 11784, "loss": 0.0958, "lr": 1.52669141192587e-06, "epoch": 0.3912084181941616, "percentage": 39.12, "elapsed_time": "0:11:09", "remaining_time": "0:17:21", "throughput": 6613.05, "total_tokens": 4424896}
{"current_steps": 4615, "total_steps": 11784, "loss": 0.0946, "lr": 1.5254317438962052e-06, "epoch": 0.39163272233537, "percentage": 39.16, "elapsed_time": "0:11:09", "remaining_time": "0:17:19", "throughput": 6616.37, "total_tokens": 4429312}
{"current_steps": 4620, "total_steps": 11784, "loss": 0.1145, "lr": 1.5241709231178539e-06, "epoch": 0.3920570264765784, "percentage": 39.21, "elapsed_time": "0:11:09", "remaining_time": "0:17:18", "throughput": 6619.97, "total_tokens": 4433920}
{"current_steps": 4625, "total_steps": 11784, "loss": 0.0557, "lr": 1.5229089523569405e-06, "epoch": 0.39248133061778684, "percentage": 39.25, "elapsed_time": "0:11:10", "remaining_time": "0:17:17", "throughput": 6623.45, "total_tokens": 4438464}
{"current_steps": 4630, "total_steps": 11784, "loss": 0.0481, "lr": 1.5216458343821122e-06, "epoch": 0.39290563475899526, "percentage": 39.29, "elapsed_time": "0:11:10", "remaining_time": "0:17:15", "throughput": 6627.68, "total_tokens": 4443584}
{"current_steps": 4635, "total_steps": 11784, "loss": 0.0451, "lr": 1.5203815719645328e-06, "epoch": 0.3933299389002037, "percentage": 39.33, "elapsed_time": "0:11:10", "remaining_time": "0:17:14", "throughput": 6632.27, "total_tokens": 4448960}
{"current_steps": 4640, "total_steps": 11784, "loss": 0.0307, "lr": 1.5191161678778773e-06, "epoch": 0.3937542430414121, "percentage": 39.38, "elapsed_time": "0:11:11", "remaining_time": "0:17:13", "throughput": 6635.7, "total_tokens": 4453504}
{"current_steps": 4645, "total_steps": 11784, "loss": 0.108, "lr": 1.5178496248983251e-06, "epoch": 0.3941785471826205, "percentage": 39.42, "elapsed_time": "0:11:11", "remaining_time": "0:17:12", "throughput": 6639.18, "total_tokens": 4458048}
{"current_steps": 4650, "total_steps": 11784, "loss": 0.0384, "lr": 1.5165819458045554e-06, "epoch": 0.39460285132382894, "percentage": 39.46, "elapsed_time": "0:11:11", "remaining_time": "0:17:10", "throughput": 6643.35, "total_tokens": 4463168}
{"current_steps": 4655, "total_steps": 11784, "loss": 0.1386, "lr": 1.5153131333777377e-06, "epoch": 0.39502715546503736, "percentage": 39.5, "elapsed_time": "0:11:12", "remaining_time": "0:17:09", "throughput": 6646.58, "total_tokens": 4467520}
{"current_steps": 4660, "total_steps": 11784, "loss": 0.0864, "lr": 1.51404319040153e-06, "epoch": 0.3954514596062458, "percentage": 39.55, "elapsed_time": "0:11:12", "remaining_time": "0:17:08", "throughput": 6651.18, "total_tokens": 4472960}
{"current_steps": 4665, "total_steps": 11784, "loss": 0.058, "lr": 1.5127721196620697e-06, "epoch": 0.3958757637474542, "percentage": 39.59, "elapsed_time": "0:11:12", "remaining_time": "0:17:06", "throughput": 6654.43, "total_tokens": 4477312}
{"current_steps": 4670, "total_steps": 11784, "loss": 0.0255, "lr": 1.5114999239479685e-06, "epoch": 0.39630006788866257, "percentage": 39.63, "elapsed_time": "0:11:13", "remaining_time": "0:17:05", "throughput": 6658.66, "total_tokens": 4482432}
{"current_steps": 4675, "total_steps": 11784, "loss": 0.0754, "lr": 1.5102266060503063e-06, "epoch": 0.396724372029871, "percentage": 39.67, "elapsed_time": "0:11:13", "remaining_time": "0:17:04", "throughput": 6661.48, "total_tokens": 4486464}
{"current_steps": 4680, "total_steps": 11784, "loss": 0.104, "lr": 1.508952168762624e-06, "epoch": 0.3971486761710794, "percentage": 39.71, "elapsed_time": "0:11:13", "remaining_time": "0:17:02", "throughput": 6665.57, "total_tokens": 4491520}
{"current_steps": 4685, "total_steps": 11784, "loss": 0.0473, "lr": 1.5076766148809209e-06, "epoch": 0.3975729803122878, "percentage": 39.76, "elapsed_time": "0:11:14", "remaining_time": "0:17:01", "throughput": 6669.27, "total_tokens": 4496256}
{"current_steps": 4690, "total_steps": 11784, "loss": 0.0532, "lr": 1.506399947203643e-06, "epoch": 0.39799728445349625, "percentage": 39.8, "elapsed_time": "0:11:14", "remaining_time": "0:17:00", "throughput": 6672.23, "total_tokens": 4500416}
{"current_steps": 4695, "total_steps": 11784, "loss": 0.052, "lr": 1.5051221685316815e-06, "epoch": 0.39842158859470467, "percentage": 39.84, "elapsed_time": "0:11:14", "remaining_time": "0:16:58", "throughput": 6676.48, "total_tokens": 4505536}
{"current_steps": 4700, "total_steps": 11784, "loss": 0.1351, "lr": 1.5038432816683652e-06, "epoch": 0.3988458927359131, "percentage": 39.88, "elapsed_time": "0:11:15", "remaining_time": "0:16:57", "throughput": 6680.36, "total_tokens": 4510400}
{"current_steps": 4705, "total_steps": 11784, "loss": 0.0894, "lr": 1.5025632894194532e-06, "epoch": 0.3992701968771215, "percentage": 39.93, "elapsed_time": "0:11:15", "remaining_time": "0:16:56", "throughput": 6685.05, "total_tokens": 4515904}
{"current_steps": 4710, "total_steps": 11784, "loss": 0.0939, "lr": 1.5012821945931303e-06, "epoch": 0.39969450101832993, "percentage": 39.97, "elapsed_time": "0:11:15", "remaining_time": "0:16:55", "throughput": 6688.51, "total_tokens": 4520448}
{"current_steps": 4715, "total_steps": 11784, "loss": 0.0654, "lr": 1.5e-06, "epoch": 0.40011880515953835, "percentage": 40.01, "elapsed_time": "0:11:16", "remaining_time": "0:16:53", "throughput": 6693.01, "total_tokens": 4525824}
{"current_steps": 4720, "total_steps": 11784, "loss": 0.0782, "lr": 1.498716708453079e-06, "epoch": 0.40054310930074677, "percentage": 40.05, "elapsed_time": "0:11:16", "remaining_time": "0:16:52", "throughput": 6696.39, "total_tokens": 4530304}
{"current_steps": 4720, "total_steps": 11784, "eval_loss": 0.055105432868003845, "epoch": 0.40054310930074677, "percentage": 40.05, "elapsed_time": "0:11:32", "remaining_time": "0:17:16", "throughput": 6543.6, "total_tokens": 4530304}
{"current_steps": 4725, "total_steps": 11784, "loss": 0.1067, "lr": 1.4974323227677903e-06, "epoch": 0.4009674134419552, "percentage": 40.1, "elapsed_time": "0:12:09", "remaining_time": "0:18:10", "throughput": 6213.75, "total_tokens": 4534720}
{"current_steps": 4730, "total_steps": 11784, "loss": 0.1018, "lr": 1.4961468457619575e-06, "epoch": 0.4013917175831636, "percentage": 40.14, "elapsed_time": "0:12:10", "remaining_time": "0:18:08", "throughput": 6217.49, "total_tokens": 4539520}
{"current_steps": 4735, "total_steps": 11784, "loss": 0.0083, "lr": 1.4948602802557982e-06, "epoch": 0.40181602172437203, "percentage": 40.18, "elapsed_time": "0:12:10", "remaining_time": "0:18:07", "throughput": 6221.36, "total_tokens": 4544448}
{"current_steps": 4740, "total_steps": 11784, "loss": 0.0448, "lr": 1.4935726290719177e-06, "epoch": 0.40224032586558045, "percentage": 40.22, "elapsed_time": "0:12:10", "remaining_time": "0:18:06", "throughput": 6225.5, "total_tokens": 4549632}
{"current_steps": 4745, "total_steps": 11784, "loss": 0.0697, "lr": 1.492283895035305e-06, "epoch": 0.40266463000678887, "percentage": 40.27, "elapsed_time": "0:12:11", "remaining_time": "0:18:04", "throughput": 6229.38, "total_tokens": 4554560}
{"current_steps": 4750, "total_steps": 11784, "loss": 0.0605, "lr": 1.490994080973322e-06, "epoch": 0.4030889341479973, "percentage": 40.31, "elapsed_time": "0:12:11", "remaining_time": "0:18:03", "throughput": 6232.88, "total_tokens": 4559168}
{"current_steps": 4755, "total_steps": 11784, "loss": 0.0556, "lr": 1.4897031897157025e-06, "epoch": 0.4035132382892057, "percentage": 40.35, "elapsed_time": "0:12:11", "remaining_time": "0:18:01", "throughput": 6236.56, "total_tokens": 4563968}
{"current_steps": 4760, "total_steps": 11784, "loss": 0.0479, "lr": 1.4884112240945425e-06, "epoch": 0.40393754243041413, "percentage": 40.39, "elapsed_time": "0:12:12", "remaining_time": "0:18:00", "throughput": 6241.0, "total_tokens": 4569408}
{"current_steps": 4765, "total_steps": 11784, "loss": 0.0856, "lr": 1.4871181869442952e-06, "epoch": 0.40436184657162255, "percentage": 40.44, "elapsed_time": "0:12:12", "remaining_time": "0:17:58", "throughput": 6244.24, "total_tokens": 4573824}
{"current_steps": 4770, "total_steps": 11784, "loss": 0.126, "lr": 1.485824081101764e-06, "epoch": 0.40478615071283097, "percentage": 40.48, "elapsed_time": "0:12:12", "remaining_time": "0:17:57", "throughput": 6247.65, "total_tokens": 4578368}
{"current_steps": 4775, "total_steps": 11784, "loss": 0.0938, "lr": 1.4845289094060984e-06, "epoch": 0.4052104548540394, "percentage": 40.52, "elapsed_time": "0:12:13", "remaining_time": "0:17:56", "throughput": 6251.21, "total_tokens": 4583040}
{"current_steps": 4780, "total_steps": 11784, "loss": 0.1106, "lr": 1.4832326746987846e-06, "epoch": 0.4056347589952478, "percentage": 40.56, "elapsed_time": "0:12:13", "remaining_time": "0:17:54", "throughput": 6255.06, "total_tokens": 4587968}
{"current_steps": 4785, "total_steps": 11784, "loss": 0.1431, "lr": 1.4819353798236424e-06, "epoch": 0.40605906313645623, "percentage": 40.61, "elapsed_time": "0:12:13", "remaining_time": "0:17:53", "throughput": 6259.28, "total_tokens": 4593216}
{"current_steps": 4790, "total_steps": 11784, "loss": 0.0959, "lr": 1.4806370276268163e-06, "epoch": 0.40648336727766465, "percentage": 40.65, "elapsed_time": "0:12:14", "remaining_time": "0:17:51", "throughput": 6262.74, "total_tokens": 4597824}
{"current_steps": 4795, "total_steps": 11784, "loss": 0.0695, "lr": 1.4793376209567714e-06, "epoch": 0.4069076714188731, "percentage": 40.69, "elapsed_time": "0:12:14", "remaining_time": "0:17:50", "throughput": 6266.73, "total_tokens": 4602880}
{"current_steps": 4800, "total_steps": 11784, "loss": 0.0287, "lr": 1.4780371626642858e-06, "epoch": 0.4073319755600815, "percentage": 40.73, "elapsed_time": "0:12:14", "remaining_time": "0:17:49", "throughput": 6270.53, "total_tokens": 4607744}
{"current_steps": 4805, "total_steps": 11784, "loss": 0.1188, "lr": 1.4767356556024448e-06, "epoch": 0.40775627970128986, "percentage": 40.78, "elapsed_time": "0:12:15", "remaining_time": "0:17:47", "throughput": 6273.86, "total_tokens": 4612224}
{"current_steps": 4810, "total_steps": 11784, "loss": 0.0525, "lr": 1.4754331026266344e-06, "epoch": 0.4081805838424983, "percentage": 40.82, "elapsed_time": "0:12:15", "remaining_time": "0:17:46", "throughput": 6277.17, "total_tokens": 4616704}
{"current_steps": 4815, "total_steps": 11784, "loss": 0.0684, "lr": 1.474129506594536e-06, "epoch": 0.4086048879837067, "percentage": 40.86, "elapsed_time": "0:12:15", "remaining_time": "0:17:44", "throughput": 6280.93, "total_tokens": 4621568}
{"current_steps": 4820, "total_steps": 11784, "loss": 0.0427, "lr": 1.472824870366118e-06, "epoch": 0.4090291921249151, "percentage": 40.9, "elapsed_time": "0:12:16", "remaining_time": "0:17:43", "throughput": 6284.41, "total_tokens": 4626176}
{"current_steps": 4825, "total_steps": 11784, "loss": 0.0541, "lr": 1.4715191968036324e-06, "epoch": 0.40945349626612354, "percentage": 40.95, "elapsed_time": "0:12:16", "remaining_time": "0:17:42", "throughput": 6287.39, "total_tokens": 4630400}
{"current_steps": 4830, "total_steps": 11784, "loss": 0.0376, "lr": 1.4702124887716058e-06, "epoch": 0.40987780040733196, "percentage": 40.99, "elapsed_time": "0:12:16", "remaining_time": "0:17:40", "throughput": 6290.45, "total_tokens": 4634688}
{"current_steps": 4835, "total_steps": 11784, "loss": 0.0444, "lr": 1.4689047491368354e-06, "epoch": 0.4103021045485404, "percentage": 41.03, "elapsed_time": "0:12:17", "remaining_time": "0:17:39", "throughput": 6293.68, "total_tokens": 4639104}
{"current_steps": 4840, "total_steps": 11784, "loss": 0.0833, "lr": 1.4675959807683808e-06, "epoch": 0.4107264086897488, "percentage": 41.07, "elapsed_time": "0:12:17", "remaining_time": "0:17:37", "throughput": 6296.65, "total_tokens": 4643328}
{"current_steps": 4845, "total_steps": 11784, "loss": 0.0481, "lr": 1.4662861865375588e-06, "epoch": 0.4111507128309572, "percentage": 41.12, "elapsed_time": "0:12:17", "remaining_time": "0:17:36", "throughput": 6300.53, "total_tokens": 4648320}
{"current_steps": 4850, "total_steps": 11784, "loss": 0.0984, "lr": 1.4649753693179373e-06, "epoch": 0.41157501697216564, "percentage": 41.16, "elapsed_time": "0:12:18", "remaining_time": "0:17:35", "throughput": 6304.19, "total_tokens": 4653120}
{"current_steps": 4855, "total_steps": 11784, "loss": 0.073, "lr": 1.4636635319853272e-06, "epoch": 0.41199932111337406, "percentage": 41.2, "elapsed_time": "0:12:18", "remaining_time": "0:17:33", "throughput": 6307.98, "total_tokens": 4658048}
{"current_steps": 4860, "total_steps": 11784, "loss": 0.0463, "lr": 1.4623506774177796e-06, "epoch": 0.4124236252545825, "percentage": 41.24, "elapsed_time": "0:12:18", "remaining_time": "0:17:32", "throughput": 6311.74, "total_tokens": 4662976}
{"current_steps": 4865, "total_steps": 11784, "loss": 0.0902, "lr": 1.4610368084955748e-06, "epoch": 0.4128479293957909, "percentage": 41.28, "elapsed_time": "0:12:19", "remaining_time": "0:17:31", "throughput": 6315.39, "total_tokens": 4667840}
{"current_steps": 4870, "total_steps": 11784, "loss": 0.096, "lr": 1.4597219281012208e-06, "epoch": 0.4132722335369993, "percentage": 41.33, "elapsed_time": "0:12:19", "remaining_time": "0:17:29", "throughput": 6319.92, "total_tokens": 4673408}
{"current_steps": 4875, "total_steps": 11784, "loss": 0.1332, "lr": 1.4584060391194436e-06, "epoch": 0.41369653767820774, "percentage": 41.37, "elapsed_time": "0:12:19", "remaining_time": "0:17:28", "throughput": 6325.11, "total_tokens": 4679552}
{"current_steps": 4880, "total_steps": 11784, "loss": 0.0965, "lr": 1.4570891444371814e-06, "epoch": 0.41412084181941616, "percentage": 41.41, "elapsed_time": "0:12:20", "remaining_time": "0:17:27", "throughput": 6328.77, "total_tokens": 4684352}
{"current_steps": 4885, "total_steps": 11784, "loss": 0.0692, "lr": 1.4557712469435797e-06, "epoch": 0.4145451459606246, "percentage": 41.45, "elapsed_time": "0:12:20", "remaining_time": "0:17:25", "throughput": 6331.87, "total_tokens": 4688704}
{"current_steps": 4890, "total_steps": 11784, "loss": 0.0413, "lr": 1.4544523495299841e-06, "epoch": 0.414969450101833, "percentage": 41.5, "elapsed_time": "0:12:20", "remaining_time": "0:17:24", "throughput": 6335.4, "total_tokens": 4693440}
{"current_steps": 4895, "total_steps": 11784, "loss": 0.0806, "lr": 1.4531324550899333e-06, "epoch": 0.4153937542430414, "percentage": 41.54, "elapsed_time": "0:12:21", "remaining_time": "0:17:23", "throughput": 6339.32, "total_tokens": 4698496}
{"current_steps": 4900, "total_steps": 11784, "loss": 0.0962, "lr": 1.451811566519154e-06, "epoch": 0.41581805838424984, "percentage": 41.58, "elapsed_time": "0:12:21", "remaining_time": "0:17:21", "throughput": 6343.3, "total_tokens": 4703616}
{"current_steps": 4905, "total_steps": 11784, "loss": 0.0827, "lr": 1.450489686715553e-06, "epoch": 0.41624236252545826, "percentage": 41.62, "elapsed_time": "0:12:21", "remaining_time": "0:17:20", "throughput": 6345.92, "total_tokens": 4707584}
{"current_steps": 4910, "total_steps": 11784, "loss": 0.1271, "lr": 1.4491668185792131e-06, "epoch": 0.4166666666666667, "percentage": 41.67, "elapsed_time": "0:12:22", "remaining_time": "0:17:19", "throughput": 6349.01, "total_tokens": 4711936}
{"current_steps": 4915, "total_steps": 11784, "loss": 0.0545, "lr": 1.4478429650123851e-06, "epoch": 0.4170909708078751, "percentage": 41.71, "elapsed_time": "0:12:22", "remaining_time": "0:17:17", "throughput": 6352.9, "total_tokens": 4716992}
{"current_steps": 4920, "total_steps": 11784, "loss": 0.0595, "lr": 1.44651812891948e-06, "epoch": 0.4175152749490835, "percentage": 41.75, "elapsed_time": "0:12:22", "remaining_time": "0:17:16", "throughput": 6356.54, "total_tokens": 4721792}
{"current_steps": 4925, "total_steps": 11784, "loss": 0.0644, "lr": 1.4451923132070669e-06, "epoch": 0.41793957909029195, "percentage": 41.79, "elapsed_time": "0:12:23", "remaining_time": "0:17:14", "throughput": 6359.71, "total_tokens": 4726208}
{"current_steps": 4930, "total_steps": 11784, "loss": 0.0712, "lr": 1.4438655207838628e-06, "epoch": 0.41836388323150037, "percentage": 41.84, "elapsed_time": "0:12:23", "remaining_time": "0:17:13", "throughput": 6363.15, "total_tokens": 4730880}
{"current_steps": 4935, "total_steps": 11784, "loss": 0.0898, "lr": 1.4425377545607275e-06, "epoch": 0.41878818737270873, "percentage": 41.88, "elapsed_time": "0:12:23", "remaining_time": "0:17:12", "throughput": 6367.25, "total_tokens": 4736128}
{"current_steps": 4940, "total_steps": 11784, "loss": 0.0292, "lr": 1.4412090174506567e-06, "epoch": 0.41921249151391715, "percentage": 41.92, "elapsed_time": "0:12:24", "remaining_time": "0:17:10", "throughput": 6370.47, "total_tokens": 4740608}
{"current_steps": 4945, "total_steps": 11784, "loss": 0.0739, "lr": 1.4398793123687777e-06, "epoch": 0.41963679565512557, "percentage": 41.96, "elapsed_time": "0:12:24", "remaining_time": "0:17:09", "throughput": 6374.05, "total_tokens": 4745408}
{"current_steps": 4950, "total_steps": 11784, "loss": 0.0038, "lr": 1.4385486422323404e-06, "epoch": 0.420061099796334, "percentage": 42.01, "elapsed_time": "0:12:24", "remaining_time": "0:17:08", "throughput": 6377.85, "total_tokens": 4750400}
{"current_steps": 4955, "total_steps": 11784, "loss": 0.0556, "lr": 1.4372170099607123e-06, "epoch": 0.4204854039375424, "percentage": 42.05, "elapsed_time": "0:12:25", "remaining_time": "0:17:06", "throughput": 6381.22, "total_tokens": 4755008}
{"current_steps": 4960, "total_steps": 11784, "loss": 0.1251, "lr": 1.435884418475371e-06, "epoch": 0.42090970807875083, "percentage": 42.09, "elapsed_time": "0:12:25", "remaining_time": "0:17:05", "throughput": 6384.36, "total_tokens": 4759424}
{"current_steps": 4965, "total_steps": 11784, "loss": 0.0476, "lr": 1.4345508706998994e-06, "epoch": 0.42133401221995925, "percentage": 42.13, "elapsed_time": "0:12:25", "remaining_time": "0:17:04", "throughput": 6387.64, "total_tokens": 4763968}
{"current_steps": 4970, "total_steps": 11784, "loss": 0.065, "lr": 1.433216369559978e-06, "epoch": 0.4217583163611677, "percentage": 42.18, "elapsed_time": "0:12:26", "remaining_time": "0:17:02", "throughput": 6391.44, "total_tokens": 4768960}
{"current_steps": 4975, "total_steps": 11784, "loss": 0.0698, "lr": 1.4318809179833791e-06, "epoch": 0.4221826205023761, "percentage": 42.22, "elapsed_time": "0:12:26", "remaining_time": "0:17:01", "throughput": 6395.94, "total_tokens": 4774592}
{"current_steps": 4980, "total_steps": 11784, "loss": 0.0981, "lr": 1.4305445188999596e-06, "epoch": 0.4226069246435845, "percentage": 42.26, "elapsed_time": "0:12:26", "remaining_time": "0:17:00", "throughput": 6399.0, "total_tokens": 4778944}
{"current_steps": 4985, "total_steps": 11784, "loss": 0.1095, "lr": 1.4292071752416558e-06, "epoch": 0.42303122878479293, "percentage": 42.3, "elapsed_time": "0:12:27", "remaining_time": "0:16:59", "throughput": 6402.29, "total_tokens": 4783488}
{"current_steps": 4990, "total_steps": 11784, "loss": 0.0264, "lr": 1.4278688899424764e-06, "epoch": 0.42345553292600135, "percentage": 42.35, "elapsed_time": "0:12:27", "remaining_time": "0:16:57", "throughput": 6405.8, "total_tokens": 4788288}
{"current_steps": 4995, "total_steps": 11784, "loss": 0.0264, "lr": 1.4265296659384953e-06, "epoch": 0.4238798370672098, "percentage": 42.39, "elapsed_time": "0:12:27", "remaining_time": "0:16:56", "throughput": 6409.06, "total_tokens": 4792896}
{"current_steps": 5000, "total_steps": 11784, "loss": 0.1121, "lr": 1.4251895061678463e-06, "epoch": 0.4243041412084182, "percentage": 42.43, "elapsed_time": "0:12:28", "remaining_time": "0:16:55", "throughput": 6411.86, "total_tokens": 4797056}
{"current_steps": 5005, "total_steps": 11784, "loss": 0.0697, "lr": 1.4238484135707162e-06, "epoch": 0.4247284453496266, "percentage": 42.47, "elapsed_time": "0:12:28", "remaining_time": "0:16:53", "throughput": 6415.93, "total_tokens": 4802304}
{"current_steps": 5010, "total_steps": 11784, "loss": 0.0716, "lr": 1.4225063910893384e-06, "epoch": 0.42515274949083504, "percentage": 42.52, "elapsed_time": "0:12:28", "remaining_time": "0:16:52", "throughput": 6419.84, "total_tokens": 4807424}
{"current_steps": 5015, "total_steps": 11784, "loss": 0.0602, "lr": 1.4211634416679855e-06, "epoch": 0.42557705363204346, "percentage": 42.56, "elapsed_time": "0:12:29", "remaining_time": "0:16:51", "throughput": 6423.36, "total_tokens": 4812224}
{"current_steps": 5020, "total_steps": 11784, "loss": 0.1474, "lr": 1.419819568252965e-06, "epoch": 0.4260013577732519, "percentage": 42.6, "elapsed_time": "0:12:29", "remaining_time": "0:16:49", "throughput": 6427.13, "total_tokens": 4817216}
{"current_steps": 5025, "total_steps": 11784, "loss": 0.0352, "lr": 1.418474773792611e-06, "epoch": 0.4264256619144603, "percentage": 42.64, "elapsed_time": "0:12:29", "remaining_time": "0:16:48", "throughput": 6431.02, "total_tokens": 4822336}
{"current_steps": 5030, "total_steps": 11784, "loss": 0.0397, "lr": 1.4171290612372779e-06, "epoch": 0.4268499660556687, "percentage": 42.68, "elapsed_time": "0:12:30", "remaining_time": "0:16:47", "throughput": 6434.79, "total_tokens": 4827328}
{"current_steps": 5035, "total_steps": 11784, "loss": 0.0677, "lr": 1.4157824335393349e-06, "epoch": 0.42727427019687714, "percentage": 42.73, "elapsed_time": "0:12:30", "remaining_time": "0:16:46", "throughput": 6437.94, "total_tokens": 4831808}
{"current_steps": 5040, "total_steps": 11784, "loss": 0.0246, "lr": 1.4144348936531588e-06, "epoch": 0.42769857433808556, "percentage": 42.77, "elapsed_time": "0:12:30", "remaining_time": "0:16:44", "throughput": 6440.87, "total_tokens": 4836096}
{"current_steps": 5045, "total_steps": 11784, "loss": 0.0595, "lr": 1.413086444535127e-06, "epoch": 0.428122878479294, "percentage": 42.81, "elapsed_time": "0:12:31", "remaining_time": "0:16:43", "throughput": 6443.88, "total_tokens": 4840448}
{"current_steps": 5050, "total_steps": 11784, "loss": 0.0571, "lr": 1.4117370891436133e-06, "epoch": 0.4285471826205024, "percentage": 42.85, "elapsed_time": "0:12:31", "remaining_time": "0:16:42", "throughput": 6447.31, "total_tokens": 4845184}
{"current_steps": 5055, "total_steps": 11784, "loss": 0.1268, "lr": 1.410386830438978e-06, "epoch": 0.4289714867617108, "percentage": 42.9, "elapsed_time": "0:12:31", "remaining_time": "0:16:40", "throughput": 6450.75, "total_tokens": 4849920}
{"current_steps": 5060, "total_steps": 11784, "loss": 0.0976, "lr": 1.4090356713835635e-06, "epoch": 0.42939579090291924, "percentage": 42.94, "elapsed_time": "0:12:32", "remaining_time": "0:16:39", "throughput": 6453.87, "total_tokens": 4854400}
{"current_steps": 5065, "total_steps": 11784, "loss": 0.085, "lr": 1.4076836149416886e-06, "epoch": 0.4298200950441276, "percentage": 42.98, "elapsed_time": "0:12:32", "remaining_time": "0:16:38", "throughput": 6457.62, "total_tokens": 4859392}
{"current_steps": 5070, "total_steps": 11784, "loss": 0.1246, "lr": 1.4063306640796404e-06, "epoch": 0.430244399185336, "percentage": 43.02, "elapsed_time": "0:12:32", "remaining_time": "0:16:36", "throughput": 6461.45, "total_tokens": 4864512}
{"current_steps": 5075, "total_steps": 11784, "loss": 0.0893, "lr": 1.4049768217656674e-06, "epoch": 0.43066870332654444, "percentage": 43.07, "elapsed_time": "0:12:33", "remaining_time": "0:16:35", "throughput": 6465.59, "total_tokens": 4869888}
{"current_steps": 5080, "total_steps": 11784, "loss": 0.0676, "lr": 1.4036220909699748e-06, "epoch": 0.43109300746775286, "percentage": 43.11, "elapsed_time": "0:12:33", "remaining_time": "0:16:34", "throughput": 6468.59, "total_tokens": 4874304}
{"current_steps": 5085, "total_steps": 11784, "loss": 0.0927, "lr": 1.4022664746647168e-06, "epoch": 0.4315173116089613, "percentage": 43.15, "elapsed_time": "0:12:33", "remaining_time": "0:16:33", "throughput": 6472.36, "total_tokens": 4879360}
{"current_steps": 5090, "total_steps": 11784, "loss": 0.0828, "lr": 1.40090997582399e-06, "epoch": 0.4319416157501697, "percentage": 43.19, "elapsed_time": "0:12:34", "remaining_time": "0:16:31", "throughput": 6475.11, "total_tokens": 4883520}
{"current_steps": 5095, "total_steps": 11784, "loss": 0.039, "lr": 1.3995525974238278e-06, "epoch": 0.4323659198913781, "percentage": 43.24, "elapsed_time": "0:12:34", "remaining_time": "0:16:30", "throughput": 6478.58, "total_tokens": 4888320}
{"current_steps": 5100, "total_steps": 11784, "loss": 0.0103, "lr": 1.398194342442193e-06, "epoch": 0.43279022403258655, "percentage": 43.28, "elapsed_time": "0:12:34", "remaining_time": "0:16:29", "throughput": 6482.83, "total_tokens": 4893824}
{"current_steps": 5105, "total_steps": 11784, "loss": 0.0693, "lr": 1.396835213858971e-06, "epoch": 0.43321452817379497, "percentage": 43.32, "elapsed_time": "0:12:35", "remaining_time": "0:16:28", "throughput": 6486.08, "total_tokens": 4898432}
{"current_steps": 5110, "total_steps": 11784, "loss": 0.106, "lr": 1.395475214655965e-06, "epoch": 0.4336388323150034, "percentage": 43.36, "elapsed_time": "0:12:35", "remaining_time": "0:16:26", "throughput": 6489.35, "total_tokens": 4903040}
{"current_steps": 5115, "total_steps": 11784, "loss": 0.0744, "lr": 1.394114347816887e-06, "epoch": 0.4340631364562118, "percentage": 43.41, "elapsed_time": "0:12:35", "remaining_time": "0:16:25", "throughput": 6493.08, "total_tokens": 4908096}
{"current_steps": 5120, "total_steps": 11784, "loss": 0.1002, "lr": 1.3927526163273538e-06, "epoch": 0.4344874405974202, "percentage": 43.45, "elapsed_time": "0:12:36", "remaining_time": "0:16:24", "throughput": 6496.27, "total_tokens": 4912640}
{"current_steps": 5125, "total_steps": 11784, "loss": 0.0305, "lr": 1.3913900231748776e-06, "epoch": 0.43491174473862865, "percentage": 43.49, "elapsed_time": "0:12:36", "remaining_time": "0:16:23", "throughput": 6499.8, "total_tokens": 4917504}
{"current_steps": 5130, "total_steps": 11784, "loss": 0.0281, "lr": 1.3900265713488623e-06, "epoch": 0.43533604887983707, "percentage": 43.53, "elapsed_time": "0:12:36", "remaining_time": "0:16:21", "throughput": 6503.66, "total_tokens": 4922688}
{"current_steps": 5135, "total_steps": 11784, "loss": 0.0589, "lr": 1.3886622638405952e-06, "epoch": 0.4357603530210455, "percentage": 43.58, "elapsed_time": "0:12:37", "remaining_time": "0:16:20", "throughput": 6506.47, "total_tokens": 4926976}
{"current_steps": 5140, "total_steps": 11784, "loss": 0.052, "lr": 1.3872971036432406e-06, "epoch": 0.4361846571622539, "percentage": 43.62, "elapsed_time": "0:12:37", "remaining_time": "0:16:19", "throughput": 6509.52, "total_tokens": 4931456}
{"current_steps": 5145, "total_steps": 11784, "loss": 0.0948, "lr": 1.385931093751834e-06, "epoch": 0.43660896130346233, "percentage": 43.66, "elapsed_time": "0:12:37", "remaining_time": "0:16:17", "throughput": 6512.67, "total_tokens": 4936000}
{"current_steps": 5150, "total_steps": 11784, "loss": 0.0645, "lr": 1.384564237163275e-06, "epoch": 0.43703326544467075, "percentage": 43.7, "elapsed_time": "0:12:38", "remaining_time": "0:16:16", "throughput": 6515.5, "total_tokens": 4940288}
{"current_steps": 5155, "total_steps": 11784, "loss": 0.0545, "lr": 1.3831965368763203e-06, "epoch": 0.43745756958587917, "percentage": 43.75, "elapsed_time": "0:12:38", "remaining_time": "0:16:15", "throughput": 6518.37, "total_tokens": 4944576}
{"current_steps": 5160, "total_steps": 11784, "loss": 0.0682, "lr": 1.3818279958915785e-06, "epoch": 0.4378818737270876, "percentage": 43.79, "elapsed_time": "0:12:38", "remaining_time": "0:16:14", "throughput": 6521.35, "total_tokens": 4948992}
{"current_steps": 5165, "total_steps": 11784, "loss": 0.0657, "lr": 1.3804586172115015e-06, "epoch": 0.438306177868296, "percentage": 43.83, "elapsed_time": "0:12:39", "remaining_time": "0:16:12", "throughput": 6524.7, "total_tokens": 4953728}
{"current_steps": 5170, "total_steps": 11784, "loss": 0.055, "lr": 1.3790884038403793e-06, "epoch": 0.43873048200950443, "percentage": 43.87, "elapsed_time": "0:12:39", "remaining_time": "0:16:11", "throughput": 6528.37, "total_tokens": 4958720}
{"current_steps": 5175, "total_steps": 11784, "loss": 0.0761, "lr": 1.3777173587843341e-06, "epoch": 0.43915478615071285, "percentage": 43.92, "elapsed_time": "0:12:39", "remaining_time": "0:16:10", "throughput": 6532.14, "total_tokens": 4963840}
{"current_steps": 5180, "total_steps": 11784, "loss": 0.0099, "lr": 1.3763454850513122e-06, "epoch": 0.43957909029192127, "percentage": 43.96, "elapsed_time": "0:12:40", "remaining_time": "0:16:09", "throughput": 6535.46, "total_tokens": 4968512}
{"current_steps": 5185, "total_steps": 11784, "loss": 0.079, "lr": 1.3749727856510766e-06, "epoch": 0.4400033944331297, "percentage": 44.0, "elapsed_time": "0:12:40", "remaining_time": "0:16:07", "throughput": 6538.45, "total_tokens": 4972928}
{"current_steps": 5190, "total_steps": 11784, "loss": 0.1034, "lr": 1.373599263595204e-06, "epoch": 0.4404276985743381, "percentage": 44.04, "elapsed_time": "0:12:40", "remaining_time": "0:16:06", "throughput": 6541.77, "total_tokens": 4977664}
{"current_steps": 5195, "total_steps": 11784, "loss": 0.1265, "lr": 1.3722249218970744e-06, "epoch": 0.4408520027155465, "percentage": 44.09, "elapsed_time": "0:12:41", "remaining_time": "0:16:05", "throughput": 6545.66, "total_tokens": 4982912}
{"current_steps": 5200, "total_steps": 11784, "loss": 0.0489, "lr": 1.3708497635718672e-06, "epoch": 0.4412763068567549, "percentage": 44.13, "elapsed_time": "0:12:41", "remaining_time": "0:16:04", "throughput": 6549.87, "total_tokens": 4988416}
{"current_steps": 5205, "total_steps": 11784, "loss": 0.0982, "lr": 1.3694737916365515e-06, "epoch": 0.4417006109979633, "percentage": 44.17, "elapsed_time": "0:12:41", "remaining_time": "0:16:03", "throughput": 6553.57, "total_tokens": 4993472}
{"current_steps": 5210, "total_steps": 11784, "loss": 0.037, "lr": 1.3680970091098832e-06, "epoch": 0.44212491513917174, "percentage": 44.21, "elapsed_time": "0:12:42", "remaining_time": "0:16:01", "throughput": 6556.91, "total_tokens": 4998208}
{"current_steps": 5215, "total_steps": 11784, "loss": 0.0563, "lr": 1.366719419012396e-06, "epoch": 0.44254921928038016, "percentage": 44.25, "elapsed_time": "0:12:42", "remaining_time": "0:16:00", "throughput": 6560.31, "total_tokens": 5003008}
{"current_steps": 5220, "total_steps": 11784, "loss": 0.0438, "lr": 1.3653410243663951e-06, "epoch": 0.4429735234215886, "percentage": 44.3, "elapsed_time": "0:12:42", "remaining_time": "0:15:59", "throughput": 6564.66, "total_tokens": 5008704}
{"current_steps": 5225, "total_steps": 11784, "loss": 0.1245, "lr": 1.363961828195951e-06, "epoch": 0.443397827562797, "percentage": 44.34, "elapsed_time": "0:12:43", "remaining_time": "0:15:58", "throughput": 6567.58, "total_tokens": 5013120}
{"current_steps": 5230, "total_steps": 11784, "loss": 0.0402, "lr": 1.3625818335268923e-06, "epoch": 0.4438221317040054, "percentage": 44.38, "elapsed_time": "0:12:43", "remaining_time": "0:15:56", "throughput": 6570.67, "total_tokens": 5017664}
{"current_steps": 5235, "total_steps": 11784, "loss": 0.058, "lr": 1.3612010433868004e-06, "epoch": 0.44424643584521384, "percentage": 44.42, "elapsed_time": "0:12:43", "remaining_time": "0:15:55", "throughput": 6574.13, "total_tokens": 5022528}
{"current_steps": 5240, "total_steps": 11784, "loss": 0.0781, "lr": 1.3598194608050008e-06, "epoch": 0.44467073998642226, "percentage": 44.47, "elapsed_time": "0:12:44", "remaining_time": "0:15:54", "throughput": 6577.21, "total_tokens": 5027072}
{"current_steps": 5245, "total_steps": 11784, "loss": 0.0093, "lr": 1.3584370888125583e-06, "epoch": 0.4450950441276307, "percentage": 44.51, "elapsed_time": "0:12:44", "remaining_time": "0:15:53", "throughput": 6580.06, "total_tokens": 5031424}
{"current_steps": 5250, "total_steps": 11784, "loss": 0.056, "lr": 1.357053930442269e-06, "epoch": 0.4455193482688391, "percentage": 44.55, "elapsed_time": "0:12:44", "remaining_time": "0:15:52", "throughput": 6583.69, "total_tokens": 5036480}
{"current_steps": 5255, "total_steps": 11784, "loss": 0.0619, "lr": 1.355669988728655e-06, "epoch": 0.4459436524100475, "percentage": 44.59, "elapsed_time": "0:12:45", "remaining_time": "0:15:50", "throughput": 6587.61, "total_tokens": 5041792}
{"current_steps": 5260, "total_steps": 11784, "loss": 0.0033, "lr": 1.3542852667079557e-06, "epoch": 0.44636795655125594, "percentage": 44.64, "elapsed_time": "0:12:45", "remaining_time": "0:15:49", "throughput": 6590.95, "total_tokens": 5046592}
{"current_steps": 5265, "total_steps": 11784, "loss": 0.1114, "lr": 1.352899767418124e-06, "epoch": 0.44679226069246436, "percentage": 44.68, "elapsed_time": "0:12:46", "remaining_time": "0:15:48", "throughput": 6594.4, "total_tokens": 5051456}
{"current_steps": 5270, "total_steps": 11784, "loss": 0.0761, "lr": 1.3515134938988168e-06, "epoch": 0.4472165648336728, "percentage": 44.72, "elapsed_time": "0:12:46", "remaining_time": "0:15:47", "throughput": 6597.76, "total_tokens": 5056320}
{"current_steps": 5275, "total_steps": 11784, "loss": 0.0149, "lr": 1.3501264491913906e-06, "epoch": 0.4476408689748812, "percentage": 44.76, "elapsed_time": "0:12:46", "remaining_time": "0:15:46", "throughput": 6601.22, "total_tokens": 5061248}
{"current_steps": 5280, "total_steps": 11784, "loss": 0.0755, "lr": 1.348738636338893e-06, "epoch": 0.4480651731160896, "percentage": 44.81, "elapsed_time": "0:12:47", "remaining_time": "0:15:44", "throughput": 6604.12, "total_tokens": 5065664}
{"current_steps": 5285, "total_steps": 11784, "loss": 0.0789, "lr": 1.3473500583860568e-06, "epoch": 0.44848947725729804, "percentage": 44.85, "elapsed_time": "0:12:47", "remaining_time": "0:15:43", "throughput": 6608.69, "total_tokens": 5071552}
{"current_steps": 5290, "total_steps": 11784, "loss": 0.0564, "lr": 1.3459607183792945e-06, "epoch": 0.44891378139850646, "percentage": 44.89, "elapsed_time": "0:12:47", "remaining_time": "0:15:42", "throughput": 6611.67, "total_tokens": 5076032}
{"current_steps": 5295, "total_steps": 11784, "loss": 0.0543, "lr": 1.344570619366689e-06, "epoch": 0.4493380855397149, "percentage": 44.93, "elapsed_time": "0:12:48", "remaining_time": "0:15:41", "throughput": 6614.54, "total_tokens": 5080384}
{"current_steps": 5300, "total_steps": 11784, "loss": 0.0623, "lr": 1.3431797643979894e-06, "epoch": 0.4497623896809233, "percentage": 44.98, "elapsed_time": "0:12:48", "remaining_time": "0:15:40", "throughput": 6618.07, "total_tokens": 5085376}
{"current_steps": 5305, "total_steps": 11784, "loss": 0.0338, "lr": 1.3417881565246027e-06, "epoch": 0.4501866938221317, "percentage": 45.02, "elapsed_time": "0:12:48", "remaining_time": "0:15:38", "throughput": 6621.35, "total_tokens": 5090112}
{"current_steps": 5310, "total_steps": 11784, "loss": 0.05, "lr": 1.3403957987995882e-06, "epoch": 0.45061099796334014, "percentage": 45.06, "elapsed_time": "0:12:49", "remaining_time": "0:15:37", "throughput": 6625.25, "total_tokens": 5095424}
{"current_steps": 5310, "total_steps": 11784, "eval_loss": 0.06341014802455902, "epoch": 0.45061099796334014, "percentage": 45.06, "elapsed_time": "0:13:04", "remaining_time": "0:15:56", "throughput": 6491.69, "total_tokens": 5095424}
{"current_steps": 5315, "total_steps": 11784, "loss": 0.0584, "lr": 1.33900269427765e-06, "epoch": 0.45103530210454856, "percentage": 45.1, "elapsed_time": "0:13:31", "remaining_time": "0:16:27", "throughput": 6283.83, "total_tokens": 5100864}
{"current_steps": 5320, "total_steps": 11784, "loss": 0.0825, "lr": 1.3376088460151306e-06, "epoch": 0.451459606245757, "percentage": 45.15, "elapsed_time": "0:13:32", "remaining_time": "0:16:26", "throughput": 6286.47, "total_tokens": 5105088}
{"current_steps": 5325, "total_steps": 11784, "loss": 0.044, "lr": 1.336214257070004e-06, "epoch": 0.4518839103869654, "percentage": 45.19, "elapsed_time": "0:13:32", "remaining_time": "0:16:25", "throughput": 6289.68, "total_tokens": 5109760}
{"current_steps": 5330, "total_steps": 11784, "loss": 0.0885, "lr": 1.3348189305018702e-06, "epoch": 0.45230821452817377, "percentage": 45.23, "elapsed_time": "0:13:32", "remaining_time": "0:16:24", "throughput": 6292.6, "total_tokens": 5114176}
{"current_steps": 5335, "total_steps": 11784, "loss": 0.0254, "lr": 1.3334228693719464e-06, "epoch": 0.4527325186693822, "percentage": 45.27, "elapsed_time": "0:13:33", "remaining_time": "0:16:22", "throughput": 6295.51, "total_tokens": 5118592}
{"current_steps": 5340, "total_steps": 11784, "loss": 0.1096, "lr": 1.3320260767430614e-06, "epoch": 0.4531568228105906, "percentage": 45.32, "elapsed_time": "0:13:33", "remaining_time": "0:16:21", "throughput": 6299.03, "total_tokens": 5123584}
{"current_steps": 5345, "total_steps": 11784, "loss": 0.0228, "lr": 1.3306285556796492e-06, "epoch": 0.45358112695179903, "percentage": 45.36, "elapsed_time": "0:13:33", "remaining_time": "0:16:20", "throughput": 6302.16, "total_tokens": 5128192}
{"current_steps": 5350, "total_steps": 11784, "loss": 0.0764, "lr": 1.3292303092477424e-06, "epoch": 0.45400543109300745, "percentage": 45.4, "elapsed_time": "0:13:34", "remaining_time": "0:16:18", "throughput": 6305.34, "total_tokens": 5132864}
{"current_steps": 5355, "total_steps": 11784, "loss": 0.0411, "lr": 1.3278313405149638e-06, "epoch": 0.45442973523421587, "percentage": 45.44, "elapsed_time": "0:13:34", "remaining_time": "0:16:17", "throughput": 6308.19, "total_tokens": 5137216}
{"current_steps": 5360, "total_steps": 11784, "loss": 0.0462, "lr": 1.3264316525505216e-06, "epoch": 0.4548540393754243, "percentage": 45.49, "elapsed_time": "0:13:34", "remaining_time": "0:16:16", "throughput": 6312.03, "total_tokens": 5142528}
{"current_steps": 5365, "total_steps": 11784, "loss": 0.0102, "lr": 1.3250312484252021e-06, "epoch": 0.4552783435166327, "percentage": 45.53, "elapsed_time": "0:13:35", "remaining_time": "0:16:15", "throughput": 6316.0, "total_tokens": 5147968}
{"current_steps": 5370, "total_steps": 11784, "loss": 0.0413, "lr": 1.3236301312113627e-06, "epoch": 0.45570264765784113, "percentage": 45.57, "elapsed_time": "0:13:35", "remaining_time": "0:16:13", "throughput": 6318.9, "total_tokens": 5152384}
{"current_steps": 5375, "total_steps": 11784, "loss": 0.1069, "lr": 1.3222283039829247e-06, "epoch": 0.45612695179904955, "percentage": 45.61, "elapsed_time": "0:13:35", "remaining_time": "0:16:12", "throughput": 6321.99, "total_tokens": 5156992}
{"current_steps": 5380, "total_steps": 11784, "loss": 0.0965, "lr": 1.3208257698153676e-06, "epoch": 0.45655125594025797, "percentage": 45.66, "elapsed_time": "0:13:36", "remaining_time": "0:16:11", "throughput": 6325.5, "total_tokens": 5161984}
{"current_steps": 5385, "total_steps": 11784, "loss": 0.0604, "lr": 1.3194225317857216e-06, "epoch": 0.4569755600814664, "percentage": 45.7, "elapsed_time": "0:13:36", "remaining_time": "0:16:10", "throughput": 6329.07, "total_tokens": 5167040}
{"current_steps": 5390, "total_steps": 11784, "loss": 0.0475, "lr": 1.3180185929725616e-06, "epoch": 0.4573998642226748, "percentage": 45.74, "elapsed_time": "0:13:36", "remaining_time": "0:16:08", "throughput": 6332.29, "total_tokens": 5171776}
{"current_steps": 5395, "total_steps": 11784, "loss": 0.117, "lr": 1.3166139564559992e-06, "epoch": 0.45782416836388323, "percentage": 45.78, "elapsed_time": "0:13:37", "remaining_time": "0:16:07", "throughput": 6335.92, "total_tokens": 5176896}
{"current_steps": 5400, "total_steps": 11784, "loss": 0.0416, "lr": 1.3152086253176773e-06, "epoch": 0.45824847250509165, "percentage": 45.82, "elapsed_time": "0:13:37", "remaining_time": "0:16:06", "throughput": 6338.8, "total_tokens": 5181312}
{"current_steps": 5405, "total_steps": 11784, "loss": 0.008, "lr": 1.313802602640763e-06, "epoch": 0.4586727766463001, "percentage": 45.87, "elapsed_time": "0:13:37", "remaining_time": "0:16:05", "throughput": 6342.07, "total_tokens": 5186112}
{"current_steps": 5410, "total_steps": 11784, "loss": 0.0387, "lr": 1.3123958915099392e-06, "epoch": 0.4590970807875085, "percentage": 45.91, "elapsed_time": "0:13:38", "remaining_time": "0:16:03", "throughput": 6345.47, "total_tokens": 5191040}
{"current_steps": 5415, "total_steps": 11784, "loss": 0.0441, "lr": 1.3109884950114005e-06, "epoch": 0.4595213849287169, "percentage": 45.95, "elapsed_time": "0:13:38", "remaining_time": "0:16:02", "throughput": 6348.47, "total_tokens": 5195584}
{"current_steps": 5420, "total_steps": 11784, "loss": 0.0799, "lr": 1.309580416232845e-06, "epoch": 0.45994568906992533, "percentage": 45.99, "elapsed_time": "0:13:38", "remaining_time": "0:16:01", "throughput": 6351.6, "total_tokens": 5200256}
{"current_steps": 5425, "total_steps": 11784, "loss": 0.0576, "lr": 1.3081716582634672e-06, "epoch": 0.46036999321113375, "percentage": 46.04, "elapsed_time": "0:13:39", "remaining_time": "0:16:00", "throughput": 6355.23, "total_tokens": 5205376}
{"current_steps": 5430, "total_steps": 11784, "loss": 0.0254, "lr": 1.3067622241939518e-06, "epoch": 0.4607942973523422, "percentage": 46.08, "elapsed_time": "0:13:39", "remaining_time": "0:15:58", "throughput": 6359.75, "total_tokens": 5211392}
{"current_steps": 5435, "total_steps": 11784, "loss": 0.0247, "lr": 1.305352117116467e-06, "epoch": 0.4612186014935506, "percentage": 46.12, "elapsed_time": "0:13:39", "remaining_time": "0:15:57", "throughput": 6362.41, "total_tokens": 5215616}
{"current_steps": 5440, "total_steps": 11784, "loss": 0.0862, "lr": 1.3039413401246576e-06, "epoch": 0.461642905634759, "percentage": 46.16, "elapsed_time": "0:13:40", "remaining_time": "0:15:56", "throughput": 6365.88, "total_tokens": 5220608}
{"current_steps": 5445, "total_steps": 11784, "loss": 0.1111, "lr": 1.3025298963136377e-06, "epoch": 0.46206720977596744, "percentage": 46.21, "elapsed_time": "0:13:40", "remaining_time": "0:15:55", "throughput": 6369.09, "total_tokens": 5225344}
{"current_steps": 5450, "total_steps": 11784, "loss": 0.0417, "lr": 1.3011177887799844e-06, "epoch": 0.46249151391717586, "percentage": 46.25, "elapsed_time": "0:13:40", "remaining_time": "0:15:53", "throughput": 6372.72, "total_tokens": 5230464}
{"current_steps": 5455, "total_steps": 11784, "loss": 0.0548, "lr": 1.2997050206217315e-06, "epoch": 0.4629158180583843, "percentage": 46.29, "elapsed_time": "0:13:41", "remaining_time": "0:15:52", "throughput": 6375.97, "total_tokens": 5235264}
{"current_steps": 5460, "total_steps": 11784, "loss": 0.0883, "lr": 1.2982915949383614e-06, "epoch": 0.46334012219959264, "percentage": 46.33, "elapsed_time": "0:13:41", "remaining_time": "0:15:51", "throughput": 6378.95, "total_tokens": 5239808}
{"current_steps": 5465, "total_steps": 11784, "loss": 0.0629, "lr": 1.2968775148308002e-06, "epoch": 0.46376442634080106, "percentage": 46.38, "elapsed_time": "0:13:41", "remaining_time": "0:15:50", "throughput": 6381.98, "total_tokens": 5244416}
{"current_steps": 5470, "total_steps": 11784, "loss": 0.0882, "lr": 1.295462783401408e-06, "epoch": 0.4641887304820095, "percentage": 46.42, "elapsed_time": "0:13:42", "remaining_time": "0:15:48", "throughput": 6385.29, "total_tokens": 5249280}
{"current_steps": 5475, "total_steps": 11784, "loss": 0.1072, "lr": 1.2940474037539755e-06, "epoch": 0.4646130346232179, "percentage": 46.46, "elapsed_time": "0:13:42", "remaining_time": "0:15:47", "throughput": 6388.57, "total_tokens": 5254080}
{"current_steps": 5480, "total_steps": 11784, "loss": 0.0185, "lr": 1.2926313789937143e-06, "epoch": 0.4650373387644263, "percentage": 46.5, "elapsed_time": "0:13:42", "remaining_time": "0:15:46", "throughput": 6392.11, "total_tokens": 5259136}
{"current_steps": 5485, "total_steps": 11784, "loss": 0.0443, "lr": 1.2912147122272522e-06, "epoch": 0.46546164290563474, "percentage": 46.55, "elapsed_time": "0:13:43", "remaining_time": "0:15:45", "throughput": 6395.13, "total_tokens": 5263744}
{"current_steps": 5490, "total_steps": 11784, "loss": 0.0569, "lr": 1.289797406562625e-06, "epoch": 0.46588594704684316, "percentage": 46.59, "elapsed_time": "0:13:43", "remaining_time": "0:15:44", "throughput": 6398.37, "total_tokens": 5268544}
{"current_steps": 5495, "total_steps": 11784, "loss": 0.0288, "lr": 1.2883794651092704e-06, "epoch": 0.4663102511880516, "percentage": 46.63, "elapsed_time": "0:13:43", "remaining_time": "0:15:42", "throughput": 6401.53, "total_tokens": 5273280}
{"current_steps": 5500, "total_steps": 11784, "loss": 0.0231, "lr": 1.2869608909780212e-06, "epoch": 0.46673455532926, "percentage": 46.67, "elapsed_time": "0:13:44", "remaining_time": "0:15:41", "throughput": 6404.56, "total_tokens": 5277888}
