Files
QwenTranslate_English_Russian/trainer_log.jsonl
ModelHub XC 100edabc23 初始化项目,由ModelHub XC社区提供模型
Model: baban/QwenTranslate_English_Russian
Source: Original Platform
2026-07-07 19:31:23 +08:00

296 lines
72 KiB
JSON

{"current_steps": 10, "total_steps": 2931, "loss": 0.9742774963378906, "lr": 4.9977515176118345e-05, "epoch": 0.01024, "percentage": 0.34, "elapsed_time": "0:01:20", "remaining_time": "6:30:02", "throughput": 25660.54, "total_tokens": 2055872}
{"current_steps": 20, "total_steps": 2931, "loss": 0.7722540855407715, "lr": 4.9952567580506e-05, "epoch": 0.02048, "percentage": 0.68, "elapsed_time": "0:02:29", "remaining_time": "6:02:15", "throughput": 27013.06, "total_tokens": 4033984}
{"current_steps": 30, "total_steps": 2931, "loss": 0.7429269313812256, "lr": 4.992765730738634e-05, "epoch": 0.03072, "percentage": 1.02, "elapsed_time": "0:03:37", "remaining_time": "5:49:46", "throughput": 27696.97, "total_tokens": 6010880}
{"current_steps": 40, "total_steps": 2931, "loss": 0.7194486618041992, "lr": 4.9902784263792476e-05, "epoch": 0.04096, "percentage": 1.36, "elapsed_time": "0:04:45", "remaining_time": "5:43:46", "throughput": 28031.97, "total_tokens": 7999872}
{"current_steps": 50, "total_steps": 2931, "loss": 0.7071797370910644, "lr": 4.987794835708133e-05, "epoch": 0.0512, "percentage": 1.71, "elapsed_time": "0:06:02", "remaining_time": "5:47:56", "throughput": 27738.86, "total_tokens": 10049984}
{"current_steps": 60, "total_steps": 2931, "loss": 0.6854294776916504, "lr": 4.985314949493234e-05, "epoch": 0.06144, "percentage": 2.05, "elapsed_time": "0:07:14", "remaining_time": "5:46:27", "throughput": 27751.53, "total_tokens": 12056320}
{"current_steps": 70, "total_steps": 2931, "loss": 0.6797103881835938, "lr": 4.982838758534584e-05, "epoch": 0.07168, "percentage": 2.39, "elapsed_time": "0:08:23", "remaining_time": "5:42:53", "throughput": 27864.45, "total_tokens": 14026240}
{"current_steps": 80, "total_steps": 2931, "loss": 0.6712788581848145, "lr": 4.980366253664179e-05, "epoch": 0.08192, "percentage": 2.73, "elapsed_time": "0:09:33", "remaining_time": "5:40:37", "throughput": 27969.94, "total_tokens": 16040128}
{"current_steps": 90, "total_steps": 2931, "loss": 0.6637749671936035, "lr": 4.977897425745825e-05, "epoch": 0.09216, "percentage": 3.07, "elapsed_time": "0:10:45", "remaining_time": "5:39:46", "throughput": 27969.21, "total_tokens": 18062848}
{"current_steps": 100, "total_steps": 2931, "loss": 0.6546947479248046, "lr": 4.975432265674997e-05, "epoch": 0.1024, "percentage": 3.41, "elapsed_time": "0:11:52", "remaining_time": "5:36:09", "throughput": 28131.98, "total_tokens": 20042944}
{"current_steps": 110, "total_steps": 2931, "loss": 0.6477886199951172, "lr": 4.972970764378705e-05, "epoch": 0.11264, "percentage": 3.75, "elapsed_time": "0:13:06", "remaining_time": "5:36:11", "throughput": 28073.04, "total_tokens": 22080512}
{"current_steps": 120, "total_steps": 2931, "loss": 0.6376790046691895, "lr": 4.970512912815344e-05, "epoch": 0.12288, "percentage": 4.09, "elapsed_time": "0:14:16", "remaining_time": "5:34:33", "throughput": 28087.48, "total_tokens": 24069056}
{"current_steps": 130, "total_steps": 2931, "loss": 0.6336091518402099, "lr": 4.968058701974564e-05, "epoch": 0.13312, "percentage": 4.44, "elapsed_time": "0:15:28", "remaining_time": "5:33:29", "throughput": 28067.02, "total_tokens": 26065472}
{"current_steps": 140, "total_steps": 2931, "loss": 0.6247911930084229, "lr": 4.96560812287712e-05, "epoch": 0.14336, "percentage": 4.78, "elapsed_time": "0:16:38", "remaining_time": "5:31:40", "throughput": 28105.7, "total_tokens": 28056704}
{"current_steps": 150, "total_steps": 2931, "loss": 0.628913402557373, "lr": 4.963161166574748e-05, "epoch": 0.1536, "percentage": 5.12, "elapsed_time": "0:17:52", "remaining_time": "5:31:24", "throughput": 28045.93, "total_tokens": 30080064}
{"current_steps": 160, "total_steps": 2931, "loss": 0.6165059089660645, "lr": 4.960717824150013e-05, "epoch": 0.16384, "percentage": 5.46, "elapsed_time": "0:19:04", "remaining_time": "5:30:17", "throughput": 28018.31, "total_tokens": 32061312}
{"current_steps": 170, "total_steps": 2931, "loss": 0.6091556549072266, "lr": 4.9582780867161893e-05, "epoch": 0.17408, "percentage": 5.8, "elapsed_time": "0:20:13", "remaining_time": "5:28:21", "throughput": 28066.36, "total_tokens": 34045312}
{"current_steps": 180, "total_steps": 2931, "loss": 0.6014857292175293, "lr": 4.955841945417105e-05, "epoch": 0.18432, "percentage": 6.14, "elapsed_time": "0:21:24", "remaining_time": "5:27:10", "throughput": 28060.05, "total_tokens": 36041984}
{"current_steps": 190, "total_steps": 2931, "loss": 0.6027495384216308, "lr": 4.953409391427024e-05, "epoch": 0.19456, "percentage": 6.48, "elapsed_time": "0:22:37", "remaining_time": "5:26:17", "throughput": 28045.62, "total_tokens": 38059520}
{"current_steps": 200, "total_steps": 2931, "loss": 0.5953609943389893, "lr": 4.950980415950502e-05, "epoch": 0.2048, "percentage": 6.82, "elapsed_time": "0:23:47", "remaining_time": "5:24:48", "throughput": 28072.35, "total_tokens": 40065728}
{"current_steps": 210, "total_steps": 2931, "loss": 0.591309928894043, "lr": 4.9485550102222575e-05, "epoch": 0.21504, "percentage": 7.16, "elapsed_time": "0:25:01", "remaining_time": "5:24:09", "throughput": 28035.65, "total_tokens": 42083968}
{"current_steps": 220, "total_steps": 2931, "loss": 0.5896960258483886, "lr": 4.946133165507037e-05, "epoch": 0.22528, "percentage": 7.51, "elapsed_time": "0:26:09", "remaining_time": "5:22:20", "throughput": 28081.43, "total_tokens": 44073920}
{"current_steps": 230, "total_steps": 2931, "loss": 0.5793526649475098, "lr": 4.943714873099483e-05, "epoch": 0.23552, "percentage": 7.85, "elapsed_time": "0:27:21", "remaining_time": "5:21:17", "throughput": 28063.98, "total_tokens": 46068544}
{"current_steps": 240, "total_steps": 2931, "loss": 0.5720966339111329, "lr": 4.9413001243240024e-05, "epoch": 0.24576, "percentage": 8.19, "elapsed_time": "0:28:29", "remaining_time": "5:19:32", "throughput": 28101.29, "total_tokens": 48050304}
{"current_steps": 250, "total_steps": 2931, "loss": 0.5646713256835938, "lr": 4.938888910534637e-05, "epoch": 0.256, "percentage": 8.53, "elapsed_time": "0:29:41", "remaining_time": "5:18:22", "throughput": 28105.36, "total_tokens": 50064064}
{"current_steps": 260, "total_steps": 2931, "loss": 0.5561185359954834, "lr": 4.936481223114932e-05, "epoch": 0.26624, "percentage": 8.87, "elapsed_time": "0:30:51", "remaining_time": "5:16:56", "throughput": 28108.74, "total_tokens": 52031040}
{"current_steps": 270, "total_steps": 2931, "loss": 0.5607205390930176, "lr": 4.934077053477808e-05, "epoch": 0.27648, "percentage": 9.21, "elapsed_time": "0:32:07", "remaining_time": "5:16:33", "throughput": 28064.44, "total_tokens": 54084992}
{"current_steps": 280, "total_steps": 2931, "loss": 0.5556824207305908, "lr": 4.931676393065431e-05, "epoch": 0.28672, "percentage": 9.55, "elapsed_time": "0:33:22", "remaining_time": "5:16:00", "throughput": 28027.06, "total_tokens": 56127680}
{"current_steps": 290, "total_steps": 2931, "loss": 0.5448642253875733, "lr": 4.929279233349088e-05, "epoch": 0.29696, "percentage": 9.89, "elapsed_time": "0:34:35", "remaining_time": "5:15:01", "throughput": 28003.46, "total_tokens": 58121600}
{"current_steps": 300, "total_steps": 2931, "loss": 0.5425375461578369, "lr": 4.926885565829051e-05, "epoch": 0.3072, "percentage": 10.24, "elapsed_time": "0:35:44", "remaining_time": "5:13:25", "throughput": 28032.08, "total_tokens": 60109120}
{"current_steps": 310, "total_steps": 2931, "loss": 0.5364805221557617, "lr": 4.924495382034461e-05, "epoch": 0.31744, "percentage": 10.58, "elapsed_time": "0:36:57", "remaining_time": "5:12:25", "throughput": 28025.03, "total_tokens": 62133824}
{"current_steps": 320, "total_steps": 2931, "loss": 0.5378639221191406, "lr": 4.9221086735231975e-05, "epoch": 0.32768, "percentage": 10.92, "elapsed_time": "0:38:07", "remaining_time": "5:11:04", "throughput": 28030.43, "total_tokens": 64119488}
{"current_steps": 330, "total_steps": 2931, "loss": 0.5275018692016602, "lr": 4.919725431881751e-05, "epoch": 0.33792, "percentage": 11.26, "elapsed_time": "0:39:18", "remaining_time": "5:09:47", "throughput": 28041.41, "total_tokens": 66128448}
{"current_steps": 340, "total_steps": 2931, "loss": 0.5153440475463867, "lr": 4.917345648725101e-05, "epoch": 0.34816, "percentage": 11.6, "elapsed_time": "0:40:28", "remaining_time": "5:08:23", "throughput": 28053.72, "total_tokens": 68116544}
{"current_steps": 350, "total_steps": 2931, "loss": 0.5185441493988037, "lr": 4.914969315696596e-05, "epoch": 0.3584, "percentage": 11.94, "elapsed_time": "0:41:41", "remaining_time": "5:07:27", "throughput": 28041.94, "total_tokens": 70149184}
{"current_steps": 360, "total_steps": 2931, "loss": 0.5040504455566406, "lr": 4.912596424467818e-05, "epoch": 0.36864, "percentage": 12.28, "elapsed_time": "0:42:54", "remaining_time": "5:06:27", "throughput": 28029.68, "total_tokens": 72165696}
{"current_steps": 370, "total_steps": 2931, "loss": 0.5027976989746094, "lr": 4.910226966738475e-05, "epoch": 0.37888, "percentage": 12.62, "elapsed_time": "0:44:04", "remaining_time": "5:05:06", "throughput": 28045.94, "total_tokens": 74176064}
