Terminal-dependency_management / trainer_log.jsonl
cuong1692001's picture
Upload folder using huggingface_hub
6443b14 verified
Raw
History Blame Contribute Delete
248 kB
{"current_steps": 5, "total_steps": 12420, "loss": 0.8469, "lr": 9.999997440727632e-06, "epoch": 0.002012882447665056, "percentage": 0.04, "elapsed_time": "0:00:55", "remaining_time": "1 day, 14:06:22", "throughput": 5973.12, "total_tokens": 330008}
{"current_steps": 10, "total_steps": 12420, "loss": 0.7136, "lr": 9.99998704368812e-06, "epoch": 0.004025764895330112, "percentage": 0.08, "elapsed_time": "0:01:49", "remaining_time": "1 day, 13:49:48", "throughput": 5729.22, "total_tokens": 628728}
{"current_steps": 15, "total_steps": 12420, "loss": 0.6434, "lr": 9.99996864894356e-06, "epoch": 0.006038647342995169, "percentage": 0.12, "elapsed_time": "0:02:51", "remaining_time": "1 day, 15:20:47", "throughput": 5309.51, "total_tokens": 909408}
{"current_steps": 20, "total_steps": 12420, "loss": 0.6388, "lr": 9.999942256523378e-06, "epoch": 0.008051529790660225, "percentage": 0.16, "elapsed_time": "0:04:08", "remaining_time": "1 day, 18:48:59", "throughput": 4978.33, "total_tokens": 1237672}
{"current_steps": 25, "total_steps": 12420, "loss": 0.5767, "lr": 9.999907866469787e-06, "epoch": 0.010064412238325281, "percentage": 0.2, "elapsed_time": "0:05:12", "remaining_time": "1 day, 19:01:18", "throughput": 4942.91, "total_tokens": 1544072}
{"current_steps": 30, "total_steps": 12420, "loss": 0.5902, "lr": 9.999865478837796e-06, "epoch": 0.012077294685990338, "percentage": 0.24, "elapsed_time": "0:06:18", "remaining_time": "1 day, 19:24:14", "throughput": 4866.89, "total_tokens": 1841344}
{"current_steps": 35, "total_steps": 12420, "loss": 0.5832, "lr": 9.999815093695206e-06, "epoch": 0.014090177133655395, "percentage": 0.28, "elapsed_time": "0:07:20", "remaining_time": "1 day, 19:18:32", "throughput": 4849.06, "total_tokens": 2136536}
{"current_steps": 40, "total_steps": 12420, "loss": 0.5639, "lr": 9.999756711122613e-06, "epoch": 0.01610305958132045, "percentage": 0.32, "elapsed_time": "0:08:26", "remaining_time": "1 day, 19:31:11", "throughput": 4887.71, "total_tokens": 2474192}
{"current_steps": 45, "total_steps": 12420, "loss": 0.5584, "lr": 9.999690331213397e-06, "epoch": 0.018115942028985508, "percentage": 0.36, "elapsed_time": "0:09:26", "remaining_time": "1 day, 19:16:00", "throughput": 4913.09, "total_tokens": 2782792}
{"current_steps": 50, "total_steps": 12420, "loss": 0.58, "lr": 9.99961595407374e-06, "epoch": 0.020128824476650563, "percentage": 0.4, "elapsed_time": "0:10:16", "remaining_time": "1 day, 18:21:49", "throughput": 5019.27, "total_tokens": 3094136}
{"current_steps": 55, "total_steps": 12420, "loss": 0.5655, "lr": 9.999533579822611e-06, "epoch": 0.02214170692431562, "percentage": 0.44, "elapsed_time": "0:11:43", "remaining_time": "1 day, 19:56:20", "throughput": 4910.61, "total_tokens": 3455064}
{"current_steps": 60, "total_steps": 12420, "loss": 0.5049, "lr": 9.99944320859177e-06, "epoch": 0.024154589371980676, "percentage": 0.48, "elapsed_time": "0:12:38", "remaining_time": "1 day, 19:23:45", "throughput": 4935.94, "total_tokens": 3743304}
{"current_steps": 5, "total_steps": 4968, "loss": 0.8671, "lr": 9.999984004554854e-06, "epoch": 0.002012882447665056, "percentage": 0.1, "elapsed_time": "0:00:41", "remaining_time": "11:23:06", "throughput": 7091.7, "total_tokens": 292832}
{"current_steps": 10, "total_steps": 4968, "loss": 0.7276, "lr": 9.999919023234347e-06, "epoch": 0.004025764895330112, "percentage": 0.2, "elapsed_time": "0:01:07", "remaining_time": "9:21:06", "throughput": 8319.77, "total_tokens": 564944}
{"current_steps": 15, "total_steps": 4968, "loss": 0.6581, "lr": 9.999804056972284e-06, "epoch": 0.006038647342995169, "percentage": 0.3, "elapsed_time": "0:01:36", "remaining_time": "8:52:07", "throughput": 8440.48, "total_tokens": 816128}
{"current_steps": 20, "total_steps": 4968, "loss": 0.6622, "lr": 9.999639106918003e-06, "epoch": 0.008051529790660225, "percentage": 0.4, "elapsed_time": "0:02:08", "remaining_time": "8:50:53", "throughput": 8538.34, "total_tokens": 1099328}
{"current_steps": 5, "total_steps": 4968, "loss": 0.867, "lr": 9.999984004554854e-06, "epoch": 0.002012882447665056, "percentage": 0.1, "elapsed_time": "0:00:39", "remaining_time": "10:56:47", "throughput": 7375.88, "total_tokens": 292832}
{"current_steps": 10, "total_steps": 4968, "loss": 0.7277, "lr": 9.999919023234347e-06, "epoch": 0.004025764895330112, "percentage": 0.2, "elapsed_time": "0:01:06", "remaining_time": "9:09:01", "throughput": 8502.93, "total_tokens": 564944}
{"current_steps": 15, "total_steps": 4968, "loss": 0.6583, "lr": 9.999804056972284e-06, "epoch": 0.006038647342995169, "percentage": 0.3, "elapsed_time": "0:01:35", "remaining_time": "8:42:57", "throughput": 8588.57, "total_tokens": 816128}
{"current_steps": 20, "total_steps": 4968, "loss": 0.6616, "lr": 9.999639106918003e-06, "epoch": 0.008051529790660225, "percentage": 0.4, "elapsed_time": "0:02:07", "remaining_time": "8:44:36", "throughput": 8640.64, "total_tokens": 1099328}
{"current_steps": 25, "total_steps": 4968, "loss": 0.5853, "lr": 9.99942417472053e-06, "epoch": 0.010064412238325281, "percentage": 0.5, "elapsed_time": "0:02:33", "remaining_time": "8:27:22", "throughput": 8924.2, "total_tokens": 1374032}
{"current_steps": 30, "total_steps": 4968, "loss": 0.604, "lr": 9.999159262528582e-06, "epoch": 0.012077294685990338, "percentage": 0.6, "elapsed_time": "0:02:58", "remaining_time": "8:09:16", "throughput": 9173.49, "total_tokens": 1636080}
{"current_steps": 35, "total_steps": 4968, "loss": 0.5905, "lr": 9.99884437299052e-06, "epoch": 0.014090177133655395, "percentage": 0.7, "elapsed_time": "0:03:21", "remaining_time": "7:52:48", "throughput": 9443.16, "total_tokens": 1900688}
{"current_steps": 40, "total_steps": 4968, "loss": 0.575, "lr": 9.998479509254341e-06, "epoch": 0.01610305958132045, "percentage": 0.81, "elapsed_time": "0:03:55", "remaining_time": "8:04:00", "throughput": 9331.48, "total_tokens": 2199616}
{"current_steps": 45, "total_steps": 4968, "loss": 0.5676, "lr": 9.998064674967647e-06, "epoch": 0.018115942028985508, "percentage": 0.91, "elapsed_time": "0:04:30", "remaining_time": "8:12:47", "throughput": 9163.1, "total_tokens": 2476496}
{"current_steps": 50, "total_steps": 4968, "loss": 0.5935, "lr": 9.997599874277596e-06, "epoch": 0.020128824476650563, "percentage": 1.01, "elapsed_time": "0:05:03", "remaining_time": "8:17:45", "throughput": 9093.44, "total_tokens": 2761112}
{"current_steps": 55, "total_steps": 4968, "loss": 0.5641, "lr": 9.99708511183087e-06, "epoch": 0.02214170692431562, "percentage": 1.11, "elapsed_time": "0:05:32", "remaining_time": "8:15:38", "throughput": 9197.43, "total_tokens": 3062000}
{"current_steps": 60, "total_steps": 4968, "loss": 0.5104, "lr": 9.99652039277363e-06, "epoch": 0.024154589371980676, "percentage": 1.21, "elapsed_time": "0:06:04", "remaining_time": "8:16:25", "throughput": 9143.56, "total_tokens": 3329408}
{"current_steps": 65, "total_steps": 4968, "loss": 0.554, "lr": 9.995905722751453e-06, "epoch": 0.026167471819645734, "percentage": 1.31, "elapsed_time": "0:06:36", "remaining_time": "8:18:14", "throughput": 9061.81, "total_tokens": 3591352}
{"current_steps": 70, "total_steps": 4968, "loss": 0.5112, "lr": 9.99524110790929e-06, "epoch": 0.02818035426731079, "percentage": 1.41, "elapsed_time": "0:07:02", "remaining_time": "8:13:13", "throughput": 9137.53, "total_tokens": 3864640}
{"current_steps": 75, "total_steps": 4968, "loss": 0.5092, "lr": 9.994526554891394e-06, "epoch": 0.030193236714975844, "percentage": 1.51, "elapsed_time": "0:07:35", "remaining_time": "8:15:07", "throughput": 9044.86, "total_tokens": 4118608}
{"current_steps": 80, "total_steps": 4968, "loss": 0.5149, "lr": 9.99376207084126e-06, "epoch": 0.0322061191626409, "percentage": 1.61, "elapsed_time": "0:08:00", "remaining_time": "8:09:34", "throughput": 9147.94, "total_tokens": 4397920}
{"current_steps": 85, "total_steps": 4968, "loss": 0.5463, "lr": 9.992947663401548e-06, "epoch": 0.03421900161030596, "percentage": 1.71, "elapsed_time": "0:08:32", "remaining_time": "8:10:58", "throughput": 9153.25, "total_tokens": 4693768}
{"current_steps": 90, "total_steps": 4968, "loss": 0.5106, "lr": 9.992083340714016e-06, "epoch": 0.036231884057971016, "percentage": 1.81, "elapsed_time": "0:09:04", "remaining_time": "8:12:10", "throughput": 9106.6, "total_tokens": 4961600}
{"current_steps": 95, "total_steps": 4968, "loss": 0.5364, "lr": 9.991169111419422e-06, "epoch": 0.038244766505636074, "percentage": 1.91, "elapsed_time": "0:09:42", "remaining_time": "8:18:09", "throughput": 9007.44, "total_tokens": 5248632}
{"current_steps": 100, "total_steps": 4968, "loss": 0.5126, "lr": 9.990204984657458e-06, "epoch": 0.040257648953301126, "percentage": 2.01, "elapsed_time": "0:10:13", "remaining_time": "8:17:38", "throughput": 9024.93, "total_tokens": 5535592}
{"current_steps": 105, "total_steps": 4968, "loss": 0.4907, "lr": 9.989190970066643e-06, "epoch": 0.042270531400966184, "percentage": 2.11, "elapsed_time": "0:10:48", "remaining_time": "8:20:30", "throughput": 8984.43, "total_tokens": 5825616}
{"current_steps": 110, "total_steps": 4968, "loss": 0.5066, "lr": 9.98812707778423e-06, "epoch": 0.04428341384863124, "percentage": 2.21, "elapsed_time": "0:11:17", "remaining_time": "8:18:26", "throughput": 9002.81, "total_tokens": 6096520}
{"current_steps": 115, "total_steps": 4968, "loss": 0.5259, "lr": 9.987013318446114e-06, "epoch": 0.046296296296296294, "percentage": 2.31, "elapsed_time": "0:11:43", "remaining_time": "8:14:55", "throughput": 9078.37, "total_tokens": 6388368}
{"current_steps": 120, "total_steps": 4968, "loss": 0.5149, "lr": 9.985849703186711e-06, "epoch": 0.04830917874396135, "percentage": 2.42, "elapsed_time": "0:12:17", "remaining_time": "8:16:42", "throughput": 9037.17, "total_tokens": 6666624}
{"current_steps": 125, "total_steps": 4968, "loss": 0.5026, "lr": 9.984636243638864e-06, "epoch": 0.05032206119162641, "percentage": 2.52, "elapsed_time": "0:12:45", "remaining_time": "8:14:14", "throughput": 9062.64, "total_tokens": 6936568}
{"current_steps": 130, "total_steps": 4968, "loss": 0.4955, "lr": 9.983372951933702e-06, "epoch": 0.05233494363929147, "percentage": 2.62, "elapsed_time": "0:13:16", "remaining_time": "8:14:02", "throughput": 9047.82, "total_tokens": 7206584}
{"current_steps": 135, "total_steps": 4968, "loss": 0.4968, "lr": 9.982059840700546e-06, "epoch": 0.05434782608695652, "percentage": 2.72, "elapsed_time": "0:13:48", "remaining_time": "8:14:28", "throughput": 9020.92, "total_tokens": 7475776}
{"current_steps": 140, "total_steps": 4968, "loss": 0.4931, "lr": 9.980696923066768e-06, "epoch": 0.05636070853462158, "percentage": 2.82, "elapsed_time": "0:14:21", "remaining_time": "8:15:24", "throughput": 8969.91, "total_tokens": 7731464}
{"current_steps": 145, "total_steps": 4968, "loss": 0.5025, "lr": 9.979284212657658e-06, "epoch": 0.05837359098228664, "percentage": 2.92, "elapsed_time": "0:14:44", "remaining_time": "8:10:08", "throughput": 9068.75, "total_tokens": 8017968}
{"current_steps": 150, "total_steps": 4968, "loss": 0.5134, "lr": 9.977821723596293e-06, "epoch": 0.06038647342995169, "percentage": 3.02, "elapsed_time": "0:15:08", "remaining_time": "8:06:28", "throughput": 9124.32, "total_tokens": 8291456}
{"current_steps": 155, "total_steps": 4968, "loss": 0.4773, "lr": 9.976309470503398e-06, "epoch": 0.06239935587761675, "percentage": 3.12, "elapsed_time": "0:15:44", "remaining_time": "8:08:32", "throughput": 9087.7, "total_tokens": 8578792}
{"current_steps": 160, "total_steps": 4968, "loss": 0.5019, "lr": 9.974747468497194e-06, "epoch": 0.0644122383252818, "percentage": 3.22, "elapsed_time": "0:16:11", "remaining_time": "8:06:48", "throughput": 9146.69, "total_tokens": 8890568}
{"current_steps": 165, "total_steps": 4968, "loss": 0.4943, "lr": 9.973135733193249e-06, "epoch": 0.06642512077294686, "percentage": 3.32, "elapsed_time": "0:16:41", "remaining_time": "8:05:39", "throughput": 9170.0, "total_tokens": 9179704}
{"current_steps": 170, "total_steps": 4968, "loss": 0.4921, "lr": 9.971474280704325e-06, "epoch": 0.06843800322061191, "percentage": 3.42, "elapsed_time": "0:17:07", "remaining_time": "8:03:11", "throughput": 9210.84, "total_tokens": 9461368}
{"current_steps": 175, "total_steps": 4968, "loss": 0.4741, "lr": 9.969763127640209e-06, "epoch": 0.07045088566827697, "percentage": 3.52, "elapsed_time": "0:17:36", "remaining_time": "8:02:25", "throughput": 9191.58, "total_tokens": 9713984}
{"current_steps": 180, "total_steps": 4968, "loss": 0.4759, "lr": 9.968002291107557e-06, "epoch": 0.07246376811594203, "percentage": 3.62, "elapsed_time": "0:18:06", "remaining_time": "8:01:49", "throughput": 9212.62, "total_tokens": 10012384}
{"current_steps": 185, "total_steps": 4968, "loss": 0.4987, "lr": 9.966191788709716e-06, "epoch": 0.07447665056360708, "percentage": 3.72, "elapsed_time": "0:18:44", "remaining_time": "8:04:35", "throughput": 9166.96, "total_tokens": 10309304}
{"current_steps": 190, "total_steps": 4968, "loss": 0.5044, "lr": 9.96433163854655e-06, "epoch": 0.07648953301127215, "percentage": 3.82, "elapsed_time": "0:19:14", "remaining_time": "8:03:51", "throughput": 9182.7, "total_tokens": 10601024}
{"current_steps": 195, "total_steps": 4968, "loss": 0.4963, "lr": 9.96242185921426e-06, "epoch": 0.0785024154589372, "percentage": 3.93, "elapsed_time": "0:19:44", "remaining_time": "8:03:22", "throughput": 9151.18, "total_tokens": 10843288}
{"current_steps": 200, "total_steps": 4968, "loss": 0.4897, "lr": 9.9604624698052e-06, "epoch": 0.08051529790660225, "percentage": 4.03, "elapsed_time": "0:20:15", "remaining_time": "8:02:53", "throughput": 9151.78, "total_tokens": 11122280}
{"current_steps": 205, "total_steps": 4968, "loss": 0.4868, "lr": 9.958453489907673e-06, "epoch": 0.08252818035426732, "percentage": 4.13, "elapsed_time": "0:20:47", "remaining_time": "8:02:58", "throughput": 9139.39, "total_tokens": 11398920}
{"current_steps": 210, "total_steps": 4968, "loss": 0.4624, "lr": 9.95639493960576e-06, "epoch": 0.08454106280193237, "percentage": 4.23, "elapsed_time": "0:21:21", "remaining_time": "8:04:04", "throughput": 9117.22, "total_tokens": 11687640}
{"current_steps": 215, "total_steps": 4968, "loss": 0.4623, "lr": 9.954286839479093e-06, "epoch": 0.08655394524959742, "percentage": 4.33, "elapsed_time": "0:21:50", "remaining_time": "8:02:48", "throughput": 9129.77, "total_tokens": 11963376}
{"current_steps": 220, "total_steps": 4968, "loss": 0.5101, "lr": 9.952129210602667e-06, "epoch": 0.08856682769726248, "percentage": 4.43, "elapsed_time": "0:22:23", "remaining_time": "8:03:12", "throughput": 9115.0, "total_tokens": 12245024}
{"current_steps": 225, "total_steps": 4968, "loss": 0.4567, "lr": 9.949922074546622e-06, "epoch": 0.09057971014492754, "percentage": 4.53, "elapsed_time": "0:22:49", "remaining_time": "8:01:01", "throughput": 9147.31, "total_tokens": 12524040}
{"current_steps": 230, "total_steps": 4968, "loss": 0.4815, "lr": 9.947665453376032e-06, "epoch": 0.09259259259259259, "percentage": 4.63, "elapsed_time": "0:23:20", "remaining_time": "8:00:52", "throughput": 9128.45, "total_tokens": 12785280}
{"current_steps": 235, "total_steps": 4968, "loss": 0.4564, "lr": 9.945359369650673e-06, "epoch": 0.09460547504025765, "percentage": 4.73, "elapsed_time": "0:23:54", "remaining_time": "8:01:33", "throughput": 9102.26, "total_tokens": 13058144}
{"current_steps": 240, "total_steps": 4968, "loss": 0.4618, "lr": 9.943003846424811e-06, "epoch": 0.0966183574879227, "percentage": 4.83, "elapsed_time": "0:24:25", "remaining_time": "8:01:03", "throughput": 9107.88, "total_tokens": 13344560}
{"current_steps": 245, "total_steps": 4968, "loss": 0.48, "lr": 9.940598907246968e-06, "epoch": 0.09863123993558776, "percentage": 4.93, "elapsed_time": "0:25:01", "remaining_time": "8:02:16", "throughput": 9070.86, "total_tokens": 13615896}
{"current_steps": 250, "total_steps": 4968, "loss": 0.4692, "lr": 9.93814457615968e-06, "epoch": 0.10064412238325282, "percentage": 5.03, "elapsed_time": "0:25:29", "remaining_time": "8:01:01", "throughput": 9093.67, "total_tokens": 13907312}
{"current_steps": 255, "total_steps": 4968, "loss": 0.4603, "lr": 9.935640877699267e-06, "epoch": 0.10265700483091787, "percentage": 5.13, "elapsed_time": "0:26:00", "remaining_time": "8:00:39", "throughput": 9077.51, "total_tokens": 14164552}
{"current_steps": 260, "total_steps": 4968, "loss": 0.4722, "lr": 9.933087836895575e-06, "epoch": 0.10466988727858294, "percentage": 5.23, "elapsed_time": "0:26:27", "remaining_time": "7:59:07", "throughput": 9097.84, "total_tokens": 14443752}
{"current_steps": 265, "total_steps": 4968, "loss": 0.4877, "lr": 9.930485479271735e-06, "epoch": 0.10668276972624799, "percentage": 5.33, "elapsed_time": "0:27:00", "remaining_time": "7:59:26", "throughput": 9091.26, "total_tokens": 14736200}
{"current_steps": 270, "total_steps": 4968, "loss": 0.466, "lr": 9.927833830843912e-06, "epoch": 0.10869565217391304, "percentage": 5.43, "elapsed_time": "0:27:37", "remaining_time": "8:00:39", "throughput": 9060.09, "total_tokens": 15016808}
{"current_steps": 275, "total_steps": 4968, "loss": 0.4919, "lr": 9.925132918121031e-06, "epoch": 0.1107085346215781, "percentage": 5.54, "elapsed_time": "0:28:07", "remaining_time": "7:59:49", "throughput": 9074.27, "total_tokens": 15308392}
{"current_steps": 280, "total_steps": 4968, "loss": 0.4688, "lr": 9.922382768104522e-06, "epoch": 0.11272141706924316, "percentage": 5.64, "elapsed_time": "0:28:34", "remaining_time": "7:58:25", "throughput": 9075.11, "total_tokens": 15559416}
{"current_steps": 285, "total_steps": 4968, "loss": 0.4684, "lr": 9.919583408288049e-06, "epoch": 0.11473429951690821, "percentage": 5.74, "elapsed_time": "0:29:04", "remaining_time": "7:57:44", "throughput": 9077.96, "total_tokens": 15836040}
{"current_steps": 290, "total_steps": 4968, "loss": 0.4808, "lr": 9.916734866657233e-06, "epoch": 0.11674718196457327, "percentage": 5.84, "elapsed_time": "0:29:35", "remaining_time": "7:57:20", "throughput": 9074.01, "total_tokens": 16110584}
{"current_steps": 295, "total_steps": 4968, "loss": 0.4565, "lr": 9.913837171689371e-06, "epoch": 0.11876006441223833, "percentage": 5.94, "elapsed_time": "0:30:00", "remaining_time": "7:55:23", "throughput": 9100.54, "total_tokens": 16386896}
{"current_steps": 300, "total_steps": 4968, "loss": 0.4622, "lr": 9.910890352353154e-06, "epoch": 0.12077294685990338, "percentage": 6.04, "elapsed_time": "0:30:26", "remaining_time": "7:53:40", "throughput": 9133.27, "total_tokens": 16681768}
{"current_steps": 305, "total_steps": 4968, "loss": 0.4496, "lr": 9.90789443810838e-06, "epoch": 0.12278582930756844, "percentage": 6.14, "elapsed_time": "0:30:52", "remaining_time": "7:52:02", "throughput": 9153.54, "total_tokens": 16957488}
{"current_steps": 310, "total_steps": 4968, "loss": 0.486, "lr": 9.904849458905654e-06, "epoch": 0.1247987117552335, "percentage": 6.24, "elapsed_time": "0:31:30", "remaining_time": "7:53:23", "throughput": 9130.91, "total_tokens": 17260552}
{"current_steps": 315, "total_steps": 4968, "loss": 0.4643, "lr": 9.901755445186088e-06, "epoch": 0.12681159420289856, "percentage": 6.34, "elapsed_time": "0:31:59", "remaining_time": "7:52:28", "throughput": 9132.39, "total_tokens": 17526528}