{"current_steps": 5505, "total_steps": 11784, "loss": 0.0518, "lr": 1.2855416872810973e-06, "epoch": 0.4671588594704684, "percentage": 46.72, "elapsed_time": "0:13:44", "remaining_time": "0:15:40", "throughput": 6407.48, "total_tokens": 5282432}
{"current_steps": 5510, "total_steps": 11784, "loss": 0.0088, "lr": 1.284121857132101e-06, "epoch": 0.46758316361167684, "percentage": 46.76, "elapsed_time": "0:13:44", "remaining_time": "0:15:39", "throughput": 6412.05, "total_tokens": 5288512}
{"current_steps": 5515, "total_steps": 11784, "loss": 0.0204, "lr": 1.2827014036460082e-06, "epoch": 0.46800746775288526, "percentage": 46.8, "elapsed_time": "0:13:45", "remaining_time": "0:15:37", "throughput": 6414.72, "total_tokens": 5292800}
{"current_steps": 5520, "total_steps": 11784, "loss": 0.0274, "lr": 1.2812803299391628e-06, "epoch": 0.4684317718940937, "percentage": 46.84, "elapsed_time": "0:13:45", "remaining_time": "0:15:36", "throughput": 6418.22, "total_tokens": 5297856}
{"current_steps": 5525, "total_steps": 11784, "loss": 0.0859, "lr": 1.2798586391292689e-06, "epoch": 0.4688560760353021, "percentage": 46.89, "elapsed_time": "0:13:45", "remaining_time": "0:15:35", "throughput": 6421.6, "total_tokens": 5302784}
{"current_steps": 5530, "total_steps": 11784, "loss": 0.0555, "lr": 1.2784363343353848e-06, "epoch": 0.4692803801765105, "percentage": 46.93, "elapsed_time": "0:13:46", "remaining_time": "0:15:34", "throughput": 6424.87, "total_tokens": 5307648}
{"current_steps": 5535, "total_steps": 11784, "loss": 0.0496, "lr": 1.2770134186779158e-06, "epoch": 0.46970468431771895, "percentage": 46.97, "elapsed_time": "0:13:46", "remaining_time": "0:15:33", "throughput": 6427.27, "total_tokens": 5311680}
{"current_steps": 5540, "total_steps": 11784, "loss": 0.053, "lr": 1.2755898952786076e-06, "epoch": 0.47012898845892737, "percentage": 47.01, "elapsed_time": "0:13:46", "remaining_time": "0:15:31", "throughput": 6430.28, "total_tokens": 5316288}
{"current_steps": 5545, "total_steps": 11784, "loss": 0.0291, "lr": 1.2741657672605385e-06, "epoch": 0.4705532926001358, "percentage": 47.06, "elapsed_time": "0:13:47", "remaining_time": "0:15:30", "throughput": 6432.82, "total_tokens": 5320448}
{"current_steps": 5550, "total_steps": 11784, "loss": 0.0483, "lr": 1.272741037748114e-06, "epoch": 0.4709775967413442, "percentage": 47.1, "elapsed_time": "0:13:47", "remaining_time": "0:15:29", "throughput": 6435.66, "total_tokens": 5324928}
{"current_steps": 5555, "total_steps": 11784, "loss": 0.0429, "lr": 1.2713157098670588e-06, "epoch": 0.4714019008825526, "percentage": 47.14, "elapsed_time": "0:13:47", "remaining_time": "0:15:28", "throughput": 6438.94, "total_tokens": 5329792}
{"current_steps": 5560, "total_steps": 11784, "loss": 0.0697, "lr": 1.2698897867444112e-06, "epoch": 0.47182620502376105, "percentage": 47.18, "elapsed_time": "0:13:48", "remaining_time": "0:15:26", "throughput": 6442.26, "total_tokens": 5334720}
{"current_steps": 5565, "total_steps": 11784, "loss": 0.0769, "lr": 1.268463271508514e-06, "epoch": 0.47225050916496947, "percentage": 47.23, "elapsed_time": "0:13:48", "remaining_time": "0:15:25", "throughput": 6445.93, "total_tokens": 5339968}
{"current_steps": 5570, "total_steps": 11784, "loss": 0.0083, "lr": 1.2670361672890099e-06, "epoch": 0.4726748133061779, "percentage": 47.27, "elapsed_time": "0:13:48", "remaining_time": "0:15:24", "throughput": 6449.57, "total_tokens": 5345216}
{"current_steps": 5575, "total_steps": 11784, "loss": 0.116, "lr": 1.265608477216834e-06, "epoch": 0.4730991174473863, "percentage": 47.31, "elapsed_time": "0:13:49", "remaining_time": "0:15:23", "throughput": 6453.17, "total_tokens": 5350400}
{"current_steps": 5580, "total_steps": 11784, "loss": 0.0868, "lr": 1.2641802044242065e-06, "epoch": 0.47352342158859473, "percentage": 47.35, "elapsed_time": "0:13:49", "remaining_time": "0:15:22", "throughput": 6456.1, "total_tokens": 5354944}
{"current_steps": 5585, "total_steps": 11784, "loss": 0.1187, "lr": 1.2627513520446252e-06, "epoch": 0.47394772572980315, "percentage": 47.39, "elapsed_time": "0:13:49", "remaining_time": "0:15:20", "throughput": 6458.55, "total_tokens": 5359040}
{"current_steps": 5590, "total_steps": 11784, "loss": 0.0866, "lr": 1.2613219232128608e-06, "epoch": 0.4743720298710115, "percentage": 47.44, "elapsed_time": "0:13:50", "remaining_time": "0:15:19", "throughput": 6461.48, "total_tokens": 5363584}
{"current_steps": 5595, "total_steps": 11784, "loss": 0.0184, "lr": 1.2598919210649475e-06, "epoch": 0.47479633401221993, "percentage": 47.48, "elapsed_time": "0:13:50", "remaining_time": "0:15:18", "throughput": 6464.54, "total_tokens": 5368256}
{"current_steps": 5600, "total_steps": 11784, "loss": 0.0563, "lr": 1.2584613487381787e-06, "epoch": 0.47522063815342835, "percentage": 47.52, "elapsed_time": "0:13:50", "remaining_time": "0:15:17", "throughput": 6467.47, "total_tokens": 5372800}
{"current_steps": 5605, "total_steps": 11784, "loss": 0.0413, "lr": 1.257030209371097e-06, "epoch": 0.4756449422946368, "percentage": 47.56, "elapsed_time": "0:13:51", "remaining_time": "0:15:16", "throughput": 6470.33, "total_tokens": 5377280}
{"current_steps": 5610, "total_steps": 11784, "loss": 0.1219, "lr": 1.2555985061034902e-06, "epoch": 0.4760692464358452, "percentage": 47.61, "elapsed_time": "0:13:51", "remaining_time": "0:15:14", "throughput": 6473.64, "total_tokens": 5382208}
{"current_steps": 5615, "total_steps": 11784, "loss": 0.0935, "lr": 1.2541662420763832e-06, "epoch": 0.4764935505770536, "percentage": 47.65, "elapsed_time": "0:13:51", "remaining_time": "0:15:13", "throughput": 6476.62, "total_tokens": 5386816}
{"current_steps": 5620, "total_steps": 11784, "loss": 0.0457, "lr": 1.2527334204320306e-06, "epoch": 0.47691785471826204, "percentage": 47.69, "elapsed_time": "0:13:52", "remaining_time": "0:15:12", "throughput": 6479.53, "total_tokens": 5391360}
{"current_steps": 5625, "total_steps": 11784, "loss": 0.0584, "lr": 1.251300044313911e-06, "epoch": 0.47734215885947046, "percentage": 47.73, "elapsed_time": "0:13:52", "remaining_time": "0:15:11", "throughput": 6482.44, "total_tokens": 5395904}
{"current_steps": 5630, "total_steps": 11784, "loss": 0.0555, "lr": 1.2498661168667188e-06, "epoch": 0.4777664630006789, "percentage": 47.78, "elapsed_time": "0:13:52", "remaining_time": "0:15:10", "throughput": 6485.33, "total_tokens": 5400448}
{"current_steps": 5635, "total_steps": 11784, "loss": 0.0431, "lr": 1.2484316412363585e-06, "epoch": 0.4781907671418873, "percentage": 47.82, "elapsed_time": "0:13:53", "remaining_time": "0:15:09", "throughput": 6489.08, "total_tokens": 5405824}
{"current_steps": 5640, "total_steps": 11784, "loss": 0.0407, "lr": 1.246996620569937e-06, "epoch": 0.4786150712830957, "percentage": 47.86, "elapsed_time": "0:13:53", "remaining_time": "0:15:07", "throughput": 6492.31, "total_tokens": 5410688}
{"current_steps": 5645, "total_steps": 11784, "loss": 0.0646, "lr": 1.245561058015757e-06, "epoch": 0.47903937542430414, "percentage": 47.9, "elapsed_time": "0:13:53", "remaining_time": "0:15:06", "throughput": 6495.27, "total_tokens": 5415296}
{"current_steps": 5650, "total_steps": 11784, "loss": 0.1001, "lr": 1.2441249567233098e-06, "epoch": 0.47946367956551256, "percentage": 47.95, "elapsed_time": "0:13:54", "remaining_time": "0:15:05", "throughput": 6497.93, "total_tokens": 5419648}
{"current_steps": 5655, "total_steps": 11784, "loss": 0.0398, "lr": 1.2426883198432696e-06, "epoch": 0.479887983706721, "percentage": 47.99, "elapsed_time": "0:13:54", "remaining_time": "0:15:04", "throughput": 6501.18, "total_tokens": 5424576}
{"current_steps": 5660, "total_steps": 11784, "loss": 0.033, "lr": 1.2412511505274844e-06, "epoch": 0.4803122878479294, "percentage": 48.03, "elapsed_time": "0:13:54", "remaining_time": "0:15:03", "throughput": 6504.11, "total_tokens": 5429184}
{"current_steps": 5665, "total_steps": 11784, "loss": 0.0589, "lr": 1.2398134519289708e-06, "epoch": 0.4807365919891378, "percentage": 48.07, "elapsed_time": "0:13:55", "remaining_time": "0:15:01", "throughput": 6506.78, "total_tokens": 5433536}
{"current_steps": 5670, "total_steps": 11784, "loss": 0.1094, "lr": 1.2383752272019071e-06, "epoch": 0.48116089613034624, "percentage": 48.12, "elapsed_time": "0:13:55", "remaining_time": "0:15:00", "throughput": 6510.07, "total_tokens": 5438464}
{"current_steps": 5675, "total_steps": 11784, "loss": 0.0679, "lr": 1.2369364795016252e-06, "epoch": 0.48158520027155466, "percentage": 48.16, "elapsed_time": "0:13:55", "remaining_time": "0:14:59", "throughput": 6513.09, "total_tokens": 5443136}
{"current_steps": 5680, "total_steps": 11784, "loss": 0.0332, "lr": 1.2354972119846045e-06, "epoch": 0.4820095044127631, "percentage": 48.2, "elapsed_time": "0:13:56", "remaining_time": "0:14:58", "throughput": 6516.05, "total_tokens": 5447744}
{"current_steps": 5685, "total_steps": 11784, "loss": 0.0926, "lr": 1.2340574278084648e-06, "epoch": 0.4824338085539715, "percentage": 48.24, "elapsed_time": "0:13:56", "remaining_time": "0:14:57", "throughput": 6519.48, "total_tokens": 5452800}
{"current_steps": 5690, "total_steps": 11784, "loss": 0.0565, "lr": 1.23261713013196e-06, "epoch": 0.4828581126951799, "percentage": 48.29, "elapsed_time": "0:13:56", "remaining_time": "0:14:56", "throughput": 6522.51, "total_tokens": 5457472}
{"current_steps": 5695, "total_steps": 11784, "loss": 0.0754, "lr": 1.2311763221149697e-06, "epoch": 0.48328241683638834, "percentage": 48.33, "elapsed_time": "0:13:57", "remaining_time": "0:14:54", "throughput": 6525.66, "total_tokens": 5462272}
{"current_steps": 5700, "total_steps": 11784, "loss": 0.0176, "lr": 1.2297350069184935e-06, "epoch": 0.48370672097759676, "percentage": 48.37, "elapsed_time": "0:13:57", "remaining_time": "0:14:53", "throughput": 6528.6, "total_tokens": 5466880}
{"current_steps": 5705, "total_steps": 11784, "loss": 0.0447, "lr": 1.228293187704644e-06, "epoch": 0.4841310251188052, "percentage": 48.41, "elapsed_time": "0:13:57", "remaining_time": "0:14:52", "throughput": 6531.67, "total_tokens": 5471616}
{"current_steps": 5710, "total_steps": 11784, "loss": 0.0748, "lr": 1.2268508676366393e-06, "epoch": 0.4845553292600136, "percentage": 48.46, "elapsed_time": "0:13:58", "remaining_time": "0:14:51", "throughput": 6534.52, "total_tokens": 5476160}
{"current_steps": 5715, "total_steps": 11784, "loss": 0.1343, "lr": 1.225408049878796e-06, "epoch": 0.484979633401222, "percentage": 48.5, "elapsed_time": "0:13:58", "remaining_time": "0:14:50", "throughput": 6537.65, "total_tokens": 5480960}
{"current_steps": 5720, "total_steps": 11784, "loss": 0.062, "lr": 1.223964737596523e-06, "epoch": 0.48540393754243044, "percentage": 48.54, "elapsed_time": "0:13:58", "remaining_time": "0:14:49", "throughput": 6541.55, "total_tokens": 5486528}
{"current_steps": 5725, "total_steps": 11784, "loss": 0.0411, "lr": 1.2225209339563143e-06, "epoch": 0.4858282416836388, "percentage": 48.58, "elapsed_time": "0:13:59", "remaining_time": "0:14:48", "throughput": 6544.78, "total_tokens": 5491456}
{"current_steps": 5730, "total_steps": 11784, "loss": 0.0602, "lr": 1.2210766421257419e-06, "epoch": 0.4862525458248472, "percentage": 48.63, "elapsed_time": "0:13:59", "remaining_time": "0:14:46", "throughput": 6548.29, "total_tokens": 5496640}
{"current_steps": 5735, "total_steps": 11784, "loss": 0.0293, "lr": 1.2196318652734477e-06, "epoch": 0.48667684996605565, "percentage": 48.67, "elapsed_time": "0:13:59", "remaining_time": "0:14:45", "throughput": 6551.33, "total_tokens": 5501376}
{"current_steps": 5740, "total_steps": 11784, "loss": 0.0521, "lr": 1.2181866065691392e-06, "epoch": 0.48710115410726407, "percentage": 48.71, "elapsed_time": "0:14:00", "remaining_time": "0:14:44", "throughput": 6554.11, "total_tokens": 5505856}
{"current_steps": 5745, "total_steps": 11784, "loss": 0.0564, "lr": 1.2167408691835807e-06, "epoch": 0.4875254582484725, "percentage": 48.75, "elapsed_time": "0:14:00", "remaining_time": "0:14:43", "throughput": 6557.31, "total_tokens": 5510720}
{"current_steps": 5750, "total_steps": 11784, "loss": 0.0466, "lr": 1.2152946562885857e-06, "epoch": 0.4879497623896809, "percentage": 48.79, "elapsed_time": "0:14:00", "remaining_time": "0:14:42", "throughput": 6559.76, "total_tokens": 5514880}
{"current_steps": 5755, "total_steps": 11784, "loss": 0.0491, "lr": 1.2138479710570123e-06, "epoch": 0.48837406653088933, "percentage": 48.84, "elapsed_time": "0:14:01", "remaining_time": "0:14:41", "throughput": 6562.8, "total_tokens": 5519616}
{"current_steps": 5760, "total_steps": 11784, "loss": 0.0656, "lr": 1.2124008166627535e-06, "epoch": 0.48879837067209775, "percentage": 48.88, "elapsed_time": "0:14:01", "remaining_time": "0:14:39", "throughput": 6565.45, "total_tokens": 5523968}
{"current_steps": 5765, "total_steps": 11784, "loss": 0.0673, "lr": 1.2109531962807332e-06, "epoch": 0.48922267481330617, "percentage": 48.92, "elapsed_time": "0:14:01", "remaining_time": "0:14:38", "throughput": 6568.78, "total_tokens": 5528960}
{"current_steps": 5770, "total_steps": 11784, "loss": 0.0817, "lr": 1.2095051130868959e-06, "epoch": 0.4896469789545146, "percentage": 48.96, "elapsed_time": "0:14:02", "remaining_time": "0:14:37", "throughput": 6573.6, "total_tokens": 5535488}
{"current_steps": 5775, "total_steps": 11784, "loss": 0.1018, "lr": 1.2080565702582027e-06, "epoch": 0.490071283095723, "percentage": 49.01, "elapsed_time": "0:14:02", "remaining_time": "0:14:36", "throughput": 6576.68, "total_tokens": 5540288}
{"current_steps": 5780, "total_steps": 11784, "loss": 0.0485, "lr": 1.2066075709726225e-06, "epoch": 0.49049558723693143, "percentage": 49.05, "elapsed_time": "0:14:02", "remaining_time": "0:14:35", "throughput": 6580.51, "total_tokens": 5545792}
{"current_steps": 5785, "total_steps": 11784, "loss": 0.0674, "lr": 1.2051581184091263e-06, "epoch": 0.49091989137813985, "percentage": 49.09, "elapsed_time": "0:14:03", "remaining_time": "0:14:34", "throughput": 6583.36, "total_tokens": 5550336}
{"current_steps": 5790, "total_steps": 11784, "loss": 0.0727, "lr": 1.2037082157476782e-06, "epoch": 0.49134419551934827, "percentage": 49.13, "elapsed_time": "0:14:03", "remaining_time": "0:14:33", "throughput": 6586.64, "total_tokens": 5555328}
{"current_steps": 5795, "total_steps": 11784, "loss": 0.0649, "lr": 1.2022578661692312e-06, "epoch": 0.4917684996605567, "percentage": 49.18, "elapsed_time": "0:14:03", "remaining_time": "0:14:32", "throughput": 6590.51, "total_tokens": 5560896}
{"current_steps": 5800, "total_steps": 11784, "loss": 0.0633, "lr": 1.2008070728557185e-06, "epoch": 0.4921928038017651, "percentage": 49.22, "elapsed_time": "0:14:04", "remaining_time": "0:14:30", "throughput": 6593.73, "total_tokens": 5565824}
{"current_steps": 5805, "total_steps": 11784, "loss": 0.0425, "lr": 1.1993558389900462e-06, "epoch": 0.49261710794297353, "percentage": 49.26, "elapsed_time": "0:14:04", "remaining_time": "0:14:29", "throughput": 6596.54, "total_tokens": 5570368}
{"current_steps": 5810, "total_steps": 11784, "loss": 0.0633, "lr": 1.197904167756087e-06, "epoch": 0.49304141208418195, "percentage": 49.3, "elapsed_time": "0:14:04", "remaining_time": "0:14:28", "throughput": 6599.31, "total_tokens": 5574848}
{"current_steps": 5815, "total_steps": 11784, "loss": 0.0689, "lr": 1.1964520623386741e-06, "epoch": 0.49346571622539037, "percentage": 49.35, "elapsed_time": "0:14:05", "remaining_time": "0:14:27", "throughput": 6602.17, "total_tokens": 5579456}
{"current_steps": 5820, "total_steps": 11784, "loss": 0.0423, "lr": 1.1949995259235919e-06, "epoch": 0.4938900203665988, "percentage": 49.39, "elapsed_time": "0:14:05", "remaining_time": "0:14:26", "throughput": 6605.4, "total_tokens": 5584384}
{"current_steps": 5825, "total_steps": 11784, "loss": 0.123, "lr": 1.1935465616975716e-06, "epoch": 0.4943143245078072, "percentage": 49.43, "elapsed_time": "0:14:05", "remaining_time": "0:14:25", "throughput": 6608.94, "total_tokens": 5589632}
{"current_steps": 5830, "total_steps": 11784, "loss": 0.0281, "lr": 1.192093172848282e-06, "epoch": 0.49473862864901563, "percentage": 49.47, "elapsed_time": "0:14:06", "remaining_time": "0:14:24", "throughput": 6611.63, "total_tokens": 5594048}
{"current_steps": 5835, "total_steps": 11784, "loss": 0.0515, "lr": 1.1906393625643242e-06, "epoch": 0.49516293279022405, "percentage": 49.52, "elapsed_time": "0:14:06", "remaining_time": "0:14:22", "throughput": 6614.57, "total_tokens": 5598720}
{"current_steps": 5840, "total_steps": 11784, "loss": 0.1113, "lr": 1.1891851340352235e-06, "epoch": 0.4955872369314325, "percentage": 49.56, "elapsed_time": "0:14:06", "remaining_time": "0:14:21", "throughput": 6617.23, "total_tokens": 5603136}
{"current_steps": 5845, "total_steps": 11784, "loss": 0.0388, "lr": 1.1877304904514232e-06, "epoch": 0.4960115410726409, "percentage": 49.6, "elapsed_time": "0:14:07", "remaining_time": "0:14:20", "throughput": 6620.25, "total_tokens": 5607872}
{"current_steps": 5850, "total_steps": 11784, "loss": 0.039, "lr": 1.1862754350042764e-06, "epoch": 0.4964358452138493, "percentage": 49.64, "elapsed_time": "0:14:07", "remaining_time": "0:14:19", "throughput": 6622.99, "total_tokens": 5612352}
{"current_steps": 5855, "total_steps": 11784, "loss": 0.077, "lr": 1.1848199708860404e-06, "epoch": 0.4968601493550577, "percentage": 49.69, "elapsed_time": "0:14:07", "remaining_time": "0:14:18", "throughput": 6626.38, "total_tokens": 5617472}
{"current_steps": 5860, "total_steps": 11784, "loss": 0.0934, "lr": 1.183364101289869e-06, "epoch": 0.4972844534962661, "percentage": 49.73, "elapsed_time": "0:14:08", "remaining_time": "0:14:17", "throughput": 6628.98, "total_tokens": 5621824}
{"current_steps": 5865, "total_steps": 11784, "loss": 0.0631, "lr": 1.1819078294098057e-06, "epoch": 0.4977087576374745, "percentage": 49.77, "elapsed_time": "0:14:08", "remaining_time": "0:14:16", "throughput": 6631.69, "total_tokens": 5626304}
{"current_steps": 5870, "total_steps": 11784, "loss": 0.0413, "lr": 1.180451158440776e-06, "epoch": 0.49813306177868294, "percentage": 49.81, "elapsed_time": "0:14:08", "remaining_time": "0:14:15", "throughput": 6635.33, "total_tokens": 5631680}
{"current_steps": 5875, "total_steps": 11784, "loss": 0.115, "lr": 1.1789940915785823e-06, "epoch": 0.49855736591989136, "percentage": 49.86, "elapsed_time": "0:14:09", "remaining_time": "0:14:13", "throughput": 6637.8, "total_tokens": 5635904}
{"current_steps": 5880, "total_steps": 11784, "loss": 0.0422, "lr": 1.177536632019894e-06, "epoch": 0.4989816700610998, "percentage": 49.9, "elapsed_time": "0:14:09", "remaining_time": "0:14:12", "throughput": 6640.66, "total_tokens": 5640512}
{"current_steps": 5885, "total_steps": 11784, "loss": 0.0691, "lr": 1.1760787829622423e-06, "epoch": 0.4994059742023082, "percentage": 49.94, "elapsed_time": "0:14:09", "remaining_time": "0:14:11", "throughput": 6644.83, "total_tokens": 5646464}
{"current_steps": 5890, "total_steps": 11784, "loss": 0.0249, "lr": 1.1746205476040137e-06, "epoch": 0.4998302783435166, "percentage": 49.98, "elapsed_time": "0:14:10", "remaining_time": "0:14:10", "throughput": 6647.63, "total_tokens": 5651008}
{"current_steps": 5895, "total_steps": 11784, "loss": 0.0536, "lr": 1.173161929144442e-06, "epoch": 0.5002545824847251, "percentage": 50.03, "elapsed_time": "0:14:10", "remaining_time": "0:14:09", "throughput": 6650.46, "total_tokens": 5655616}
{"current_steps": 5900, "total_steps": 11784, "loss": 0.0293, "lr": 1.171702930783601e-06, "epoch": 0.5006788866259335, "percentage": 50.07, "elapsed_time": "0:14:10", "remaining_time": "0:14:08", "throughput": 6653.41, "total_tokens": 5660352}
{"current_steps": 5900, "total_steps": 11784, "eval_loss": 0.05498848110437393, "epoch": 0.5006788866259335, "percentage": 50.07, "elapsed_time": "0:14:26", "remaining_time": "0:14:24", "throughput": 6531.54, "total_tokens": 5660352}
{"current_steps": 5905, "total_steps": 11784, "loss": 0.0627, "lr": 1.1702435557223986e-06, "epoch": 0.5011031907671419, "percentage": 50.11, "elapsed_time": "0:15:05", "remaining_time": "0:15:01", "throughput": 6253.95, "total_tokens": 5664832}
{"current_steps": 5910, "total_steps": 11784, "loss": 0.0832, "lr": 1.1687838071625684e-06, "epoch": 0.5015274949083504, "percentage": 50.15, "elapsed_time": "0:15:06", "remaining_time": "0:15:00", "throughput": 6257.13, "total_tokens": 5669824}
{"current_steps": 5915, "total_steps": 11784, "loss": 0.0744, "lr": 1.167323688306664e-06, "epoch": 0.5019517990495588, "percentage": 50.2, "elapsed_time": "0:15:06", "remaining_time": "0:14:59", "throughput": 6259.75, "total_tokens": 5674240}
{"current_steps": 5920, "total_steps": 11784, "loss": 0.0557, "lr": 1.1658632023580515e-06, "epoch": 0.5023761031907671, "percentage": 50.24, "elapsed_time": "0:15:06", "remaining_time": "0:14:58", "throughput": 6262.97, "total_tokens": 5679296}
{"current_steps": 5925, "total_steps": 11784, "loss": 0.0411, "lr": 1.1644023525209014e-06, "epoch": 0.5028004073319755, "percentage": 50.28, "elapsed_time": "0:15:07", "remaining_time": "0:14:57", "throughput": 6265.73, "total_tokens": 5683840}
{"current_steps": 5930, "total_steps": 11784, "loss": 0.0754, "lr": 1.162941142000184e-06, "epoch": 0.5032247114731839, "percentage": 50.32, "elapsed_time": "0:15:07", "remaining_time": "0:14:55", "throughput": 6268.97, "total_tokens": 5688896}
{"current_steps": 5935, "total_steps": 11784, "loss": 0.0428, "lr": 1.1614795740016598e-06, "epoch": 0.5036490156143923, "percentage": 50.36, "elapsed_time": "0:15:07", "remaining_time": "0:14:54", "throughput": 6271.72, "total_tokens": 5693440}
{"current_steps": 5940, "total_steps": 11784, "loss": 0.073, "lr": 1.160017651731874e-06, "epoch": 0.5040733197556008, "percentage": 50.41, "elapsed_time": "0:15:08", "remaining_time": "0:14:53", "throughput": 6274.41, "total_tokens": 5697920}
{"current_steps": 5945, "total_steps": 11784, "loss": 0.0417, "lr": 1.1585553783981486e-06, "epoch": 0.5044976238968092, "percentage": 50.45, "elapsed_time": "0:15:08", "remaining_time": "0:14:52", "throughput": 6277.22, "total_tokens": 5702528}
{"current_steps": 5950, "total_steps": 11784, "loss": 0.0924, "lr": 1.1570927572085766e-06, "epoch": 0.5049219280380176, "percentage": 50.49, "elapsed_time": "0:15:08", "remaining_time": "0:14:51", "throughput": 6280.42, "total_tokens": 5707584}
{"current_steps": 5955, "total_steps": 11784, "loss": 0.046, "lr": 1.1556297913720137e-06, "epoch": 0.505346232179226, "percentage": 50.53, "elapsed_time": "0:15:09", "remaining_time": "0:14:49", "throughput": 6283.19, "total_tokens": 5712192}
{"current_steps": 5960, "total_steps": 11784, "loss": 0.1587, "lr": 1.1541664840980715e-06, "epoch": 0.5057705363204344, "percentage": 50.58, "elapsed_time": "0:15:09", "remaining_time": "0:14:48", "throughput": 6286.77, "total_tokens": 5717632}
{"current_steps": 5965, "total_steps": 11784, "loss": 0.0854, "lr": 1.1527028385971107e-06, "epoch": 0.5061948404616429, "percentage": 50.62, "elapsed_time": "0:15:09", "remaining_time": "0:14:47", "throughput": 6289.51, "total_tokens": 5722176}
{"current_steps": 5970, "total_steps": 11784, "loss": 0.0459, "lr": 1.1512388580802348e-06, "epoch": 0.5066191446028513, "percentage": 50.66, "elapsed_time": "0:15:10", "remaining_time": "0:14:46", "throughput": 6292.25, "total_tokens": 5726720}
{"current_steps": 5975, "total_steps": 11784, "loss": 0.0672, "lr": 1.1497745457592815e-06, "epoch": 0.5070434487440597, "percentage": 50.7, "elapsed_time": "0:15:10", "remaining_time": "0:14:45", "throughput": 6295.06, "total_tokens": 5731328}
{"current_steps": 5980, "total_steps": 11784, "loss": 0.0614, "lr": 1.1483099048468168e-06, "epoch": 0.5074677528852681, "percentage": 50.75, "elapsed_time": "0:15:10", "remaining_time": "0:14:43", "throughput": 6298.14, "total_tokens": 5736256}
{"current_steps": 5985, "total_steps": 11784, "loss": 0.0764, "lr": 1.1468449385561272e-06, "epoch": 0.5078920570264766, "percentage": 50.79, "elapsed_time": "0:15:11", "remaining_time": "0:14:42", "throughput": 6301.26, "total_tokens": 5741248}
{"current_steps": 5990, "total_steps": 11784, "loss": 0.0344, "lr": 1.145379650101214e-06, "epoch": 0.508316361167685, "percentage": 50.83, "elapsed_time": "0:15:11", "remaining_time": "0:14:41", "throughput": 6304.47, "total_tokens": 5746304}
{"current_steps": 5995, "total_steps": 11784, "loss": 0.097, "lr": 1.143914042696784e-06, "epoch": 0.5087406653088934, "percentage": 50.87, "elapsed_time": "0:15:11", "remaining_time": "0:14:40", "throughput": 6307.85, "total_tokens": 5751552}
{"current_steps": 6000, "total_steps": 11784, "loss": 0.0568, "lr": 1.1424481195582445e-06, "epoch": 0.5091649694501018, "percentage": 50.92, "elapsed_time": "0:15:12", "remaining_time": "0:14:39", "throughput": 6310.52, "total_tokens": 5756032}
{"current_steps": 6005, "total_steps": 11784, "loss": 0.0818, "lr": 1.1409818839016958e-06, "epoch": 0.5095892735913102, "percentage": 50.96, "elapsed_time": "0:15:12", "remaining_time": "0:14:38", "throughput": 6314.2, "total_tokens": 5761600}
{"current_steps": 6010, "total_steps": 11784, "loss": 0.0286, "lr": 1.1395153389439231e-06, "epoch": 0.5100135777325187, "percentage": 51.0, "elapsed_time": "0:15:12", "remaining_time": "0:14:36", "throughput": 6317.1, "total_tokens": 5766336}
{"current_steps": 6015, "total_steps": 11784, "loss": 0.0889, "lr": 1.1380484879023903e-06, "epoch": 0.5104378818737271, "percentage": 51.04, "elapsed_time": "0:15:13", "remaining_time": "0:14:35", "throughput": 6320.3, "total_tokens": 5771392}
{"current_steps": 6020, "total_steps": 11784, "loss": 0.0375, "lr": 1.1365813339952334e-06, "epoch": 0.5108621860149355, "percentage": 51.09, "elapsed_time": "0:15:13", "remaining_time": "0:14:34", "throughput": 6322.88, "total_tokens": 5775808}
{"current_steps": 6025, "total_steps": 11784, "loss": 0.0905, "lr": 1.1351138804412524e-06, "epoch": 0.5112864901561439, "percentage": 51.13, "elapsed_time": "0:15:13", "remaining_time": "0:14:33", "throughput": 6325.97, "total_tokens": 5780800}
{"current_steps": 6030, "total_steps": 11784, "loss": 0.031, "lr": 1.1336461304599047e-06, "epoch": 0.5117107942973523, "percentage": 51.17, "elapsed_time": "0:15:14", "remaining_time": "0:14:32", "throughput": 6329.53, "total_tokens": 5786304}
{"current_steps": 6035, "total_steps": 11784, "loss": 0.0295, "lr": 1.1321780872712983e-06, "epoch": 0.5121350984385608, "percentage": 51.21, "elapsed_time": "0:15:14", "remaining_time": "0:14:31", "throughput": 6332.72, "total_tokens": 5791360}
{"current_steps": 6040, "total_steps": 11784, "loss": 0.019, "lr": 1.1307097540961838e-06, "epoch": 0.5125594025797692, "percentage": 51.26, "elapsed_time": "0:15:14", "remaining_time": "0:14:30", "throughput": 6335.34, "total_tokens": 5795840}
{"current_steps": 6045, "total_steps": 11784, "loss": 0.0386, "lr": 1.129241134155949e-06, "epoch": 0.5129837067209776, "percentage": 51.3, "elapsed_time": "0:15:15", "remaining_time": "0:14:28", "throughput": 6338.21, "total_tokens": 5800576}
{"current_steps": 6050, "total_steps": 11784, "loss": 0.0621, "lr": 1.1277722306726103e-06, "epoch": 0.513408010862186, "percentage": 51.34, "elapsed_time": "0:15:15", "remaining_time": "0:14:27", "throughput": 6341.38, "total_tokens": 5805632}
{"current_steps": 6055, "total_steps": 11784, "loss": 0.0254, "lr": 1.1263030468688057e-06, "epoch": 0.5138323150033944, "percentage": 51.38, "elapsed_time": "0:15:15", "remaining_time": "0:14:26", "throughput": 6344.56, "total_tokens": 5810688}
{"current_steps": 6060, "total_steps": 11784, "loss": 0.0513, "lr": 1.1248335859677891e-06, "epoch": 0.5142566191446029, "percentage": 51.43, "elapsed_time": "0:15:16", "remaining_time": "0:14:25", "throughput": 6347.6, "total_tokens": 5815616}
{"current_steps": 6065, "total_steps": 11784, "loss": 0.0772, "lr": 1.1233638511934218e-06, "epoch": 0.5146809232858113, "percentage": 51.47, "elapsed_time": "0:15:16", "remaining_time": "0:14:24", "throughput": 6350.75, "total_tokens": 5820672}
{"current_steps": 6070, "total_steps": 11784, "loss": 0.0595, "lr": 1.121893845770166e-06, "epoch": 0.5151052274270197, "percentage": 51.51, "elapsed_time": "0:15:16", "remaining_time": "0:14:23", "throughput": 6353.13, "total_tokens": 5824896}
{"current_steps": 6075, "total_steps": 11784, "loss": 0.0458, "lr": 1.120423572923078e-06, "epoch": 0.5155295315682281, "percentage": 51.55, "elapsed_time": "0:15:17", "remaining_time": "0:14:21", "throughput": 6355.98, "total_tokens": 5829632}
{"current_steps": 6080, "total_steps": 11784, "loss": 0.0292, "lr": 1.1189530358778004e-06, "epoch": 0.5159538357094365, "percentage": 51.6, "elapsed_time": "0:15:17", "remaining_time": "0:14:20", "throughput": 6358.68, "total_tokens": 5834240}
{"current_steps": 6085, "total_steps": 11784, "loss": 0.0951, "lr": 1.1174822378605551e-06, "epoch": 0.516378139850645, "percentage": 51.64, "elapsed_time": "0:15:17", "remaining_time": "0:14:19", "throughput": 6361.35, "total_tokens": 5838784}
{"current_steps": 6090, "total_steps": 11784, "loss": 0.0588, "lr": 1.116011182098138e-06, "epoch": 0.5168024439918534, "percentage": 51.68, "elapsed_time": "0:15:18", "remaining_time": "0:14:18", "throughput": 6363.75, "total_tokens": 5843072}
{"current_steps": 6095, "total_steps": 11784, "loss": 0.0476, "lr": 1.1145398718179085e-06, "epoch": 0.5172267481330618, "percentage": 51.72, "elapsed_time": "0:15:18", "remaining_time": "0:14:17", "throughput": 6366.19, "total_tokens": 5847360}
{"current_steps": 6100, "total_steps": 11784, "loss": 0.019, "lr": 1.1130683102477862e-06, "epoch": 0.5176510522742702, "percentage": 51.77, "elapsed_time": "0:15:18", "remaining_time": "0:14:16", "throughput": 6369.14, "total_tokens": 5852224}
{"current_steps": 6105, "total_steps": 11784, "loss": 0.0241, "lr": 1.1115965006162405e-06, "epoch": 0.5180753564154786, "percentage": 51.81, "elapsed_time": "0:15:19", "remaining_time": "0:14:15", "throughput": 6372.14, "total_tokens": 5857152}
{"current_steps": 6110, "total_steps": 11784, "loss": 0.1214, "lr": 1.110124446152286e-06, "epoch": 0.5184996605566871, "percentage": 51.85, "elapsed_time": "0:15:19", "remaining_time": "0:14:13", "throughput": 6374.98, "total_tokens": 5861888}
{"current_steps": 6115, "total_steps": 11784, "loss": 0.1294, "lr": 1.1086521500854744e-06, "epoch": 0.5189239646978955, "percentage": 51.89, "elapsed_time": "0:15:19", "remaining_time": "0:14:12", "throughput": 6377.72, "total_tokens": 5866496}
{"current_steps": 6120, "total_steps": 11784, "loss": 0.0606, "lr": 1.1071796156458868e-06, "epoch": 0.5193482688391039, "percentage": 51.93, "elapsed_time": "0:15:20", "remaining_time": "0:14:11", "throughput": 6380.25, "total_tokens": 5870912}
{"current_steps": 6125, "total_steps": 11784, "loss": 0.0881, "lr": 1.1057068460641281e-06, "epoch": 0.5197725729803123, "percentage": 51.98, "elapsed_time": "0:15:20", "remaining_time": "0:14:10", "throughput": 6384.04, "total_tokens": 5876672}
{"current_steps": 6130, "total_steps": 11784, "loss": 0.0278, "lr": 1.1042338445713183e-06, "epoch": 0.5201968771215207, "percentage": 52.02, "elapsed_time": "0:15:20", "remaining_time": "0:14:09", "throughput": 6386.51, "total_tokens": 5881024}
{"current_steps": 6135, "total_steps": 11784, "loss": 0.1703, "lr": 1.1027606143990867e-06, "epoch": 0.5206211812627292, "percentage": 52.06, "elapsed_time": "0:15:21", "remaining_time": "0:14:08", "throughput": 6389.67, "total_tokens": 5886080}
{"current_steps": 6140, "total_steps": 11784, "loss": 0.0505, "lr": 1.1012871587795638e-06, "epoch": 0.5210454854039376, "percentage": 52.1, "elapsed_time": "0:15:21", "remaining_time": "0:14:07", "throughput": 6392.57, "total_tokens": 5890880}
{"current_steps": 6145, "total_steps": 11784, "loss": 0.0369, "lr": 1.0998134809453756e-06, "epoch": 0.521469789545146, "percentage": 52.15, "elapsed_time": "0:15:21", "remaining_time": "0:14:05", "throughput": 6395.22, "total_tokens": 5895424}
{"current_steps": 6150, "total_steps": 11784, "loss": 0.0887, "lr": 1.0983395841296347e-06, "epoch": 0.5218940936863544, "percentage": 52.19, "elapsed_time": "0:15:22", "remaining_time": "0:14:04", "throughput": 6398.22, "total_tokens": 5900352}
{"current_steps": 6155, "total_steps": 11784, "loss": 0.0695, "lr": 1.0968654715659347e-06, "epoch": 0.5223183978275628, "percentage": 52.23, "elapsed_time": "0:15:22", "remaining_time": "0:14:03", "throughput": 6400.94, "total_tokens": 5904960}
{"current_steps": 6160, "total_steps": 11784, "loss": 0.0687, "lr": 1.095391146488342e-06, "epoch": 0.5227427019687713, "percentage": 52.27, "elapsed_time": "0:15:22", "remaining_time": "0:14:02", "throughput": 6404.06, "total_tokens": 5910016}
{"current_steps": 6165, "total_steps": 11784, "loss": 0.0779, "lr": 1.09391661213139e-06, "epoch": 0.5231670061099797, "percentage": 52.32, "elapsed_time": "0:15:23", "remaining_time": "0:14:01", "throughput": 6407.07, "total_tokens": 5914944}
{"current_steps": 6170, "total_steps": 11784, "loss": 0.0389, "lr": 1.0924418717300707e-06, "epoch": 0.5235913102511881, "percentage": 52.36, "elapsed_time": "0:15:23", "remaining_time": "0:14:00", "throughput": 6410.61, "total_tokens": 5920448}
{"current_steps": 6175, "total_steps": 11784, "loss": 0.0357, "lr": 1.090966928519828e-06, "epoch": 0.5240156143923965, "percentage": 52.4, "elapsed_time": "0:15:23", "remaining_time": "0:13:59", "throughput": 6413.9, "total_tokens": 5925696}
{"current_steps": 6180, "total_steps": 11784, "loss": 0.0356, "lr": 1.0894917857365511e-06, "epoch": 0.5244399185336049, "percentage": 52.44, "elapsed_time": "0:15:24", "remaining_time": "0:13:58", "throughput": 6416.87, "total_tokens": 5930624}
{"current_steps": 6185, "total_steps": 11784, "loss": 0.0751, "lr": 1.0880164466165673e-06, "epoch": 0.5248642226748133, "percentage": 52.49, "elapsed_time": "0:15:24", "remaining_time": "0:13:56", "throughput": 6419.49, "total_tokens": 5935168}
{"current_steps": 6190, "total_steps": 11784, "loss": 0.0332, "lr": 1.0865409143966338e-06, "epoch": 0.5252885268160217, "percentage": 52.53, "elapsed_time": "0:15:24", "remaining_time": "0:13:55", "throughput": 6422.1, "total_tokens": 5939712}
{"current_steps": 6195, "total_steps": 11784, "loss": 0.0108, "lr": 1.0850651923139317e-06, "epoch": 0.5257128309572301, "percentage": 52.57, "elapsed_time": "0:15:25", "remaining_time": "0:13:54", "throughput": 6425.02, "total_tokens": 5944576}
{"current_steps": 6200, "total_steps": 11784, "loss": 0.0517, "lr": 1.0835892836060598e-06, "epoch": 0.5261371350984385, "percentage": 52.61, "elapsed_time": "0:15:25", "remaining_time": "0:13:53", "throughput": 6427.69, "total_tokens": 5949184}
{"current_steps": 6205, "total_steps": 11784, "loss": 0.0215, "lr": 1.0821131915110246e-06, "epoch": 0.5265614392396469, "percentage": 52.66, "elapsed_time": "0:15:25", "remaining_time": "0:13:52", "throughput": 6430.71, "total_tokens": 5954176}
{"current_steps": 6210, "total_steps": 11784, "loss": 0.0753, "lr": 1.080636919267236e-06, "epoch": 0.5269857433808554, "percentage": 52.7, "elapsed_time": "0:15:26", "remaining_time": "0:13:51", "throughput": 6433.27, "total_tokens": 5958656}
{"current_steps": 6215, "total_steps": 11784, "loss": 0.0789, "lr": 1.079160470113499e-06, "epoch": 0.5274100475220638, "percentage": 52.74, "elapsed_time": "0:15:26", "remaining_time": "0:13:50", "throughput": 6435.96, "total_tokens": 5963264}
{"current_steps": 6220, "total_steps": 11784, "loss": 0.0936, "lr": 1.0776838472890064e-06, "epoch": 0.5278343516632722, "percentage": 52.78, "elapsed_time": "0:15:26", "remaining_time": "0:13:49", "throughput": 6439.27, "total_tokens": 5968576}
{"current_steps": 6225, "total_steps": 11784, "loss": 0.0034, "lr": 1.0762070540333322e-06, "epoch": 0.5282586558044806, "percentage": 52.83, "elapsed_time": "0:15:27", "remaining_time": "0:13:48", "throughput": 6442.0, "total_tokens": 5973248}
{"current_steps": 6230, "total_steps": 11784, "loss": 0.0488, "lr": 1.0747300935864243e-06, "epoch": 0.528682959945689, "percentage": 52.87, "elapsed_time": "0:15:27", "remaining_time": "0:13:46", "throughput": 6444.69, "total_tokens": 5977920}
{"current_steps": 6235, "total_steps": 11784, "loss": 0.0588, "lr": 1.0732529691885977e-06, "epoch": 0.5291072640868975, "percentage": 52.91, "elapsed_time": "0:15:27", "remaining_time": "0:13:45", "throughput": 6447.43, "total_tokens": 5982656}
{"current_steps": 6240, "total_steps": 11784, "loss": 0.0431, "lr": 1.0717756840805263e-06, "epoch": 0.5295315682281059, "percentage": 52.95, "elapsed_time": "0:15:28", "remaining_time": "0:13:44", "throughput": 6450.2, "total_tokens": 5987392}
{"current_steps": 6245, "total_steps": 11784, "loss": 0.0505, "lr": 1.0702982415032378e-06, "epoch": 0.5299558723693143, "percentage": 53.0, "elapsed_time": "0:15:28", "remaining_time": "0:13:43", "throughput": 6454.05, "total_tokens": 5993280}
{"current_steps": 6250, "total_steps": 11784, "loss": 0.0423, "lr": 1.068820644698104e-06, "epoch": 0.5303801765105227, "percentage": 53.04, "elapsed_time": "0:15:28", "remaining_time": "0:13:42", "throughput": 6457.05, "total_tokens": 5998272}
{"current_steps": 6255, "total_steps": 11784, "loss": 0.023, "lr": 1.0673428969068363e-06, "epoch": 0.5308044806517311, "percentage": 53.08, "elapsed_time": "0:15:29", "remaining_time": "0:13:41", "throughput": 6459.65, "total_tokens": 6002816}
{"current_steps": 6260, "total_steps": 11784, "loss": 0.028, "lr": 1.0658650013714765e-06, "epoch": 0.5312287847929396, "percentage": 53.12, "elapsed_time": "0:15:29", "remaining_time": "0:13:40", "throughput": 6462.61, "total_tokens": 6007744}
{"current_steps": 6265, "total_steps": 11784, "loss": 0.099, "lr": 1.0643869613343906e-06, "epoch": 0.531653088934148, "percentage": 53.17, "elapsed_time": "0:15:29", "remaining_time": "0:13:39", "throughput": 6464.7, "total_tokens": 6011776}
{"current_steps": 6270, "total_steps": 11784, "loss": 0.0939, "lr": 1.062908780038262e-06, "epoch": 0.5320773930753564, "percentage": 53.21, "elapsed_time": "0:15:30", "remaining_time": "0:13:38", "throughput": 6468.21, "total_tokens": 6017344}
{"current_steps": 6275, "total_steps": 11784, "loss": 0.0401, "lr": 1.0614304607260843e-06, "epoch": 0.5325016972165648, "percentage": 53.25, "elapsed_time": "0:15:30", "remaining_time": "0:13:37", "throughput": 6471.03, "total_tokens": 6022144}
{"current_steps": 6280, "total_steps": 11784, "loss": 0.0351, "lr": 1.0599520066411529e-06, "epoch": 0.5329260013577732, "percentage": 53.29, "elapsed_time": "0:15:30", "remaining_time": "0:13:35", "throughput": 6474.55, "total_tokens": 6027712}
{"current_steps": 6285, "total_steps": 11784, "loss": 0.0586, "lr": 1.0584734210270597e-06, "epoch": 0.5333503054989817, "percentage": 53.34, "elapsed_time": "0:15:31", "remaining_time": "0:13:34", "throughput": 6476.9, "total_tokens": 6032064}
{"current_steps": 6290, "total_steps": 11784, "loss": 0.0382, "lr": 1.0569947071276845e-06, "epoch": 0.5337746096401901, "percentage": 53.38, "elapsed_time": "0:15:31", "remaining_time": "0:13:33", "throughput": 6479.16, "total_tokens": 6036288}
{"current_steps": 6295, "total_steps": 11784, "loss": 0.0912, "lr": 1.0555158681871897e-06, "epoch": 0.5341989137813985, "percentage": 53.42, "elapsed_time": "0:15:31", "remaining_time": "0:13:32", "throughput": 6481.87, "total_tokens": 6040960}
{"current_steps": 6300, "total_steps": 11784, "loss": 0.0313, "lr": 1.0540369074500103e-06, "epoch": 0.5346232179226069, "percentage": 53.46, "elapsed_time": "0:15:32", "remaining_time": "0:13:31", "throughput": 6484.31, "total_tokens": 6045376}
{"current_steps": 6305, "total_steps": 11784, "loss": 0.0809, "lr": 1.0525578281608503e-06, "epoch": 0.5350475220638153, "percentage": 53.5, "elapsed_time": "0:15:32", "remaining_time": "0:13:30", "throughput": 6486.83, "total_tokens": 6049856}
{"current_steps": 6310, "total_steps": 11784, "loss": 0.0089, "lr": 1.0510786335646725e-06, "epoch": 0.5354718262050238, "percentage": 53.55, "elapsed_time": "0:15:32", "remaining_time": "0:13:29", "throughput": 6489.17, "total_tokens": 6054144}
{"current_steps": 6315, "total_steps": 11784, "loss": 0.0477, "lr": 1.0495993269066935e-06, "epoch": 0.5358961303462322, "percentage": 53.59, "elapsed_time": "0:15:33", "remaining_time": "0:13:28", "throughput": 6492.95, "total_tokens": 6060032}
{"current_steps": 6320, "total_steps": 11784, "loss": 0.132, "lr": 1.0481199114323746e-06, "epoch": 0.5363204344874406, "percentage": 53.63, "elapsed_time": "0:15:33", "remaining_time": "0:13:27", "throughput": 6496.11, "total_tokens": 6065280}
{"current_steps": 6325, "total_steps": 11784, "loss": 0.0846, "lr": 1.0466403903874175e-06, "epoch": 0.536744738628649, "percentage": 53.67, "elapsed_time": "0:15:34", "remaining_time": "0:13:26", "throughput": 6498.88, "total_tokens": 6070080}
{"current_steps": 6330, "total_steps": 11784, "loss": 0.0642, "lr": 1.0451607670177543e-06, "epoch": 0.5371690427698574, "percentage": 53.72, "elapsed_time": "0:15:34", "remaining_time": "0:13:25", "throughput": 6502.69, "total_tokens": 6076032}
{"current_steps": 6335, "total_steps": 11784, "loss": 0.0577, "lr": 1.0436810445695421e-06, "epoch": 0.5375933469110659, "percentage": 53.76, "elapsed_time": "0:15:34", "remaining_time": "0:13:23", "throughput": 6505.43, "total_tokens": 6080768}
{"current_steps": 6340, "total_steps": 11784, "loss": 0.0294, "lr": 1.0422012262891548e-06, "epoch": 0.5380176510522743, "percentage": 53.8, "elapsed_time": "0:15:35", "remaining_time": "0:13:22", "throughput": 6507.99, "total_tokens": 6085312}
{"current_steps": 6345, "total_steps": 11784, "loss": 0.0297, "lr": 1.0407213154231774e-06, "epoch": 0.5384419551934827, "percentage": 53.84, "elapsed_time": "0:15:35", "remaining_time": "0:13:21", "throughput": 6510.74, "total_tokens": 6090048}
{"current_steps": 6350, "total_steps": 11784, "loss": 0.0992, "lr": 1.0392413152183973e-06, "epoch": 0.5388662593346911, "percentage": 53.89, "elapsed_time": "0:15:35", "remaining_time": "0:13:20", "throughput": 6513.38, "total_tokens": 6094720}
{"current_steps": 6355, "total_steps": 11784, "loss": 0.1116, "lr": 1.0377612289217982e-06, "epoch": 0.5392905634758995, "percentage": 53.93, "elapsed_time": "0:15:36", "remaining_time": "0:13:19", "throughput": 6516.06, "total_tokens": 6099456}
{"current_steps": 6360, "total_steps": 11784, "loss": 0.033, "lr": 1.0362810597805524e-06, "epoch": 0.539714867617108, "percentage": 53.97, "elapsed_time": "0:15:36", "remaining_time": "0:13:18", "throughput": 6518.99, "total_tokens": 6104448}
{"current_steps": 6365, "total_steps": 11784, "loss": 0.0312, "lr": 1.0348008110420149e-06, "epoch": 0.5401391717583164, "percentage": 54.01, "elapsed_time": "0:15:36", "remaining_time": "0:13:17", "throughput": 6521.57, "total_tokens": 6109056}
{"current_steps": 6370, "total_steps": 11784, "loss": 0.088, "lr": 1.0333204859537142e-06, "epoch": 0.5405634758995248, "percentage": 54.06, "elapsed_time": "0:15:37", "remaining_time": "0:13:16", "throughput": 6524.92, "total_tokens": 6114496}
{"current_steps": 6375, "total_steps": 11784, "loss": 0.0882, "lr": 1.0318400877633466e-06, "epoch": 0.5409877800407332, "percentage": 54.1, "elapsed_time": "0:15:37", "remaining_time": "0:13:15", "throughput": 6527.75, "total_tokens": 6119360}
{"current_steps": 6380, "total_steps": 11784, "loss": 0.0926, "lr": 1.030359619718769e-06, "epoch": 0.5414120841819416, "percentage": 54.14, "elapsed_time": "0:15:37", "remaining_time": "0:13:14", "throughput": 6530.73, "total_tokens": 6124352}
{"current_steps": 6385, "total_steps": 11784, "loss": 0.0509, "lr": 1.0288790850679916e-06, "epoch": 0.5418363883231501, "percentage": 54.18, "elapsed_time": "0:15:38", "remaining_time": "0:13:13", "throughput": 6533.24, "total_tokens": 6128832}
{"current_steps": 6390, "total_steps": 11784, "loss": 0.1019, "lr": 1.0273984870591706e-06, "epoch": 0.5422606924643585, "percentage": 54.23, "elapsed_time": "0:15:38", "remaining_time": "0:13:12", "throughput": 6535.7, "total_tokens": 6133312}
{"current_steps": 6395, "total_steps": 11784, "loss": 0.0668, "lr": 1.025917828940601e-06, "epoch": 0.5426849966055669, "percentage": 54.27, "elapsed_time": "0:15:38", "remaining_time": "0:13:11", "throughput": 6537.98, "total_tokens": 6137600}
{"current_steps": 6400, "total_steps": 11784, "loss": 0.0544, "lr": 1.02443711396071e-06, "epoch": 0.5431093007467753, "percentage": 54.31, "elapsed_time": "0:15:39", "remaining_time": "0:13:10", "throughput": 6540.78, "total_tokens": 6142464}