{"current_steps": 380, "total_steps": 2931, "loss": 0.5017495155334473, "lr": 4.9078609342362666e-05, "epoch": 0.38912, "percentage": 12.96, "elapsed_time": "0:45:20", "remaining_time": "5:04:23", "throughput": 28011.74, "total_tokens": 76208256}
{"current_steps": 390, "total_steps": 2931, "loss": 0.49234929084777834, "lr": 4.905498318716775e-05, "epoch": 0.39936, "percentage": 13.31, "elapsed_time": "0:46:35", "remaining_time": "5:03:32", "throughput": 27985.5, "total_tokens": 78227520}
{"current_steps": 400, "total_steps": 2931, "loss": 0.484727144241333, "lr": 4.9031391119633295e-05, "epoch": 0.4096, "percentage": 13.65, "elapsed_time": "0:47:49", "remaining_time": "5:02:36", "throughput": 27966.68, "total_tokens": 80247232}
{"current_steps": 410, "total_steps": 2931, "loss": 0.4728262901306152, "lr": 4.9007833057869e-05, "epoch": 0.41984, "percentage": 13.99, "elapsed_time": "0:48:56", "remaining_time": "5:00:58", "throughput": 27992.96, "total_tokens": 82212032}
{"current_steps": 420, "total_steps": 2931, "loss": 0.46816487312316896, "lr": 4.898430892025967e-05, "epoch": 0.43008, "percentage": 14.33, "elapsed_time": "0:50:10", "remaining_time": "4:59:58", "throughput": 27972.93, "total_tokens": 84214528}
{"current_steps": 430, "total_steps": 2931, "loss": 0.4631038665771484, "lr": 4.896081862546415e-05, "epoch": 0.44032, "percentage": 14.67, "elapsed_time": "0:51:21", "remaining_time": "4:58:44", "throughput": 27973.94, "total_tokens": 86207424}
{"current_steps": 440, "total_steps": 2931, "loss": 0.461610221862793, "lr": 4.8937362092414e-05, "epoch": 0.45056, "percentage": 15.01, "elapsed_time": "0:52:33", "remaining_time": "4:57:30", "throughput": 27979.7, "total_tokens": 88220096}
{"current_steps": 450, "total_steps": 2931, "loss": 0.4538113594055176, "lr": 4.891393924031244e-05, "epoch": 0.4608, "percentage": 15.35, "elapsed_time": "0:53:46", "remaining_time": "4:56:29", "throughput": 27971.35, "total_tokens": 90255296}
{"current_steps": 460, "total_steps": 2931, "loss": 0.44371371269226073, "lr": 4.8890549988633095e-05, "epoch": 0.47104, "percentage": 15.69, "elapsed_time": "0:55:02", "remaining_time": "4:55:39", "throughput": 27945.12, "total_tokens": 92284992}
{"current_steps": 470, "total_steps": 2931, "loss": 0.43736696243286133, "lr": 4.8867194257118907e-05, "epoch": 0.48128, "percentage": 16.04, "elapsed_time": "0:56:12", "remaining_time": "4:54:19", "throughput": 27958.09, "total_tokens": 94290304}
{"current_steps": 480, "total_steps": 2931, "loss": 0.4319791793823242, "lr": 4.884387196578093e-05, "epoch": 0.49152, "percentage": 16.38, "elapsed_time": "0:57:24", "remaining_time": "4:53:07", "throughput": 27959.33, "total_tokens": 96299392}
{"current_steps": 490, "total_steps": 2931, "loss": 0.42551512718200685, "lr": 4.882058303489718e-05, "epoch": 0.50176, "percentage": 16.72, "elapsed_time": "0:58:32", "remaining_time": "4:51:39", "throughput": 27977.75, "total_tokens": 98281856}
{"current_steps": 500, "total_steps": 2931, "loss": 0.4181091785430908, "lr": 4.8797327385011496e-05, "epoch": 0.512, "percentage": 17.06, "elapsed_time": "0:59:43", "remaining_time": "4:50:24", "throughput": 27980.15, "total_tokens": 100274880}
{"current_steps": 510, "total_steps": 2931, "loss": 0.41173620223999025, "lr": 4.8774104936932425e-05, "epoch": 0.52224, "percentage": 17.4, "elapsed_time": "1:00:56", "remaining_time": "4:49:18", "throughput": 27971.95, "total_tokens": 102286784}
{"current_steps": 520, "total_steps": 2931, "loss": 0.4068614959716797, "lr": 4.8750915611732076e-05, "epoch": 0.53248, "percentage": 17.74, "elapsed_time": "1:02:11", "remaining_time": "4:48:20", "throughput": 27958.88, "total_tokens": 104322752}
{"current_steps": 530, "total_steps": 2931, "loss": 0.39957451820373535, "lr": 4.8727759330744986e-05, "epoch": 0.54272, "percentage": 18.08, "elapsed_time": "1:03:24", "remaining_time": "4:47:15", "throughput": 27948.12, "total_tokens": 106331264}
{"current_steps": 540, "total_steps": 2931, "loss": 0.39169912338256835, "lr": 4.870463601556696e-05, "epoch": 0.55296, "percentage": 18.42, "elapsed_time": "1:04:38", "remaining_time": "4:46:13", "throughput": 27939.51, "total_tokens": 108363392}
{"current_steps": 550, "total_steps": 2931, "loss": 0.39029181003570557, "lr": 4.8681545588054075e-05, "epoch": 0.5632, "percentage": 18.76, "elapsed_time": "1:05:51", "remaining_time": "4:45:05", "throughput": 27933.66, "total_tokens": 110375744}
{"current_steps": 560, "total_steps": 2931, "loss": 0.37695889472961425, "lr": 4.8658487970321404e-05, "epoch": 0.57344, "percentage": 19.11, "elapsed_time": "1:07:01", "remaining_time": "4:43:44", "throughput": 27949.58, "total_tokens": 112386624}
{"current_steps": 570, "total_steps": 2931, "loss": 0.3717223644256592, "lr": 4.863546308474209e-05, "epoch": 0.58368, "percentage": 19.45, "elapsed_time": "1:08:22", "remaining_time": "4:43:11", "throughput": 27908.8, "total_tokens": 114487616}
{"current_steps": 580, "total_steps": 2931, "loss": 0.36314547061920166, "lr": 4.86124708539461e-05, "epoch": 0.59392, "percentage": 19.79, "elapsed_time": "1:09:32", "remaining_time": "4:41:54", "throughput": 27918.78, "total_tokens": 116502464}
{"current_steps": 590, "total_steps": 2931, "loss": 0.35808553695678713, "lr": 4.8589511200819216e-05, "epoch": 0.60416, "percentage": 20.13, "elapsed_time": "1:10:42", "remaining_time": "4:40:33", "throughput": 27925.72, "total_tokens": 118472896}
{"current_steps": 600, "total_steps": 2931, "loss": 0.354917311668396, "lr": 4.8566584048501926e-05, "epoch": 0.6144, "percentage": 20.47, "elapsed_time": "1:11:52", "remaining_time": "4:39:15", "throughput": 27933.85, "total_tokens": 120475328}
{"current_steps": 610, "total_steps": 2931, "loss": 0.3452127456665039, "lr": 4.854368932038835e-05, "epoch": 0.62464, "percentage": 20.81, "elapsed_time": "1:13:03", "remaining_time": "4:38:00", "throughput": 27933.27, "total_tokens": 122458496}
{"current_steps": 620, "total_steps": 2931, "loss": 0.3381240129470825, "lr": 4.8520826940125144e-05, "epoch": 0.63488, "percentage": 21.15, "elapsed_time": "1:14:13", "remaining_time": "4:36:38", "throughput": 27944.71, "total_tokens": 124439360}
{"current_steps": 630, "total_steps": 2931, "loss": 0.3313805818557739, "lr": 4.849799683161046e-05, "epoch": 0.64512, "percentage": 21.49, "elapsed_time": "1:15:28", "remaining_time": "4:35:38", "throughput": 27929.71, "total_tokens": 126467840}
{"current_steps": 640, "total_steps": 2931, "loss": 0.3252664566040039, "lr": 4.8475198918992835e-05, "epoch": 0.65536, "percentage": 21.84, "elapsed_time": "1:16:38", "remaining_time": "4:34:22", "throughput": 27937.58, "total_tokens": 128480448}
{"current_steps": 650, "total_steps": 2931, "loss": 0.3170381784439087, "lr": 4.845243312667023e-05, "epoch": 0.6656, "percentage": 22.18, "elapsed_time": "1:17:50", "remaining_time": "4:33:11", "throughput": 27933.97, "total_tokens": 130479232}
{"current_steps": 660, "total_steps": 2931, "loss": 0.3079851150512695, "lr": 4.842969937928884e-05, "epoch": 0.67584, "percentage": 22.52, "elapsed_time": "1:19:03", "remaining_time": "4:32:01", "throughput": 27928.74, "total_tokens": 132478912}
{"current_steps": 670, "total_steps": 2931, "loss": 0.3024315357208252, "lr": 4.840699760174217e-05, "epoch": 0.68608, "percentage": 22.86, "elapsed_time": "1:20:14", "remaining_time": "4:30:45", "throughput": 27933.17, "total_tokens": 134473408}
{"current_steps": 680, "total_steps": 2931, "loss": 0.29927806854248046, "lr": 4.8384327719169906e-05, "epoch": 0.69632, "percentage": 23.2, "elapsed_time": "1:21:25", "remaining_time": "4:29:31", "throughput": 27937.61, "total_tokens": 136482944}
{"current_steps": 690, "total_steps": 2931, "loss": 0.2894315242767334, "lr": 4.836168965695694e-05, "epoch": 0.70656, "percentage": 23.54, "elapsed_time": "1:22:34", "remaining_time": "4:28:12", "throughput": 27947.79, "total_tokens": 138476544}
{"current_steps": 700, "total_steps": 2931, "loss": 0.2819934129714966, "lr": 4.8339083340732304e-05, "epoch": 0.7168, "percentage": 23.88, "elapsed_time": "1:23:46", "remaining_time": "4:27:01", "throughput": 27945.58, "total_tokens": 140478784}
{"current_steps": 710, "total_steps": 2931, "loss": 0.2754687309265137, "lr": 4.8316508696368154e-05, "epoch": 0.72704, "percentage": 24.22, "elapsed_time": "1:25:03", "remaining_time": "4:26:04", "throughput": 27930.28, "total_tokens": 142543936}
{"current_steps": 720, "total_steps": 2931, "loss": 0.2691352367401123, "lr": 4.8293965649978714e-05, "epoch": 0.73728, "percentage": 24.56, "elapsed_time": "1:26:15", "remaining_time": "4:24:52", "throughput": 27932.81, "total_tokens": 144565184}
{"current_steps": 730, "total_steps": 2931, "loss": 0.2596245765686035, "lr": 4.8271454127919364e-05, "epoch": 0.74752, "percentage": 24.91, "elapsed_time": "1:27:27", "remaining_time": "4:23:42", "throughput": 27934.4, "total_tokens": 146591872}
{"current_steps": 740, "total_steps": 2931, "loss": 0.253094482421875, "lr": 4.824897405678549e-05, "epoch": 0.75776, "percentage": 25.25, "elapsed_time": "1:28:39", "remaining_time": "4:22:31", "throughput": 27934.81, "total_tokens": 148609728}