{"current_steps": 320, "total_steps": 4968, "loss": 0.4747, "lr": 9.898612427881002e-06, "epoch": 0.1288244766505636, "percentage": 6.44, "elapsed_time": "0:32:31", "remaining_time": "7:52:29", "throughput": 9120.63, "total_tokens": 17801096}
{"current_steps": 325, "total_steps": 4968, "loss": 0.5203, "lr": 9.895420438411616e-06, "epoch": 0.13083735909822866, "percentage": 6.54, "elapsed_time": "0:32:59", "remaining_time": "7:51:21", "throughput": 9136.17, "total_tokens": 18086600}
{"current_steps": 330, "total_steps": 4968, "loss": 0.4754, "lr": 9.892179508688724e-06, "epoch": 0.13285024154589373, "percentage": 6.64, "elapsed_time": "0:33:30", "remaining_time": "7:50:52", "throughput": 9127.82, "total_tokens": 18348912}
{"current_steps": 335, "total_steps": 4968, "loss": 0.445, "lr": 9.888889671112388e-06, "epoch": 0.13486312399355876, "percentage": 6.74, "elapsed_time": "0:33:56", "remaining_time": "7:49:23", "throughput": 9143.05, "total_tokens": 18619192}
{"current_steps": 340, "total_steps": 4968, "loss": 0.4669, "lr": 9.88555095857161e-06, "epoch": 0.13687600644122383, "percentage": 6.84, "elapsed_time": "0:34:28", "remaining_time": "7:49:20", "throughput": 9137.87, "total_tokens": 18905056}
{"current_steps": 345, "total_steps": 4968, "loss": 0.4782, "lr": 9.882163404444001e-06, "epoch": 0.1388888888888889, "percentage": 6.94, "elapsed_time": "0:34:58", "remaining_time": "7:48:44", "throughput": 9140.42, "total_tokens": 19184608}
{"current_steps": 350, "total_steps": 4968, "loss": 0.4543, "lr": 9.878727042595447e-06, "epoch": 0.14090177133655393, "percentage": 7.05, "elapsed_time": "0:35:28", "remaining_time": "7:48:07", "throughput": 9142.14, "total_tokens": 19461712}
{"current_steps": 355, "total_steps": 4968, "loss": 0.4441, "lr": 9.875241907379774e-06, "epoch": 0.142914653784219, "percentage": 7.15, "elapsed_time": "0:36:00", "remaining_time": "7:47:54", "throughput": 9136.69, "total_tokens": 19740152}
{"current_steps": 360, "total_steps": 4968, "loss": 0.4712, "lr": 9.871708033638403e-06, "epoch": 0.14492753623188406, "percentage": 7.25, "elapsed_time": "0:36:28", "remaining_time": "7:46:50", "throughput": 9143.06, "total_tokens": 20008048}
{"current_steps": 365, "total_steps": 4968, "loss": 0.461, "lr": 9.8681254567e-06, "epoch": 0.1469404186795491, "percentage": 7.35, "elapsed_time": "0:36:52", "remaining_time": "7:45:06", "throughput": 9164.83, "total_tokens": 20280608}
{"current_steps": 370, "total_steps": 4968, "loss": 0.4195, "lr": 9.864494212380125e-06, "epoch": 0.14895330112721417, "percentage": 7.45, "elapsed_time": "0:37:19", "remaining_time": "7:43:55", "throughput": 9165.31, "total_tokens": 20529280}
{"current_steps": 375, "total_steps": 4968, "loss": 0.4436, "lr": 9.860814336980873e-06, "epoch": 0.15096618357487923, "percentage": 7.55, "elapsed_time": "0:37:49", "remaining_time": "7:43:16", "throughput": 9170.37, "total_tokens": 20811944}
{"current_steps": 380, "total_steps": 4968, "loss": 0.4566, "lr": 9.85708586729051e-06, "epoch": 0.1529790660225443, "percentage": 7.65, "elapsed_time": "0:38:23", "remaining_time": "7:43:28", "throughput": 9160.71, "total_tokens": 21099408}
{"current_steps": 385, "total_steps": 4968, "loss": 0.4646, "lr": 9.85330884058311e-06, "epoch": 0.15499194847020933, "percentage": 7.75, "elapsed_time": "0:38:52", "remaining_time": "7:42:50", "throughput": 9166.39, "total_tokens": 21383888}
{"current_steps": 390, "total_steps": 4968, "loss": 0.4672, "lr": 9.849483294618174e-06, "epoch": 0.1570048309178744, "percentage": 7.85, "elapsed_time": "0:39:17", "remaining_time": "7:41:17", "throughput": 9181.99, "total_tokens": 21649424}
{"current_steps": 395, "total_steps": 4968, "loss": 0.4698, "lr": 9.84560926764026e-06, "epoch": 0.15901771336553946, "percentage": 7.95, "elapsed_time": "0:39:48", "remaining_time": "7:40:48", "throughput": 9185.41, "total_tokens": 21936800}
{"current_steps": 400, "total_steps": 4968, "loss": 0.4787, "lr": 9.8416867983786e-06, "epoch": 0.1610305958132045, "percentage": 8.05, "elapsed_time": "0:40:15", "remaining_time": "7:39:46", "throughput": 9205.26, "total_tokens": 22236592}
{"current_steps": 405, "total_steps": 4968, "loss": 0.4563, "lr": 9.837715926046705e-06, "epoch": 0.16304347826086957, "percentage": 8.15, "elapsed_time": "0:40:43", "remaining_time": "7:38:49", "throughput": 9213.05, "total_tokens": 22511304}
{"current_steps": 410, "total_steps": 4968, "loss": 0.4427, "lr": 9.833696690341985e-06, "epoch": 0.16505636070853463, "percentage": 8.25, "elapsed_time": "0:41:13", "remaining_time": "7:38:17", "throughput": 9213.74, "total_tokens": 22789600}
{"current_steps": 415, "total_steps": 4968, "loss": 0.4448, "lr": 9.829629131445342e-06, "epoch": 0.16706924315619967, "percentage": 8.35, "elapsed_time": "0:41:39", "remaining_time": "7:37:05", "throughput": 9223.81, "total_tokens": 23057896}
{"current_steps": 420, "total_steps": 4968, "loss": 0.4716, "lr": 9.825513290020774e-06, "epoch": 0.16908212560386474, "percentage": 8.45, "elapsed_time": "0:42:04", "remaining_time": "7:35:41", "throughput": 9237.17, "total_tokens": 23322920}
{"current_steps": 425, "total_steps": 4968, "loss": 0.4635, "lr": 9.821349207214965e-06, "epoch": 0.1710950080515298, "percentage": 8.55, "elapsed_time": "0:42:35", "remaining_time": "7:35:13", "throughput": 9238.97, "total_tokens": 23607720}
{"current_steps": 430, "total_steps": 4968, "loss": 0.4601, "lr": 9.817136924656876e-06, "epoch": 0.17310789049919484, "percentage": 8.66, "elapsed_time": "0:43:02", "remaining_time": "7:34:15", "throughput": 9245.93, "total_tokens": 23878208}
{"current_steps": 435, "total_steps": 4968, "loss": 0.4771, "lr": 9.81287648445733e-06, "epoch": 0.1751207729468599, "percentage": 8.76, "elapsed_time": "0:43:30", "remaining_time": "7:33:22", "throughput": 9244.69, "total_tokens": 24132696}
{"current_steps": 440, "total_steps": 4968, "loss": 0.5071, "lr": 9.808567929208585e-06, "epoch": 0.17713365539452497, "percentage": 8.86, "elapsed_time": "0:43:55", "remaining_time": "7:32:02", "throughput": 9246.75, "total_tokens": 24370704}
{"current_steps": 445, "total_steps": 4968, "loss": 0.4677, "lr": 9.804211301983919e-06, "epoch": 0.17914653784219, "percentage": 8.96, "elapsed_time": "0:44:24", "remaining_time": "7:31:19", "throughput": 9251.09, "total_tokens": 24646976}
{"current_steps": 450, "total_steps": 4968, "loss": 0.4412, "lr": 9.799806646337186e-06, "epoch": 0.18115942028985507, "percentage": 9.06, "elapsed_time": "0:44:52", "remaining_time": "7:30:34", "throughput": 9258.04, "total_tokens": 24928696}
{"current_steps": 455, "total_steps": 4968, "loss": 0.4778, "lr": 9.795354006302391e-06, "epoch": 0.18317230273752014, "percentage": 9.16, "elapsed_time": "0:45:16", "remaining_time": "7:28:59", "throughput": 9285.2, "total_tokens": 25219216}
{"current_steps": 460, "total_steps": 4968, "loss": 0.4418, "lr": 9.790853426393246e-06, "epoch": 0.18518518518518517, "percentage": 9.26, "elapsed_time": "0:45:45", "remaining_time": "7:28:23", "throughput": 9280.77, "total_tokens": 25478368}
{"current_steps": 465, "total_steps": 4968, "loss": 0.4505, "lr": 9.786304951602721e-06, "epoch": 0.18719806763285024, "percentage": 9.36, "elapsed_time": "0:46:16", "remaining_time": "7:28:10", "throughput": 9280.09, "total_tokens": 25769232}
{"current_steps": 470, "total_steps": 4968, "loss": 0.4682, "lr": 9.781708627402607e-06, "epoch": 0.1892109500805153, "percentage": 9.46, "elapsed_time": "0:46:55", "remaining_time": "7:29:05", "throughput": 9251.71, "total_tokens": 26048576}
{"current_steps": 475, "total_steps": 4968, "loss": 0.4755, "lr": 9.777064499743044e-06, "epoch": 0.19122383252818034, "percentage": 9.56, "elapsed_time": "0:47:28", "remaining_time": "7:28:59", "throughput": 9244.14, "total_tokens": 26328000}
{"current_steps": 480, "total_steps": 4968, "loss": 0.4521, "lr": 9.772372615052073e-06, "epoch": 0.1932367149758454, "percentage": 9.66, "elapsed_time": "0:47:51", "remaining_time": "7:27:31", "throughput": 9271.28, "total_tokens": 26625520}
{"current_steps": 485, "total_steps": 4968, "loss": 0.4664, "lr": 9.767633020235175e-06, "epoch": 0.19524959742351047, "percentage": 9.76, "elapsed_time": "0:48:25", "remaining_time": "7:27:37", "throughput": 9262.33, "total_tokens": 26912912}
{"current_steps": 490, "total_steps": 4968, "loss": 0.4483, "lr": 9.762845762674783e-06, "epoch": 0.1972624798711755, "percentage": 9.86, "elapsed_time": "0:48:53", "remaining_time": "7:26:47", "throughput": 9268.0, "total_tokens": 27186112}
{"current_steps": 495, "total_steps": 4968, "loss": 0.4425, "lr": 9.758010890229841e-06, "epoch": 0.19927536231884058, "percentage": 9.96, "elapsed_time": "0:49:18", "remaining_time": "7:25:30", "throughput": 9282.29, "total_tokens": 27458000}
{"current_steps": 500, "total_steps": 4968, "loss": 0.4376, "lr": 9.753128451235286e-06, "epoch": 0.20128824476650564, "percentage": 10.06, "elapsed_time": "0:49:44", "remaining_time": "7:24:25", "throughput": 9292.08, "total_tokens": 27728384}
{"current_steps": 505, "total_steps": 4968, "loss": 0.4464, "lr": 9.748198494501598e-06, "epoch": 0.20330112721417068, "percentage": 10.17, "elapsed_time": "0:50:12", "remaining_time": "7:23:45", "throughput": 9292.32, "total_tokens": 27995208}
{"current_steps": 510, "total_steps": 4968, "loss": 0.4636, "lr": 9.743221069314293e-06, "epoch": 0.20531400966183574, "percentage": 10.27, "elapsed_time": "0:50:50", "remaining_time": "7:24:25", "throughput": 9271.21, "total_tokens": 28282768}
{"current_steps": 515, "total_steps": 4968, "loss": 0.4625, "lr": 9.73819622543344e-06, "epoch": 0.2073268921095008, "percentage": 10.37, "elapsed_time": "0:51:25", "remaining_time": "7:24:41", "throughput": 9252.31, "total_tokens": 28551128}
{"current_steps": 520, "total_steps": 4968, "loss": 0.4933, "lr": 9.733124013093158e-06, "epoch": 0.20933977455716588, "percentage": 10.47, "elapsed_time": "0:51:59", "remaining_time": "7:24:39", "throughput": 9237.27, "total_tokens": 28811192}
{"current_steps": 525, "total_steps": 4968, "loss": 0.4467, "lr": 9.728004483001117e-06, "epoch": 0.2113526570048309, "percentage": 10.57, "elapsed_time": "0:52:28", "remaining_time": "7:24:06", "throughput": 9229.31, "total_tokens": 29059944}
{"current_steps": 530, "total_steps": 4968, "loss": 0.4537, "lr": 9.722837686338025e-06, "epoch": 0.21336553945249598, "percentage": 10.67, "elapsed_time": "0:52:57", "remaining_time": "7:23:27", "throughput": 9239.52, "total_tokens": 29359232}
{"current_steps": 535, "total_steps": 4968, "loss": 0.4708, "lr": 9.717623674757126e-06, "epoch": 0.21537842190016104, "percentage": 10.77, "elapsed_time": "0:53:29", "remaining_time": "7:23:17", "throughput": 9234.29, "total_tokens": 29641328}
{"current_steps": 540, "total_steps": 4968, "loss": 0.4612, "lr": 9.712362500383678e-06, "epoch": 0.21739130434782608, "percentage": 10.87, "elapsed_time": "0:53:58", "remaining_time": "7:22:39", "throughput": 9234.83, "total_tokens": 29911064}
{"current_steps": 545, "total_steps": 4968, "loss": 0.4375, "lr": 9.707054215814428e-06, "epoch": 0.21940418679549115, "percentage": 10.97, "elapsed_time": "0:54:32", "remaining_time": "7:22:40", "throughput": 9224.3, "total_tokens": 30189032}
{"current_steps": 550, "total_steps": 4968, "loss": 0.4562, "lr": 9.7016988741171e-06, "epoch": 0.2214170692431562, "percentage": 11.07, "elapsed_time": "0:55:06", "remaining_time": "7:22:43", "throughput": 9220.02, "total_tokens": 30489720}
{"current_steps": 555, "total_steps": 4968, "loss": 0.4629, "lr": 9.696296528829847e-06, "epoch": 0.22342995169082125, "percentage": 11.17, "elapsed_time": "0:55:26", "remaining_time": "7:20:51", "throughput": 9245.06, "total_tokens": 30755376}
{"current_steps": 560, "total_steps": 4968, "loss": 0.4438, "lr": 9.690847233960723e-06, "epoch": 0.22544283413848631, "percentage": 11.27, "elapsed_time": "0:55:56", "remaining_time": "7:20:19", "throughput": 9236.36, "total_tokens": 31000552}
{"current_steps": 565, "total_steps": 4968, "loss": 0.455, "lr": 9.685351043987151e-06, "epoch": 0.22745571658615138, "percentage": 11.37, "elapsed_time": "0:56:25", "remaining_time": "7:19:42", "throughput": 9240.82, "total_tokens": 31284360}
{"current_steps": 570, "total_steps": 4968, "loss": 0.4755, "lr": 9.679808013855367e-06, "epoch": 0.22946859903381642, "percentage": 11.47, "elapsed_time": "0:57:00", "remaining_time": "7:19:54", "throughput": 9234.47, "total_tokens": 31590160}
{"current_steps": 575, "total_steps": 4968, "loss": 0.4564, "lr": 9.674218198979876e-06, "epoch": 0.23148148148148148, "percentage": 11.57, "elapsed_time": "0:57:33", "remaining_time": "7:19:41", "throughput": 9235.59, "total_tokens": 31891040}
{"current_steps": 580, "total_steps": 4968, "loss": 0.4195, "lr": 9.668581655242896e-06, "epoch": 0.23349436392914655, "percentage": 11.67, "elapsed_time": "0:57:58", "remaining_time": "7:18:34", "throughput": 9249.57, "total_tokens": 32172592}
{"current_steps": 585, "total_steps": 4968, "loss": 0.4326, "lr": 9.662898438993803e-06, "epoch": 0.23550724637681159, "percentage": 11.78, "elapsed_time": "0:58:33", "remaining_time": "7:18:41", "throughput": 9237.52, "total_tokens": 32453192}
{"current_steps": 590, "total_steps": 4968, "loss": 0.4261, "lr": 9.657168607048564e-06, "epoch": 0.23752012882447665, "percentage": 11.88, "elapsed_time": "0:58:55", "remaining_time": "7:17:15", "throughput": 9258.42, "total_tokens": 32734816}
{"current_steps": 595, "total_steps": 4968, "loss": 0.4395, "lr": 9.651392216689167e-06, "epoch": 0.23953301127214172, "percentage": 11.98, "elapsed_time": "0:59:24", "remaining_time": "7:16:39", "throughput": 9264.48, "total_tokens": 33026104}
{"current_steps": 600, "total_steps": 4968, "loss": 0.4538, "lr": 9.645569325663055e-06, "epoch": 0.24154589371980675, "percentage": 12.08, "elapsed_time": "0:59:51", "remaining_time": "7:15:43", "throughput": 9274.38, "total_tokens": 33305592}
{"current_steps": 605, "total_steps": 4968, "loss": 0.4397, "lr": 9.639699992182547e-06, "epoch": 0.24355877616747182, "percentage": 12.18, "elapsed_time": "1:00:22", "remaining_time": "7:15:25", "throughput": 9264.58, "total_tokens": 33562824}
{"current_steps": 610, "total_steps": 4968, "loss": 0.4345, "lr": 9.633784274924247e-06, "epoch": 0.24557165861513688, "percentage": 12.28, "elapsed_time": "1:00:55", "remaining_time": "7:15:12", "throughput": 9254.74, "total_tokens": 33826536}
{"current_steps": 615, "total_steps": 4968, "loss": 0.4519, "lr": 9.627822233028472e-06, "epoch": 0.24758454106280192, "percentage": 12.38, "elapsed_time": "1:01:22", "remaining_time": "7:14:21", "throughput": 9260.59, "total_tokens": 34097896}
{"current_steps": 620, "total_steps": 4968, "loss": 0.4348, "lr": 9.62181392609865e-06, "epoch": 0.249597423510467, "percentage": 12.48, "elapsed_time": "1:01:54", "remaining_time": "7:14:09", "throughput": 9250.86, "total_tokens": 34362496}
{"current_steps": 625, "total_steps": 4968, "loss": 0.4379, "lr": 9.615759414200729e-06, "epoch": 0.25161030595813205, "percentage": 12.58, "elapsed_time": "1:02:21", "remaining_time": "7:13:16", "throughput": 9247.9, "total_tokens": 34597456}
{"current_steps": 630, "total_steps": 4968, "loss": 0.432, "lr": 9.609658757862572e-06, "epoch": 0.2536231884057971, "percentage": 12.68, "elapsed_time": "1:02:54", "remaining_time": "7:13:09", "throughput": 9242.15, "total_tokens": 34884304}
{"current_steps": 635, "total_steps": 4968, "loss": 0.4543, "lr": 9.603512018073357e-06, "epoch": 0.2556360708534622, "percentage": 12.78, "elapsed_time": "1:03:20", "remaining_time": "7:12:10", "throughput": 9250.5, "total_tokens": 35153336}
{"current_steps": 640, "total_steps": 4968, "loss": 0.4371, "lr": 9.597319256282968e-06, "epoch": 0.2576489533011272, "percentage": 12.88, "elapsed_time": "1:03:46", "remaining_time": "7:11:18", "throughput": 9258.34, "total_tokens": 35430144}
{"current_steps": 645, "total_steps": 4968, "loss": 0.4655, "lr": 9.591080534401371e-06, "epoch": 0.25966183574879226, "percentage": 12.98, "elapsed_time": "1:04:22", "remaining_time": "7:11:28", "throughput": 9247.27, "total_tokens": 35718240}
{"current_steps": 650, "total_steps": 4968, "loss": 0.4402, "lr": 9.584795914798007e-06, "epoch": 0.2616747181964573, "percentage": 13.08, "elapsed_time": "1:05:00", "remaining_time": "7:11:48", "throughput": 9236.6, "total_tokens": 36023336}
{"current_steps": 655, "total_steps": 4968, "loss": 0.4209, "lr": 9.578465460301162e-06, "epoch": 0.2636876006441224, "percentage": 13.18, "elapsed_time": "1:05:29", "remaining_time": "7:11:15", "throughput": 9237.45, "total_tokens": 36299232}
{"current_steps": 660, "total_steps": 4968, "loss": 0.423, "lr": 9.572089234197343e-06, "epoch": 0.26570048309178745, "percentage": 13.29, "elapsed_time": "1:05:58", "remaining_time": "7:10:41", "throughput": 9238.97, "total_tokens": 36576512}
{"current_steps": 665, "total_steps": 4968, "loss": 0.444, "lr": 9.565667300230637e-06, "epoch": 0.2677133655394525, "percentage": 13.39, "elapsed_time": "1:06:28", "remaining_time": "7:10:05", "throughput": 9243.81, "total_tokens": 36865456}
{"current_steps": 670, "total_steps": 4968, "loss": 0.4292, "lr": 9.559199722602087e-06, "epoch": 0.26972624798711753, "percentage": 13.49, "elapsed_time": "1:07:00", "remaining_time": "7:09:53", "throughput": 9233.89, "total_tokens": 37128216}
{"current_steps": 675, "total_steps": 4968, "loss": 0.4603, "lr": 9.55268656596903e-06, "epoch": 0.2717391304347826, "percentage": 13.59, "elapsed_time": "1:07:28", "remaining_time": "7:09:07", "throughput": 9240.97, "total_tokens": 37410888}
{"current_steps": 680, "total_steps": 4968, "loss": 0.4375, "lr": 9.546127895444479e-06, "epoch": 0.27375201288244766, "percentage": 13.69, "elapsed_time": "1:08:00", "remaining_time": "7:08:48", "throughput": 9231.58, "total_tokens": 37665520}
{"current_steps": 685, "total_steps": 4968, "loss": 0.4516, "lr": 9.539523776596446e-06, "epoch": 0.2757648953301127, "percentage": 13.79, "elapsed_time": "1:08:32", "remaining_time": "7:08:35", "throughput": 9223.42, "total_tokens": 37934576}
{"current_steps": 690, "total_steps": 4968, "loss": 0.44, "lr": 9.532874275447298e-06, "epoch": 0.2777777777777778, "percentage": 13.89, "elapsed_time": "1:09:02", "remaining_time": "7:08:04", "throughput": 9223.91, "total_tokens": 38210848}
{"current_steps": 695, "total_steps": 4968, "loss": 0.4742, "lr": 9.526179458473098e-06, "epoch": 0.27979066022544286, "percentage": 13.99, "elapsed_time": "1:09:31", "remaining_time": "7:07:26", "throughput": 9225.72, "total_tokens": 38484672}
{"current_steps": 700, "total_steps": 4968, "loss": 0.4228, "lr": 9.519439392602938e-06, "epoch": 0.28180354267310787, "percentage": 14.09, "elapsed_time": "1:09:57", "remaining_time": "7:06:35", "throughput": 9236.26, "total_tokens": 38773360}
{"current_steps": 705, "total_steps": 4968, "loss": 0.4582, "lr": 9.512654145218265e-06, "epoch": 0.28381642512077293, "percentage": 14.19, "elapsed_time": "1:10:24", "remaining_time": "7:05:46", "throughput": 9249.55, "total_tokens": 39076664}
{"current_steps": 710, "total_steps": 4968, "loss": 0.4208, "lr": 9.505823784152222e-06, "epoch": 0.285829307568438, "percentage": 14.29, "elapsed_time": "1:10:57", "remaining_time": "7:05:33", "throughput": 9248.47, "total_tokens": 39376712}
{"current_steps": 715, "total_steps": 4968, "loss": 0.4375, "lr": 9.49894837768895e-06, "epoch": 0.28784219001610306, "percentage": 14.39, "elapsed_time": "1:11:25", "remaining_time": "7:04:52", "throughput": 9256.49, "total_tokens": 39671280}