{"current_steps": 6405, "total_steps": 11784, "loss": 0.0586, "lr": 1.0229563453680495e-06, "epoch": 0.5435336048879837, "percentage": 54.35, "elapsed_time": "0:15:39", "remaining_time": "0:13:08", "throughput": 6543.37, "total_tokens": 6147072}
{"current_steps": 6410, "total_steps": 11784, "loss": 0.045, "lr": 1.021475526411289e-06, "epoch": 0.5439579090291922, "percentage": 54.4, "elapsed_time": "0:15:39", "remaining_time": "0:13:07", "throughput": 6546.01, "total_tokens": 6151744}
{"current_steps": 6415, "total_steps": 11784, "loss": 0.085, "lr": 1.0199946603392078e-06, "epoch": 0.5443822131704006, "percentage": 54.44, "elapsed_time": "0:15:40", "remaining_time": "0:13:06", "throughput": 6548.9, "total_tokens": 6156672}
{"current_steps": 6420, "total_steps": 11784, "loss": 0.0563, "lr": 1.01851375040069e-06, "epoch": 0.544806517311609, "percentage": 54.48, "elapsed_time": "0:15:40", "remaining_time": "0:13:05", "throughput": 6551.76, "total_tokens": 6161600}
{"current_steps": 6425, "total_steps": 11784, "loss": 0.0312, "lr": 1.0170327998447149e-06, "epoch": 0.5452308214528174, "percentage": 54.52, "elapsed_time": "0:15:40", "remaining_time": "0:13:04", "throughput": 6553.91, "total_tokens": 6165760}
{"current_steps": 6430, "total_steps": 11784, "loss": 0.0114, "lr": 1.015551811920351e-06, "epoch": 0.5456551255940258, "percentage": 54.57, "elapsed_time": "0:15:41", "remaining_time": "0:13:03", "throughput": 6560.49, "total_tokens": 6174912}
{"current_steps": 6435, "total_steps": 11784, "loss": 0.0856, "lr": 1.014070789876749e-06, "epoch": 0.5460794297352343, "percentage": 54.61, "elapsed_time": "0:15:41", "remaining_time": "0:13:02", "throughput": 6562.68, "total_tokens": 6179136}
{"current_steps": 6440, "total_steps": 11784, "loss": 0.1228, "lr": 1.0125897369631342e-06, "epoch": 0.5465037338764427, "percentage": 54.65, "elapsed_time": "0:15:41", "remaining_time": "0:13:01", "throughput": 6565.2, "total_tokens": 6183680}
{"current_steps": 6445, "total_steps": 11784, "loss": 0.0587, "lr": 1.0111086564288003e-06, "epoch": 0.546928038017651, "percentage": 54.69, "elapsed_time": "0:15:42", "remaining_time": "0:13:00", "throughput": 6568.05, "total_tokens": 6188608}
{"current_steps": 6450, "total_steps": 11784, "loss": 0.0592, "lr": 1.009627551523101e-06, "epoch": 0.5473523421588594, "percentage": 54.74, "elapsed_time": "0:15:42", "remaining_time": "0:12:59", "throughput": 6570.98, "total_tokens": 6193600}
{"current_steps": 6455, "total_steps": 11784, "loss": 0.0367, "lr": 1.008146425495443e-06, "epoch": 0.5477766463000678, "percentage": 54.78, "elapsed_time": "0:15:42", "remaining_time": "0:12:58", "throughput": 6573.83, "total_tokens": 6198528}
{"current_steps": 6460, "total_steps": 11784, "loss": 0.0359, "lr": 1.0066652815952805e-06, "epoch": 0.5482009504412763, "percentage": 54.82, "elapsed_time": "0:15:43", "remaining_time": "0:12:57", "throughput": 6577.26, "total_tokens": 6204096}
{"current_steps": 6465, "total_steps": 11784, "loss": 0.0465, "lr": 1.0051841230721063e-06, "epoch": 0.5486252545824847, "percentage": 54.86, "elapsed_time": "0:15:43", "remaining_time": "0:12:56", "throughput": 6579.8, "total_tokens": 6208704}
{"current_steps": 6470, "total_steps": 11784, "loss": 0.1061, "lr": 1.0037029531754453e-06, "epoch": 0.5490495587236931, "percentage": 54.9, "elapsed_time": "0:15:43", "remaining_time": "0:12:55", "throughput": 6582.46, "total_tokens": 6213440}
{"current_steps": 6475, "total_steps": 11784, "loss": 0.0551, "lr": 1.002221775154847e-06, "epoch": 0.5494738628649015, "percentage": 54.95, "elapsed_time": "0:15:44", "remaining_time": "0:12:54", "throughput": 6585.31, "total_tokens": 6218368}
{"current_steps": 6480, "total_steps": 11784, "loss": 0.0618, "lr": 1.0007405922598793e-06, "epoch": 0.5498981670061099, "percentage": 54.99, "elapsed_time": "0:15:44", "remaining_time": "0:12:53", "throughput": 6588.41, "total_tokens": 6223616}
{"current_steps": 6485, "total_steps": 11784, "loss": 0.0938, "lr": 9.992594077401208e-07, "epoch": 0.5503224711473184, "percentage": 55.03, "elapsed_time": "0:15:44", "remaining_time": "0:12:52", "throughput": 6591.15, "total_tokens": 6228480}
{"current_steps": 6490, "total_steps": 11784, "loss": 0.0534, "lr": 9.977782248451534e-07, "epoch": 0.5507467752885268, "percentage": 55.07, "elapsed_time": "0:15:45", "remaining_time": "0:12:51", "throughput": 6593.5, "total_tokens": 6232896}
{"current_steps": 6490, "total_steps": 11784, "eval_loss": 0.05577274411916733, "epoch": 0.5507467752885268, "percentage": 55.07, "elapsed_time": "0:16:01", "remaining_time": "0:13:04", "throughput": 6484.94, "total_tokens": 6232896}
{"current_steps": 6495, "total_steps": 11784, "loss": 0.0959, "lr": 9.962970468245548e-07, "epoch": 0.5511710794297352, "percentage": 55.12, "elapsed_time": "0:16:31", "remaining_time": "0:13:27", "throughput": 6290.9, "total_tokens": 6237696}
{"current_steps": 6500, "total_steps": 11784, "loss": 0.0324, "lr": 9.948158769278939e-07, "epoch": 0.5515953835709436, "percentage": 55.16, "elapsed_time": "0:16:31", "remaining_time": "0:13:26", "throughput": 6293.45, "total_tokens": 6242304}
{"current_steps": 6505, "total_steps": 11784, "loss": 0.0393, "lr": 9.933347184047194e-07, "epoch": 0.552019687712152, "percentage": 55.2, "elapsed_time": "0:16:32", "remaining_time": "0:13:25", "throughput": 6296.07, "total_tokens": 6246976}
{"current_steps": 6510, "total_steps": 11784, "loss": 0.0629, "lr": 9.918535745045571e-07, "epoch": 0.5524439918533605, "percentage": 55.24, "elapsed_time": "0:16:32", "remaining_time": "0:13:24", "throughput": 6298.35, "total_tokens": 6251264}
{"current_steps": 6515, "total_steps": 11784, "loss": 0.0104, "lr": 9.903724484768991e-07, "epoch": 0.5528682959945689, "percentage": 55.29, "elapsed_time": "0:16:32", "remaining_time": "0:13:22", "throughput": 6300.88, "total_tokens": 6255872}
{"current_steps": 6520, "total_steps": 11784, "loss": 0.0381, "lr": 9.888913435711996e-07, "epoch": 0.5532926001357773, "percentage": 55.33, "elapsed_time": "0:16:33", "remaining_time": "0:13:21", "throughput": 6303.8, "total_tokens": 6260928}
{"current_steps": 6525, "total_steps": 11784, "loss": 0.04, "lr": 9.874102630368658e-07, "epoch": 0.5537169042769857, "percentage": 55.37, "elapsed_time": "0:16:33", "remaining_time": "0:13:20", "throughput": 6306.39, "total_tokens": 6265600}
{"current_steps": 6530, "total_steps": 11784, "loss": 0.113, "lr": 9.859292101232514e-07, "epoch": 0.5541412084181941, "percentage": 55.41, "elapsed_time": "0:16:33", "remaining_time": "0:13:19", "throughput": 6309.16, "total_tokens": 6270464}
{"current_steps": 6535, "total_steps": 11784, "loss": 0.0957, "lr": 9.84448188079649e-07, "epoch": 0.5545655125594026, "percentage": 55.46, "elapsed_time": "0:16:34", "remaining_time": "0:13:18", "throughput": 6311.56, "total_tokens": 6274944}
{"current_steps": 6540, "total_steps": 11784, "loss": 0.0578, "lr": 9.829672001552853e-07, "epoch": 0.554989816700611, "percentage": 55.5, "elapsed_time": "0:16:34", "remaining_time": "0:13:17", "throughput": 6313.98, "total_tokens": 6279424}
{"current_steps": 6545, "total_steps": 11784, "loss": 0.1313, "lr": 9.8148624959931e-07, "epoch": 0.5554141208418194, "percentage": 55.54, "elapsed_time": "0:16:34", "remaining_time": "0:13:16", "throughput": 6316.58, "total_tokens": 6284096}
{"current_steps": 6550, "total_steps": 11784, "loss": 0.03, "lr": 9.80005339660792e-07, "epoch": 0.5558384249830278, "percentage": 55.58, "elapsed_time": "0:16:35", "remaining_time": "0:13:15", "throughput": 6319.98, "total_tokens": 6289728}
{"current_steps": 6555, "total_steps": 11784, "loss": 0.0289, "lr": 9.785244735887112e-07, "epoch": 0.5562627291242362, "percentage": 55.63, "elapsed_time": "0:16:35", "remaining_time": "0:13:14", "throughput": 6322.59, "total_tokens": 6294400}
{"current_steps": 6560, "total_steps": 11784, "loss": 0.0557, "lr": 9.770436546319504e-07, "epoch": 0.5566870332654447, "percentage": 55.67, "elapsed_time": "0:16:35", "remaining_time": "0:13:13", "throughput": 6325.03, "total_tokens": 6298880}
{"current_steps": 6565, "total_steps": 11784, "loss": 0.0636, "lr": 9.755628860392901e-07, "epoch": 0.5571113374066531, "percentage": 55.71, "elapsed_time": "0:16:36", "remaining_time": "0:13:11", "throughput": 6327.49, "total_tokens": 6303424}
{"current_steps": 6570, "total_steps": 11784, "loss": 0.026, "lr": 9.740821710593988e-07, "epoch": 0.5575356415478615, "percentage": 55.75, "elapsed_time": "0:16:36", "remaining_time": "0:13:10", "throughput": 6330.03, "total_tokens": 6308032}
{"current_steps": 6575, "total_steps": 11784, "loss": 0.048, "lr": 9.726015129408296e-07, "epoch": 0.5579599456890699, "percentage": 55.8, "elapsed_time": "0:16:36", "remaining_time": "0:13:09", "throughput": 6332.75, "total_tokens": 6312832}
{"current_steps": 6580, "total_steps": 11784, "loss": 0.035, "lr": 9.711209149320083e-07, "epoch": 0.5583842498302783, "percentage": 55.84, "elapsed_time": "0:16:37", "remaining_time": "0:13:08", "throughput": 6335.18, "total_tokens": 6317312}
{"current_steps": 6585, "total_steps": 11784, "loss": 0.0341, "lr": 9.69640380281231e-07, "epoch": 0.5588085539714868, "percentage": 55.88, "elapsed_time": "0:16:37", "remaining_time": "0:13:07", "throughput": 6337.73, "total_tokens": 6321920}
{"current_steps": 6590, "total_steps": 11784, "loss": 0.0732, "lr": 9.681599122366533e-07, "epoch": 0.5592328581126952, "percentage": 55.92, "elapsed_time": "0:16:37", "remaining_time": "0:13:06", "throughput": 6340.09, "total_tokens": 6326336}
{"current_steps": 6595, "total_steps": 11784, "loss": 0.0904, "lr": 9.66679514046286e-07, "epoch": 0.5596571622539036, "percentage": 55.97, "elapsed_time": "0:16:38", "remaining_time": "0:13:05", "throughput": 6342.67, "total_tokens": 6331008}
{"current_steps": 6600, "total_steps": 11784, "loss": 0.0866, "lr": 9.65199188957985e-07, "epoch": 0.560081466395112, "percentage": 56.01, "elapsed_time": "0:16:38", "remaining_time": "0:13:04", "throughput": 6345.3, "total_tokens": 6335744}
{"current_steps": 6605, "total_steps": 11784, "loss": 0.0558, "lr": 9.637189402194475e-07, "epoch": 0.5605057705363204, "percentage": 56.05, "elapsed_time": "0:16:38", "remaining_time": "0:13:03", "throughput": 6348.18, "total_tokens": 6340736}
{"current_steps": 6610, "total_steps": 11784, "loss": 0.0955, "lr": 9.622387710782017e-07, "epoch": 0.5609300746775289, "percentage": 56.09, "elapsed_time": "0:16:39", "remaining_time": "0:13:02", "throughput": 6350.6, "total_tokens": 6345216}
{"current_steps": 6615, "total_steps": 11784, "loss": 0.0383, "lr": 9.607586847816029e-07, "epoch": 0.5613543788187373, "percentage": 56.14, "elapsed_time": "0:16:39", "remaining_time": "0:13:01", "throughput": 6353.33, "total_tokens": 6350080}
{"current_steps": 6620, "total_steps": 11784, "loss": 0.0689, "lr": 9.592786845768225e-07, "epoch": 0.5617786829599457, "percentage": 56.18, "elapsed_time": "0:16:39", "remaining_time": "0:12:59", "throughput": 6355.98, "total_tokens": 6354816}
{"current_steps": 6625, "total_steps": 11784, "loss": 0.0538, "lr": 9.577987737108454e-07, "epoch": 0.5622029871011541, "percentage": 56.22, "elapsed_time": "0:16:40", "remaining_time": "0:12:58", "throughput": 6358.97, "total_tokens": 6360000}
{"current_steps": 6630, "total_steps": 11784, "loss": 0.1221, "lr": 9.563189554304578e-07, "epoch": 0.5626272912423625, "percentage": 56.26, "elapsed_time": "0:16:40", "remaining_time": "0:12:57", "throughput": 6361.53, "total_tokens": 6364672}
{"current_steps": 6635, "total_steps": 11784, "loss": 0.0828, "lr": 9.548392329822456e-07, "epoch": 0.563051595383571, "percentage": 56.31, "elapsed_time": "0:16:40", "remaining_time": "0:12:56", "throughput": 6364.19, "total_tokens": 6369408}
{"current_steps": 6640, "total_steps": 11784, "loss": 0.0482, "lr": 9.533596096125825e-07, "epoch": 0.5634758995247794, "percentage": 56.35, "elapsed_time": "0:16:41", "remaining_time": "0:12:55", "throughput": 6366.76, "total_tokens": 6374080}
{"current_steps": 6645, "total_steps": 11784, "loss": 0.051, "lr": 9.518800885676256e-07, "epoch": 0.5639002036659878, "percentage": 56.39, "elapsed_time": "0:16:41", "remaining_time": "0:12:54", "throughput": 6369.69, "total_tokens": 6379200}
{"current_steps": 6650, "total_steps": 11784, "loss": 0.0577, "lr": 9.504006730933068e-07, "epoch": 0.5643245078071962, "percentage": 56.43, "elapsed_time": "0:16:41", "remaining_time": "0:12:53", "throughput": 6372.85, "total_tokens": 6384576}
{"current_steps": 6655, "total_steps": 11784, "loss": 0.0797, "lr": 9.489213664353276e-07, "epoch": 0.5647488119484046, "percentage": 56.47, "elapsed_time": "0:16:42", "remaining_time": "0:12:52", "throughput": 6375.84, "total_tokens": 6389760}
{"current_steps": 6660, "total_steps": 11784, "loss": 0.1317, "lr": 9.474421718391497e-07, "epoch": 0.5651731160896131, "percentage": 56.52, "elapsed_time": "0:16:42", "remaining_time": "0:12:51", "throughput": 6378.18, "total_tokens": 6394176}
{"current_steps": 6665, "total_steps": 11784, "loss": 0.0693, "lr": 9.459630925499897e-07, "epoch": 0.5655974202308215, "percentage": 56.56, "elapsed_time": "0:16:42", "remaining_time": "0:12:50", "throughput": 6380.86, "total_tokens": 6398976}
{"current_steps": 6670, "total_steps": 11784, "loss": 0.0414, "lr": 9.444841318128103e-07, "epoch": 0.5660217243720299, "percentage": 56.6, "elapsed_time": "0:16:43", "remaining_time": "0:12:49", "throughput": 6383.07, "total_tokens": 6403264}
{"current_steps": 6675, "total_steps": 11784, "loss": 0.0771, "lr": 9.430052928723152e-07, "epoch": 0.5664460285132383, "percentage": 56.64, "elapsed_time": "0:16:43", "remaining_time": "0:12:48", "throughput": 6385.8, "total_tokens": 6408128}
{"current_steps": 6680, "total_steps": 11784, "loss": 0.1131, "lr": 9.415265789729403e-07, "epoch": 0.5668703326544468, "percentage": 56.69, "elapsed_time": "0:16:43", "remaining_time": "0:12:46", "throughput": 6388.24, "total_tokens": 6412672}
{"current_steps": 6685, "total_steps": 11784, "loss": 0.0724, "lr": 9.400479933588468e-07, "epoch": 0.5672946367956552, "percentage": 56.73, "elapsed_time": "0:16:44", "remaining_time": "0:12:45", "throughput": 6390.58, "total_tokens": 6417088}
{"current_steps": 6690, "total_steps": 11784, "loss": 0.0707, "lr": 9.385695392739156e-07, "epoch": 0.5677189409368636, "percentage": 56.77, "elapsed_time": "0:16:44", "remaining_time": "0:12:44", "throughput": 6393.18, "total_tokens": 6421824}
{"current_steps": 6695, "total_steps": 11784, "loss": 0.0411, "lr": 9.370912199617376e-07, "epoch": 0.568143245078072, "percentage": 56.81, "elapsed_time": "0:16:44", "remaining_time": "0:12:43", "throughput": 6395.77, "total_tokens": 6426560}
{"current_steps": 6700, "total_steps": 11784, "loss": 0.0867, "lr": 9.356130386656093e-07, "epoch": 0.5685675492192804, "percentage": 56.86, "elapsed_time": "0:16:45", "remaining_time": "0:12:42", "throughput": 6398.15, "total_tokens": 6431040}
{"current_steps": 6705, "total_steps": 11784, "loss": 0.0488, "lr": 9.341349986285234e-07, "epoch": 0.5689918533604889, "percentage": 56.9, "elapsed_time": "0:16:45", "remaining_time": "0:12:41", "throughput": 6400.92, "total_tokens": 6435968}
{"current_steps": 6710, "total_steps": 11784, "loss": 0.1258, "lr": 9.326571030931636e-07, "epoch": 0.5694161575016972, "percentage": 56.94, "elapsed_time": "0:16:45", "remaining_time": "0:12:40", "throughput": 6403.45, "total_tokens": 6440640}
{"current_steps": 6715, "total_steps": 11784, "loss": 0.0646, "lr": 9.311793553018958e-07, "epoch": 0.5698404616429056, "percentage": 56.98, "elapsed_time": "0:16:46", "remaining_time": "0:12:39", "throughput": 6406.14, "total_tokens": 6445504}
{"current_steps": 6720, "total_steps": 11784, "loss": 0.0453, "lr": 9.297017584967624e-07, "epoch": 0.570264765784114, "percentage": 57.03, "elapsed_time": "0:16:46", "remaining_time": "0:12:38", "throughput": 6408.18, "total_tokens": 6449600}
{"current_steps": 6725, "total_steps": 11784, "loss": 0.0386, "lr": 9.282243159194734e-07, "epoch": 0.5706890699253224, "percentage": 57.07, "elapsed_time": "0:16:46", "remaining_time": "0:12:37", "throughput": 6410.95, "total_tokens": 6454528}
{"current_steps": 6730, "total_steps": 11784, "loss": 0.0768, "lr": 9.267470308114025e-07, "epoch": 0.5711133740665308, "percentage": 57.11, "elapsed_time": "0:16:47", "remaining_time": "0:12:36", "throughput": 6413.56, "total_tokens": 6459264}
{"current_steps": 6735, "total_steps": 11784, "loss": 0.078, "lr": 9.252699064135758e-07, "epoch": 0.5715376782077393, "percentage": 57.15, "elapsed_time": "0:16:47", "remaining_time": "0:12:35", "throughput": 6415.75, "total_tokens": 6463552}
{"current_steps": 6740, "total_steps": 11784, "loss": 0.0072, "lr": 9.23792945966668e-07, "epoch": 0.5719619823489477, "percentage": 57.2, "elapsed_time": "0:16:47", "remaining_time": "0:12:34", "throughput": 6418.61, "total_tokens": 6468608}
{"current_steps": 6745, "total_steps": 11784, "loss": 0.0303, "lr": 9.223161527109936e-07, "epoch": 0.5723862864901561, "percentage": 57.24, "elapsed_time": "0:16:48", "remaining_time": "0:12:33", "throughput": 6421.27, "total_tokens": 6473408}
{"current_steps": 6750, "total_steps": 11784, "loss": 0.0353, "lr": 9.208395298865014e-07, "epoch": 0.5728105906313645, "percentage": 57.28, "elapsed_time": "0:16:48", "remaining_time": "0:12:32", "throughput": 6424.28, "total_tokens": 6478656}
{"current_steps": 6755, "total_steps": 11784, "loss": 0.0986, "lr": 9.19363080732764e-07, "epoch": 0.573234894772573, "percentage": 57.32, "elapsed_time": "0:16:48", "remaining_time": "0:12:31", "throughput": 6426.79, "total_tokens": 6483328}
{"current_steps": 6760, "total_steps": 11784, "loss": 0.0211, "lr": 9.178868084889756e-07, "epoch": 0.5736591989137814, "percentage": 57.37, "elapsed_time": "0:16:49", "remaining_time": "0:12:29", "throughput": 6429.36, "total_tokens": 6488064}
{"current_steps": 6765, "total_steps": 11784, "loss": 0.1111, "lr": 9.164107163939401e-07, "epoch": 0.5740835030549898, "percentage": 57.41, "elapsed_time": "0:16:49", "remaining_time": "0:12:28", "throughput": 6432.02, "total_tokens": 6492864}
{"current_steps": 6770, "total_steps": 11784, "loss": 0.038, "lr": 9.149348076860685e-07, "epoch": 0.5745078071961982, "percentage": 57.45, "elapsed_time": "0:16:49", "remaining_time": "0:12:27", "throughput": 6434.27, "total_tokens": 6497216}
{"current_steps": 6775, "total_steps": 11784, "loss": 0.0373, "lr": 9.134590856033664e-07, "epoch": 0.5749321113374066, "percentage": 57.49, "elapsed_time": "0:16:50", "remaining_time": "0:12:26", "throughput": 6436.8, "total_tokens": 6501888}
{"current_steps": 6780, "total_steps": 11784, "loss": 0.0708, "lr": 9.11983553383433e-07, "epoch": 0.575356415478615, "percentage": 57.54, "elapsed_time": "0:16:50", "remaining_time": "0:12:25", "throughput": 6439.87, "total_tokens": 6507200}
{"current_steps": 6785, "total_steps": 11784, "loss": 0.0143, "lr": 9.105082142634489e-07, "epoch": 0.5757807196198235, "percentage": 57.58, "elapsed_time": "0:16:50", "remaining_time": "0:12:24", "throughput": 6445.63, "total_tokens": 6515840}
{"current_steps": 6790, "total_steps": 11784, "loss": 0.1098, "lr": 9.090330714801723e-07, "epoch": 0.5762050237610319, "percentage": 57.62, "elapsed_time": "0:16:51", "remaining_time": "0:12:23", "throughput": 6448.02, "total_tokens": 6520384}
{"current_steps": 6795, "total_steps": 11784, "loss": 0.0894, "lr": 9.075581282699294e-07, "epoch": 0.5766293279022403, "percentage": 57.66, "elapsed_time": "0:16:51", "remaining_time": "0:12:22", "throughput": 6450.49, "total_tokens": 6524992}
{"current_steps": 6800, "total_steps": 11784, "loss": 0.1289, "lr": 9.060833878686098e-07, "epoch": 0.5770536320434487, "percentage": 57.71, "elapsed_time": "0:16:51", "remaining_time": "0:12:21", "throughput": 6455.08, "total_tokens": 6532160}
{"current_steps": 6805, "total_steps": 11784, "loss": 0.0264, "lr": 9.046088535116581e-07, "epoch": 0.5774779361846571, "percentage": 57.75, "elapsed_time": "0:16:52", "remaining_time": "0:12:20", "throughput": 6457.21, "total_tokens": 6536384}
{"current_steps": 6810, "total_steps": 11784, "loss": 0.0253, "lr": 9.031345284340652e-07, "epoch": 0.5779022403258656, "percentage": 57.79, "elapsed_time": "0:16:52", "remaining_time": "0:12:19", "throughput": 6459.5, "total_tokens": 6540800}
{"current_steps": 6815, "total_steps": 11784, "loss": 0.1609, "lr": 9.016604158703654e-07, "epoch": 0.578326544467074, "percentage": 57.83, "elapsed_time": "0:16:52", "remaining_time": "0:12:18", "throughput": 6461.79, "total_tokens": 6545216}
{"current_steps": 6820, "total_steps": 11784, "loss": 0.0496, "lr": 9.001865190546244e-07, "epoch": 0.5787508486082824, "percentage": 57.88, "elapsed_time": "0:16:53", "remaining_time": "0:12:17", "throughput": 6464.7, "total_tokens": 6550400}
{"current_steps": 6825, "total_steps": 11784, "loss": 0.0241, "lr": 8.987128412204363e-07, "epoch": 0.5791751527494908, "percentage": 57.92, "elapsed_time": "0:16:53", "remaining_time": "0:12:16", "throughput": 6466.92, "total_tokens": 6554752}
{"current_steps": 6830, "total_steps": 11784, "loss": 0.0436, "lr": 8.972393856009132e-07, "epoch": 0.5795994568906992, "percentage": 57.96, "elapsed_time": "0:16:53", "remaining_time": "0:12:15", "throughput": 6469.58, "total_tokens": 6559616}
{"current_steps": 6835, "total_steps": 11784, "loss": 0.0387, "lr": 8.957661554286817e-07, "epoch": 0.5800237610319077, "percentage": 58.0, "elapsed_time": "0:16:54", "remaining_time": "0:12:14", "throughput": 6472.35, "total_tokens": 6564608}
{"current_steps": 6840, "total_steps": 11784, "loss": 0.0477, "lr": 8.942931539358718e-07, "epoch": 0.5804480651731161, "percentage": 58.04, "elapsed_time": "0:16:54", "remaining_time": "0:12:13", "throughput": 6474.65, "total_tokens": 6569024}
{"current_steps": 6845, "total_steps": 11784, "loss": 0.056, "lr": 8.928203843541131e-07, "epoch": 0.5808723693143245, "percentage": 58.09, "elapsed_time": "0:16:54", "remaining_time": "0:12:12", "throughput": 6477.44, "total_tokens": 6574016}
{"current_steps": 6850, "total_steps": 11784, "loss": 0.0153, "lr": 8.913478499145254e-07, "epoch": 0.5812966734555329, "percentage": 58.13, "elapsed_time": "0:16:55", "remaining_time": "0:12:11", "throughput": 6480.14, "total_tokens": 6578944}
{"current_steps": 6855, "total_steps": 11784, "loss": 0.0494, "lr": 8.898755538477138e-07, "epoch": 0.5817209775967414, "percentage": 58.17, "elapsed_time": "0:16:55", "remaining_time": "0:12:10", "throughput": 6483.12, "total_tokens": 6584192}
{"current_steps": 6860, "total_steps": 11784, "loss": 0.1016, "lr": 8.884034993837594e-07, "epoch": 0.5821452817379498, "percentage": 58.21, "elapsed_time": "0:16:55", "remaining_time": "0:12:09", "throughput": 6485.78, "total_tokens": 6589056}
{"current_steps": 6865, "total_steps": 11784, "loss": 0.0777, "lr": 8.869316897522141e-07, "epoch": 0.5825695858791582, "percentage": 58.26, "elapsed_time": "0:16:56", "remaining_time": "0:12:08", "throughput": 6488.08, "total_tokens": 6593536}
{"current_steps": 6870, "total_steps": 11784, "loss": 0.0843, "lr": 8.854601281820914e-07, "epoch": 0.5829938900203666, "percentage": 58.3, "elapsed_time": "0:16:56", "remaining_time": "0:12:07", "throughput": 6492.13, "total_tokens": 6600128}
{"current_steps": 6875, "total_steps": 11784, "loss": 0.0393, "lr": 8.839888179018621e-07, "epoch": 0.583418194161575, "percentage": 58.34, "elapsed_time": "0:16:56", "remaining_time": "0:12:06", "throughput": 6494.69, "total_tokens": 6604864}
{"current_steps": 6880, "total_steps": 11784, "loss": 0.0228, "lr": 8.825177621394449e-07, "epoch": 0.5838424983027835, "percentage": 58.38, "elapsed_time": "0:16:57", "remaining_time": "0:12:05", "throughput": 6497.31, "total_tokens": 6609728}
{"current_steps": 6885, "total_steps": 11784, "loss": 0.0307, "lr": 8.810469641222001e-07, "epoch": 0.5842668024439919, "percentage": 58.43, "elapsed_time": "0:16:57", "remaining_time": "0:12:04", "throughput": 6500.35, "total_tokens": 6615104}
{"current_steps": 6890, "total_steps": 11784, "loss": 0.0439, "lr": 8.795764270769221e-07, "epoch": 0.5846911065852003, "percentage": 58.47, "elapsed_time": "0:16:57", "remaining_time": "0:12:03", "throughput": 6503.1, "total_tokens": 6620096}
{"current_steps": 6895, "total_steps": 11784, "loss": 0.0911, "lr": 8.781061542298341e-07, "epoch": 0.5851154107264087, "percentage": 58.51, "elapsed_time": "0:16:58", "remaining_time": "0:12:02", "throughput": 6505.3, "total_tokens": 6624448}
{"current_steps": 6900, "total_steps": 11784, "loss": 0.1139, "lr": 8.766361488065783e-07, "epoch": 0.5855397148676171, "percentage": 58.55, "elapsed_time": "0:16:58", "remaining_time": "0:12:01", "throughput": 6507.52, "total_tokens": 6628800}
{"current_steps": 6905, "total_steps": 11784, "loss": 0.046, "lr": 8.751664140322112e-07, "epoch": 0.5859640190088256, "percentage": 58.6, "elapsed_time": "0:16:58", "remaining_time": "0:11:59", "throughput": 6510.15, "total_tokens": 6633664}
{"current_steps": 6910, "total_steps": 11784, "loss": 0.0924, "lr": 8.736969531311942e-07, "epoch": 0.586388323150034, "percentage": 58.64, "elapsed_time": "0:16:59", "remaining_time": "0:11:58", "throughput": 6512.92, "total_tokens": 6638720}
{"current_steps": 6915, "total_steps": 11784, "loss": 0.0468, "lr": 8.7222776932739e-07, "epoch": 0.5868126272912424, "percentage": 58.68, "elapsed_time": "0:16:59", "remaining_time": "0:11:57", "throughput": 6515.05, "total_tokens": 6643008}
{"current_steps": 6920, "total_steps": 11784, "loss": 0.0501, "lr": 8.70758865844051e-07, "epoch": 0.5872369314324508, "percentage": 58.72, "elapsed_time": "0:16:59", "remaining_time": "0:11:56", "throughput": 6517.23, "total_tokens": 6647360}
{"current_steps": 6925, "total_steps": 11784, "loss": 0.0371, "lr": 8.69290245903816e-07, "epoch": 0.5876612355736592, "percentage": 58.77, "elapsed_time": "0:17:00", "remaining_time": "0:11:55", "throughput": 6519.67, "total_tokens": 6652032}
{"current_steps": 6930, "total_steps": 11784, "loss": 0.0833, "lr": 8.678219127287018e-07, "epoch": 0.5880855397148677, "percentage": 58.81, "elapsed_time": "0:17:00", "remaining_time": "0:11:54", "throughput": 6521.79, "total_tokens": 6656320}
{"current_steps": 6935, "total_steps": 11784, "loss": 0.0731, "lr": 8.663538695400951e-07, "epoch": 0.5885098438560761, "percentage": 58.85, "elapsed_time": "0:17:00", "remaining_time": "0:11:53", "throughput": 6524.17, "total_tokens": 6660928}
{"current_steps": 6940, "total_steps": 11784, "loss": 0.027, "lr": 8.648861195587475e-07, "epoch": 0.5889341479972845, "percentage": 58.89, "elapsed_time": "0:17:01", "remaining_time": "0:11:52", "throughput": 6526.83, "total_tokens": 6665856}
{"current_steps": 6945, "total_steps": 11784, "loss": 0.0478, "lr": 8.634186660047663e-07, "epoch": 0.5893584521384929, "percentage": 58.94, "elapsed_time": "0:17:01", "remaining_time": "0:11:51", "throughput": 6528.93, "total_tokens": 6670144}
{"current_steps": 6950, "total_steps": 11784, "loss": 0.0928, "lr": 8.619515120976097e-07, "epoch": 0.5897827562797013, "percentage": 58.98, "elapsed_time": "0:17:01", "remaining_time": "0:11:50", "throughput": 6531.76, "total_tokens": 6675264}
{"current_steps": 6955, "total_steps": 11784, "loss": 0.13, "lr": 8.60484661056077e-07, "epoch": 0.5902070604209098, "percentage": 59.02, "elapsed_time": "0:17:02", "remaining_time": "0:11:49", "throughput": 6533.86, "total_tokens": 6679552}
{"current_steps": 6960, "total_steps": 11784, "loss": 0.0307, "lr": 8.590181160983043e-07, "epoch": 0.5906313645621182, "percentage": 59.06, "elapsed_time": "0:17:02", "remaining_time": "0:11:48", "throughput": 6535.99, "total_tokens": 6683904}
{"current_steps": 6965, "total_steps": 11784, "loss": 0.0527, "lr": 8.575518804417552e-07, "epoch": 0.5910556687033266, "percentage": 59.11, "elapsed_time": "0:17:02", "remaining_time": "0:11:47", "throughput": 6538.24, "total_tokens": 6688320}
{"current_steps": 6970, "total_steps": 11784, "loss": 0.0419, "lr": 8.560859573032161e-07, "epoch": 0.591479972844535, "percentage": 59.15, "elapsed_time": "0:17:03", "remaining_time": "0:11:46", "throughput": 6541.27, "total_tokens": 6693696}
{"current_steps": 6975, "total_steps": 11784, "loss": 0.0631, "lr": 8.546203498987861e-07, "epoch": 0.5919042769857433, "percentage": 59.19, "elapsed_time": "0:17:03", "remaining_time": "0:11:45", "throughput": 6543.82, "total_tokens": 6698496}
{"current_steps": 6980, "total_steps": 11784, "loss": 0.0257, "lr": 8.531550614438729e-07, "epoch": 0.5923285811269517, "percentage": 59.23, "elapsed_time": "0:17:03", "remaining_time": "0:11:44", "throughput": 6547.1, "total_tokens": 6704192}
{"current_steps": 6985, "total_steps": 11784, "loss": 0.0148, "lr": 8.516900951531832e-07, "epoch": 0.5927528852681602, "percentage": 59.28, "elapsed_time": "0:17:04", "remaining_time": "0:11:43", "throughput": 6549.22, "total_tokens": 6708480}
{"current_steps": 6990, "total_steps": 11784, "loss": 0.0556, "lr": 8.502254542407185e-07, "epoch": 0.5931771894093686, "percentage": 59.32, "elapsed_time": "0:17:04", "remaining_time": "0:11:42", "throughput": 6552.24, "total_tokens": 6713856}
{"current_steps": 6995, "total_steps": 11784, "loss": 0.1009, "lr": 8.487611419197653e-07, "epoch": 0.593601493550577, "percentage": 59.36, "elapsed_time": "0:17:05", "remaining_time": "0:11:41", "throughput": 6555.14, "total_tokens": 6719104}
{"current_steps": 7000, "total_steps": 11784, "loss": 0.0662, "lr": 8.472971614028895e-07, "epoch": 0.5940257976917854, "percentage": 59.4, "elapsed_time": "0:17:05", "remaining_time": "0:11:40", "throughput": 6557.19, "total_tokens": 6723328}
{"current_steps": 7005, "total_steps": 11784, "loss": 0.0326, "lr": 8.458335159019288e-07, "epoch": 0.5944501018329938, "percentage": 59.45, "elapsed_time": "0:17:05", "remaining_time": "0:11:39", "throughput": 6559.67, "total_tokens": 6728064}
{"current_steps": 7010, "total_steps": 11784, "loss": 0.0827, "lr": 8.443702086279866e-07, "epoch": 0.5948744059742023, "percentage": 59.49, "elapsed_time": "0:17:06", "remaining_time": "0:11:38", "throughput": 6562.22, "total_tokens": 6732864}
{"current_steps": 7015, "total_steps": 11784, "loss": 0.0157, "lr": 8.429072427914235e-07, "epoch": 0.5952987101154107, "percentage": 59.53, "elapsed_time": "0:17:06", "remaining_time": "0:11:37", "throughput": 6564.84, "total_tokens": 6737792}
{"current_steps": 7020, "total_steps": 11784, "loss": 0.0443, "lr": 8.414446216018516e-07, "epoch": 0.5957230142566191, "percentage": 59.57, "elapsed_time": "0:17:06", "remaining_time": "0:11:36", "throughput": 6567.6, "total_tokens": 6742848}
{"current_steps": 7025, "total_steps": 11784, "loss": 0.0561, "lr": 8.399823482681261e-07, "epoch": 0.5961473183978275, "percentage": 59.61, "elapsed_time": "0:17:07", "remaining_time": "0:11:35", "throughput": 6570.53, "total_tokens": 6748160}
{"current_steps": 7030, "total_steps": 11784, "loss": 0.0759, "lr": 8.385204259983403e-07, "epoch": 0.596571622539036, "percentage": 59.66, "elapsed_time": "0:17:07", "remaining_time": "0:11:34", "throughput": 6573.07, "total_tokens": 6752960}
{"current_steps": 7035, "total_steps": 11784, "loss": 0.0535, "lr": 8.37058857999816e-07, "epoch": 0.5969959266802444, "percentage": 59.7, "elapsed_time": "0:17:07", "remaining_time": "0:11:33", "throughput": 6575.8, "total_tokens": 6758016}
{"current_steps": 7040, "total_steps": 11784, "loss": 0.104, "lr": 8.355976474790987e-07, "epoch": 0.5974202308214528, "percentage": 59.74, "elapsed_time": "0:17:08", "remaining_time": "0:11:32", "throughput": 6578.22, "total_tokens": 6762688}
{"current_steps": 7045, "total_steps": 11784, "loss": 0.0365, "lr": 8.341367976419485e-07, "epoch": 0.5978445349626612, "percentage": 59.78, "elapsed_time": "0:17:08", "remaining_time": "0:11:31", "throughput": 6580.65, "total_tokens": 6767424}
{"current_steps": 7050, "total_steps": 11784, "loss": 0.0831, "lr": 8.326763116933359e-07, "epoch": 0.5982688391038696, "percentage": 59.83, "elapsed_time": "0:17:08", "remaining_time": "0:11:30", "throughput": 6582.65, "total_tokens": 6771648}
{"current_steps": 7055, "total_steps": 11784, "loss": 0.0632, "lr": 8.312161928374317e-07, "epoch": 0.598693143245078, "percentage": 59.87, "elapsed_time": "0:17:09", "remaining_time": "0:11:29", "throughput": 6585.46, "total_tokens": 6776832}
{"current_steps": 7060, "total_steps": 11784, "loss": 0.0284, "lr": 8.297564442776012e-07, "epoch": 0.5991174473862865, "percentage": 59.91, "elapsed_time": "0:17:09", "remaining_time": "0:11:28", "throughput": 6587.52, "total_tokens": 6781120}
{"current_steps": 7065, "total_steps": 11784, "loss": 0.0353, "lr": 8.282970692163988e-07, "epoch": 0.5995417515274949, "percentage": 59.95, "elapsed_time": "0:17:09", "remaining_time": "0:11:27", "throughput": 6589.66, "total_tokens": 6785472}
{"current_steps": 7070, "total_steps": 11784, "loss": 0.0856, "lr": 8.268380708555579e-07, "epoch": 0.5999660556687033, "percentage": 60.0, "elapsed_time": "0:17:10", "remaining_time": "0:11:26", "throughput": 6593.14, "total_tokens": 6791488}
{"current_steps": 7075, "total_steps": 11784, "loss": 0.081, "lr": 8.253794523959863e-07, "epoch": 0.6003903598099117, "percentage": 60.04, "elapsed_time": "0:17:10", "remaining_time": "0:11:25", "throughput": 6596.33, "total_tokens": 6797120}
{"current_steps": 7080, "total_steps": 11784, "loss": 0.0467, "lr": 8.239212170377576e-07, "epoch": 0.6008146639511202, "percentage": 60.08, "elapsed_time": "0:17:10", "remaining_time": "0:11:24", "throughput": 6598.86, "total_tokens": 6801984}
{"current_steps": 7080, "total_steps": 11784, "eval_loss": 0.05977928265929222, "epoch": 0.6008146639511202, "percentage": 60.08, "elapsed_time": "0:17:26", "remaining_time": "0:11:35", "throughput": 6498.94, "total_tokens": 6801984}
{"current_steps": 7085, "total_steps": 11784, "loss": 0.0763, "lr": 8.224633679801062e-07, "epoch": 0.6012389680923286, "percentage": 60.12, "elapsed_time": "0:18:08", "remaining_time": "0:12:01", "throughput": 6253.7, "total_tokens": 6806528}
{"current_steps": 7090, "total_steps": 11784, "loss": 0.1491, "lr": 8.210059084214176e-07, "epoch": 0.601663272233537, "percentage": 60.17, "elapsed_time": "0:18:08", "remaining_time": "0:12:00", "throughput": 6256.31, "total_tokens": 6811456}
{"current_steps": 7095, "total_steps": 11784, "loss": 0.027, "lr": 8.195488415592237e-07, "epoch": 0.6020875763747454, "percentage": 60.21, "elapsed_time": "0:18:09", "remaining_time": "0:11:59", "throughput": 6258.49, "total_tokens": 6815872}
{"current_steps": 7100, "total_steps": 11784, "loss": 0.0177, "lr": 8.180921705901941e-07, "epoch": 0.6025118805159538, "percentage": 60.25, "elapsed_time": "0:18:09", "remaining_time": "0:11:58", "throughput": 6261.54, "total_tokens": 6821376}
{"current_steps": 7105, "total_steps": 11784, "loss": 0.0499, "lr": 8.16635898710131e-07, "epoch": 0.6029361846571623, "percentage": 60.29, "elapsed_time": "0:18:09", "remaining_time": "0:11:57", "throughput": 6264.43, "total_tokens": 6826688}
{"current_steps": 7110, "total_steps": 11784, "loss": 0.0411, "lr": 8.151800291139596e-07, "epoch": 0.6033604887983707, "percentage": 60.34, "elapsed_time": "0:18:10", "remaining_time": "0:11:56", "throughput": 6267.05, "total_tokens": 6831680}
{"current_steps": 7115, "total_steps": 11784, "loss": 0.0234, "lr": 8.137245649957239e-07, "epoch": 0.6037847929395791, "percentage": 60.38, "elapsed_time": "0:18:10", "remaining_time": "0:11:55", "throughput": 6269.17, "total_tokens": 6836032}
{"current_steps": 7120, "total_steps": 11784, "loss": 0.0511, "lr": 8.122695095485767e-07, "epoch": 0.6042090970807875, "percentage": 60.42, "elapsed_time": "0:18:10", "remaining_time": "0:11:54", "throughput": 6271.46, "total_tokens": 6840576}
{"current_steps": 7125, "total_steps": 11784, "loss": 0.0629, "lr": 8.108148659647764e-07, "epoch": 0.6046334012219959, "percentage": 60.46, "elapsed_time": "0:18:11", "remaining_time": "0:11:53", "throughput": 6274.19, "total_tokens": 6845696}
{"current_steps": 7130, "total_steps": 11784, "loss": 0.0581, "lr": 8.093606374356758e-07, "epoch": 0.6050577053632044, "percentage": 60.51, "elapsed_time": "0:18:11", "remaining_time": "0:11:52", "throughput": 6276.25, "total_tokens": 6849984}
{"current_steps": 7135, "total_steps": 11784, "loss": 0.0429, "lr": 8.079068271517182e-07, "epoch": 0.6054820095044128, "percentage": 60.55, "elapsed_time": "0:18:11", "remaining_time": "0:11:51", "throughput": 6278.58, "total_tokens": 6854592}
{"current_steps": 7140, "total_steps": 11784, "loss": 0.1295, "lr": 8.064534383024284e-07, "epoch": 0.6059063136456212, "percentage": 60.59, "elapsed_time": "0:18:12", "remaining_time": "0:11:50", "throughput": 6281.19, "total_tokens": 6859584}
{"current_steps": 7145, "total_steps": 11784, "loss": 0.062, "lr": 8.050004740764082e-07, "epoch": 0.6063306177868296, "percentage": 60.63, "elapsed_time": "0:18:12", "remaining_time": "0:11:49", "throughput": 6283.62, "total_tokens": 6864320}
{"current_steps": 7150, "total_steps": 11784, "loss": 0.038, "lr": 8.035479376613261e-07, "epoch": 0.606754921928038, "percentage": 60.68, "elapsed_time": "0:18:12", "remaining_time": "0:11:48", "throughput": 6285.74, "total_tokens": 6868672}
{"current_steps": 7155, "total_steps": 11784, "loss": 0.0651, "lr": 8.020958322439132e-07, "epoch": 0.6071792260692465, "percentage": 60.72, "elapsed_time": "0:18:13", "remaining_time": "0:11:47", "throughput": 6287.92, "total_tokens": 6873088}
{"current_steps": 7160, "total_steps": 11784, "loss": 0.0519, "lr": 8.006441610099539e-07, "epoch": 0.6076035302104549, "percentage": 60.76, "elapsed_time": "0:18:13", "remaining_time": "0:11:46", "throughput": 6290.14, "total_tokens": 6877568}
{"current_steps": 7165, "total_steps": 11784, "loss": 0.1173, "lr": 7.991929271442817e-07, "epoch": 0.6080278343516633, "percentage": 60.8, "elapsed_time": "0:18:13", "remaining_time": "0:11:45", "throughput": 6292.41, "total_tokens": 6882112}
{"current_steps": 7170, "total_steps": 11784, "loss": 0.1062, "lr": 7.977421338307687e-07, "epoch": 0.6084521384928717, "percentage": 60.85, "elapsed_time": "0:18:14", "remaining_time": "0:11:44", "throughput": 6294.73, "total_tokens": 6886720}
{"current_steps": 7175, "total_steps": 11784, "loss": 0.0485, "lr": 7.962917842523215e-07, "epoch": 0.6088764426340801, "percentage": 60.89, "elapsed_time": "0:18:14", "remaining_time": "0:11:42", "throughput": 6297.25, "total_tokens": 6891584}
{"current_steps": 7180, "total_steps": 11784, "loss": 0.0222, "lr": 7.94841881590874e-07, "epoch": 0.6093007467752886, "percentage": 60.93, "elapsed_time": "0:18:14", "remaining_time": "0:11:41", "throughput": 6299.69, "total_tokens": 6896320}
{"current_steps": 7185, "total_steps": 11784, "loss": 0.1228, "lr": 7.933924290273774e-07, "epoch": 0.609725050916497, "percentage": 60.97, "elapsed_time": "0:18:15", "remaining_time": "0:11:40", "throughput": 6302.07, "total_tokens": 6900992}
{"current_steps": 7190, "total_steps": 11784, "loss": 0.0742, "lr": 7.919434297417976e-07, "epoch": 0.6101493550577054, "percentage": 61.01, "elapsed_time": "0:18:15", "remaining_time": "0:11:39", "throughput": 6304.36, "total_tokens": 6905600}
{"current_steps": 7195, "total_steps": 11784, "loss": 0.103, "lr": 7.904948869131039e-07, "epoch": 0.6105736591989138, "percentage": 61.06, "elapsed_time": "0:18:15", "remaining_time": "0:11:38", "throughput": 6306.65, "total_tokens": 6910208}
{"current_steps": 7200, "total_steps": 11784, "loss": 0.0421, "lr": 7.89046803719267e-07, "epoch": 0.6109979633401222, "percentage": 61.1, "elapsed_time": "0:18:16", "remaining_time": "0:11:37", "throughput": 6309.31, "total_tokens": 6915264}
{"current_steps": 7205, "total_steps": 11784, "loss": 0.0266, "lr": 7.875991833372463e-07, "epoch": 0.6114222674813307, "percentage": 61.14, "elapsed_time": "0:18:16", "remaining_time": "0:11:36", "throughput": 6311.57, "total_tokens": 6919808}
{"current_steps": 7210, "total_steps": 11784, "loss": 0.0321, "lr": 7.861520289429879e-07, "epoch": 0.6118465716225391, "percentage": 61.18, "elapsed_time": "0:18:16", "remaining_time": "0:11:35", "throughput": 6314.01, "total_tokens": 6924608}
{"current_steps": 7215, "total_steps": 11784, "loss": 0.0338, "lr": 7.847053437114141e-07, "epoch": 0.6122708757637475, "percentage": 61.23, "elapsed_time": "0:18:17", "remaining_time": "0:11:34", "throughput": 6316.44, "total_tokens": 6929344}
{"current_steps": 7220, "total_steps": 11784, "loss": 0.1193, "lr": 7.832591308164193e-07, "epoch": 0.6126951799049559, "percentage": 61.27, "elapsed_time": "0:18:17", "remaining_time": "0:11:33", "throughput": 6319.16, "total_tokens": 6934464}
{"current_steps": 7225, "total_steps": 11784, "loss": 0.0717, "lr": 7.818133934308606e-07, "epoch": 0.6131194840461643, "percentage": 61.31, "elapsed_time": "0:18:17", "remaining_time": "0:11:32", "throughput": 6321.76, "total_tokens": 6939456}
{"current_steps": 7230, "total_steps": 11784, "loss": 0.0072, "lr": 7.803681347265524e-07, "epoch": 0.6135437881873728, "percentage": 61.35, "elapsed_time": "0:18:18", "remaining_time": "0:11:31", "throughput": 6323.85, "total_tokens": 6943808}
{"current_steps": 7235, "total_steps": 11784, "loss": 0.0254, "lr": 7.789233578742583e-07, "epoch": 0.6139680923285811, "percentage": 61.4, "elapsed_time": "0:18:18", "remaining_time": "0:11:30", "throughput": 6326.39, "total_tokens": 6948736}
{"current_steps": 7240, "total_steps": 11784, "loss": 0.0926, "lr": 7.774790660436857e-07, "epoch": 0.6143923964697895, "percentage": 61.44, "elapsed_time": "0:18:18", "remaining_time": "0:11:29", "throughput": 6329.04, "total_tokens": 6953792}
{"current_steps": 7245, "total_steps": 11784, "loss": 0.0226, "lr": 7.760352624034769e-07, "epoch": 0.6148167006109979, "percentage": 61.48, "elapsed_time": "0:18:19", "remaining_time": "0:11:28", "throughput": 6331.55, "total_tokens": 6958656}
{"current_steps": 7250, "total_steps": 11784, "loss": 0.0326, "lr": 7.745919501212043e-07, "epoch": 0.6152410047522063, "percentage": 61.52, "elapsed_time": "0:18:19", "remaining_time": "0:11:27", "throughput": 6333.77, "total_tokens": 6963200}
{"current_steps": 7255, "total_steps": 11784, "loss": 0.0307, "lr": 7.731491323633608e-07, "epoch": 0.6156653088934148, "percentage": 61.57, "elapsed_time": "0:18:19", "remaining_time": "0:11:26", "throughput": 6336.58, "total_tokens": 6968448}
{"current_steps": 7260, "total_steps": 11784, "loss": 0.0835, "lr": 7.71706812295356e-07, "epoch": 0.6160896130346232, "percentage": 61.61, "elapsed_time": "0:18:20", "remaining_time": "0:11:25", "throughput": 6339.52, "total_tokens": 6973888}
{"current_steps": 7265, "total_steps": 11784, "loss": 0.0817, "lr": 7.702649930815065e-07, "epoch": 0.6165139171758316, "percentage": 61.65, "elapsed_time": "0:18:20", "remaining_time": "0:11:24", "throughput": 6341.61, "total_tokens": 6978304}
{"current_steps": 7270, "total_steps": 11784, "loss": 0.0605, "lr": 7.688236778850306e-07, "epoch": 0.61693822131704, "percentage": 61.69, "elapsed_time": "0:18:20", "remaining_time": "0:11:23", "throughput": 6344.09, "total_tokens": 6983168}
{"current_steps": 7275, "total_steps": 11784, "loss": 0.0463, "lr": 7.6738286986804e-07, "epoch": 0.6173625254582484, "percentage": 61.74, "elapsed_time": "0:18:21", "remaining_time": "0:11:22", "throughput": 6346.73, "total_tokens": 6988224}
{"current_steps": 7280, "total_steps": 11784, "loss": 0.0742, "lr": 7.659425721915351e-07, "epoch": 0.6177868295994569, "percentage": 61.78, "elapsed_time": "0:18:21", "remaining_time": "0:11:21", "throughput": 6348.69, "total_tokens": 6992448}
{"current_steps": 7285, "total_steps": 11784, "loss": 0.0507, "lr": 7.645027880153956e-07, "epoch": 0.6182111337406653, "percentage": 61.82, "elapsed_time": "0:18:21", "remaining_time": "0:11:20", "throughput": 6350.8, "total_tokens": 6996864}
{"current_steps": 7290, "total_steps": 11784, "loss": 0.0316, "lr": 7.63063520498375e-07, "epoch": 0.6186354378818737, "percentage": 61.86, "elapsed_time": "0:18:22", "remaining_time": "0:11:19", "throughput": 6353.48, "total_tokens": 7001984}
{"current_steps": 7295, "total_steps": 11784, "loss": 0.0762, "lr": 7.616247727980927e-07, "epoch": 0.6190597420230821, "percentage": 61.91, "elapsed_time": "0:18:22", "remaining_time": "0:11:18", "throughput": 6356.2, "total_tokens": 7007168}