{"current_steps": 750, "total_steps": 2931, "loss": 0.24751272201538085, "lr": 4.8226525363411576e-05, "epoch": 0.768, "percentage": 25.59, "elapsed_time": "1:29:52", "remaining_time": "4:21:20", "throughput": 27932.17, "total_tokens": 150619520}
{"current_steps": 760, "total_steps": 2931, "loss": 0.2425351619720459, "lr": 4.820410797487017e-05, "epoch": 0.77824, "percentage": 25.93, "elapsed_time": "1:31:03", "remaining_time": "4:20:08", "throughput": 27932.12, "total_tokens": 152618560}
{"current_steps": 770, "total_steps": 2931, "loss": 0.2338550090789795, "lr": 4.818172181847091e-05, "epoch": 0.78848, "percentage": 26.27, "elapsed_time": "1:32:16", "remaining_time": "4:18:57", "throughput": 27927.16, "total_tokens": 154616256}
{"current_steps": 780, "total_steps": 2931, "loss": 0.23002958297729492, "lr": 4.81593668217595e-05, "epoch": 0.79872, "percentage": 26.61, "elapsed_time": "1:33:29", "remaining_time": "4:17:49", "throughput": 27921.64, "total_tokens": 156632640}
{"current_steps": 790, "total_steps": 2931, "loss": 0.22488293647766114, "lr": 4.813704291251675e-05, "epoch": 0.80896, "percentage": 26.95, "elapsed_time": "1:34:39", "remaining_time": "4:16:32", "throughput": 27929.67, "total_tokens": 158627584}
{"current_steps": 800, "total_steps": 2931, "loss": 0.21674442291259766, "lr": 4.811475001875759e-05, "epoch": 0.8192, "percentage": 27.29, "elapsed_time": "1:35:51", "remaining_time": "4:15:20", "throughput": 27929.06, "total_tokens": 160628608}
{"current_steps": 810, "total_steps": 2931, "loss": 0.21201133728027344, "lr": 4.8092488068730105e-05, "epoch": 0.82944, "percentage": 27.64, "elapsed_time": "1:37:03", "remaining_time": "4:14:09", "throughput": 27926.21, "total_tokens": 162631040}
{"current_steps": 820, "total_steps": 2931, "loss": 0.20578887462615966, "lr": 4.807025699091452e-05, "epoch": 0.83968, "percentage": 27.98, "elapsed_time": "1:38:16", "remaining_time": "4:12:59", "throughput": 27924.71, "total_tokens": 164655936}
{"current_steps": 830, "total_steps": 2931, "loss": 0.20376951694488527, "lr": 4.8048056714022325e-05, "epoch": 0.84992, "percentage": 28.32, "elapsed_time": "1:39:25", "remaining_time": "4:11:41", "throughput": 27932.28, "total_tokens": 166635648}
{"current_steps": 840, "total_steps": 2931, "loss": 0.19258487224578857, "lr": 4.802588716699519e-05, "epoch": 0.86016, "percentage": 28.66, "elapsed_time": "1:40:39", "remaining_time": "4:10:34", "throughput": 27928.95, "total_tokens": 168677504}
{"current_steps": 850, "total_steps": 2931, "loss": 0.18773103952407838, "lr": 4.8003748279004156e-05, "epoch": 0.8704, "percentage": 29.0, "elapsed_time": "1:41:53", "remaining_time": "4:09:26", "throughput": 27925.11, "total_tokens": 170712320}
{"current_steps": 860, "total_steps": 2931, "loss": 0.1815708875656128, "lr": 4.798163997944854e-05, "epoch": 0.88064, "percentage": 29.34, "elapsed_time": "1:43:05", "remaining_time": "4:08:15", "throughput": 27923.64, "total_tokens": 172726592}
{"current_steps": 870, "total_steps": 2931, "loss": 0.17781240940093995, "lr": 4.79595621979551e-05, "epoch": 0.89088, "percentage": 29.68, "elapsed_time": "1:44:17", "remaining_time": "4:07:03", "throughput": 27922.96, "total_tokens": 174723904}
{"current_steps": 880, "total_steps": 2931, "loss": 0.1705024003982544, "lr": 4.793751486437702e-05, "epoch": 0.90112, "percentage": 30.02, "elapsed_time": "1:45:27", "remaining_time": "4:05:47", "throughput": 27928.53, "total_tokens": 176724608}
{"current_steps": 890, "total_steps": 2931, "loss": 0.1674124240875244, "lr": 4.7915497908793064e-05, "epoch": 0.91136, "percentage": 30.37, "elapsed_time": "1:46:43", "remaining_time": "4:04:44", "throughput": 27918.65, "total_tokens": 178766720}
{"current_steps": 900, "total_steps": 2931, "loss": 0.1599474549293518, "lr": 4.7893511261506516e-05, "epoch": 0.9216, "percentage": 30.71, "elapsed_time": "1:47:54", "remaining_time": "4:03:30", "throughput": 27923.37, "total_tokens": 180780864}
{"current_steps": 910, "total_steps": 2931, "loss": 0.1556488037109375, "lr": 4.787155485304435e-05, "epoch": 0.93184, "percentage": 31.05, "elapsed_time": "1:49:03", "remaining_time": "4:02:13", "throughput": 27927.68, "total_tokens": 182756544}
{"current_steps": 920, "total_steps": 2931, "loss": 0.14749314785003662, "lr": 4.784962861415629e-05, "epoch": 0.94208, "percentage": 31.39, "elapsed_time": "1:50:14", "remaining_time": "4:00:58", "throughput": 27932.19, "total_tokens": 184760448}
{"current_steps": 930, "total_steps": 2931, "loss": 0.14295361042022706, "lr": 4.7827732475813884e-05, "epoch": 0.95232, "percentage": 31.73, "elapsed_time": "1:51:23", "remaining_time": "3:59:41", "throughput": 27940.72, "total_tokens": 186755072}
{"current_steps": 940, "total_steps": 2931, "loss": 0.13959715366363526, "lr": 4.7805866369209576e-05, "epoch": 0.96256, "percentage": 32.07, "elapsed_time": "1:52:35", "remaining_time": "3:58:29", "throughput": 27940.87, "total_tokens": 188760896}
{"current_steps": 950, "total_steps": 2931, "loss": 0.13509231805801392, "lr": 4.778403022575583e-05, "epoch": 0.9728, "percentage": 32.41, "elapsed_time": "1:53:48", "remaining_time": "3:57:19", "throughput": 27938.09, "total_tokens": 190778560}
{"current_steps": 960, "total_steps": 2931, "loss": 0.12972679138183593, "lr": 4.7762223977084195e-05, "epoch": 0.98304, "percentage": 32.75, "elapsed_time": "1:55:01", "remaining_time": "3:56:08", "throughput": 27937.63, "total_tokens": 192799232}
{"current_steps": 970, "total_steps": 2931, "loss": 0.12503955364227295, "lr": 4.774044755504444e-05, "epoch": 0.99328, "percentage": 33.09, "elapsed_time": "1:56:10", "remaining_time": "3:54:51", "throughput": 27945.94, "total_tokens": 194792768}
{"current_steps": 980, "total_steps": 2931, "loss": 0.10986135005950928, "lr": 4.7718700891703616e-05, "epoch": 1.003072, "percentage": 33.44, "elapsed_time": "1:57:15", "remaining_time": "3:53:25", "throughput": 27955.36, "total_tokens": 196668032}
{"current_steps": 990, "total_steps": 2931, "loss": 0.08115079402923583, "lr": 4.7696983919345215e-05, "epoch": 1.013312, "percentage": 33.78, "elapsed_time": "1:58:29", "remaining_time": "3:52:19", "throughput": 27948.27, "total_tokens": 198703552}
{"current_steps": 1000, "total_steps": 2931, "loss": 0.07811311483383179, "lr": 4.7675296570468216e-05, "epoch": 1.023552, "percentage": 34.12, "elapsed_time": "1:59:42", "remaining_time": "3:51:08", "throughput": 27947.45, "total_tokens": 200721088}
{"current_steps": 1010, "total_steps": 2931, "loss": 0.07646113634109497, "lr": 4.76536387777863e-05, "epoch": 1.033792, "percentage": 34.46, "elapsed_time": "2:00:55", "remaining_time": "3:50:00", "throughput": 27940.14, "total_tokens": 202724032}
{"current_steps": 1020, "total_steps": 2931, "loss": 0.07352162599563598, "lr": 4.7632010474226915e-05, "epoch": 1.044032, "percentage": 34.8, "elapsed_time": "2:02:05", "remaining_time": "3:48:45", "throughput": 27945.21, "total_tokens": 204720448}
{"current_steps": 1030, "total_steps": 2931, "loss": 0.07193953990936279, "lr": 4.761041159293035e-05, "epoch": 1.054272, "percentage": 35.14, "elapsed_time": "2:03:18", "remaining_time": "3:47:34", "throughput": 27944.37, "total_tokens": 206747072}
{"current_steps": 1040, "total_steps": 2931, "loss": 0.07109384536743164, "lr": 4.7588842067249e-05, "epoch": 1.064512, "percentage": 35.48, "elapsed_time": "2:04:31", "remaining_time": "3:46:26", "throughput": 27940.03, "total_tokens": 208767168}
{"current_steps": 1050, "total_steps": 2931, "loss": 0.06862571239471435, "lr": 4.756730183074637e-05, "epoch": 1.074752, "percentage": 35.82, "elapsed_time": "2:05:42", "remaining_time": "3:45:11", "throughput": 27942.14, "total_tokens": 210755648}
{"current_steps": 1060, "total_steps": 2931, "loss": 0.06509301662445069, "lr": 4.7545790817196314e-05, "epoch": 1.084992, "percentage": 36.17, "elapsed_time": "2:06:51", "remaining_time": "3:43:54", "throughput": 27951.52, "total_tokens": 212746688}
{"current_steps": 1070, "total_steps": 2931, "loss": 0.06395751237869263, "lr": 4.752430896058212e-05, "epoch": 1.095232, "percentage": 36.51, "elapsed_time": "2:08:04", "remaining_time": "3:42:44", "throughput": 27949.61, "total_tokens": 214772352}
{"current_steps": 1080, "total_steps": 2931, "loss": 0.06260917186737061, "lr": 4.750285619509567e-05, "epoch": 1.105472, "percentage": 36.85, "elapsed_time": "2:09:14", "remaining_time": "3:41:31", "throughput": 27953.07, "total_tokens": 216773568}
{"current_steps": 1090, "total_steps": 2931, "loss": 0.062073934078216556, "lr": 4.7481432455136644e-05, "epoch": 1.115712, "percentage": 37.19, "elapsed_time": "2:10:26", "remaining_time": "3:40:19", "throughput": 27950.6, "total_tokens": 218764928}
{"current_steps": 1100, "total_steps": 2931, "loss": 0.057993775606155394, "lr": 4.7460037675311584e-05, "epoch": 1.125952, "percentage": 37.53, "elapsed_time": "2:11:37", "remaining_time": "3:39:05", "throughput": 27952.42, "total_tokens": 220755776}
{"current_steps": 1110, "total_steps": 2931, "loss": 0.05776026248931885, "lr": 4.7438671790433126e-05, "epoch": 1.136192, "percentage": 37.87, "elapsed_time": "2:12:47", "remaining_time": "3:37:50", "throughput": 27957.57, "total_tokens": 222748608}