{"current_steps": 720, "total_steps": 4968, "loss": 0.4424, "lr": 9.492027994562922e-06, "epoch": 0.2898550724637681, "percentage": 14.49, "elapsed_time": "1:11:52", "remaining_time": "7:04:01", "throughput": 9267.08, "total_tokens": 39961104}
{"current_steps": 725, "total_steps": 4968, "loss": 0.4444, "lr": 9.485062703958248e-06, "epoch": 0.2918679549114332, "percentage": 14.59, "elapsed_time": "1:12:25", "remaining_time": "7:03:54", "throughput": 9261.26, "total_tokens": 40248688}
{"current_steps": 730, "total_steps": 4968, "loss": 0.4435, "lr": 9.478052575507983e-06, "epoch": 0.2938808373590982, "percentage": 14.69, "elapsed_time": "1:12:58", "remaining_time": "7:03:39", "throughput": 9257.35, "total_tokens": 40533448}
{"current_steps": 735, "total_steps": 4968, "loss": 0.4491, "lr": 9.470997679293437e-06, "epoch": 0.29589371980676327, "percentage": 14.79, "elapsed_time": "1:13:34", "remaining_time": "7:03:45", "throughput": 9243.75, "total_tokens": 40808632}
{"current_steps": 740, "total_steps": 4968, "loss": 0.4357, "lr": 9.463898085843466e-06, "epoch": 0.29790660225442833, "percentage": 14.9, "elapsed_time": "1:14:09", "remaining_time": "7:03:40", "throughput": 9231.8, "total_tokens": 41074136}
{"current_steps": 745, "total_steps": 4968, "loss": 0.4616, "lr": 9.45675386613377e-06, "epoch": 0.2999194847020934, "percentage": 15.0, "elapsed_time": "1:14:39", "remaining_time": "7:03:12", "throughput": 9237.81, "total_tokens": 41381384}
{"current_steps": 750, "total_steps": 4968, "loss": 0.4129, "lr": 9.449565091586189e-06, "epoch": 0.30193236714975846, "percentage": 15.1, "elapsed_time": "1:15:12", "remaining_time": "7:02:55", "throughput": 9236.84, "total_tokens": 41677360}
{"current_steps": 755, "total_steps": 4968, "loss": 0.4439, "lr": 9.442331834067982e-06, "epoch": 0.30394524959742353, "percentage": 15.2, "elapsed_time": "1:15:38", "remaining_time": "7:02:07", "throughput": 9244.33, "total_tokens": 41958456}
{"current_steps": 760, "total_steps": 4968, "loss": 0.4476, "lr": 9.43505416589111e-06, "epoch": 0.3059581320450886, "percentage": 15.3, "elapsed_time": "1:16:08", "remaining_time": "7:01:32", "throughput": 9247.08, "total_tokens": 42241672}
{"current_steps": 765, "total_steps": 4968, "loss": 0.4011, "lr": 9.427732159811514e-06, "epoch": 0.3079710144927536, "percentage": 15.4, "elapsed_time": "1:16:37", "remaining_time": "7:00:59", "throughput": 9248.61, "total_tokens": 42520552}
{"current_steps": 770, "total_steps": 4968, "loss": 0.4158, "lr": 9.420365889028392e-06, "epoch": 0.30998389694041867, "percentage": 15.5, "elapsed_time": "1:17:05", "remaining_time": "7:00:15", "throughput": 9250.78, "total_tokens": 42785184}
{"current_steps": 775, "total_steps": 4968, "loss": 0.4231, "lr": 9.412955427183457e-06, "epoch": 0.31199677938808373, "percentage": 15.6, "elapsed_time": "1:17:31", "remaining_time": "6:59:23", "throughput": 9252.99, "total_tokens": 43036192}
{"current_steps": 780, "total_steps": 4968, "loss": 0.4444, "lr": 9.405500848360209e-06, "epoch": 0.3140096618357488, "percentage": 15.7, "elapsed_time": "1:18:06", "remaining_time": "6:59:21", "throughput": 9243.98, "total_tokens": 43319440}
{"current_steps": 785, "total_steps": 4968, "loss": 0.4405, "lr": 9.398002227083193e-06, "epoch": 0.31602254428341386, "percentage": 15.8, "elapsed_time": "1:18:38", "remaining_time": "6:59:01", "throughput": 9245.64, "total_tokens": 43622824}
{"current_steps": 790, "total_steps": 4968, "loss": 0.4537, "lr": 9.390459638317255e-06, "epoch": 0.31803542673107893, "percentage": 15.9, "elapsed_time": "1:19:17", "remaining_time": "6:59:19", "throughput": 9227.05, "total_tokens": 43895160}
{"current_steps": 795, "total_steps": 4968, "loss": 0.4064, "lr": 9.382873157466783e-06, "epoch": 0.32004830917874394, "percentage": 16.0, "elapsed_time": "1:19:44", "remaining_time": "6:58:35", "throughput": 9227.71, "total_tokens": 44151912}
{"current_steps": 800, "total_steps": 4968, "loss": 0.4505, "lr": 9.37524286037497e-06, "epoch": 0.322061191626409, "percentage": 16.1, "elapsed_time": "1:20:09", "remaining_time": "6:57:37", "throughput": 9240.39, "total_tokens": 44441312}
{"current_steps": 805, "total_steps": 4968, "loss": 0.4343, "lr": 9.367568823323039e-06, "epoch": 0.32407407407407407, "percentage": 16.2, "elapsed_time": "1:20:37", "remaining_time": "6:56:59", "throughput": 9246.78, "total_tokens": 44735576}
{"current_steps": 810, "total_steps": 4968, "loss": 0.4256, "lr": 9.359851123029493e-06, "epoch": 0.32608695652173914, "percentage": 16.3, "elapsed_time": "1:21:04", "remaining_time": "6:56:12", "throughput": 9257.23, "total_tokens": 45033720}
{"current_steps": 815, "total_steps": 4968, "loss": 0.4307, "lr": 9.352089836649341e-06, "epoch": 0.3280998389694042, "percentage": 16.4, "elapsed_time": "1:21:30", "remaining_time": "6:55:19", "throughput": 9261.13, "total_tokens": 45290536}
{"current_steps": 820, "total_steps": 4968, "loss": 0.4425, "lr": 9.344285041773329e-06, "epoch": 0.33011272141706927, "percentage": 16.51, "elapsed_time": "1:21:59", "remaining_time": "6:54:47", "throughput": 9265.2, "total_tokens": 45583520}
{"current_steps": 825, "total_steps": 4968, "loss": 0.4223, "lr": 9.336436816427161e-06, "epoch": 0.3321256038647343, "percentage": 16.61, "elapsed_time": "1:22:26", "remaining_time": "6:54:00", "throughput": 9269.74, "total_tokens": 45852248}
{"current_steps": 830, "total_steps": 4968, "loss": 0.4349, "lr": 9.32854523907073e-06, "epoch": 0.33413848631239934, "percentage": 16.71, "elapsed_time": "1:22:58", "remaining_time": "6:53:42", "throughput": 9260.61, "total_tokens": 46107152}
{"current_steps": 835, "total_steps": 4968, "loss": 0.4411, "lr": 9.320610388597316e-06, "epoch": 0.3361513687600644, "percentage": 16.81, "elapsed_time": "1:23:24", "remaining_time": "6:52:52", "throughput": 9266.81, "total_tokens": 46378192}
{"current_steps": 840, "total_steps": 4968, "loss": 0.4439, "lr": 9.312632344332812e-06, "epoch": 0.33816425120772947, "percentage": 16.91, "elapsed_time": "1:23:55", "remaining_time": "6:52:23", "throughput": 9264.77, "total_tokens": 46648456}
{"current_steps": 845, "total_steps": 4968, "loss": 0.4151, "lr": 9.304611186034926e-06, "epoch": 0.34017713365539454, "percentage": 17.01, "elapsed_time": "1:24:24", "remaining_time": "6:51:51", "throughput": 9265.31, "total_tokens": 46925064}
{"current_steps": 850, "total_steps": 4968, "loss": 0.418, "lr": 9.296546993892383e-06, "epoch": 0.3421900161030596, "percentage": 17.11, "elapsed_time": "1:24:55", "remaining_time": "6:51:24", "throughput": 9263.59, "total_tokens": 47200176}
{"current_steps": 855, "total_steps": 4968, "loss": 0.4578, "lr": 9.28843984852412e-06, "epoch": 0.3442028985507246, "percentage": 17.21, "elapsed_time": "1:25:29", "remaining_time": "6:51:13", "throughput": 9256.99, "total_tokens": 47480384}
{"current_steps": 860, "total_steps": 4968, "loss": 0.4561, "lr": 9.280289830978491e-06, "epoch": 0.3462157809983897, "percentage": 17.31, "elapsed_time": "1:26:03", "remaining_time": "6:51:02", "throughput": 9249.56, "total_tokens": 47755752}
{"current_steps": 865, "total_steps": 4968, "loss": 0.4489, "lr": 9.272097022732444e-06, "epoch": 0.34822866344605474, "percentage": 17.41, "elapsed_time": "1:26:34", "remaining_time": "6:50:37", "throughput": 9255.38, "total_tokens": 48073920}
{"current_steps": 870, "total_steps": 4968, "loss": 0.4155, "lr": 9.263861505690712e-06, "epoch": 0.3502415458937198, "percentage": 17.51, "elapsed_time": "1:27:03", "remaining_time": "6:50:03", "throughput": 9261.62, "total_tokens": 48375272}
{"current_steps": 875, "total_steps": 4968, "loss": 0.408, "lr": 9.255583362184998e-06, "epoch": 0.3522544283413849, "percentage": 17.61, "elapsed_time": "1:27:27", "remaining_time": "6:49:05", "throughput": 9272.94, "total_tokens": 48658240}
{"current_steps": 880, "total_steps": 4968, "loss": 0.4384, "lr": 9.247262674973147e-06, "epoch": 0.35426731078904994, "percentage": 17.71, "elapsed_time": "1:27:58", "remaining_time": "6:48:42", "throughput": 9268.83, "total_tokens": 48929232}
{"current_steps": 885, "total_steps": 4968, "loss": 0.4335, "lr": 9.238899527238319e-06, "epoch": 0.35628019323671495, "percentage": 17.81, "elapsed_time": "1:28:25", "remaining_time": "6:47:55", "throughput": 9277.99, "total_tokens": 49221736}
{"current_steps": 890, "total_steps": 4968, "loss": 0.4227, "lr": 9.230494002588154e-06, "epoch": 0.35829307568438, "percentage": 17.91, "elapsed_time": "1:28:51", "remaining_time": "6:47:11", "throughput": 9282.94, "total_tokens": 49496208}
{"current_steps": 895, "total_steps": 4968, "loss": 0.4222, "lr": 9.22204618505395e-06, "epoch": 0.3603059581320451, "percentage": 18.02, "elapsed_time": "1:29:24", "remaining_time": "6:46:53", "throughput": 9274.14, "total_tokens": 49752400}
{"current_steps": 900, "total_steps": 4968, "loss": 0.4317, "lr": 9.213556159089805e-06, "epoch": 0.36231884057971014, "percentage": 18.12, "elapsed_time": "1:29:54", "remaining_time": "6:46:23", "throughput": 9274.83, "total_tokens": 50034312}
{"current_steps": 905, "total_steps": 4968, "loss": 0.4577, "lr": 9.205024009571784e-06, "epoch": 0.3643317230273752, "percentage": 18.22, "elapsed_time": "1:30:25", "remaining_time": "6:45:56", "throughput": 9271.79, "total_tokens": 50301344}
{"current_steps": 910, "total_steps": 4968, "loss": 0.4242, "lr": 9.196449821797067e-06, "epoch": 0.3663446054750403, "percentage": 18.32, "elapsed_time": "1:30:58", "remaining_time": "6:45:42", "throughput": 9268.41, "total_tokens": 50594360}
{"current_steps": 915, "total_steps": 4968, "loss": 0.4389, "lr": 9.187833681483098e-06, "epoch": 0.36835748792270534, "percentage": 18.42, "elapsed_time": "1:31:29", "remaining_time": "6:45:14", "throughput": 9266.55, "total_tokens": 50865872}
{"current_steps": 920, "total_steps": 4968, "loss": 0.41, "lr": 9.179175674766727e-06, "epoch": 0.37037037037037035, "percentage": 18.52, "elapsed_time": "1:31:56", "remaining_time": "6:44:31", "throughput": 9271.14, "total_tokens": 51140920}
{"current_steps": 925, "total_steps": 4968, "loss": 0.4284, "lr": 9.170475888203348e-06, "epoch": 0.3723832528180354, "percentage": 18.62, "elapsed_time": "1:32:25", "remaining_time": "6:44:00", "throughput": 9268.99, "total_tokens": 51405568}
{"current_steps": 930, "total_steps": 4968, "loss": 0.428, "lr": 9.16173440876603e-06, "epoch": 0.3743961352657005, "percentage": 18.72, "elapsed_time": "1:32:51", "remaining_time": "6:43:11", "throughput": 9279.34, "total_tokens": 51699992}
{"current_steps": 935, "total_steps": 4968, "loss": 0.4387, "lr": 9.152951323844661e-06, "epoch": 0.37640901771336555, "percentage": 18.82, "elapsed_time": "1:33:25", "remaining_time": "6:42:59", "throughput": 9274.38, "total_tokens": 51988568}
{"current_steps": 940, "total_steps": 4968, "loss": 0.439, "lr": 9.144126721245059e-06, "epoch": 0.3784219001610306, "percentage": 18.92, "elapsed_time": "1:33:53", "remaining_time": "6:42:18", "throughput": 9277.14, "total_tokens": 52260104}
{"current_steps": 945, "total_steps": 4968, "loss": 0.4157, "lr": 9.1352606891881e-06, "epoch": 0.3804347826086957, "percentage": 19.02, "elapsed_time": "1:34:21", "remaining_time": "6:41:42", "throughput": 9281.54, "total_tokens": 52549592}
{"current_steps": 950, "total_steps": 4968, "loss": 0.4293, "lr": 9.126353316308838e-06, "epoch": 0.3824476650563607, "percentage": 19.12, "elapsed_time": "1:34:49", "remaining_time": "6:41:02", "throughput": 9288.31, "total_tokens": 52844200}
{"current_steps": 955, "total_steps": 4968, "loss": 0.3919, "lr": 9.11740469165562e-06, "epoch": 0.38446054750402575, "percentage": 19.22, "elapsed_time": "1:35:24", "remaining_time": "6:40:56", "throughput": 9281.19, "total_tokens": 53133880}
{"current_steps": 960, "total_steps": 4968, "loss": 0.4312, "lr": 9.108414904689192e-06, "epoch": 0.3864734299516908, "percentage": 19.32, "elapsed_time": "1:35:59", "remaining_time": "6:40:44", "throughput": 9274.32, "total_tokens": 53411536}
{"current_steps": 965, "total_steps": 4968, "loss": 0.4185, "lr": 9.099384045281801e-06, "epoch": 0.3884863123993559, "percentage": 19.42, "elapsed_time": "1:36:26", "remaining_time": "6:40:05", "throughput": 9273.17, "total_tokens": 53662792}
{"current_steps": 970, "total_steps": 4968, "loss": 0.4295, "lr": 9.090312203716307e-06, "epoch": 0.39049919484702095, "percentage": 19.52, "elapsed_time": "1:37:00", "remaining_time": "6:39:50", "throughput": 9266.86, "total_tokens": 53939184}
{"current_steps": 975, "total_steps": 4968, "loss": 0.402, "lr": 9.081199470685273e-06, "epoch": 0.392512077294686, "percentage": 19.63, "elapsed_time": "1:37:24", "remaining_time": "6:38:57", "throughput": 9273.81, "total_tokens": 54204248}
{"current_steps": 980, "total_steps": 4968, "loss": 0.413, "lr": 9.07204593729006e-06, "epoch": 0.394524959742351, "percentage": 19.73, "elapsed_time": "1:37:55", "remaining_time": "6:38:29", "throughput": 9273.65, "total_tokens": 54487640}
{"current_steps": 985, "total_steps": 4968, "loss": 0.4246, "lr": 9.062851695039915e-06, "epoch": 0.3965378421900161, "percentage": 19.83, "elapsed_time": "1:38:23", "remaining_time": "6:37:49", "throughput": 9281.3, "total_tokens": 54787960}
{"current_steps": 990, "total_steps": 4968, "loss": 0.4407, "lr": 9.053616835851062e-06, "epoch": 0.39855072463768115, "percentage": 19.93, "elapsed_time": "1:38:52", "remaining_time": "6:37:16", "throughput": 9283.01, "total_tokens": 55067216}
{"current_steps": 995, "total_steps": 4968, "loss": 0.4234, "lr": 9.044341452045773e-06, "epoch": 0.4005636070853462, "percentage": 20.03, "elapsed_time": "1:39:25", "remaining_time": "6:36:58", "throughput": 9281.65, "total_tokens": 55366344}
{"current_steps": 1000, "total_steps": 4968, "loss": 0.4302, "lr": 9.035025636351453e-06, "epoch": 0.4025764895330113, "percentage": 20.13, "elapsed_time": "1:39:52", "remaining_time": "6:36:18", "throughput": 9281.72, "total_tokens": 55620376}
{"current_steps": 1005, "total_steps": 4968, "loss": 0.4356, "lr": 9.025669481899713e-06, "epoch": 0.40458937198067635, "percentage": 20.23, "elapsed_time": "1:40:25", "remaining_time": "6:35:59", "throughput": 9280.74, "total_tokens": 55919896}
{"current_steps": 1010, "total_steps": 4968, "loss": 0.455, "lr": 9.016273082225434e-06, "epoch": 0.40660225442834136, "percentage": 20.33, "elapsed_time": "1:40:56", "remaining_time": "6:35:36", "throughput": 9278.66, "total_tokens": 56200704}
{"current_steps": 1015, "total_steps": 4968, "loss": 0.4021, "lr": 9.006836531265832e-06, "epoch": 0.4086151368760064, "percentage": 20.43, "elapsed_time": "1:41:33", "remaining_time": "6:35:32", "throughput": 9270.49, "total_tokens": 56491768}
{"current_steps": 1020, "total_steps": 4968, "loss": 0.4372, "lr": 8.997359923359527e-06, "epoch": 0.4106280193236715, "percentage": 20.53, "elapsed_time": "1:42:07", "remaining_time": "6:35:15", "throughput": 9266.51, "total_tokens": 56776864}
{"current_steps": 1025, "total_steps": 4968, "loss": 0.426, "lr": 8.987843353245594e-06, "epoch": 0.41264090177133655, "percentage": 20.63, "elapsed_time": "1:42:39", "remaining_time": "6:34:55", "throughput": 9255.94, "total_tokens": 57014104}
{"current_steps": 1030, "total_steps": 4968, "loss": 0.4181, "lr": 8.978286916062609e-06, "epoch": 0.4146537842190016, "percentage": 20.73, "elapsed_time": "1:43:09", "remaining_time": "6:34:23", "throughput": 9259.17, "total_tokens": 57308432}
{"current_steps": 1035, "total_steps": 4968, "loss": 0.4224, "lr": 8.968690707347714e-06, "epoch": 0.4166666666666667, "percentage": 20.83, "elapsed_time": "1:43:36", "remaining_time": "6:33:42", "throughput": 9262.57, "total_tokens": 57579872}
{"current_steps": 1040, "total_steps": 4968, "loss": 0.4212, "lr": 8.95905482303565e-06, "epoch": 0.41867954911433175, "percentage": 20.93, "elapsed_time": "1:44:04", "remaining_time": "6:33:06", "throughput": 9263.65, "total_tokens": 57851320}
{"current_steps": 1045, "total_steps": 4968, "loss": 0.4277, "lr": 8.949379359457795e-06, "epoch": 0.42069243156199676, "percentage": 21.03, "elapsed_time": "1:44:34", "remaining_time": "6:32:35", "throughput": 9263.92, "total_tokens": 58127192}
{"current_steps": 1050, "total_steps": 4968, "loss": 0.43, "lr": 8.939664413341214e-06, "epoch": 0.4227053140096618, "percentage": 21.14, "elapsed_time": "1:44:56", "remaining_time": "6:31:33", "throughput": 9277.42, "total_tokens": 58411088}
{"current_steps": 1055, "total_steps": 4968, "loss": 0.4499, "lr": 8.929910081807685e-06, "epoch": 0.4247181964573269, "percentage": 21.24, "elapsed_time": "1:45:29", "remaining_time": "6:31:17", "throughput": 9272.13, "total_tokens": 58690328}
{"current_steps": 1060, "total_steps": 4968, "loss": 0.4042, "lr": 8.920116462372723e-06, "epoch": 0.42673107890499196, "percentage": 21.34, "elapsed_time": "1:45:52", "remaining_time": "6:30:22", "throughput": 9284.12, "total_tokens": 58981968}
{"current_steps": 1065, "total_steps": 4968, "loss": 0.4248, "lr": 8.910283652944614e-06, "epoch": 0.428743961352657, "percentage": 21.44, "elapsed_time": "1:46:25", "remaining_time": "6:30:03", "throughput": 9279.29, "total_tokens": 59257176}
{"current_steps": 1070, "total_steps": 4968, "loss": 0.4202, "lr": 8.900411751823427e-06, "epoch": 0.4307568438003221, "percentage": 21.54, "elapsed_time": "1:46:54", "remaining_time": "6:29:27", "throughput": 9283.92, "total_tokens": 59551288}
{"current_steps": 1075, "total_steps": 4968, "loss": 0.4336, "lr": 8.890500857700049e-06, "epoch": 0.4327697262479871, "percentage": 21.64, "elapsed_time": "1:47:24", "remaining_time": "6:28:56", "throughput": 9280.39, "total_tokens": 59802968}
{"current_steps": 1080, "total_steps": 4968, "loss": 0.4087, "lr": 8.88055106965517e-06, "epoch": 0.43478260869565216, "percentage": 21.74, "elapsed_time": "1:47:58", "remaining_time": "6:28:41", "throughput": 9274.23, "total_tokens": 60081152}
{"current_steps": 1085, "total_steps": 4968, "loss": 0.4111, "lr": 8.870562487158317e-06, "epoch": 0.4367954911433172, "percentage": 21.84, "elapsed_time": "1:48:26", "remaining_time": "6:28:04", "throughput": 9275.27, "total_tokens": 60347144}
{"current_steps": 1090, "total_steps": 4968, "loss": 0.4005, "lr": 8.860535210066851e-06, "epoch": 0.4388083735909823, "percentage": 21.94, "elapsed_time": "1:48:55", "remaining_time": "6:27:31", "throughput": 9279.61, "total_tokens": 60646176}
{"current_steps": 1095, "total_steps": 4968, "loss": 0.42, "lr": 8.850469338624968e-06, "epoch": 0.44082125603864736, "percentage": 22.04, "elapsed_time": "1:49:27", "remaining_time": "6:27:07", "throughput": 9276.58, "total_tokens": 60919904}
{"current_steps": 1100, "total_steps": 4968, "loss": 0.4269, "lr": 8.840364973462697e-06, "epoch": 0.4428341384863124, "percentage": 22.14, "elapsed_time": "1:49:53", "remaining_time": "6:26:26", "throughput": 9281.91, "total_tokens": 61203944}
{"current_steps": 1105, "total_steps": 4968, "loss": 0.42, "lr": 8.83022221559489e-06, "epoch": 0.44484702093397743, "percentage": 22.24, "elapsed_time": "1:50:21", "remaining_time": "6:25:46", "throughput": 9288.72, "total_tokens": 61500688}
{"current_steps": 1110, "total_steps": 4968, "loss": 0.4155, "lr": 8.820041166420228e-06, "epoch": 0.4468599033816425, "percentage": 22.34, "elapsed_time": "1:50:45", "remaining_time": "6:24:57", "throughput": 9293.73, "total_tokens": 61761752}
{"current_steps": 1115, "total_steps": 4968, "loss": 0.4029, "lr": 8.809821927720182e-06, "epoch": 0.44887278582930756, "percentage": 22.44, "elapsed_time": "1:51:08", "remaining_time": "6:24:03", "throughput": 9302.9, "total_tokens": 62034568}