{"current_steps": 7300, "total_steps": 11784, "loss": 0.0582, "lr": 7.601865480710289e-07, "epoch": 0.6194840461642905, "percentage": 61.95, "elapsed_time": "0:18:22", "remaining_time": "0:11:17", "throughput": 6358.98, "total_tokens": 7012416}
{"current_steps": 7305, "total_steps": 11784, "loss": 0.0792, "lr": 7.587488494725156e-07, "epoch": 0.619908350305499, "percentage": 61.99, "elapsed_time": "0:18:23", "remaining_time": "0:11:16", "throughput": 6360.91, "total_tokens": 7016576}
{"current_steps": 7310, "total_steps": 11784, "loss": 0.0391, "lr": 7.573116801567301e-07, "epoch": 0.6203326544467074, "percentage": 62.03, "elapsed_time": "0:18:23", "remaining_time": "0:11:15", "throughput": 6363.06, "total_tokens": 7021056}
{"current_steps": 7315, "total_steps": 11784, "loss": 0.091, "lr": 7.558750432766901e-07, "epoch": 0.6207569585879158, "percentage": 62.08, "elapsed_time": "0:18:23", "remaining_time": "0:11:14", "throughput": 6365.54, "total_tokens": 7025984}
{"current_steps": 7320, "total_steps": 11784, "loss": 0.0191, "lr": 7.544389419842429e-07, "epoch": 0.6211812627291242, "percentage": 62.12, "elapsed_time": "0:18:24", "remaining_time": "0:11:13", "throughput": 6368.23, "total_tokens": 7031104}
{"current_steps": 7325, "total_steps": 11784, "loss": 0.0467, "lr": 7.530033794300631e-07, "epoch": 0.6216055668703326, "percentage": 62.16, "elapsed_time": "0:18:24", "remaining_time": "0:11:12", "throughput": 6370.68, "total_tokens": 7035904}
{"current_steps": 7330, "total_steps": 11784, "loss": 0.1059, "lr": 7.515683587636412e-07, "epoch": 0.6220298710115411, "percentage": 62.2, "elapsed_time": "0:18:24", "remaining_time": "0:11:11", "throughput": 6372.86, "total_tokens": 7040384}
{"current_steps": 7335, "total_steps": 11784, "loss": 0.0149, "lr": 7.501338831332813e-07, "epoch": 0.6224541751527495, "percentage": 62.25, "elapsed_time": "0:18:25", "remaining_time": "0:11:10", "throughput": 6375.38, "total_tokens": 7045312}
{"current_steps": 7340, "total_steps": 11784, "loss": 0.034, "lr": 7.486999556860889e-07, "epoch": 0.6228784792939579, "percentage": 62.29, "elapsed_time": "0:18:25", "remaining_time": "0:11:09", "throughput": 6377.75, "total_tokens": 7050048}
{"current_steps": 7345, "total_steps": 11784, "loss": 0.0281, "lr": 7.472665795679694e-07, "epoch": 0.6233027834351663, "percentage": 62.33, "elapsed_time": "0:18:25", "remaining_time": "0:11:08", "throughput": 6379.97, "total_tokens": 7054592}
{"current_steps": 7350, "total_steps": 11784, "loss": 0.0953, "lr": 7.458337579236168e-07, "epoch": 0.6237270875763747, "percentage": 62.37, "elapsed_time": "0:18:26", "remaining_time": "0:11:07", "throughput": 6382.38, "total_tokens": 7059392}
{"current_steps": 7355, "total_steps": 11784, "loss": 0.113, "lr": 7.4440149389651e-07, "epoch": 0.6241513917175832, "percentage": 62.42, "elapsed_time": "0:18:26", "remaining_time": "0:11:06", "throughput": 6384.3, "total_tokens": 7063552}
{"current_steps": 7360, "total_steps": 11784, "loss": 0.0476, "lr": 7.429697906289029e-07, "epoch": 0.6245756958587916, "percentage": 62.46, "elapsed_time": "0:18:26", "remaining_time": "0:11:05", "throughput": 6386.67, "total_tokens": 7068288}
{"current_steps": 7365, "total_steps": 11784, "loss": 0.005, "lr": 7.415386512618216e-07, "epoch": 0.625, "percentage": 62.5, "elapsed_time": "0:18:27", "remaining_time": "0:11:04", "throughput": 6389.18, "total_tokens": 7073216}
{"current_steps": 7370, "total_steps": 11784, "loss": 0.0727, "lr": 7.401080789350525e-07, "epoch": 0.6254243041412084, "percentage": 62.54, "elapsed_time": "0:18:27", "remaining_time": "0:11:03", "throughput": 6391.41, "total_tokens": 7077824}
{"current_steps": 7375, "total_steps": 11784, "loss": 0.0238, "lr": 7.386780767871396e-07, "epoch": 0.6258486082824168, "percentage": 62.58, "elapsed_time": "0:18:27", "remaining_time": "0:11:02", "throughput": 6393.49, "total_tokens": 7082240}
{"current_steps": 7380, "total_steps": 11784, "loss": 0.078, "lr": 7.372486479553748e-07, "epoch": 0.6262729124236253, "percentage": 62.63, "elapsed_time": "0:18:28", "remaining_time": "0:11:01", "throughput": 6396.12, "total_tokens": 7087360}
{"current_steps": 7385, "total_steps": 11784, "loss": 0.0387, "lr": 7.358197955757939e-07, "epoch": 0.6266972165648337, "percentage": 62.67, "elapsed_time": "0:18:28", "remaining_time": "0:11:00", "throughput": 6398.66, "total_tokens": 7092288}
{"current_steps": 7390, "total_steps": 11784, "loss": 0.0334, "lr": 7.343915227831661e-07, "epoch": 0.6271215207060421, "percentage": 62.71, "elapsed_time": "0:18:28", "remaining_time": "0:10:59", "throughput": 6400.8, "total_tokens": 7096768}
{"current_steps": 7395, "total_steps": 11784, "loss": 0.0722, "lr": 7.329638327109902e-07, "epoch": 0.6275458248472505, "percentage": 62.75, "elapsed_time": "0:18:29", "remaining_time": "0:10:58", "throughput": 6402.99, "total_tokens": 7101312}
{"current_steps": 7400, "total_steps": 11784, "loss": 0.0878, "lr": 7.315367284914861e-07, "epoch": 0.6279701289884589, "percentage": 62.8, "elapsed_time": "0:18:29", "remaining_time": "0:10:57", "throughput": 6405.02, "total_tokens": 7105664}
{"current_steps": 7405, "total_steps": 11784, "loss": 0.0652, "lr": 7.301102132555891e-07, "epoch": 0.6283944331296674, "percentage": 62.84, "elapsed_time": "0:18:29", "remaining_time": "0:10:56", "throughput": 6407.21, "total_tokens": 7110208}
{"current_steps": 7410, "total_steps": 11784, "loss": 0.004, "lr": 7.286842901329412e-07, "epoch": 0.6288187372708758, "percentage": 62.88, "elapsed_time": "0:18:30", "remaining_time": "0:10:55", "throughput": 6409.7, "total_tokens": 7115136}
{"current_steps": 7415, "total_steps": 11784, "loss": 0.0337, "lr": 7.272589622518863e-07, "epoch": 0.6292430414120842, "percentage": 62.92, "elapsed_time": "0:18:30", "remaining_time": "0:10:54", "throughput": 6411.8, "total_tokens": 7119552}
{"current_steps": 7420, "total_steps": 11784, "loss": 0.0522, "lr": 7.258342327394616e-07, "epoch": 0.6296673455532926, "percentage": 62.97, "elapsed_time": "0:18:30", "remaining_time": "0:10:53", "throughput": 6414.18, "total_tokens": 7124352}
{"current_steps": 7425, "total_steps": 11784, "loss": 0.0316, "lr": 7.244101047213927e-07, "epoch": 0.630091649694501, "percentage": 63.01, "elapsed_time": "0:18:31", "remaining_time": "0:10:52", "throughput": 6416.28, "total_tokens": 7128768}
{"current_steps": 7430, "total_steps": 11784, "loss": 0.0971, "lr": 7.229865813220843e-07, "epoch": 0.6305159538357095, "percentage": 63.05, "elapsed_time": "0:18:31", "remaining_time": "0:10:51", "throughput": 6418.67, "total_tokens": 7133568}
{"current_steps": 7435, "total_steps": 11784, "loss": 0.0625, "lr": 7.215636656646151e-07, "epoch": 0.6309402579769179, "percentage": 63.09, "elapsed_time": "0:18:31", "remaining_time": "0:10:50", "throughput": 6420.88, "total_tokens": 7138112}
{"current_steps": 7440, "total_steps": 11784, "loss": 0.0557, "lr": 7.201413608707312e-07, "epoch": 0.6313645621181263, "percentage": 63.14, "elapsed_time": "0:18:32", "remaining_time": "0:10:49", "throughput": 6423.2, "total_tokens": 7142848}
{"current_steps": 7445, "total_steps": 11784, "loss": 0.0781, "lr": 7.187196700608372e-07, "epoch": 0.6317888662593347, "percentage": 63.18, "elapsed_time": "0:18:32", "remaining_time": "0:10:48", "throughput": 6425.53, "total_tokens": 7147584}
{"current_steps": 7450, "total_steps": 11784, "loss": 0.0768, "lr": 7.172985963539919e-07, "epoch": 0.6322131704005431, "percentage": 63.22, "elapsed_time": "0:18:32", "remaining_time": "0:10:47", "throughput": 6427.77, "total_tokens": 7152192}
{"current_steps": 7455, "total_steps": 11784, "loss": 0.0604, "lr": 7.158781428678989e-07, "epoch": 0.6326374745417516, "percentage": 63.26, "elapsed_time": "0:18:33", "remaining_time": "0:10:46", "throughput": 6429.91, "total_tokens": 7156672}
{"current_steps": 7460, "total_steps": 11784, "loss": 0.0545, "lr": 7.144583127189028e-07, "epoch": 0.63306177868296, "percentage": 63.31, "elapsed_time": "0:18:33", "remaining_time": "0:10:45", "throughput": 6432.42, "total_tokens": 7161664}
{"current_steps": 7465, "total_steps": 11784, "loss": 0.0352, "lr": 7.130391090219789e-07, "epoch": 0.6334860828241684, "percentage": 63.35, "elapsed_time": "0:18:33", "remaining_time": "0:10:44", "throughput": 6434.45, "total_tokens": 7166016}
{"current_steps": 7470, "total_steps": 11784, "loss": 0.0671, "lr": 7.116205348907298e-07, "epoch": 0.6339103869653768, "percentage": 63.39, "elapsed_time": "0:18:34", "remaining_time": "0:10:43", "throughput": 6436.76, "total_tokens": 7170752}
{"current_steps": 7475, "total_steps": 11784, "loss": 0.0546, "lr": 7.10202593437375e-07, "epoch": 0.6343346911065852, "percentage": 63.43, "elapsed_time": "0:18:34", "remaining_time": "0:10:42", "throughput": 6439.5, "total_tokens": 7176064}
{"current_steps": 7480, "total_steps": 11784, "loss": 0.0549, "lr": 7.08785287772748e-07, "epoch": 0.6347589952477937, "percentage": 63.48, "elapsed_time": "0:18:34", "remaining_time": "0:10:41", "throughput": 6442.16, "total_tokens": 7181312}
{"current_steps": 7485, "total_steps": 11784, "loss": 0.095, "lr": 7.073686210062859e-07, "epoch": 0.6351832993890021, "percentage": 63.52, "elapsed_time": "0:18:35", "remaining_time": "0:10:40", "throughput": 6444.58, "total_tokens": 7186176}
{"current_steps": 7490, "total_steps": 11784, "loss": 0.0358, "lr": 7.059525962460248e-07, "epoch": 0.6356076035302105, "percentage": 63.56, "elapsed_time": "0:18:35", "remaining_time": "0:10:39", "throughput": 6446.79, "total_tokens": 7190784}
{"current_steps": 7495, "total_steps": 11784, "loss": 0.0687, "lr": 7.045372165985919e-07, "epoch": 0.6360319076714189, "percentage": 63.6, "elapsed_time": "0:18:35", "remaining_time": "0:10:38", "throughput": 6449.34, "total_tokens": 7195840}
{"current_steps": 7500, "total_steps": 11784, "loss": 0.0347, "lr": 7.031224851691999e-07, "epoch": 0.6364562118126272, "percentage": 63.65, "elapsed_time": "0:18:36", "remaining_time": "0:10:37", "throughput": 6451.99, "total_tokens": 7201024}
{"current_steps": 7505, "total_steps": 11784, "loss": 0.0709, "lr": 7.017084050616385e-07, "epoch": 0.6368805159538357, "percentage": 63.69, "elapsed_time": "0:18:36", "remaining_time": "0:10:36", "throughput": 6454.28, "total_tokens": 7205760}
{"current_steps": 7510, "total_steps": 11784, "loss": 0.0482, "lr": 7.002949793782686e-07, "epoch": 0.6373048200950441, "percentage": 63.73, "elapsed_time": "0:18:36", "remaining_time": "0:10:35", "throughput": 6456.64, "total_tokens": 7210560}
{"current_steps": 7515, "total_steps": 11784, "loss": 0.0555, "lr": 6.988822112200156e-07, "epoch": 0.6377291242362525, "percentage": 63.77, "elapsed_time": "0:18:37", "remaining_time": "0:10:34", "throughput": 6459.09, "total_tokens": 7215488}
{"current_steps": 7520, "total_steps": 11784, "loss": 0.0843, "lr": 6.974701036863626e-07, "epoch": 0.6381534283774609, "percentage": 63.82, "elapsed_time": "0:18:37", "remaining_time": "0:10:33", "throughput": 6461.67, "total_tokens": 7220608}
{"current_steps": 7525, "total_steps": 11784, "loss": 0.029, "lr": 6.960586598753426e-07, "epoch": 0.6385777325186693, "percentage": 63.86, "elapsed_time": "0:18:37", "remaining_time": "0:10:32", "throughput": 6463.93, "total_tokens": 7225280}
{"current_steps": 7530, "total_steps": 11784, "loss": 0.0439, "lr": 6.946478828835331e-07, "epoch": 0.6390020366598778, "percentage": 63.9, "elapsed_time": "0:18:38", "remaining_time": "0:10:31", "throughput": 6465.99, "total_tokens": 7229696}
{"current_steps": 7535, "total_steps": 11784, "loss": 0.0425, "lr": 6.932377758060481e-07, "epoch": 0.6394263408010862, "percentage": 63.94, "elapsed_time": "0:18:38", "remaining_time": "0:10:30", "throughput": 6467.92, "total_tokens": 7233984}
{"current_steps": 7540, "total_steps": 11784, "loss": 0.0495, "lr": 6.91828341736533e-07, "epoch": 0.6398506449422946, "percentage": 63.99, "elapsed_time": "0:18:38", "remaining_time": "0:10:29", "throughput": 6471.16, "total_tokens": 7239936}
{"current_steps": 7545, "total_steps": 11784, "loss": 0.0334, "lr": 6.904195837671552e-07, "epoch": 0.640274949083503, "percentage": 64.03, "elapsed_time": "0:18:39", "remaining_time": "0:10:28", "throughput": 6473.29, "total_tokens": 7244480}
{"current_steps": 7550, "total_steps": 11784, "loss": 0.0664, "lr": 6.890115049885994e-07, "epoch": 0.6406992532247114, "percentage": 64.07, "elapsed_time": "0:18:39", "remaining_time": "0:10:27", "throughput": 6475.41, "total_tokens": 7248960}
{"current_steps": 7555, "total_steps": 11784, "loss": 0.0579, "lr": 6.87604108490061e-07, "epoch": 0.6411235573659199, "percentage": 64.11, "elapsed_time": "0:18:39", "remaining_time": "0:10:26", "throughput": 6477.87, "total_tokens": 7253888}
{"current_steps": 7560, "total_steps": 11784, "loss": 0.0378, "lr": 6.861973973592372e-07, "epoch": 0.6415478615071283, "percentage": 64.15, "elapsed_time": "0:18:40", "remaining_time": "0:10:25", "throughput": 6480.62, "total_tokens": 7259200}
{"current_steps": 7565, "total_steps": 11784, "loss": 0.0178, "lr": 6.847913746823227e-07, "epoch": 0.6419721656483367, "percentage": 64.2, "elapsed_time": "0:18:40", "remaining_time": "0:10:24", "throughput": 6482.8, "total_tokens": 7263808}
{"current_steps": 7570, "total_steps": 11784, "loss": 0.0296, "lr": 6.833860435440006e-07, "epoch": 0.6423964697895451, "percentage": 64.24, "elapsed_time": "0:18:40", "remaining_time": "0:10:23", "throughput": 6485.64, "total_tokens": 7269248}
{"current_steps": 7575, "total_steps": 11784, "loss": 0.0162, "lr": 6.819814070274384e-07, "epoch": 0.6428207739307535, "percentage": 64.28, "elapsed_time": "0:18:41", "remaining_time": "0:10:22", "throughput": 6488.34, "total_tokens": 7274496}
{"current_steps": 7580, "total_steps": 11784, "loss": 0.1676, "lr": 6.805774682142782e-07, "epoch": 0.643245078071962, "percentage": 64.32, "elapsed_time": "0:18:41", "remaining_time": "0:10:22", "throughput": 6490.89, "total_tokens": 7279552}
{"current_steps": 7585, "total_steps": 11784, "loss": 0.0954, "lr": 6.791742301846325e-07, "epoch": 0.6436693822131704, "percentage": 64.37, "elapsed_time": "0:18:41", "remaining_time": "0:10:21", "throughput": 6493.04, "total_tokens": 7284096}
{"current_steps": 7590, "total_steps": 11784, "loss": 0.039, "lr": 6.777716960170752e-07, "epoch": 0.6440936863543788, "percentage": 64.41, "elapsed_time": "0:18:42", "remaining_time": "0:10:20", "throughput": 6495.54, "total_tokens": 7289088}
{"current_steps": 7595, "total_steps": 11784, "loss": 0.1273, "lr": 6.763698687886372e-07, "epoch": 0.6445179904955872, "percentage": 64.45, "elapsed_time": "0:18:42", "remaining_time": "0:10:19", "throughput": 6497.71, "total_tokens": 7293696}
{"current_steps": 7600, "total_steps": 11784, "loss": 0.047, "lr": 6.749687515747977e-07, "epoch": 0.6449422946367956, "percentage": 64.49, "elapsed_time": "0:18:42", "remaining_time": "0:10:18", "throughput": 6500.28, "total_tokens": 7298816}
{"current_steps": 7605, "total_steps": 11784, "loss": 0.0821, "lr": 6.735683474494784e-07, "epoch": 0.6453665987780041, "percentage": 64.54, "elapsed_time": "0:18:43", "remaining_time": "0:10:17", "throughput": 6502.31, "total_tokens": 7303232}
{"current_steps": 7610, "total_steps": 11784, "loss": 0.0391, "lr": 6.721686594850362e-07, "epoch": 0.6457909029192125, "percentage": 64.58, "elapsed_time": "0:18:43", "remaining_time": "0:10:16", "throughput": 6504.95, "total_tokens": 7308416}
{"current_steps": 7615, "total_steps": 11784, "loss": 0.0789, "lr": 6.707696907522577e-07, "epoch": 0.6462152070604209, "percentage": 64.62, "elapsed_time": "0:18:43", "remaining_time": "0:10:15", "throughput": 6507.11, "total_tokens": 7313024}
{"current_steps": 7620, "total_steps": 11784, "loss": 0.0668, "lr": 6.693714443203507e-07, "epoch": 0.6466395112016293, "percentage": 64.66, "elapsed_time": "0:18:44", "remaining_time": "0:10:14", "throughput": 6509.39, "total_tokens": 7317760}
{"current_steps": 7625, "total_steps": 11784, "loss": 0.0315, "lr": 6.679739232569388e-07, "epoch": 0.6470638153428377, "percentage": 64.71, "elapsed_time": "0:18:44", "remaining_time": "0:10:13", "throughput": 6511.75, "total_tokens": 7322624}
{"current_steps": 7630, "total_steps": 11784, "loss": 0.0434, "lr": 6.665771306280537e-07, "epoch": 0.6474881194840462, "percentage": 64.75, "elapsed_time": "0:18:44", "remaining_time": "0:10:12", "throughput": 6513.79, "total_tokens": 7327104}
{"current_steps": 7635, "total_steps": 11784, "loss": 0.0735, "lr": 6.651810694981299e-07, "epoch": 0.6479124236252546, "percentage": 64.79, "elapsed_time": "0:18:45", "remaining_time": "0:10:11", "throughput": 6515.78, "total_tokens": 7331520}
{"current_steps": 7640, "total_steps": 11784, "loss": 0.0712, "lr": 6.637857429299958e-07, "epoch": 0.648336727766463, "percentage": 64.83, "elapsed_time": "0:18:45", "remaining_time": "0:10:10", "throughput": 6518.19, "total_tokens": 7336448}
{"current_steps": 7645, "total_steps": 11784, "loss": 0.0669, "lr": 6.623911539848697e-07, "epoch": 0.6487610319076714, "percentage": 64.88, "elapsed_time": "0:18:45", "remaining_time": "0:10:09", "throughput": 6520.47, "total_tokens": 7341248}
{"current_steps": 7650, "total_steps": 11784, "loss": 0.0657, "lr": 6.6099730572235e-07, "epoch": 0.6491853360488798, "percentage": 64.92, "elapsed_time": "0:18:46", "remaining_time": "0:10:08", "throughput": 6522.65, "total_tokens": 7345920}
{"current_steps": 7655, "total_steps": 11784, "loss": 0.0214, "lr": 6.596042012004119e-07, "epoch": 0.6496096401900883, "percentage": 64.96, "elapsed_time": "0:18:46", "remaining_time": "0:10:07", "throughput": 6524.76, "total_tokens": 7350464}
{"current_steps": 7660, "total_steps": 11784, "loss": 0.0931, "lr": 6.582118434753973e-07, "epoch": 0.6500339443312967, "percentage": 65.0, "elapsed_time": "0:18:46", "remaining_time": "0:10:06", "throughput": 6526.88, "total_tokens": 7355008}
{"current_steps": 7665, "total_steps": 11784, "loss": 0.0362, "lr": 6.568202356020108e-07, "epoch": 0.6504582484725051, "percentage": 65.05, "elapsed_time": "0:18:47", "remaining_time": "0:10:05", "throughput": 6529.1, "total_tokens": 7359680}
{"current_steps": 7670, "total_steps": 11784, "loss": 0.0404, "lr": 6.554293806333109e-07, "epoch": 0.6508825526137135, "percentage": 65.09, "elapsed_time": "0:18:47", "remaining_time": "0:10:04", "throughput": 6531.01, "total_tokens": 7363968}
{"current_steps": 7670, "total_steps": 11784, "eval_loss": 0.05561085045337677, "epoch": 0.6508825526137135, "percentage": 65.09, "elapsed_time": "0:19:03", "remaining_time": "0:10:13", "throughput": 6440.54, "total_tokens": 7363968}
{"current_steps": 7675, "total_steps": 11784, "loss": 0.108, "lr": 6.540392816207054e-07, "epoch": 0.651306856754922, "percentage": 65.13, "elapsed_time": "0:19:41", "remaining_time": "0:10:32", "throughput": 6237.6, "total_tokens": 7368064}
{"current_steps": 7680, "total_steps": 11784, "loss": 0.0423, "lr": 6.52649941613943e-07, "epoch": 0.6517311608961304, "percentage": 65.17, "elapsed_time": "0:19:41", "remaining_time": "0:10:31", "throughput": 6239.8, "total_tokens": 7372736}
{"current_steps": 7685, "total_steps": 11784, "loss": 0.0361, "lr": 6.512613636611068e-07, "epoch": 0.6521554650373388, "percentage": 65.22, "elapsed_time": "0:19:41", "remaining_time": "0:10:30", "throughput": 6242.17, "total_tokens": 7377600}
{"current_steps": 7690, "total_steps": 11784, "loss": 0.0238, "lr": 6.498735508086093e-07, "epoch": 0.6525797691785472, "percentage": 65.26, "elapsed_time": "0:19:42", "remaining_time": "0:10:29", "throughput": 6244.13, "total_tokens": 7381952}
{"current_steps": 7695, "total_steps": 11784, "loss": 0.0258, "lr": 6.484865061011829e-07, "epoch": 0.6530040733197556, "percentage": 65.3, "elapsed_time": "0:19:42", "remaining_time": "0:10:28", "throughput": 6246.83, "total_tokens": 7387264}
{"current_steps": 7700, "total_steps": 11784, "loss": 0.0708, "lr": 6.471002325818761e-07, "epoch": 0.653428377460964, "percentage": 65.34, "elapsed_time": "0:19:42", "remaining_time": "0:10:27", "throughput": 6249.04, "total_tokens": 7391936}
{"current_steps": 7705, "total_steps": 11784, "loss": 0.0622, "lr": 6.45714733292044e-07, "epoch": 0.6538526816021725, "percentage": 65.39, "elapsed_time": "0:19:43", "remaining_time": "0:10:26", "throughput": 6251.71, "total_tokens": 7397248}
{"current_steps": 7710, "total_steps": 11784, "loss": 0.0741, "lr": 6.443300112713452e-07, "epoch": 0.6542769857433809, "percentage": 65.43, "elapsed_time": "0:19:43", "remaining_time": "0:10:25", "throughput": 6253.9, "total_tokens": 7401920}
{"current_steps": 7715, "total_steps": 11784, "loss": 0.0523, "lr": 6.429460695577309e-07, "epoch": 0.6547012898845893, "percentage": 65.47, "elapsed_time": "0:19:43", "remaining_time": "0:10:24", "throughput": 6256.35, "total_tokens": 7406912}
{"current_steps": 7720, "total_steps": 11784, "loss": 0.0758, "lr": 6.415629111874418e-07, "epoch": 0.6551255940257977, "percentage": 65.51, "elapsed_time": "0:19:44", "remaining_time": "0:10:23", "throughput": 6258.69, "total_tokens": 7411776}
{"current_steps": 7725, "total_steps": 11784, "loss": 0.0585, "lr": 6.401805391949989e-07, "epoch": 0.6555498981670062, "percentage": 65.55, "elapsed_time": "0:19:44", "remaining_time": "0:10:22", "throughput": 6260.67, "total_tokens": 7416128}
{"current_steps": 7730, "total_steps": 11784, "loss": 0.0381, "lr": 6.387989566131996e-07, "epoch": 0.6559742023082146, "percentage": 65.6, "elapsed_time": "0:19:44", "remaining_time": "0:10:21", "throughput": 6263.88, "total_tokens": 7422208}
{"current_steps": 7735, "total_steps": 11784, "loss": 0.0647, "lr": 6.374181664731076e-07, "epoch": 0.656398506449423, "percentage": 65.64, "elapsed_time": "0:19:45", "remaining_time": "0:10:20", "throughput": 6266.17, "total_tokens": 7427008}
{"current_steps": 7740, "total_steps": 11784, "loss": 0.053, "lr": 6.360381718040493e-07, "epoch": 0.6568228105906314, "percentage": 65.68, "elapsed_time": "0:19:45", "remaining_time": "0:10:19", "throughput": 6268.22, "total_tokens": 7431488}
{"current_steps": 7745, "total_steps": 11784, "loss": 0.0645, "lr": 6.34658975633605e-07, "epoch": 0.6572471147318398, "percentage": 65.72, "elapsed_time": "0:19:45", "remaining_time": "0:10:18", "throughput": 6270.69, "total_tokens": 7436544}
{"current_steps": 7750, "total_steps": 11784, "loss": 0.0631, "lr": 6.332805809876041e-07, "epoch": 0.6576714188730483, "percentage": 65.77, "elapsed_time": "0:19:46", "remaining_time": "0:10:17", "throughput": 6272.65, "total_tokens": 7440896}
{"current_steps": 7755, "total_steps": 11784, "loss": 0.1176, "lr": 6.319029908901168e-07, "epoch": 0.6580957230142567, "percentage": 65.81, "elapsed_time": "0:19:46", "remaining_time": "0:10:16", "throughput": 6275.05, "total_tokens": 7445824}
{"current_steps": 7760, "total_steps": 11784, "loss": 0.0954, "lr": 6.305262083634487e-07, "epoch": 0.658520027155465, "percentage": 65.85, "elapsed_time": "0:19:46", "remaining_time": "0:10:15", "throughput": 6277.16, "total_tokens": 7450368}
{"current_steps": 7765, "total_steps": 11784, "loss": 0.0724, "lr": 6.29150236428133e-07, "epoch": 0.6589443312966734, "percentage": 65.89, "elapsed_time": "0:19:47", "remaining_time": "0:10:14", "throughput": 6279.06, "total_tokens": 7454720}
{"current_steps": 7770, "total_steps": 11784, "loss": 0.0929, "lr": 6.277750781029254e-07, "epoch": 0.6593686354378818, "percentage": 65.94, "elapsed_time": "0:19:47", "remaining_time": "0:10:13", "throughput": 6281.15, "total_tokens": 7459264}
{"current_steps": 7775, "total_steps": 11784, "loss": 0.0311, "lr": 6.26400736404796e-07, "epoch": 0.6597929395790902, "percentage": 65.98, "elapsed_time": "0:19:47", "remaining_time": "0:10:12", "throughput": 6283.21, "total_tokens": 7463744}
{"current_steps": 7780, "total_steps": 11784, "loss": 0.0185, "lr": 6.250272143489236e-07, "epoch": 0.6602172437202987, "percentage": 66.02, "elapsed_time": "0:19:48", "remaining_time": "0:10:11", "throughput": 6285.68, "total_tokens": 7468800}
{"current_steps": 7785, "total_steps": 11784, "loss": 0.0711, "lr": 6.23654514948688e-07, "epoch": 0.6606415478615071, "percentage": 66.06, "elapsed_time": "0:19:48", "remaining_time": "0:10:10", "throughput": 6288.14, "total_tokens": 7473856}
{"current_steps": 7790, "total_steps": 11784, "loss": 0.0637, "lr": 6.222826412156659e-07, "epoch": 0.6610658520027155, "percentage": 66.11, "elapsed_time": "0:19:48", "remaining_time": "0:10:09", "throughput": 6290.04, "total_tokens": 7478144}
{"current_steps": 7795, "total_steps": 11784, "loss": 0.0699, "lr": 6.209115961596207e-07, "epoch": 0.6614901561439239, "percentage": 66.15, "elapsed_time": "0:19:49", "remaining_time": "0:10:08", "throughput": 6291.94, "total_tokens": 7482432}
{"current_steps": 7800, "total_steps": 11784, "loss": 0.0804, "lr": 6.195413827884986e-07, "epoch": 0.6619144602851323, "percentage": 66.19, "elapsed_time": "0:19:49", "remaining_time": "0:10:07", "throughput": 6294.39, "total_tokens": 7487488}
{"current_steps": 7805, "total_steps": 11784, "loss": 0.0639, "lr": 6.181720041084216e-07, "epoch": 0.6623387644263408, "percentage": 66.23, "elapsed_time": "0:19:49", "remaining_time": "0:10:06", "throughput": 6296.47, "total_tokens": 7492032}
{"current_steps": 7810, "total_steps": 11784, "loss": 0.0315, "lr": 6.168034631236794e-07, "epoch": 0.6627630685675492, "percentage": 66.28, "elapsed_time": "0:19:50", "remaining_time": "0:10:05", "throughput": 6298.54, "total_tokens": 7496576}
{"current_steps": 7815, "total_steps": 11784, "loss": 0.0285, "lr": 6.154357628367251e-07, "epoch": 0.6631873727087576, "percentage": 66.32, "elapsed_time": "0:19:50", "remaining_time": "0:10:04", "throughput": 6300.58, "total_tokens": 7501056}
{"current_steps": 7820, "total_steps": 11784, "loss": 0.0801, "lr": 6.140689062481657e-07, "epoch": 0.663611676849966, "percentage": 66.36, "elapsed_time": "0:19:50", "remaining_time": "0:10:03", "throughput": 6302.8, "total_tokens": 7505792}
{"current_steps": 7825, "total_steps": 11784, "loss": 0.0378, "lr": 6.127028963567593e-07, "epoch": 0.6640359809911744, "percentage": 66.4, "elapsed_time": "0:19:51", "remaining_time": "0:10:02", "throughput": 6305.05, "total_tokens": 7510528}
{"current_steps": 7830, "total_steps": 11784, "loss": 0.0707, "lr": 6.113377361594048e-07, "epoch": 0.6644602851323829, "percentage": 66.45, "elapsed_time": "0:19:51", "remaining_time": "0:10:01", "throughput": 6307.21, "total_tokens": 7515200}
{"current_steps": 7835, "total_steps": 11784, "loss": 0.0271, "lr": 6.099734286511378e-07, "epoch": 0.6648845892735913, "percentage": 66.49, "elapsed_time": "0:19:51", "remaining_time": "0:10:00", "throughput": 6309.59, "total_tokens": 7520128}
{"current_steps": 7840, "total_steps": 11784, "loss": 0.0496, "lr": 6.086099768251222e-07, "epoch": 0.6653088934147997, "percentage": 66.53, "elapsed_time": "0:19:52", "remaining_time": "0:09:59", "throughput": 6311.56, "total_tokens": 7524544}
{"current_steps": 7845, "total_steps": 11784, "loss": 0.123, "lr": 6.072473836726461e-07, "epoch": 0.6657331975560081, "percentage": 66.57, "elapsed_time": "0:19:52", "remaining_time": "0:09:58", "throughput": 6314.06, "total_tokens": 7529664}
{"current_steps": 7850, "total_steps": 11784, "loss": 0.0509, "lr": 6.058856521831126e-07, "epoch": 0.6661575016972165, "percentage": 66.62, "elapsed_time": "0:19:52", "remaining_time": "0:09:57", "throughput": 6315.8, "total_tokens": 7533760}
{"current_steps": 7855, "total_steps": 11784, "loss": 0.0302, "lr": 6.045247853440349e-07, "epoch": 0.666581805838425, "percentage": 66.66, "elapsed_time": "0:19:53", "remaining_time": "0:09:56", "throughput": 6317.98, "total_tokens": 7538432}
{"current_steps": 7860, "total_steps": 11784, "loss": 0.0664, "lr": 6.031647861410287e-07, "epoch": 0.6670061099796334, "percentage": 66.7, "elapsed_time": "0:19:53", "remaining_time": "0:09:55", "throughput": 6320.19, "total_tokens": 7543168}
{"current_steps": 7865, "total_steps": 11784, "loss": 0.0448, "lr": 6.018056575578074e-07, "epoch": 0.6674304141208418, "percentage": 66.74, "elapsed_time": "0:19:53", "remaining_time": "0:09:54", "throughput": 6322.38, "total_tokens": 7547840}
{"current_steps": 7870, "total_steps": 11784, "loss": 0.0146, "lr": 6.004474025761723e-07, "epoch": 0.6678547182620502, "percentage": 66.79, "elapsed_time": "0:19:54", "remaining_time": "0:09:53", "throughput": 6324.71, "total_tokens": 7552768}
{"current_steps": 7875, "total_steps": 11784, "loss": 0.1316, "lr": 5.990900241760102e-07, "epoch": 0.6682790224032586, "percentage": 66.83, "elapsed_time": "0:19:54", "remaining_time": "0:09:52", "throughput": 6326.8, "total_tokens": 7557312}
{"current_steps": 7880, "total_steps": 11784, "loss": 0.0859, "lr": 5.977335253352833e-07, "epoch": 0.6687033265444671, "percentage": 66.87, "elapsed_time": "0:19:54", "remaining_time": "0:09:51", "throughput": 6328.91, "total_tokens": 7561920}
{"current_steps": 7885, "total_steps": 11784, "loss": 0.0652, "lr": 5.963779090300254e-07, "epoch": 0.6691276306856755, "percentage": 66.91, "elapsed_time": "0:19:55", "remaining_time": "0:09:50", "throughput": 6331.44, "total_tokens": 7567104}
{"current_steps": 7890, "total_steps": 11784, "loss": 0.0364, "lr": 5.950231782343326e-07, "epoch": 0.6695519348268839, "percentage": 66.96, "elapsed_time": "0:19:55", "remaining_time": "0:09:50", "throughput": 6333.46, "total_tokens": 7571584}
{"current_steps": 7895, "total_steps": 11784, "loss": 0.0182, "lr": 5.936693359203597e-07, "epoch": 0.6699762389680923, "percentage": 67.0, "elapsed_time": "0:19:55", "remaining_time": "0:09:49", "throughput": 6335.63, "total_tokens": 7576256}
{"current_steps": 7900, "total_steps": 11784, "loss": 0.0678, "lr": 5.923163850583113e-07, "epoch": 0.6704005431093008, "percentage": 67.04, "elapsed_time": "0:19:56", "remaining_time": "0:09:48", "throughput": 6338.03, "total_tokens": 7581248}
{"current_steps": 7905, "total_steps": 11784, "loss": 0.0382, "lr": 5.909643286164367e-07, "epoch": 0.6708248472505092, "percentage": 67.08, "elapsed_time": "0:19:56", "remaining_time": "0:09:47", "throughput": 6340.23, "total_tokens": 7585984}
{"current_steps": 7910, "total_steps": 11784, "loss": 0.0831, "lr": 5.896131695610223e-07, "epoch": 0.6712491513917176, "percentage": 67.12, "elapsed_time": "0:19:56", "remaining_time": "0:09:46", "throughput": 6342.31, "total_tokens": 7590528}
{"current_steps": 7915, "total_steps": 11784, "loss": 0.0263, "lr": 5.88262910856387e-07, "epoch": 0.671673455532926, "percentage": 67.17, "elapsed_time": "0:19:57", "remaining_time": "0:09:45", "throughput": 6344.55, "total_tokens": 7595328}
{"current_steps": 7920, "total_steps": 11784, "loss": 0.0661, "lr": 5.869135554648728e-07, "epoch": 0.6720977596741344, "percentage": 67.21, "elapsed_time": "0:19:57", "remaining_time": "0:09:44", "throughput": 6346.79, "total_tokens": 7600128}
{"current_steps": 7925, "total_steps": 11784, "loss": 0.0523, "lr": 5.855651063468411e-07, "epoch": 0.6725220638153429, "percentage": 67.25, "elapsed_time": "0:19:57", "remaining_time": "0:09:43", "throughput": 6348.54, "total_tokens": 7604288}
{"current_steps": 7930, "total_steps": 11784, "loss": 0.0387, "lr": 5.84217566460665e-07, "epoch": 0.6729463679565513, "percentage": 67.29, "elapsed_time": "0:19:58", "remaining_time": "0:09:42", "throughput": 6350.93, "total_tokens": 7609280}
{"current_steps": 7935, "total_steps": 11784, "loss": 0.0498, "lr": 5.828709387627217e-07, "epoch": 0.6733706720977597, "percentage": 67.34, "elapsed_time": "0:19:58", "remaining_time": "0:09:41", "throughput": 6353.49, "total_tokens": 7614528}
{"current_steps": 7940, "total_steps": 11784, "loss": 0.112, "lr": 5.815252262073891e-07, "epoch": 0.6737949762389681, "percentage": 67.38, "elapsed_time": "0:19:58", "remaining_time": "0:09:40", "throughput": 6355.69, "total_tokens": 7619264}
{"current_steps": 7945, "total_steps": 11784, "loss": 0.0041, "lr": 5.801804317470349e-07, "epoch": 0.6742192803801765, "percentage": 67.42, "elapsed_time": "0:19:59", "remaining_time": "0:09:39", "throughput": 6358.02, "total_tokens": 7624192}
{"current_steps": 7950, "total_steps": 11784, "loss": 0.0446, "lr": 5.788365583320144e-07, "epoch": 0.674643584521385, "percentage": 67.46, "elapsed_time": "0:19:59", "remaining_time": "0:09:38", "throughput": 6360.33, "total_tokens": 7629120}
{"current_steps": 7955, "total_steps": 11784, "loss": 0.0664, "lr": 5.774936089106617e-07, "epoch": 0.6750678886625934, "percentage": 67.51, "elapsed_time": "0:19:59", "remaining_time": "0:09:37", "throughput": 6362.59, "total_tokens": 7633984}
{"current_steps": 7960, "total_steps": 11784, "loss": 0.0222, "lr": 5.761515864292835e-07, "epoch": 0.6754921928038018, "percentage": 67.55, "elapsed_time": "0:20:00", "remaining_time": "0:09:36", "throughput": 6364.95, "total_tokens": 7638976}
{"current_steps": 7965, "total_steps": 11784, "loss": 0.001, "lr": 5.748104938321534e-07, "epoch": 0.6759164969450102, "percentage": 67.59, "elapsed_time": "0:20:00", "remaining_time": "0:09:35", "throughput": 6367.0, "total_tokens": 7643520}
{"current_steps": 7970, "total_steps": 11784, "loss": 0.0733, "lr": 5.734703340615049e-07, "epoch": 0.6763408010862186, "percentage": 67.63, "elapsed_time": "0:20:00", "remaining_time": "0:09:34", "throughput": 6369.4, "total_tokens": 7648576}
{"current_steps": 7975, "total_steps": 11784, "loss": 0.0419, "lr": 5.721311100575235e-07, "epoch": 0.676765105227427, "percentage": 67.68, "elapsed_time": "0:20:01", "remaining_time": "0:09:33", "throughput": 6371.78, "total_tokens": 7653632}
{"current_steps": 7980, "total_steps": 11784, "loss": 0.0034, "lr": 5.707928247583444e-07, "epoch": 0.6771894093686355, "percentage": 67.72, "elapsed_time": "0:20:01", "remaining_time": "0:09:32", "throughput": 6373.82, "total_tokens": 7658176}
{"current_steps": 7985, "total_steps": 11784, "loss": 0.1114, "lr": 5.694554811000407e-07, "epoch": 0.6776137135098439, "percentage": 67.76, "elapsed_time": "0:20:01", "remaining_time": "0:09:31", "throughput": 6376.09, "total_tokens": 7663040}
{"current_steps": 7990, "total_steps": 11784, "loss": 0.0707, "lr": 5.681190820166213e-07, "epoch": 0.6780380176510523, "percentage": 67.8, "elapsed_time": "0:20:02", "remaining_time": "0:09:30", "throughput": 6378.53, "total_tokens": 7668160}
{"current_steps": 7995, "total_steps": 11784, "loss": 0.0181, "lr": 5.667836304400221e-07, "epoch": 0.6784623217922607, "percentage": 67.85, "elapsed_time": "0:20:02", "remaining_time": "0:09:29", "throughput": 6380.79, "total_tokens": 7673024}
{"current_steps": 8000, "total_steps": 11784, "loss": 0.0702, "lr": 5.654491293001005e-07, "epoch": 0.6788866259334692, "percentage": 67.89, "elapsed_time": "0:20:02", "remaining_time": "0:09:28", "throughput": 6382.91, "total_tokens": 7677696}
{"current_steps": 8005, "total_steps": 11784, "loss": 0.046, "lr": 5.641155815246289e-07, "epoch": 0.6793109300746776, "percentage": 67.93, "elapsed_time": "0:20:03", "remaining_time": "0:09:28", "throughput": 6385.33, "total_tokens": 7682752}
{"current_steps": 8010, "total_steps": 11784, "loss": 0.0835, "lr": 5.62782990039288e-07, "epoch": 0.679735234215886, "percentage": 67.97, "elapsed_time": "0:20:03", "remaining_time": "0:09:27", "throughput": 6387.76, "total_tokens": 7687872}
{"current_steps": 8015, "total_steps": 11784, "loss": 0.0774, "lr": 5.614513577676592e-07, "epoch": 0.6801595383570944, "percentage": 68.02, "elapsed_time": "0:20:03", "remaining_time": "0:09:26", "throughput": 6390.04, "total_tokens": 7692800}
{"current_steps": 8020, "total_steps": 11784, "loss": 0.0339, "lr": 5.601206876312223e-07, "epoch": 0.6805838424983028, "percentage": 68.06, "elapsed_time": "0:20:04", "remaining_time": "0:09:25", "throughput": 6392.13, "total_tokens": 7697472}
{"current_steps": 8025, "total_steps": 11784, "loss": 0.0687, "lr": 5.587909825493433e-07, "epoch": 0.6810081466395111, "percentage": 68.1, "elapsed_time": "0:20:04", "remaining_time": "0:09:24", "throughput": 6394.36, "total_tokens": 7702336}
{"current_steps": 8030, "total_steps": 11784, "loss": 0.0828, "lr": 5.57462245439273e-07, "epoch": 0.6814324507807196, "percentage": 68.14, "elapsed_time": "0:20:04", "remaining_time": "0:09:23", "throughput": 6396.56, "total_tokens": 7707136}
{"current_steps": 8035, "total_steps": 11784, "loss": 0.1116, "lr": 5.561344792161373e-07, "epoch": 0.681856754921928, "percentage": 68.19, "elapsed_time": "0:20:05", "remaining_time": "0:09:22", "throughput": 6398.66, "total_tokens": 7711808}
{"current_steps": 8040, "total_steps": 11784, "loss": 0.0646, "lr": 5.54807686792933e-07, "epoch": 0.6822810590631364, "percentage": 68.23, "elapsed_time": "0:20:05", "remaining_time": "0:09:21", "throughput": 6400.67, "total_tokens": 7716352}
{"current_steps": 8045, "total_steps": 11784, "loss": 0.1109, "lr": 5.534818710805198e-07, "epoch": 0.6827053632043448, "percentage": 68.27, "elapsed_time": "0:20:05", "remaining_time": "0:09:20", "throughput": 6402.77, "total_tokens": 7721024}
{"current_steps": 8050, "total_steps": 11784, "loss": 0.0793, "lr": 5.52157034987615e-07, "epoch": 0.6831296673455532, "percentage": 68.31, "elapsed_time": "0:20:06", "remaining_time": "0:09:19", "throughput": 6405.21, "total_tokens": 7726208}
{"current_steps": 8055, "total_steps": 11784, "loss": 0.0826, "lr": 5.508331814207864e-07, "epoch": 0.6835539714867617, "percentage": 68.36, "elapsed_time": "0:20:06", "remaining_time": "0:09:18", "throughput": 6407.48, "total_tokens": 7731136}
{"current_steps": 8060, "total_steps": 11784, "loss": 0.1033, "lr": 5.495103132844466e-07, "epoch": 0.6839782756279701, "percentage": 68.4, "elapsed_time": "0:20:06", "remaining_time": "0:09:17", "throughput": 6409.4, "total_tokens": 7735552}
{"current_steps": 8065, "total_steps": 11784, "loss": 0.0839, "lr": 5.481884334808463e-07, "epoch": 0.6844025797691785, "percentage": 68.44, "elapsed_time": "0:20:07", "remaining_time": "0:09:16", "throughput": 6411.33, "total_tokens": 7740032}
{"current_steps": 8070, "total_steps": 11784, "loss": 0.0441, "lr": 5.468675449100664e-07, "epoch": 0.6848268839103869, "percentage": 68.48, "elapsed_time": "0:20:07", "remaining_time": "0:09:15", "throughput": 6413.57, "total_tokens": 7744960}
{"current_steps": 8075, "total_steps": 11784, "loss": 0.1324, "lr": 5.455476504700161e-07, "epoch": 0.6852511880515954, "percentage": 68.53, "elapsed_time": "0:20:07", "remaining_time": "0:09:14", "throughput": 6415.64, "total_tokens": 7749632}
{"current_steps": 8080, "total_steps": 11784, "loss": 0.0765, "lr": 5.442287530564203e-07, "epoch": 0.6856754921928038, "percentage": 68.57, "elapsed_time": "0:20:08", "remaining_time": "0:09:13", "throughput": 6417.64, "total_tokens": 7754176}
{"current_steps": 8085, "total_steps": 11784, "loss": 0.1193, "lr": 5.429108555628186e-07, "epoch": 0.6860997963340122, "percentage": 68.61, "elapsed_time": "0:20:08", "remaining_time": "0:09:12", "throughput": 6420.09, "total_tokens": 7759360}
{"current_steps": 8090, "total_steps": 11784, "loss": 0.0654, "lr": 5.415939608805564e-07, "epoch": 0.6865241004752206, "percentage": 68.65, "elapsed_time": "0:20:08", "remaining_time": "0:09:12", "throughput": 6422.1, "total_tokens": 7763904}
{"current_steps": 8095, "total_steps": 11784, "loss": 0.0189, "lr": 5.402780718987789e-07, "epoch": 0.686948404616429, "percentage": 68.69, "elapsed_time": "0:20:09", "remaining_time": "0:09:11", "throughput": 6424.0, "total_tokens": 7768320}
{"current_steps": 8100, "total_steps": 11784, "loss": 0.0697, "lr": 5.389631915044249e-07, "epoch": 0.6873727087576375, "percentage": 68.74, "elapsed_time": "0:20:09", "remaining_time": "0:09:10", "throughput": 6426.07, "total_tokens": 7772928}
{"current_steps": 8105, "total_steps": 11784, "loss": 0.0421, "lr": 5.376493225822208e-07, "epoch": 0.6877970128988459, "percentage": 68.78, "elapsed_time": "0:20:09", "remaining_time": "0:09:09", "throughput": 6427.94, "total_tokens": 7777280}
{"current_steps": 8110, "total_steps": 11784, "loss": 0.0558, "lr": 5.363364680146725e-07, "epoch": 0.6882213170400543, "percentage": 68.82, "elapsed_time": "0:20:10", "remaining_time": "0:09:08", "throughput": 6430.13, "total_tokens": 7782080}
{"current_steps": 8115, "total_steps": 11784, "loss": 0.0597, "lr": 5.350246306820632e-07, "epoch": 0.6886456211812627, "percentage": 68.86, "elapsed_time": "0:20:10", "remaining_time": "0:09:07", "throughput": 6432.32, "total_tokens": 7786880}
{"current_steps": 8120, "total_steps": 11784, "loss": 0.0316, "lr": 5.337138134624412e-07, "epoch": 0.6890699253224711, "percentage": 68.91, "elapsed_time": "0:20:10", "remaining_time": "0:09:06", "throughput": 6434.18, "total_tokens": 7791232}
{"current_steps": 8125, "total_steps": 11784, "loss": 0.0082, "lr": 5.324040192316193e-07, "epoch": 0.6894942294636796, "percentage": 68.95, "elapsed_time": "0:20:11", "remaining_time": "0:09:05", "throughput": 6436.45, "total_tokens": 7796160}
{"current_steps": 8130, "total_steps": 11784, "loss": 0.0278, "lr": 5.310952508631645e-07, "epoch": 0.689918533604888, "percentage": 68.99, "elapsed_time": "0:20:11", "remaining_time": "0:09:04", "throughput": 6438.68, "total_tokens": 7801024}
{"current_steps": 8135, "total_steps": 11784, "loss": 0.0599, "lr": 5.297875112283941e-07, "epoch": 0.6903428377460964, "percentage": 69.03, "elapsed_time": "0:20:11", "remaining_time": "0:09:03", "throughput": 6440.95, "total_tokens": 7805952}
{"current_steps": 8140, "total_steps": 11784, "loss": 0.0434, "lr": 5.284808031963676e-07, "epoch": 0.6907671418873048, "percentage": 69.08, "elapsed_time": "0:20:12", "remaining_time": "0:09:02", "throughput": 6443.28, "total_tokens": 7811008}
{"current_steps": 8145, "total_steps": 11784, "loss": 0.0109, "lr": 5.271751296338822e-07, "epoch": 0.6911914460285132, "percentage": 69.12, "elapsed_time": "0:20:12", "remaining_time": "0:09:01", "throughput": 6445.08, "total_tokens": 7815296}
{"current_steps": 8150, "total_steps": 11784, "loss": 0.0378, "lr": 5.25870493405464e-07, "epoch": 0.6916157501697217, "percentage": 69.16, "elapsed_time": "0:20:12", "remaining_time": "0:09:00", "throughput": 6447.78, "total_tokens": 7820864}
{"current_steps": 8155, "total_steps": 11784, "loss": 0.0569, "lr": 5.245668973733657e-07, "epoch": 0.6920400543109301, "percentage": 69.2, "elapsed_time": "0:20:13", "remaining_time": "0:08:59", "throughput": 6450.07, "total_tokens": 7825856}
{"current_steps": 8160, "total_steps": 11784, "loss": 0.0184, "lr": 5.232643443975553e-07, "epoch": 0.6924643584521385, "percentage": 69.25, "elapsed_time": "0:20:13", "remaining_time": "0:08:58", "throughput": 6452.05, "total_tokens": 7830400}
{"current_steps": 8165, "total_steps": 11784, "loss": 0.0032, "lr": 5.219628373357142e-07, "epoch": 0.6928886625933469, "percentage": 69.29, "elapsed_time": "0:20:13", "remaining_time": "0:08:58", "throughput": 6454.6, "total_tokens": 7835776}
{"current_steps": 8170, "total_steps": 11784, "loss": 0.0689, "lr": 5.206623790432285e-07, "epoch": 0.6933129667345553, "percentage": 69.33, "elapsed_time": "0:20:14", "remaining_time": "0:08:57", "throughput": 6456.77, "total_tokens": 7840640}
{"current_steps": 8175, "total_steps": 11784, "loss": 0.0707, "lr": 5.193629723731837e-07, "epoch": 0.6937372708757638, "percentage": 69.37, "elapsed_time": "0:20:14", "remaining_time": "0:08:56", "throughput": 6458.71, "total_tokens": 7845120}
{"current_steps": 8180, "total_steps": 11784, "loss": 0.0528, "lr": 5.180646201763577e-07, "epoch": 0.6941615750169722, "percentage": 69.42, "elapsed_time": "0:20:14", "remaining_time": "0:08:55", "throughput": 6460.71, "total_tokens": 7849664}
{"current_steps": 8185, "total_steps": 11784, "loss": 0.008, "lr": 5.167673253012152e-07, "epoch": 0.6945858791581806, "percentage": 69.46, "elapsed_time": "0:20:15", "remaining_time": "0:08:54", "throughput": 6462.59, "total_tokens": 7854080}
{"current_steps": 8190, "total_steps": 11784, "loss": 0.0412, "lr": 5.154710905939015e-07, "epoch": 0.695010183299389, "percentage": 69.5, "elapsed_time": "0:20:15", "remaining_time": "0:08:53", "throughput": 6464.2, "total_tokens": 7858176}
{"current_steps": 8195, "total_steps": 11784, "loss": 0.0572, "lr": 5.141759188982356e-07, "epoch": 0.6954344874405974, "percentage": 69.54, "elapsed_time": "0:20:15", "remaining_time": "0:08:52", "throughput": 6466.32, "total_tokens": 7862912}
{"current_steps": 8200, "total_steps": 11784, "loss": 0.0708, "lr": 5.12881813055705e-07, "epoch": 0.6958587915818059, "percentage": 69.59, "elapsed_time": "0:20:16", "remaining_time": "0:08:51", "throughput": 6468.41, "total_tokens": 7867648}