{"current_steps": 1120, "total_steps": 2931, "loss": 0.05773916840553284, "lr": 4.741733473551915e-05, "epoch": 1.146432, "percentage": 38.21, "elapsed_time": "2:14:01", "remaining_time": "3:36:43", "throughput": 27952.0, "total_tokens": 224784512}
{"current_steps": 1130, "total_steps": 2931, "loss": 0.05507153272628784, "lr": 4.7396026445791966e-05, "epoch": 1.156672, "percentage": 38.55, "elapsed_time": "2:15:15", "remaining_time": "3:35:34", "throughput": 27948.16, "total_tokens": 226813120}
{"current_steps": 1140, "total_steps": 2931, "loss": 0.05341644287109375, "lr": 4.737474685667742e-05, "epoch": 1.166912, "percentage": 38.89, "elapsed_time": "2:16:27", "remaining_time": "3:34:22", "throughput": 27947.35, "total_tokens": 228815232}
{"current_steps": 1150, "total_steps": 2931, "loss": 0.05063482522964478, "lr": 4.7353495903804165e-05, "epoch": 1.177152, "percentage": 39.24, "elapsed_time": "2:17:44", "remaining_time": "3:33:18", "throughput": 27937.33, "total_tokens": 230880320}
{"current_steps": 1160, "total_steps": 2931, "loss": 0.050589507818222045, "lr": 4.733227352300277e-05, "epoch": 1.187392, "percentage": 39.58, "elapsed_time": "2:18:58", "remaining_time": "3:32:10", "throughput": 27930.75, "total_tokens": 232907904}
{"current_steps": 1170, "total_steps": 2931, "loss": 0.04946887493133545, "lr": 4.731107965030496e-05, "epoch": 1.197632, "percentage": 39.92, "elapsed_time": "2:20:10", "remaining_time": "3:30:59", "throughput": 27931.32, "total_tokens": 234922176}
{"current_steps": 1180, "total_steps": 2931, "loss": 0.04885604977607727, "lr": 4.728991422194278e-05, "epoch": 1.207872, "percentage": 40.26, "elapsed_time": "2:21:21", "remaining_time": "3:29:45", "throughput": 27934.26, "total_tokens": 236912128}
{"current_steps": 1190, "total_steps": 2931, "loss": 0.048174849152565, "lr": 4.726877717434773e-05, "epoch": 1.218112, "percentage": 40.6, "elapsed_time": "2:22:31", "remaining_time": "3:28:30", "throughput": 27937.82, "total_tokens": 238900864}
{"current_steps": 1200, "total_steps": 2931, "loss": 0.04597228169441223, "lr": 4.724766844415013e-05, "epoch": 1.228352, "percentage": 40.94, "elapsed_time": "2:23:47", "remaining_time": "3:27:25", "throughput": 27928.63, "total_tokens": 240960448}
{"current_steps": 1210, "total_steps": 2931, "loss": 0.04480882287025452, "lr": 4.722658796817813e-05, "epoch": 1.238592, "percentage": 41.28, "elapsed_time": "2:25:02", "remaining_time": "3:26:17", "throughput": 27922.25, "total_tokens": 242998848}
{"current_steps": 1220, "total_steps": 2931, "loss": 0.04354588389396667, "lr": 4.7205535683457044e-05, "epoch": 1.248832, "percentage": 41.62, "elapsed_time": "2:26:07", "remaining_time": "3:24:56", "throughput": 27937.55, "total_tokens": 244947776}
{"current_steps": 1230, "total_steps": 2931, "loss": 0.041252422332763675, "lr": 4.7184511527208484e-05, "epoch": 1.259072, "percentage": 41.97, "elapsed_time": "2:27:18", "remaining_time": "3:23:43", "throughput": 27939.67, "total_tokens": 246951744}
{"current_steps": 1240, "total_steps": 2931, "loss": 0.03930726945400238, "lr": 4.7163515436849644e-05, "epoch": 1.269312, "percentage": 42.31, "elapsed_time": "2:28:32", "remaining_time": "3:22:34", "throughput": 27936.85, "total_tokens": 248987840}
{"current_steps": 1250, "total_steps": 2931, "loss": 0.03749307096004486, "lr": 4.714254734999245e-05, "epoch": 1.279552, "percentage": 42.65, "elapsed_time": "2:29:41", "remaining_time": "3:21:18", "throughput": 27941.87, "total_tokens": 250972928}
{"current_steps": 1260, "total_steps": 2931, "loss": 0.03726911842823029, "lr": 4.712160720444284e-05, "epoch": 1.289792, "percentage": 42.99, "elapsed_time": "2:30:53", "remaining_time": "3:20:07", "throughput": 27942.78, "total_tokens": 252991744}
{"current_steps": 1270, "total_steps": 2931, "loss": 0.03688657283782959, "lr": 4.710069493819992e-05, "epoch": 1.300032, "percentage": 43.33, "elapsed_time": "2:32:04", "remaining_time": "3:18:53", "throughput": 27945.9, "total_tokens": 254978432}
{"current_steps": 1280, "total_steps": 2931, "loss": 0.03622893989086151, "lr": 4.70798104894553e-05, "epoch": 1.3102719999999999, "percentage": 43.67, "elapsed_time": "2:33:12", "remaining_time": "3:17:37", "throughput": 27951.86, "total_tokens": 256958912}
{"current_steps": 1290, "total_steps": 2931, "loss": 0.03448793888092041, "lr": 4.705895379659219e-05, "epoch": 1.320512, "percentage": 44.01, "elapsed_time": "2:34:21", "remaining_time": "3:16:21", "throughput": 27956.46, "total_tokens": 258927104}
{"current_steps": 1300, "total_steps": 2931, "loss": 0.03333508670330047, "lr": 4.7038124798184766e-05, "epoch": 1.330752, "percentage": 44.35, "elapsed_time": "2:35:31", "remaining_time": "3:15:07", "throughput": 27959.58, "total_tokens": 260902016}
{"current_steps": 1310, "total_steps": 2931, "loss": 0.032725405693054196, "lr": 4.7017323432997304e-05, "epoch": 1.340992, "percentage": 44.69, "elapsed_time": "2:36:43", "remaining_time": "3:13:56", "throughput": 27957.23, "total_tokens": 262909696}
{"current_steps": 1320, "total_steps": 2931, "loss": 0.03168002963066101, "lr": 4.6996549639983506e-05, "epoch": 1.351232, "percentage": 45.04, "elapsed_time": "2:37:56", "remaining_time": "3:12:45", "throughput": 27956.79, "total_tokens": 264930176}
{"current_steps": 1330, "total_steps": 2931, "loss": 0.02995384335517883, "lr": 4.697580335828569e-05, "epoch": 1.361472, "percentage": 45.38, "elapsed_time": "2:39:10", "remaining_time": "3:11:36", "throughput": 27952.21, "total_tokens": 266964480}
{"current_steps": 1340, "total_steps": 2931, "loss": 0.030216827988624573, "lr": 4.6955084527234076e-05, "epoch": 1.371712, "percentage": 45.72, "elapsed_time": "2:40:23", "remaining_time": "3:10:25", "throughput": 27952.26, "total_tokens": 268993664}
{"current_steps": 1350, "total_steps": 2931, "loss": 0.028735750913619997, "lr": 4.6934393086346034e-05, "epoch": 1.381952, "percentage": 46.06, "elapsed_time": "2:41:31", "remaining_time": "3:09:09", "throughput": 27961.35, "total_tokens": 270981248}
{"current_steps": 1360, "total_steps": 2931, "loss": 0.026437461376190186, "lr": 4.6913728975325324e-05, "epoch": 1.392192, "percentage": 46.4, "elapsed_time": "2:42:42", "remaining_time": "3:07:56", "throughput": 27964.06, "total_tokens": 272987712}
{"current_steps": 1370, "total_steps": 2931, "loss": 0.02681639790534973, "lr": 4.6893092134061393e-05, "epoch": 1.4024320000000001, "percentage": 46.74, "elapsed_time": "2:43:56", "remaining_time": "3:06:48", "throughput": 27958.14, "total_tokens": 275016192}
{"current_steps": 1380, "total_steps": 2931, "loss": 0.02621593475341797, "lr": 4.687248250262859e-05, "epoch": 1.412672, "percentage": 47.08, "elapsed_time": "2:45:06", "remaining_time": "3:05:34", "throughput": 27960.23, "total_tokens": 277001984}
{"current_steps": 1390, "total_steps": 2931, "loss": 0.025581035017967223, "lr": 4.685190002128548e-05, "epoch": 1.422912, "percentage": 47.42, "elapsed_time": "2:46:22", "remaining_time": "3:04:26", "throughput": 27953.45, "total_tokens": 279033856}
{"current_steps": 1400, "total_steps": 2931, "loss": 0.02472420036792755, "lr": 4.6831344630474114e-05, "epoch": 1.433152, "percentage": 47.77, "elapsed_time": "2:47:41", "remaining_time": "3:03:22", "throughput": 27939.8, "total_tokens": 281106624}
{"current_steps": 1410, "total_steps": 2931, "loss": 0.023309352993965148, "lr": 4.6810816270819276e-05, "epoch": 1.443392, "percentage": 48.11, "elapsed_time": "2:48:49", "remaining_time": "3:02:06", "throughput": 27948.72, "total_tokens": 283099072}
{"current_steps": 1420, "total_steps": 2931, "loss": 0.0234044149518013, "lr": 4.679031488312777e-05, "epoch": 1.453632, "percentage": 48.45, "elapsed_time": "2:50:04", "remaining_time": "3:00:57", "throughput": 27942.05, "total_tokens": 285122560}
{"current_steps": 1430, "total_steps": 2931, "loss": 0.021864794194698334, "lr": 4.6769840408387717e-05, "epoch": 1.463872, "percentage": 48.79, "elapsed_time": "2:51:15", "remaining_time": "2:59:45", "throughput": 27940.97, "total_tokens": 287115584}
{"current_steps": 1440, "total_steps": 2931, "loss": 0.022062216699123383, "lr": 4.674939278776787e-05, "epoch": 1.4741119999999999, "percentage": 49.13, "elapsed_time": "2:52:28", "remaining_time": "2:58:34", "throughput": 27940.84, "total_tokens": 289142976}
{"current_steps": 1450, "total_steps": 2931, "loss": 0.020946532487869263, "lr": 4.672897196261683e-05, "epoch": 1.484352, "percentage": 49.47, "elapsed_time": "2:53:40", "remaining_time": "2:57:23", "throughput": 27940.86, "total_tokens": 291151552}
{"current_steps": 1460, "total_steps": 2931, "loss": 0.021855458617210388, "lr": 4.670857787446238e-05, "epoch": 1.494592, "percentage": 49.81, "elapsed_time": "2:54:54", "remaining_time": "2:56:13", "throughput": 27937.09, "total_tokens": 293175936}
{"current_steps": 1470, "total_steps": 2931, "loss": 0.019446633756160736, "lr": 4.668821046501082e-05, "epoch": 1.504832, "percentage": 50.15, "elapsed_time": "2:56:06", "remaining_time": "2:55:02", "throughput": 27936.62, "total_tokens": 295201984}
{"current_steps": 1480, "total_steps": 2931, "loss": 0.018910986185073853, "lr": 4.6667869676146194e-05, "epoch": 1.515072, "percentage": 50.49, "elapsed_time": "2:57:23", "remaining_time": "2:53:54", "throughput": 27927.41, "total_tokens": 297239808}