{"current_steps": 1120, "total_steps": 4968, "loss": 0.4241, "lr": 8.799564601658022e-06, "epoch": 0.45088566827697263, "percentage": 22.54, "elapsed_time": "1:51:37", "remaining_time": "6:23:32", "throughput": 9303.22, "total_tokens": 62312536}
{"current_steps": 1125, "total_steps": 4968, "loss": 0.4015, "lr": 8.789269290777774e-06, "epoch": 0.4528985507246377, "percentage": 22.64, "elapsed_time": "1:52:08", "remaining_time": "6:23:05", "throughput": 9304.0, "total_tokens": 62604504}
{"current_steps": 1130, "total_steps": 4968, "loss": 0.4176, "lr": 8.778936098003208e-06, "epoch": 0.45491143317230276, "percentage": 22.75, "elapsed_time": "1:52:43", "remaining_time": "6:22:51", "throughput": 9295.91, "total_tokens": 62870376}
{"current_steps": 1135, "total_steps": 4968, "loss": 0.4079, "lr": 8.768565126636806e-06, "epoch": 0.45692431561996777, "percentage": 22.85, "elapsed_time": "1:53:09", "remaining_time": "6:22:09", "throughput": 9303.55, "total_tokens": 63167576}
{"current_steps": 1140, "total_steps": 4968, "loss": 0.4161, "lr": 8.758156480358725e-06, "epoch": 0.45893719806763283, "percentage": 22.95, "elapsed_time": "1:53:33", "remaining_time": "6:21:18", "throughput": 9308.38, "total_tokens": 63421152}
{"current_steps": 1145, "total_steps": 4968, "loss": 0.3905, "lr": 8.747710263225768e-06, "epoch": 0.4609500805152979, "percentage": 23.05, "elapsed_time": "1:54:00", "remaining_time": "6:20:40", "throughput": 9309.98, "total_tokens": 63688680}
{"current_steps": 1150, "total_steps": 4968, "loss": 0.4339, "lr": 8.737226579670332e-06, "epoch": 0.46296296296296297, "percentage": 23.15, "elapsed_time": "1:54:29", "remaining_time": "6:20:07", "throughput": 9310.42, "total_tokens": 63959584}
{"current_steps": 1155, "total_steps": 4968, "loss": 0.4133, "lr": 8.726705534499382e-06, "epoch": 0.46497584541062803, "percentage": 23.25, "elapsed_time": "1:54:55", "remaining_time": "6:19:25", "throughput": 9311.7, "total_tokens": 64213416}
{"current_steps": 1160, "total_steps": 4968, "loss": 0.4012, "lr": 8.716147232893382e-06, "epoch": 0.4669887278582931, "percentage": 23.35, "elapsed_time": "1:55:27", "remaining_time": "6:19:01", "throughput": 9310.41, "total_tokens": 64497912}
{"current_steps": 1165, "total_steps": 4968, "loss": 0.4135, "lr": 8.705551780405264e-06, "epoch": 0.4690016103059581, "percentage": 23.45, "elapsed_time": "1:55:56", "remaining_time": "6:18:29", "throughput": 9311.84, "total_tokens": 64780848}
{"current_steps": 1170, "total_steps": 4968, "loss": 0.421, "lr": 8.694919282959353e-06, "epoch": 0.47101449275362317, "percentage": 23.55, "elapsed_time": "1:56:22", "remaining_time": "6:17:47", "throughput": 9316.09, "total_tokens": 65054040}
{"current_steps": 1175, "total_steps": 4968, "loss": 0.4014, "lr": 8.684249846850328e-06, "epoch": 0.47302737520128824, "percentage": 23.65, "elapsed_time": "1:56:52", "remaining_time": "6:17:15", "throughput": 9318.96, "total_tokens": 65345304}
{"current_steps": 1180, "total_steps": 4968, "loss": 0.4398, "lr": 8.673543578742141e-06, "epoch": 0.4750402576489533, "percentage": 23.75, "elapsed_time": "1:57:20", "remaining_time": "6:16:39", "throughput": 9321.72, "total_tokens": 65625352}
{"current_steps": 1185, "total_steps": 4968, "loss": 0.417, "lr": 8.662800585666963e-06, "epoch": 0.47705314009661837, "percentage": 23.85, "elapsed_time": "1:57:56", "remaining_time": "6:16:29", "throughput": 9314.72, "total_tokens": 65912288}
{"current_steps": 1190, "total_steps": 4968, "loss": 0.4081, "lr": 8.652020975024114e-06, "epoch": 0.47906602254428343, "percentage": 23.95, "elapsed_time": "1:58:31", "remaining_time": "6:16:16", "throughput": 9310.55, "total_tokens": 66208080}
{"current_steps": 1195, "total_steps": 4968, "loss": 0.3991, "lr": 8.641204854578975e-06, "epoch": 0.4810789049919485, "percentage": 24.05, "elapsed_time": "1:59:01", "remaining_time": "6:15:47", "throughput": 9311.03, "total_tokens": 66494368}
{"current_steps": 1200, "total_steps": 4968, "loss": 0.4278, "lr": 8.63035233246193e-06, "epoch": 0.4830917874396135, "percentage": 24.15, "elapsed_time": "1:59:33", "remaining_time": "6:15:25", "throughput": 9306.05, "total_tokens": 66760448}
{"current_steps": 1205, "total_steps": 4968, "loss": 0.4183, "lr": 8.61946351716727e-06, "epoch": 0.4851046698872786, "percentage": 24.26, "elapsed_time": "2:00:01", "remaining_time": "6:14:48", "throughput": 9303.62, "total_tokens": 66997576}
{"current_steps": 1210, "total_steps": 4968, "loss": 0.3992, "lr": 8.608538517552121e-06, "epoch": 0.48711755233494364, "percentage": 24.36, "elapsed_time": "2:00:34", "remaining_time": "6:14:29", "throughput": 9298.57, "total_tokens": 67271736}
{"current_steps": 1215, "total_steps": 4968, "loss": 0.4436, "lr": 8.597577442835343e-06, "epoch": 0.4891304347826087, "percentage": 24.46, "elapsed_time": "2:01:01", "remaining_time": "6:13:49", "throughput": 9301.35, "total_tokens": 67538936}
{"current_steps": 1220, "total_steps": 4968, "loss": 0.3819, "lr": 8.586580402596448e-06, "epoch": 0.49114331723027377, "percentage": 24.56, "elapsed_time": "2:01:27", "remaining_time": "6:13:08", "throughput": 9304.34, "total_tokens": 67806248}
{"current_steps": 1225, "total_steps": 4968, "loss": 0.4269, "lr": 8.575547506774498e-06, "epoch": 0.49315619967793883, "percentage": 24.66, "elapsed_time": "2:01:56", "remaining_time": "6:12:35", "throughput": 9302.79, "total_tokens": 68063000}
{"current_steps": 1230, "total_steps": 4968, "loss": 0.4279, "lr": 8.56447886566701e-06, "epoch": 0.49516908212560384, "percentage": 24.76, "elapsed_time": "2:02:21", "remaining_time": "6:11:50", "throughput": 9307.52, "total_tokens": 68330672}
{"current_steps": 1235, "total_steps": 4968, "loss": 0.4165, "lr": 8.553374589928851e-06, "epoch": 0.4971819645732689, "percentage": 24.86, "elapsed_time": "2:02:56", "remaining_time": "6:11:36", "throughput": 9301.12, "total_tokens": 68610320}
{"current_steps": 1240, "total_steps": 4968, "loss": 0.4048, "lr": 8.542234790571136e-06, "epoch": 0.499194847020934, "percentage": 24.96, "elapsed_time": "2:03:20", "remaining_time": "6:10:49", "throughput": 9308.54, "total_tokens": 68887656}
{"current_steps": 1245, "total_steps": 4968, "loss": 0.4076, "lr": 8.531059578960111e-06, "epoch": 0.501207729468599, "percentage": 25.06, "elapsed_time": "2:03:48", "remaining_time": "6:10:12", "throughput": 9312.02, "total_tokens": 69170832}
{"current_steps": 1250, "total_steps": 4968, "loss": 0.4199, "lr": 8.519849066816046e-06, "epoch": 0.5032206119162641, "percentage": 25.16, "elapsed_time": "2:04:08", "remaining_time": "6:09:15", "throughput": 9324.17, "total_tokens": 69454320}
{"current_steps": 1255, "total_steps": 4968, "loss": 0.4133, "lr": 8.508603366212113e-06, "epoch": 0.5052334943639292, "percentage": 25.26, "elapsed_time": "2:04:35", "remaining_time": "6:08:35", "throughput": 9325.26, "total_tokens": 69706760}
{"current_steps": 1260, "total_steps": 4968, "loss": 0.3747, "lr": 8.497322589573272e-06, "epoch": 0.5072463768115942, "percentage": 25.36, "elapsed_time": "2:05:07", "remaining_time": "6:08:12", "throughput": 9320.78, "total_tokens": 69971696}
{"current_steps": 1265, "total_steps": 4968, "loss": 0.4276, "lr": 8.486006849675142e-06, "epoch": 0.5092592592592593, "percentage": 25.46, "elapsed_time": "2:05:33", "remaining_time": "6:07:31", "throughput": 9323.19, "total_tokens": 70233552}
{"current_steps": 1270, "total_steps": 4968, "loss": 0.4103, "lr": 8.474656259642874e-06, "epoch": 0.5112721417069244, "percentage": 25.56, "elapsed_time": "2:06:04", "remaining_time": "6:07:07", "throughput": 9317.32, "total_tokens": 70484672}
{"current_steps": 1275, "total_steps": 4968, "loss": 0.4062, "lr": 8.46327093295002e-06, "epoch": 0.5132850241545893, "percentage": 25.66, "elapsed_time": "2:06:32", "remaining_time": "6:06:31", "throughput": 9321.96, "total_tokens": 70777128}
{"current_steps": 1280, "total_steps": 4968, "loss": 0.4385, "lr": 8.451850983417404e-06, "epoch": 0.5152979066022544, "percentage": 25.76, "elapsed_time": "2:06:58", "remaining_time": "6:05:50", "throughput": 9325.5, "total_tokens": 71046616}
{"current_steps": 1285, "total_steps": 4968, "loss": 0.401, "lr": 8.440396525211976e-06, "epoch": 0.5173107890499195, "percentage": 25.87, "elapsed_time": "2:07:21", "remaining_time": "6:05:01", "throughput": 9335.88, "total_tokens": 71338800}
{"current_steps": 1290, "total_steps": 4968, "loss": 0.4165, "lr": 8.428907672845674e-06, "epoch": 0.5193236714975845, "percentage": 25.97, "elapsed_time": "2:07:46", "remaining_time": "6:04:17", "throughput": 9337.43, "total_tokens": 71582640}
{"current_steps": 1295, "total_steps": 4968, "loss": 0.4286, "lr": 8.417384541174283e-06, "epoch": 0.5213365539452496, "percentage": 26.07, "elapsed_time": "2:08:08", "remaining_time": "6:03:28", "throughput": 9347.5, "total_tokens": 71872720}
{"current_steps": 1300, "total_steps": 4968, "loss": 0.4322, "lr": 8.405827245396279e-06, "epoch": 0.5233494363929146, "percentage": 26.17, "elapsed_time": "2:08:44", "remaining_time": "6:03:13", "throughput": 9344.07, "total_tokens": 72174080}
{"current_steps": 1305, "total_steps": 4968, "loss": 0.4092, "lr": 8.394235901051687e-06, "epoch": 0.5253623188405797, "percentage": 26.27, "elapsed_time": "2:09:13", "remaining_time": "6:02:43", "throughput": 9340.35, "total_tokens": 72421432}
{"current_steps": 1310, "total_steps": 4968, "loss": 0.3822, "lr": 8.382610624020913e-06, "epoch": 0.5273752012882448, "percentage": 26.37, "elapsed_time": "2:09:45", "remaining_time": "6:02:19", "throughput": 9337.52, "total_tokens": 72696312}
{"current_steps": 1315, "total_steps": 4968, "loss": 0.4106, "lr": 8.370951530523602e-06, "epoch": 0.5293880837359098, "percentage": 26.47, "elapsed_time": "2:10:12", "remaining_time": "6:01:41", "throughput": 9340.68, "total_tokens": 72970264}
{"current_steps": 1320, "total_steps": 4968, "loss": 0.4172, "lr": 8.359258737117463e-06, "epoch": 0.5314009661835749, "percentage": 26.57, "elapsed_time": "2:10:43", "remaining_time": "6:01:17", "throughput": 9336.32, "total_tokens": 73232672}
{"current_steps": 1325, "total_steps": 4968, "loss": 0.4056, "lr": 8.347532360697105e-06, "epoch": 0.53341384863124, "percentage": 26.67, "elapsed_time": "2:11:16", "remaining_time": "6:00:57", "throughput": 9333.32, "total_tokens": 73518464}
{"current_steps": 1330, "total_steps": 4968, "loss": 0.3938, "lr": 8.335772518492878e-06, "epoch": 0.535426731078905, "percentage": 26.77, "elapsed_time": "2:11:50", "remaining_time": "6:00:37", "throughput": 9327.93, "total_tokens": 73785808}
{"current_steps": 1335, "total_steps": 4968, "loss": 0.4377, "lr": 8.323979328069689e-06, "epoch": 0.5374396135265701, "percentage": 26.87, "elapsed_time": "2:12:20", "remaining_time": "6:00:09", "throughput": 9326.42, "total_tokens": 74059720}
{"current_steps": 1340, "total_steps": 4968, "loss": 0.4267, "lr": 8.312152907325837e-06, "epoch": 0.5394524959742351, "percentage": 26.97, "elapsed_time": "2:12:55", "remaining_time": "5:59:54", "throughput": 9321.43, "total_tokens": 74346536}
{"current_steps": 1345, "total_steps": 4968, "loss": 0.4234, "lr": 8.300293374491821e-06, "epoch": 0.5414653784219001, "percentage": 27.07, "elapsed_time": "2:13:25", "remaining_time": "5:59:24", "throughput": 9321.74, "total_tokens": 74626960}
{"current_steps": 1350, "total_steps": 4968, "loss": 0.4116, "lr": 8.288400848129179e-06, "epoch": 0.5434782608695652, "percentage": 27.17, "elapsed_time": "2:13:58", "remaining_time": "5:59:03", "throughput": 9321.23, "total_tokens": 74928504}
{"current_steps": 1355, "total_steps": 4968, "loss": 0.3841, "lr": 8.276475447129278e-06, "epoch": 0.5454911433172303, "percentage": 27.27, "elapsed_time": "2:14:34", "remaining_time": "5:58:50", "throughput": 9316.67, "total_tokens": 75228432}
{"current_steps": 1360, "total_steps": 4968, "loss": 0.4082, "lr": 8.264517290712146e-06, "epoch": 0.5475040257648953, "percentage": 27.38, "elapsed_time": "2:14:58", "remaining_time": "5:58:05", "throughput": 9323.7, "total_tokens": 75509304}
{"current_steps": 1365, "total_steps": 4968, "loss": 0.4147, "lr": 8.252526498425271e-06, "epoch": 0.5495169082125604, "percentage": 27.48, "elapsed_time": "2:15:25", "remaining_time": "5:57:27", "throughput": 9328.71, "total_tokens": 75798112}
{"current_steps": 1370, "total_steps": 4968, "loss": 0.4163, "lr": 8.2405031901424e-06, "epoch": 0.5515297906602254, "percentage": 27.58, "elapsed_time": "2:15:53", "remaining_time": "5:56:52", "throughput": 9330.7, "total_tokens": 76073616}
{"current_steps": 1375, "total_steps": 4968, "loss": 0.4307, "lr": 8.228447486062355e-06, "epoch": 0.5535426731078905, "percentage": 27.68, "elapsed_time": "2:16:22", "remaining_time": "5:56:22", "throughput": 9329.58, "total_tokens": 76342592}
{"current_steps": 1380, "total_steps": 4968, "loss": 0.3974, "lr": 8.216359506707819e-06, "epoch": 0.5555555555555556, "percentage": 27.78, "elapsed_time": "2:16:54", "remaining_time": "5:55:56", "throughput": 9328.03, "total_tokens": 76621592}
{"current_steps": 1385, "total_steps": 4968, "loss": 0.4112, "lr": 8.20423937292414e-06, "epoch": 0.5575684380032206, "percentage": 27.88, "elapsed_time": "2:17:22", "remaining_time": "5:55:22", "throughput": 9331.13, "total_tokens": 76907904}
{"current_steps": 1390, "total_steps": 4968, "loss": 0.4179, "lr": 8.192087205878112e-06, "epoch": 0.5595813204508857, "percentage": 27.98, "elapsed_time": "2:17:57", "remaining_time": "5:55:06", "throughput": 9328.28, "total_tokens": 77214200}
{"current_steps": 1395, "total_steps": 4968, "loss": 0.4108, "lr": 8.17990312705678e-06, "epoch": 0.5615942028985508, "percentage": 28.08, "elapsed_time": "2:18:31", "remaining_time": "5:54:48", "throughput": 9320.08, "total_tokens": 77465448}
{"current_steps": 1400, "total_steps": 4968, "loss": 0.4103, "lr": 8.167687258266203e-06, "epoch": 0.5636070853462157, "percentage": 28.18, "elapsed_time": "2:18:59", "remaining_time": "5:54:14", "throughput": 9321.96, "total_tokens": 77741864}
{"current_steps": 1405, "total_steps": 4968, "loss": 0.3903, "lr": 8.155439721630265e-06, "epoch": 0.5656199677938808, "percentage": 28.28, "elapsed_time": "2:19:29", "remaining_time": "5:53:45", "throughput": 9323.9, "total_tokens": 78039024}
{"current_steps": 1410, "total_steps": 4968, "loss": 0.3872, "lr": 8.143160639589424e-06, "epoch": 0.5676328502415459, "percentage": 28.38, "elapsed_time": "2:20:02", "remaining_time": "5:53:23", "throughput": 9321.05, "total_tokens": 78323352}
{"current_steps": 1415, "total_steps": 4968, "loss": 0.3951, "lr": 8.130850134899508e-06, "epoch": 0.5696457326892109, "percentage": 28.48, "elapsed_time": "2:20:29", "remaining_time": "5:52:46", "throughput": 9324.98, "total_tokens": 78605544}
{"current_steps": 1420, "total_steps": 4968, "loss": 0.4369, "lr": 8.118508330630484e-06, "epoch": 0.571658615136876, "percentage": 28.58, "elapsed_time": "2:21:01", "remaining_time": "5:52:21", "throughput": 9322.99, "total_tokens": 78884656}
{"current_steps": 1425, "total_steps": 4968, "loss": 0.4105, "lr": 8.106135350165219e-06, "epoch": 0.5736714975845411, "percentage": 28.68, "elapsed_time": "2:21:34", "remaining_time": "5:51:58", "throughput": 9319.06, "total_tokens": 79156248}
{"current_steps": 1430, "total_steps": 4968, "loss": 0.4199, "lr": 8.093731317198262e-06, "epoch": 0.5756843800322061, "percentage": 28.78, "elapsed_time": "2:21:59", "remaining_time": "5:51:19", "throughput": 9324.14, "total_tokens": 79440224}
{"current_steps": 1435, "total_steps": 4968, "loss": 0.4022, "lr": 8.08129635573459e-06, "epoch": 0.5776972624798712, "percentage": 28.88, "elapsed_time": "2:22:36", "remaining_time": "5:51:05", "throughput": 9316.53, "total_tokens": 79715160}
{"current_steps": 1440, "total_steps": 4968, "loss": 0.4251, "lr": 8.068830590088386e-06, "epoch": 0.5797101449275363, "percentage": 28.99, "elapsed_time": "2:23:12", "remaining_time": "5:50:50", "throughput": 9307.28, "total_tokens": 79969208}
{"current_steps": 1445, "total_steps": 4968, "loss": 0.4166, "lr": 8.056334144881776e-06, "epoch": 0.5817230273752013, "percentage": 29.09, "elapsed_time": "2:23:49", "remaining_time": "5:50:38", "throughput": 9302.56, "total_tokens": 80274104}
{"current_steps": 1450, "total_steps": 4968, "loss": 0.4187, "lr": 8.043807145043604e-06, "epoch": 0.5837359098228664, "percentage": 29.19, "elapsed_time": "2:24:20", "remaining_time": "5:50:11", "throughput": 9304.27, "total_tokens": 80575952}
{"current_steps": 1455, "total_steps": 4968, "loss": 0.4365, "lr": 8.031249715808166e-06, "epoch": 0.5857487922705314, "percentage": 29.29, "elapsed_time": "2:24:52", "remaining_time": "5:49:48", "throughput": 9303.75, "total_tokens": 80875656}
{"current_steps": 1460, "total_steps": 4968, "loss": 0.416, "lr": 8.018661982713971e-06, "epoch": 0.5877616747181964, "percentage": 29.39, "elapsed_time": "2:25:25", "remaining_time": "5:49:24", "throughput": 9299.77, "total_tokens": 81141016}
{"current_steps": 1465, "total_steps": 4968, "loss": 0.4446, "lr": 8.006044071602476e-06, "epoch": 0.5897745571658615, "percentage": 29.49, "elapsed_time": "2:25:55", "remaining_time": "5:48:55", "throughput": 9299.46, "total_tokens": 81420136}
{"current_steps": 1470, "total_steps": 4968, "loss": 0.3903, "lr": 7.993396108616835e-06, "epoch": 0.5917874396135265, "percentage": 29.59, "elapsed_time": "2:26:23", "remaining_time": "5:48:20", "throughput": 9298.51, "total_tokens": 81671240}
{"current_steps": 1475, "total_steps": 4968, "loss": 0.4509, "lr": 7.980718220200633e-06, "epoch": 0.5938003220611916, "percentage": 29.69, "elapsed_time": "2:26:56", "remaining_time": "5:47:58", "throughput": 9292.44, "total_tokens": 81924936}
{"current_steps": 1480, "total_steps": 4968, "loss": 0.3863, "lr": 7.968010533096626e-06, "epoch": 0.5958132045088567, "percentage": 29.79, "elapsed_time": "2:27:30", "remaining_time": "5:47:37", "throughput": 9288.58, "total_tokens": 82205400}
{"current_steps": 1485, "total_steps": 4968, "loss": 0.4269, "lr": 7.955273174345469e-06, "epoch": 0.5978260869565217, "percentage": 29.89, "elapsed_time": "2:28:05", "remaining_time": "5:47:21", "throughput": 9284.86, "total_tokens": 82502664}
{"current_steps": 1490, "total_steps": 4968, "loss": 0.423, "lr": 7.942506271284453e-06, "epoch": 0.5998389694041868, "percentage": 29.99, "elapsed_time": "2:28:34", "remaining_time": "5:46:49", "throughput": 9283.15, "total_tokens": 82757296}
{"current_steps": 1495, "total_steps": 4968, "loss": 0.4119, "lr": 7.929709951546224e-06, "epoch": 0.6018518518518519, "percentage": 30.09, "elapsed_time": "2:29:06", "remaining_time": "5:46:24", "throughput": 9279.72, "total_tokens": 83024168}
{"current_steps": 1500, "total_steps": 4968, "loss": 0.3975, "lr": 7.916884343057514e-06, "epoch": 0.6038647342995169, "percentage": 30.19, "elapsed_time": "2:29:37", "remaining_time": "5:45:56", "throughput": 9277.36, "total_tokens": 83289440}
{"current_steps": 1505, "total_steps": 4968, "loss": 0.3957, "lr": 7.904029574037856e-06, "epoch": 0.605877616747182, "percentage": 30.29, "elapsed_time": "2:30:05", "remaining_time": "5:45:21", "throughput": 9280.95, "total_tokens": 83578104}
{"current_steps": 1510, "total_steps": 4968, "loss": 0.4119, "lr": 7.891145772998308e-06, "epoch": 0.6078904991948471, "percentage": 30.39, "elapsed_time": "2:30:41", "remaining_time": "5:45:04", "throughput": 9274.56, "total_tokens": 83852400}
{"current_steps": 1515, "total_steps": 4968, "loss": 0.4114, "lr": 7.878233068740167e-06, "epoch": 0.6099033816425121, "percentage": 30.5, "elapsed_time": "2:31:08", "remaining_time": "5:44:28", "throughput": 9278.71, "total_tokens": 84142088}