{"current_steps": 8205, "total_steps": 11784, "loss": 0.1211, "lr": 5.115887759054571e-07, "epoch": 0.6962830957230143, "percentage": 69.63, "elapsed_time": "0:20:16", "remaining_time": "0:08:50", "throughput": 6471.04, "total_tokens": 7873152}
{"current_steps": 8210, "total_steps": 11784, "loss": 0.0675, "lr": 5.102968102842973e-07, "epoch": 0.6967073998642227, "percentage": 69.67, "elapsed_time": "0:20:17", "remaining_time": "0:08:49", "throughput": 6473.1, "total_tokens": 7877824}
{"current_steps": 8215, "total_steps": 11784, "loss": 0.0948, "lr": 5.090059190266779e-07, "epoch": 0.6971317040054311, "percentage": 69.71, "elapsed_time": "0:20:17", "remaining_time": "0:08:48", "throughput": 6475.3, "total_tokens": 7882688}
{"current_steps": 8220, "total_steps": 11784, "loss": 0.0272, "lr": 5.077161049646951e-07, "epoch": 0.6975560081466395, "percentage": 69.76, "elapsed_time": "0:20:17", "remaining_time": "0:08:47", "throughput": 6477.4, "total_tokens": 7887424}
{"current_steps": 8225, "total_steps": 11784, "loss": 0.0328, "lr": 5.06427370928082e-07, "epoch": 0.697980312287848, "percentage": 69.8, "elapsed_time": "0:20:18", "remaining_time": "0:08:47", "throughput": 6479.09, "total_tokens": 7891584}
{"current_steps": 8230, "total_steps": 11784, "loss": 0.1217, "lr": 5.05139719744202e-07, "epoch": 0.6984046164290564, "percentage": 69.84, "elapsed_time": "0:20:18", "remaining_time": "0:08:46", "throughput": 6481.37, "total_tokens": 7896576}
{"current_steps": 8235, "total_steps": 11784, "loss": 0.0685, "lr": 5.038531542380425e-07, "epoch": 0.6988289205702648, "percentage": 69.88, "elapsed_time": "0:20:18", "remaining_time": "0:08:45", "throughput": 6483.52, "total_tokens": 7901376}
{"current_steps": 8240, "total_steps": 11784, "loss": 0.0305, "lr": 5.025676772322099e-07, "epoch": 0.6992532247114732, "percentage": 69.93, "elapsed_time": "0:20:19", "remaining_time": "0:08:44", "throughput": 6485.79, "total_tokens": 7906368}
{"current_steps": 8245, "total_steps": 11784, "loss": 0.0503, "lr": 5.012832915469207e-07, "epoch": 0.6996775288526816, "percentage": 69.97, "elapsed_time": "0:20:19", "remaining_time": "0:08:43", "throughput": 6487.98, "total_tokens": 7911232}
{"current_steps": 8250, "total_steps": 11784, "loss": 0.0654, "lr": 5.000000000000002e-07, "epoch": 0.7001018329938901, "percentage": 70.01, "elapsed_time": "0:20:19", "remaining_time": "0:08:42", "throughput": 6489.93, "total_tokens": 7915776}
{"current_steps": 8255, "total_steps": 11784, "loss": 0.0226, "lr": 4.987178054068699e-07, "epoch": 0.7005261371350985, "percentage": 70.05, "elapsed_time": "0:20:20", "remaining_time": "0:08:41", "throughput": 6491.78, "total_tokens": 7920192}
{"current_steps": 8260, "total_steps": 11784, "loss": 0.0633, "lr": 4.97436710580547e-07, "epoch": 0.7009504412763069, "percentage": 70.1, "elapsed_time": "0:20:20", "remaining_time": "0:08:40", "throughput": 6493.77, "total_tokens": 7924800}
{"current_steps": 8260, "total_steps": 11784, "eval_loss": 0.0545908585190773, "epoch": 0.7009504412763069, "percentage": 70.1, "elapsed_time": "0:20:36", "remaining_time": "0:08:47", "throughput": 6410.12, "total_tokens": 7924800}
{"current_steps": 8265, "total_steps": 11784, "loss": 0.0334, "lr": 4.961567183316348e-07, "epoch": 0.7013747454175153, "percentage": 70.14, "elapsed_time": "0:21:08", "remaining_time": "0:09:00", "throughput": 6252.26, "total_tokens": 7929664}
{"current_steps": 8270, "total_steps": 11784, "loss": 0.1168, "lr": 4.948778314683183e-07, "epoch": 0.7017990495587237, "percentage": 70.18, "elapsed_time": "0:21:08", "remaining_time": "0:08:59", "throughput": 6254.41, "total_tokens": 7934464}
{"current_steps": 8275, "total_steps": 11784, "loss": 0.0608, "lr": 4.93600052796357e-07, "epoch": 0.7022233536999322, "percentage": 70.22, "elapsed_time": "0:21:08", "remaining_time": "0:08:58", "throughput": 6256.56, "total_tokens": 7939264}
{"current_steps": 8280, "total_steps": 11784, "loss": 0.0751, "lr": 4.923233851190794e-07, "epoch": 0.7026476578411406, "percentage": 70.26, "elapsed_time": "0:21:09", "remaining_time": "0:08:57", "throughput": 6258.33, "total_tokens": 7943552}
{"current_steps": 8285, "total_steps": 11784, "loss": 0.0151, "lr": 4.910478312373756e-07, "epoch": 0.703071961982349, "percentage": 70.31, "elapsed_time": "0:21:09", "remaining_time": "0:08:56", "throughput": 6260.25, "total_tokens": 7948032}
{"current_steps": 8290, "total_steps": 11784, "loss": 0.0642, "lr": 4.897733939496942e-07, "epoch": 0.7034962661235573, "percentage": 70.35, "elapsed_time": "0:21:09", "remaining_time": "0:08:55", "throughput": 6262.78, "total_tokens": 7953408}
{"current_steps": 8295, "total_steps": 11784, "loss": 0.0675, "lr": 4.885000760520317e-07, "epoch": 0.7039205702647657, "percentage": 70.39, "elapsed_time": "0:21:10", "remaining_time": "0:08:54", "throughput": 6264.6, "total_tokens": 7957760}
{"current_steps": 8300, "total_steps": 11784, "loss": 0.035, "lr": 4.872278803379299e-07, "epoch": 0.7043448744059742, "percentage": 70.43, "elapsed_time": "0:21:10", "remaining_time": "0:08:53", "throughput": 6267.5, "total_tokens": 7963712}
{"current_steps": 8305, "total_steps": 11784, "loss": 0.0596, "lr": 4.8595680959847e-07, "epoch": 0.7047691785471826, "percentage": 70.48, "elapsed_time": "0:21:10", "remaining_time": "0:08:52", "throughput": 6269.69, "total_tokens": 7968576}
{"current_steps": 8310, "total_steps": 11784, "loss": 0.0847, "lr": 4.846868666222622e-07, "epoch": 0.705193482688391, "percentage": 70.52, "elapsed_time": "0:21:11", "remaining_time": "0:08:51", "throughput": 6271.69, "total_tokens": 7973184}
{"current_steps": 8315, "total_steps": 11784, "loss": 0.0375, "lr": 4.834180541954447e-07, "epoch": 0.7056177868295994, "percentage": 70.56, "elapsed_time": "0:21:11", "remaining_time": "0:08:50", "throughput": 6273.68, "total_tokens": 7977792}
{"current_steps": 8320, "total_steps": 11784, "loss": 0.0239, "lr": 4.821503751016745e-07, "epoch": 0.7060420909708078, "percentage": 70.6, "elapsed_time": "0:21:11", "remaining_time": "0:08:49", "throughput": 6275.26, "total_tokens": 7981824}
{"current_steps": 8325, "total_steps": 11784, "loss": 0.0527, "lr": 4.808838321221226e-07, "epoch": 0.7064663951120163, "percentage": 70.65, "elapsed_time": "0:21:12", "remaining_time": "0:08:48", "throughput": 6277.03, "total_tokens": 7986112}
{"current_steps": 8330, "total_steps": 11784, "loss": 0.1099, "lr": 4.79618428035467e-07, "epoch": 0.7068906992532247, "percentage": 70.69, "elapsed_time": "0:21:12", "remaining_time": "0:08:47", "throughput": 6278.95, "total_tokens": 7990592}
{"current_steps": 8335, "total_steps": 11784, "loss": 0.1138, "lr": 4.78354165617888e-07, "epoch": 0.7073150033944331, "percentage": 70.73, "elapsed_time": "0:21:12", "remaining_time": "0:08:46", "throughput": 6280.9, "total_tokens": 7995136}
{"current_steps": 8340, "total_steps": 11784, "loss": 0.0542, "lr": 4.77091047643059e-07, "epoch": 0.7077393075356415, "percentage": 70.77, "elapsed_time": "0:21:13", "remaining_time": "0:08:45", "throughput": 6283.01, "total_tokens": 7999872}
{"current_steps": 8345, "total_steps": 11784, "loss": 0.0385, "lr": 4.7582907688214593e-07, "epoch": 0.7081636116768499, "percentage": 70.82, "elapsed_time": "0:21:13", "remaining_time": "0:08:44", "throughput": 6285.09, "total_tokens": 8004608}
{"current_steps": 8350, "total_steps": 11784, "loss": 0.0206, "lr": 4.745682561037947e-07, "epoch": 0.7085879158180584, "percentage": 70.86, "elapsed_time": "0:21:13", "remaining_time": "0:08:43", "throughput": 6286.96, "total_tokens": 8009024}
{"current_steps": 8355, "total_steps": 11784, "loss": 0.0727, "lr": 4.733085880741301e-07, "epoch": 0.7090122199592668, "percentage": 70.9, "elapsed_time": "0:21:14", "remaining_time": "0:08:42", "throughput": 6288.87, "total_tokens": 8013504}
{"current_steps": 8360, "total_steps": 11784, "loss": 0.0952, "lr": 4.7205007555674714e-07, "epoch": 0.7094365241004752, "percentage": 70.94, "elapsed_time": "0:21:14", "remaining_time": "0:08:42", "throughput": 6291.09, "total_tokens": 8018432}
{"current_steps": 8365, "total_steps": 11784, "loss": 0.0025, "lr": 4.707927213127062e-07, "epoch": 0.7098608282416836, "percentage": 70.99, "elapsed_time": "0:21:14", "remaining_time": "0:08:41", "throughput": 6292.95, "total_tokens": 8022848}
{"current_steps": 8370, "total_steps": 11784, "loss": 0.0645, "lr": 4.6953652810052615e-07, "epoch": 0.710285132382892, "percentage": 71.03, "elapsed_time": "0:21:15", "remaining_time": "0:08:40", "throughput": 6294.88, "total_tokens": 8027392}
{"current_steps": 8375, "total_steps": 11784, "loss": 0.154, "lr": 4.682814986761792e-07, "epoch": 0.7107094365241005, "percentage": 71.07, "elapsed_time": "0:21:15", "remaining_time": "0:08:39", "throughput": 6297.29, "total_tokens": 8032640}
{"current_steps": 8380, "total_steps": 11784, "loss": 0.0511, "lr": 4.670276357930828e-07, "epoch": 0.7111337406653089, "percentage": 71.11, "elapsed_time": "0:21:15", "remaining_time": "0:08:38", "throughput": 6299.33, "total_tokens": 8037312}
{"current_steps": 8385, "total_steps": 11784, "loss": 0.1108, "lr": 4.657749422020979e-07, "epoch": 0.7115580448065173, "percentage": 71.16, "elapsed_time": "0:21:16", "remaining_time": "0:08:37", "throughput": 6301.54, "total_tokens": 8042240}
{"current_steps": 8390, "total_steps": 11784, "loss": 0.0449, "lr": 4.6452342065151704e-07, "epoch": 0.7119823489477257, "percentage": 71.2, "elapsed_time": "0:21:16", "remaining_time": "0:08:36", "throughput": 6303.87, "total_tokens": 8047360}
{"current_steps": 8395, "total_steps": 11784, "loss": 0.0763, "lr": 4.632730738870634e-07, "epoch": 0.7124066530889341, "percentage": 71.24, "elapsed_time": "0:21:16", "remaining_time": "0:08:35", "throughput": 6305.94, "total_tokens": 8052096}
{"current_steps": 8400, "total_steps": 11784, "loss": 0.0305, "lr": 4.6202390465188225e-07, "epoch": 0.7128309572301426, "percentage": 71.28, "elapsed_time": "0:21:17", "remaining_time": "0:08:34", "throughput": 6308.1, "total_tokens": 8056960}
{"current_steps": 8405, "total_steps": 11784, "loss": 0.0582, "lr": 4.6077591568653575e-07, "epoch": 0.713255261371351, "percentage": 71.33, "elapsed_time": "0:21:17", "remaining_time": "0:08:33", "throughput": 6310.08, "total_tokens": 8061568}
{"current_steps": 8410, "total_steps": 11784, "loss": 0.0432, "lr": 4.595291097289952e-07, "epoch": 0.7136795655125594, "percentage": 71.37, "elapsed_time": "0:21:17", "remaining_time": "0:08:32", "throughput": 6312.36, "total_tokens": 8066624}
{"current_steps": 8415, "total_steps": 11784, "loss": 0.0634, "lr": 4.582834895146391e-07, "epoch": 0.7141038696537678, "percentage": 71.41, "elapsed_time": "0:21:18", "remaining_time": "0:08:31", "throughput": 6314.64, "total_tokens": 8071680}
{"current_steps": 8420, "total_steps": 11784, "loss": 0.061, "lr": 4.5703905777624184e-07, "epoch": 0.7145281737949762, "percentage": 71.45, "elapsed_time": "0:21:18", "remaining_time": "0:08:30", "throughput": 6316.72, "total_tokens": 8076480}
{"current_steps": 8425, "total_steps": 11784, "loss": 0.0268, "lr": 4.5579581724397255e-07, "epoch": 0.7149524779361847, "percentage": 71.5, "elapsed_time": "0:21:18", "remaining_time": "0:08:29", "throughput": 6318.48, "total_tokens": 8080768}
{"current_steps": 8430, "total_steps": 11784, "loss": 0.0509, "lr": 4.5455377064538603e-07, "epoch": 0.7153767820773931, "percentage": 71.54, "elapsed_time": "0:21:19", "remaining_time": "0:08:28", "throughput": 6320.39, "total_tokens": 8085248}
{"current_steps": 8435, "total_steps": 11784, "loss": 0.0485, "lr": 4.533129207054167e-07, "epoch": 0.7158010862186015, "percentage": 71.58, "elapsed_time": "0:21:19", "remaining_time": "0:08:28", "throughput": 6322.62, "total_tokens": 8090176}
{"current_steps": 8440, "total_steps": 11784, "loss": 0.0764, "lr": 4.520732701463762e-07, "epoch": 0.7162253903598099, "percentage": 71.62, "elapsed_time": "0:21:19", "remaining_time": "0:08:27", "throughput": 6324.38, "total_tokens": 8094464}
{"current_steps": 8445, "total_steps": 11784, "loss": 0.1021, "lr": 4.508348216879421e-07, "epoch": 0.7166496945010183, "percentage": 71.66, "elapsed_time": "0:21:20", "remaining_time": "0:08:26", "throughput": 6326.32, "total_tokens": 8099008}
{"current_steps": 8450, "total_steps": 11784, "loss": 0.0745, "lr": 4.4959757804715613e-07, "epoch": 0.7170739986422268, "percentage": 71.71, "elapsed_time": "0:21:20", "remaining_time": "0:08:25", "throughput": 6328.73, "total_tokens": 8104256}
{"current_steps": 8455, "total_steps": 11784, "loss": 0.0703, "lr": 4.483615419384167e-07, "epoch": 0.7174983027834352, "percentage": 71.75, "elapsed_time": "0:21:20", "remaining_time": "0:08:24", "throughput": 6330.82, "total_tokens": 8109056}
{"current_steps": 8460, "total_steps": 11784, "loss": 0.1058, "lr": 4.4712671607347307e-07, "epoch": 0.7179226069246436, "percentage": 71.79, "elapsed_time": "0:21:21", "remaining_time": "0:08:23", "throughput": 6333.14, "total_tokens": 8114176}
{"current_steps": 8465, "total_steps": 11784, "loss": 0.0812, "lr": 4.458931031614179e-07, "epoch": 0.718346911065852, "percentage": 71.83, "elapsed_time": "0:21:21", "remaining_time": "0:08:22", "throughput": 6335.42, "total_tokens": 8119232}
{"current_steps": 8470, "total_steps": 11784, "loss": 0.0612, "lr": 4.4466070590868543e-07, "epoch": 0.7187712152070604, "percentage": 71.88, "elapsed_time": "0:21:21", "remaining_time": "0:08:21", "throughput": 6337.39, "total_tokens": 8123840}
{"current_steps": 8475, "total_steps": 11784, "loss": 0.1036, "lr": 4.434295270190402e-07, "epoch": 0.7191955193482689, "percentage": 71.92, "elapsed_time": "0:21:22", "remaining_time": "0:08:20", "throughput": 6339.24, "total_tokens": 8128256}
{"current_steps": 8480, "total_steps": 11784, "loss": 0.0321, "lr": 4.4219956919357546e-07, "epoch": 0.7196198234894773, "percentage": 71.96, "elapsed_time": "0:21:22", "remaining_time": "0:08:19", "throughput": 6341.63, "total_tokens": 8133504}
{"current_steps": 8485, "total_steps": 11784, "loss": 0.0123, "lr": 4.409708351307049e-07, "epoch": 0.7200441276306857, "percentage": 72.0, "elapsed_time": "0:21:22", "remaining_time": "0:08:18", "throughput": 6343.64, "total_tokens": 8138176}
{"current_steps": 8490, "total_steps": 11784, "loss": 0.0502, "lr": 4.3974332752615727e-07, "epoch": 0.7204684317718941, "percentage": 72.05, "elapsed_time": "0:21:23", "remaining_time": "0:08:17", "throughput": 6345.83, "total_tokens": 8143104}
{"current_steps": 8495, "total_steps": 11784, "loss": 0.028, "lr": 4.385170490729712e-07, "epoch": 0.7208927359131025, "percentage": 72.09, "elapsed_time": "0:21:23", "remaining_time": "0:08:16", "throughput": 6347.7, "total_tokens": 8147584}
{"current_steps": 8500, "total_steps": 11784, "loss": 0.1012, "lr": 4.3729200246148835e-07, "epoch": 0.721317040054311, "percentage": 72.13, "elapsed_time": "0:21:23", "remaining_time": "0:08:16", "throughput": 6350.13, "total_tokens": 8152896}
{"current_steps": 8505, "total_steps": 11784, "loss": 0.0263, "lr": 4.3606819037934673e-07, "epoch": 0.7217413441955194, "percentage": 72.17, "elapsed_time": "0:21:24", "remaining_time": "0:08:15", "throughput": 6352.69, "total_tokens": 8158400}
{"current_steps": 8510, "total_steps": 11784, "loss": 0.0805, "lr": 4.348456155114786e-07, "epoch": 0.7221656483367278, "percentage": 72.22, "elapsed_time": "0:21:24", "remaining_time": "0:08:14", "throughput": 6355.01, "total_tokens": 8163520}
{"current_steps": 8515, "total_steps": 11784, "loss": 0.0636, "lr": 4.336242805400989e-07, "epoch": 0.7225899524779362, "percentage": 72.26, "elapsed_time": "0:21:24", "remaining_time": "0:08:13", "throughput": 6357.05, "total_tokens": 8168256}
{"current_steps": 8520, "total_steps": 11784, "loss": 0.0225, "lr": 4.324041881447041e-07, "epoch": 0.7230142566191446, "percentage": 72.3, "elapsed_time": "0:21:25", "remaining_time": "0:08:12", "throughput": 6359.07, "total_tokens": 8172928}
{"current_steps": 8525, "total_steps": 11784, "loss": 0.033, "lr": 4.311853410020643e-07, "epoch": 0.7234385607603531, "percentage": 72.34, "elapsed_time": "0:21:25", "remaining_time": "0:08:11", "throughput": 6361.15, "total_tokens": 8177728}
{"current_steps": 8530, "total_steps": 11784, "loss": 0.0376, "lr": 4.299677417862173e-07, "epoch": 0.7238628649015615, "percentage": 72.39, "elapsed_time": "0:21:25", "remaining_time": "0:08:10", "throughput": 6363.08, "total_tokens": 8182272}
{"current_steps": 8535, "total_steps": 11784, "loss": 0.142, "lr": 4.287513931684634e-07, "epoch": 0.7242871690427699, "percentage": 72.43, "elapsed_time": "0:21:26", "remaining_time": "0:08:09", "throughput": 6365.64, "total_tokens": 8187776}
{"current_steps": 8540, "total_steps": 11784, "loss": 0.0742, "lr": 4.2753629781735936e-07, "epoch": 0.7247114731839783, "percentage": 72.47, "elapsed_time": "0:21:26", "remaining_time": "0:08:08", "throughput": 6368.0, "total_tokens": 8192960}
{"current_steps": 8545, "total_steps": 11784, "loss": 0.1659, "lr": 4.2632245839871095e-07, "epoch": 0.7251357773251867, "percentage": 72.51, "elapsed_time": "0:21:26", "remaining_time": "0:08:07", "throughput": 6370.13, "total_tokens": 8197824}
{"current_steps": 8550, "total_steps": 11784, "loss": 0.0614, "lr": 4.251098775755708e-07, "epoch": 0.7255600814663951, "percentage": 72.56, "elapsed_time": "0:21:27", "remaining_time": "0:08:06", "throughput": 6372.39, "total_tokens": 8202880}
{"current_steps": 8555, "total_steps": 11784, "loss": 0.1057, "lr": 4.238985580082293e-07, "epoch": 0.7259843856076035, "percentage": 72.6, "elapsed_time": "0:21:27", "remaining_time": "0:08:05", "throughput": 6374.38, "total_tokens": 8207552}
{"current_steps": 8560, "total_steps": 11784, "loss": 0.0801, "lr": 4.2268850235420827e-07, "epoch": 0.7264086897488119, "percentage": 72.64, "elapsed_time": "0:21:27", "remaining_time": "0:08:05", "throughput": 6376.67, "total_tokens": 8212672}
{"current_steps": 8565, "total_steps": 11784, "loss": 0.0461, "lr": 4.214797132682596e-07, "epoch": 0.7268329938900203, "percentage": 72.68, "elapsed_time": "0:21:28", "remaining_time": "0:08:04", "throughput": 6379.99, "total_tokens": 8219392}
{"current_steps": 8570, "total_steps": 11784, "loss": 0.0472, "lr": 4.202721934023536e-07, "epoch": 0.7272572980312287, "percentage": 72.73, "elapsed_time": "0:21:28", "remaining_time": "0:08:03", "throughput": 6381.96, "total_tokens": 8224064}
{"current_steps": 8575, "total_steps": 11784, "loss": 0.0636, "lr": 4.19065945405678e-07, "epoch": 0.7276816021724372, "percentage": 72.77, "elapsed_time": "0:21:28", "remaining_time": "0:08:02", "throughput": 6384.36, "total_tokens": 8229376}
{"current_steps": 8580, "total_steps": 11784, "loss": 0.0224, "lr": 4.17860971924629e-07, "epoch": 0.7281059063136456, "percentage": 72.81, "elapsed_time": "0:21:29", "remaining_time": "0:08:01", "throughput": 6386.84, "total_tokens": 8234816}
{"current_steps": 8585, "total_steps": 11784, "loss": 0.0674, "lr": 4.166572756028073e-07, "epoch": 0.728530210454854, "percentage": 72.85, "elapsed_time": "0:21:29", "remaining_time": "0:08:00", "throughput": 6388.88, "total_tokens": 8239552}
{"current_steps": 8590, "total_steps": 11784, "loss": 0.0569, "lr": 4.154548590810113e-07, "epoch": 0.7289545145960624, "percentage": 72.9, "elapsed_time": "0:21:29", "remaining_time": "0:07:59", "throughput": 6390.6, "total_tokens": 8243840}
{"current_steps": 8595, "total_steps": 11784, "loss": 0.1121, "lr": 4.14253724997232e-07, "epoch": 0.7293788187372708, "percentage": 72.94, "elapsed_time": "0:21:30", "remaining_time": "0:07:58", "throughput": 6392.85, "total_tokens": 8248960}
{"current_steps": 8600, "total_steps": 11784, "loss": 0.0483, "lr": 4.1305387598664567e-07, "epoch": 0.7298031228784793, "percentage": 72.98, "elapsed_time": "0:21:30", "remaining_time": "0:07:57", "throughput": 6395.0, "total_tokens": 8253888}
{"current_steps": 8605, "total_steps": 11784, "loss": 0.0628, "lr": 4.118553146816115e-07, "epoch": 0.7302274270196877, "percentage": 73.02, "elapsed_time": "0:21:31", "remaining_time": "0:07:56", "throughput": 6397.15, "total_tokens": 8258816}
{"current_steps": 8610, "total_steps": 11784, "loss": 0.0508, "lr": 4.1065804371166114e-07, "epoch": 0.7306517311608961, "percentage": 73.07, "elapsed_time": "0:21:31", "remaining_time": "0:07:56", "throughput": 6399.08, "total_tokens": 8263424}
{"current_steps": 8615, "total_steps": 11784, "loss": 0.0554, "lr": 4.0946206570349685e-07, "epoch": 0.7310760353021045, "percentage": 73.11, "elapsed_time": "0:21:31", "remaining_time": "0:07:55", "throughput": 6401.17, "total_tokens": 8268288}
{"current_steps": 8620, "total_steps": 11784, "loss": 0.0945, "lr": 4.082673832809838e-07, "epoch": 0.7315003394433129, "percentage": 73.15, "elapsed_time": "0:21:32", "remaining_time": "0:07:54", "throughput": 6403.3, "total_tokens": 8273152}
{"current_steps": 8625, "total_steps": 11784, "loss": 0.0166, "lr": 4.0707399906514483e-07, "epoch": 0.7319246435845214, "percentage": 73.19, "elapsed_time": "0:21:32", "remaining_time": "0:07:53", "throughput": 6405.41, "total_tokens": 8278016}
{"current_steps": 8630, "total_steps": 11784, "loss": 0.0345, "lr": 4.058819156741545e-07, "epoch": 0.7323489477257298, "percentage": 73.23, "elapsed_time": "0:21:32", "remaining_time": "0:07:52", "throughput": 6407.85, "total_tokens": 8283392}
{"current_steps": 8635, "total_steps": 11784, "loss": 0.0519, "lr": 4.0469113572333426e-07, "epoch": 0.7327732518669382, "percentage": 73.28, "elapsed_time": "0:21:33", "remaining_time": "0:07:51", "throughput": 6409.82, "total_tokens": 8288064}
{"current_steps": 8640, "total_steps": 11784, "loss": 0.0699, "lr": 4.03501661825144e-07, "epoch": 0.7331975560081466, "percentage": 73.32, "elapsed_time": "0:21:33", "remaining_time": "0:07:50", "throughput": 6411.75, "total_tokens": 8292672}
{"current_steps": 8645, "total_steps": 11784, "loss": 0.09, "lr": 4.023134965891809e-07, "epoch": 0.733621860149355, "percentage": 73.36, "elapsed_time": "0:21:33", "remaining_time": "0:07:49", "throughput": 6413.7, "total_tokens": 8297344}
{"current_steps": 8650, "total_steps": 11784, "loss": 0.0495, "lr": 4.0112664262216866e-07, "epoch": 0.7340461642905635, "percentage": 73.4, "elapsed_time": "0:21:34", "remaining_time": "0:07:48", "throughput": 6415.7, "total_tokens": 8302080}
{"current_steps": 8655, "total_steps": 11784, "loss": 0.1092, "lr": 3.9994110252795563e-07, "epoch": 0.7344704684317719, "percentage": 73.45, "elapsed_time": "0:21:34", "remaining_time": "0:07:47", "throughput": 6417.82, "total_tokens": 8307008}
{"current_steps": 8660, "total_steps": 11784, "loss": 0.0748, "lr": 3.987568789075072e-07, "epoch": 0.7348947725729803, "percentage": 73.49, "elapsed_time": "0:21:34", "remaining_time": "0:07:47", "throughput": 6420.03, "total_tokens": 8312064}
{"current_steps": 8665, "total_steps": 11784, "loss": 0.0264, "lr": 3.975739743589004e-07, "epoch": 0.7353190767141887, "percentage": 73.53, "elapsed_time": "0:21:35", "remaining_time": "0:07:46", "throughput": 6421.82, "total_tokens": 8316480}
{"current_steps": 8670, "total_steps": 11784, "loss": 0.024, "lr": 3.9639239147731864e-07, "epoch": 0.7357433808553971, "percentage": 73.57, "elapsed_time": "0:21:35", "remaining_time": "0:07:45", "throughput": 6424.13, "total_tokens": 8321664}
{"current_steps": 8675, "total_steps": 11784, "loss": 0.0706, "lr": 3.952121328550455e-07, "epoch": 0.7361676849966056, "percentage": 73.62, "elapsed_time": "0:21:35", "remaining_time": "0:07:44", "throughput": 6425.87, "total_tokens": 8326016}
{"current_steps": 8680, "total_steps": 11784, "loss": 0.01, "lr": 3.9403320108145943e-07, "epoch": 0.736591989137814, "percentage": 73.66, "elapsed_time": "0:21:36", "remaining_time": "0:07:43", "throughput": 6427.82, "total_tokens": 8330688}
{"current_steps": 8685, "total_steps": 11784, "loss": 0.0251, "lr": 3.928555987430275e-07, "epoch": 0.7370162932790224, "percentage": 73.7, "elapsed_time": "0:21:36", "remaining_time": "0:07:42", "throughput": 6429.93, "total_tokens": 8335552}
{"current_steps": 8690, "total_steps": 11784, "loss": 0.0294, "lr": 3.916793284233011e-07, "epoch": 0.7374405974202308, "percentage": 73.74, "elapsed_time": "0:21:36", "remaining_time": "0:07:41", "throughput": 6431.86, "total_tokens": 8340224}
{"current_steps": 8695, "total_steps": 11784, "loss": 0.0556, "lr": 3.9050439270290733e-07, "epoch": 0.7378649015614392, "percentage": 73.79, "elapsed_time": "0:21:37", "remaining_time": "0:07:40", "throughput": 6433.89, "total_tokens": 8345024}
{"current_steps": 8700, "total_steps": 11784, "loss": 0.0438, "lr": 3.8933079415954805e-07, "epoch": 0.7382892057026477, "percentage": 73.83, "elapsed_time": "0:21:37", "remaining_time": "0:07:39", "throughput": 6435.79, "total_tokens": 8349632}
{"current_steps": 8705, "total_steps": 11784, "loss": 0.0502, "lr": 3.8815853536798905e-07, "epoch": 0.7387135098438561, "percentage": 73.87, "elapsed_time": "0:21:37", "remaining_time": "0:07:39", "throughput": 6437.94, "total_tokens": 8354624}
{"current_steps": 8710, "total_steps": 11784, "loss": 0.0513, "lr": 3.8698761890005794e-07, "epoch": 0.7391378139850645, "percentage": 73.91, "elapsed_time": "0:21:38", "remaining_time": "0:07:38", "throughput": 6439.81, "total_tokens": 8359168}
{"current_steps": 8715, "total_steps": 11784, "loss": 0.0154, "lr": 3.858180473246373e-07, "epoch": 0.7395621181262729, "percentage": 73.96, "elapsed_time": "0:21:38", "remaining_time": "0:07:37", "throughput": 6441.82, "total_tokens": 8363968}
{"current_steps": 8720, "total_steps": 11784, "loss": 0.0438, "lr": 3.8464982320765906e-07, "epoch": 0.7399864222674813, "percentage": 74.0, "elapsed_time": "0:21:38", "remaining_time": "0:07:36", "throughput": 6444.09, "total_tokens": 8369152}
{"current_steps": 8725, "total_steps": 11784, "loss": 0.0391, "lr": 3.834829491120991e-07, "epoch": 0.7404107264086898, "percentage": 74.04, "elapsed_time": "0:21:39", "remaining_time": "0:07:35", "throughput": 6446.1, "total_tokens": 8373952}
{"current_steps": 8730, "total_steps": 11784, "loss": 0.0883, "lr": 3.8231742759797157e-07, "epoch": 0.7408350305498982, "percentage": 74.08, "elapsed_time": "0:21:39", "remaining_time": "0:07:34", "throughput": 6448.59, "total_tokens": 8379456}
{"current_steps": 8735, "total_steps": 11784, "loss": 0.0386, "lr": 3.811532612223219e-07, "epoch": 0.7412593346911066, "percentage": 74.13, "elapsed_time": "0:21:39", "remaining_time": "0:07:33", "throughput": 6450.41, "total_tokens": 8383936}
{"current_steps": 8740, "total_steps": 11784, "loss": 0.0699, "lr": 3.7999045253922504e-07, "epoch": 0.741683638832315, "percentage": 74.17, "elapsed_time": "0:21:40", "remaining_time": "0:07:32", "throughput": 6452.52, "total_tokens": 8388864}
{"current_steps": 8745, "total_steps": 11784, "loss": 0.0511, "lr": 3.788290040997746e-07, "epoch": 0.7421079429735234, "percentage": 74.21, "elapsed_time": "0:21:40", "remaining_time": "0:07:31", "throughput": 6454.7, "total_tokens": 8393920}
{"current_steps": 8750, "total_steps": 11784, "loss": 0.0927, "lr": 3.776689184520815e-07, "epoch": 0.7425322471147319, "percentage": 74.25, "elapsed_time": "0:21:40", "remaining_time": "0:07:31", "throughput": 6456.8, "total_tokens": 8398848}
{"current_steps": 8755, "total_steps": 11784, "loss": 0.1256, "lr": 3.765101981412665e-07, "epoch": 0.7429565512559403, "percentage": 74.3, "elapsed_time": "0:21:41", "remaining_time": "0:07:30", "throughput": 6459.16, "total_tokens": 8404160}
{"current_steps": 8760, "total_steps": 11784, "loss": 0.0433, "lr": 3.753528457094548e-07, "epoch": 0.7433808553971487, "percentage": 74.34, "elapsed_time": "0:21:41", "remaining_time": "0:07:29", "throughput": 6461.12, "total_tokens": 8408896}
{"current_steps": 8765, "total_steps": 11784, "loss": 0.1051, "lr": 3.7419686369577076e-07, "epoch": 0.7438051595383571, "percentage": 74.38, "elapsed_time": "0:21:41", "remaining_time": "0:07:28", "throughput": 6462.87, "total_tokens": 8413312}
{"current_steps": 8770, "total_steps": 11784, "loss": 0.0251, "lr": 3.730422546363323e-07, "epoch": 0.7442294636795656, "percentage": 74.42, "elapsed_time": "0:21:42", "remaining_time": "0:07:27", "throughput": 6464.77, "total_tokens": 8417920}
{"current_steps": 8775, "total_steps": 11784, "loss": 0.068, "lr": 3.7188902106424414e-07, "epoch": 0.744653767820774, "percentage": 74.47, "elapsed_time": "0:21:42", "remaining_time": "0:07:26", "throughput": 6466.79, "total_tokens": 8422720}
{"current_steps": 8780, "total_steps": 11784, "loss": 0.0595, "lr": 3.7073716550959533e-07, "epoch": 0.7450780719619824, "percentage": 74.51, "elapsed_time": "0:21:42", "remaining_time": "0:07:25", "throughput": 6468.43, "total_tokens": 8426944}
{"current_steps": 8785, "total_steps": 11784, "loss": 0.0491, "lr": 3.6958669049944956e-07, "epoch": 0.7455023761031908, "percentage": 74.55, "elapsed_time": "0:21:43", "remaining_time": "0:07:24", "throughput": 6470.0, "total_tokens": 8431104}
{"current_steps": 8790, "total_steps": 11784, "loss": 0.0572, "lr": 3.684375985578431e-07, "epoch": 0.7459266802443992, "percentage": 74.59, "elapsed_time": "0:21:43", "remaining_time": "0:07:23", "throughput": 6471.77, "total_tokens": 8435520}
{"current_steps": 8795, "total_steps": 11784, "loss": 0.0451, "lr": 3.672898922057773e-07, "epoch": 0.7463509843856077, "percentage": 74.64, "elapsed_time": "0:21:43", "remaining_time": "0:07:23", "throughput": 6474.35, "total_tokens": 8441152}
{"current_steps": 8800, "total_steps": 11784, "loss": 0.0423, "lr": 3.66143573961214e-07, "epoch": 0.7467752885268161, "percentage": 74.68, "elapsed_time": "0:21:44", "remaining_time": "0:07:22", "throughput": 6476.28, "total_tokens": 8445824}
{"current_steps": 8805, "total_steps": 11784, "loss": 0.0749, "lr": 3.649986463390694e-07, "epoch": 0.7471995926680245, "percentage": 74.72, "elapsed_time": "0:21:44", "remaining_time": "0:07:21", "throughput": 6478.38, "total_tokens": 8450752}
{"current_steps": 8810, "total_steps": 11784, "loss": 0.0542, "lr": 3.6385511185120885e-07, "epoch": 0.7476238968092329, "percentage": 74.76, "elapsed_time": "0:21:44", "remaining_time": "0:07:20", "throughput": 6480.24, "total_tokens": 8455296}
{"current_steps": 8815, "total_steps": 11784, "loss": 0.0453, "lr": 3.6271297300644156e-07, "epoch": 0.7480482009504412, "percentage": 74.8, "elapsed_time": "0:21:45", "remaining_time": "0:07:19", "throughput": 6482.52, "total_tokens": 8460480}
{"current_steps": 8820, "total_steps": 11784, "loss": 0.0876, "lr": 3.6157223231051426e-07, "epoch": 0.7484725050916496, "percentage": 74.85, "elapsed_time": "0:21:45", "remaining_time": "0:07:18", "throughput": 6484.46, "total_tokens": 8465152}
{"current_steps": 8825, "total_steps": 11784, "loss": 0.0494, "lr": 3.6043289226610717e-07, "epoch": 0.7488968092328581, "percentage": 74.89, "elapsed_time": "0:21:45", "remaining_time": "0:07:17", "throughput": 6486.61, "total_tokens": 8470144}
{"current_steps": 8830, "total_steps": 11784, "loss": 0.0376, "lr": 3.5929495537282596e-07, "epoch": 0.7493211133740665, "percentage": 74.93, "elapsed_time": "0:21:46", "remaining_time": "0:07:16", "throughput": 6489.23, "total_tokens": 8475840}
{"current_steps": 8835, "total_steps": 11784, "loss": 0.0778, "lr": 3.5815842412720045e-07, "epoch": 0.7497454175152749, "percentage": 74.97, "elapsed_time": "0:21:46", "remaining_time": "0:07:16", "throughput": 6491.0, "total_tokens": 8480256}
{"current_steps": 8840, "total_steps": 11784, "loss": 0.0507, "lr": 3.57023301022674e-07, "epoch": 0.7501697216564833, "percentage": 75.02, "elapsed_time": "0:21:46", "remaining_time": "0:07:15", "throughput": 6493.37, "total_tokens": 8485568}
{"current_steps": 8845, "total_steps": 11784, "loss": 0.0751, "lr": 3.558895885496023e-07, "epoch": 0.7505940257976917, "percentage": 75.06, "elapsed_time": "0:21:47", "remaining_time": "0:07:14", "throughput": 6495.19, "total_tokens": 8490048}
{"current_steps": 8850, "total_steps": 11784, "loss": 0.0632, "lr": 3.547572891952456e-07, "epoch": 0.7510183299389002, "percentage": 75.1, "elapsed_time": "0:21:47", "remaining_time": "0:07:13", "throughput": 6497.13, "total_tokens": 8494720}
{"current_steps": 8850, "total_steps": 11784, "eval_loss": 0.05398377776145935, "epoch": 0.7510183299389002, "percentage": 75.1, "elapsed_time": "0:22:03", "remaining_time": "0:07:18", "throughput": 6419.78, "total_tokens": 8494720}
{"current_steps": 8855, "total_steps": 11784, "loss": 0.0387, "lr": 3.536264054437641e-07, "epoch": 0.7514426340801086, "percentage": 75.14, "elapsed_time": "0:22:35", "remaining_time": "0:07:28", "throughput": 6270.34, "total_tokens": 8499392}
{"current_steps": 8860, "total_steps": 11784, "loss": 0.0444, "lr": 3.524969397762122e-07, "epoch": 0.751866938221317, "percentage": 75.19, "elapsed_time": "0:22:35", "remaining_time": "0:07:27", "throughput": 6272.37, "total_tokens": 8504256}
{"current_steps": 8865, "total_steps": 11784, "loss": 0.074, "lr": 3.5136889467053353e-07, "epoch": 0.7522912423625254, "percentage": 75.23, "elapsed_time": "0:22:36", "remaining_time": "0:07:26", "throughput": 6274.25, "total_tokens": 8508864}
{"current_steps": 8870, "total_steps": 11784, "loss": 0.0805, "lr": 3.5024227260155383e-07, "epoch": 0.7527155465037338, "percentage": 75.27, "elapsed_time": "0:22:36", "remaining_time": "0:07:25", "throughput": 6276.49, "total_tokens": 8514048}
{"current_steps": 8875, "total_steps": 11784, "loss": 0.0212, "lr": 3.4911707604097916e-07, "epoch": 0.7531398506449423, "percentage": 75.31, "elapsed_time": "0:22:36", "remaining_time": "0:07:24", "throughput": 6278.37, "total_tokens": 8518656}
{"current_steps": 8880, "total_steps": 11784, "loss": 0.0455, "lr": 3.4799330745738573e-07, "epoch": 0.7535641547861507, "percentage": 75.36, "elapsed_time": "0:22:37", "remaining_time": "0:07:23", "throughput": 6280.41, "total_tokens": 8523520}
{"current_steps": 8885, "total_steps": 11784, "loss": 0.1758, "lr": 3.468709693162183e-07, "epoch": 0.7539884589273591, "percentage": 75.4, "elapsed_time": "0:22:37", "remaining_time": "0:07:22", "throughput": 6282.4, "total_tokens": 8528320}
{"current_steps": 8890, "total_steps": 11784, "loss": 0.0379, "lr": 3.4575006407978304e-07, "epoch": 0.7544127630685675, "percentage": 75.44, "elapsed_time": "0:22:37", "remaining_time": "0:07:22", "throughput": 6284.43, "total_tokens": 8533184}
{"current_steps": 8895, "total_steps": 11784, "loss": 0.0292, "lr": 3.446305942072425e-07, "epoch": 0.754837067209776, "percentage": 75.48, "elapsed_time": "0:22:38", "remaining_time": "0:07:21", "throughput": 6286.16, "total_tokens": 8537536}
{"current_steps": 8900, "total_steps": 11784, "loss": 0.0689, "lr": 3.4351256215461e-07, "epoch": 0.7552613713509844, "percentage": 75.53, "elapsed_time": "0:22:38", "remaining_time": "0:07:20", "throughput": 6287.74, "total_tokens": 8541696}
{"current_steps": 8905, "total_steps": 11784, "loss": 0.0226, "lr": 3.423959703747449e-07, "epoch": 0.7556856754921928, "percentage": 75.57, "elapsed_time": "0:22:38", "remaining_time": "0:07:19", "throughput": 6289.54, "total_tokens": 8546176}
{"current_steps": 8910, "total_steps": 11784, "loss": 0.0418, "lr": 3.4128082131734535e-07, "epoch": 0.7561099796334012, "percentage": 75.61, "elapsed_time": "0:22:39", "remaining_time": "0:07:18", "throughput": 6291.28, "total_tokens": 8550592}
{"current_steps": 8915, "total_steps": 11784, "loss": 0.0512, "lr": 3.401671174289469e-07, "epoch": 0.7565342837746096, "percentage": 75.65, "elapsed_time": "0:22:39", "remaining_time": "0:07:17", "throughput": 6293.45, "total_tokens": 8555648}
{"current_steps": 8920, "total_steps": 11784, "loss": 0.0859, "lr": 3.390548611529116e-07, "epoch": 0.756958587915818, "percentage": 75.7, "elapsed_time": "0:22:39", "remaining_time": "0:07:16", "throughput": 6295.57, "total_tokens": 8560640}
{"current_steps": 8925, "total_steps": 11784, "loss": 0.0721, "lr": 3.3794405492942713e-07, "epoch": 0.7573828920570265, "percentage": 75.74, "elapsed_time": "0:22:40", "remaining_time": "0:07:15", "throughput": 6297.52, "total_tokens": 8565376}
{"current_steps": 8930, "total_steps": 11784, "loss": 0.0562, "lr": 3.368347011955006e-07, "epoch": 0.7578071961982349, "percentage": 75.78, "elapsed_time": "0:22:40", "remaining_time": "0:07:14", "throughput": 6299.23, "total_tokens": 8569728}
{"current_steps": 8935, "total_steps": 11784, "loss": 0.0676, "lr": 3.3572680238495064e-07, "epoch": 0.7582315003394433, "percentage": 75.82, "elapsed_time": "0:22:40", "remaining_time": "0:07:13", "throughput": 6301.29, "total_tokens": 8574656}
{"current_steps": 8940, "total_steps": 11784, "loss": 0.0675, "lr": 3.346203609284053e-07, "epoch": 0.7586558044806517, "percentage": 75.87, "elapsed_time": "0:22:41", "remaining_time": "0:07:12", "throughput": 6303.04, "total_tokens": 8579072}
{"current_steps": 8945, "total_steps": 11784, "loss": 0.0307, "lr": 3.335153792532945e-07, "epoch": 0.7590801086218602, "percentage": 75.91, "elapsed_time": "0:22:41", "remaining_time": "0:07:12", "throughput": 6305.1, "total_tokens": 8584000}
{"current_steps": 8950, "total_steps": 11784, "loss": 0.0874, "lr": 3.324118597838463e-07, "epoch": 0.7595044127630686, "percentage": 75.95, "elapsed_time": "0:22:41", "remaining_time": "0:07:11", "throughput": 6307.37, "total_tokens": 8589248}
{"current_steps": 8955, "total_steps": 11784, "loss": 0.0565, "lr": 3.313098049410803e-07, "epoch": 0.759928716904277, "percentage": 75.99, "elapsed_time": "0:22:42", "remaining_time": "0:07:10", "throughput": 6309.0, "total_tokens": 8593472}
{"current_steps": 8960, "total_steps": 11784, "loss": 0.0134, "lr": 3.3020921714280325e-07, "epoch": 0.7603530210454854, "percentage": 76.04, "elapsed_time": "0:22:42", "remaining_time": "0:07:09", "throughput": 6310.77, "total_tokens": 8597952}
{"current_steps": 8965, "total_steps": 11784, "loss": 0.0331, "lr": 3.291100988036022e-07, "epoch": 0.7607773251866938, "percentage": 76.08, "elapsed_time": "0:22:42", "remaining_time": "0:07:08", "throughput": 6312.8, "total_tokens": 8602816}
{"current_steps": 8970, "total_steps": 11784, "loss": 0.0146, "lr": 3.280124523348423e-07, "epoch": 0.7612016293279023, "percentage": 76.12, "elapsed_time": "0:22:43", "remaining_time": "0:07:07", "throughput": 6315.19, "total_tokens": 8608256}
{"current_steps": 8975, "total_steps": 11784, "loss": 0.0495, "lr": 3.269162801446578e-07, "epoch": 0.7616259334691107, "percentage": 76.16, "elapsed_time": "0:22:43", "remaining_time": "0:07:06", "throughput": 6317.11, "total_tokens": 8612928}
{"current_steps": 8980, "total_steps": 11784, "loss": 0.1099, "lr": 3.258215846379492e-07, "epoch": 0.7620502376103191, "percentage": 76.21, "elapsed_time": "0:22:43", "remaining_time": "0:07:05", "throughput": 6318.82, "total_tokens": 8617280}
{"current_steps": 8985, "total_steps": 11784, "loss": 0.0041, "lr": 3.247283682163774e-07, "epoch": 0.7624745417515275, "percentage": 76.25, "elapsed_time": "0:22:44", "remaining_time": "0:07:04", "throughput": 6320.73, "total_tokens": 8621952}
{"current_steps": 8990, "total_steps": 11784, "loss": 0.0261, "lr": 3.2363663327835855e-07, "epoch": 0.7628988458927359, "percentage": 76.29, "elapsed_time": "0:22:44", "remaining_time": "0:07:04", "throughput": 6322.96, "total_tokens": 8627136}
{"current_steps": 8995, "total_steps": 11784, "loss": 0.0975, "lr": 3.2254638221905716e-07, "epoch": 0.7633231500339444, "percentage": 76.33, "elapsed_time": "0:22:44", "remaining_time": "0:07:03", "throughput": 6324.9, "total_tokens": 8631872}
{"current_steps": 9000, "total_steps": 11784, "loss": 0.0871, "lr": 3.214576174303846e-07, "epoch": 0.7637474541751528, "percentage": 76.37, "elapsed_time": "0:22:45", "remaining_time": "0:07:02", "throughput": 6327.0, "total_tokens": 8636864}
{"current_steps": 9005, "total_steps": 11784, "loss": 0.033, "lr": 3.2037034130098905e-07, "epoch": 0.7641717583163612, "percentage": 76.42, "elapsed_time": "0:22:45", "remaining_time": "0:07:01", "throughput": 6329.05, "total_tokens": 8641792}
{"current_steps": 9010, "total_steps": 11784, "loss": 0.0412, "lr": 3.192845562162549e-07, "epoch": 0.7645960624575696, "percentage": 76.46, "elapsed_time": "0:22:45", "remaining_time": "0:07:00", "throughput": 6330.91, "total_tokens": 8646400}
{"current_steps": 9015, "total_steps": 11784, "loss": 0.0528, "lr": 3.1820026455829353e-07, "epoch": 0.765020366598778, "percentage": 76.5, "elapsed_time": "0:22:46", "remaining_time": "0:06:59", "throughput": 6332.73, "total_tokens": 8650944}
{"current_steps": 9020, "total_steps": 11784, "loss": 0.0714, "lr": 3.171174687059408e-07, "epoch": 0.7654446707399865, "percentage": 76.54, "elapsed_time": "0:22:46", "remaining_time": "0:06:58", "throughput": 6335.31, "total_tokens": 8656704}
{"current_steps": 9025, "total_steps": 11784, "loss": 0.0878, "lr": 3.160361710347508e-07, "epoch": 0.7658689748811949, "percentage": 76.59, "elapsed_time": "0:22:46", "remaining_time": "0:06:57", "throughput": 6337.05, "total_tokens": 8661120}
{"current_steps": 9030, "total_steps": 11784, "loss": 0.0299, "lr": 3.14956373916991e-07, "epoch": 0.7662932790224033, "percentage": 76.63, "elapsed_time": "0:22:47", "remaining_time": "0:06:56", "throughput": 6338.86, "total_tokens": 8665664}
{"current_steps": 9035, "total_steps": 11784, "loss": 0.0576, "lr": 3.138780797216356e-07, "epoch": 0.7667175831636117, "percentage": 76.67, "elapsed_time": "0:22:47", "remaining_time": "0:06:56", "throughput": 6340.92, "total_tokens": 8670592}
{"current_steps": 9040, "total_steps": 11784, "loss": 0.0568, "lr": 3.128012908143636e-07, "epoch": 0.7671418873048201, "percentage": 76.71, "elapsed_time": "0:22:47", "remaining_time": "0:06:55", "throughput": 6343.94, "total_tokens": 8677120}
{"current_steps": 9045, "total_steps": 11784, "loss": 0.0727, "lr": 3.1172600955754935e-07, "epoch": 0.7675661914460286, "percentage": 76.76, "elapsed_time": "0:22:48", "remaining_time": "0:06:54", "throughput": 6346.07, "total_tokens": 8682176}
{"current_steps": 9050, "total_steps": 11784, "loss": 0.0849, "lr": 3.1065223831026066e-07, "epoch": 0.767990495587237, "percentage": 76.8, "elapsed_time": "0:22:48", "remaining_time": "0:06:53", "throughput": 6348.04, "total_tokens": 8686976}
{"current_steps": 9055, "total_steps": 11784, "loss": 0.0669, "lr": 3.095799794282533e-07, "epoch": 0.7684147997284454, "percentage": 76.84, "elapsed_time": "0:22:48", "remaining_time": "0:06:52", "throughput": 6350.07, "total_tokens": 8691904}
{"current_steps": 9060, "total_steps": 11784, "loss": 0.0465, "lr": 3.0850923526396334e-07, "epoch": 0.7688391038696538, "percentage": 76.88, "elapsed_time": "0:22:49", "remaining_time": "0:06:51", "throughput": 6354.6, "total_tokens": 8700928}
{"current_steps": 9065, "total_steps": 11784, "loss": 0.0227, "lr": 3.0744000816650464e-07, "epoch": 0.7692634080108622, "percentage": 76.93, "elapsed_time": "0:22:49", "remaining_time": "0:06:50", "throughput": 6356.31, "total_tokens": 8705344}
{"current_steps": 9070, "total_steps": 11784, "loss": 0.0562, "lr": 3.0637230048166263e-07, "epoch": 0.7696877121520707, "percentage": 76.97, "elapsed_time": "0:22:49", "remaining_time": "0:06:49", "throughput": 6358.69, "total_tokens": 8710784}
{"current_steps": 9075, "total_steps": 11784, "loss": 0.0205, "lr": 3.0530611455188946e-07, "epoch": 0.770112016293279, "percentage": 77.01, "elapsed_time": "0:22:50", "remaining_time": "0:06:49", "throughput": 6360.93, "total_tokens": 8716032}
{"current_steps": 9080, "total_steps": 11784, "loss": 0.0332, "lr": 3.0424145271629844e-07, "epoch": 0.7705363204344874, "percentage": 77.05, "elapsed_time": "0:22:50", "remaining_time": "0:06:48", "throughput": 6363.05, "total_tokens": 8721088}
{"current_steps": 9085, "total_steps": 11784, "loss": 0.0212, "lr": 3.031783173106596e-07, "epoch": 0.7709606245756958, "percentage": 77.1, "elapsed_time": "0:22:50", "remaining_time": "0:06:47", "throughput": 6364.83, "total_tokens": 8725632}
{"current_steps": 9090, "total_steps": 11784, "loss": 0.0318, "lr": 3.0211671066739276e-07, "epoch": 0.7713849287169042, "percentage": 77.14, "elapsed_time": "0:22:51", "remaining_time": "0:06:46", "throughput": 6366.88, "total_tokens": 8730560}
{"current_steps": 9095, "total_steps": 11784, "loss": 0.0695, "lr": 3.01056635115566e-07, "epoch": 0.7718092328581126, "percentage": 77.18, "elapsed_time": "0:22:51", "remaining_time": "0:06:45", "throughput": 6369.62, "total_tokens": 8736640}
{"current_steps": 9100, "total_steps": 11784, "loss": 0.0152, "lr": 2.999980929808863e-07, "epoch": 0.7722335369993211, "percentage": 77.22, "elapsed_time": "0:22:51", "remaining_time": "0:06:44", "throughput": 6371.44, "total_tokens": 8741248}