{"current_steps": 1490, "total_steps": 2931, "loss": 0.0188526451587677, "lr": 4.6647555449929645e-05, "epoch": 1.525312, "percentage": 50.84, "elapsed_time": "2:58:38", "remaining_time": "2:52:46", "throughput": 27920.22, "total_tokens": 299265024}
{"current_steps": 1500, "total_steps": 2931, "loss": 0.0179020956158638, "lr": 4.662726772859869e-05, "epoch": 1.535552, "percentage": 51.18, "elapsed_time": "2:59:51", "remaining_time": "2:51:34", "throughput": 27919.79, "total_tokens": 301289600}
{"current_steps": 1510, "total_steps": 2931, "loss": 0.017698875069618224, "lr": 4.660700645456655e-05, "epoch": 1.545792, "percentage": 51.52, "elapsed_time": "3:01:01", "remaining_time": "2:50:21", "throughput": 27923.08, "total_tokens": 303298944}
{"current_steps": 1520, "total_steps": 2931, "loss": 0.016229704022407532, "lr": 4.658677157042149e-05, "epoch": 1.556032, "percentage": 51.86, "elapsed_time": "3:02:12", "remaining_time": "2:49:08", "throughput": 27926.78, "total_tokens": 305301120}
{"current_steps": 1530, "total_steps": 2931, "loss": 0.015268620848655701, "lr": 4.656656301892605e-05, "epoch": 1.566272, "percentage": 52.2, "elapsed_time": "3:03:25", "remaining_time": "2:47:57", "throughput": 27921.96, "total_tokens": 307290560}
{"current_steps": 1540, "total_steps": 2931, "loss": 0.016469526290893554, "lr": 4.6546380743016465e-05, "epoch": 1.5765120000000001, "percentage": 52.54, "elapsed_time": "3:04:34", "remaining_time": "2:46:42", "throughput": 27926.73, "total_tokens": 309270848}
{"current_steps": 1550, "total_steps": 2931, "loss": 0.015096321702003479, "lr": 4.652622468580193e-05, "epoch": 1.5867520000000002, "percentage": 52.88, "elapsed_time": "3:05:46", "remaining_time": "2:45:31", "throughput": 27927.44, "total_tokens": 311299328}
{"current_steps": 1560, "total_steps": 2931, "loss": 0.015387380123138427, "lr": 4.650609479056392e-05, "epoch": 1.596992, "percentage": 53.22, "elapsed_time": "3:06:54", "remaining_time": "2:44:15", "throughput": 27934.06, "total_tokens": 313267840}
{"current_steps": 1570, "total_steps": 2931, "loss": 0.014029040932655334, "lr": 4.648599100075556e-05, "epoch": 1.607232, "percentage": 53.57, "elapsed_time": "3:08:05", "remaining_time": "2:43:02", "throughput": 27938.0, "total_tokens": 315284992}
{"current_steps": 1580, "total_steps": 2931, "loss": 0.014028981328010559, "lr": 4.6465913260000945e-05, "epoch": 1.617472, "percentage": 53.91, "elapsed_time": "3:09:18", "remaining_time": "2:41:52", "throughput": 27935.74, "total_tokens": 317306816}
{"current_steps": 1590, "total_steps": 2931, "loss": 0.013350155949592591, "lr": 4.644586151209444e-05, "epoch": 1.627712, "percentage": 54.25, "elapsed_time": "3:10:29", "remaining_time": "2:40:39", "throughput": 27938.43, "total_tokens": 319310464}
{"current_steps": 1600, "total_steps": 2931, "loss": 0.013065680861473083, "lr": 4.6425835701000084e-05, "epoch": 1.6379519999999999, "percentage": 54.59, "elapsed_time": "3:11:40", "remaining_time": "2:39:27", "throughput": 27939.73, "total_tokens": 321328896}
{"current_steps": 1610, "total_steps": 2931, "loss": 0.012181369960308075, "lr": 4.640583577085084e-05, "epoch": 1.6481919999999999, "percentage": 54.93, "elapsed_time": "3:12:53", "remaining_time": "2:38:16", "throughput": 27937.78, "total_tokens": 323339008}
{"current_steps": 1620, "total_steps": 2931, "loss": 0.012439670413732529, "lr": 4.638586166594806e-05, "epoch": 1.658432, "percentage": 55.27, "elapsed_time": "3:14:02", "remaining_time": "2:37:01", "throughput": 27941.64, "total_tokens": 325311936}
{"current_steps": 1630, "total_steps": 2931, "loss": 0.01156621277332306, "lr": 4.6365913330760726e-05, "epoch": 1.668672, "percentage": 55.61, "elapsed_time": "3:15:14", "remaining_time": "2:35:50", "throughput": 27942.01, "total_tokens": 327330944}
{"current_steps": 1640, "total_steps": 2931, "loss": 0.011320900171995163, "lr": 4.6345990709924855e-05, "epoch": 1.678912, "percentage": 55.95, "elapsed_time": "3:16:25", "remaining_time": "2:34:37", "throughput": 27944.93, "total_tokens": 329349504}
{"current_steps": 1650, "total_steps": 2931, "loss": 0.011535357683897018, "lr": 4.632609374824284e-05, "epoch": 1.689152, "percentage": 56.29, "elapsed_time": "3:17:34", "remaining_time": "2:33:23", "throughput": 27951.39, "total_tokens": 331350144}
{"current_steps": 1660, "total_steps": 2931, "loss": 0.010813712328672408, "lr": 4.630622239068285e-05, "epoch": 1.699392, "percentage": 56.64, "elapsed_time": "3:18:47", "remaining_time": "2:32:12", "throughput": 27949.59, "total_tokens": 333357824}
{"current_steps": 1670, "total_steps": 2931, "loss": 0.010460171103477477, "lr": 4.628637658237808e-05, "epoch": 1.709632, "percentage": 56.98, "elapsed_time": "3:19:58", "remaining_time": "2:31:00", "throughput": 27950.47, "total_tokens": 335369856}
{"current_steps": 1680, "total_steps": 2931, "loss": 0.0098984993994236, "lr": 4.626655626862625e-05, "epoch": 1.719872, "percentage": 57.32, "elapsed_time": "3:21:09", "remaining_time": "2:29:47", "throughput": 27952.34, "total_tokens": 337365952}
{"current_steps": 1690, "total_steps": 2931, "loss": 0.009945446252822876, "lr": 4.624676139488888e-05, "epoch": 1.730112, "percentage": 57.66, "elapsed_time": "3:22:25", "remaining_time": "2:28:38", "throughput": 27945.73, "total_tokens": 339410240}
{"current_steps": 1700, "total_steps": 2931, "loss": 0.009306684136390686, "lr": 4.6226991906790686e-05, "epoch": 1.7403520000000001, "percentage": 58.0, "elapsed_time": "3:23:35", "remaining_time": "2:27:25", "throughput": 27950.19, "total_tokens": 341428992}
{"current_steps": 1710, "total_steps": 2931, "loss": 0.009691517055034637, "lr": 4.620724775011897e-05, "epoch": 1.7505920000000001, "percentage": 58.34, "elapsed_time": "3:24:48", "remaining_time": "2:26:14", "throughput": 27948.64, "total_tokens": 343457216}
{"current_steps": 1720, "total_steps": 2931, "loss": 0.008967689424753188, "lr": 4.618752887082297e-05, "epoch": 1.760832, "percentage": 58.68, "elapsed_time": "3:25:57", "remaining_time": "2:25:00", "throughput": 27952.8, "total_tokens": 345431232}
{"current_steps": 1730, "total_steps": 2931, "loss": 0.008772896230220794, "lr": 4.616783521501325e-05, "epoch": 1.771072, "percentage": 59.02, "elapsed_time": "3:27:12", "remaining_time": "2:23:51", "throughput": 27945.91, "total_tokens": 347450176}
{"current_steps": 1740, "total_steps": 2931, "loss": 0.008689258992671967, "lr": 4.614816672896108e-05, "epoch": 1.781312, "percentage": 59.37, "elapsed_time": "3:28:22", "remaining_time": "2:22:37", "throughput": 27948.82, "total_tokens": 349421504}
{"current_steps": 1750, "total_steps": 2931, "loss": 0.008518567681312561, "lr": 4.612852335909782e-05, "epoch": 1.791552, "percentage": 59.71, "elapsed_time": "3:29:27", "remaining_time": "2:21:21", "throughput": 27957.63, "total_tokens": 351366656}
{"current_steps": 1760, "total_steps": 2931, "loss": 0.008236590027809142, "lr": 4.6108905052014323e-05, "epoch": 1.8017919999999998, "percentage": 60.05, "elapsed_time": "3:30:39", "remaining_time": "2:20:09", "throughput": 27959.21, "total_tokens": 353376960}
{"current_steps": 1770, "total_steps": 2931, "loss": 0.007975803315639496, "lr": 4.608931175446027e-05, "epoch": 1.8120319999999999, "percentage": 60.39, "elapsed_time": "3:31:47", "remaining_time": "2:18:55", "throughput": 27965.36, "total_tokens": 355372096}
{"current_steps": 1780, "total_steps": 2931, "loss": 0.008116719126701356, "lr": 4.606974341334367e-05, "epoch": 1.822272, "percentage": 60.73, "elapsed_time": "3:32:56", "remaining_time": "2:17:41", "throughput": 27969.56, "total_tokens": 357352000}
{"current_steps": 1790, "total_steps": 2931, "loss": 0.007819350808858871, "lr": 4.605019997573011e-05, "epoch": 1.832512, "percentage": 61.07, "elapsed_time": "3:34:09", "remaining_time": "2:16:30", "throughput": 27968.38, "total_tokens": 359375232}
{"current_steps": 1800, "total_steps": 2931, "loss": 0.008013889193534851, "lr": 4.603068138884229e-05, "epoch": 1.842752, "percentage": 61.41, "elapsed_time": "3:35:24", "remaining_time": "2:15:21", "throughput": 27963.43, "total_tokens": 361425216}
{"current_steps": 1810, "total_steps": 2931, "loss": 0.007500405609607697, "lr": 4.6011187600059345e-05, "epoch": 1.852992, "percentage": 61.75, "elapsed_time": "3:36:35", "remaining_time": "2:14:08", "throughput": 27965.61, "total_tokens": 363422336}
{"current_steps": 1820, "total_steps": 2931, "loss": 0.007371760904788971, "lr": 4.599171855691629e-05, "epoch": 1.863232, "percentage": 62.09, "elapsed_time": "3:37:53", "remaining_time": "2:13:00", "throughput": 27954.72, "total_tokens": 365459840}
{"current_steps": 1830, "total_steps": 2931, "loss": 0.007434654235839844, "lr": 4.597227420710335e-05, "epoch": 1.873472, "percentage": 62.44, "elapsed_time": "3:39:03", "remaining_time": "2:11:47", "throughput": 27957.82, "total_tokens": 367456320}
{"current_steps": 1840, "total_steps": 2931, "loss": 0.007234874367713928, "lr": 4.595285449846551e-05, "epoch": 1.883712, "percentage": 62.78, "elapsed_time": "3:40:11", "remaining_time": "2:10:33", "throughput": 27961.08, "total_tokens": 369417920}
{"current_steps": 1850, "total_steps": 2931, "loss": 0.007048602402210236, "lr": 4.593345937900178e-05, "epoch": 1.893952, "percentage": 63.12, "elapsed_time": "3:41:22", "remaining_time": "2:09:21", "throughput": 27964.98, "total_tokens": 371435072}