{"current_steps": 1520, "total_steps": 4968, "loss": 0.4299, "lr": 7.865291590353673e-06, "epoch": 0.6119162640901772, "percentage": 30.6, "elapsed_time": "2:31:37", "remaining_time": "5:43:56", "throughput": 9276.24, "total_tokens": 84387064}
{"current_steps": 1525, "total_steps": 4968, "loss": 0.414, "lr": 7.85232146721673e-06, "epoch": 0.6139291465378421, "percentage": 30.7, "elapsed_time": "2:31:59", "remaining_time": "5:43:09", "throughput": 9285.66, "total_tokens": 84681760}
{"current_steps": 1530, "total_steps": 4968, "loss": 0.3939, "lr": 7.83932282899361e-06, "epoch": 0.6159420289855072, "percentage": 30.8, "elapsed_time": "2:32:27", "remaining_time": "5:42:35", "throughput": 9288.48, "total_tokens": 84970560}
{"current_steps": 1535, "total_steps": 4968, "loss": 0.4165, "lr": 7.826295805633647e-06, "epoch": 0.6179549114331723, "percentage": 30.9, "elapsed_time": "2:32:58", "remaining_time": "5:42:07", "throughput": 9284.87, "total_tokens": 85221368}
{"current_steps": 1540, "total_steps": 4968, "loss": 0.4124, "lr": 7.813240527369958e-06, "epoch": 0.6199677938808373, "percentage": 31.0, "elapsed_time": "2:33:28", "remaining_time": "5:41:37", "throughput": 9288.24, "total_tokens": 85527928}
{"current_steps": 1545, "total_steps": 4968, "loss": 0.4255, "lr": 7.800157124718115e-06, "epoch": 0.6219806763285024, "percentage": 31.1, "elapsed_time": "2:33:58", "remaining_time": "5:41:09", "throughput": 9286.4, "total_tokens": 85796712}
{"current_steps": 1550, "total_steps": 4968, "loss": 0.4025, "lr": 7.787045728474862e-06, "epoch": 0.6239935587761675, "percentage": 31.2, "elapsed_time": "2:34:23", "remaining_time": "5:40:27", "throughput": 9290.32, "total_tokens": 86058784}
{"current_steps": 1555, "total_steps": 4968, "loss": 0.4256, "lr": 7.773906469716795e-06, "epoch": 0.6260064412238325, "percentage": 31.3, "elapsed_time": "2:34:57", "remaining_time": "5:40:06", "throughput": 9285.05, "total_tokens": 86327264}
{"current_steps": 1560, "total_steps": 4968, "loss": 0.3984, "lr": 7.76073947979906e-06, "epoch": 0.6280193236714976, "percentage": 31.4, "elapsed_time": "2:35:21", "remaining_time": "5:39:22", "throughput": 9291.73, "total_tokens": 86608720}
{"current_steps": 1565, "total_steps": 4968, "loss": 0.3923, "lr": 7.747544890354031e-06, "epoch": 0.6300322061191627, "percentage": 31.5, "elapsed_time": "2:35:47", "remaining_time": "5:38:44", "throughput": 9292.89, "total_tokens": 86861072}
{"current_steps": 1570, "total_steps": 4968, "loss": 0.4188, "lr": 7.734322833290002e-06, "epoch": 0.6320450885668277, "percentage": 31.6, "elapsed_time": "2:36:16", "remaining_time": "5:38:13", "throughput": 9292.99, "total_tokens": 87136000}
{"current_steps": 1575, "total_steps": 4968, "loss": 0.4144, "lr": 7.721073440789863e-06, "epoch": 0.6340579710144928, "percentage": 31.7, "elapsed_time": "2:36:41", "remaining_time": "5:37:33", "throughput": 9298.74, "total_tokens": 87420648}
{"current_steps": 1580, "total_steps": 4968, "loss": 0.4197, "lr": 7.707796845309782e-06, "epoch": 0.6360708534621579, "percentage": 31.8, "elapsed_time": "2:37:11", "remaining_time": "5:37:04", "throughput": 9298.16, "total_tokens": 87698832}
{"current_steps": 1585, "total_steps": 4968, "loss": 0.4038, "lr": 7.69449317957788e-06, "epoch": 0.6380837359098228, "percentage": 31.9, "elapsed_time": "2:37:42", "remaining_time": "5:36:36", "throughput": 9297.99, "total_tokens": 87983560}
{"current_steps": 1590, "total_steps": 4968, "loss": 0.4143, "lr": 7.681162576592896e-06, "epoch": 0.6400966183574879, "percentage": 32.0, "elapsed_time": "2:38:07", "remaining_time": "5:35:56", "throughput": 9300.24, "total_tokens": 88238112}
{"current_steps": 1595, "total_steps": 4968, "loss": 0.4131, "lr": 7.667805169622874e-06, "epoch": 0.6421095008051529, "percentage": 32.11, "elapsed_time": "2:38:36", "remaining_time": "5:35:25", "throughput": 9300.79, "total_tokens": 88514136}
{"current_steps": 1600, "total_steps": 4968, "loss": 0.4108, "lr": 7.65442109220382e-06, "epoch": 0.644122383252818, "percentage": 32.21, "elapsed_time": "2:39:08", "remaining_time": "5:34:58", "throughput": 9300.37, "total_tokens": 88801416}
{"current_steps": 1605, "total_steps": 4968, "loss": 0.3984, "lr": 7.641010478138365e-06, "epoch": 0.6461352657004831, "percentage": 32.31, "elapsed_time": "2:39:40", "remaining_time": "5:34:33", "throughput": 9300.07, "total_tokens": 89095008}
{"current_steps": 1610, "total_steps": 4968, "loss": 0.3996, "lr": 7.627573461494431e-06, "epoch": 0.6481481481481481, "percentage": 32.41, "elapsed_time": "2:40:09", "remaining_time": "5:34:02", "throughput": 9300.43, "total_tokens": 89371968}
{"current_steps": 1615, "total_steps": 4968, "loss": 0.4212, "lr": 7.614110176603893e-06, "epoch": 0.6501610305958132, "percentage": 32.51, "elapsed_time": "2:40:36", "remaining_time": "5:33:26", "throughput": 9303.52, "total_tokens": 89652280}
{"current_steps": 1620, "total_steps": 4968, "loss": 0.4112, "lr": 7.600620758061233e-06, "epoch": 0.6521739130434783, "percentage": 32.61, "elapsed_time": "2:41:04", "remaining_time": "5:32:53", "throughput": 9305.74, "total_tokens": 89934216}
{"current_steps": 1625, "total_steps": 4968, "loss": 0.4044, "lr": 7.587105340722194e-06, "epoch": 0.6541867954911433, "percentage": 32.71, "elapsed_time": "2:41:34", "remaining_time": "5:32:24", "throughput": 9304.11, "total_tokens": 90201848}
{"current_steps": 1630, "total_steps": 4968, "loss": 0.4221, "lr": 7.573564059702432e-06, "epoch": 0.6561996779388084, "percentage": 32.81, "elapsed_time": "2:42:09", "remaining_time": "5:32:04", "throughput": 9299.25, "total_tokens": 90476912}
{"current_steps": 1635, "total_steps": 4968, "loss": 0.3935, "lr": 7.55999705037617e-06, "epoch": 0.6582125603864735, "percentage": 32.91, "elapsed_time": "2:42:41", "remaining_time": "5:31:40", "throughput": 9297.07, "total_tokens": 90757344}
{"current_steps": 1640, "total_steps": 4968, "loss": 0.4108, "lr": 7.546404448374835e-06, "epoch": 0.6602254428341385, "percentage": 33.01, "elapsed_time": "2:43:05", "remaining_time": "5:30:58", "throughput": 9301.34, "total_tokens": 91022032}
{"current_steps": 1645, "total_steps": 4968, "loss": 0.3911, "lr": 7.532786389585715e-06, "epoch": 0.6622383252818036, "percentage": 33.11, "elapsed_time": "2:43:37", "remaining_time": "5:30:30", "throughput": 9299.38, "total_tokens": 91292160}
{"current_steps": 1650, "total_steps": 4968, "loss": 0.4167, "lr": 7.5191430101505894e-06, "epoch": 0.6642512077294686, "percentage": 33.21, "elapsed_time": "2:44:08", "remaining_time": "5:30:03", "throughput": 9295.96, "total_tokens": 91547568}
{"current_steps": 1655, "total_steps": 4968, "loss": 0.4038, "lr": 7.5054744464643666e-06, "epoch": 0.6662640901771336, "percentage": 33.31, "elapsed_time": "2:44:39", "remaining_time": "5:29:36", "throughput": 9292.96, "total_tokens": 91809704}
{"current_steps": 1660, "total_steps": 4968, "loss": 0.3984, "lr": 7.491780835173735e-06, "epoch": 0.6682769726247987, "percentage": 33.41, "elapsed_time": "2:45:03", "remaining_time": "5:28:56", "throughput": 9300.44, "total_tokens": 92110000}
{"current_steps": 1665, "total_steps": 4968, "loss": 0.3998, "lr": 7.478062313175784e-06, "epoch": 0.6702898550724637, "percentage": 33.51, "elapsed_time": "2:45:30", "remaining_time": "5:28:20", "throughput": 9300.74, "total_tokens": 92362424}
{"current_steps": 1670, "total_steps": 4968, "loss": 0.4099, "lr": 7.464319017616638e-06, "epoch": 0.6723027375201288, "percentage": 33.62, "elapsed_time": "2:46:04", "remaining_time": "5:27:57", "throughput": 9297.26, "total_tokens": 92638656}
{"current_steps": 1675, "total_steps": 4968, "loss": 0.4278, "lr": 7.450551085890087e-06, "epoch": 0.6743156199677939, "percentage": 33.72, "elapsed_time": "2:46:37", "remaining_time": "5:27:35", "throughput": 9294.36, "total_tokens": 92921648}
{"current_steps": 1680, "total_steps": 4968, "loss": 0.3996, "lr": 7.4367586556362125e-06, "epoch": 0.6763285024154589, "percentage": 33.82, "elapsed_time": "2:47:06", "remaining_time": "5:27:04", "throughput": 9293.85, "total_tokens": 93188816}
{"current_steps": 1685, "total_steps": 4968, "loss": 0.4223, "lr": 7.422941864740012e-06, "epoch": 0.678341384863124, "percentage": 33.92, "elapsed_time": "2:47:29", "remaining_time": "5:26:20", "throughput": 9300.61, "total_tokens": 93469840}
{"current_steps": 1690, "total_steps": 4968, "loss": 0.4353, "lr": 7.40910085133002e-06, "epoch": 0.6803542673107891, "percentage": 34.02, "elapsed_time": "2:48:05", "remaining_time": "5:26:02", "throughput": 9293.1, "total_tokens": 93728136}
{"current_steps": 1695, "total_steps": 4968, "loss": 0.4033, "lr": 7.395235753776925e-06, "epoch": 0.6823671497584541, "percentage": 34.12, "elapsed_time": "2:48:34", "remaining_time": "5:25:31", "throughput": 9292.46, "total_tokens": 93992976}
{"current_steps": 1700, "total_steps": 4968, "loss": 0.4061, "lr": 7.381346710692192e-06, "epoch": 0.6843800322061192, "percentage": 34.22, "elapsed_time": "2:48:54", "remaining_time": "5:24:41", "throughput": 9301.37, "total_tokens": 94261376}
{"current_steps": 1705, "total_steps": 4968, "loss": 0.415, "lr": 7.3674338609266705e-06, "epoch": 0.6863929146537843, "percentage": 34.32, "elapsed_time": "2:49:23", "remaining_time": "5:24:10", "throughput": 9301.6, "total_tokens": 94533288}
{"current_steps": 1710, "total_steps": 4968, "loss": 0.4091, "lr": 7.3534973435692106e-06, "epoch": 0.6884057971014492, "percentage": 34.42, "elapsed_time": "2:49:47", "remaining_time": "5:23:29", "throughput": 9303.83, "total_tokens": 94780728}
{"current_steps": 1715, "total_steps": 4968, "loss": 0.4162, "lr": 7.3395372979452675e-06, "epoch": 0.6904186795491143, "percentage": 34.52, "elapsed_time": "2:50:18", "remaining_time": "5:23:01", "throughput": 9302.32, "total_tokens": 95052216}
{"current_steps": 1720, "total_steps": 4968, "loss": 0.39, "lr": 7.325553863615516e-06, "epoch": 0.6924315619967794, "percentage": 34.62, "elapsed_time": "2:50:46", "remaining_time": "5:22:28", "throughput": 9302.65, "total_tokens": 95317512}
{"current_steps": 1725, "total_steps": 4968, "loss": 0.3915, "lr": 7.311547180374448e-06, "epoch": 0.6944444444444444, "percentage": 34.72, "elapsed_time": "2:51:09", "remaining_time": "5:21:45", "throughput": 9309.14, "total_tokens": 95595816}
{"current_steps": 1730, "total_steps": 4968, "loss": 0.4359, "lr": 7.297517388248983e-06, "epoch": 0.6964573268921095, "percentage": 34.82, "elapsed_time": "2:51:39", "remaining_time": "5:21:16", "throughput": 9307.2, "total_tokens": 95857792}
{"current_steps": 1735, "total_steps": 4968, "loss": 0.4279, "lr": 7.283464627497056e-06, "epoch": 0.6984702093397746, "percentage": 34.92, "elapsed_time": "2:52:11", "remaining_time": "5:20:51", "throughput": 9302.66, "total_tokens": 96111304}
{"current_steps": 1740, "total_steps": 4968, "loss": 0.4117, "lr": 7.269389038606231e-06, "epoch": 0.7004830917874396, "percentage": 35.02, "elapsed_time": "2:52:34", "remaining_time": "5:20:09", "throughput": 9307.28, "total_tokens": 96375072}
{"current_steps": 1745, "total_steps": 4968, "loss": 0.3852, "lr": 7.255290762292286e-06, "epoch": 0.7024959742351047, "percentage": 35.12, "elapsed_time": "2:53:04", "remaining_time": "5:19:39", "throughput": 9308.77, "total_tokens": 96665096}
{"current_steps": 1750, "total_steps": 4968, "loss": 0.4035, "lr": 7.241169939497801e-06, "epoch": 0.7045088566827697, "percentage": 35.23, "elapsed_time": "2:53:32", "remaining_time": "5:19:07", "throughput": 9309.98, "total_tokens": 96944624}
{"current_steps": 1755, "total_steps": 4968, "loss": 0.415, "lr": 7.227026711390766e-06, "epoch": 0.7065217391304348, "percentage": 35.33, "elapsed_time": "2:54:01", "remaining_time": "5:18:35", "throughput": 9309.5, "total_tokens": 97202880}
{"current_steps": 1760, "total_steps": 4968, "loss": 0.4244, "lr": 7.2128612193631595e-06, "epoch": 0.7085346215780999, "percentage": 35.43, "elapsed_time": "2:54:28", "remaining_time": "5:18:01", "throughput": 9314.77, "total_tokens": 97511016}
{"current_steps": 1765, "total_steps": 4968, "loss": 0.4286, "lr": 7.198673605029529e-06, "epoch": 0.7105475040257649, "percentage": 35.53, "elapsed_time": "2:54:59", "remaining_time": "5:17:33", "throughput": 9313.14, "total_tokens": 97781072}
{"current_steps": 1770, "total_steps": 4968, "loss": 0.409, "lr": 7.18446401022559e-06, "epoch": 0.7125603864734299, "percentage": 35.63, "elapsed_time": "2:55:35", "remaining_time": "5:17:15", "throughput": 9306.6, "total_tokens": 98050776}
{"current_steps": 1775, "total_steps": 4968, "loss": 0.4178, "lr": 7.1702325770067935e-06, "epoch": 0.714573268921095, "percentage": 35.73, "elapsed_time": "2:56:08", "remaining_time": "5:16:50", "throughput": 9304.44, "total_tokens": 98331192}
{"current_steps": 1780, "total_steps": 4968, "loss": 0.3932, "lr": 7.155979447646916e-06, "epoch": 0.71658615136876, "percentage": 35.83, "elapsed_time": "2:56:32", "remaining_time": "5:16:11", "throughput": 9307.17, "total_tokens": 98587896}
{"current_steps": 1785, "total_steps": 4968, "loss": 0.4151, "lr": 7.141704764636632e-06, "epoch": 0.7185990338164251, "percentage": 35.93, "elapsed_time": "2:57:02", "remaining_time": "5:15:42", "throughput": 9305.55, "total_tokens": 98849320}
{"current_steps": 1790, "total_steps": 4968, "loss": 0.4117, "lr": 7.127408670682094e-06, "epoch": 0.7206119162640902, "percentage": 36.03, "elapsed_time": "2:57:36", "remaining_time": "5:15:18", "throughput": 9301.76, "total_tokens": 99119776}
{"current_steps": 1795, "total_steps": 4968, "loss": 0.3865, "lr": 7.113091308703498e-06, "epoch": 0.7226247987117552, "percentage": 36.13, "elapsed_time": "2:58:07", "remaining_time": "5:14:52", "throughput": 9300.43, "total_tokens": 99397616}
{"current_steps": 1800, "total_steps": 4968, "loss": 0.4035, "lr": 7.0987528218336655e-06, "epoch": 0.7246376811594203, "percentage": 36.23, "elapsed_time": "2:58:38", "remaining_time": "5:14:24", "throughput": 9299.21, "total_tokens": 99675792}
{"current_steps": 1805, "total_steps": 4968, "loss": 0.3899, "lr": 7.084393353416601e-06, "epoch": 0.7266505636070854, "percentage": 36.33, "elapsed_time": "2:59:09", "remaining_time": "5:13:56", "throughput": 9298.56, "total_tokens": 99951568}
{"current_steps": 1810, "total_steps": 4968, "loss": 0.4243, "lr": 7.070013047006068e-06, "epoch": 0.7286634460547504, "percentage": 36.43, "elapsed_time": "2:59:42", "remaining_time": "5:13:32", "throughput": 9296.37, "total_tokens": 100236096}
{"current_steps": 1815, "total_steps": 4968, "loss": 0.4052, "lr": 7.055612046364151e-06, "epoch": 0.7306763285024155, "percentage": 36.53, "elapsed_time": "3:00:18", "remaining_time": "5:13:13", "throughput": 9290.4, "total_tokens": 100505616}
{"current_steps": 1820, "total_steps": 4968, "loss": 0.4107, "lr": 7.041190495459816e-06, "epoch": 0.7326892109500805, "percentage": 36.63, "elapsed_time": "3:00:52", "remaining_time": "5:12:51", "throughput": 9287.83, "total_tokens": 100798848}
{"current_steps": 1825, "total_steps": 4968, "loss": 0.4015, "lr": 7.026748538467474e-06, "epoch": 0.7347020933977456, "percentage": 36.74, "elapsed_time": "3:01:21", "remaining_time": "5:12:20", "throughput": 9288.09, "total_tokens": 101070488}
{"current_steps": 1830, "total_steps": 4968, "loss": 0.4101, "lr": 7.012286319765538e-06, "epoch": 0.7367149758454107, "percentage": 36.84, "elapsed_time": "3:01:53", "remaining_time": "5:11:53", "throughput": 9287.69, "total_tokens": 101358128}
{"current_steps": 1835, "total_steps": 4968, "loss": 0.4067, "lr": 6.997803983934982e-06, "epoch": 0.7387278582930756, "percentage": 36.94, "elapsed_time": "3:02:24", "remaining_time": "5:11:26", "throughput": 9286.9, "total_tokens": 101643344}
{"current_steps": 1840, "total_steps": 4968, "loss": 0.3939, "lr": 6.983301675757892e-06, "epoch": 0.7407407407407407, "percentage": 37.04, "elapsed_time": "3:02:53", "remaining_time": "5:10:54", "throughput": 9287.86, "total_tokens": 101920000}
{"current_steps": 1845, "total_steps": 4968, "loss": 0.4289, "lr": 6.96877954021602e-06, "epoch": 0.7427536231884058, "percentage": 37.14, "elapsed_time": "3:03:20", "remaining_time": "5:10:20", "throughput": 9291.27, "total_tokens": 102208776}
{"current_steps": 1850, "total_steps": 4968, "loss": 0.397, "lr": 6.9542377224893365e-06, "epoch": 0.7447665056360708, "percentage": 37.24, "elapsed_time": "3:03:52", "remaining_time": "5:09:54", "throughput": 9288.66, "total_tokens": 102480896}
{"current_steps": 1855, "total_steps": 4968, "loss": 0.4126, "lr": 6.939676367954582e-06, "epoch": 0.7467793880837359, "percentage": 37.34, "elapsed_time": "3:04:29", "remaining_time": "5:09:36", "throughput": 9283.11, "total_tokens": 102761648}
{"current_steps": 1860, "total_steps": 4968, "loss": 0.3929, "lr": 6.925095622183801e-06, "epoch": 0.748792270531401, "percentage": 37.44, "elapsed_time": "3:04:56", "remaining_time": "5:09:02", "throughput": 9283.42, "total_tokens": 103017568}
{"current_steps": 1865, "total_steps": 4968, "loss": 0.3881, "lr": 6.910495630942899e-06, "epoch": 0.750805152979066, "percentage": 37.54, "elapsed_time": "3:05:25", "remaining_time": "5:08:30", "throughput": 9284.86, "total_tokens": 103298384}
{"current_steps": 1870, "total_steps": 4968, "loss": 0.4048, "lr": 6.895876540190185e-06, "epoch": 0.7528180354267311, "percentage": 37.64, "elapsed_time": "3:06:02", "remaining_time": "5:08:12", "throughput": 9279.65, "total_tokens": 103585408}
{"current_steps": 1875, "total_steps": 4968, "loss": 0.39, "lr": 6.8812384960749024e-06, "epoch": 0.7548309178743962, "percentage": 37.74, "elapsed_time": "3:06:33", "remaining_time": "5:07:44", "throughput": 9279.39, "total_tokens": 103868056}
{"current_steps": 1880, "total_steps": 4968, "loss": 0.4114, "lr": 6.8665816449357795e-06, "epoch": 0.7568438003220612, "percentage": 37.84, "elapsed_time": "3:07:01", "remaining_time": "5:07:11", "throughput": 9279.24, "total_tokens": 104123080}
{"current_steps": 1885, "total_steps": 4968, "loss": 0.4074, "lr": 6.851906133299556e-06, "epoch": 0.7588566827697263, "percentage": 37.94, "elapsed_time": "3:07:30", "remaining_time": "5:06:40", "throughput": 9278.63, "total_tokens": 104389184}
{"current_steps": 1890, "total_steps": 4968, "loss": 0.3969, "lr": 6.837212107879528e-06, "epoch": 0.7608695652173914, "percentage": 38.04, "elapsed_time": "3:08:04", "remaining_time": "5:06:17", "throughput": 9276.95, "total_tokens": 104685376}
{"current_steps": 1895, "total_steps": 4968, "loss": 0.4031, "lr": 6.822499715574076e-06, "epoch": 0.7628824476650563, "percentage": 38.14, "elapsed_time": "3:08:25", "remaining_time": "5:05:33", "throughput": 9284.9, "total_tokens": 104970752}
{"current_steps": 1900, "total_steps": 4968, "loss": 0.3981, "lr": 6.8077691034651936e-06, "epoch": 0.7648953301127214, "percentage": 38.24, "elapsed_time": "3:08:57", "remaining_time": "5:05:06", "throughput": 9283.21, "total_tokens": 105245720}
{"current_steps": 1905, "total_steps": 4968, "loss": 0.4206, "lr": 6.7930204188170244e-06, "epoch": 0.7669082125603864, "percentage": 38.35, "elapsed_time": "3:09:30", "remaining_time": "5:04:42", "throughput": 9281.34, "total_tokens": 105532392}
{"current_steps": 1910, "total_steps": 4968, "loss": 0.377, "lr": 6.778253809074384e-06, "epoch": 0.7689210950080515, "percentage": 38.45, "elapsed_time": "3:09:58", "remaining_time": "5:04:09", "throughput": 9283.39, "total_tokens": 105816496}
{"current_steps": 1915, "total_steps": 4968, "loss": 0.4185, "lr": 6.7634694218612865e-06, "epoch": 0.7709339774557166, "percentage": 38.55, "elapsed_time": "3:10:26", "remaining_time": "5:03:37", "throughput": 9281.68, "total_tokens": 106061088}