{"current_steps": 9105, "total_steps": 11784, "loss": 0.0392, "lr": 2.989410865856975e-07, "epoch": 0.7726578411405295, "percentage": 77.27, "elapsed_time": "0:22:52", "remaining_time": "0:06:43", "throughput": 6373.28, "total_tokens": 8745856}
{"current_steps": 9110, "total_steps": 11784, "loss": 0.1469, "lr": 2.9788561824897397e-07, "epoch": 0.7730821452817379, "percentage": 77.31, "elapsed_time": "0:22:52", "remaining_time": "0:06:42", "throughput": 6374.83, "total_tokens": 8750016}
{"current_steps": 9115, "total_steps": 11784, "loss": 0.0212, "lr": 2.968316902863157e-07, "epoch": 0.7735064494229463, "percentage": 77.35, "elapsed_time": "0:22:52", "remaining_time": "0:06:42", "throughput": 6376.85, "total_tokens": 8754944}
{"current_steps": 9120, "total_steps": 11784, "loss": 0.0967, "lr": 2.957793050099433e-07, "epoch": 0.7739307535641547, "percentage": 77.39, "elapsed_time": "0:22:53", "remaining_time": "0:06:41", "throughput": 6378.64, "total_tokens": 8759488}
{"current_steps": 9125, "total_steps": 11784, "loss": 0.0815, "lr": 2.9472846472869295e-07, "epoch": 0.7743550577053632, "percentage": 77.44, "elapsed_time": "0:22:53", "remaining_time": "0:06:40", "throughput": 6380.31, "total_tokens": 8763840}
{"current_steps": 9130, "total_steps": 11784, "loss": 0.0108, "lr": 2.936791717480104e-07, "epoch": 0.7747793618465716, "percentage": 77.48, "elapsed_time": "0:22:53", "remaining_time": "0:06:39", "throughput": 6382.06, "total_tokens": 8768320}
{"current_steps": 9135, "total_steps": 11784, "loss": 0.0252, "lr": 2.9263142836994845e-07, "epoch": 0.77520366598778, "percentage": 77.52, "elapsed_time": "0:22:54", "remaining_time": "0:06:38", "throughput": 6384.29, "total_tokens": 8773568}
{"current_steps": 9140, "total_steps": 11784, "loss": 0.0947, "lr": 2.915852368931585e-07, "epoch": 0.7756279701289884, "percentage": 77.56, "elapsed_time": "0:22:54", "remaining_time": "0:06:37", "throughput": 6386.12, "total_tokens": 8778176}
{"current_steps": 9145, "total_steps": 11784, "loss": 0.111, "lr": 2.905405996128882e-07, "epoch": 0.7760522742701969, "percentage": 77.61, "elapsed_time": "0:22:54", "remaining_time": "0:06:36", "throughput": 6387.94, "total_tokens": 8782784}
{"current_steps": 9150, "total_steps": 11784, "loss": 0.0308, "lr": 2.894975188209754e-07, "epoch": 0.7764765784114053, "percentage": 77.65, "elapsed_time": "0:22:55", "remaining_time": "0:06:35", "throughput": 6389.83, "total_tokens": 8787456}
{"current_steps": 9155, "total_steps": 11784, "loss": 0.0682, "lr": 2.8845599680584265e-07, "epoch": 0.7769008825526137, "percentage": 77.69, "elapsed_time": "0:22:55", "remaining_time": "0:06:35", "throughput": 6391.77, "total_tokens": 8792256}
{"current_steps": 9160, "total_steps": 11784, "loss": 0.1251, "lr": 2.8741603585249306e-07, "epoch": 0.7773251866938221, "percentage": 77.73, "elapsed_time": "0:22:55", "remaining_time": "0:06:34", "throughput": 6394.03, "total_tokens": 8797568}
{"current_steps": 9165, "total_steps": 11784, "loss": 0.0504, "lr": 2.8637763824250507e-07, "epoch": 0.7777494908350305, "percentage": 77.77, "elapsed_time": "0:22:56", "remaining_time": "0:06:33", "throughput": 6395.8, "total_tokens": 8802112}
{"current_steps": 9170, "total_steps": 11784, "loss": 0.0153, "lr": 2.8534080625402677e-07, "epoch": 0.778173794976239, "percentage": 77.82, "elapsed_time": "0:22:56", "remaining_time": "0:06:32", "throughput": 6397.66, "total_tokens": 8806784}
{"current_steps": 9175, "total_steps": 11784, "loss": 0.0108, "lr": 2.8430554216177203e-07, "epoch": 0.7785980991174474, "percentage": 77.86, "elapsed_time": "0:22:56", "remaining_time": "0:06:31", "throughput": 6399.94, "total_tokens": 8812096}
{"current_steps": 9180, "total_steps": 11784, "loss": 0.11, "lr": 2.8327184823701464e-07, "epoch": 0.7790224032586558, "percentage": 77.9, "elapsed_time": "0:22:57", "remaining_time": "0:06:30", "throughput": 6401.96, "total_tokens": 8817024}
{"current_steps": 9185, "total_steps": 11784, "loss": 0.1664, "lr": 2.822397267475827e-07, "epoch": 0.7794467073998642, "percentage": 77.94, "elapsed_time": "0:22:57", "remaining_time": "0:06:29", "throughput": 6403.8, "total_tokens": 8821696}
{"current_steps": 9190, "total_steps": 11784, "loss": 0.1155, "lr": 2.812091799578566e-07, "epoch": 0.7798710115410726, "percentage": 77.99, "elapsed_time": "0:22:57", "remaining_time": "0:06:28", "throughput": 6405.78, "total_tokens": 8826560}
{"current_steps": 9195, "total_steps": 11784, "loss": 0.0301, "lr": 2.8018021012875995e-07, "epoch": 0.780295315682281, "percentage": 78.03, "elapsed_time": "0:22:58", "remaining_time": "0:06:28", "throughput": 6407.84, "total_tokens": 8831552}
{"current_steps": 9200, "total_steps": 11784, "loss": 0.0673, "lr": 2.791528195177576e-07, "epoch": 0.7807196198234895, "percentage": 78.07, "elapsed_time": "0:22:58", "remaining_time": "0:06:27", "throughput": 6409.87, "total_tokens": 8836480}
{"current_steps": 9205, "total_steps": 11784, "loss": 0.0681, "lr": 2.7812701037884964e-07, "epoch": 0.7811439239646979, "percentage": 78.11, "elapsed_time": "0:22:58", "remaining_time": "0:06:26", "throughput": 6411.52, "total_tokens": 8840832}
{"current_steps": 9210, "total_steps": 11784, "loss": 0.0717, "lr": 2.7710278496256665e-07, "epoch": 0.7815682281059063, "percentage": 78.16, "elapsed_time": "0:22:59", "remaining_time": "0:06:25", "throughput": 6413.3, "total_tokens": 8845376}
{"current_steps": 9215, "total_steps": 11784, "loss": 0.0424, "lr": 2.7608014551596437e-07, "epoch": 0.7819925322471147, "percentage": 78.2, "elapsed_time": "0:22:59", "remaining_time": "0:06:24", "throughput": 6415.24, "total_tokens": 8850176}
{"current_steps": 9220, "total_steps": 11784, "loss": 0.0697, "lr": 2.7505909428261956e-07, "epoch": 0.7824168363883232, "percentage": 78.24, "elapsed_time": "0:22:59", "remaining_time": "0:06:23", "throughput": 6417.16, "total_tokens": 8854976}
{"current_steps": 9225, "total_steps": 11784, "loss": 0.0415, "lr": 2.740396335026234e-07, "epoch": 0.7828411405295316, "percentage": 78.28, "elapsed_time": "0:23:00", "remaining_time": "0:06:22", "throughput": 6418.85, "total_tokens": 8859392}
{"current_steps": 9230, "total_steps": 11784, "loss": 0.0155, "lr": 2.7302176541257984e-07, "epoch": 0.78326544467074, "percentage": 78.33, "elapsed_time": "0:23:00", "remaining_time": "0:06:22", "throughput": 6420.63, "total_tokens": 8863936}
{"current_steps": 9235, "total_steps": 11784, "loss": 0.1092, "lr": 2.720054922455964e-07, "epoch": 0.7836897488119484, "percentage": 78.37, "elapsed_time": "0:23:00", "remaining_time": "0:06:21", "throughput": 6422.42, "total_tokens": 8868480}
{"current_steps": 9240, "total_steps": 11784, "loss": 0.0854, "lr": 2.7099081623128294e-07, "epoch": 0.7841140529531568, "percentage": 78.41, "elapsed_time": "0:23:01", "remaining_time": "0:06:20", "throughput": 6424.4, "total_tokens": 8873344}
{"current_steps": 9245, "total_steps": 11784, "loss": 0.0661, "lr": 2.699777395957449e-07, "epoch": 0.7845383570943653, "percentage": 78.45, "elapsed_time": "0:23:01", "remaining_time": "0:06:19", "throughput": 6426.24, "total_tokens": 8878016}
{"current_steps": 9250, "total_steps": 11784, "loss": 0.1429, "lr": 2.6896626456157846e-07, "epoch": 0.7849626612355737, "percentage": 78.5, "elapsed_time": "0:23:01", "remaining_time": "0:06:18", "throughput": 6428.17, "total_tokens": 8882816}
{"current_steps": 9255, "total_steps": 11784, "loss": 0.0025, "lr": 2.679563933478667e-07, "epoch": 0.7853869653767821, "percentage": 78.54, "elapsed_time": "0:23:02", "remaining_time": "0:06:17", "throughput": 6430.3, "total_tokens": 8887936}
{"current_steps": 9260, "total_steps": 11784, "loss": 0.0219, "lr": 2.6694812817017387e-07, "epoch": 0.7858112695179905, "percentage": 78.58, "elapsed_time": "0:23:02", "remaining_time": "0:06:16", "throughput": 6432.18, "total_tokens": 8892672}
{"current_steps": 9265, "total_steps": 11784, "loss": 0.053, "lr": 2.659414712405398e-07, "epoch": 0.7862355736591989, "percentage": 78.62, "elapsed_time": "0:23:02", "remaining_time": "0:06:15", "throughput": 6433.9, "total_tokens": 8897152}
{"current_steps": 9270, "total_steps": 11784, "loss": 0.0312, "lr": 2.649364247674779e-07, "epoch": 0.7866598778004074, "percentage": 78.67, "elapsed_time": "0:23:03", "remaining_time": "0:06:15", "throughput": 6435.54, "total_tokens": 8901504}
{"current_steps": 9275, "total_steps": 11784, "loss": 0.073, "lr": 2.639329909559662e-07, "epoch": 0.7870841819416158, "percentage": 78.71, "elapsed_time": "0:23:03", "remaining_time": "0:06:14", "throughput": 6437.38, "total_tokens": 8906176}
{"current_steps": 9280, "total_steps": 11784, "loss": 0.0315, "lr": 2.6293117200744643e-07, "epoch": 0.7875084860828242, "percentage": 78.75, "elapsed_time": "0:23:03", "remaining_time": "0:06:13", "throughput": 6439.13, "total_tokens": 8910720}
{"current_steps": 9285, "total_steps": 11784, "loss": 0.0515, "lr": 2.6193097011981635e-07, "epoch": 0.7879327902240326, "percentage": 78.79, "elapsed_time": "0:23:04", "remaining_time": "0:06:12", "throughput": 6440.86, "total_tokens": 8915200}
{"current_steps": 9290, "total_steps": 11784, "loss": 0.0686, "lr": 2.609323874874266e-07, "epoch": 0.788357094365241, "percentage": 78.84, "elapsed_time": "0:23:04", "remaining_time": "0:06:11", "throughput": 6442.93, "total_tokens": 8920256}
{"current_steps": 9295, "total_steps": 11784, "loss": 0.0547, "lr": 2.5993542630107533e-07, "epoch": 0.7887813985064495, "percentage": 78.88, "elapsed_time": "0:23:04", "remaining_time": "0:06:10", "throughput": 6444.71, "total_tokens": 8924864}
{"current_steps": 9300, "total_steps": 11784, "loss": 0.0615, "lr": 2.589400887480032e-07, "epoch": 0.7892057026476579, "percentage": 78.92, "elapsed_time": "0:23:05", "remaining_time": "0:06:09", "throughput": 6446.73, "total_tokens": 8929856}
{"current_steps": 9305, "total_steps": 11784, "loss": 0.0191, "lr": 2.579463770118887e-07, "epoch": 0.7896300067888663, "percentage": 78.96, "elapsed_time": "0:23:05", "remaining_time": "0:06:09", "throughput": 6449.84, "total_tokens": 8936640}
{"current_steps": 9310, "total_steps": 11784, "loss": 0.0344, "lr": 2.569542932728436e-07, "epoch": 0.7900543109300747, "percentage": 79.01, "elapsed_time": "0:23:05", "remaining_time": "0:06:08", "throughput": 6451.45, "total_tokens": 8940992}
{"current_steps": 9315, "total_steps": 11784, "loss": 0.0789, "lr": 2.5596383970740833e-07, "epoch": 0.7904786150712831, "percentage": 79.05, "elapsed_time": "0:23:06", "remaining_time": "0:06:07", "throughput": 6453.27, "total_tokens": 8945664}
{"current_steps": 9320, "total_steps": 11784, "loss": 0.1219, "lr": 2.549750184885454e-07, "epoch": 0.7909029192124916, "percentage": 79.09, "elapsed_time": "0:23:06", "remaining_time": "0:06:06", "throughput": 6454.89, "total_tokens": 8950016}
{"current_steps": 9325, "total_steps": 11784, "loss": 0.0785, "lr": 2.5398783178563844e-07, "epoch": 0.7913272233537, "percentage": 79.13, "elapsed_time": "0:23:06", "remaining_time": "0:06:05", "throughput": 6456.83, "total_tokens": 8954880}
{"current_steps": 9330, "total_steps": 11784, "loss": 0.058, "lr": 2.5300228176448304e-07, "epoch": 0.7917515274949084, "percentage": 79.18, "elapsed_time": "0:23:07", "remaining_time": "0:06:04", "throughput": 6459.01, "total_tokens": 8960128}
{"current_steps": 9335, "total_steps": 11784, "loss": 0.0552, "lr": 2.52018370587285e-07, "epoch": 0.7921758316361168, "percentage": 79.22, "elapsed_time": "0:23:07", "remaining_time": "0:06:04", "throughput": 6460.87, "total_tokens": 8964864}
{"current_steps": 9340, "total_steps": 11784, "loss": 0.0933, "lr": 2.5103610041265475e-07, "epoch": 0.7926001357773251, "percentage": 79.26, "elapsed_time": "0:23:07", "remaining_time": "0:06:03", "throughput": 6463.04, "total_tokens": 8970112}
{"current_steps": 9345, "total_steps": 11784, "loss": 0.0475, "lr": 2.5005547339560207e-07, "epoch": 0.7930244399185336, "percentage": 79.3, "elapsed_time": "0:23:08", "remaining_time": "0:06:02", "throughput": 6465.05, "total_tokens": 8975104}
{"current_steps": 9350, "total_steps": 11784, "loss": 0.0478, "lr": 2.4907649168753197e-07, "epoch": 0.793448744059742, "percentage": 79.34, "elapsed_time": "0:23:08", "remaining_time": "0:06:01", "throughput": 6467.11, "total_tokens": 8980160}
{"current_steps": 9355, "total_steps": 11784, "loss": 0.1039, "lr": 2.480991574362403e-07, "epoch": 0.7938730482009504, "percentage": 79.39, "elapsed_time": "0:23:08", "remaining_time": "0:06:00", "throughput": 6468.6, "total_tokens": 8984320}
{"current_steps": 9360, "total_steps": 11784, "loss": 0.0495, "lr": 2.471234727859072e-07, "epoch": 0.7942973523421588, "percentage": 79.43, "elapsed_time": "0:23:09", "remaining_time": "0:05:59", "throughput": 6470.66, "total_tokens": 8989376}
{"current_steps": 9365, "total_steps": 11784, "loss": 0.026, "lr": 2.461494398770957e-07, "epoch": 0.7947216564833672, "percentage": 79.47, "elapsed_time": "0:23:09", "remaining_time": "0:05:58", "throughput": 6472.39, "total_tokens": 8993920}
{"current_steps": 9370, "total_steps": 11784, "loss": 0.0662, "lr": 2.4517706084674316e-07, "epoch": 0.7951459606245757, "percentage": 79.51, "elapsed_time": "0:23:09", "remaining_time": "0:05:58", "throughput": 6474.35, "total_tokens": 8998848}
{"current_steps": 9375, "total_steps": 11784, "loss": 0.0314, "lr": 2.4420633782815945e-07, "epoch": 0.7955702647657841, "percentage": 79.56, "elapsed_time": "0:23:10", "remaining_time": "0:05:57", "throughput": 6476.3, "total_tokens": 9003712}
{"current_steps": 9380, "total_steps": 11784, "loss": 0.0552, "lr": 2.432372729510214e-07, "epoch": 0.7959945689069925, "percentage": 79.6, "elapsed_time": "0:23:10", "remaining_time": "0:05:56", "throughput": 6478.72, "total_tokens": 9009472}
{"current_steps": 9385, "total_steps": 11784, "loss": 0.0265, "lr": 2.4226986834136763e-07, "epoch": 0.7964188730482009, "percentage": 79.64, "elapsed_time": "0:23:10", "remaining_time": "0:05:55", "throughput": 6480.53, "total_tokens": 9014144}
{"current_steps": 9390, "total_steps": 11784, "loss": 0.0193, "lr": 2.4130412612159445e-07, "epoch": 0.7968431771894093, "percentage": 79.68, "elapsed_time": "0:23:11", "remaining_time": "0:05:54", "throughput": 6482.24, "total_tokens": 9018688}
{"current_steps": 9395, "total_steps": 11784, "loss": 0.0334, "lr": 2.403400484104514e-07, "epoch": 0.7972674813306178, "percentage": 79.73, "elapsed_time": "0:23:11", "remaining_time": "0:05:53", "throughput": 6483.83, "total_tokens": 9023040}
{"current_steps": 9400, "total_steps": 11784, "loss": 0.0262, "lr": 2.3937763732303504e-07, "epoch": 0.7976917854718262, "percentage": 79.77, "elapsed_time": "0:23:11", "remaining_time": "0:05:53", "throughput": 6485.39, "total_tokens": 9027328}
{"current_steps": 9405, "total_steps": 11784, "loss": 0.0333, "lr": 2.3841689497078742e-07, "epoch": 0.7981160896130346, "percentage": 79.81, "elapsed_time": "0:23:12", "remaining_time": "0:05:52", "throughput": 6486.89, "total_tokens": 9031552}
{"current_steps": 9410, "total_steps": 11784, "loss": 0.0224, "lr": 2.3745782346148756e-07, "epoch": 0.798540393754243, "percentage": 79.85, "elapsed_time": "0:23:12", "remaining_time": "0:05:51", "throughput": 6488.96, "total_tokens": 9036672}
{"current_steps": 9415, "total_steps": 11784, "loss": 0.0491, "lr": 2.3650042489924992e-07, "epoch": 0.7989646978954514, "percentage": 79.9, "elapsed_time": "0:23:12", "remaining_time": "0:05:50", "throughput": 6490.82, "total_tokens": 9041472}
{"current_steps": 9420, "total_steps": 11784, "loss": 0.0686, "lr": 2.3554470138451909e-07, "epoch": 0.7993890020366599, "percentage": 79.94, "elapsed_time": "0:23:13", "remaining_time": "0:05:49", "throughput": 6493.1, "total_tokens": 9046912}
{"current_steps": 9425, "total_steps": 11784, "loss": 0.0481, "lr": 2.345906550140634e-07, "epoch": 0.7998133061778683, "percentage": 79.98, "elapsed_time": "0:23:13", "remaining_time": "0:05:48", "throughput": 6494.98, "total_tokens": 9051712}
{"current_steps": 9430, "total_steps": 11784, "loss": 0.0909, "lr": 2.3363828788097274e-07, "epoch": 0.8002376103190767, "percentage": 80.02, "elapsed_time": "0:23:13", "remaining_time": "0:05:47", "throughput": 6496.73, "total_tokens": 9056256}
{"current_steps": 9435, "total_steps": 11784, "loss": 0.0345, "lr": 2.3268760207465244e-07, "epoch": 0.8006619144602851, "percentage": 80.07, "elapsed_time": "0:23:14", "remaining_time": "0:05:47", "throughput": 6498.81, "total_tokens": 9061376}
{"current_steps": 9440, "total_steps": 11784, "loss": 0.1023, "lr": 2.3173859968081944e-07, "epoch": 0.8010862186014935, "percentage": 80.11, "elapsed_time": "0:23:14", "remaining_time": "0:05:46", "throughput": 6500.61, "total_tokens": 9066048}
{"current_steps": 9440, "total_steps": 11784, "eval_loss": 0.05470386520028114, "epoch": 0.8010862186014935, "percentage": 80.11, "elapsed_time": "0:23:30", "remaining_time": "0:05:50", "throughput": 6427.11, "total_tokens": 9066048}
{"current_steps": 9445, "total_steps": 11784, "loss": 0.0286, "lr": 2.3079128278149717e-07, "epoch": 0.801510522742702, "percentage": 80.15, "elapsed_time": "0:24:00", "remaining_time": "0:05:56", "throughput": 6297.92, "total_tokens": 9071232}
{"current_steps": 9450, "total_steps": 11784, "loss": 0.0474, "lr": 2.2984565345501172e-07, "epoch": 0.8019348268839104, "percentage": 80.19, "elapsed_time": "0:24:00", "remaining_time": "0:05:55", "throughput": 6299.49, "total_tokens": 9075520}
{"current_steps": 9455, "total_steps": 11784, "loss": 0.0605, "lr": 2.2890171377598556e-07, "epoch": 0.8023591310251188, "percentage": 80.24, "elapsed_time": "0:24:01", "remaining_time": "0:05:54", "throughput": 6301.29, "total_tokens": 9080192}
{"current_steps": 9460, "total_steps": 11784, "loss": 0.0041, "lr": 2.2795946581533632e-07, "epoch": 0.8027834351663272, "percentage": 80.28, "elapsed_time": "0:24:01", "remaining_time": "0:05:54", "throughput": 6303.6, "total_tokens": 9085696}
{"current_steps": 9465, "total_steps": 11784, "loss": 0.0716, "lr": 2.27018911640268e-07, "epoch": 0.8032077393075356, "percentage": 80.32, "elapsed_time": "0:24:01", "remaining_time": "0:05:53", "throughput": 6305.45, "total_tokens": 9090432}
{"current_steps": 9470, "total_steps": 11784, "loss": 0.0832, "lr": 2.2608005331426982e-07, "epoch": 0.8036320434487441, "percentage": 80.36, "elapsed_time": "0:24:02", "remaining_time": "0:05:52", "throughput": 6307.17, "total_tokens": 9094976}
{"current_steps": 9475, "total_steps": 11784, "loss": 0.0863, "lr": 2.251428928971102e-07, "epoch": 0.8040563475899525, "percentage": 80.41, "elapsed_time": "0:24:02", "remaining_time": "0:05:51", "throughput": 6309.25, "total_tokens": 9100096}
{"current_steps": 9480, "total_steps": 11784, "loss": 0.0752, "lr": 2.2420743244483253e-07, "epoch": 0.8044806517311609, "percentage": 80.45, "elapsed_time": "0:24:02", "remaining_time": "0:05:50", "throughput": 6311.42, "total_tokens": 9105408}
{"current_steps": 9485, "total_steps": 11784, "loss": 0.0346, "lr": 2.2327367400975051e-07, "epoch": 0.8049049558723693, "percentage": 80.49, "elapsed_time": "0:24:03", "remaining_time": "0:05:49", "throughput": 6313.25, "total_tokens": 9110144}
{"current_steps": 9490, "total_steps": 11784, "loss": 0.0509, "lr": 2.2234161964044417e-07, "epoch": 0.8053292600135777, "percentage": 80.53, "elapsed_time": "0:24:03", "remaining_time": "0:05:48", "throughput": 6315.46, "total_tokens": 9115520}
{"current_steps": 9495, "total_steps": 11784, "loss": 0.0249, "lr": 2.2141127138175386e-07, "epoch": 0.8057535641547862, "percentage": 80.58, "elapsed_time": "0:24:03", "remaining_time": "0:05:48", "throughput": 6317.03, "total_tokens": 9119808}
{"current_steps": 9500, "total_steps": 11784, "loss": 0.0707, "lr": 2.2048263127477861e-07, "epoch": 0.8061778682959946, "percentage": 80.62, "elapsed_time": "0:24:04", "remaining_time": "0:05:47", "throughput": 6318.94, "total_tokens": 9124672}
{"current_steps": 9505, "total_steps": 11784, "loss": 0.0903, "lr": 2.195557013568684e-07, "epoch": 0.806602172437203, "percentage": 80.66, "elapsed_time": "0:24:04", "remaining_time": "0:05:46", "throughput": 6320.65, "total_tokens": 9129216}
{"current_steps": 9510, "total_steps": 11784, "loss": 0.0704, "lr": 2.1863048366162207e-07, "epoch": 0.8070264765784114, "percentage": 80.7, "elapsed_time": "0:24:04", "remaining_time": "0:05:45", "throughput": 6322.49, "total_tokens": 9133952}
{"current_steps": 9515, "total_steps": 11784, "loss": 0.0464, "lr": 2.1770698021888145e-07, "epoch": 0.8074507807196198, "percentage": 80.75, "elapsed_time": "0:24:04", "remaining_time": "0:05:44", "throughput": 6324.05, "total_tokens": 9138240}
{"current_steps": 9520, "total_steps": 11784, "loss": 0.1019, "lr": 2.167851930547283e-07, "epoch": 0.8078750848608283, "percentage": 80.79, "elapsed_time": "0:24:05", "remaining_time": "0:05:43", "throughput": 6325.69, "total_tokens": 9142656}
{"current_steps": 9525, "total_steps": 11784, "loss": 0.0595, "lr": 2.1586512419147763e-07, "epoch": 0.8082993890020367, "percentage": 80.83, "elapsed_time": "0:24:05", "remaining_time": "0:05:42", "throughput": 6327.55, "total_tokens": 9147456}
{"current_steps": 9530, "total_steps": 11784, "loss": 0.0314, "lr": 2.149467756476765e-07, "epoch": 0.8087236931432451, "percentage": 80.87, "elapsed_time": "0:24:05", "remaining_time": "0:05:41", "throughput": 6329.31, "total_tokens": 9152064}
{"current_steps": 9535, "total_steps": 11784, "loss": 0.0694, "lr": 2.140301494380956e-07, "epoch": 0.8091479972844535, "percentage": 80.91, "elapsed_time": "0:24:06", "remaining_time": "0:05:41", "throughput": 6330.97, "total_tokens": 9156544}
{"current_steps": 9540, "total_steps": 11784, "loss": 0.0385, "lr": 2.1311524757372901e-07, "epoch": 0.8095723014256619, "percentage": 80.96, "elapsed_time": "0:24:06", "remaining_time": "0:05:40", "throughput": 6332.69, "total_tokens": 9161088}
{"current_steps": 9545, "total_steps": 11784, "loss": 0.05, "lr": 2.1220207206178685e-07, "epoch": 0.8099966055668704, "percentage": 81.0, "elapsed_time": "0:24:06", "remaining_time": "0:05:39", "throughput": 6334.29, "total_tokens": 9165440}
{"current_steps": 9550, "total_steps": 11784, "loss": 0.0143, "lr": 2.1129062490569106e-07, "epoch": 0.8104209097080788, "percentage": 81.04, "elapsed_time": "0:24:07", "remaining_time": "0:05:38", "throughput": 6336.3, "total_tokens": 9170496}
{"current_steps": 9555, "total_steps": 11784, "loss": 0.034, "lr": 2.1038090810507348e-07, "epoch": 0.8108452138492872, "percentage": 81.08, "elapsed_time": "0:24:07", "remaining_time": "0:05:37", "throughput": 6338.2, "total_tokens": 9175360}
{"current_steps": 9560, "total_steps": 11784, "loss": 0.057, "lr": 2.0947292365576785e-07, "epoch": 0.8112695179904956, "percentage": 81.13, "elapsed_time": "0:24:07", "remaining_time": "0:05:36", "throughput": 6339.84, "total_tokens": 9179776}
{"current_steps": 9565, "total_steps": 11784, "loss": 0.0305, "lr": 2.085666735498085e-07, "epoch": 0.811693822131704, "percentage": 81.17, "elapsed_time": "0:24:08", "remaining_time": "0:05:35", "throughput": 6342.27, "total_tokens": 9185536}
{"current_steps": 9570, "total_steps": 11784, "loss": 0.0328, "lr": 2.0766215977542435e-07, "epoch": 0.8121181262729125, "percentage": 81.21, "elapsed_time": "0:24:08", "remaining_time": "0:05:35", "throughput": 6344.25, "total_tokens": 9190528}
{"current_steps": 9575, "total_steps": 11784, "loss": 0.0937, "lr": 2.0675938431703532e-07, "epoch": 0.8125424304141209, "percentage": 81.25, "elapsed_time": "0:24:08", "remaining_time": "0:05:34", "throughput": 6346.06, "total_tokens": 9195264}
{"current_steps": 9580, "total_steps": 11784, "loss": 0.065, "lr": 2.0585834915524646e-07, "epoch": 0.8129667345553293, "percentage": 81.3, "elapsed_time": "0:24:09", "remaining_time": "0:05:33", "throughput": 6347.99, "total_tokens": 9200192}
{"current_steps": 9585, "total_steps": 11784, "loss": 0.0184, "lr": 2.0495905626684674e-07, "epoch": 0.8133910386965377, "percentage": 81.34, "elapsed_time": "0:24:09", "remaining_time": "0:05:32", "throughput": 6349.88, "total_tokens": 9205056}
{"current_steps": 9590, "total_steps": 11784, "loss": 0.0328, "lr": 2.0406150762480089e-07, "epoch": 0.8138153428377461, "percentage": 81.38, "elapsed_time": "0:24:09", "remaining_time": "0:05:31", "throughput": 6351.75, "total_tokens": 9209856}
{"current_steps": 9595, "total_steps": 11784, "loss": 0.033, "lr": 2.0316570519824806e-07, "epoch": 0.8142396469789546, "percentage": 81.42, "elapsed_time": "0:24:10", "remaining_time": "0:05:30", "throughput": 6353.5, "total_tokens": 9214464}
{"current_steps": 9600, "total_steps": 11784, "loss": 0.0432, "lr": 2.0227165095249564e-07, "epoch": 0.814663951120163, "percentage": 81.47, "elapsed_time": "0:24:10", "remaining_time": "0:05:30", "throughput": 6355.24, "total_tokens": 9219072}
{"current_steps": 9605, "total_steps": 11784, "loss": 0.0675, "lr": 2.0137934684901636e-07, "epoch": 0.8150882552613713, "percentage": 81.51, "elapsed_time": "0:24:10", "remaining_time": "0:05:29", "throughput": 6357.64, "total_tokens": 9224768}
{"current_steps": 9610, "total_steps": 11784, "loss": 0.0464, "lr": 2.0048879484544279e-07, "epoch": 0.8155125594025797, "percentage": 81.55, "elapsed_time": "0:24:11", "remaining_time": "0:05:28", "throughput": 6359.56, "total_tokens": 9229696}
{"current_steps": 9615, "total_steps": 11784, "loss": 0.0971, "lr": 1.9959999689556407e-07, "epoch": 0.8159368635437881, "percentage": 81.59, "elapsed_time": "0:24:11", "remaining_time": "0:05:27", "throughput": 6361.75, "total_tokens": 9235072}
{"current_steps": 9620, "total_steps": 11784, "loss": 0.0947, "lr": 1.9871295494931994e-07, "epoch": 0.8163611676849966, "percentage": 81.64, "elapsed_time": "0:24:11", "remaining_time": "0:05:26", "throughput": 6363.87, "total_tokens": 9240320}
{"current_steps": 9625, "total_steps": 11784, "loss": 0.0287, "lr": 1.978276709527994e-07, "epoch": 0.816785471826205, "percentage": 81.68, "elapsed_time": "0:24:12", "remaining_time": "0:05:25", "throughput": 6365.6, "total_tokens": 9244928}
{"current_steps": 9630, "total_steps": 11784, "loss": 0.1166, "lr": 1.9694414684823313e-07, "epoch": 0.8172097759674134, "percentage": 81.72, "elapsed_time": "0:24:12", "remaining_time": "0:05:24", "throughput": 6367.49, "total_tokens": 9249792}
{"current_steps": 9635, "total_steps": 11784, "loss": 0.0569, "lr": 1.960623845739914e-07, "epoch": 0.8176340801086218, "percentage": 81.76, "elapsed_time": "0:24:13", "remaining_time": "0:05:24", "throughput": 6369.48, "total_tokens": 9254848}
{"current_steps": 9640, "total_steps": 11784, "loss": 0.0463, "lr": 1.9518238606457925e-07, "epoch": 0.8180583842498302, "percentage": 81.81, "elapsed_time": "0:24:13", "remaining_time": "0:05:23", "throughput": 6371.17, "total_tokens": 9259392}
{"current_steps": 9645, "total_steps": 11784, "loss": 0.066, "lr": 1.943041532506322e-07, "epoch": 0.8184826883910387, "percentage": 81.85, "elapsed_time": "0:24:13", "remaining_time": "0:05:22", "throughput": 6372.83, "total_tokens": 9263872}
{"current_steps": 9650, "total_steps": 11784, "loss": 0.0389, "lr": 1.9342768805891173e-07, "epoch": 0.8189069925322471, "percentage": 81.89, "elapsed_time": "0:24:13", "remaining_time": "0:05:21", "throughput": 6374.74, "total_tokens": 9268800}
{"current_steps": 9655, "total_steps": 11784, "loss": 0.1183, "lr": 1.9255299241230182e-07, "epoch": 0.8193312966734555, "percentage": 81.93, "elapsed_time": "0:24:14", "remaining_time": "0:05:20", "throughput": 6376.46, "total_tokens": 9273408}
{"current_steps": 9660, "total_steps": 11784, "loss": 0.0679, "lr": 1.91680068229803e-07, "epoch": 0.8197556008146639, "percentage": 81.98, "elapsed_time": "0:24:14", "remaining_time": "0:05:19", "throughput": 6378.3, "total_tokens": 9278208}
{"current_steps": 9665, "total_steps": 11784, "loss": 0.0643, "lr": 1.9080891742653105e-07, "epoch": 0.8201799049558723, "percentage": 82.02, "elapsed_time": "0:24:14", "remaining_time": "0:05:18", "throughput": 6380.09, "total_tokens": 9282944}
{"current_steps": 9670, "total_steps": 11784, "loss": 0.0074, "lr": 1.8993954191371042e-07, "epoch": 0.8206042090970808, "percentage": 82.06, "elapsed_time": "0:24:15", "remaining_time": "0:05:18", "throughput": 6382.12, "total_tokens": 9288064}
{"current_steps": 9675, "total_steps": 11784, "loss": 0.0289, "lr": 1.8907194359866986e-07, "epoch": 0.8210285132382892, "percentage": 82.1, "elapsed_time": "0:24:15", "remaining_time": "0:05:17", "throughput": 6384.1, "total_tokens": 9293120}
{"current_steps": 9680, "total_steps": 11784, "loss": 0.0717, "lr": 1.8820612438484075e-07, "epoch": 0.8214528173794976, "percentage": 82.15, "elapsed_time": "0:24:15", "remaining_time": "0:05:16", "throughput": 6385.67, "total_tokens": 9297472}
{"current_steps": 9685, "total_steps": 11784, "loss": 0.0743, "lr": 1.8734208617174986e-07, "epoch": 0.821877121520706, "percentage": 82.19, "elapsed_time": "0:24:16", "remaining_time": "0:05:15", "throughput": 6387.44, "total_tokens": 9302144}
{"current_steps": 9690, "total_steps": 11784, "loss": 0.0671, "lr": 1.864798308550173e-07, "epoch": 0.8223014256619144, "percentage": 82.23, "elapsed_time": "0:24:16", "remaining_time": "0:05:14", "throughput": 6389.41, "total_tokens": 9307200}
{"current_steps": 9695, "total_steps": 11784, "loss": 0.0212, "lr": 1.856193603263515e-07, "epoch": 0.8227257298031229, "percentage": 82.27, "elapsed_time": "0:24:17", "remaining_time": "0:05:13", "throughput": 6391.47, "total_tokens": 9312384}
{"current_steps": 9700, "total_steps": 11784, "loss": 0.0079, "lr": 1.8476067647354553e-07, "epoch": 0.8231500339443313, "percentage": 82.32, "elapsed_time": "0:24:17", "remaining_time": "0:05:13", "throughput": 6393.28, "total_tokens": 9317120}
{"current_steps": 9705, "total_steps": 11784, "loss": 0.0715, "lr": 1.8390378118047213e-07, "epoch": 0.8235743380855397, "percentage": 82.36, "elapsed_time": "0:24:17", "remaining_time": "0:05:12", "throughput": 6394.95, "total_tokens": 9321664}
{"current_steps": 9710, "total_steps": 11784, "loss": 0.0367, "lr": 1.8304867632708077e-07, "epoch": 0.8239986422267481, "percentage": 82.4, "elapsed_time": "0:24:17", "remaining_time": "0:05:11", "throughput": 6396.64, "total_tokens": 9326208}
{"current_steps": 9715, "total_steps": 11784, "loss": 0.0819, "lr": 1.821953637893917e-07, "epoch": 0.8244229463679565, "percentage": 82.44, "elapsed_time": "0:24:18", "remaining_time": "0:05:10", "throughput": 6398.61, "total_tokens": 9331264}
{"current_steps": 9720, "total_steps": 11784, "loss": 0.0681, "lr": 1.8134384543949478e-07, "epoch": 0.824847250509165, "percentage": 82.48, "elapsed_time": "0:24:18", "remaining_time": "0:05:09", "throughput": 6400.82, "total_tokens": 9336704}
{"current_steps": 9725, "total_steps": 11784, "loss": 0.0809, "lr": 1.804941231455417e-07, "epoch": 0.8252715546503734, "percentage": 82.53, "elapsed_time": "0:24:19", "remaining_time": "0:05:08", "throughput": 6402.94, "total_tokens": 9342016}
{"current_steps": 9730, "total_steps": 11784, "loss": 0.0543, "lr": 1.7964619877174513e-07, "epoch": 0.8256958587915818, "percentage": 82.57, "elapsed_time": "0:24:19", "remaining_time": "0:05:08", "throughput": 6404.74, "total_tokens": 9346752}
{"current_steps": 9735, "total_steps": 11784, "loss": 0.045, "lr": 1.788000741783725e-07, "epoch": 0.8261201629327902, "percentage": 82.61, "elapsed_time": "0:24:19", "remaining_time": "0:05:07", "throughput": 6406.42, "total_tokens": 9351296}
{"current_steps": 9740, "total_steps": 11784, "loss": 0.078, "lr": 1.7795575122174323e-07, "epoch": 0.8265444670739986, "percentage": 82.65, "elapsed_time": "0:24:20", "remaining_time": "0:05:06", "throughput": 6408.01, "total_tokens": 9355712}
{"current_steps": 9745, "total_steps": 11784, "loss": 0.0929, "lr": 1.7711323175422376e-07, "epoch": 0.8269687712152071, "percentage": 82.7, "elapsed_time": "0:24:20", "remaining_time": "0:05:05", "throughput": 6409.75, "total_tokens": 9360384}
{"current_steps": 9750, "total_steps": 11784, "loss": 0.0472, "lr": 1.7627251762422413e-07, "epoch": 0.8273930753564155, "percentage": 82.74, "elapsed_time": "0:24:20", "remaining_time": "0:05:04", "throughput": 6411.24, "total_tokens": 9364608}
{"current_steps": 9755, "total_steps": 11784, "loss": 0.0203, "lr": 1.7543361067619267e-07, "epoch": 0.8278173794976239, "percentage": 82.78, "elapsed_time": "0:24:20", "remaining_time": "0:05:03", "throughput": 6413.24, "total_tokens": 9369728}
{"current_steps": 9760, "total_steps": 11784, "loss": 0.0865, "lr": 1.7459651275061483e-07, "epoch": 0.8282416836388323, "percentage": 82.82, "elapsed_time": "0:24:21", "remaining_time": "0:05:03", "throughput": 6415.07, "total_tokens": 9374592}
{"current_steps": 9765, "total_steps": 11784, "loss": 0.0433, "lr": 1.737612256840053e-07, "epoch": 0.8286659877800407, "percentage": 82.87, "elapsed_time": "0:24:21", "remaining_time": "0:05:02", "throughput": 6417.34, "total_tokens": 9380160}
{"current_steps": 9770, "total_steps": 11784, "loss": 0.0528, "lr": 1.729277513089068e-07, "epoch": 0.8290902919212492, "percentage": 82.91, "elapsed_time": "0:24:22", "remaining_time": "0:05:01", "throughput": 6419.31, "total_tokens": 9385216}
{"current_steps": 9775, "total_steps": 11784, "loss": 0.0437, "lr": 1.7209609145388538e-07, "epoch": 0.8295145960624576, "percentage": 82.95, "elapsed_time": "0:24:22", "remaining_time": "0:05:00", "throughput": 6421.17, "total_tokens": 9390080}
{"current_steps": 9780, "total_steps": 11784, "loss": 0.0108, "lr": 1.7126624794352563e-07, "epoch": 0.829938900203666, "percentage": 82.99, "elapsed_time": "0:24:22", "remaining_time": "0:04:59", "throughput": 6422.65, "total_tokens": 9394304}
{"current_steps": 9785, "total_steps": 11784, "loss": 0.0646, "lr": 1.7043822259842766e-07, "epoch": 0.8303632043448744, "percentage": 83.04, "elapsed_time": "0:24:23", "remaining_time": "0:04:58", "throughput": 6424.62, "total_tokens": 9399360}
{"current_steps": 9790, "total_steps": 11784, "loss": 0.0338, "lr": 1.6961201723520247e-07, "epoch": 0.8307875084860828, "percentage": 83.08, "elapsed_time": "0:24:23", "remaining_time": "0:04:58", "throughput": 6426.56, "total_tokens": 9404352}
{"current_steps": 9795, "total_steps": 11784, "loss": 0.0434, "lr": 1.6878763366646832e-07, "epoch": 0.8312118126272913, "percentage": 83.12, "elapsed_time": "0:24:23", "remaining_time": "0:04:57", "throughput": 6428.36, "total_tokens": 9409152}
{"current_steps": 9800, "total_steps": 11784, "loss": 0.0449, "lr": 1.6796507370084656e-07, "epoch": 0.8316361167684997, "percentage": 83.16, "elapsed_time": "0:24:24", "remaining_time": "0:04:56", "throughput": 6430.34, "total_tokens": 9414208}
{"current_steps": 9805, "total_steps": 11784, "loss": 0.0646, "lr": 1.671443391429581e-07, "epoch": 0.8320604209097081, "percentage": 83.21, "elapsed_time": "0:24:24", "remaining_time": "0:04:55", "throughput": 6432.15, "total_tokens": 9419008}
{"current_steps": 9810, "total_steps": 11784, "loss": 0.0368, "lr": 1.6632543179341772e-07, "epoch": 0.8324847250509165, "percentage": 83.25, "elapsed_time": "0:24:24", "remaining_time": "0:04:54", "throughput": 6434.18, "total_tokens": 9424192}
{"current_steps": 9815, "total_steps": 11784, "loss": 0.0235, "lr": 1.6550835344883364e-07, "epoch": 0.832909029192125, "percentage": 83.29, "elapsed_time": "0:24:25", "remaining_time": "0:04:53", "throughput": 6436.01, "total_tokens": 9429056}
{"current_steps": 9820, "total_steps": 11784, "loss": 0.053, "lr": 1.646931059017994e-07, "epoch": 0.8333333333333334, "percentage": 83.33, "elapsed_time": "0:24:25", "remaining_time": "0:04:53", "throughput": 6437.32, "total_tokens": 9433024}
{"current_steps": 9825, "total_steps": 11784, "loss": 0.0435, "lr": 1.6387969094089317e-07, "epoch": 0.8337576374745418, "percentage": 83.38, "elapsed_time": "0:24:25", "remaining_time": "0:04:52", "throughput": 6439.05, "total_tokens": 9437696}
{"current_steps": 9830, "total_steps": 11784, "loss": 0.0472, "lr": 1.6306811035067203e-07, "epoch": 0.8341819416157502, "percentage": 83.42, "elapsed_time": "0:24:26", "remaining_time": "0:04:51", "throughput": 6441.11, "total_tokens": 9442944}
{"current_steps": 9835, "total_steps": 11784, "loss": 0.0394, "lr": 1.6225836591166886e-07, "epoch": 0.8346062457569586, "percentage": 83.46, "elapsed_time": "0:24:26", "remaining_time": "0:04:50", "throughput": 6442.9, "total_tokens": 9447680}
{"current_steps": 9840, "total_steps": 11784, "loss": 0.0774, "lr": 1.6145045940038803e-07, "epoch": 0.835030549898167, "percentage": 83.5, "elapsed_time": "0:24:26", "remaining_time": "0:04:49", "throughput": 6444.6, "total_tokens": 9452288}
{"current_steps": 9845, "total_steps": 11784, "loss": 0.063, "lr": 1.6064439258930217e-07, "epoch": 0.8354548540393755, "percentage": 83.55, "elapsed_time": "0:24:27", "remaining_time": "0:04:48", "throughput": 6446.28, "total_tokens": 9456896}
{"current_steps": 9850, "total_steps": 11784, "loss": 0.0847, "lr": 1.5984016724684658e-07, "epoch": 0.8358791581805839, "percentage": 83.59, "elapsed_time": "0:24:27", "remaining_time": "0:04:48", "throughput": 6448.07, "total_tokens": 9461632}
{"current_steps": 9855, "total_steps": 11784, "loss": 0.077, "lr": 1.5903778513741816e-07, "epoch": 0.8363034623217923, "percentage": 83.63, "elapsed_time": "0:24:27", "remaining_time": "0:04:47", "throughput": 6449.92, "total_tokens": 9466560}
{"current_steps": 9860, "total_steps": 11784, "loss": 0.0369, "lr": 1.5823724802136862e-07, "epoch": 0.8367277664630007, "percentage": 83.67, "elapsed_time": "0:24:28", "remaining_time": "0:04:46", "throughput": 6451.62, "total_tokens": 9471168}
{"current_steps": 9865, "total_steps": 11784, "loss": 0.105, "lr": 1.5743855765500258e-07, "epoch": 0.837152070604209, "percentage": 83.72, "elapsed_time": "0:24:28", "remaining_time": "0:04:45", "throughput": 6453.4, "total_tokens": 9475968}
{"current_steps": 9870, "total_steps": 11784, "loss": 0.0345, "lr": 1.5664171579057273e-07, "epoch": 0.8375763747454175, "percentage": 83.76, "elapsed_time": "0:24:28", "remaining_time": "0:04:44", "throughput": 6455.5, "total_tokens": 9481280}
{"current_steps": 9875, "total_steps": 11784, "loss": 0.0235, "lr": 1.5584672417627665e-07, "epoch": 0.8380006788866259, "percentage": 83.8, "elapsed_time": "0:24:29", "remaining_time": "0:04:43", "throughput": 6457.22, "total_tokens": 9485952}
{"current_steps": 9880, "total_steps": 11784, "loss": 0.0437, "lr": 1.5505358455625229e-07, "epoch": 0.8384249830278343, "percentage": 83.84, "elapsed_time": "0:24:29", "remaining_time": "0:04:43", "throughput": 6458.61, "total_tokens": 9490048}
{"current_steps": 9885, "total_steps": 11784, "loss": 0.0855, "lr": 1.5426229867057516e-07, "epoch": 0.8388492871690427, "percentage": 83.88, "elapsed_time": "0:24:29", "remaining_time": "0:04:42", "throughput": 6460.7, "total_tokens": 9495360}
{"current_steps": 9890, "total_steps": 11784, "loss": 0.0929, "lr": 1.5347286825525252e-07, "epoch": 0.8392735913102511, "percentage": 83.93, "elapsed_time": "0:24:30", "remaining_time": "0:04:41", "throughput": 6462.39, "total_tokens": 9499968}
{"current_steps": 9895, "total_steps": 11784, "loss": 0.0571, "lr": 1.526852950422226e-07, "epoch": 0.8396978954514596, "percentage": 83.97, "elapsed_time": "0:24:30", "remaining_time": "0:04:40", "throughput": 6464.17, "total_tokens": 9504704}
{"current_steps": 9900, "total_steps": 11784, "loss": 0.0243, "lr": 1.5189958075934771e-07, "epoch": 0.840122199592668, "percentage": 84.01, "elapsed_time": "0:24:30", "remaining_time": "0:04:39", "throughput": 6465.78, "total_tokens": 9509184}
{"current_steps": 9905, "total_steps": 11784, "loss": 0.047, "lr": 1.5111572713041253e-07, "epoch": 0.8405465037338764, "percentage": 84.05, "elapsed_time": "0:24:31", "remaining_time": "0:04:39", "throughput": 6467.61, "total_tokens": 9514048}
{"current_steps": 9910, "total_steps": 11784, "loss": 0.0214, "lr": 1.5033373587511944e-07, "epoch": 0.8409708078750848, "percentage": 84.1, "elapsed_time": "0:24:31", "remaining_time": "0:04:38", "throughput": 6469.56, "total_tokens": 9519104}
{"current_steps": 9915, "total_steps": 11784, "loss": 0.0717, "lr": 1.4955360870908505e-07, "epoch": 0.8413951120162932, "percentage": 84.14, "elapsed_time": "0:24:31", "remaining_time": "0:04:37", "throughput": 6471.3, "total_tokens": 9523840}
{"current_steps": 9920, "total_steps": 11784, "loss": 0.0594, "lr": 1.4877534734383624e-07, "epoch": 0.8418194161575017, "percentage": 84.18, "elapsed_time": "0:24:32", "remaining_time": "0:04:36", "throughput": 6472.96, "total_tokens": 9528384}
{"current_steps": 9925, "total_steps": 11784, "loss": 0.0608, "lr": 1.4799895348680647e-07, "epoch": 0.8422437202987101, "percentage": 84.22, "elapsed_time": "0:24:32", "remaining_time": "0:04:35", "throughput": 6474.77, "total_tokens": 9533184}
{"current_steps": 9930, "total_steps": 11784, "loss": 0.0261, "lr": 1.4722442884133214e-07, "epoch": 0.8426680244399185, "percentage": 84.27, "elapsed_time": "0:24:32", "remaining_time": "0:04:34", "throughput": 6477.12, "total_tokens": 9538944}
{"current_steps": 9935, "total_steps": 11784, "loss": 0.0125, "lr": 1.4645177510664886e-07, "epoch": 0.8430923285811269, "percentage": 84.31, "elapsed_time": "0:24:33", "remaining_time": "0:04:34", "throughput": 6478.66, "total_tokens": 9543296}
{"current_steps": 9940, "total_steps": 11784, "loss": 0.0706, "lr": 1.4568099397788746e-07, "epoch": 0.8435166327223353, "percentage": 84.35, "elapsed_time": "0:24:33", "remaining_time": "0:04:33", "throughput": 6480.3, "total_tokens": 9547840}
{"current_steps": 9945, "total_steps": 11784, "loss": 0.0964, "lr": 1.4491208714607016e-07, "epoch": 0.8439409368635438, "percentage": 84.39, "elapsed_time": "0:24:33", "remaining_time": "0:04:32", "throughput": 6482.12, "total_tokens": 9552704}
{"current_steps": 9950, "total_steps": 11784, "loss": 0.0629, "lr": 1.4414505629810813e-07, "epoch": 0.8443652410047522, "percentage": 84.44, "elapsed_time": "0:24:34", "remaining_time": "0:04:31", "throughput": 6484.35, "total_tokens": 9558272}
{"current_steps": 9955, "total_steps": 11784, "loss": 0.0944, "lr": 1.433799031167957e-07, "epoch": 0.8447895451459606, "percentage": 84.48, "elapsed_time": "0:24:34", "remaining_time": "0:04:30", "throughput": 6486.26, "total_tokens": 9563264}
{"current_steps": 9960, "total_steps": 11784, "loss": 0.0298, "lr": 1.426166292808083e-07, "epoch": 0.845213849287169, "percentage": 84.52, "elapsed_time": "0:24:34", "remaining_time": "0:04:30", "throughput": 6487.8, "total_tokens": 9567680}
{"current_steps": 9965, "total_steps": 11784, "loss": 0.0373, "lr": 1.4185523646469821e-07, "epoch": 0.8456381534283774, "percentage": 84.56, "elapsed_time": "0:24:35", "remaining_time": "0:04:29", "throughput": 6489.66, "total_tokens": 9572608}
{"current_steps": 9970, "total_steps": 11784, "loss": 0.0676, "lr": 1.410957263388909e-07, "epoch": 0.8460624575695859, "percentage": 84.61, "elapsed_time": "0:24:35", "remaining_time": "0:04:28", "throughput": 6491.26, "total_tokens": 9577088}
{"current_steps": 9975, "total_steps": 11784, "loss": 0.0421, "lr": 1.4033810056968155e-07, "epoch": 0.8464867617107943, "percentage": 84.65, "elapsed_time": "0:24:35", "remaining_time": "0:04:27", "throughput": 6493.07, "total_tokens": 9581952}
{"current_steps": 9980, "total_steps": 11784, "loss": 0.096, "lr": 1.3958236081923102e-07, "epoch": 0.8469110658520027, "percentage": 84.69, "elapsed_time": "0:24:36", "remaining_time": "0:04:26", "throughput": 6494.69, "total_tokens": 9586496}
{"current_steps": 9985, "total_steps": 11784, "loss": 0.0315, "lr": 1.3882850874556207e-07, "epoch": 0.8473353699932111, "percentage": 84.73, "elapsed_time": "0:24:36", "remaining_time": "0:04:26", "throughput": 6496.48, "total_tokens": 9591296}
{"current_steps": 9990, "total_steps": 11784, "loss": 0.0639, "lr": 1.3807654600255713e-07, "epoch": 0.8477596741344195, "percentage": 84.78, "elapsed_time": "0:24:36", "remaining_time": "0:04:25", "throughput": 6498.15, "total_tokens": 9595904}
{"current_steps": 9995, "total_steps": 11784, "loss": 0.1177, "lr": 1.373264742399526e-07, "epoch": 0.848183978275628, "percentage": 84.82, "elapsed_time": "0:24:37", "remaining_time": "0:04:24", "throughput": 6499.89, "total_tokens": 9600640}
{"current_steps": 10000, "total_steps": 11784, "loss": 0.0569, "lr": 1.3657829510333652e-07, "epoch": 0.8486082824168364, "percentage": 84.86, "elapsed_time": "0:24:37", "remaining_time": "0:04:23", "throughput": 6501.43, "total_tokens": 9605056}