{"current_steps": 1860, "total_steps": 2931, "loss": 0.007115562260150909, "lr": 4.591408879686472e-05, "epoch": 1.904192, "percentage": 63.46, "elapsed_time": "3:42:29", "remaining_time": "2:08:06", "throughput": 27972.84, "total_tokens": 373413504}
{"current_steps": 1870, "total_steps": 2931, "loss": 0.0069166868925094604, "lr": 4.5894742700359775e-05, "epoch": 1.9144320000000001, "percentage": 63.8, "elapsed_time": "3:43:43", "remaining_time": "2:06:56", "throughput": 27969.83, "total_tokens": 375452096}
{"current_steps": 1880, "total_steps": 2931, "loss": 0.006946581602096558, "lr": 4.587542103794477e-05, "epoch": 1.9246720000000002, "percentage": 64.14, "elapsed_time": "3:44:54", "remaining_time": "2:05:43", "throughput": 27971.42, "total_tokens": 377457408}
{"current_steps": 1890, "total_steps": 2931, "loss": 0.006722895056009292, "lr": 4.5856123758229247e-05, "epoch": 1.934912, "percentage": 64.48, "elapsed_time": "3:46:04", "remaining_time": "2:04:31", "throughput": 27974.22, "total_tokens": 379465216}
{"current_steps": 1900, "total_steps": 2931, "loss": 0.006712291389703751, "lr": 4.5836850809973993e-05, "epoch": 1.945152, "percentage": 64.82, "elapsed_time": "3:47:13", "remaining_time": "2:03:17", "throughput": 27978.54, "total_tokens": 381443840}
{"current_steps": 1910, "total_steps": 2931, "loss": 0.006593970954418183, "lr": 4.5817602142090385e-05, "epoch": 1.955392, "percentage": 65.17, "elapsed_time": "3:48:28", "remaining_time": "2:02:07", "throughput": 27974.56, "total_tokens": 383492032}
{"current_steps": 1920, "total_steps": 2931, "loss": 0.006644654273986817, "lr": 4.579837770363989e-05, "epoch": 1.965632, "percentage": 65.51, "elapsed_time": "3:49:41", "remaining_time": "2:00:57", "throughput": 27973.18, "total_tokens": 385522624}
{"current_steps": 1930, "total_steps": 2931, "loss": 0.006544043123722076, "lr": 4.57791774438334e-05, "epoch": 1.9758719999999999, "percentage": 65.85, "elapsed_time": "3:50:56", "remaining_time": "1:59:46", "throughput": 27968.56, "total_tokens": 387554240}
{"current_steps": 1940, "total_steps": 2931, "loss": 0.006355230510234833, "lr": 4.576000131203078e-05, "epoch": 1.9861119999999999, "percentage": 66.19, "elapsed_time": "3:52:08", "remaining_time": "1:58:35", "throughput": 27967.76, "total_tokens": 389552960}
{"current_steps": 1950, "total_steps": 2931, "loss": 0.006281337141990662, "lr": 4.574084925774023e-05, "epoch": 1.996352, "percentage": 66.53, "elapsed_time": "3:53:22", "remaining_time": "1:57:24", "throughput": 27964.44, "total_tokens": 391574656}
{"current_steps": 1960, "total_steps": 2931, "loss": 0.005665350705385208, "lr": 4.5721721230617795e-05, "epoch": 2.006144, "percentage": 66.87, "elapsed_time": "3:54:32", "remaining_time": "1:56:11", "throughput": 27964.29, "total_tokens": 393515200}
{"current_steps": 1970, "total_steps": 2931, "loss": 0.00525745153427124, "lr": 4.57026171804667e-05, "epoch": 2.016384, "percentage": 67.21, "elapsed_time": "3:55:44", "remaining_time": "1:54:59", "throughput": 27964.37, "total_tokens": 395529664}
{"current_steps": 1980, "total_steps": 2931, "loss": 0.005201469361782074, "lr": 4.568353705723692e-05, "epoch": 2.026624, "percentage": 67.55, "elapsed_time": "3:56:50", "remaining_time": "1:53:45", "throughput": 27972.15, "total_tokens": 397487424}
{"current_steps": 1990, "total_steps": 2931, "loss": 0.005276227742433548, "lr": 4.566448081102455e-05, "epoch": 2.036864, "percentage": 67.89, "elapsed_time": "3:58:02", "remaining_time": "1:52:33", "throughput": 27971.6, "total_tokens": 399499776}
{"current_steps": 2000, "total_steps": 2931, "loss": 0.005213438719511032, "lr": 4.564544839207128e-05, "epoch": 2.047104, "percentage": 68.24, "elapsed_time": "3:59:13", "remaining_time": "1:51:21", "throughput": 27972.73, "total_tokens": 401505216}
{"current_steps": 2010, "total_steps": 2931, "loss": 0.005236967653036118, "lr": 4.562643975076387e-05, "epoch": 2.057344, "percentage": 68.58, "elapsed_time": "4:00:24", "remaining_time": "1:50:09", "throughput": 27973.74, "total_tokens": 403493888}
{"current_steps": 2020, "total_steps": 2931, "loss": 0.0052146721631288525, "lr": 4.560745483763357e-05, "epoch": 2.067584, "percentage": 68.92, "elapsed_time": "4:01:34", "remaining_time": "1:48:56", "throughput": 27975.53, "total_tokens": 405488704}
{"current_steps": 2030, "total_steps": 2931, "loss": 0.005139049887657165, "lr": 4.5588493603355595e-05, "epoch": 2.077824, "percentage": 69.26, "elapsed_time": "4:02:44", "remaining_time": "1:47:44", "throughput": 27975.96, "total_tokens": 407464640}
{"current_steps": 2040, "total_steps": 2931, "loss": 0.005121592432260513, "lr": 4.556955599874859e-05, "epoch": 2.088064, "percentage": 69.6, "elapsed_time": "4:03:53", "remaining_time": "1:46:31", "throughput": 27980.59, "total_tokens": 409450432}
{"current_steps": 2050, "total_steps": 2931, "loss": 0.0051218770444393154, "lr": 4.555064197477409e-05, "epoch": 2.098304, "percentage": 69.94, "elapsed_time": "4:05:06", "remaining_time": "1:45:20", "throughput": 27977.51, "total_tokens": 411460480}
{"current_steps": 2060, "total_steps": 2931, "loss": 0.005105789378285408, "lr": 4.5531751482536e-05, "epoch": 2.108544, "percentage": 70.28, "elapsed_time": "4:06:17", "remaining_time": "1:44:07", "throughput": 27979.28, "total_tokens": 413451776}
{"current_steps": 2070, "total_steps": 2931, "loss": 0.005103696137666702, "lr": 4.5512884473280024e-05, "epoch": 2.118784, "percentage": 70.62, "elapsed_time": "4:07:29", "remaining_time": "1:42:56", "throughput": 27978.14, "total_tokens": 415470592}
{"current_steps": 2080, "total_steps": 2931, "loss": 0.005021055787801742, "lr": 4.549404089839322e-05, "epoch": 2.129024, "percentage": 70.97, "elapsed_time": "4:08:41", "remaining_time": "1:41:45", "throughput": 27976.56, "total_tokens": 417460160}
{"current_steps": 2090, "total_steps": 2931, "loss": 0.005071662366390228, "lr": 4.547522070940335e-05, "epoch": 2.139264, "percentage": 71.31, "elapsed_time": "4:09:52", "remaining_time": "1:40:32", "throughput": 27978.19, "total_tokens": 419456640}
{"current_steps": 2100, "total_steps": 2931, "loss": 0.005032730847597122, "lr": 4.545642385797848e-05, "epoch": 2.149504, "percentage": 71.65, "elapsed_time": "4:11:06", "remaining_time": "1:39:22", "throughput": 27974.18, "total_tokens": 421486912}
{"current_steps": 2110, "total_steps": 2931, "loss": 0.00504358783364296, "lr": 4.543765029592637e-05, "epoch": 2.159744, "percentage": 71.99, "elapsed_time": "4:12:25", "remaining_time": "1:38:12", "throughput": 27965.67, "total_tokens": 423541056}
{"current_steps": 2120, "total_steps": 2931, "loss": 0.0049100361764431, "lr": 4.541889997519403e-05, "epoch": 2.169984, "percentage": 72.33, "elapsed_time": "4:13:32", "remaining_time": "1:36:59", "throughput": 27971.32, "total_tokens": 425501760}
{"current_steps": 2130, "total_steps": 2931, "loss": 0.005002960935235024, "lr": 4.5400172847867095e-05, "epoch": 2.180224, "percentage": 72.67, "elapsed_time": "4:14:39", "remaining_time": "1:35:45", "throughput": 27976.88, "total_tokens": 427472320}
{"current_steps": 2140, "total_steps": 2931, "loss": 0.005049411952495575, "lr": 4.5381468866169466e-05, "epoch": 2.190464, "percentage": 73.01, "elapsed_time": "4:15:49", "remaining_time": "1:34:33", "throughput": 27979.98, "total_tokens": 429492544}
{"current_steps": 2150, "total_steps": 2931, "loss": 0.004954206943511963, "lr": 4.5362787982462616e-05, "epoch": 2.200704, "percentage": 73.35, "elapsed_time": "4:16:57", "remaining_time": "1:33:20", "throughput": 27986.62, "total_tokens": 431474560}
{"current_steps": 2160, "total_steps": 2931, "loss": 0.004945812746882439, "lr": 4.5344130149245275e-05, "epoch": 2.210944, "percentage": 73.69, "elapsed_time": "4:18:07", "remaining_time": "1:32:08", "throughput": 27989.3, "total_tokens": 433476224}
{"current_steps": 2170, "total_steps": 2931, "loss": 0.004998266696929932, "lr": 4.5325495319152715e-05, "epoch": 2.221184, "percentage": 74.04, "elapsed_time": "4:19:18", "remaining_time": "1:30:56", "throughput": 27991.99, "total_tokens": 435507776}
{"current_steps": 2180, "total_steps": 2931, "loss": 0.00497533455491066, "lr": 4.530688344495644e-05, "epoch": 2.231424, "percentage": 74.38, "elapsed_time": "4:20:34", "remaining_time": "1:29:45", "throughput": 27987.1, "total_tokens": 437550336}
{"current_steps": 2190, "total_steps": 2931, "loss": 0.004857704415917397, "lr": 4.528829447956357e-05, "epoch": 2.241664, "percentage": 74.72, "elapsed_time": "4:21:40", "remaining_time": "1:28:32", "throughput": 27993.7, "total_tokens": 439513280}
{"current_steps": 2200, "total_steps": 2931, "loss": 0.004866150766611099, "lr": 4.526972837601633e-05, "epoch": 2.251904, "percentage": 75.06, "elapsed_time": "4:22:51", "remaining_time": "1:27:20", "throughput": 27993.71, "total_tokens": 441508032}
{"current_steps": 2210, "total_steps": 2931, "loss": 0.004855437949299812, "lr": 4.525118508749165e-05, "epoch": 2.262144, "percentage": 75.4, "elapsed_time": "4:24:00", "remaining_time": "1:26:07", "throughput": 27997.09, "total_tokens": 443485504}