{"current_steps": 1920, "total_steps": 4968, "loss": 0.3815, "lr": 6.748667404979474e-06, "epoch": 0.7729468599033816, "percentage": 38.65, "elapsed_time": "3:11:00", "remaining_time": "5:03:13", "throughput": 9279.62, "total_tokens": 106348248}
{"current_steps": 1925, "total_steps": 4968, "loss": 0.3946, "lr": 6.733847906406933e-06, "epoch": 0.7749597423510467, "percentage": 38.75, "elapsed_time": "3:11:23", "remaining_time": "5:02:32", "throughput": 9283.89, "total_tokens": 106608736}
{"current_steps": 1930, "total_steps": 4968, "loss": 0.3968, "lr": 6.7190110742964155e-06, "epoch": 0.7769726247987118, "percentage": 38.85, "elapsed_time": "3:11:52", "remaining_time": "5:02:01", "throughput": 9284.66, "total_tokens": 106886400}
{"current_steps": 1935, "total_steps": 4968, "loss": 0.391, "lr": 6.704157056973961e-06, "epoch": 0.7789855072463768, "percentage": 38.95, "elapsed_time": "3:12:26", "remaining_time": "5:01:37", "throughput": 9282.37, "total_tokens": 107175088}
{"current_steps": 1940, "total_steps": 4968, "loss": 0.4004, "lr": 6.6892860029374125e-06, "epoch": 0.7809983896940419, "percentage": 39.05, "elapsed_time": "3:12:58", "remaining_time": "5:01:12", "throughput": 9280.0, "total_tokens": 107448632}
{"current_steps": 1945, "total_steps": 4968, "loss": 0.3858, "lr": 6.674398060854931e-06, "epoch": 0.783011272141707, "percentage": 39.15, "elapsed_time": "3:13:28", "remaining_time": "5:00:42", "throughput": 9279.46, "total_tokens": 107718736}
{"current_steps": 1950, "total_steps": 4968, "loss": 0.3965, "lr": 6.659493379563511e-06, "epoch": 0.785024154589372, "percentage": 39.25, "elapsed_time": "3:14:00", "remaining_time": "5:00:15", "throughput": 9279.97, "total_tokens": 108021064}
{"current_steps": 1955, "total_steps": 4968, "loss": 0.4064, "lr": 6.644572108067487e-06, "epoch": 0.7870370370370371, "percentage": 39.35, "elapsed_time": "3:14:32", "remaining_time": "4:59:49", "throughput": 9278.01, "total_tokens": 108296792}
{"current_steps": 1960, "total_steps": 4968, "loss": 0.3888, "lr": 6.6296343955370565e-06, "epoch": 0.789049919484702, "percentage": 39.45, "elapsed_time": "3:15:04", "remaining_time": "4:59:23", "throughput": 9274.5, "total_tokens": 108557568}
{"current_steps": 1965, "total_steps": 4968, "loss": 0.3902, "lr": 6.614680391306772e-06, "epoch": 0.7910628019323671, "percentage": 39.55, "elapsed_time": "3:15:34", "remaining_time": "4:58:53", "throughput": 9272.94, "total_tokens": 108817104}
{"current_steps": 1970, "total_steps": 4968, "loss": 0.3893, "lr": 6.59971024487406e-06, "epoch": 0.7930756843800322, "percentage": 39.65, "elapsed_time": "3:16:04", "remaining_time": "4:58:23", "throughput": 9273.01, "total_tokens": 109093256}
{"current_steps": 1975, "total_steps": 4968, "loss": 0.3993, "lr": 6.5847241058977265e-06, "epoch": 0.7950885668276972, "percentage": 39.75, "elapsed_time": "3:16:37", "remaining_time": "4:57:58", "throughput": 9271.61, "total_tokens": 109383728}
{"current_steps": 1980, "total_steps": 4968, "loss": 0.3951, "lr": 6.569722124196449e-06, "epoch": 0.7971014492753623, "percentage": 39.86, "elapsed_time": "3:17:04", "remaining_time": "4:57:24", "throughput": 9273.61, "total_tokens": 109659440}
{"current_steps": 1985, "total_steps": 4968, "loss": 0.3876, "lr": 6.554704449747295e-06, "epoch": 0.7991143317230274, "percentage": 39.96, "elapsed_time": "3:17:36", "remaining_time": "4:56:58", "throughput": 9273.5, "total_tokens": 109955232}
{"current_steps": 1990, "total_steps": 4968, "loss": 0.3825, "lr": 6.539671232684215e-06, "epoch": 0.8011272141706924, "percentage": 40.06, "elapsed_time": "3:18:01", "remaining_time": "4:56:20", "throughput": 9276.76, "total_tokens": 110223952}
{"current_steps": 1995, "total_steps": 4968, "loss": 0.4025, "lr": 6.5246226232965324e-06, "epoch": 0.8031400966183575, "percentage": 40.16, "elapsed_time": "3:18:33", "remaining_time": "4:55:54", "throughput": 9277.13, "total_tokens": 110524704}
{"current_steps": 2000, "total_steps": 4968, "loss": 0.3925, "lr": 6.5095587720274585e-06, "epoch": 0.8051529790660226, "percentage": 40.26, "elapsed_time": "3:19:00", "remaining_time": "4:55:19", "throughput": 9279.02, "total_tokens": 110793688}
{"current_steps": 2005, "total_steps": 4968, "loss": 0.3961, "lr": 6.49447982947258e-06, "epoch": 0.8071658615136876, "percentage": 40.36, "elapsed_time": "3:19:33", "remaining_time": "4:54:54", "throughput": 9278.21, "total_tokens": 111090512}
{"current_steps": 2010, "total_steps": 4968, "loss": 0.3922, "lr": 6.479385946378345e-06, "epoch": 0.8091787439613527, "percentage": 40.46, "elapsed_time": "3:20:04", "remaining_time": "4:54:26", "throughput": 9277.99, "total_tokens": 111378176}
{"current_steps": 2015, "total_steps": 4968, "loss": 0.3964, "lr": 6.4642772736405756e-06, "epoch": 0.8111916264090178, "percentage": 40.56, "elapsed_time": "3:20:30", "remaining_time": "4:53:50", "throughput": 9279.47, "total_tokens": 111635624}
{"current_steps": 2020, "total_steps": 4968, "loss": 0.4081, "lr": 6.44915396230294e-06, "epoch": 0.8132045088566827, "percentage": 40.66, "elapsed_time": "3:21:04", "remaining_time": "4:53:26", "throughput": 9277.79, "total_tokens": 111931424}
{"current_steps": 2025, "total_steps": 4968, "loss": 0.41, "lr": 6.434016163555452e-06, "epoch": 0.8152173913043478, "percentage": 40.76, "elapsed_time": "3:21:27", "remaining_time": "4:52:47", "throughput": 9283.9, "total_tokens": 112222240}
{"current_steps": 2030, "total_steps": 4968, "loss": 0.3759, "lr": 6.418864028732963e-06, "epoch": 0.8172302737520128, "percentage": 40.86, "elapsed_time": "3:21:57", "remaining_time": "4:52:17", "throughput": 9285.01, "total_tokens": 112510040}
{"current_steps": 2035, "total_steps": 4968, "loss": 0.3732, "lr": 6.403697709313639e-06, "epoch": 0.8192431561996779, "percentage": 40.96, "elapsed_time": "3:22:27", "remaining_time": "4:51:47", "throughput": 9286.05, "total_tokens": 112798112}
{"current_steps": 2040, "total_steps": 4968, "loss": 0.4093, "lr": 6.388517356917454e-06, "epoch": 0.821256038647343, "percentage": 41.06, "elapsed_time": "3:22:53", "remaining_time": "4:51:12", "throughput": 9288.52, "total_tokens": 113070456}
{"current_steps": 2045, "total_steps": 4968, "loss": 0.3904, "lr": 6.373323123304671e-06, "epoch": 0.823268921095008, "percentage": 41.16, "elapsed_time": "3:23:23", "remaining_time": "4:50:42", "throughput": 9288.01, "total_tokens": 113343376}
{"current_steps": 2050, "total_steps": 4968, "loss": 0.3883, "lr": 6.358115160374326e-06, "epoch": 0.8252818035426731, "percentage": 41.26, "elapsed_time": "3:23:57", "remaining_time": "4:50:19", "throughput": 9283.94, "total_tokens": 113614944}
{"current_steps": 2055, "total_steps": 4968, "loss": 0.4066, "lr": 6.342893620162709e-06, "epoch": 0.8272946859903382, "percentage": 41.36, "elapsed_time": "3:24:29", "remaining_time": "4:49:51", "throughput": 9284.7, "total_tokens": 113914464}
{"current_steps": 2060, "total_steps": 4968, "loss": 0.3999, "lr": 6.3276586548418454e-06, "epoch": 0.8293075684380032, "percentage": 41.47, "elapsed_time": "3:24:53", "remaining_time": "4:49:13", "throughput": 9286.27, "total_tokens": 114157984}
{"current_steps": 2065, "total_steps": 4968, "loss": 0.4058, "lr": 6.312410416717969e-06, "epoch": 0.8313204508856683, "percentage": 41.57, "elapsed_time": "3:25:19", "remaining_time": "4:48:39", "throughput": 9290.42, "total_tokens": 114456080}
{"current_steps": 2070, "total_steps": 4968, "loss": 0.4164, "lr": 6.29714905823001e-06, "epoch": 0.8333333333333334, "percentage": 41.67, "elapsed_time": "3:25:47", "remaining_time": "4:48:07", "throughput": 9291.56, "total_tokens": 114731320}
{"current_steps": 2075, "total_steps": 4968, "loss": 0.4316, "lr": 6.281874731948059e-06, "epoch": 0.8353462157809984, "percentage": 41.77, "elapsed_time": "3:26:16", "remaining_time": "4:47:35", "throughput": 9294.02, "total_tokens": 115029840}
{"current_steps": 2080, "total_steps": 4968, "loss": 0.4102, "lr": 6.266587590571852e-06, "epoch": 0.8373590982286635, "percentage": 41.87, "elapsed_time": "3:26:45", "remaining_time": "4:47:04", "throughput": 9294.12, "total_tokens": 115299712}
{"current_steps": 2085, "total_steps": 4968, "loss": 0.3855, "lr": 6.25128778692924e-06, "epoch": 0.8393719806763285, "percentage": 41.97, "elapsed_time": "3:27:14", "remaining_time": "4:46:34", "throughput": 9294.26, "total_tokens": 115573048}
{"current_steps": 2090, "total_steps": 4968, "loss": 0.4237, "lr": 6.235975473974652e-06, "epoch": 0.8413848631239935, "percentage": 42.07, "elapsed_time": "3:27:50", "remaining_time": "4:46:12", "throughput": 9290.76, "total_tokens": 115860800}
{"current_steps": 2095, "total_steps": 4968, "loss": 0.4177, "lr": 6.220650804787587e-06, "epoch": 0.8433977455716586, "percentage": 42.17, "elapsed_time": "3:28:18", "remaining_time": "4:45:39", "throughput": 9293.55, "total_tokens": 116151880}
{"current_steps": 2100, "total_steps": 4968, "loss": 0.3926, "lr": 6.205313932571062e-06, "epoch": 0.8454106280193237, "percentage": 42.27, "elapsed_time": "3:28:50", "remaining_time": "4:45:12", "throughput": 9289.42, "total_tokens": 116398848}
{"current_steps": 2105, "total_steps": 4968, "loss": 0.4029, "lr": 6.189965010650092e-06, "epoch": 0.8474235104669887, "percentage": 42.37, "elapsed_time": "3:29:17", "remaining_time": "4:44:39", "throughput": 9292.42, "total_tokens": 116688240}
{"current_steps": 2110, "total_steps": 4968, "loss": 0.3806, "lr": 6.174604192470156e-06, "epoch": 0.8494363929146538, "percentage": 42.47, "elapsed_time": "3:29:49", "remaining_time": "4:44:12", "throughput": 9292.24, "total_tokens": 116981576}
{"current_steps": 2115, "total_steps": 4968, "loss": 0.3976, "lr": 6.159231631595663e-06, "epoch": 0.8514492753623188, "percentage": 42.57, "elapsed_time": "3:30:15", "remaining_time": "4:43:36", "throughput": 9296.63, "total_tokens": 117277320}
{"current_steps": 2120, "total_steps": 4968, "loss": 0.4073, "lr": 6.1438474817084085e-06, "epoch": 0.8534621578099839, "percentage": 42.67, "elapsed_time": "3:30:38", "remaining_time": "4:42:59", "throughput": 9299.77, "total_tokens": 117539776}
{"current_steps": 2125, "total_steps": 4968, "loss": 0.3865, "lr": 6.128451896606054e-06, "epoch": 0.855475040257649, "percentage": 42.77, "elapsed_time": "3:30:59", "remaining_time": "4:42:16", "throughput": 9306.43, "total_tokens": 117812360}
{"current_steps": 2130, "total_steps": 4968, "loss": 0.3891, "lr": 6.113045030200574e-06, "epoch": 0.857487922705314, "percentage": 42.87, "elapsed_time": "3:31:22", "remaining_time": "4:41:38", "throughput": 9310.53, "total_tokens": 118081880}
{"current_steps": 2135, "total_steps": 4968, "loss": 0.3859, "lr": 6.0976270365167275e-06, "epoch": 0.8595008051529791, "percentage": 42.98, "elapsed_time": "3:31:54", "remaining_time": "4:41:10", "throughput": 9307.25, "total_tokens": 118333920}
{"current_steps": 2140, "total_steps": 4968, "loss": 0.4171, "lr": 6.0821980696905145e-06, "epoch": 0.8615136876006442, "percentage": 43.08, "elapsed_time": "3:32:22", "remaining_time": "4:40:38", "throughput": 9310.15, "total_tokens": 118630048}
{"current_steps": 2145, "total_steps": 4968, "loss": 0.3983, "lr": 6.066758283967633e-06, "epoch": 0.8635265700483091, "percentage": 43.18, "elapsed_time": "3:32:48", "remaining_time": "4:40:04", "throughput": 9312.71, "total_tokens": 118910024}
{"current_steps": 2150, "total_steps": 4968, "loss": 0.378, "lr": 6.0513078337019395e-06, "epoch": 0.8655394524959742, "percentage": 43.28, "elapsed_time": "3:33:14", "remaining_time": "4:39:29", "throughput": 9313.61, "total_tokens": 119162688}
{"current_steps": 2155, "total_steps": 4968, "loss": 0.4455, "lr": 6.0358468733539064e-06, "epoch": 0.8675523349436393, "percentage": 43.38, "elapsed_time": "3:33:45", "remaining_time": "4:39:00", "throughput": 9312.78, "total_tokens": 119436712}
{"current_steps": 2160, "total_steps": 4968, "loss": 0.3911, "lr": 6.020375557489078e-06, "epoch": 0.8695652173913043, "percentage": 43.48, "elapsed_time": "3:34:08", "remaining_time": "4:38:23", "throughput": 9315.89, "total_tokens": 119698112}
{"current_steps": 2165, "total_steps": 4968, "loss": 0.3934, "lr": 6.004894040776521e-06, "epoch": 0.8715780998389694, "percentage": 43.58, "elapsed_time": "3:34:33", "remaining_time": "4:37:46", "throughput": 9320.66, "total_tokens": 119987320}
{"current_steps": 2170, "total_steps": 4968, "loss": 0.3839, "lr": 5.9894024779872865e-06, "epoch": 0.8735909822866345, "percentage": 43.68, "elapsed_time": "3:35:03", "remaining_time": "4:37:17", "throughput": 9320.93, "total_tokens": 120270896}
{"current_steps": 2175, "total_steps": 4968, "loss": 0.4015, "lr": 5.973901023992852e-06, "epoch": 0.8756038647342995, "percentage": 43.78, "elapsed_time": "3:35:36", "remaining_time": "4:36:51", "throughput": 9320.99, "total_tokens": 120577336}
{"current_steps": 2180, "total_steps": 4968, "loss": 0.4049, "lr": 5.9583898337635835e-06, "epoch": 0.8776167471819646, "percentage": 43.88, "elapsed_time": "3:36:01", "remaining_time": "4:36:16", "throughput": 9322.89, "total_tokens": 120839696}
{"current_steps": 2185, "total_steps": 4968, "loss": 0.3835, "lr": 5.9428690623671796e-06, "epoch": 0.8796296296296297, "percentage": 43.98, "elapsed_time": "3:36:25", "remaining_time": "4:35:39", "throughput": 9327.98, "total_tokens": 121130312}
{"current_steps": 2190, "total_steps": 4968, "loss": 0.3999, "lr": 5.927338864967121e-06, "epoch": 0.8816425120772947, "percentage": 44.08, "elapsed_time": "3:36:52", "remaining_time": "4:35:05", "throughput": 9328.08, "total_tokens": 121377376}
{"current_steps": 2195, "total_steps": 4968, "loss": 0.384, "lr": 5.911799396821129e-06, "epoch": 0.8836553945249598, "percentage": 44.18, "elapsed_time": "3:37:22", "remaining_time": "4:34:37", "throughput": 9327.3, "total_tokens": 121653072}
{"current_steps": 2200, "total_steps": 4968, "loss": 0.3912, "lr": 5.896250813279596e-06, "epoch": 0.8856682769726248, "percentage": 44.28, "elapsed_time": "3:37:47", "remaining_time": "4:34:01", "throughput": 9331.74, "total_tokens": 121941520}
{"current_steps": 2205, "total_steps": 4968, "loss": 0.4283, "lr": 5.8806932697840505e-06, "epoch": 0.8876811594202898, "percentage": 44.38, "elapsed_time": "3:38:23", "remaining_time": "4:33:38", "throughput": 9327.54, "total_tokens": 122218824}
{"current_steps": 2210, "total_steps": 4968, "loss": 0.3821, "lr": 5.86512692186559e-06, "epoch": 0.8896940418679549, "percentage": 44.48, "elapsed_time": "3:38:49", "remaining_time": "4:33:04", "throughput": 9328.46, "total_tokens": 122475232}
{"current_steps": 2215, "total_steps": 4968, "loss": 0.4041, "lr": 5.849551925143334e-06, "epoch": 0.8917069243156199, "percentage": 44.59, "elapsed_time": "3:39:17", "remaining_time": "4:32:33", "throughput": 9328.0, "total_tokens": 122735752}
{"current_steps": 2220, "total_steps": 4968, "loss": 0.3769, "lr": 5.833968435322864e-06, "epoch": 0.893719806763285, "percentage": 44.69, "elapsed_time": "3:39:44", "remaining_time": "4:31:59", "throughput": 9329.12, "total_tokens": 122996200}
{"current_steps": 2225, "total_steps": 4968, "loss": 0.4118, "lr": 5.818376608194669e-06, "epoch": 0.8957326892109501, "percentage": 44.79, "elapsed_time": "3:40:19", "remaining_time": "4:31:36", "throughput": 9324.97, "total_tokens": 123270096}
{"current_steps": 2230, "total_steps": 4968, "loss": 0.3997, "lr": 5.802776599632587e-06, "epoch": 0.8977455716586151, "percentage": 44.89, "elapsed_time": "3:40:51", "remaining_time": "4:31:10", "throughput": 9323.34, "total_tokens": 123552816}
{"current_steps": 2235, "total_steps": 4968, "loss": 0.421, "lr": 5.787168565592246e-06, "epoch": 0.8997584541062802, "percentage": 44.99, "elapsed_time": "3:41:28", "remaining_time": "4:30:48", "throughput": 9319.92, "total_tokens": 123844336}
{"current_steps": 2240, "total_steps": 4968, "loss": 0.3883, "lr": 5.771552662109507e-06, "epoch": 0.9017713365539453, "percentage": 45.09, "elapsed_time": "3:42:03", "remaining_time": "4:30:25", "throughput": 9316.5, "total_tokens": 124126656}
{"current_steps": 2245, "total_steps": 4968, "loss": 0.4077, "lr": 5.755929045298905e-06, "epoch": 0.9037842190016103, "percentage": 45.19, "elapsed_time": "3:42:27", "remaining_time": "4:29:48", "throughput": 9318.74, "total_tokens": 124377824}
{"current_steps": 2250, "total_steps": 4968, "loss": 0.3801, "lr": 5.740297871352083e-06, "epoch": 0.9057971014492754, "percentage": 45.29, "elapsed_time": "3:42:57", "remaining_time": "4:29:20", "throughput": 9317.74, "total_tokens": 124650968}
{"current_steps": 2255, "total_steps": 4968, "loss": 0.4048, "lr": 5.724659296536234e-06, "epoch": 0.9078099838969405, "percentage": 45.39, "elapsed_time": "3:43:26", "remaining_time": "4:28:49", "throughput": 9314.78, "total_tokens": 124882376}
{"current_steps": 2260, "total_steps": 4968, "loss": 0.3879, "lr": 5.709013477192541e-06, "epoch": 0.9098228663446055, "percentage": 45.49, "elapsed_time": "3:44:00", "remaining_time": "4:28:24", "throughput": 9312.06, "total_tokens": 125158504}
{"current_steps": 2265, "total_steps": 4968, "loss": 0.407, "lr": 5.69336056973461e-06, "epoch": 0.9118357487922706, "percentage": 45.59, "elapsed_time": "3:44:28", "remaining_time": "4:27:52", "throughput": 9314.75, "total_tokens": 125452616}
{"current_steps": 2270, "total_steps": 4968, "loss": 0.383, "lr": 5.677700730646907e-06, "epoch": 0.9138486312399355, "percentage": 45.69, "elapsed_time": "3:45:01", "remaining_time": "4:27:26", "throughput": 9313.42, "total_tokens": 125742352}
{"current_steps": 2275, "total_steps": 4968, "loss": 0.4005, "lr": 5.662034116483197e-06, "epoch": 0.9158615136876006, "percentage": 45.79, "elapsed_time": "3:45:27", "remaining_time": "4:26:53", "throughput": 9318.4, "total_tokens": 126054944}
{"current_steps": 2280, "total_steps": 4968, "loss": 0.3846, "lr": 5.646360883864975e-06, "epoch": 0.9178743961352657, "percentage": 45.89, "elapsed_time": "3:45:54", "remaining_time": "4:26:19", "throughput": 9321.37, "total_tokens": 126344720}
{"current_steps": 2285, "total_steps": 4968, "loss": 0.3868, "lr": 5.630681189479902e-06, "epoch": 0.9198872785829307, "percentage": 45.99, "elapsed_time": "3:46:29", "remaining_time": "4:25:56", "throughput": 9318.14, "total_tokens": 126626232}
{"current_steps": 2290, "total_steps": 4968, "loss": 0.4099, "lr": 5.614995190080238e-06, "epoch": 0.9219001610305958, "percentage": 46.1, "elapsed_time": "3:46:59", "remaining_time": "4:25:27", "throughput": 9315.65, "total_tokens": 126878488}
{"current_steps": 2295, "total_steps": 4968, "loss": 0.4091, "lr": 5.5993030424812745e-06, "epoch": 0.9239130434782609, "percentage": 46.2, "elapsed_time": "3:47:28", "remaining_time": "4:24:56", "throughput": 9319.51, "total_tokens": 127194216}
{"current_steps": 2300, "total_steps": 4968, "loss": 0.3948, "lr": 5.583604903559768e-06, "epoch": 0.9259259259259259, "percentage": 46.3, "elapsed_time": "3:47:59", "remaining_time": "4:24:28", "throughput": 9318.9, "total_tokens": 127477856}
{"current_steps": 2305, "total_steps": 4968, "loss": 0.4093, "lr": 5.567900930252375e-06, "epoch": 0.927938808373591, "percentage": 46.4, "elapsed_time": "3:48:37", "remaining_time": "4:24:07", "throughput": 9314.49, "total_tokens": 127767664}
{"current_steps": 2310, "total_steps": 4968, "loss": 0.4048, "lr": 5.552191279554071e-06, "epoch": 0.9299516908212561, "percentage": 46.5, "elapsed_time": "3:49:05", "remaining_time": "4:23:35", "throughput": 9317.54, "total_tokens": 128070808}