{"current_steps": 10005, "total_steps": 11784, "loss": 0.0102, "lr": 1.3583201023414493e-07, "epoch": 0.8490325865580448, "percentage": 84.9, "elapsed_time": "0:24:37", "remaining_time": "0:04:22", "throughput": 6503.33, "total_tokens": 9610112}
{"current_steps": 10010, "total_steps": 11784, "loss": 0.0276, "lr": 1.350876212696579e-07, "epoch": 0.8494568906992532, "percentage": 84.95, "elapsed_time": "0:24:38", "remaining_time": "0:04:21", "throughput": 6505.54, "total_tokens": 9615744}
{"current_steps": 10015, "total_steps": 11784, "loss": 0.0089, "lr": 1.3434512984299596e-07, "epoch": 0.8498811948404617, "percentage": 84.99, "elapsed_time": "0:24:38", "remaining_time": "0:04:21", "throughput": 6507.15, "total_tokens": 9620288}
{"current_steps": 10020, "total_steps": 11784, "loss": 0.0775, "lr": 1.3360453758311686e-07, "epoch": 0.8503054989816701, "percentage": 85.03, "elapsed_time": "0:24:38", "remaining_time": "0:04:20", "throughput": 6508.86, "total_tokens": 9625024}
{"current_steps": 10025, "total_steps": 11784, "loss": 0.0471, "lr": 1.32865846114811e-07, "epoch": 0.8507298031228785, "percentage": 85.07, "elapsed_time": "0:24:39", "remaining_time": "0:04:19", "throughput": 6510.79, "total_tokens": 9630144}
{"current_steps": 10030, "total_steps": 11784, "loss": 0.0665, "lr": 1.321290570586999e-07, "epoch": 0.8511541072640869, "percentage": 85.12, "elapsed_time": "0:24:39", "remaining_time": "0:04:18", "throughput": 6512.37, "total_tokens": 9634624}
{"current_steps": 10030, "total_steps": 11784, "eval_loss": 0.05264058709144592, "epoch": 0.8511541072640869, "percentage": 85.12, "elapsed_time": "0:24:55", "remaining_time": "0:04:21", "throughput": 6442.69, "total_tokens": 9634624}
{"current_steps": 10035, "total_steps": 11784, "loss": 0.0181, "lr": 1.3139417203123027e-07, "epoch": 0.8515784114052953, "percentage": 85.16, "elapsed_time": "0:25:11", "remaining_time": "0:04:23", "throughput": 6378.51, "total_tokens": 9639744}
{"current_steps": 10040, "total_steps": 11784, "loss": 0.009, "lr": 1.306611926446718e-07, "epoch": 0.8520027155465038, "percentage": 85.2, "elapsed_time": "0:25:11", "remaining_time": "0:04:22", "throughput": 6380.23, "total_tokens": 9644480}
{"current_steps": 10045, "total_steps": 11784, "loss": 0.0478, "lr": 1.2993012050711406e-07, "epoch": 0.8524270196877122, "percentage": 85.24, "elapsed_time": "0:25:11", "remaining_time": "0:04:21", "throughput": 6382.07, "total_tokens": 9649408}
{"current_steps": 10050, "total_steps": 11784, "loss": 0.0887, "lr": 1.292009572224614e-07, "epoch": 0.8528513238289206, "percentage": 85.29, "elapsed_time": "0:25:12", "remaining_time": "0:04:20", "throughput": 6383.39, "total_tokens": 9653440}
{"current_steps": 10055, "total_steps": 11784, "loss": 0.0318, "lr": 1.284737043904306e-07, "epoch": 0.853275627970129, "percentage": 85.33, "elapsed_time": "0:25:12", "remaining_time": "0:04:20", "throughput": 6385.11, "total_tokens": 9658176}
{"current_steps": 10060, "total_steps": 11784, "loss": 0.0806, "lr": 1.2774836360654717e-07, "epoch": 0.8536999321113374, "percentage": 85.37, "elapsed_time": "0:25:12", "remaining_time": "0:04:19", "throughput": 6386.81, "total_tokens": 9662848}
{"current_steps": 10065, "total_steps": 11784, "loss": 0.0707, "lr": 1.2702493646214207e-07, "epoch": 0.8541242362525459, "percentage": 85.41, "elapsed_time": "0:25:13", "remaining_time": "0:04:18", "throughput": 6388.45, "total_tokens": 9667392}
{"current_steps": 10070, "total_steps": 11784, "loss": 0.1539, "lr": 1.2630342454434728e-07, "epoch": 0.8545485403937543, "percentage": 85.45, "elapsed_time": "0:25:13", "remaining_time": "0:04:17", "throughput": 6390.32, "total_tokens": 9672384}
{"current_steps": 10075, "total_steps": 11784, "loss": 0.0521, "lr": 1.2558382943609357e-07, "epoch": 0.8549728445349627, "percentage": 85.5, "elapsed_time": "0:25:13", "remaining_time": "0:04:16", "throughput": 6392.13, "total_tokens": 9677248}
{"current_steps": 10080, "total_steps": 11784, "loss": 0.0558, "lr": 1.2486615271610558e-07, "epoch": 0.8553971486761711, "percentage": 85.54, "elapsed_time": "0:25:14", "remaining_time": "0:04:15", "throughput": 6393.59, "total_tokens": 9681536}
{"current_steps": 10085, "total_steps": 11784, "loss": 0.081, "lr": 1.241503959589003e-07, "epoch": 0.8558214528173795, "percentage": 85.58, "elapsed_time": "0:25:14", "remaining_time": "0:04:15", "throughput": 6395.51, "total_tokens": 9686592}
{"current_steps": 10090, "total_steps": 11784, "loss": 0.0423, "lr": 1.234365607347816e-07, "epoch": 0.856245756958588, "percentage": 85.62, "elapsed_time": "0:25:14", "remaining_time": "0:04:14", "throughput": 6397.43, "total_tokens": 9691648}
{"current_steps": 10095, "total_steps": 11784, "loss": 0.0433, "lr": 1.22724648609838e-07, "epoch": 0.8566700610997964, "percentage": 85.67, "elapsed_time": "0:25:15", "remaining_time": "0:04:13", "throughput": 6399.38, "total_tokens": 9696768}
{"current_steps": 10100, "total_steps": 11784, "loss": 0.0689, "lr": 1.2201466114593884e-07, "epoch": 0.8570943652410048, "percentage": 85.71, "elapsed_time": "0:25:15", "remaining_time": "0:04:12", "throughput": 6401.04, "total_tokens": 9701376}
{"current_steps": 10105, "total_steps": 11784, "loss": 0.0659, "lr": 1.2130659990073144e-07, "epoch": 0.8575186693822132, "percentage": 85.75, "elapsed_time": "0:25:15", "remaining_time": "0:04:11", "throughput": 6402.37, "total_tokens": 9705408}
{"current_steps": 10110, "total_steps": 11784, "loss": 0.064, "lr": 1.206004664276359e-07, "epoch": 0.8579429735234216, "percentage": 85.79, "elapsed_time": "0:25:16", "remaining_time": "0:04:11", "throughput": 6403.91, "total_tokens": 9709824}
{"current_steps": 10115, "total_steps": 11784, "loss": 0.0826, "lr": 1.198962622758447e-07, "epoch": 0.8583672776646301, "percentage": 85.84, "elapsed_time": "0:25:16", "remaining_time": "0:04:10", "throughput": 6405.92, "total_tokens": 9715072}
{"current_steps": 10120, "total_steps": 11784, "loss": 0.0706, "lr": 1.1919398899031585e-07, "epoch": 0.8587915818058385, "percentage": 85.88, "elapsed_time": "0:25:16", "remaining_time": "0:04:09", "throughput": 6407.77, "total_tokens": 9720000}
{"current_steps": 10125, "total_steps": 11784, "loss": 0.0041, "lr": 1.1849364811177288e-07, "epoch": 0.8592158859470469, "percentage": 85.92, "elapsed_time": "0:25:17", "remaining_time": "0:04:08", "throughput": 6409.25, "total_tokens": 9724288}
{"current_steps": 10130, "total_steps": 11784, "loss": 0.0681, "lr": 1.1779524117669837e-07, "epoch": 0.8596401900882552, "percentage": 85.96, "elapsed_time": "0:25:17", "remaining_time": "0:04:07", "throughput": 6411.1, "total_tokens": 9729280}
{"current_steps": 10135, "total_steps": 11784, "loss": 0.0764, "lr": 1.1709876971733269e-07, "epoch": 0.8600644942294636, "percentage": 86.01, "elapsed_time": "0:25:17", "remaining_time": "0:04:06", "throughput": 6412.63, "total_tokens": 9733696}
{"current_steps": 10140, "total_steps": 11784, "loss": 0.016, "lr": 1.1640423526166987e-07, "epoch": 0.860488798370672, "percentage": 86.05, "elapsed_time": "0:25:18", "remaining_time": "0:04:06", "throughput": 6414.44, "total_tokens": 9738624}
{"current_steps": 10145, "total_steps": 11784, "loss": 0.0557, "lr": 1.1571163933345462e-07, "epoch": 0.8609131025118805, "percentage": 86.09, "elapsed_time": "0:25:18", "remaining_time": "0:04:05", "throughput": 6416.23, "total_tokens": 9743488}
{"current_steps": 10150, "total_steps": 11784, "loss": 0.0133, "lr": 1.150209834521777e-07, "epoch": 0.8613374066530889, "percentage": 86.13, "elapsed_time": "0:25:18", "remaining_time": "0:04:04", "throughput": 6418.72, "total_tokens": 9749632}
{"current_steps": 10155, "total_steps": 11784, "loss": 0.0291, "lr": 1.1433226913307514e-07, "epoch": 0.8617617107942973, "percentage": 86.18, "elapsed_time": "0:25:19", "remaining_time": "0:04:03", "throughput": 6420.48, "total_tokens": 9754432}
{"current_steps": 10160, "total_steps": 11784, "loss": 0.0293, "lr": 1.1364549788712185e-07, "epoch": 0.8621860149355057, "percentage": 86.22, "elapsed_time": "0:25:19", "remaining_time": "0:04:02", "throughput": 6422.21, "total_tokens": 9759168}
{"current_steps": 10165, "total_steps": 11784, "loss": 0.012, "lr": 1.1296067122103059e-07, "epoch": 0.8626103190767141, "percentage": 86.26, "elapsed_time": "0:25:19", "remaining_time": "0:04:02", "throughput": 6424.04, "total_tokens": 9764096}
{"current_steps": 10170, "total_steps": 11784, "loss": 0.0581, "lr": 1.1227779063724818e-07, "epoch": 0.8630346232179226, "percentage": 86.3, "elapsed_time": "0:25:20", "remaining_time": "0:04:01", "throughput": 6425.72, "total_tokens": 9768768}
{"current_steps": 10175, "total_steps": 11784, "loss": 0.0188, "lr": 1.115968576339511e-07, "epoch": 0.863458927359131, "percentage": 86.35, "elapsed_time": "0:25:20", "remaining_time": "0:04:00", "throughput": 6427.25, "total_tokens": 9773184}
{"current_steps": 10180, "total_steps": 11784, "loss": 0.0713, "lr": 1.1091787370504347e-07, "epoch": 0.8638832315003394, "percentage": 86.39, "elapsed_time": "0:25:20", "remaining_time": "0:03:59", "throughput": 6429.41, "total_tokens": 9778688}
{"current_steps": 10185, "total_steps": 11784, "loss": 0.0388, "lr": 1.1024084034015347e-07, "epoch": 0.8643075356415478, "percentage": 86.43, "elapsed_time": "0:25:21", "remaining_time": "0:03:58", "throughput": 6430.99, "total_tokens": 9783168}
{"current_steps": 10190, "total_steps": 11784, "loss": 0.0622, "lr": 1.095657590246295e-07, "epoch": 0.8647318397827563, "percentage": 86.47, "elapsed_time": "0:25:21", "remaining_time": "0:03:58", "throughput": 6432.61, "total_tokens": 9787712}
{"current_steps": 10195, "total_steps": 11784, "loss": 0.0461, "lr": 1.0889263123953773e-07, "epoch": 0.8651561439239647, "percentage": 86.52, "elapsed_time": "0:25:21", "remaining_time": "0:03:57", "throughput": 6434.3, "total_tokens": 9792384}
{"current_steps": 10200, "total_steps": 11784, "loss": 0.1011, "lr": 1.0822145846165853e-07, "epoch": 0.8655804480651731, "percentage": 86.56, "elapsed_time": "0:25:22", "remaining_time": "0:03:56", "throughput": 6436.41, "total_tokens": 9797824}
{"current_steps": 10205, "total_steps": 11784, "loss": 0.1421, "lr": 1.0755224216348235e-07, "epoch": 0.8660047522063815, "percentage": 86.6, "elapsed_time": "0:25:22", "remaining_time": "0:03:55", "throughput": 6438.3, "total_tokens": 9802880}
{"current_steps": 10210, "total_steps": 11784, "loss": 0.088, "lr": 1.0688498381320854e-07, "epoch": 0.8664290563475899, "percentage": 86.64, "elapsed_time": "0:25:22", "remaining_time": "0:03:54", "throughput": 6439.88, "total_tokens": 9807424}
{"current_steps": 10215, "total_steps": 11784, "loss": 0.0545, "lr": 1.0621968487473975e-07, "epoch": 0.8668533604887984, "percentage": 86.69, "elapsed_time": "0:25:23", "remaining_time": "0:03:53", "throughput": 6441.78, "total_tokens": 9812480}
{"current_steps": 10220, "total_steps": 11784, "loss": 0.0356, "lr": 1.0555634680768066e-07, "epoch": 0.8672776646300068, "percentage": 86.73, "elapsed_time": "0:25:23", "remaining_time": "0:03:53", "throughput": 6443.35, "total_tokens": 9816960}
{"current_steps": 10225, "total_steps": 11784, "loss": 0.0259, "lr": 1.0489497106733347e-07, "epoch": 0.8677019687712152, "percentage": 86.77, "elapsed_time": "0:25:23", "remaining_time": "0:03:52", "throughput": 6444.98, "total_tokens": 9821568}
{"current_steps": 10230, "total_steps": 11784, "loss": 0.0805, "lr": 1.0423555910469561e-07, "epoch": 0.8681262729124236, "percentage": 86.81, "elapsed_time": "0:25:24", "remaining_time": "0:03:51", "throughput": 6446.54, "total_tokens": 9826048}
{"current_steps": 10235, "total_steps": 11784, "loss": 0.0412, "lr": 1.0357811236645597e-07, "epoch": 0.868550577053632, "percentage": 86.86, "elapsed_time": "0:25:24", "remaining_time": "0:03:50", "throughput": 6448.23, "total_tokens": 9830720}
{"current_steps": 10240, "total_steps": 11784, "loss": 0.0653, "lr": 1.0292263229499209e-07, "epoch": 0.8689748811948405, "percentage": 86.9, "elapsed_time": "0:25:24", "remaining_time": "0:03:49", "throughput": 6450.05, "total_tokens": 9835648}
{"current_steps": 10245, "total_steps": 11784, "loss": 0.1175, "lr": 1.022691203283661e-07, "epoch": 0.8693991853360489, "percentage": 86.94, "elapsed_time": "0:25:25", "remaining_time": "0:03:49", "throughput": 6451.5, "total_tokens": 9839936}
{"current_steps": 10250, "total_steps": 11784, "loss": 0.0568, "lr": 1.0161757790032355e-07, "epoch": 0.8698234894772573, "percentage": 86.98, "elapsed_time": "0:25:25", "remaining_time": "0:03:48", "throughput": 6453.18, "total_tokens": 9844608}
{"current_steps": 10255, "total_steps": 11784, "loss": 0.0191, "lr": 1.0096800644028791e-07, "epoch": 0.8702477936184657, "percentage": 87.02, "elapsed_time": "0:25:25", "remaining_time": "0:03:47", "throughput": 6454.62, "total_tokens": 9848896}
{"current_steps": 10260, "total_steps": 11784, "loss": 0.0822, "lr": 1.003204073733589e-07, "epoch": 0.8706720977596741, "percentage": 87.07, "elapsed_time": "0:25:26", "remaining_time": "0:03:46", "throughput": 6456.08, "total_tokens": 9853184}
{"current_steps": 10265, "total_steps": 11784, "loss": 0.0627, "lr": 9.967478212030923e-08, "epoch": 0.8710964019008826, "percentage": 87.11, "elapsed_time": "0:25:26", "remaining_time": "0:03:45", "throughput": 6457.75, "total_tokens": 9857856}
{"current_steps": 10270, "total_steps": 11784, "loss": 0.0556, "lr": 9.903113209758096e-08, "epoch": 0.871520706042091, "percentage": 87.15, "elapsed_time": "0:25:26", "remaining_time": "0:03:45", "throughput": 6459.47, "total_tokens": 9862592}
{"current_steps": 10275, "total_steps": 11784, "loss": 0.0582, "lr": 9.838945871728266e-08, "epoch": 0.8719450101832994, "percentage": 87.19, "elapsed_time": "0:25:27", "remaining_time": "0:03:44", "throughput": 6461.3, "total_tokens": 9867584}
{"current_steps": 10280, "total_steps": 11784, "loss": 0.0089, "lr": 9.774976338718677e-08, "epoch": 0.8723693143245078, "percentage": 87.24, "elapsed_time": "0:25:27", "remaining_time": "0:03:43", "throughput": 6463.04, "total_tokens": 9872384}
{"current_steps": 10285, "total_steps": 11784, "loss": 0.0969, "lr": 9.711204751072499e-08, "epoch": 0.8727936184657162, "percentage": 87.28, "elapsed_time": "0:25:27", "remaining_time": "0:03:42", "throughput": 6464.5, "total_tokens": 9876672}
{"current_steps": 10290, "total_steps": 11784, "loss": 0.0259, "lr": 9.647631248698773e-08, "epoch": 0.8732179226069247, "percentage": 87.32, "elapsed_time": "0:25:28", "remaining_time": "0:03:41", "throughput": 6466.42, "total_tokens": 9881792}
{"current_steps": 10295, "total_steps": 11784, "loss": 0.1201, "lr": 9.584255971071886e-08, "epoch": 0.8736422267481331, "percentage": 87.36, "elapsed_time": "0:25:28", "remaining_time": "0:03:41", "throughput": 6468.08, "total_tokens": 9886464}
{"current_steps": 10300, "total_steps": 11784, "loss": 0.0121, "lr": 9.521079057231274e-08, "epoch": 0.8740665308893415, "percentage": 87.41, "elapsed_time": "0:25:28", "remaining_time": "0:03:40", "throughput": 6469.81, "total_tokens": 9891264}
{"current_steps": 10305, "total_steps": 11784, "loss": 0.0298, "lr": 9.45810064578133e-08, "epoch": 0.8744908350305499, "percentage": 87.45, "elapsed_time": "0:25:29", "remaining_time": "0:03:39", "throughput": 6471.69, "total_tokens": 9896320}
{"current_steps": 10310, "total_steps": 11784, "loss": 0.0864, "lr": 9.39532087489081e-08, "epoch": 0.8749151391717583, "percentage": 87.49, "elapsed_time": "0:25:29", "remaining_time": "0:03:38", "throughput": 6473.65, "total_tokens": 9901504}
{"current_steps": 10315, "total_steps": 11784, "loss": 0.0504, "lr": 9.33273988229275e-08, "epoch": 0.8753394433129668, "percentage": 87.53, "elapsed_time": "0:25:29", "remaining_time": "0:03:37", "throughput": 6475.77, "total_tokens": 9907008}
{"current_steps": 10320, "total_steps": 11784, "loss": 0.0989, "lr": 9.270357805284057e-08, "epoch": 0.8757637474541752, "percentage": 87.58, "elapsed_time": "0:25:30", "remaining_time": "0:03:37", "throughput": 6477.47, "total_tokens": 9911744}
{"current_steps": 10325, "total_steps": 11784, "loss": 0.1047, "lr": 9.208174780725253e-08, "epoch": 0.8761880515953836, "percentage": 87.62, "elapsed_time": "0:25:30", "remaining_time": "0:03:36", "throughput": 6478.95, "total_tokens": 9916096}
{"current_steps": 10330, "total_steps": 11784, "loss": 0.0295, "lr": 9.146190945040145e-08, "epoch": 0.876612355736592, "percentage": 87.66, "elapsed_time": "0:25:30", "remaining_time": "0:03:35", "throughput": 6480.41, "total_tokens": 9920448}
{"current_steps": 10335, "total_steps": 11784, "loss": 0.0886, "lr": 9.084406434215553e-08, "epoch": 0.8770366598778004, "percentage": 87.7, "elapsed_time": "0:25:31", "remaining_time": "0:03:34", "throughput": 6482.17, "total_tokens": 9925312}
{"current_steps": 10340, "total_steps": 11784, "loss": 0.0846, "lr": 9.022821383800926e-08, "epoch": 0.8774609640190089, "percentage": 87.75, "elapsed_time": "0:25:31", "remaining_time": "0:03:33", "throughput": 6483.78, "total_tokens": 9929920}
{"current_steps": 10345, "total_steps": 11784, "loss": 0.0035, "lr": 8.961435928908267e-08, "epoch": 0.8778852681602173, "percentage": 87.79, "elapsed_time": "0:25:31", "remaining_time": "0:03:33", "throughput": 6485.61, "total_tokens": 9934912}
{"current_steps": 10350, "total_steps": 11784, "loss": 0.0809, "lr": 8.900250204211513e-08, "epoch": 0.8783095723014257, "percentage": 87.83, "elapsed_time": "0:25:32", "remaining_time": "0:03:32", "throughput": 6487.25, "total_tokens": 9939520}
{"current_steps": 10355, "total_steps": 11784, "loss": 0.0441, "lr": 8.839264343946506e-08, "epoch": 0.8787338764426341, "percentage": 87.87, "elapsed_time": "0:25:32", "remaining_time": "0:03:31", "throughput": 6489.01, "total_tokens": 9944384}
{"current_steps": 10360, "total_steps": 11784, "loss": 0.0557, "lr": 8.778478481910611e-08, "epoch": 0.8791581805838425, "percentage": 87.92, "elapsed_time": "0:25:32", "remaining_time": "0:03:30", "throughput": 6490.67, "total_tokens": 9949056}
{"current_steps": 10365, "total_steps": 11784, "loss": 0.0435, "lr": 8.717892751462363e-08, "epoch": 0.879582484725051, "percentage": 87.96, "elapsed_time": "0:25:33", "remaining_time": "0:03:29", "throughput": 6492.59, "total_tokens": 9954176}
{"current_steps": 10370, "total_steps": 11784, "loss": 0.0449, "lr": 8.657507285521281e-08, "epoch": 0.8800067888662594, "percentage": 88.0, "elapsed_time": "0:25:33", "remaining_time": "0:03:29", "throughput": 6494.29, "total_tokens": 9958912}
{"current_steps": 10375, "total_steps": 11784, "loss": 0.0793, "lr": 8.597322216567493e-08, "epoch": 0.8804310930074678, "percentage": 88.04, "elapsed_time": "0:25:33", "remaining_time": "0:03:28", "throughput": 6495.97, "total_tokens": 9963648}
{"current_steps": 10380, "total_steps": 11784, "loss": 0.0145, "lr": 8.537337676641442e-08, "epoch": 0.8808553971486762, "percentage": 88.09, "elapsed_time": "0:25:34", "remaining_time": "0:03:27", "throughput": 6497.6, "total_tokens": 9968256}
{"current_steps": 10385, "total_steps": 11784, "loss": 0.0439, "lr": 8.477553797343728e-08, "epoch": 0.8812797012898846, "percentage": 88.13, "elapsed_time": "0:25:34", "remaining_time": "0:03:26", "throughput": 6499.5, "total_tokens": 9973376}
{"current_steps": 10390, "total_steps": 11784, "loss": 0.0804, "lr": 8.41797070983461e-08, "epoch": 0.881704005431093, "percentage": 88.17, "elapsed_time": "0:25:34", "remaining_time": "0:03:25", "throughput": 6501.27, "total_tokens": 9978240}
{"current_steps": 10395, "total_steps": 11784, "loss": 0.003, "lr": 8.358588544833877e-08, "epoch": 0.8821283095723014, "percentage": 88.21, "elapsed_time": "0:25:35", "remaining_time": "0:03:25", "throughput": 6502.86, "total_tokens": 9982784}
{"current_steps": 10400, "total_steps": 11784, "loss": 0.0894, "lr": 8.29940743262052e-08, "epoch": 0.8825526137135098, "percentage": 88.26, "elapsed_time": "0:25:35", "remaining_time": "0:03:24", "throughput": 6504.26, "total_tokens": 9987008}
{"current_steps": 10405, "total_steps": 11784, "loss": 0.0803, "lr": 8.240427503032443e-08, "epoch": 0.8829769178547182, "percentage": 88.3, "elapsed_time": "0:25:35", "remaining_time": "0:03:23", "throughput": 6506.43, "total_tokens": 9992640}
{"current_steps": 10410, "total_steps": 11784, "loss": 0.0592, "lr": 8.181648885466141e-08, "epoch": 0.8834012219959266, "percentage": 88.34, "elapsed_time": "0:25:36", "remaining_time": "0:03:22", "throughput": 6507.71, "total_tokens": 9996672}
{"current_steps": 10415, "total_steps": 11784, "loss": 0.07, "lr": 8.123071708876473e-08, "epoch": 0.883825526137135, "percentage": 88.38, "elapsed_time": "0:25:36", "remaining_time": "0:03:21", "throughput": 6509.29, "total_tokens": 10001216}
{"current_steps": 10420, "total_steps": 11784, "loss": 0.0299, "lr": 8.064696101776358e-08, "epoch": 0.8842498302783435, "percentage": 88.42, "elapsed_time": "0:25:36", "remaining_time": "0:03:21", "throughput": 6511.09, "total_tokens": 10006144}
{"current_steps": 10425, "total_steps": 11784, "loss": 0.0395, "lr": 8.006522192236487e-08, "epoch": 0.8846741344195519, "percentage": 88.47, "elapsed_time": "0:25:37", "remaining_time": "0:03:20", "throughput": 6513.11, "total_tokens": 10011520}
{"current_steps": 10430, "total_steps": 11784, "loss": 0.0071, "lr": 7.948550107885043e-08, "epoch": 0.8850984385607603, "percentage": 88.51, "elapsed_time": "0:25:37", "remaining_time": "0:03:19", "throughput": 6514.93, "total_tokens": 10016512}
{"current_steps": 10435, "total_steps": 11784, "loss": 0.0866, "lr": 7.89077997590738e-08, "epoch": 0.8855227427019687, "percentage": 88.55, "elapsed_time": "0:25:37", "remaining_time": "0:03:18", "throughput": 6516.44, "total_tokens": 10020928}
{"current_steps": 10440, "total_steps": 11784, "loss": 0.0255, "lr": 7.833211923045891e-08, "epoch": 0.8859470468431772, "percentage": 88.59, "elapsed_time": "0:25:38", "remaining_time": "0:03:18", "throughput": 6518.26, "total_tokens": 10025920}
{"current_steps": 10445, "total_steps": 11784, "loss": 0.0434, "lr": 7.775846075599524e-08, "epoch": 0.8863713509843856, "percentage": 88.64, "elapsed_time": "0:25:38", "remaining_time": "0:03:17", "throughput": 6519.83, "total_tokens": 10030464}
{"current_steps": 10450, "total_steps": 11784, "loss": 0.0498, "lr": 7.718682559423651e-08, "epoch": 0.886795655125594, "percentage": 88.68, "elapsed_time": "0:25:38", "remaining_time": "0:03:16", "throughput": 6521.57, "total_tokens": 10035328}
{"current_steps": 10455, "total_steps": 11784, "loss": 0.0692, "lr": 7.661721499929752e-08, "epoch": 0.8872199592668024, "percentage": 88.72, "elapsed_time": "0:25:39", "remaining_time": "0:03:15", "throughput": 6523.43, "total_tokens": 10040384}
{"current_steps": 10460, "total_steps": 11784, "loss": 0.0334, "lr": 7.60496302208512e-08, "epoch": 0.8876442634080108, "percentage": 88.76, "elapsed_time": "0:25:39", "remaining_time": "0:03:14", "throughput": 6525.29, "total_tokens": 10045440}
{"current_steps": 10465, "total_steps": 11784, "loss": 0.0272, "lr": 7.548407250412614e-08, "epoch": 0.8880685675492193, "percentage": 88.81, "elapsed_time": "0:25:39", "remaining_time": "0:03:14", "throughput": 6527.11, "total_tokens": 10050432}
{"current_steps": 10470, "total_steps": 11784, "loss": 0.0403, "lr": 7.492054308990381e-08, "epoch": 0.8884928716904277, "percentage": 88.85, "elapsed_time": "0:25:40", "remaining_time": "0:03:13", "throughput": 6528.84, "total_tokens": 10055296}
{"current_steps": 10475, "total_steps": 11784, "loss": 0.0513, "lr": 7.435904321451524e-08, "epoch": 0.8889171758316361, "percentage": 88.89, "elapsed_time": "0:25:40", "remaining_time": "0:03:12", "throughput": 6530.73, "total_tokens": 10060416}
{"current_steps": 10480, "total_steps": 11784, "loss": 0.0397, "lr": 7.379957410983995e-08, "epoch": 0.8893414799728445, "percentage": 88.93, "elapsed_time": "0:25:40", "remaining_time": "0:03:11", "throughput": 6532.58, "total_tokens": 10065472}
{"current_steps": 10485, "total_steps": 11784, "loss": 0.0267, "lr": 7.324213700330095e-08, "epoch": 0.8897657841140529, "percentage": 88.98, "elapsed_time": "0:25:41", "remaining_time": "0:03:10", "throughput": 6534.57, "total_tokens": 10070784}
{"current_steps": 10490, "total_steps": 11784, "loss": 0.0202, "lr": 7.268673311786378e-08, "epoch": 0.8901900882552614, "percentage": 89.02, "elapsed_time": "0:25:41", "remaining_time": "0:03:10", "throughput": 6536.46, "total_tokens": 10075904}
{"current_steps": 10495, "total_steps": 11784, "loss": 0.0229, "lr": 7.213336367203338e-08, "epoch": 0.8906143923964698, "percentage": 89.06, "elapsed_time": "0:25:41", "remaining_time": "0:03:09", "throughput": 6538.19, "total_tokens": 10080768}
{"current_steps": 10500, "total_steps": 11784, "loss": 0.0579, "lr": 7.158202987985106e-08, "epoch": 0.8910386965376782, "percentage": 89.1, "elapsed_time": "0:25:42", "remaining_time": "0:03:08", "throughput": 6539.74, "total_tokens": 10085312}
{"current_steps": 10505, "total_steps": 11784, "loss": 0.1098, "lr": 7.10327329508923e-08, "epoch": 0.8914630006788866, "percentage": 89.15, "elapsed_time": "0:25:42", "remaining_time": "0:03:07", "throughput": 6541.27, "total_tokens": 10089792}
{"current_steps": 10510, "total_steps": 11784, "loss": 0.0712, "lr": 7.048547409026384e-08, "epoch": 0.891887304820095, "percentage": 89.19, "elapsed_time": "0:25:42", "remaining_time": "0:03:07", "throughput": 6543.19, "total_tokens": 10094976}
{"current_steps": 10515, "total_steps": 11784, "loss": 0.0331, "lr": 6.994025449860064e-08, "epoch": 0.8923116089613035, "percentage": 89.23, "elapsed_time": "0:25:43", "remaining_time": "0:03:06", "throughput": 6544.55, "total_tokens": 10099200}
{"current_steps": 10520, "total_steps": 11784, "loss": 0.075, "lr": 6.939707537206485e-08, "epoch": 0.8927359131025119, "percentage": 89.27, "elapsed_time": "0:25:43", "remaining_time": "0:03:05", "throughput": 6546.43, "total_tokens": 10104320}
{"current_steps": 10525, "total_steps": 11784, "loss": 0.0464, "lr": 6.885593790234056e-08, "epoch": 0.8931602172437203, "percentage": 89.32, "elapsed_time": "0:25:43", "remaining_time": "0:03:04", "throughput": 6548.24, "total_tokens": 10109312}
{"current_steps": 10530, "total_steps": 11784, "loss": 0.0293, "lr": 6.831684327663367e-08, "epoch": 0.8935845213849287, "percentage": 89.36, "elapsed_time": "0:25:44", "remaining_time": "0:03:03", "throughput": 6549.65, "total_tokens": 10113600}
{"current_steps": 10535, "total_steps": 11784, "loss": 0.0048, "lr": 6.777979267766786e-08, "epoch": 0.8940088255261371, "percentage": 89.4, "elapsed_time": "0:25:44", "remaining_time": "0:03:03", "throughput": 6551.27, "total_tokens": 10118272}
{"current_steps": 10540, "total_steps": 11784, "loss": 0.059, "lr": 6.724478728368277e-08, "epoch": 0.8944331296673456, "percentage": 89.44, "elapsed_time": "0:25:44", "remaining_time": "0:03:02", "throughput": 6552.75, "total_tokens": 10122688}
{"current_steps": 10545, "total_steps": 11784, "loss": 0.1179, "lr": 6.671182826843047e-08, "epoch": 0.894857433808554, "percentage": 89.49, "elapsed_time": "0:25:45", "remaining_time": "0:03:01", "throughput": 6554.72, "total_tokens": 10128000}
{"current_steps": 10550, "total_steps": 11784, "loss": 0.0508, "lr": 6.618091680117399e-08, "epoch": 0.8952817379497624, "percentage": 89.53, "elapsed_time": "0:25:45", "remaining_time": "0:03:00", "throughput": 6556.28, "total_tokens": 10132544}
{"current_steps": 10555, "total_steps": 11784, "loss": 0.0739, "lr": 6.565205404668395e-08, "epoch": 0.8957060420909708, "percentage": 89.57, "elapsed_time": "0:25:45", "remaining_time": "0:02:59", "throughput": 6558.61, "total_tokens": 10138496}
{"current_steps": 10560, "total_steps": 11784, "loss": 0.0383, "lr": 6.512524116523633e-08, "epoch": 0.8961303462321792, "percentage": 89.61, "elapsed_time": "0:25:46", "remaining_time": "0:02:59", "throughput": 6560.37, "total_tokens": 10143424}
{"current_steps": 10565, "total_steps": 11784, "loss": 0.0861, "lr": 6.460047931261003e-08, "epoch": 0.8965546503733877, "percentage": 89.66, "elapsed_time": "0:25:46", "remaining_time": "0:02:58", "throughput": 6562.3, "total_tokens": 10148672}
{"current_steps": 10570, "total_steps": 11784, "loss": 0.0124, "lr": 6.407776964008383e-08, "epoch": 0.8969789545145961, "percentage": 89.7, "elapsed_time": "0:25:46", "remaining_time": "0:02:57", "throughput": 6563.95, "total_tokens": 10153408}
{"current_steps": 10575, "total_steps": 11784, "loss": 0.055, "lr": 6.355711329443481e-08, "epoch": 0.8974032586558045, "percentage": 89.74, "elapsed_time": "0:25:47", "remaining_time": "0:02:56", "throughput": 6565.49, "total_tokens": 10157952}
{"current_steps": 10580, "total_steps": 11784, "loss": 0.0355, "lr": 6.303851141793437e-08, "epoch": 0.8978275627970129, "percentage": 89.78, "elapsed_time": "0:25:47", "remaining_time": "0:02:56", "throughput": 6567.71, "total_tokens": 10163712}
{"current_steps": 10585, "total_steps": 11784, "loss": 0.0312, "lr": 6.252196514834751e-08, "epoch": 0.8982518669382213, "percentage": 89.83, "elapsed_time": "0:25:47", "remaining_time": "0:02:55", "throughput": 6569.41, "total_tokens": 10168512}
{"current_steps": 10590, "total_steps": 11784, "loss": 0.0404, "lr": 6.200747561892882e-08, "epoch": 0.8986761710794298, "percentage": 89.87, "elapsed_time": "0:25:48", "remaining_time": "0:02:54", "throughput": 6571.0, "total_tokens": 10173120}
{"current_steps": 10595, "total_steps": 11784, "loss": 0.0617, "lr": 6.149504395842087e-08, "epoch": 0.8991004752206382, "percentage": 89.91, "elapsed_time": "0:25:48", "remaining_time": "0:02:53", "throughput": 6572.65, "total_tokens": 10177856}
{"current_steps": 10600, "total_steps": 11784, "loss": 0.0328, "lr": 6.098467129105123e-08, "epoch": 0.8995247793618466, "percentage": 89.95, "elapsed_time": "0:25:48", "remaining_time": "0:02:53", "throughput": 6574.01, "total_tokens": 10182080}
{"current_steps": 10605, "total_steps": 11784, "loss": 0.0675, "lr": 6.047635873653068e-08, "epoch": 0.899949083503055, "percentage": 89.99, "elapsed_time": "0:25:49", "remaining_time": "0:02:52", "throughput": 6575.49, "total_tokens": 10186496}
{"current_steps": 10610, "total_steps": 11784, "loss": 0.0368, "lr": 5.997010741004949e-08, "epoch": 0.9003733876442634, "percentage": 90.04, "elapsed_time": "0:25:49", "remaining_time": "0:02:51", "throughput": 6576.97, "total_tokens": 10190912}
{"current_steps": 10615, "total_steps": 11784, "loss": 0.0525, "lr": 5.946591842227677e-08, "epoch": 0.9007976917854719, "percentage": 90.08, "elapsed_time": "0:25:49", "remaining_time": "0:02:50", "throughput": 6578.25, "total_tokens": 10195008}
{"current_steps": 10620, "total_steps": 11784, "loss": 0.0855, "lr": 5.8963792879356265e-08, "epoch": 0.9012219959266803, "percentage": 90.12, "elapsed_time": "0:25:50", "remaining_time": "0:02:49", "throughput": 6579.72, "total_tokens": 10199424}
{"current_steps": 10620, "total_steps": 11784, "eval_loss": 0.05229973420500755, "epoch": 0.9012219959266803, "percentage": 90.12, "elapsed_time": "0:26:05", "remaining_time": "0:02:51", "throughput": 6513.62, "total_tokens": 10199424}
{"current_steps": 10625, "total_steps": 11784, "loss": 0.1033, "lr": 5.84637318829051e-08, "epoch": 0.9016463000678887, "percentage": 90.16, "elapsed_time": "0:26:27", "remaining_time": "0:02:53", "throughput": 6426.67, "total_tokens": 10203968}
{"current_steps": 10630, "total_steps": 11784, "loss": 0.0844, "lr": 5.796573653001091e-08, "epoch": 0.9020706042090971, "percentage": 90.21, "elapsed_time": "0:26:28", "remaining_time": "0:02:52", "throughput": 6428.28, "total_tokens": 10208640}
{"current_steps": 10635, "total_steps": 11784, "loss": 0.0136, "lr": 5.746980791322942e-08, "epoch": 0.9024949083503055, "percentage": 90.25, "elapsed_time": "0:26:28", "remaining_time": "0:02:51", "throughput": 6429.99, "total_tokens": 10213504}
{"current_steps": 10640, "total_steps": 11784, "loss": 0.0535, "lr": 5.697594712058218e-08, "epoch": 0.902919212491514, "percentage": 90.29, "elapsed_time": "0:26:28", "remaining_time": "0:02:50", "throughput": 6431.74, "total_tokens": 10218432}
{"current_steps": 10645, "total_steps": 11784, "loss": 0.09, "lr": 5.6484155235554275e-08, "epoch": 0.9033435166327224, "percentage": 90.33, "elapsed_time": "0:26:29", "remaining_time": "0:02:50", "throughput": 6433.44, "total_tokens": 10223296}
{"current_steps": 10650, "total_steps": 11784, "loss": 0.1227, "lr": 5.599443333709131e-08, "epoch": 0.9037678207739308, "percentage": 90.38, "elapsed_time": "0:26:29", "remaining_time": "0:02:49", "throughput": 6435.03, "total_tokens": 10227904}
{"current_steps": 10655, "total_steps": 11784, "loss": 0.0481, "lr": 5.5506782499598394e-08, "epoch": 0.9041921249151391, "percentage": 90.42, "elapsed_time": "0:26:29", "remaining_time": "0:02:48", "throughput": 6436.66, "total_tokens": 10232640}
{"current_steps": 10660, "total_steps": 11784, "loss": 0.0891, "lr": 5.502120379293585e-08, "epoch": 0.9046164290563475, "percentage": 90.46, "elapsed_time": "0:26:30", "remaining_time": "0:02:47", "throughput": 6438.02, "total_tokens": 10236864}
{"current_steps": 10665, "total_steps": 11784, "loss": 0.0525, "lr": 5.453769828241872e-08, "epoch": 0.905040733197556, "percentage": 90.5, "elapsed_time": "0:26:30", "remaining_time": "0:02:46", "throughput": 6439.45, "total_tokens": 10241216}
{"current_steps": 10670, "total_steps": 11784, "loss": 0.0544, "lr": 5.4056267028813606e-08, "epoch": 0.9054650373387644, "percentage": 90.55, "elapsed_time": "0:26:30", "remaining_time": "0:02:46", "throughput": 6441.1, "total_tokens": 10245952}
{"current_steps": 10675, "total_steps": 11784, "loss": 0.0321, "lr": 5.357691108833584e-08, "epoch": 0.9058893414799728, "percentage": 90.59, "elapsed_time": "0:26:31", "remaining_time": "0:02:45", "throughput": 6443.12, "total_tokens": 10251392}
{"current_steps": 10680, "total_steps": 11784, "loss": 0.1047, "lr": 5.309963151264829e-08, "epoch": 0.9063136456211812, "percentage": 90.63, "elapsed_time": "0:26:31", "remaining_time": "0:02:44", "throughput": 6444.75, "total_tokens": 10256128}
{"current_steps": 10685, "total_steps": 11784, "loss": 0.043, "lr": 5.262442934885813e-08, "epoch": 0.9067379497623896, "percentage": 90.67, "elapsed_time": "0:26:31", "remaining_time": "0:02:43", "throughput": 6446.1, "total_tokens": 10260352}
{"current_steps": 10690, "total_steps": 11784, "loss": 0.0157, "lr": 5.21513056395152e-08, "epoch": 0.9071622539035981, "percentage": 90.72, "elapsed_time": "0:26:32", "remaining_time": "0:02:42", "throughput": 6447.88, "total_tokens": 10265344}
{"current_steps": 10695, "total_steps": 11784, "loss": 0.0575, "lr": 5.168026142260862e-08, "epoch": 0.9075865580448065, "percentage": 90.76, "elapsed_time": "0:26:32", "remaining_time": "0:02:42", "throughput": 6449.24, "total_tokens": 10269632}
{"current_steps": 10700, "total_steps": 11784, "loss": 0.0206, "lr": 5.121129773156663e-08, "epoch": 0.9080108621860149, "percentage": 90.8, "elapsed_time": "0:26:32", "remaining_time": "0:02:41", "throughput": 6450.97, "total_tokens": 10274560}
{"current_steps": 10705, "total_steps": 11784, "loss": 0.0327, "lr": 5.074441559525167e-08, "epoch": 0.9084351663272233, "percentage": 90.84, "elapsed_time": "0:26:33", "remaining_time": "0:02:40", "throughput": 6452.73, "total_tokens": 10279552}
{"current_steps": 10710, "total_steps": 11784, "loss": 0.0499, "lr": 5.027961603796027e-08, "epoch": 0.9088594704684317, "percentage": 90.89, "elapsed_time": "0:26:33", "remaining_time": "0:02:39", "throughput": 6454.35, "total_tokens": 10284288}
{"current_steps": 10715, "total_steps": 11784, "loss": 0.0414, "lr": 4.981690007941952e-08, "epoch": 0.9092837746096402, "percentage": 90.93, "elapsed_time": "0:26:33", "remaining_time": "0:02:39", "throughput": 6456.29, "total_tokens": 10289600}
{"current_steps": 10720, "total_steps": 11784, "loss": 0.0168, "lr": 4.93562687347856e-08, "epoch": 0.9097080787508486, "percentage": 90.97, "elapsed_time": "0:26:34", "remaining_time": "0:02:38", "throughput": 6457.81, "total_tokens": 10294144}
{"current_steps": 10725, "total_steps": 11784, "loss": 0.0495, "lr": 4.889772301464112e-08, "epoch": 0.910132382892057, "percentage": 91.01, "elapsed_time": "0:26:34", "remaining_time": "0:02:37", "throughput": 6459.38, "total_tokens": 10298752}
{"current_steps": 10730, "total_steps": 11784, "loss": 0.0437, "lr": 4.844126392499304e-08, "epoch": 0.9105566870332654, "percentage": 91.06, "elapsed_time": "0:26:34", "remaining_time": "0:02:36", "throughput": 6460.98, "total_tokens": 10303424}
{"current_steps": 10735, "total_steps": 11784, "loss": 0.0589, "lr": 4.7986892467270057e-08, "epoch": 0.9109809911744738, "percentage": 91.1, "elapsed_time": "0:26:35", "remaining_time": "0:02:35", "throughput": 6462.58, "total_tokens": 10308096}
{"current_steps": 10740, "total_steps": 11784, "loss": 0.0508, "lr": 4.7534609638321785e-08, "epoch": 0.9114052953156823, "percentage": 91.14, "elapsed_time": "0:26:35", "remaining_time": "0:02:35", "throughput": 6464.39, "total_tokens": 10313152}
{"current_steps": 10745, "total_steps": 11784, "loss": 0.0348, "lr": 4.70844164304145e-08, "epoch": 0.9118295994568907, "percentage": 91.18, "elapsed_time": "0:26:35", "remaining_time": "0:02:34", "throughput": 6466.09, "total_tokens": 10318016}
{"current_steps": 10750, "total_steps": 11784, "loss": 0.0304, "lr": 4.663631383123057e-08, "epoch": 0.9122539035980991, "percentage": 91.23, "elapsed_time": "0:26:36", "remaining_time": "0:02:33", "throughput": 6467.55, "total_tokens": 10322432}
{"current_steps": 10755, "total_steps": 11784, "loss": 0.0115, "lr": 4.61903028238656e-08, "epoch": 0.9126782077393075, "percentage": 91.27, "elapsed_time": "0:26:36", "remaining_time": "0:02:32", "throughput": 6469.17, "total_tokens": 10327168}
{"current_steps": 10760, "total_steps": 11784, "loss": 0.0781, "lr": 4.5746384386826767e-08, "epoch": 0.9131025118805159, "percentage": 91.31, "elapsed_time": "0:26:36", "remaining_time": "0:02:31", "throughput": 6470.64, "total_tokens": 10331584}
{"current_steps": 10765, "total_steps": 11784, "loss": 0.0269, "lr": 4.5304559494030004e-08, "epoch": 0.9135268160217244, "percentage": 91.35, "elapsed_time": "0:26:37", "remaining_time": "0:02:31", "throughput": 6472.45, "total_tokens": 10336640}
{"current_steps": 10770, "total_steps": 11784, "loss": 0.0617, "lr": 4.486482911479839e-08, "epoch": 0.9139511201629328, "percentage": 91.4, "elapsed_time": "0:26:37", "remaining_time": "0:02:30", "throughput": 6474.12, "total_tokens": 10341440}
{"current_steps": 10775, "total_steps": 11784, "loss": 0.0104, "lr": 4.442719421385921e-08, "epoch": 0.9143754243041412, "percentage": 91.44, "elapsed_time": "0:26:37", "remaining_time": "0:02:29", "throughput": 6475.97, "total_tokens": 10346624}
{"current_steps": 10780, "total_steps": 11784, "loss": 0.0092, "lr": 4.399165575134378e-08, "epoch": 0.9147997284453496, "percentage": 91.48, "elapsed_time": "0:26:38", "remaining_time": "0:02:28", "throughput": 6477.69, "total_tokens": 10351552}
{"current_steps": 10785, "total_steps": 11784, "loss": 0.0601, "lr": 4.3558214682782645e-08, "epoch": 0.915224032586558, "percentage": 91.52, "elapsed_time": "0:26:38", "remaining_time": "0:02:28", "throughput": 6479.33, "total_tokens": 10356352}
{"current_steps": 10790, "total_steps": 11784, "loss": 0.0717, "lr": 4.312687195910558e-08, "epoch": 0.9156483367277665, "percentage": 91.56, "elapsed_time": "0:26:38", "remaining_time": "0:02:27", "throughput": 6481.39, "total_tokens": 10361920}
{"current_steps": 10795, "total_steps": 11784, "loss": 0.0724, "lr": 4.269762852663894e-08, "epoch": 0.9160726408689749, "percentage": 91.61, "elapsed_time": "0:26:39", "remaining_time": "0:02:26", "throughput": 6482.79, "total_tokens": 10366272}
{"current_steps": 10800, "total_steps": 11784, "loss": 0.0167, "lr": 4.227048532710287e-08, "epoch": 0.9164969450101833, "percentage": 91.65, "elapsed_time": "0:26:39", "remaining_time": "0:02:25", "throughput": 6484.59, "total_tokens": 10371328}
{"current_steps": 10805, "total_steps": 11784, "loss": 0.0604, "lr": 4.184544329761008e-08, "epoch": 0.9169212491513917, "percentage": 91.69, "elapsed_time": "0:26:39", "remaining_time": "0:02:24", "throughput": 6486.36, "total_tokens": 10376384}
{"current_steps": 10810, "total_steps": 11784, "loss": 0.0687, "lr": 4.1422503370663553e-08, "epoch": 0.9173455532926001, "percentage": 91.73, "elapsed_time": "0:26:40", "remaining_time": "0:02:24", "throughput": 6487.97, "total_tokens": 10381120}
{"current_steps": 10815, "total_steps": 11784, "loss": 0.0225, "lr": 4.100166647415437e-08, "epoch": 0.9177698574338086, "percentage": 91.78, "elapsed_time": "0:26:40", "remaining_time": "0:02:23", "throughput": 6489.39, "total_tokens": 10385536}
{"current_steps": 10820, "total_steps": 11784, "loss": 0.0188, "lr": 4.058293353135988e-08, "epoch": 0.918194161575017, "percentage": 91.82, "elapsed_time": "0:26:40", "remaining_time": "0:02:22", "throughput": 6490.97, "total_tokens": 10390208}
{"current_steps": 10825, "total_steps": 11784, "loss": 0.051, "lr": 4.016630546094158e-08, "epoch": 0.9186184657162254, "percentage": 91.86, "elapsed_time": "0:26:41", "remaining_time": "0:02:21", "throughput": 6492.38, "total_tokens": 10394560}
{"current_steps": 10830, "total_steps": 11784, "loss": 0.0707, "lr": 3.975178317694239e-08, "epoch": 0.9190427698574338, "percentage": 91.9, "elapsed_time": "0:26:41", "remaining_time": "0:02:21", "throughput": 6493.74, "total_tokens": 10398848}
{"current_steps": 10835, "total_steps": 11784, "loss": 0.036, "lr": 3.9339367588786644e-08, "epoch": 0.9194670739986422, "percentage": 91.95, "elapsed_time": "0:26:41", "remaining_time": "0:02:20", "throughput": 6495.67, "total_tokens": 10404160}
{"current_steps": 10840, "total_steps": 11784, "loss": 0.051, "lr": 3.892905960127546e-08, "epoch": 0.9198913781398507, "percentage": 91.99, "elapsed_time": "0:26:42", "remaining_time": "0:02:19", "throughput": 6497.16, "total_tokens": 10408704}
{"current_steps": 10845, "total_steps": 11784, "loss": 0.0547, "lr": 3.852086011458688e-08, "epoch": 0.9203156822810591, "percentage": 92.03, "elapsed_time": "0:26:42", "remaining_time": "0:02:18", "throughput": 6498.69, "total_tokens": 10413312}
{"current_steps": 10850, "total_steps": 11784, "loss": 0.048, "lr": 3.811477002427288e-08, "epoch": 0.9207399864222675, "percentage": 92.07, "elapsed_time": "0:26:42", "remaining_time": "0:02:17", "throughput": 6500.3, "total_tokens": 10418048}
{"current_steps": 10855, "total_steps": 11784, "loss": 0.0239, "lr": 3.771079022125745e-08, "epoch": 0.9211642905634759, "percentage": 92.12, "elapsed_time": "0:26:43", "remaining_time": "0:02:17", "throughput": 6501.73, "total_tokens": 10422464}
{"current_steps": 10860, "total_steps": 11784, "loss": 0.1148, "lr": 3.7308921591835074e-08, "epoch": 0.9215885947046843, "percentage": 92.16, "elapsed_time": "0:26:43", "remaining_time": "0:02:16", "throughput": 6503.16, "total_tokens": 10426880}
{"current_steps": 10865, "total_steps": 11784, "loss": 0.1021, "lr": 3.6909165017668385e-08, "epoch": 0.9220128988458928, "percentage": 92.2, "elapsed_time": "0:26:43", "remaining_time": "0:02:15", "throughput": 6504.55, "total_tokens": 10431232}
{"current_steps": 10870, "total_steps": 11784, "loss": 0.1128, "lr": 3.651152137578617e-08, "epoch": 0.9224372029871012, "percentage": 92.24, "elapsed_time": "0:26:44", "remaining_time": "0:02:14", "throughput": 6506.77, "total_tokens": 10437120}
{"current_steps": 10875, "total_steps": 11784, "loss": 0.1289, "lr": 3.611599153858214e-08, "epoch": 0.9228615071283096, "percentage": 92.29, "elapsed_time": "0:26:44", "remaining_time": "0:02:14", "throughput": 6509.22, "total_tokens": 10443456}
{"current_steps": 10880, "total_steps": 11784, "loss": 0.0611, "lr": 3.572257637381182e-08, "epoch": 0.923285811269518, "percentage": 92.33, "elapsed_time": "0:26:44", "remaining_time": "0:02:13", "throughput": 6511.01, "total_tokens": 10448576}
{"current_steps": 10885, "total_steps": 11784, "loss": 0.0389, "lr": 3.533127674459202e-08, "epoch": 0.9237101154107265, "percentage": 92.37, "elapsed_time": "0:26:45", "remaining_time": "0:02:12", "throughput": 6512.68, "total_tokens": 10453440}
{"current_steps": 10890, "total_steps": 11784, "loss": 0.0268, "lr": 3.494209350939792e-08, "epoch": 0.9241344195519349, "percentage": 92.41, "elapsed_time": "0:26:45", "remaining_time": "0:02:11", "throughput": 6514.27, "total_tokens": 10458176}