{"current_steps": 2220, "total_steps": 2931, "loss": 0.0049121581017971035, "lr": 4.5232664567300546e-05, "epoch": 2.272384, "percentage": 75.74, "elapsed_time": "4:25:12", "remaining_time": "1:24:56", "throughput": 27996.52, "total_tokens": 445490048}
{"current_steps": 2230, "total_steps": 2931, "loss": 0.004935600981116295, "lr": 4.521416676888773e-05, "epoch": 2.282624, "percentage": 76.08, "elapsed_time": "4:26:24", "remaining_time": "1:23:44", "throughput": 27995.98, "total_tokens": 447501248}
{"current_steps": 2240, "total_steps": 2931, "loss": 0.004881329089403153, "lr": 4.519569164583107e-05, "epoch": 2.292864, "percentage": 76.42, "elapsed_time": "4:27:36", "remaining_time": "1:22:33", "throughput": 27995.42, "total_tokens": 449501312}
{"current_steps": 2250, "total_steps": 2931, "loss": 0.004859179258346558, "lr": 4.517723915184109e-05, "epoch": 2.303104, "percentage": 76.77, "elapsed_time": "4:28:50", "remaining_time": "1:21:22", "throughput": 27992.11, "total_tokens": 451525888}
{"current_steps": 2260, "total_steps": 2931, "loss": 0.0048702418804168705, "lr": 4.5158809240760506e-05, "epoch": 2.313344, "percentage": 77.11, "elapsed_time": "4:30:03", "remaining_time": "1:20:10", "throughput": 27990.94, "total_tokens": 453539456}
{"current_steps": 2270, "total_steps": 2931, "loss": 0.004770452529191971, "lr": 4.514040186656375e-05, "epoch": 2.323584, "percentage": 77.45, "elapsed_time": "4:31:15", "remaining_time": "1:18:59", "throughput": 27989.01, "total_tokens": 455540800}
{"current_steps": 2280, "total_steps": 2931, "loss": 0.004840082675218582, "lr": 4.512201698335644e-05, "epoch": 2.333824, "percentage": 77.79, "elapsed_time": "4:32:26", "remaining_time": "1:17:47", "throughput": 27989.76, "total_tokens": 457537984}
{"current_steps": 2290, "total_steps": 2931, "loss": 0.004802238196134567, "lr": 4.510365454537496e-05, "epoch": 2.344064, "percentage": 78.13, "elapsed_time": "4:33:34", "remaining_time": "1:16:34", "throughput": 27994.07, "total_tokens": 459519040}
{"current_steps": 2300, "total_steps": 2931, "loss": 0.0047688383609056475, "lr": 4.5085314506985945e-05, "epoch": 2.354304, "percentage": 78.47, "elapsed_time": "4:34:44", "remaining_time": "1:15:22", "throughput": 27996.36, "total_tokens": 461504320}
{"current_steps": 2310, "total_steps": 2931, "loss": 0.004731994122266769, "lr": 4.50669968226858e-05, "epoch": 2.364544, "percentage": 78.81, "elapsed_time": "4:35:52", "remaining_time": "1:14:09", "throughput": 28000.76, "total_tokens": 463484608}
{"current_steps": 2320, "total_steps": 2931, "loss": 0.004760279133915901, "lr": 4.504870144710027e-05, "epoch": 2.374784, "percentage": 79.15, "elapsed_time": "4:37:03", "remaining_time": "1:12:57", "throughput": 28001.43, "total_tokens": 465478912}
{"current_steps": 2330, "total_steps": 2931, "loss": 0.004723610356450081, "lr": 4.5030428334983884e-05, "epoch": 2.385024, "percentage": 79.5, "elapsed_time": "4:38:19", "remaining_time": "1:11:47", "throughput": 27998.5, "total_tokens": 467551232}
{"current_steps": 2340, "total_steps": 2931, "loss": 0.004661402851343155, "lr": 4.501217744121959e-05, "epoch": 2.395264, "percentage": 79.84, "elapsed_time": "4:39:33", "remaining_time": "1:10:36", "throughput": 27994.72, "total_tokens": 469581568}
{"current_steps": 2350, "total_steps": 2931, "loss": 0.004748685657978058, "lr": 4.499394872081821e-05, "epoch": 2.405504, "percentage": 80.18, "elapsed_time": "4:40:45", "remaining_time": "1:09:24", "throughput": 27995.1, "total_tokens": 471585152}
{"current_steps": 2360, "total_steps": 2931, "loss": 0.004757498577237129, "lr": 4.4975742128918e-05, "epoch": 2.415744, "percentage": 80.52, "elapsed_time": "4:41:55", "remaining_time": "1:08:12", "throughput": 27996.78, "total_tokens": 473578176}
{"current_steps": 2370, "total_steps": 2931, "loss": 0.004699341207742691, "lr": 4.495755762078418e-05, "epoch": 2.425984, "percentage": 80.86, "elapsed_time": "4:43:09", "remaining_time": "1:07:01", "throughput": 27993.71, "total_tokens": 475608960}
{"current_steps": 2380, "total_steps": 2931, "loss": 0.004687727242708206, "lr": 4.49393951518085e-05, "epoch": 2.436224, "percentage": 81.2, "elapsed_time": "4:44:26", "remaining_time": "1:05:51", "throughput": 27989.1, "total_tokens": 477675968}
{"current_steps": 2390, "total_steps": 2931, "loss": 0.004727355390787125, "lr": 4.4921254677508716e-05, "epoch": 2.446464, "percentage": 81.54, "elapsed_time": "4:45:37", "remaining_time": "1:04:39", "throughput": 27990.86, "total_tokens": 479688000}
{"current_steps": 2400, "total_steps": 2931, "loss": 0.004683735221624375, "lr": 4.490313615352821e-05, "epoch": 2.456704, "percentage": 81.88, "elapsed_time": "4:46:50", "remaining_time": "1:03:27", "throughput": 27989.53, "total_tokens": 481709440}
{"current_steps": 2410, "total_steps": 2931, "loss": 0.0046593818813562395, "lr": 4.48850395356355e-05, "epoch": 2.466944, "percentage": 82.22, "elapsed_time": "4:48:02", "remaining_time": "1:02:16", "throughput": 27988.63, "total_tokens": 483715648}
{"current_steps": 2420, "total_steps": 2931, "loss": 0.004705347865819931, "lr": 4.486696477972375e-05, "epoch": 2.477184, "percentage": 82.57, "elapsed_time": "4:49:16", "remaining_time": "1:01:04", "throughput": 27986.2, "total_tokens": 485743040}
{"current_steps": 2430, "total_steps": 2931, "loss": 0.004584659263491631, "lr": 4.484891184181041e-05, "epoch": 2.487424, "percentage": 82.91, "elapsed_time": "4:50:29", "remaining_time": "0:59:53", "throughput": 27984.83, "total_tokens": 487766208}
{"current_steps": 2440, "total_steps": 2931, "loss": 0.0046070806682109834, "lr": 4.483088067803662e-05, "epoch": 2.497664, "percentage": 83.25, "elapsed_time": "4:51:45", "remaining_time": "0:58:42", "throughput": 27980.31, "total_tokens": 489803136}
{"current_steps": 2450, "total_steps": 2931, "loss": 0.004666749015450477, "lr": 4.481287124466697e-05, "epoch": 2.507904, "percentage": 83.59, "elapsed_time": "4:52:52", "remaining_time": "0:57:29", "throughput": 27985.13, "total_tokens": 491769280}
{"current_steps": 2460, "total_steps": 2931, "loss": 0.0045741736888885495, "lr": 4.479488349808885e-05, "epoch": 2.518144, "percentage": 83.93, "elapsed_time": "4:54:00", "remaining_time": "0:56:17", "throughput": 27990.38, "total_tokens": 493764288}
{"current_steps": 2470, "total_steps": 2931, "loss": 0.004661215096712112, "lr": 4.4776917394812114e-05, "epoch": 2.528384, "percentage": 84.27, "elapsed_time": "4:55:12", "remaining_time": "0:55:05", "throughput": 27989.1, "total_tokens": 495765184}
{"current_steps": 2480, "total_steps": 2931, "loss": 0.004575810208916664, "lr": 4.475897289146862e-05, "epoch": 2.538624, "percentage": 84.61, "elapsed_time": "4:56:26", "remaining_time": "0:53:54", "throughput": 27987.01, "total_tokens": 497788736}
{"current_steps": 2490, "total_steps": 2931, "loss": 0.0045924406498670575, "lr": 4.4741049944811806e-05, "epoch": 2.548864, "percentage": 84.95, "elapsed_time": "4:57:39", "remaining_time": "0:52:42", "throughput": 27986.34, "total_tokens": 499810304}
{"current_steps": 2500, "total_steps": 2931, "loss": 0.004592006653547287, "lr": 4.472314851171621e-05, "epoch": 2.559104, "percentage": 85.3, "elapsed_time": "4:58:48", "remaining_time": "0:51:30", "throughput": 27988.3, "total_tokens": 501800576}
{"current_steps": 2510, "total_steps": 2931, "loss": 0.004537731781601906, "lr": 4.4705268549177084e-05, "epoch": 2.569344, "percentage": 85.64, "elapsed_time": "5:00:00", "remaining_time": "0:50:19", "throughput": 27987.34, "total_tokens": 503798656}
{"current_steps": 2520, "total_steps": 2931, "loss": 0.004587111622095108, "lr": 4.468741001430989e-05, "epoch": 2.579584, "percentage": 85.98, "elapsed_time": "5:01:10", "remaining_time": "0:49:07", "throughput": 27989.38, "total_tokens": 505787584}
{"current_steps": 2530, "total_steps": 2931, "loss": 0.004565178602933884, "lr": 4.466957286434997e-05, "epoch": 2.589824, "percentage": 86.32, "elapsed_time": "5:02:19", "remaining_time": "0:47:55", "throughput": 27992.4, "total_tokens": 507778304}
{"current_steps": 2540, "total_steps": 2931, "loss": 0.004532522708177567, "lr": 4.4651757056652e-05, "epoch": 2.600064, "percentage": 86.66, "elapsed_time": "5:03:30", "remaining_time": "0:46:43", "throughput": 27993.26, "total_tokens": 509777024}
{"current_steps": 2550, "total_steps": 2931, "loss": 0.004580499976873398, "lr": 4.463396254868968e-05, "epoch": 2.610304, "percentage": 87.0, "elapsed_time": "5:04:45", "remaining_time": "0:45:32", "throughput": 27989.96, "total_tokens": 511806464}
{"current_steps": 2560, "total_steps": 2931, "loss": 0.0044912703335285185, "lr": 4.461618929805519e-05, "epoch": 2.6205439999999998, "percentage": 87.34, "elapsed_time": "5:05:55", "remaining_time": "0:44:20", "throughput": 27991.62, "total_tokens": 513789760}
{"current_steps": 2570, "total_steps": 2931, "loss": 0.0045277226716279985, "lr": 4.459843726245888e-05, "epoch": 2.6307840000000002, "percentage": 87.68, "elapsed_time": "5:07:09", "remaining_time": "0:43:08", "throughput": 27989.61, "total_tokens": 515820928}
{"current_steps": 2580, "total_steps": 2931, "loss": 0.004519717395305633, "lr": 4.458070639972875e-05, "epoch": 2.641024, "percentage": 88.02, "elapsed_time": "5:08:22", "remaining_time": "0:41:57", "throughput": 27988.42, "total_tokens": 517852160}