{"current_steps": 2315, "total_steps": 4968, "loss": 0.3879, "lr": 5.536476108516598e-06, "epoch": 0.9319645732689211, "percentage": 46.6, "elapsed_time": "3:49:35", "remaining_time": "4:23:06", "throughput": 9317.41, "total_tokens": 128353544}
{"current_steps": 2320, "total_steps": 4968, "loss": 0.3954, "lr": 5.5207555742468785e-06, "epoch": 0.9339774557165862, "percentage": 46.7, "elapsed_time": "3:50:07", "remaining_time": "4:22:39", "throughput": 9317.02, "total_tokens": 128641088}
{"current_steps": 2325, "total_steps": 4968, "loss": 0.3863, "lr": 5.505029833905456e-06, "epoch": 0.9359903381642513, "percentage": 46.8, "elapsed_time": "3:50:38", "remaining_time": "4:22:11", "throughput": 9316.18, "total_tokens": 128926168}
{"current_steps": 2330, "total_steps": 4968, "loss": 0.3998, "lr": 5.4892990447049225e-06, "epoch": 0.9380032206119162, "percentage": 46.9, "elapsed_time": "3:51:08", "remaining_time": "4:21:42", "throughput": 9317.21, "total_tokens": 129219784}
{"current_steps": 2335, "total_steps": 4968, "loss": 0.4001, "lr": 5.473563363908333e-06, "epoch": 0.9400161030595813, "percentage": 47.0, "elapsed_time": "3:51:40", "remaining_time": "4:21:14", "throughput": 9317.34, "total_tokens": 129517336}
{"current_steps": 2340, "total_steps": 4968, "loss": 0.4007, "lr": 5.457822948827658e-06, "epoch": 0.9420289855072463, "percentage": 47.1, "elapsed_time": "3:52:11", "remaining_time": "4:20:46", "throughput": 9317.67, "total_tokens": 129810320}
{"current_steps": 2345, "total_steps": 4968, "loss": 0.3956, "lr": 5.442077956822191e-06, "epoch": 0.9440418679549114, "percentage": 47.2, "elapsed_time": "3:52:43", "remaining_time": "4:20:19", "throughput": 9315.58, "total_tokens": 130079760}
{"current_steps": 2350, "total_steps": 4968, "loss": 0.3793, "lr": 5.4263285452969805e-06, "epoch": 0.9460547504025765, "percentage": 47.3, "elapsed_time": "3:53:15", "remaining_time": "4:19:51", "throughput": 9313.29, "total_tokens": 130345000}
{"current_steps": 2355, "total_steps": 4968, "loss": 0.3712, "lr": 5.410574871701261e-06, "epoch": 0.9480676328502415, "percentage": 47.4, "elapsed_time": "3:53:44", "remaining_time": "4:19:20", "throughput": 9313.62, "total_tokens": 130614688}
{"current_steps": 2360, "total_steps": 4968, "loss": 0.4034, "lr": 5.394817093526873e-06, "epoch": 0.9500805152979066, "percentage": 47.5, "elapsed_time": "3:54:18", "remaining_time": "4:18:55", "throughput": 9310.73, "total_tokens": 130891080}
{"current_steps": 2365, "total_steps": 4968, "loss": 0.3847, "lr": 5.379055368306693e-06, "epoch": 0.9520933977455717, "percentage": 47.6, "elapsed_time": "3:54:41", "remaining_time": "4:18:18", "throughput": 9314.9, "total_tokens": 131169720}
{"current_steps": 2370, "total_steps": 4968, "loss": 0.3993, "lr": 5.363289853613054e-06, "epoch": 0.9541062801932367, "percentage": 47.71, "elapsed_time": "3:55:04", "remaining_time": "4:17:41", "throughput": 9320.6, "total_tokens": 131464072}
{"current_steps": 2375, "total_steps": 4968, "loss": 0.4135, "lr": 5.347520707056175e-06, "epoch": 0.9561191626409018, "percentage": 47.81, "elapsed_time": "3:55:36", "remaining_time": "4:17:14", "throughput": 9318.53, "total_tokens": 131732456}
{"current_steps": 2380, "total_steps": 4968, "loss": 0.3655, "lr": 5.331748086282584e-06, "epoch": 0.9581320450885669, "percentage": 47.91, "elapsed_time": "3:56:03", "remaining_time": "4:16:40", "throughput": 9320.4, "total_tokens": 132005232}
{"current_steps": 2385, "total_steps": 4968, "loss": 0.4308, "lr": 5.315972148973541e-06, "epoch": 0.9601449275362319, "percentage": 48.01, "elapsed_time": "3:56:36", "remaining_time": "4:16:14", "throughput": 9318.72, "total_tokens": 132291704}
{"current_steps": 2390, "total_steps": 4968, "loss": 0.3818, "lr": 5.30019305284346e-06, "epoch": 0.962157809983897, "percentage": 48.11, "elapsed_time": "3:57:05", "remaining_time": "4:15:44", "throughput": 9318.53, "total_tokens": 132561512}
{"current_steps": 2395, "total_steps": 4968, "loss": 0.4175, "lr": 5.284410955638335e-06, "epoch": 0.964170692431562, "percentage": 48.21, "elapsed_time": "3:57:41", "remaining_time": "4:15:21", "throughput": 9314.68, "total_tokens": 132840880}
{"current_steps": 2400, "total_steps": 4968, "loss": 0.3679, "lr": 5.268626015134163e-06, "epoch": 0.966183574879227, "percentage": 48.31, "elapsed_time": "3:58:07", "remaining_time": "4:14:47", "throughput": 9316.58, "total_tokens": 133110416}
{"current_steps": 2405, "total_steps": 4968, "loss": 0.3863, "lr": 5.252838389135364e-06, "epoch": 0.9681964573268921, "percentage": 48.41, "elapsed_time": "3:58:38", "remaining_time": "4:14:19", "throughput": 9316.99, "total_tokens": 133406792}
{"current_steps": 2410, "total_steps": 4968, "loss": 0.3964, "lr": 5.237048235473207e-06, "epoch": 0.9702093397745571, "percentage": 48.51, "elapsed_time": "3:59:09", "remaining_time": "4:13:51", "throughput": 9317.2, "total_tokens": 133699960}
{"current_steps": 2415, "total_steps": 4968, "loss": 0.3927, "lr": 5.221255712004233e-06, "epoch": 0.9722222222222222, "percentage": 48.61, "elapsed_time": "3:59:35", "remaining_time": "4:13:16", "throughput": 9317.64, "total_tokens": 133944592}
{"current_steps": 2420, "total_steps": 4968, "loss": 0.3715, "lr": 5.205460976608668e-06, "epoch": 0.9742351046698873, "percentage": 48.71, "elapsed_time": "4:00:03", "remaining_time": "4:12:45", "throughput": 9319.56, "total_tokens": 134236176}
{"current_steps": 2425, "total_steps": 4968, "loss": 0.3808, "lr": 5.189664187188857e-06, "epoch": 0.9762479871175523, "percentage": 48.81, "elapsed_time": "4:00:31", "remaining_time": "4:12:13", "throughput": 9322.35, "total_tokens": 134534560}
{"current_steps": 2430, "total_steps": 4968, "loss": 0.3986, "lr": 5.173865501667675e-06, "epoch": 0.9782608695652174, "percentage": 48.91, "elapsed_time": "4:01:01", "remaining_time": "4:11:44", "throughput": 9321.4, "total_tokens": 134799696}
{"current_steps": 2435, "total_steps": 4968, "loss": 0.3952, "lr": 5.158065077986956e-06, "epoch": 0.9802737520128825, "percentage": 49.01, "elapsed_time": "4:01:26", "remaining_time": "4:11:09", "throughput": 9324.1, "total_tokens": 135070128}
{"current_steps": 2440, "total_steps": 4968, "loss": 0.3916, "lr": 5.1422630741059075e-06, "epoch": 0.9822866344605475, "percentage": 49.11, "elapsed_time": "4:02:00", "remaining_time": "4:10:44", "throughput": 9321.51, "total_tokens": 135356280}
{"current_steps": 2445, "total_steps": 4968, "loss": 0.3911, "lr": 5.126459647999535e-06, "epoch": 0.9842995169082126, "percentage": 49.21, "elapsed_time": "4:02:31", "remaining_time": "4:10:15", "throughput": 9322.49, "total_tokens": 135652664}
{"current_steps": 2450, "total_steps": 4968, "loss": 0.4172, "lr": 5.110654957657067e-06, "epoch": 0.9863123993558777, "percentage": 49.32, "elapsed_time": "4:02:56", "remaining_time": "4:09:41", "throughput": 9325.15, "total_tokens": 135930152}
{"current_steps": 2455, "total_steps": 4968, "loss": 0.389, "lr": 5.094849161080366e-06, "epoch": 0.9883252818035426, "percentage": 49.42, "elapsed_time": "4:03:21", "remaining_time": "4:09:06", "throughput": 9330.42, "total_tokens": 136235360}
{"current_steps": 2460, "total_steps": 4968, "loss": 0.4016, "lr": 5.079042416282351e-06, "epoch": 0.9903381642512077, "percentage": 49.52, "elapsed_time": "4:03:47", "remaining_time": "4:08:33", "throughput": 9331.7, "total_tokens": 136501672}
{"current_steps": 2465, "total_steps": 4968, "loss": 0.3992, "lr": 5.063234881285428e-06, "epoch": 0.9923510466988728, "percentage": 49.62, "elapsed_time": "4:04:11", "remaining_time": "4:07:57", "throughput": 9336.95, "total_tokens": 136798896}
{"current_steps": 2470, "total_steps": 4968, "loss": 0.4029, "lr": 5.047426714119897e-06, "epoch": 0.9943639291465378, "percentage": 49.72, "elapsed_time": "4:04:33", "remaining_time": "4:07:20", "throughput": 9340.03, "total_tokens": 137054328}
{"current_steps": 2475, "total_steps": 4968, "loss": 0.3606, "lr": 5.0316180728223815e-06, "epoch": 0.9963768115942029, "percentage": 49.82, "elapsed_time": "4:05:09", "remaining_time": "4:06:56", "throughput": 9336.94, "total_tokens": 137342352}
{"current_steps": 2480, "total_steps": 4968, "loss": 0.3912, "lr": 5.015809115434243e-06, "epoch": 0.998389694041868, "percentage": 49.92, "elapsed_time": "4:05:38", "remaining_time": "4:06:25", "throughput": 9337.64, "total_tokens": 137622184}
{"current_steps": 2485, "total_steps": 4968, "loss": 0.3799, "lr": 5e-06, "epoch": 1.000402576489533, "percentage": 50.02, "elapsed_time": "4:06:12", "remaining_time": "4:06:00", "throughput": 9335.07, "total_tokens": 137898728}
{"current_steps": 2490, "total_steps": 4968, "loss": 0.3449, "lr": 4.984190884565759e-06, "epoch": 1.002415458937198, "percentage": 50.12, "elapsed_time": "4:06:39", "remaining_time": "4:05:28", "throughput": 9337.03, "total_tokens": 138185760}
{"current_steps": 2495, "total_steps": 4968, "loss": 0.3613, "lr": 4.96838192717762e-06, "epoch": 1.0044283413848631, "percentage": 50.22, "elapsed_time": "4:07:10", "remaining_time": "4:04:59", "throughput": 9337.14, "total_tokens": 138471720}
{"current_steps": 2500, "total_steps": 4968, "loss": 0.3402, "lr": 4.952573285880104e-06, "epoch": 1.0064412238325282, "percentage": 50.32, "elapsed_time": "4:07:37", "remaining_time": "4:04:27", "throughput": 9337.85, "total_tokens": 138734928}
{"current_steps": 2505, "total_steps": 4968, "loss": 0.3342, "lr": 4.936765118714574e-06, "epoch": 1.0084541062801933, "percentage": 50.42, "elapsed_time": "4:08:06", "remaining_time": "4:03:57", "throughput": 9338.62, "total_tokens": 139021744}
{"current_steps": 2510, "total_steps": 4968, "loss": 0.3403, "lr": 4.9209575837176495e-06, "epoch": 1.0104669887278583, "percentage": 50.52, "elapsed_time": "4:08:30", "remaining_time": "4:03:21", "throughput": 9340.32, "total_tokens": 139265688}
{"current_steps": 2515, "total_steps": 4968, "loss": 0.3671, "lr": 4.905150838919635e-06, "epoch": 1.0124798711755234, "percentage": 50.62, "elapsed_time": "4:08:58", "remaining_time": "4:02:50", "throughput": 9341.71, "total_tokens": 139551768}
{"current_steps": 2520, "total_steps": 4968, "loss": 0.3411, "lr": 4.889345042342934e-06, "epoch": 1.0144927536231885, "percentage": 50.72, "elapsed_time": "4:09:24", "remaining_time": "4:02:16", "throughput": 9344.36, "total_tokens": 139831936}
{"current_steps": 2525, "total_steps": 4968, "loss": 0.326, "lr": 4.873540352000464e-06, "epoch": 1.0165056360708535, "percentage": 50.83, "elapsed_time": "4:09:57", "remaining_time": "4:01:50", "throughput": 9343.65, "total_tokens": 140130504}
{"current_steps": 2530, "total_steps": 4968, "loss": 0.3333, "lr": 4.857736925894093e-06, "epoch": 1.0185185185185186, "percentage": 50.93, "elapsed_time": "4:10:30", "remaining_time": "4:01:23", "throughput": 9340.3, "total_tokens": 140386784}
{"current_steps": 2535, "total_steps": 4968, "loss": 0.3316, "lr": 4.841934922013045e-06, "epoch": 1.0205314009661837, "percentage": 51.03, "elapsed_time": "4:10:55", "remaining_time": "4:00:49", "throughput": 9344.97, "total_tokens": 140694184}
{"current_steps": 2540, "total_steps": 4968, "loss": 0.3276, "lr": 4.826134498332325e-06, "epoch": 1.0225442834138487, "percentage": 51.13, "elapsed_time": "4:11:23", "remaining_time": "4:00:18", "throughput": 9343.62, "total_tokens": 140932536}
{"current_steps": 2545, "total_steps": 4968, "loss": 0.3419, "lr": 4.8103358128111435e-06, "epoch": 1.0245571658615138, "percentage": 51.23, "elapsed_time": "4:11:47", "remaining_time": "3:59:43", "throughput": 9345.0, "total_tokens": 141181184}
{"current_steps": 2550, "total_steps": 4968, "loss": 0.3366, "lr": 4.7945390233913345e-06, "epoch": 1.0265700483091786, "percentage": 51.33, "elapsed_time": "4:12:13", "remaining_time": "3:59:09", "throughput": 9347.56, "total_tokens": 141459424}
{"current_steps": 2555, "total_steps": 4968, "loss": 0.3385, "lr": 4.778744287995769e-06, "epoch": 1.0285829307568437, "percentage": 51.43, "elapsed_time": "4:12:42", "remaining_time": "3:58:39", "throughput": 9347.89, "total_tokens": 141737336}
{"current_steps": 2560, "total_steps": 4968, "loss": 0.3445, "lr": 4.762951764526794e-06, "epoch": 1.0305958132045088, "percentage": 51.53, "elapsed_time": "4:13:11", "remaining_time": "3:58:09", "throughput": 9348.76, "total_tokens": 142018120}
{"current_steps": 2565, "total_steps": 4968, "loss": 0.3273, "lr": 4.747161610864639e-06, "epoch": 1.0326086956521738, "percentage": 51.63, "elapsed_time": "4:13:36", "remaining_time": "3:57:35", "throughput": 9350.57, "total_tokens": 142287152}
{"current_steps": 2570, "total_steps": 4968, "loss": 0.3421, "lr": 4.73137398486584e-06, "epoch": 1.034621578099839, "percentage": 51.73, "elapsed_time": "4:14:05", "remaining_time": "3:57:05", "throughput": 9351.31, "total_tokens": 142568088}
{"current_steps": 2575, "total_steps": 4968, "loss": 0.3474, "lr": 4.715589044361667e-06, "epoch": 1.036634460547504, "percentage": 51.83, "elapsed_time": "4:14:35", "remaining_time": "3:56:35", "throughput": 9350.78, "total_tokens": 142838040}
{"current_steps": 2580, "total_steps": 4968, "loss": 0.3458, "lr": 4.699806947156542e-06, "epoch": 1.038647342995169, "percentage": 51.93, "elapsed_time": "4:15:04", "remaining_time": "3:56:05", "throughput": 9351.61, "total_tokens": 143123216}
{"current_steps": 2585, "total_steps": 4968, "loss": 0.3652, "lr": 4.6840278510264595e-06, "epoch": 1.040660225442834, "percentage": 52.03, "elapsed_time": "4:15:32", "remaining_time": "3:55:34", "throughput": 9352.2, "total_tokens": 143393424}
{"current_steps": 2590, "total_steps": 4968, "loss": 0.3167, "lr": 4.668251913717417e-06, "epoch": 1.0426731078904992, "percentage": 52.13, "elapsed_time": "4:16:04", "remaining_time": "3:55:06", "throughput": 9349.6, "total_tokens": 143652632}
{"current_steps": 2595, "total_steps": 4968, "loss": 0.3408, "lr": 4.652479292943826e-06, "epoch": 1.0446859903381642, "percentage": 52.23, "elapsed_time": "4:16:35", "remaining_time": "3:54:38", "throughput": 9346.18, "total_tokens": 143888208}
{"current_steps": 2600, "total_steps": 4968, "loss": 0.3552, "lr": 4.636710146386948e-06, "epoch": 1.0466988727858293, "percentage": 52.33, "elapsed_time": "4:17:04", "remaining_time": "3:54:07", "throughput": 9345.66, "total_tokens": 144150200}
{"current_steps": 2605, "total_steps": 4968, "loss": 0.3389, "lr": 4.620944631693309e-06, "epoch": 1.0487117552334944, "percentage": 52.44, "elapsed_time": "4:17:33", "remaining_time": "3:53:38", "throughput": 9347.0, "total_tokens": 144447672}
{"current_steps": 2610, "total_steps": 4968, "loss": 0.3368, "lr": 4.605182906473128e-06, "epoch": 1.0507246376811594, "percentage": 52.54, "elapsed_time": "4:18:02", "remaining_time": "3:53:07", "throughput": 9347.49, "total_tokens": 144722136}
{"current_steps": 2615, "total_steps": 4968, "loss": 0.3323, "lr": 4.589425128298741e-06, "epoch": 1.0527375201288245, "percentage": 52.64, "elapsed_time": "4:18:27", "remaining_time": "3:52:33", "throughput": 9351.35, "total_tokens": 145013032}
{"current_steps": 2620, "total_steps": 4968, "loss": 0.3327, "lr": 4.57367145470302e-06, "epoch": 1.0547504025764896, "percentage": 52.74, "elapsed_time": "4:18:59", "remaining_time": "3:52:06", "throughput": 9349.27, "total_tokens": 145285128}
{"current_steps": 2625, "total_steps": 4968, "loss": 0.3425, "lr": 4.55792204317781e-06, "epoch": 1.0567632850241546, "percentage": 52.84, "elapsed_time": "4:19:25", "remaining_time": "3:51:33", "throughput": 9352.04, "total_tokens": 145568072}
{"current_steps": 2630, "total_steps": 4968, "loss": 0.3339, "lr": 4.5421770511723434e-06, "epoch": 1.0587761674718197, "percentage": 52.94, "elapsed_time": "4:20:00", "remaining_time": "3:51:08", "throughput": 9348.41, "total_tokens": 145837472}
{"current_steps": 2635, "total_steps": 4968, "loss": 0.3356, "lr": 4.5264366360916675e-06, "epoch": 1.0607890499194848, "percentage": 53.04, "elapsed_time": "4:20:29", "remaining_time": "3:50:38", "throughput": 9349.23, "total_tokens": 146128112}
{"current_steps": 2640, "total_steps": 4968, "loss": 0.3404, "lr": 4.51070095529508e-06, "epoch": 1.0628019323671498, "percentage": 53.14, "elapsed_time": "4:21:06", "remaining_time": "3:50:15", "throughput": 9345.66, "total_tokens": 146416416}
{"current_steps": 2645, "total_steps": 4968, "loss": 0.3486, "lr": 4.494970166094545e-06, "epoch": 1.0648148148148149, "percentage": 53.24, "elapsed_time": "4:21:36", "remaining_time": "3:49:45", "throughput": 9345.79, "total_tokens": 146697176}
{"current_steps": 2650, "total_steps": 4968, "loss": 0.3443, "lr": 4.4792444257531215e-06, "epoch": 1.06682769726248, "percentage": 53.34, "elapsed_time": "4:21:57", "remaining_time": "3:49:08", "throughput": 9350.57, "total_tokens": 146967184}
{"current_steps": 2655, "total_steps": 4968, "loss": 0.3269, "lr": 4.4635238914834035e-06, "epoch": 1.068840579710145, "percentage": 53.44, "elapsed_time": "4:22:23", "remaining_time": "3:48:35", "throughput": 9352.82, "total_tokens": 147245352}
{"current_steps": 2660, "total_steps": 4968, "loss": 0.343, "lr": 4.447808720445928e-06, "epoch": 1.07085346215781, "percentage": 53.54, "elapsed_time": "4:22:54", "remaining_time": "3:48:06", "throughput": 9352.36, "total_tokens": 147527912}
{"current_steps": 2665, "total_steps": 4968, "loss": 0.3454, "lr": 4.432099069747625e-06, "epoch": 1.0728663446054751, "percentage": 53.64, "elapsed_time": "4:23:17", "remaining_time": "3:47:32", "throughput": 9355.99, "total_tokens": 147805376}
{"current_steps": 2670, "total_steps": 4968, "loss": 0.3414, "lr": 4.416395096440232e-06, "epoch": 1.07487922705314, "percentage": 53.74, "elapsed_time": "4:23:44", "remaining_time": "3:46:59", "throughput": 9358.53, "total_tokens": 148096704}
{"current_steps": 2675, "total_steps": 4968, "loss": 0.3226, "lr": 4.400696957518729e-06, "epoch": 1.076892109500805, "percentage": 53.84, "elapsed_time": "4:24:14", "remaining_time": "3:46:30", "throughput": 9358.73, "total_tokens": 148374240}
{"current_steps": 2680, "total_steps": 4968, "loss": 0.3456, "lr": 4.3850048099197655e-06, "epoch": 1.0789049919484701, "percentage": 53.95, "elapsed_time": "4:24:41", "remaining_time": "3:45:58", "throughput": 9359.29, "total_tokens": 148636264}
{"current_steps": 2685, "total_steps": 4968, "loss": 0.3499, "lr": 4.369318810520101e-06, "epoch": 1.0809178743961352, "percentage": 54.05, "elapsed_time": "4:25:16", "remaining_time": "3:45:33", "throughput": 9355.27, "total_tokens": 148904160}
{"current_steps": 2690, "total_steps": 4968, "loss": 0.3499, "lr": 4.353639116135027e-06, "epoch": 1.0829307568438002, "percentage": 54.15, "elapsed_time": "4:25:46", "remaining_time": "3:45:04", "throughput": 9355.11, "total_tokens": 149184824}
{"current_steps": 2695, "total_steps": 4968, "loss": 0.3267, "lr": 4.337965883516805e-06, "epoch": 1.0849436392914653, "percentage": 54.25, "elapsed_time": "4:26:19", "remaining_time": "3:44:37", "throughput": 9352.69, "total_tokens": 149456000}
{"current_steps": 2700, "total_steps": 4968, "loss": 0.3325, "lr": 4.322299269353095e-06, "epoch": 1.0869565217391304, "percentage": 54.35, "elapsed_time": "4:26:52", "remaining_time": "3:44:10", "throughput": 9351.88, "total_tokens": 149745208}
{"current_steps": 2705, "total_steps": 4968, "loss": 0.3446, "lr": 4.306639430265392e-06, "epoch": 1.0889694041867954, "percentage": 54.45, "elapsed_time": "4:27:24", "remaining_time": "3:43:42", "throughput": 9350.43, "total_tokens": 150022800}