{"current_steps": 10895, "total_steps": 11784, "loss": 0.0594, "lr": 3.455502752206152e-08, "epoch": 0.9245587236931433, "percentage": 92.46, "elapsed_time": "0:26:45", "remaining_time": "0:02:11", "throughput": 6516.02, "total_tokens": 10463232}
{"current_steps": 10900, "total_steps": 11784, "loss": 0.0892, "lr": 3.4170079631769764e-08, "epoch": 0.9249830278343517, "percentage": 92.5, "elapsed_time": "0:26:46", "remaining_time": "0:02:10", "throughput": 6517.65, "total_tokens": 10468032}
{"current_steps": 10905, "total_steps": 11784, "loss": 0.0135, "lr": 3.378725068306298e-08, "epoch": 0.9254073319755601, "percentage": 92.54, "elapsed_time": "0:26:46", "remaining_time": "0:02:09", "throughput": 6519.27, "total_tokens": 10472832}
{"current_steps": 10910, "total_steps": 11784, "loss": 0.0199, "lr": 3.3406541515832e-08, "epoch": 0.9258316361167686, "percentage": 92.58, "elapsed_time": "0:26:46", "remaining_time": "0:02:08", "throughput": 6520.69, "total_tokens": 10477248}
{"current_steps": 10915, "total_steps": 11784, "loss": 0.057, "lr": 3.302795296531813e-08, "epoch": 0.926255940257977, "percentage": 92.63, "elapsed_time": "0:26:47", "remaining_time": "0:02:07", "throughput": 6522.24, "total_tokens": 10481920}
{"current_steps": 10920, "total_steps": 11784, "loss": 0.0741, "lr": 3.265148586210942e-08, "epoch": 0.9266802443991853, "percentage": 92.67, "elapsed_time": "0:26:47", "remaining_time": "0:02:07", "throughput": 6523.97, "total_tokens": 10486976}
{"current_steps": 10925, "total_steps": 11784, "loss": 0.0575, "lr": 3.2277141032139746e-08, "epoch": 0.9271045485403937, "percentage": 92.71, "elapsed_time": "0:26:47", "remaining_time": "0:02:06", "throughput": 6525.55, "total_tokens": 10491712}
{"current_steps": 10930, "total_steps": 11784, "loss": 0.0889, "lr": 3.190491929668748e-08, "epoch": 0.9275288526816021, "percentage": 92.75, "elapsed_time": "0:26:48", "remaining_time": "0:02:05", "throughput": 6527.4, "total_tokens": 10496960}
{"current_steps": 10935, "total_steps": 11784, "loss": 0.0602, "lr": 3.15348214723723e-08, "epoch": 0.9279531568228105, "percentage": 92.8, "elapsed_time": "0:26:48", "remaining_time": "0:02:04", "throughput": 6528.68, "total_tokens": 10501120}
{"current_steps": 10940, "total_steps": 11784, "loss": 0.0228, "lr": 3.11668483711548e-08, "epoch": 0.928377460964019, "percentage": 92.84, "elapsed_time": "0:26:48", "remaining_time": "0:02:04", "throughput": 6530.88, "total_tokens": 10507008}
{"current_steps": 10945, "total_steps": 11784, "loss": 0.0284, "lr": 3.0801000800333876e-08, "epoch": 0.9288017651052274, "percentage": 92.88, "elapsed_time": "0:26:49", "remaining_time": "0:02:03", "throughput": 6532.28, "total_tokens": 10511424}
{"current_steps": 10950, "total_steps": 11784, "loss": 0.0394, "lr": 3.043727956254538e-08, "epoch": 0.9292260692464358, "percentage": 92.92, "elapsed_time": "0:26:49", "remaining_time": "0:02:02", "throughput": 6533.75, "total_tokens": 10515968}
{"current_steps": 10955, "total_steps": 11784, "loss": 0.0882, "lr": 3.007568545576011e-08, "epoch": 0.9296503733876442, "percentage": 92.97, "elapsed_time": "0:26:49", "remaining_time": "0:02:01", "throughput": 6535.27, "total_tokens": 10520576}
{"current_steps": 10960, "total_steps": 11784, "loss": 0.0491, "lr": 2.971621927328216e-08, "epoch": 0.9300746775288526, "percentage": 93.01, "elapsed_time": "0:26:50", "remaining_time": "0:02:01", "throughput": 6536.96, "total_tokens": 10525504}
{"current_steps": 10965, "total_steps": 11784, "loss": 0.1112, "lr": 2.9358881803746794e-08, "epoch": 0.9304989816700611, "percentage": 93.05, "elapsed_time": "0:26:50", "remaining_time": "0:02:00", "throughput": 6538.46, "total_tokens": 10530112}
{"current_steps": 10970, "total_steps": 11784, "loss": 0.0864, "lr": 2.900367383111979e-08, "epoch": 0.9309232858112695, "percentage": 93.09, "elapsed_time": "0:26:50", "remaining_time": "0:01:59", "throughput": 6540.24, "total_tokens": 10535232}
{"current_steps": 10975, "total_steps": 11784, "loss": 0.0258, "lr": 2.865059613469434e-08, "epoch": 0.9313475899524779, "percentage": 93.13, "elapsed_time": "0:26:51", "remaining_time": "0:01:58", "throughput": 6541.68, "total_tokens": 10539712}
{"current_steps": 10980, "total_steps": 11784, "loss": 0.057, "lr": 2.829964948909047e-08, "epoch": 0.9317718940936863, "percentage": 93.18, "elapsed_time": "0:26:51", "remaining_time": "0:01:58", "throughput": 6543.08, "total_tokens": 10544128}
{"current_steps": 10985, "total_steps": 11784, "loss": 0.0174, "lr": 2.795083466425252e-08, "epoch": 0.9321961982348947, "percentage": 93.22, "elapsed_time": "0:26:51", "remaining_time": "0:01:57", "throughput": 6544.33, "total_tokens": 10548288}
{"current_steps": 10990, "total_steps": 11784, "loss": 0.0176, "lr": 2.760415242544811e-08, "epoch": 0.9326205023761032, "percentage": 93.26, "elapsed_time": "0:26:52", "remaining_time": "0:01:56", "throughput": 6545.62, "total_tokens": 10552512}
{"current_steps": 10995, "total_steps": 11784, "loss": 0.0617, "lr": 2.7259603533266063e-08, "epoch": 0.9330448065173116, "percentage": 93.3, "elapsed_time": "0:26:52", "remaining_time": "0:01:55", "throughput": 6547.58, "total_tokens": 10557952}
{"current_steps": 11000, "total_steps": 11784, "loss": 0.0529, "lr": 2.6917188743614704e-08, "epoch": 0.93346911065852, "percentage": 93.35, "elapsed_time": "0:26:52", "remaining_time": "0:01:54", "throughput": 6548.89, "total_tokens": 10562240}
{"current_steps": 11005, "total_steps": 11784, "loss": 0.0832, "lr": 2.6576908807720233e-08, "epoch": 0.9338934147997284, "percentage": 93.39, "elapsed_time": "0:26:53", "remaining_time": "0:01:54", "throughput": 6550.45, "total_tokens": 10566976}
{"current_steps": 11010, "total_steps": 11784, "loss": 0.0393, "lr": 2.623876447212592e-08, "epoch": 0.9343177189409368, "percentage": 93.43, "elapsed_time": "0:26:53", "remaining_time": "0:01:53", "throughput": 6551.94, "total_tokens": 10571584}
{"current_steps": 11015, "total_steps": 11784, "loss": 0.082, "lr": 2.590275647868867e-08, "epoch": 0.9347420230821453, "percentage": 93.47, "elapsed_time": "0:26:53", "remaining_time": "0:01:52", "throughput": 6553.78, "total_tokens": 10576832}
{"current_steps": 11020, "total_steps": 11784, "loss": 0.0305, "lr": 2.5568885564579258e-08, "epoch": 0.9351663272233537, "percentage": 93.52, "elapsed_time": "0:26:54", "remaining_time": "0:01:51", "throughput": 6555.14, "total_tokens": 10581184}
{"current_steps": 11025, "total_steps": 11784, "loss": 0.0419, "lr": 2.5237152462279532e-08, "epoch": 0.9355906313645621, "percentage": 93.56, "elapsed_time": "0:26:54", "remaining_time": "0:01:51", "throughput": 6556.64, "total_tokens": 10585792}
{"current_steps": 11030, "total_steps": 11784, "loss": 0.0216, "lr": 2.4907557899581212e-08, "epoch": 0.9360149355057705, "percentage": 93.6, "elapsed_time": "0:26:54", "remaining_time": "0:01:50", "throughput": 6557.93, "total_tokens": 10590016}
{"current_steps": 11035, "total_steps": 11784, "loss": 0.0183, "lr": 2.4580102599584317e-08, "epoch": 0.936439239646979, "percentage": 93.64, "elapsed_time": "0:26:55", "remaining_time": "0:01:49", "throughput": 6559.42, "total_tokens": 10594624}
{"current_steps": 11040, "total_steps": 11784, "loss": 0.1089, "lr": 2.425478728069552e-08, "epoch": 0.9368635437881874, "percentage": 93.69, "elapsed_time": "0:26:55", "remaining_time": "0:01:48", "throughput": 6560.75, "total_tokens": 10598912}
{"current_steps": 11045, "total_steps": 11784, "loss": 0.0255, "lr": 2.3931612656626688e-08, "epoch": 0.9372878479293958, "percentage": 93.73, "elapsed_time": "0:26:55", "remaining_time": "0:01:48", "throughput": 6562.34, "total_tokens": 10603648}
{"current_steps": 11050, "total_steps": 11784, "loss": 0.0221, "lr": 2.3610579436392996e-08, "epoch": 0.9377121520706042, "percentage": 93.77, "elapsed_time": "0:26:56", "remaining_time": "0:01:47", "throughput": 6564.05, "total_tokens": 10608640}
{"current_steps": 11055, "total_steps": 11784, "loss": 0.1013, "lr": 2.329168832431161e-08, "epoch": 0.9381364562118126, "percentage": 93.81, "elapsed_time": "0:26:56", "remaining_time": "0:01:46", "throughput": 6565.58, "total_tokens": 10613312}
{"current_steps": 11060, "total_steps": 11784, "loss": 0.0113, "lr": 2.2974940020000112e-08, "epoch": 0.938560760353021, "percentage": 93.86, "elapsed_time": "0:26:56", "remaining_time": "0:01:45", "throughput": 6566.92, "total_tokens": 10617600}
{"current_steps": 11065, "total_steps": 11784, "loss": 0.109, "lr": 2.266033521837529e-08, "epoch": 0.9389850644942295, "percentage": 93.9, "elapsed_time": "0:26:57", "remaining_time": "0:01:45", "throughput": 6568.39, "total_tokens": 10622144}
{"current_steps": 11070, "total_steps": 11784, "loss": 0.0026, "lr": 2.2347874609650596e-08, "epoch": 0.9394093686354379, "percentage": 93.94, "elapsed_time": "0:26:57", "remaining_time": "0:01:44", "throughput": 6569.95, "total_tokens": 10626880}
{"current_steps": 11075, "total_steps": 11784, "loss": 0.0656, "lr": 2.2037558879336004e-08, "epoch": 0.9398336727766463, "percentage": 93.98, "elapsed_time": "0:26:57", "remaining_time": "0:01:43", "throughput": 6571.8, "total_tokens": 10632128}
{"current_steps": 11080, "total_steps": 11784, "loss": 0.0192, "lr": 2.1729388708235485e-08, "epoch": 0.9402579769178547, "percentage": 94.03, "elapsed_time": "0:26:58", "remaining_time": "0:01:42", "throughput": 6573.36, "total_tokens": 10636800}
{"current_steps": 11085, "total_steps": 11784, "loss": 0.0352, "lr": 2.1423364772445886e-08, "epoch": 0.9406822810590632, "percentage": 94.07, "elapsed_time": "0:26:58", "remaining_time": "0:01:42", "throughput": 6574.85, "total_tokens": 10641408}
{"current_steps": 11090, "total_steps": 11784, "loss": 0.0058, "lr": 2.111948774335548e-08, "epoch": 0.9411065852002716, "percentage": 94.11, "elapsed_time": "0:26:58", "remaining_time": "0:01:41", "throughput": 6576.55, "total_tokens": 10646400}
{"current_steps": 11095, "total_steps": 11784, "loss": 0.1124, "lr": 2.081775828764254e-08, "epoch": 0.94153088934148, "percentage": 94.15, "elapsed_time": "0:26:59", "remaining_time": "0:01:40", "throughput": 6577.94, "total_tokens": 10650816}
{"current_steps": 11100, "total_steps": 11784, "loss": 0.0133, "lr": 2.0518177067273103e-08, "epoch": 0.9419551934826884, "percentage": 94.2, "elapsed_time": "0:26:59", "remaining_time": "0:01:39", "throughput": 6579.43, "total_tokens": 10655424}
{"current_steps": 11105, "total_steps": 11784, "loss": 0.0908, "lr": 2.0220744739501305e-08, "epoch": 0.9423794976238968, "percentage": 94.24, "elapsed_time": "0:26:59", "remaining_time": "0:01:39", "throughput": 6581.14, "total_tokens": 10660416}
{"current_steps": 11110, "total_steps": 11784, "loss": 0.0695, "lr": 1.992546195686573e-08, "epoch": 0.9428038017651053, "percentage": 94.28, "elapsed_time": "0:27:00", "remaining_time": "0:01:38", "throughput": 6582.68, "total_tokens": 10665088}
{"current_steps": 11115, "total_steps": 11784, "loss": 0.0392, "lr": 1.9632329367189725e-08, "epoch": 0.9432281059063137, "percentage": 94.32, "elapsed_time": "0:27:00", "remaining_time": "0:01:37", "throughput": 6584.12, "total_tokens": 10669632}
{"current_steps": 11120, "total_steps": 11784, "loss": 0.0275, "lr": 1.9341347613579086e-08, "epoch": 0.9436524100475221, "percentage": 94.37, "elapsed_time": "0:27:00", "remaining_time": "0:01:36", "throughput": 6585.89, "total_tokens": 10674752}
{"current_steps": 11125, "total_steps": 11784, "loss": 0.0512, "lr": 1.9052517334420704e-08, "epoch": 0.9440767141887305, "percentage": 94.41, "elapsed_time": "0:27:01", "remaining_time": "0:01:36", "throughput": 6587.34, "total_tokens": 10679296}
{"current_steps": 11130, "total_steps": 11784, "loss": 0.0959, "lr": 1.8765839163381815e-08, "epoch": 0.9445010183299389, "percentage": 94.45, "elapsed_time": "0:27:01", "remaining_time": "0:01:35", "throughput": 6588.87, "total_tokens": 10683968}
{"current_steps": 11135, "total_steps": 11784, "loss": 0.0589, "lr": 1.8481313729407645e-08, "epoch": 0.9449253224711474, "percentage": 94.49, "elapsed_time": "0:27:01", "remaining_time": "0:01:34", "throughput": 6590.32, "total_tokens": 10688512}
{"current_steps": 11140, "total_steps": 11784, "loss": 0.1141, "lr": 1.8198941656720646e-08, "epoch": 0.9453496266123558, "percentage": 94.53, "elapsed_time": "0:27:02", "remaining_time": "0:01:33", "throughput": 6591.91, "total_tokens": 10693312}
{"current_steps": 11145, "total_steps": 11784, "loss": 0.105, "lr": 1.7918723564819272e-08, "epoch": 0.9457739307535642, "percentage": 94.58, "elapsed_time": "0:27:02", "remaining_time": "0:01:33", "throughput": 6593.81, "total_tokens": 10698688}
{"current_steps": 11150, "total_steps": 11784, "loss": 0.1199, "lr": 1.7640660068475976e-08, "epoch": 0.9461982348947726, "percentage": 94.62, "elapsed_time": "0:27:02", "remaining_time": "0:01:32", "throughput": 6595.91, "total_tokens": 10704448}
{"current_steps": 11155, "total_steps": 11784, "loss": 0.0696, "lr": 1.7364751777736332e-08, "epoch": 0.946622539035981, "percentage": 94.66, "elapsed_time": "0:27:03", "remaining_time": "0:01:31", "throughput": 6597.54, "total_tokens": 10709312}
{"current_steps": 11160, "total_steps": 11784, "loss": 0.0331, "lr": 1.7090999297917684e-08, "epoch": 0.9470468431771895, "percentage": 94.7, "elapsed_time": "0:27:03", "remaining_time": "0:01:30", "throughput": 6599.28, "total_tokens": 10714368}
{"current_steps": 11165, "total_steps": 11784, "loss": 0.0659, "lr": 1.6819403229607732e-08, "epoch": 0.9474711473183979, "percentage": 94.75, "elapsed_time": "0:27:03", "remaining_time": "0:01:30", "throughput": 6600.7, "total_tokens": 10718848}
{"current_steps": 11170, "total_steps": 11784, "loss": 0.0355, "lr": 1.6549964168663054e-08, "epoch": 0.9478954514596063, "percentage": 94.79, "elapsed_time": "0:27:04", "remaining_time": "0:01:29", "throughput": 6602.32, "total_tokens": 10723712}
{"current_steps": 11175, "total_steps": 11784, "loss": 0.0551, "lr": 1.6282682706208028e-08, "epoch": 0.9483197556008147, "percentage": 94.83, "elapsed_time": "0:27:04", "remaining_time": "0:01:28", "throughput": 6603.83, "total_tokens": 10728384}
{"current_steps": 11180, "total_steps": 11784, "loss": 0.0233, "lr": 1.6017559428633588e-08, "epoch": 0.948744059742023, "percentage": 94.87, "elapsed_time": "0:27:04", "remaining_time": "0:01:27", "throughput": 6605.64, "total_tokens": 10733632}
{"current_steps": 11185, "total_steps": 11784, "loss": 0.0556, "lr": 1.5754594917595564e-08, "epoch": 0.9491683638832314, "percentage": 94.92, "elapsed_time": "0:27:05", "remaining_time": "0:01:27", "throughput": 6607.47, "total_tokens": 10738880}
{"current_steps": 11190, "total_steps": 11784, "loss": 0.0574, "lr": 1.549378975001403e-08, "epoch": 0.9495926680244399, "percentage": 94.96, "elapsed_time": "0:27:05", "remaining_time": "0:01:26", "throughput": 6609.43, "total_tokens": 10744384}
{"current_steps": 11195, "total_steps": 11784, "loss": 0.0319, "lr": 1.5235144498071172e-08, "epoch": 0.9500169721656483, "percentage": 95.0, "elapsed_time": "0:27:05", "remaining_time": "0:01:25", "throughput": 6611.29, "total_tokens": 10749632}
{"current_steps": 11200, "total_steps": 11784, "loss": 0.0301, "lr": 1.4978659729210974e-08, "epoch": 0.9504412763068567, "percentage": 95.04, "elapsed_time": "0:27:06", "remaining_time": "0:01:24", "throughput": 6613.0, "total_tokens": 10754624}
{"current_steps": 11205, "total_steps": 11784, "loss": 0.0761, "lr": 1.4724336006137094e-08, "epoch": 0.9508655804480651, "percentage": 95.09, "elapsed_time": "0:27:06", "remaining_time": "0:01:24", "throughput": 6614.64, "total_tokens": 10759488}
{"current_steps": 11210, "total_steps": 11784, "loss": 0.004, "lr": 1.4472173886812433e-08, "epoch": 0.9512898845892735, "percentage": 95.13, "elapsed_time": "0:27:06", "remaining_time": "0:01:23", "throughput": 6616.13, "total_tokens": 10764096}
{"current_steps": 11210, "total_steps": 11784, "eval_loss": 0.05228454992175102, "epoch": 0.9512898845892735, "percentage": 95.13, "elapsed_time": "0:27:22", "remaining_time": "0:01:24", "throughput": 6552.32, "total_tokens": 10764096}
{"current_steps": 11215, "total_steps": 11784, "loss": 0.0577, "lr": 1.4222173924457348e-08, "epoch": 0.951714188730482, "percentage": 95.17, "elapsed_time": "0:28:08", "remaining_time": "0:01:25", "throughput": 6378.93, "total_tokens": 10768640}
{"current_steps": 11220, "total_steps": 11784, "loss": 0.0544, "lr": 1.3974336667548659e-08, "epoch": 0.9521384928716904, "percentage": 95.21, "elapsed_time": "0:28:08", "remaining_time": "0:01:24", "throughput": 6380.81, "total_tokens": 10774016}
{"current_steps": 11225, "total_steps": 11784, "loss": 0.0036, "lr": 1.3728662659818201e-08, "epoch": 0.9525627970128988, "percentage": 95.26, "elapsed_time": "0:28:08", "remaining_time": "0:01:24", "throughput": 6382.52, "total_tokens": 10779072}
{"current_steps": 11230, "total_steps": 11784, "loss": 0.0487, "lr": 1.3485152440252389e-08, "epoch": 0.9529871011541072, "percentage": 95.3, "elapsed_time": "0:28:09", "remaining_time": "0:01:23", "throughput": 6384.18, "total_tokens": 10784000}
{"current_steps": 11235, "total_steps": 11784, "loss": 0.0644, "lr": 1.3243806543089875e-08, "epoch": 0.9534114052953157, "percentage": 95.34, "elapsed_time": "0:28:09", "remaining_time": "0:01:22", "throughput": 6385.82, "total_tokens": 10788928}
{"current_steps": 11240, "total_steps": 11784, "loss": 0.0275, "lr": 1.3004625497821553e-08, "epoch": 0.9538357094365241, "percentage": 95.38, "elapsed_time": "0:28:09", "remaining_time": "0:01:21", "throughput": 6387.7, "total_tokens": 10794304}
{"current_steps": 11245, "total_steps": 11784, "loss": 0.0298, "lr": 1.276760982918812e-08, "epoch": 0.9542600135777325, "percentage": 95.43, "elapsed_time": "0:28:10", "remaining_time": "0:01:21", "throughput": 6388.98, "total_tokens": 10798528}
{"current_steps": 11250, "total_steps": 11784, "loss": 0.0547, "lr": 1.2532760057180291e-08, "epoch": 0.9546843177189409, "percentage": 95.47, "elapsed_time": "0:28:10", "remaining_time": "0:01:20", "throughput": 6390.51, "total_tokens": 10803200}
{"current_steps": 11255, "total_steps": 11784, "loss": 0.0283, "lr": 1.230007669703681e-08, "epoch": 0.9551086218601493, "percentage": 95.51, "elapsed_time": "0:28:10", "remaining_time": "0:01:19", "throughput": 6391.93, "total_tokens": 10807680}
{"current_steps": 11260, "total_steps": 11784, "loss": 0.0351, "lr": 1.2069560259243328e-08, "epoch": 0.9555329260013578, "percentage": 95.55, "elapsed_time": "0:28:11", "remaining_time": "0:01:18", "throughput": 6393.39, "total_tokens": 10812224}
{"current_steps": 11265, "total_steps": 11784, "loss": 0.045, "lr": 1.1841211249531636e-08, "epoch": 0.9559572301425662, "percentage": 95.6, "elapsed_time": "0:28:11", "remaining_time": "0:01:17", "throughput": 6394.78, "total_tokens": 10816640}
{"current_steps": 11270, "total_steps": 11784, "loss": 0.0182, "lr": 1.1615030168878438e-08, "epoch": 0.9563815342837746, "percentage": 95.64, "elapsed_time": "0:28:11", "remaining_time": "0:01:17", "throughput": 6396.37, "total_tokens": 10821440}
{"current_steps": 11275, "total_steps": 11784, "loss": 0.0752, "lr": 1.139101751350402e-08, "epoch": 0.956805838424983, "percentage": 95.68, "elapsed_time": "0:28:12", "remaining_time": "0:01:16", "throughput": 6398.12, "total_tokens": 10826560}
{"current_steps": 11280, "total_steps": 11784, "loss": 0.0729, "lr": 1.1169173774871477e-08, "epoch": 0.9572301425661914, "percentage": 95.72, "elapsed_time": "0:28:12", "remaining_time": "0:01:15", "throughput": 6399.8, "total_tokens": 10831552}
{"current_steps": 11285, "total_steps": 11784, "loss": 0.027, "lr": 1.0949499439685483e-08, "epoch": 0.9576544467073999, "percentage": 95.77, "elapsed_time": "0:28:12", "remaining_time": "0:01:14", "throughput": 6401.19, "total_tokens": 10835968}
{"current_steps": 11290, "total_steps": 11784, "loss": 0.0548, "lr": 1.0731994989891302e-08, "epoch": 0.9580787508486083, "percentage": 95.81, "elapsed_time": "0:28:13", "remaining_time": "0:01:14", "throughput": 6402.39, "total_tokens": 10840064}
{"current_steps": 11295, "total_steps": 11784, "loss": 0.0353, "lr": 1.0516660902673446e-08, "epoch": 0.9585030549898167, "percentage": 95.85, "elapsed_time": "0:28:13", "remaining_time": "0:01:13", "throughput": 6403.86, "total_tokens": 10844672}
{"current_steps": 11300, "total_steps": 11784, "loss": 0.0655, "lr": 1.0303497650455128e-08, "epoch": 0.9589273591310251, "percentage": 95.89, "elapsed_time": "0:28:13", "remaining_time": "0:01:12", "throughput": 6405.87, "total_tokens": 10850304}
{"current_steps": 11305, "total_steps": 11784, "loss": 0.0381, "lr": 1.0092505700896703e-08, "epoch": 0.9593516632722335, "percentage": 95.94, "elapsed_time": "0:28:14", "remaining_time": "0:01:11", "throughput": 6407.35, "total_tokens": 10854912}
{"current_steps": 11310, "total_steps": 11784, "loss": 0.0385, "lr": 9.883685516895113e-09, "epoch": 0.959775967413442, "percentage": 95.98, "elapsed_time": "0:28:14", "remaining_time": "0:01:11", "throughput": 6409.01, "total_tokens": 10859904}
{"current_steps": 11315, "total_steps": 11784, "loss": 0.0542, "lr": 9.677037556582557e-09, "epoch": 0.9602002715546504, "percentage": 96.02, "elapsed_time": "0:28:14", "remaining_time": "0:01:10", "throughput": 6410.58, "total_tokens": 10864704}
{"current_steps": 11320, "total_steps": 11784, "loss": 0.0082, "lr": 9.47256227332538e-09, "epoch": 0.9606245756958588, "percentage": 96.06, "elapsed_time": "0:28:15", "remaining_time": "0:01:09", "throughput": 6412.03, "total_tokens": 10869248}
{"current_steps": 11325, "total_steps": 11784, "loss": 0.0511, "lr": 9.270260115723739e-09, "epoch": 0.9610488798370672, "percentage": 96.1, "elapsed_time": "0:28:15", "remaining_time": "0:01:08", "throughput": 6413.56, "total_tokens": 10873984}
{"current_steps": 11330, "total_steps": 11784, "loss": 0.0736, "lr": 9.070131527609603e-09, "epoch": 0.9614731839782756, "percentage": 96.15, "elapsed_time": "0:28:15", "remaining_time": "0:01:07", "throughput": 6415.04, "total_tokens": 10878592}
{"current_steps": 11335, "total_steps": 11784, "loss": 0.0627, "lr": 8.872176948046761e-09, "epoch": 0.9618974881194841, "percentage": 96.19, "elapsed_time": "0:28:16", "remaining_time": "0:01:07", "throughput": 6416.54, "total_tokens": 10883264}
{"current_steps": 11340, "total_steps": 11784, "loss": 0.0327, "lr": 8.676396811329145e-09, "epoch": 0.9623217922606925, "percentage": 96.23, "elapsed_time": "0:28:16", "remaining_time": "0:01:06", "throughput": 6417.84, "total_tokens": 10887552}
{"current_steps": 11345, "total_steps": 11784, "loss": 0.0727, "lr": 8.482791546980506e-09, "epoch": 0.9627460964019009, "percentage": 96.27, "elapsed_time": "0:28:16", "remaining_time": "0:01:05", "throughput": 6419.64, "total_tokens": 10892800}
{"current_steps": 11350, "total_steps": 11784, "loss": 0.0624, "lr": 8.291361579752631e-09, "epoch": 0.9631704005431093, "percentage": 96.32, "elapsed_time": "0:28:17", "remaining_time": "0:01:04", "throughput": 6421.05, "total_tokens": 10897280}
{"current_steps": 11355, "total_steps": 11784, "loss": 0.0544, "lr": 8.102107329625351e-09, "epoch": 0.9635947046843177, "percentage": 96.36, "elapsed_time": "0:28:17", "remaining_time": "0:01:04", "throughput": 6422.65, "total_tokens": 10902144}
{"current_steps": 11360, "total_steps": 11784, "loss": 0.0805, "lr": 7.91502921180487e-09, "epoch": 0.9640190088255262, "percentage": 96.4, "elapsed_time": "0:28:17", "remaining_time": "0:01:03", "throughput": 6424.37, "total_tokens": 10907264}
{"current_steps": 11365, "total_steps": 11784, "loss": 0.0146, "lr": 7.730127636723538e-09, "epoch": 0.9644433129667346, "percentage": 96.44, "elapsed_time": "0:28:18", "remaining_time": "0:01:02", "throughput": 6425.81, "total_tokens": 10911808}
{"current_steps": 11370, "total_steps": 11784, "loss": 0.0853, "lr": 7.547403010037978e-09, "epoch": 0.964867617107943, "percentage": 96.49, "elapsed_time": "0:28:18", "remaining_time": "0:01:01", "throughput": 6427.35, "total_tokens": 10916544}
{"current_steps": 11375, "total_steps": 11784, "loss": 0.0814, "lr": 7.366855732629407e-09, "epoch": 0.9652919212491514, "percentage": 96.53, "elapsed_time": "0:28:18", "remaining_time": "0:01:01", "throughput": 6428.75, "total_tokens": 10921024}
{"current_steps": 11380, "total_steps": 11784, "loss": 0.0551, "lr": 7.1884862006017514e-09, "epoch": 0.9657162253903598, "percentage": 96.57, "elapsed_time": "0:28:19", "remaining_time": "0:01:00", "throughput": 6430.39, "total_tokens": 10926016}
{"current_steps": 11385, "total_steps": 11784, "loss": 0.0426, "lr": 7.012294805281205e-09, "epoch": 0.9661405295315683, "percentage": 96.61, "elapsed_time": "0:28:19", "remaining_time": "0:00:59", "throughput": 6432.15, "total_tokens": 10931200}
{"current_steps": 11390, "total_steps": 11784, "loss": 0.0681, "lr": 6.838281933215562e-09, "epoch": 0.9665648336727767, "percentage": 96.66, "elapsed_time": "0:28:19", "remaining_time": "0:00:58", "throughput": 6433.9, "total_tokens": 10936384}
{"current_steps": 11395, "total_steps": 11784, "loss": 0.0278, "lr": 6.6664479661729944e-09, "epoch": 0.9669891378139851, "percentage": 96.7, "elapsed_time": "0:28:20", "remaining_time": "0:00:58", "throughput": 6435.46, "total_tokens": 10941184}
{"current_steps": 11400, "total_steps": 11784, "loss": 0.0654, "lr": 6.496793281141055e-09, "epoch": 0.9674134419551935, "percentage": 96.74, "elapsed_time": "0:28:20", "remaining_time": "0:00:57", "throughput": 6436.72, "total_tokens": 10945408}
{"current_steps": 11405, "total_steps": 11784, "loss": 0.0877, "lr": 6.329318250326898e-09, "epoch": 0.9678377460964019, "percentage": 96.78, "elapsed_time": "0:28:20", "remaining_time": "0:00:56", "throughput": 6438.25, "total_tokens": 10950144}
{"current_steps": 11410, "total_steps": 11784, "loss": 0.1094, "lr": 6.164023241154837e-09, "epoch": 0.9682620502376104, "percentage": 96.83, "elapsed_time": "0:28:21", "remaining_time": "0:00:55", "throughput": 6439.97, "total_tokens": 10955264}
{"current_steps": 11415, "total_steps": 11784, "loss": 0.0078, "lr": 6.000908616267009e-09, "epoch": 0.9686863543788188, "percentage": 96.87, "elapsed_time": "0:28:21", "remaining_time": "0:00:55", "throughput": 6441.62, "total_tokens": 10960256}
{"current_steps": 11420, "total_steps": 11784, "loss": 0.0628, "lr": 5.839974733522046e-09, "epoch": 0.9691106585200272, "percentage": 96.91, "elapsed_time": "0:28:21", "remaining_time": "0:00:54", "throughput": 6442.99, "total_tokens": 10964672}
{"current_steps": 11425, "total_steps": 11784, "loss": 0.0369, "lr": 5.68122194599363e-09, "epoch": 0.9695349626612356, "percentage": 96.95, "elapsed_time": "0:28:22", "remaining_time": "0:00:53", "throughput": 6444.68, "total_tokens": 10969728}
{"current_steps": 11430, "total_steps": 11784, "loss": 0.0914, "lr": 5.5246506019709374e-09, "epoch": 0.969959266802444, "percentage": 97.0, "elapsed_time": "0:28:22", "remaining_time": "0:00:52", "throughput": 6446.34, "total_tokens": 10974720}
{"current_steps": 11435, "total_steps": 11784, "loss": 0.0407, "lr": 5.370261044956969e-09, "epoch": 0.9703835709436525, "percentage": 97.04, "elapsed_time": "0:28:22", "remaining_time": "0:00:51", "throughput": 6447.63, "total_tokens": 10979008}
{"current_steps": 11440, "total_steps": 11784, "loss": 0.0368, "lr": 5.218053613668116e-09, "epoch": 0.9708078750848609, "percentage": 97.08, "elapsed_time": "0:28:23", "remaining_time": "0:00:51", "throughput": 6449.34, "total_tokens": 10984128}
{"current_steps": 11445, "total_steps": 11784, "loss": 0.0629, "lr": 5.068028642033595e-09, "epoch": 0.9712321792260692, "percentage": 97.12, "elapsed_time": "0:28:23", "remaining_time": "0:00:50", "throughput": 6450.66, "total_tokens": 10988480}
{"current_steps": 11450, "total_steps": 11784, "loss": 0.0341, "lr": 4.92018645919412e-09, "epoch": 0.9716564833672776, "percentage": 97.17, "elapsed_time": "0:28:23", "remaining_time": "0:00:49", "throughput": 6452.0, "total_tokens": 10992896}
{"current_steps": 11455, "total_steps": 11784, "loss": 0.078, "lr": 4.774527389501681e-09, "epoch": 0.972080787508486, "percentage": 97.21, "elapsed_time": "0:28:24", "remaining_time": "0:00:48", "throughput": 6453.57, "total_tokens": 10997696}
{"current_steps": 11460, "total_steps": 11784, "loss": 0.0699, "lr": 4.63105175251921e-09, "epoch": 0.9725050916496945, "percentage": 97.25, "elapsed_time": "0:28:24", "remaining_time": "0:00:48", "throughput": 6455.35, "total_tokens": 11002944}
{"current_steps": 11465, "total_steps": 11784, "loss": 0.085, "lr": 4.489759863018583e-09, "epoch": 0.9729293957909029, "percentage": 97.29, "elapsed_time": "0:28:24", "remaining_time": "0:00:47", "throughput": 6457.22, "total_tokens": 11008384}
{"current_steps": 11470, "total_steps": 11784, "loss": 0.0997, "lr": 4.350652030981394e-09, "epoch": 0.9733536999321113, "percentage": 97.34, "elapsed_time": "0:28:25", "remaining_time": "0:00:46", "throughput": 6458.59, "total_tokens": 11012800}
{"current_steps": 11475, "total_steps": 11784, "loss": 0.1097, "lr": 4.213728561597296e-09, "epoch": 0.9737780040733197, "percentage": 97.38, "elapsed_time": "0:28:25", "remaining_time": "0:00:45", "throughput": 6459.96, "total_tokens": 11017216}
{"current_steps": 11480, "total_steps": 11784, "loss": 0.0678, "lr": 4.0789897552637735e-09, "epoch": 0.9742023082145281, "percentage": 97.42, "elapsed_time": "0:28:25", "remaining_time": "0:00:45", "throughput": 6461.25, "total_tokens": 11021504}
{"current_steps": 11485, "total_steps": 11784, "loss": 0.0978, "lr": 3.946435907585255e-09, "epoch": 0.9746266123557366, "percentage": 97.46, "elapsed_time": "0:28:26", "remaining_time": "0:00:44", "throughput": 6463.06, "total_tokens": 11026816}
{"current_steps": 11490, "total_steps": 11784, "loss": 0.0679, "lr": 3.816067309372673e-09, "epoch": 0.975050916496945, "percentage": 97.51, "elapsed_time": "0:28:26", "remaining_time": "0:00:43", "throughput": 6465.03, "total_tokens": 11032448}
{"current_steps": 11495, "total_steps": 11784, "loss": 0.1102, "lr": 3.68788424664257e-09, "epoch": 0.9754752206381534, "percentage": 97.55, "elapsed_time": "0:28:26", "remaining_time": "0:00:42", "throughput": 6466.47, "total_tokens": 11037056}
{"current_steps": 11500, "total_steps": 11784, "loss": 0.0901, "lr": 3.561887000616881e-09, "epoch": 0.9758995247793618, "percentage": 97.59, "elapsed_time": "0:28:27", "remaining_time": "0:00:42", "throughput": 6467.66, "total_tokens": 11041152}
{"current_steps": 11505, "total_steps": 11784, "loss": 0.0358, "lr": 3.438075847721933e-09, "epoch": 0.9763238289205702, "percentage": 97.63, "elapsed_time": "0:28:27", "remaining_time": "0:00:41", "throughput": 6468.98, "total_tokens": 11045504}
{"current_steps": 11510, "total_steps": 11784, "loss": 0.0784, "lr": 3.316451059587777e-09, "epoch": 0.9767481330617787, "percentage": 97.67, "elapsed_time": "0:28:27", "remaining_time": "0:00:40", "throughput": 6470.28, "total_tokens": 11049792}
{"current_steps": 11515, "total_steps": 11784, "loss": 0.0353, "lr": 3.1970129030481907e-09, "epoch": 0.9771724372029871, "percentage": 97.72, "elapsed_time": "0:28:28", "remaining_time": "0:00:39", "throughput": 6471.51, "total_tokens": 11053952}
{"current_steps": 11520, "total_steps": 11784, "loss": 0.0642, "lr": 3.0797616401392335e-09, "epoch": 0.9775967413441955, "percentage": 97.76, "elapsed_time": "0:28:28", "remaining_time": "0:00:39", "throughput": 6472.79, "total_tokens": 11058240}
{"current_steps": 11525, "total_steps": 11784, "loss": 0.0538, "lr": 2.964697528099469e-09, "epoch": 0.9780210454854039, "percentage": 97.8, "elapsed_time": "0:28:28", "remaining_time": "0:00:38", "throughput": 6474.56, "total_tokens": 11063488}
{"current_steps": 11530, "total_steps": 11784, "loss": 0.0462, "lr": 2.8518208193689664e-09, "epoch": 0.9784453496266123, "percentage": 97.84, "elapsed_time": "0:28:29", "remaining_time": "0:00:37", "throughput": 6476.01, "total_tokens": 11068096}
{"current_steps": 11535, "total_steps": 11784, "loss": 0.1083, "lr": 2.741131761588522e-09, "epoch": 0.9788696537678208, "percentage": 97.89, "elapsed_time": "0:28:29", "remaining_time": "0:00:36", "throughput": 6477.98, "total_tokens": 11073728}
{"current_steps": 11540, "total_steps": 11784, "loss": 0.0648, "lr": 2.632630597600105e-09, "epoch": 0.9792939579090292, "percentage": 97.93, "elapsed_time": "0:28:29", "remaining_time": "0:00:36", "throughput": 6479.3, "total_tokens": 11078144}
{"current_steps": 11545, "total_steps": 11784, "loss": 0.0129, "lr": 2.526317565444969e-09, "epoch": 0.9797182620502376, "percentage": 97.97, "elapsed_time": "0:28:30", "remaining_time": "0:00:35", "throughput": 6481.05, "total_tokens": 11083328}
{"current_steps": 11550, "total_steps": 11784, "loss": 0.089, "lr": 2.422192898364095e-09, "epoch": 0.980142566191446, "percentage": 98.01, "elapsed_time": "0:28:30", "remaining_time": "0:00:34", "throughput": 6482.57, "total_tokens": 11088064}
{"current_steps": 11555, "total_steps": 11784, "loss": 0.0186, "lr": 2.3202568247974175e-09, "epoch": 0.9805668703326544, "percentage": 98.06, "elapsed_time": "0:28:30", "remaining_time": "0:00:33", "throughput": 6484.05, "total_tokens": 11092736}
{"current_steps": 11560, "total_steps": 11784, "loss": 0.0534, "lr": 2.2205095683833774e-09, "epoch": 0.9809911744738629, "percentage": 98.1, "elapsed_time": "0:28:31", "remaining_time": "0:00:33", "throughput": 6485.91, "total_tokens": 11098176}
{"current_steps": 11565, "total_steps": 11784, "loss": 0.0566, "lr": 2.122951347958035e-09, "epoch": 0.9814154786150713, "percentage": 98.14, "elapsed_time": "0:28:31", "remaining_time": "0:00:32", "throughput": 6487.41, "total_tokens": 11102912}
{"current_steps": 11570, "total_steps": 11784, "loss": 0.0898, "lr": 2.0275823775551817e-09, "epoch": 0.9818397827562797, "percentage": 98.18, "elapsed_time": "0:28:31", "remaining_time": "0:00:31", "throughput": 6488.8, "total_tokens": 11107392}
{"current_steps": 11575, "total_steps": 11784, "loss": 0.0508, "lr": 1.934402866405671e-09, "epoch": 0.9822640868974881, "percentage": 98.23, "elapsed_time": "0:28:32", "remaining_time": "0:00:30", "throughput": 6490.39, "total_tokens": 11112256}
{"current_steps": 11580, "total_steps": 11784, "loss": 0.0302, "lr": 1.843413018936535e-09, "epoch": 0.9826883910386965, "percentage": 98.27, "elapsed_time": "0:28:32", "remaining_time": "0:00:30", "throughput": 6492.08, "total_tokens": 11117376}
{"current_steps": 11585, "total_steps": 11784, "loss": 0.105, "lr": 1.7546130347712018e-09, "epoch": 0.983112695179905, "percentage": 98.31, "elapsed_time": "0:28:32", "remaining_time": "0:00:29", "throughput": 6493.84, "total_tokens": 11122624}
{"current_steps": 11590, "total_steps": 11784, "loss": 0.0155, "lr": 1.6680031087286106e-09, "epoch": 0.9835369993211134, "percentage": 98.35, "elapsed_time": "0:28:33", "remaining_time": "0:00:28", "throughput": 6495.51, "total_tokens": 11127680}
{"current_steps": 11595, "total_steps": 11784, "loss": 0.0984, "lr": 1.5835834308228768e-09, "epoch": 0.9839613034623218, "percentage": 98.4, "elapsed_time": "0:28:33", "remaining_time": "0:00:27", "throughput": 6497.13, "total_tokens": 11132672}
{"current_steps": 11600, "total_steps": 11784, "loss": 0.091, "lr": 1.5013541862630708e-09, "epoch": 0.9843856076035302, "percentage": 98.44, "elapsed_time": "0:28:33", "remaining_time": "0:00:27", "throughput": 6498.64, "total_tokens": 11137408}
{"current_steps": 11605, "total_steps": 11784, "loss": 0.0188, "lr": 1.4213155554525513e-09, "epoch": 0.9848099117447386, "percentage": 98.48, "elapsed_time": "0:28:34", "remaining_time": "0:00:26", "throughput": 6500.08, "total_tokens": 11142016}
{"current_steps": 11610, "total_steps": 11784, "loss": 0.0406, "lr": 1.343467713988522e-09, "epoch": 0.9852342158859471, "percentage": 98.52, "elapsed_time": "0:28:34", "remaining_time": "0:00:25", "throughput": 6501.52, "total_tokens": 11146624}
{"current_steps": 11615, "total_steps": 11784, "loss": 0.135, "lr": 1.2678108326621418e-09, "epoch": 0.9856585200271555, "percentage": 98.57, "elapsed_time": "0:28:34", "remaining_time": "0:00:24", "throughput": 6503.18, "total_tokens": 11151680}
{"current_steps": 11620, "total_steps": 11784, "loss": 0.0567, "lr": 1.1943450774574148e-09, "epoch": 0.9860828241683639, "percentage": 98.61, "elapsed_time": "0:28:35", "remaining_time": "0:00:24", "throughput": 6504.51, "total_tokens": 11156096}
{"current_steps": 11625, "total_steps": 11784, "loss": 0.0577, "lr": 1.1230706095516352e-09, "epoch": 0.9865071283095723, "percentage": 98.65, "elapsed_time": "0:28:35", "remaining_time": "0:00:23", "throughput": 6505.72, "total_tokens": 11160256}
{"current_steps": 11630, "total_steps": 11784, "loss": 0.0315, "lr": 1.0539875853142754e-09, "epoch": 0.9869314324507807, "percentage": 98.69, "elapsed_time": "0:28:35", "remaining_time": "0:00:22", "throughput": 6507.51, "total_tokens": 11165568}
{"current_steps": 11635, "total_steps": 11784, "loss": 0.071, "lr": 9.8709615630721e-10, "epoch": 0.9873557365919892, "percentage": 98.74, "elapsed_time": "0:28:36", "remaining_time": "0:00:21", "throughput": 6509.08, "total_tokens": 11170432}
{"current_steps": 11640, "total_steps": 11784, "loss": 0.0726, "lr": 9.22396469283937e-10, "epoch": 0.9877800407331976, "percentage": 98.78, "elapsed_time": "0:28:36", "remaining_time": "0:00:21", "throughput": 6510.53, "total_tokens": 11175104}
{"current_steps": 11645, "total_steps": 11784, "loss": 0.0355, "lr": 8.598886661895787e-10, "epoch": 0.988204344874406, "percentage": 98.82, "elapsed_time": "0:28:36", "remaining_time": "0:00:20", "throughput": 6511.91, "total_tokens": 11179584}
{"current_steps": 11650, "total_steps": 11784, "loss": 0.0425, "lr": 7.995728841605487e-10, "epoch": 0.9886286490156144, "percentage": 98.86, "elapsed_time": "0:28:37", "remaining_time": "0:00:19", "throughput": 6513.72, "total_tokens": 11184960}
{"current_steps": 11655, "total_steps": 11784, "loss": 0.0954, "lr": 7.41449255524107e-10, "epoch": 0.9890529531568228, "percentage": 98.91, "elapsed_time": "0:28:37", "remaining_time": "0:00:19", "throughput": 6515.59, "total_tokens": 11190464}
{"current_steps": 11660, "total_steps": 11784, "loss": 0.0764, "lr": 6.855179077981388e-10, "epoch": 0.9894772572980313, "percentage": 98.95, "elapsed_time": "0:28:37", "remaining_time": "0:00:18", "throughput": 6517.14, "total_tokens": 11195392}
{"current_steps": 11665, "total_steps": 11784, "loss": 0.0392, "lr": 6.3177896369071e-10, "epoch": 0.9899015614392397, "percentage": 98.99, "elapsed_time": "0:28:38", "remaining_time": "0:00:17", "throughput": 6518.6, "total_tokens": 11200128}
{"current_steps": 11670, "total_steps": 11784, "loss": 0.0484, "lr": 5.802325411001785e-10, "epoch": 0.9903258655804481, "percentage": 99.03, "elapsed_time": "0:28:38", "remaining_time": "0:00:16", "throughput": 6520.05, "total_tokens": 11204800}
{"current_steps": 11675, "total_steps": 11784, "loss": 0.0924, "lr": 5.308787531147496e-10, "epoch": 0.9907501697216565, "percentage": 99.08, "elapsed_time": "0:28:38", "remaining_time": "0:00:16", "throughput": 6521.5, "total_tokens": 11209472}
{"current_steps": 11680, "total_steps": 11784, "loss": 0.0679, "lr": 4.837177080119214e-10, "epoch": 0.991174473862865, "percentage": 99.12, "elapsed_time": "0:28:39", "remaining_time": "0:00:15", "throughput": 6522.89, "total_tokens": 11214016}
{"current_steps": 11685, "total_steps": 11784, "loss": 0.072, "lr": 4.387495092587068e-10, "epoch": 0.9915987780040734, "percentage": 99.16, "elapsed_time": "0:28:39", "remaining_time": "0:00:14", "throughput": 6524.37, "total_tokens": 11218752}
{"current_steps": 11690, "total_steps": 11784, "loss": 0.1148, "lr": 3.959742555111889e-10, "epoch": 0.9920230821452818, "percentage": 99.2, "elapsed_time": "0:28:39", "remaining_time": "0:00:13", "throughput": 6525.88, "total_tokens": 11223552}
{"current_steps": 11695, "total_steps": 11784, "loss": 0.0671, "lr": 3.553920406144106e-10, "epoch": 0.9924473862864902, "percentage": 99.24, "elapsed_time": "0:28:40", "remaining_time": "0:00:13", "throughput": 6527.24, "total_tokens": 11228032}
{"current_steps": 11700, "total_steps": 11784, "loss": 0.0562, "lr": 3.1700295360181927e-10, "epoch": 0.9928716904276986, "percentage": 99.29, "elapsed_time": "0:28:40", "remaining_time": "0:00:12", "throughput": 6528.52, "total_tokens": 11232448}
{"current_steps": 11705, "total_steps": 11784, "loss": 0.0858, "lr": 2.808070786955996e-10, "epoch": 0.993295994568907, "percentage": 99.33, "elapsed_time": "0:28:40", "remaining_time": "0:00:11", "throughput": 6530.13, "total_tokens": 11237440}
{"current_steps": 11710, "total_steps": 11784, "loss": 0.0601, "lr": 2.4680449530622984e-10, "epoch": 0.9937202987101154, "percentage": 99.37, "elapsed_time": "0:28:41", "remaining_time": "0:00:10", "throughput": 6531.54, "total_tokens": 11242048}
{"current_steps": 11715, "total_steps": 11784, "loss": 0.086, "lr": 2.1499527803214846e-10, "epoch": 0.9941446028513238, "percentage": 99.41, "elapsed_time": "0:28:41", "remaining_time": "0:00:10", "throughput": 6532.8, "total_tokens": 11246400}
{"current_steps": 11720, "total_steps": 11784, "loss": 0.0707, "lr": 1.8537949665997642e-10, "epoch": 0.9945689069925322, "percentage": 99.46, "elapsed_time": "0:28:41", "remaining_time": "0:00:09", "throughput": 6534.41, "total_tokens": 11251456}
{"current_steps": 11725, "total_steps": 11784, "loss": 0.0287, "lr": 1.5795721616373992e-10, "epoch": 0.9949932111337406, "percentage": 99.5, "elapsed_time": "0:28:42", "remaining_time": "0:00:08", "throughput": 6535.83, "total_tokens": 11256128}
{"current_steps": 11730, "total_steps": 11784, "loss": 0.0433, "lr": 1.3272849670564746e-10, "epoch": 0.995417515274949, "percentage": 99.54, "elapsed_time": "0:28:42", "remaining_time": "0:00:07", "throughput": 6537.23, "total_tokens": 11260736}
{"current_steps": 11735, "total_steps": 11784, "loss": 0.0669, "lr": 1.0969339363497975e-10, "epoch": 0.9958418194161575, "percentage": 99.58, "elapsed_time": "0:28:42", "remaining_time": "0:00:07", "throughput": 6538.39, "total_tokens": 11264896}
{"current_steps": 11740, "total_steps": 11784, "loss": 0.0291, "lr": 8.885195748875584e-11, "epoch": 0.9962661235573659, "percentage": 99.63, "elapsed_time": "0:28:43", "remaining_time": "0:00:06", "throughput": 6540.22, "total_tokens": 11270400}
{"current_steps": 11745, "total_steps": 11784, "loss": 0.0136, "lr": 7.020423399117791e-11, "epoch": 0.9966904276985743, "percentage": 99.67, "elapsed_time": "0:28:43", "remaining_time": "0:00:05", "throughput": 6541.63, "total_tokens": 11275008}
{"current_steps": 11750, "total_steps": 11784, "loss": 0.0776, "lr": 5.375026405352034e-11, "epoch": 0.9971147318397827, "percentage": 99.71, "elapsed_time": "0:28:43", "remaining_time": "0:00:04", "throughput": 6543.12, "total_tokens": 11279808}
{"current_steps": 11755, "total_steps": 11784, "loss": 0.0341, "lr": 3.949008377424068e-11, "epoch": 0.9975390359809911, "percentage": 99.75, "elapsed_time": "0:28:44", "remaining_time": "0:00:04", "throughput": 6544.26, "total_tokens": 11283904}
{"current_steps": 11760, "total_steps": 11784, "loss": 0.0601, "lr": 2.742372443909069e-11, "epoch": 0.9979633401221996, "percentage": 99.8, "elapsed_time": "0:28:44", "remaining_time": "0:00:03", "throughput": 6545.65, "total_tokens": 11288512}
{"current_steps": 11765, "total_steps": 11784, "loss": 0.1003, "lr": 1.7551212520339197e-11, "epoch": 0.998387644263408, "percentage": 99.84, "elapsed_time": "0:28:44", "remaining_time": "0:00:02", "throughput": 6547.25, "total_tokens": 11293568}
{"current_steps": 11770, "total_steps": 11784, "loss": 0.1294, "lr": 9.872569677438213e-12, "epoch": 0.9988119484046164, "percentage": 99.88, "elapsed_time": "0:28:45", "remaining_time": "0:00:02", "throughput": 6548.93, "total_tokens": 11298752}
{"current_steps": 11775, "total_steps": 11784, "loss": 0.04, "lr": 4.387812756578846e-12, "epoch": 0.9992362525458248, "percentage": 99.92, "elapsed_time": "0:28:45", "remaining_time": "0:00:01", "throughput": 6550.47, "total_tokens": 11303680}
{"current_steps": 11780, "total_steps": 11784, "loss": 0.0059, "lr": 1.0969537908023242e-12, "epoch": 0.9996605566870332, "percentage": 99.97, "elapsed_time": "0:28:45", "remaining_time": "0:00:00", "throughput": 6551.9, "total_tokens": 11308288}
{"current_steps": 11784, "total_steps": 11784, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:29:02", "remaining_time": "0:00:00", "throughput": 6492.68, "total_tokens": 11312256}