{"current_steps": 2590, "total_steps": 2931, "loss": 0.004499278962612152, "lr": 4.456299666781007e-05, "epoch": 2.651264, "percentage": 88.37, "elapsed_time": "5:09:31", "remaining_time": "0:40:45", "throughput": 27991.21, "total_tokens": 519837056}
{"current_steps": 2600, "total_steps": 2931, "loss": 0.004471401870250702, "lr": 4.4545308024764984e-05, "epoch": 2.661504, "percentage": 88.71, "elapsed_time": "5:10:41", "remaining_time": "0:39:33", "throughput": 27992.39, "total_tokens": 521829760}
{"current_steps": 2610, "total_steps": 2931, "loss": 0.004468469694256782, "lr": 4.452764042877207e-05, "epoch": 2.671744, "percentage": 89.05, "elapsed_time": "5:11:54", "remaining_time": "0:38:21", "throughput": 27992.53, "total_tokens": 523852928}
{"current_steps": 2620, "total_steps": 2931, "loss": 0.0044468618929386135, "lr": 4.45099938381259e-05, "epoch": 2.681984, "percentage": 89.39, "elapsed_time": "5:13:05", "remaining_time": "0:37:09", "throughput": 27993.53, "total_tokens": 525863616}
{"current_steps": 2630, "total_steps": 2931, "loss": 0.004445591568946838, "lr": 4.449236821123667e-05, "epoch": 2.692224, "percentage": 89.73, "elapsed_time": "5:14:16", "remaining_time": "0:35:58", "throughput": 27994.27, "total_tokens": 527876672}
{"current_steps": 2640, "total_steps": 2931, "loss": 0.004489725083112716, "lr": 4.447476350662976e-05, "epoch": 2.702464, "percentage": 90.07, "elapsed_time": "5:15:24", "remaining_time": "0:34:45", "throughput": 27998.37, "total_tokens": 529852736}
{"current_steps": 2650, "total_steps": 2931, "loss": 0.004479191452264786, "lr": 4.4457179682945346e-05, "epoch": 2.712704, "percentage": 90.41, "elapsed_time": "5:16:36", "remaining_time": "0:33:34", "throughput": 27998.03, "total_tokens": 531877632}
{"current_steps": 2660, "total_steps": 2931, "loss": 0.004402218014001846, "lr": 4.443961669893798e-05, "epoch": 2.722944, "percentage": 90.75, "elapsed_time": "5:17:50", "remaining_time": "0:32:22", "throughput": 27996.67, "total_tokens": 533900416}
{"current_steps": 2670, "total_steps": 2931, "loss": 0.004445427656173706, "lr": 4.4422074513476155e-05, "epoch": 2.733184, "percentage": 91.1, "elapsed_time": "5:19:01", "remaining_time": "0:31:11", "throughput": 27998.16, "total_tokens": 535930112}
{"current_steps": 2680, "total_steps": 2931, "loss": 0.004417391866445542, "lr": 4.4404553085541955e-05, "epoch": 2.743424, "percentage": 91.44, "elapsed_time": "5:20:12", "remaining_time": "0:29:59", "throughput": 27998.29, "total_tokens": 537917952}
{"current_steps": 2690, "total_steps": 2931, "loss": 0.004418341070413589, "lr": 4.438705237423063e-05, "epoch": 2.753664, "percentage": 91.78, "elapsed_time": "5:21:24", "remaining_time": "0:28:47", "throughput": 27998.45, "total_tokens": 539928000}
{"current_steps": 2700, "total_steps": 2931, "loss": 0.00445760264992714, "lr": 4.436957233875017e-05, "epoch": 2.763904, "percentage": 92.12, "elapsed_time": "5:22:41", "remaining_time": "0:27:36", "throughput": 27993.63, "total_tokens": 541990336}
{"current_steps": 2710, "total_steps": 2931, "loss": 0.00442219078540802, "lr": 4.4352112938420956e-05, "epoch": 2.774144, "percentage": 92.46, "elapsed_time": "5:23:54", "remaining_time": "0:26:24", "throughput": 27991.44, "total_tokens": 543993664}
{"current_steps": 2720, "total_steps": 2931, "loss": 0.004379033669829368, "lr": 4.433467413267529e-05, "epoch": 2.784384, "percentage": 92.8, "elapsed_time": "5:25:01", "remaining_time": "0:25:12", "throughput": 27995.61, "total_tokens": 545968128}
{"current_steps": 2730, "total_steps": 2931, "loss": 0.00442984439432621, "lr": 4.431725588105708e-05, "epoch": 2.7946239999999998, "percentage": 93.14, "elapsed_time": "5:26:15", "remaining_time": "0:24:01", "throughput": 27993.6, "total_tokens": 547993536}
{"current_steps": 2740, "total_steps": 2931, "loss": 0.004416907578706742, "lr": 4.4299858143221377e-05, "epoch": 2.8048640000000002, "percentage": 93.48, "elapsed_time": "5:27:26", "remaining_time": "0:22:49", "throughput": 27994.26, "total_tokens": 549978176}
{"current_steps": 2750, "total_steps": 2931, "loss": 0.004360169917345047, "lr": 4.4282480878934065e-05, "epoch": 2.815104, "percentage": 93.82, "elapsed_time": "5:28:35", "remaining_time": "0:21:37", "throughput": 27996.63, "total_tokens": 551979968}
{"current_steps": 2760, "total_steps": 2931, "loss": 0.00443723276257515, "lr": 4.4265124048071346e-05, "epoch": 2.825344, "percentage": 94.17, "elapsed_time": "5:29:50", "remaining_time": "0:20:26", "throughput": 27994.08, "total_tokens": 554008768}
{"current_steps": 2770, "total_steps": 2931, "loss": 0.004331726580858231, "lr": 4.4247787610619477e-05, "epoch": 2.835584, "percentage": 94.51, "elapsed_time": "5:31:01", "remaining_time": "0:19:14", "throughput": 27994.59, "total_tokens": 556008704}
{"current_steps": 2780, "total_steps": 2931, "loss": 0.004372353851795197, "lr": 4.42304715266743e-05, "epoch": 2.845824, "percentage": 94.85, "elapsed_time": "5:32:13", "remaining_time": "0:18:02", "throughput": 27993.37, "total_tokens": 557996544}
{"current_steps": 2790, "total_steps": 2931, "loss": 0.004349645972251892, "lr": 4.421317575644092e-05, "epoch": 2.856064, "percentage": 95.19, "elapsed_time": "5:33:23", "remaining_time": "0:16:50", "throughput": 27994.37, "total_tokens": 559980992}
{"current_steps": 2800, "total_steps": 2931, "loss": 0.004384344071149826, "lr": 4.419590026023325e-05, "epoch": 2.866304, "percentage": 95.53, "elapsed_time": "5:34:34", "remaining_time": "0:15:39", "throughput": 27995.18, "total_tokens": 561990848}
{"current_steps": 2810, "total_steps": 2931, "loss": 0.004311569407582283, "lr": 4.417864499847368e-05, "epoch": 2.876544, "percentage": 95.87, "elapsed_time": "5:35:46", "remaining_time": "0:14:27", "throughput": 27995.6, "total_tokens": 564012800}
{"current_steps": 2820, "total_steps": 2931, "loss": 0.004370152205228806, "lr": 4.4161409931692676e-05, "epoch": 2.886784, "percentage": 96.21, "elapsed_time": "5:36:55", "remaining_time": "0:13:15", "throughput": 27998.38, "total_tokens": 566014592}
{"current_steps": 2830, "total_steps": 2931, "loss": 0.004308675229549408, "lr": 4.414419502052841e-05, "epoch": 2.897024, "percentage": 96.55, "elapsed_time": "5:38:11", "remaining_time": "0:12:04", "throughput": 27994.89, "total_tokens": 568045312}
{"current_steps": 2840, "total_steps": 2931, "loss": 0.0044147070497274395, "lr": 4.412700022572637e-05, "epoch": 2.907264, "percentage": 96.9, "elapsed_time": "5:39:25", "remaining_time": "0:10:52", "throughput": 27992.82, "total_tokens": 570100864}
{"current_steps": 2850, "total_steps": 2931, "loss": 0.004334438592195511, "lr": 4.410982550813902e-05, "epoch": 2.917504, "percentage": 97.24, "elapsed_time": "5:40:34", "remaining_time": "0:09:40", "throughput": 27996.74, "total_tokens": 572089472}
{"current_steps": 2860, "total_steps": 2931, "loss": 0.004324203729629517, "lr": 4.409267082872535e-05, "epoch": 2.927744, "percentage": 97.58, "elapsed_time": "5:41:47", "remaining_time": "0:08:29", "throughput": 27995.25, "total_tokens": 574117952}
{"current_steps": 2870, "total_steps": 2931, "loss": 0.0042998895049095156, "lr": 4.407553614855059e-05, "epoch": 2.937984, "percentage": 97.92, "elapsed_time": "5:43:01", "remaining_time": "0:07:17", "throughput": 27992.22, "total_tokens": 576123392}
{"current_steps": 2880, "total_steps": 2931, "loss": 0.004281196743249893, "lr": 4.405842142878579e-05, "epoch": 2.9482239999999997, "percentage": 98.26, "elapsed_time": "5:44:13", "remaining_time": "0:06:05", "throughput": 27992.58, "total_tokens": 578142144}
{"current_steps": 2890, "total_steps": 2931, "loss": 0.004318735748529434, "lr": 4.404132663070745e-05, "epoch": 2.958464, "percentage": 98.6, "elapsed_time": "5:45:24", "remaining_time": "0:04:54", "throughput": 27993.2, "total_tokens": 580136512}
{"current_steps": 2900, "total_steps": 2931, "loss": 0.004320795089006424, "lr": 4.402425171569716e-05, "epoch": 2.968704, "percentage": 98.94, "elapsed_time": "5:46:39", "remaining_time": "0:03:42", "throughput": 27990.45, "total_tokens": 582175680}
{"current_steps": 2910, "total_steps": 2931, "loss": 0.004287149757146835, "lr": 4.400719664524127e-05, "epoch": 2.9789440000000003, "percentage": 99.28, "elapsed_time": "5:47:51", "remaining_time": "0:02:30", "throughput": 27990.02, "total_tokens": 584189120}
{"current_steps": 2920, "total_steps": 2931, "loss": 0.0043055802583694455, "lr": 4.399016138093044e-05, "epoch": 2.989184, "percentage": 99.62, "elapsed_time": "5:49:05", "remaining_time": "0:01:18", "throughput": 27988.27, "total_tokens": 586222400}
{"current_steps": 2930, "total_steps": 2931, "loss": 0.004327042400836945, "lr": 4.397314588445937e-05, "epoch": 2.999424, "percentage": 99.97, "elapsed_time": "5:50:20", "remaining_time": "0:00:07", "throughput": 27985.12, "total_tokens": 588266880}
{"current_steps": 2931, "total_steps": 2931, "eval_loss": 1.456993818283081, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "5:50:26", "remaining_time": "0:00:00", "throughput": 27982.57, "total_tokens": 588389376}
{"current_steps": 2931, "total_steps": 2931, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "5:50:47", "remaining_time": "0:00:00", "throughput": 27954.82, "total_tokens": 588389376}