{"current_steps": 2710, "total_steps": 4968, "loss": 0.3413, "lr": 4.29098652280746e-06, "epoch": 1.0909822866344605, "percentage": 54.55, "elapsed_time": "4:28:00", "remaining_time": "3:43:18", "throughput": 9347.12, "total_tokens": 150310680}
{"current_steps": 2715, "total_steps": 4968, "loss": 0.3557, "lr": 4.275340703463767e-06, "epoch": 1.0929951690821256, "percentage": 54.65, "elapsed_time": "4:28:25", "remaining_time": "3:42:44", "throughput": 9350.55, "total_tokens": 150592344}
{"current_steps": 2720, "total_steps": 4968, "loss": 0.3304, "lr": 4.259702128647918e-06, "epoch": 1.0950080515297906, "percentage": 54.75, "elapsed_time": "4:28:59", "remaining_time": "3:42:18", "throughput": 9349.53, "total_tokens": 150894872}
{"current_steps": 2725, "total_steps": 4968, "loss": 0.322, "lr": 4.244070954701096e-06, "epoch": 1.0970209339774557, "percentage": 54.85, "elapsed_time": "4:29:31", "remaining_time": "3:41:51", "throughput": 9348.31, "total_tokens": 151178168}
{"current_steps": 2730, "total_steps": 4968, "loss": 0.3399, "lr": 4.2284473378904935e-06, "epoch": 1.0990338164251208, "percentage": 54.95, "elapsed_time": "4:30:02", "remaining_time": "3:41:22", "throughput": 9348.65, "total_tokens": 151470512}
{"current_steps": 2735, "total_steps": 4968, "loss": 0.3418, "lr": 4.212831434407755e-06, "epoch": 1.1010466988727858, "percentage": 55.05, "elapsed_time": "4:30:27", "remaining_time": "3:40:49", "throughput": 9352.64, "total_tokens": 151770968}
{"current_steps": 2740, "total_steps": 4968, "loss": 0.3351, "lr": 4.197223400367415e-06, "epoch": 1.103059581320451, "percentage": 55.15, "elapsed_time": "4:31:03", "remaining_time": "3:40:24", "throughput": 9349.98, "total_tokens": 152063832}
{"current_steps": 2745, "total_steps": 4968, "loss": 0.3191, "lr": 4.1816233918053316e-06, "epoch": 1.105072463768116, "percentage": 55.25, "elapsed_time": "4:31:23", "remaining_time": "3:39:46", "throughput": 9353.44, "total_tokens": 152305168}
{"current_steps": 2750, "total_steps": 4968, "loss": 0.3345, "lr": 4.166031564677138e-06, "epoch": 1.107085346215781, "percentage": 55.35, "elapsed_time": "4:31:46", "remaining_time": "3:39:11", "throughput": 9359.29, "total_tokens": 152617232}
{"current_steps": 2755, "total_steps": 4968, "loss": 0.3327, "lr": 4.150448074856667e-06, "epoch": 1.109098228663446, "percentage": 55.45, "elapsed_time": "4:32:19", "remaining_time": "3:38:45", "throughput": 9358.81, "total_tokens": 152921712}
{"current_steps": 2760, "total_steps": 4968, "loss": 0.3453, "lr": 4.1348730781344105e-06, "epoch": 1.1111111111111112, "percentage": 55.56, "elapsed_time": "4:32:51", "remaining_time": "3:38:16", "throughput": 9358.96, "total_tokens": 153215800}
{"current_steps": 2765, "total_steps": 4968, "loss": 0.3458, "lr": 4.119306730215951e-06, "epoch": 1.1131239935587762, "percentage": 55.66, "elapsed_time": "4:33:22", "remaining_time": "3:37:48", "throughput": 9357.33, "total_tokens": 153485136}
{"current_steps": 2770, "total_steps": 4968, "loss": 0.3309, "lr": 4.103749186720405e-06, "epoch": 1.1151368760064413, "percentage": 55.76, "elapsed_time": "4:33:58", "remaining_time": "3:37:23", "throughput": 9354.09, "total_tokens": 153766608}
{"current_steps": 2775, "total_steps": 4968, "loss": 0.3214, "lr": 4.088200603178872e-06, "epoch": 1.1171497584541064, "percentage": 55.86, "elapsed_time": "4:34:28", "remaining_time": "3:36:54", "throughput": 9353.34, "total_tokens": 154039072}
{"current_steps": 2780, "total_steps": 4968, "loss": 0.3459, "lr": 4.0726611350328786e-06, "epoch": 1.1191626409017714, "percentage": 55.96, "elapsed_time": "4:34:59", "remaining_time": "3:36:26", "throughput": 9351.71, "total_tokens": 154302088}
{"current_steps": 2785, "total_steps": 4968, "loss": 0.3449, "lr": 4.057130937632821e-06, "epoch": 1.1211755233494365, "percentage": 56.06, "elapsed_time": "4:35:31", "remaining_time": "3:35:57", "throughput": 9351.1, "total_tokens": 154586608}
{"current_steps": 2790, "total_steps": 4968, "loss": 0.3332, "lr": 4.041610166236417e-06, "epoch": 1.1231884057971016, "percentage": 56.16, "elapsed_time": "4:35:56", "remaining_time": "3:35:24", "throughput": 9352.8, "total_tokens": 154849256}
{"current_steps": 2795, "total_steps": 4968, "loss": 0.3199, "lr": 4.026098976007148e-06, "epoch": 1.1252012882447664, "percentage": 56.26, "elapsed_time": "4:36:25", "remaining_time": "3:34:54", "throughput": 9354.95, "total_tokens": 155156384}
{"current_steps": 2800, "total_steps": 4968, "loss": 0.3312, "lr": 4.010597522012716e-06, "epoch": 1.1272141706924317, "percentage": 56.36, "elapsed_time": "4:36:49", "remaining_time": "3:34:20", "throughput": 9359.76, "total_tokens": 155461544}
{"current_steps": 2805, "total_steps": 4968, "loss": 0.3394, "lr": 3.9951059592234805e-06, "epoch": 1.1292270531400965, "percentage": 56.46, "elapsed_time": "4:37:23", "remaining_time": "3:33:54", "throughput": 9358.69, "total_tokens": 155761992}
{"current_steps": 2810, "total_steps": 4968, "loss": 0.3567, "lr": 3.979624442510925e-06, "epoch": 1.1312399355877616, "percentage": 56.56, "elapsed_time": "4:37:54", "remaining_time": "3:33:25", "throughput": 9358.04, "total_tokens": 156042840}
{"current_steps": 2815, "total_steps": 4968, "loss": 0.3225, "lr": 3.964153126646095e-06, "epoch": 1.1332528180354267, "percentage": 56.66, "elapsed_time": "4:38:23", "remaining_time": "3:32:55", "throughput": 9359.94, "total_tokens": 156346080}
{"current_steps": 2820, "total_steps": 4968, "loss": 0.3238, "lr": 3.948692166298062e-06, "epoch": 1.1352657004830917, "percentage": 56.76, "elapsed_time": "4:38:51", "remaining_time": "3:32:24", "throughput": 9361.24, "total_tokens": 156625328}
{"current_steps": 2825, "total_steps": 4968, "loss": 0.3277, "lr": 3.9332417160323685e-06, "epoch": 1.1372785829307568, "percentage": 56.86, "elapsed_time": "4:39:18", "remaining_time": "3:31:52", "throughput": 9362.95, "total_tokens": 156911664}
{"current_steps": 2830, "total_steps": 4968, "loss": 0.3357, "lr": 3.917801930309486e-06, "epoch": 1.1392914653784219, "percentage": 56.96, "elapsed_time": "4:39:45", "remaining_time": "3:31:20", "throughput": 9363.89, "total_tokens": 157174264}
{"current_steps": 2835, "total_steps": 4968, "loss": 0.358, "lr": 3.902372963483273e-06, "epoch": 1.141304347826087, "percentage": 57.07, "elapsed_time": "4:40:16", "remaining_time": "3:30:52", "throughput": 9362.82, "total_tokens": 157451416}
{"current_steps": 2840, "total_steps": 4968, "loss": 0.3384, "lr": 3.886954969799427e-06, "epoch": 1.143317230273752, "percentage": 57.17, "elapsed_time": "4:40:51", "remaining_time": "3:30:27", "throughput": 9360.52, "total_tokens": 157743512}
{"current_steps": 2845, "total_steps": 4968, "loss": 0.3269, "lr": 3.871548103393947e-06, "epoch": 1.145330112721417, "percentage": 57.27, "elapsed_time": "4:41:17", "remaining_time": "3:29:54", "throughput": 9361.82, "total_tokens": 158007856}
{"current_steps": 2850, "total_steps": 4968, "loss": 0.3431, "lr": 3.856152518291593e-06, "epoch": 1.1473429951690821, "percentage": 57.37, "elapsed_time": "4:41:45", "remaining_time": "3:29:23", "throughput": 9362.19, "total_tokens": 158276856}
{"current_steps": 2855, "total_steps": 4968, "loss": 0.3334, "lr": 3.84076836840434e-06, "epoch": 1.1493558776167472, "percentage": 57.47, "elapsed_time": "4:42:17", "remaining_time": "3:28:55", "throughput": 9361.49, "total_tokens": 158558152}
{"current_steps": 2860, "total_steps": 4968, "loss": 0.3424, "lr": 3.825395807529845e-06, "epoch": 1.1513687600644122, "percentage": 57.57, "elapsed_time": "4:42:45", "remaining_time": "3:28:24", "throughput": 9362.33, "total_tokens": 158838168}
{"current_steps": 2865, "total_steps": 4968, "loss": 0.3199, "lr": 3.8100349893499094e-06, "epoch": 1.1533816425120773, "percentage": 57.67, "elapsed_time": "4:43:09", "remaining_time": "3:27:50", "throughput": 9364.05, "total_tokens": 159088800}
{"current_steps": 2870, "total_steps": 4968, "loss": 0.3347, "lr": 3.79468606742894e-06, "epoch": 1.1553945249597424, "percentage": 57.77, "elapsed_time": "4:43:45", "remaining_time": "3:27:25", "throughput": 9361.14, "total_tokens": 159374112}
{"current_steps": 2875, "total_steps": 4968, "loss": 0.3402, "lr": 3.779349195212415e-06, "epoch": 1.1574074074074074, "percentage": 57.87, "elapsed_time": "4:44:17", "remaining_time": "3:26:57", "throughput": 9359.08, "total_tokens": 159639960}
{"current_steps": 2880, "total_steps": 4968, "loss": 0.3638, "lr": 3.7640245260253484e-06, "epoch": 1.1594202898550725, "percentage": 57.97, "elapsed_time": "4:44:41", "remaining_time": "3:26:23", "throughput": 9362.17, "total_tokens": 159917080}
{"current_steps": 2885, "total_steps": 4968, "loss": 0.331, "lr": 3.748712213070762e-06, "epoch": 1.1614331723027376, "percentage": 58.07, "elapsed_time": "4:45:12", "remaining_time": "3:25:55", "throughput": 9360.18, "total_tokens": 160178384}
{"current_steps": 2890, "total_steps": 4968, "loss": 0.3365, "lr": 3.733412409428148e-06, "epoch": 1.1634460547504026, "percentage": 58.17, "elapsed_time": "4:45:46", "remaining_time": "3:25:29", "throughput": 9357.98, "total_tokens": 160459200}
{"current_steps": 2895, "total_steps": 4968, "loss": 0.3259, "lr": 3.7181252680519407e-06, "epoch": 1.1654589371980677, "percentage": 58.27, "elapsed_time": "4:46:09", "remaining_time": "3:24:54", "throughput": 9361.39, "total_tokens": 160734272}
{"current_steps": 2900, "total_steps": 4968, "loss": 0.3405, "lr": 3.7028509417699915e-06, "epoch": 1.1674718196457328, "percentage": 58.37, "elapsed_time": "4:46:38", "remaining_time": "3:24:23", "throughput": 9362.9, "total_tokens": 161023640}
{"current_steps": 2905, "total_steps": 4968, "loss": 0.3516, "lr": 3.687589583282031e-06, "epoch": 1.1694847020933978, "percentage": 58.47, "elapsed_time": "4:47:04", "remaining_time": "3:23:52", "throughput": 9365.12, "total_tokens": 161309400}
{"current_steps": 2910, "total_steps": 4968, "loss": 0.3309, "lr": 3.6723413451581554e-06, "epoch": 1.171497584541063, "percentage": 58.57, "elapsed_time": "4:47:38", "remaining_time": "3:23:25", "throughput": 9363.27, "total_tokens": 161594240}
{"current_steps": 2915, "total_steps": 4968, "loss": 0.3388, "lr": 3.6571063798372913e-06, "epoch": 1.173510466988728, "percentage": 58.68, "elapsed_time": "4:48:08", "remaining_time": "3:22:56", "throughput": 9363.36, "total_tokens": 161877344}
{"current_steps": 2920, "total_steps": 4968, "loss": 0.3528, "lr": 3.641884839625676e-06, "epoch": 1.1755233494363928, "percentage": 58.78, "elapsed_time": "4:48:38", "remaining_time": "3:22:26", "throughput": 9363.69, "total_tokens": 162164808}
{"current_steps": 2925, "total_steps": 4968, "loss": 0.3336, "lr": 3.626676876695331e-06, "epoch": 1.177536231884058, "percentage": 58.88, "elapsed_time": "4:49:10", "remaining_time": "3:21:58", "throughput": 9363.27, "total_tokens": 162457120}
{"current_steps": 2930, "total_steps": 4968, "loss": 0.328, "lr": 3.611482643082548e-06, "epoch": 1.179549114331723, "percentage": 58.98, "elapsed_time": "4:49:42", "remaining_time": "3:21:30", "throughput": 9363.26, "total_tokens": 162757376}
{"current_steps": 2935, "total_steps": 4968, "loss": 0.344, "lr": 3.5963022906863633e-06, "epoch": 1.181561996779388, "percentage": 59.08, "elapsed_time": "4:50:14", "remaining_time": "3:21:02", "throughput": 9363.33, "total_tokens": 163057128}
{"current_steps": 2940, "total_steps": 4968, "loss": 0.3303, "lr": 3.581135971267039e-06, "epoch": 1.183574879227053, "percentage": 59.18, "elapsed_time": "4:50:46", "remaining_time": "3:20:34", "throughput": 9361.96, "total_tokens": 163332224}
{"current_steps": 2945, "total_steps": 4968, "loss": 0.3341, "lr": 3.5659838364445505e-06, "epoch": 1.1855877616747181, "percentage": 59.28, "elapsed_time": "4:51:16", "remaining_time": "3:20:05", "throughput": 9362.71, "total_tokens": 163630112}
{"current_steps": 2950, "total_steps": 4968, "loss": 0.334, "lr": 3.550846037697063e-06, "epoch": 1.1876006441223832, "percentage": 59.38, "elapsed_time": "4:51:46", "remaining_time": "3:19:35", "throughput": 9362.46, "total_tokens": 163899888}
{"current_steps": 2955, "total_steps": 4968, "loss": 0.3316, "lr": 3.535722726359426e-06, "epoch": 1.1896135265700483, "percentage": 59.48, "elapsed_time": "4:52:18", "remaining_time": "3:19:07", "throughput": 9360.41, "total_tokens": 164164552}
{"current_steps": 2960, "total_steps": 4968, "loss": 0.3326, "lr": 3.520614053621656e-06, "epoch": 1.1916264090177133, "percentage": 59.58, "elapsed_time": "4:52:47", "remaining_time": "3:18:37", "throughput": 9361.39, "total_tokens": 164453912}
{"current_steps": 2965, "total_steps": 4968, "loss": 0.345, "lr": 3.5055201705274223e-06, "epoch": 1.1936392914653784, "percentage": 59.68, "elapsed_time": "4:53:18", "remaining_time": "3:18:08", "throughput": 9360.62, "total_tokens": 164734248}
{"current_steps": 2970, "total_steps": 4968, "loss": 0.3418, "lr": 3.490441227972542e-06, "epoch": 1.1956521739130435, "percentage": 59.78, "elapsed_time": "4:53:41", "remaining_time": "3:17:34", "throughput": 9362.56, "total_tokens": 164979064}
{"current_steps": 2975, "total_steps": 4968, "loss": 0.3125, "lr": 3.475377376703469e-06, "epoch": 1.1976650563607085, "percentage": 59.88, "elapsed_time": "4:54:13", "remaining_time": "3:17:06", "throughput": 9361.33, "total_tokens": 165256632}
{"current_steps": 2980, "total_steps": 4968, "loss": 0.3327, "lr": 3.4603287673157866e-06, "epoch": 1.1996779388083736, "percentage": 59.98, "elapsed_time": "4:54:37", "remaining_time": "3:16:33", "throughput": 9364.82, "total_tokens": 165548776}
{"current_steps": 2985, "total_steps": 4968, "loss": 0.3376, "lr": 3.445295550252705e-06, "epoch": 1.2016908212560387, "percentage": 60.08, "elapsed_time": "4:55:08", "remaining_time": "3:16:04", "throughput": 9364.61, "total_tokens": 165831856}
{"current_steps": 2990, "total_steps": 4968, "loss": 0.3366, "lr": 3.430277875803552e-06, "epoch": 1.2037037037037037, "percentage": 60.19, "elapsed_time": "4:55:38", "remaining_time": "3:15:34", "throughput": 9364.11, "total_tokens": 166105248}
{"current_steps": 2995, "total_steps": 4968, "loss": 0.3613, "lr": 3.4152758941022756e-06, "epoch": 1.2057165861513688, "percentage": 60.29, "elapsed_time": "4:56:12", "remaining_time": "3:15:08", "throughput": 9360.84, "total_tokens": 166369016}
{"current_steps": 3000, "total_steps": 4968, "loss": 0.3354, "lr": 3.400289755125941e-06, "epoch": 1.2077294685990339, "percentage": 60.39, "elapsed_time": "4:56:44", "remaining_time": "3:14:39", "throughput": 9359.74, "total_tokens": 166646592}
{"current_steps": 3005, "total_steps": 4968, "loss": 0.3338, "lr": 3.3853196086932295e-06, "epoch": 1.209742351046699, "percentage": 60.49, "elapsed_time": "4:57:23", "remaining_time": "3:14:16", "throughput": 9354.89, "total_tokens": 166923616}
{"current_steps": 3010, "total_steps": 4968, "loss": 0.3438, "lr": 3.370365604462945e-06, "epoch": 1.211755233494364, "percentage": 60.59, "elapsed_time": "4:57:50", "remaining_time": "3:13:44", "throughput": 9357.0, "total_tokens": 167215512}
{"current_steps": 3015, "total_steps": 4968, "loss": 0.3376, "lr": 3.3554278919325127e-06, "epoch": 1.213768115942029, "percentage": 60.69, "elapsed_time": "4:58:21", "remaining_time": "3:13:15", "throughput": 9357.5, "total_tokens": 167509488}
{"current_steps": 3020, "total_steps": 4968, "loss": 0.3314, "lr": 3.34050662043649e-06, "epoch": 1.2157809983896941, "percentage": 60.79, "elapsed_time": "4:58:51", "remaining_time": "3:12:46", "throughput": 9357.4, "total_tokens": 167789280}
{"current_steps": 3025, "total_steps": 4968, "loss": 0.3364, "lr": 3.3256019391450696e-06, "epoch": 1.2177938808373592, "percentage": 60.89, "elapsed_time": "4:59:17", "remaining_time": "3:12:14", "throughput": 9358.36, "total_tokens": 168056448}
{"current_steps": 3030, "total_steps": 4968, "loss": 0.3474, "lr": 3.310713997062588e-06, "epoch": 1.2198067632850242, "percentage": 60.99, "elapsed_time": "4:59:43", "remaining_time": "3:11:42", "throughput": 9360.59, "total_tokens": 168336992}
{"current_steps": 3035, "total_steps": 4968, "loss": 0.3311, "lr": 3.29584294302604e-06, "epoch": 1.2218196457326893, "percentage": 61.09, "elapsed_time": "5:00:15", "remaining_time": "3:11:14", "throughput": 9359.32, "total_tokens": 168615880}
{"current_steps": 3040, "total_steps": 4968, "loss": 0.3247, "lr": 3.2809889257035853e-06, "epoch": 1.2238325281803544, "percentage": 61.19, "elapsed_time": "5:00:42", "remaining_time": "3:10:42", "throughput": 9362.19, "total_tokens": 168917480}
{"current_steps": 3045, "total_steps": 4968, "loss": 0.3354, "lr": 3.266152093593069e-06, "epoch": 1.2258454106280192, "percentage": 61.29, "elapsed_time": "5:01:14", "remaining_time": "3:10:14", "throughput": 9360.79, "total_tokens": 169188184}
{"current_steps": 3050, "total_steps": 4968, "loss": 0.3291, "lr": 3.2513325950205277e-06, "epoch": 1.2278582930756845, "percentage": 61.39, "elapsed_time": "5:01:45", "remaining_time": "3:09:45", "throughput": 9358.12, "total_tokens": 169435608}
{"current_steps": 3055, "total_steps": 4968, "loss": 0.3244, "lr": 3.2365305781387156e-06, "epoch": 1.2298711755233493, "percentage": 61.49, "elapsed_time": "5:02:16", "remaining_time": "3:09:16", "throughput": 9354.38, "total_tokens": 169656664}
{"current_steps": 3060, "total_steps": 4968, "loss": 0.3699, "lr": 3.2217461909256186e-06, "epoch": 1.2318840579710144, "percentage": 61.59, "elapsed_time": "5:02:55", "remaining_time": "3:08:53", "throughput": 9350.29, "total_tokens": 169947560}
{"current_steps": 3065, "total_steps": 4968, "loss": 0.3279, "lr": 3.2069795811829772e-06, "epoch": 1.2338969404186795, "percentage": 61.69, "elapsed_time": "5:03:23", "remaining_time": "3:08:22", "throughput": 9351.4, "total_tokens": 170231144}
{"current_steps": 3070, "total_steps": 4968, "loss": 0.3413, "lr": 3.192230896534808e-06, "epoch": 1.2359098228663445, "percentage": 61.8, "elapsed_time": "5:03:56", "remaining_time": "3:07:54", "throughput": 9349.69, "total_tokens": 170502840}
{"current_steps": 3075, "total_steps": 4968, "loss": 0.3264, "lr": 3.1775002844259253e-06, "epoch": 1.2379227053140096, "percentage": 61.9, "elapsed_time": "5:04:24", "remaining_time": "3:07:23", "throughput": 9347.96, "total_tokens": 170734664}
{"current_steps": 3080, "total_steps": 4968, "loss": 0.3112, "lr": 3.162787892120473e-06, "epoch": 1.2399355877616747, "percentage": 62.0, "elapsed_time": "5:04:56", "remaining_time": "3:06:55", "throughput": 9344.65, "total_tokens": 170977240}
{"current_steps": 3085, "total_steps": 4968, "loss": 0.3323, "lr": 3.148093866700445e-06, "epoch": 1.2419484702093397, "percentage": 62.1, "elapsed_time": "5:05:25", "remaining_time": "3:06:25", "throughput": 9344.71, "total_tokens": 171242488}
{"current_steps": 3090, "total_steps": 4968, "loss": 0.3175, "lr": 3.1334183550642217e-06, "epoch": 1.2439613526570048, "percentage": 62.2, "elapsed_time": "5:05:57", "remaining_time": "3:05:56", "throughput": 9343.76, "total_tokens": 171525896}
{"current_steps": 3095, "total_steps": 4968, "loss": 0.3386, "lr": 3.1187615039250984e-06, "epoch": 1.2459742351046699, "percentage": 62.3, "elapsed_time": "5:06:23", "remaining_time": "3:05:24", "throughput": 9346.1, "total_tokens": 171811240}
{"current_steps": 3100, "total_steps": 4968, "loss": 0.3429, "lr": 3.1041234598098157e-06, "epoch": 1.247987117552335, "percentage": 62.4, "elapsed_time": "5:06:50", "remaining_time": "3:04:53", "throughput": 9347.33, "total_tokens": 172090640}
{"current_steps": 3105, "total_steps": 4968, "loss": 0.3215, "lr": 3.0895043690571018e-06, "epoch": 1.25, "percentage": 62.5, "elapsed_time": "5:07:15", "remaining_time": "3:04:21", "throughput": 9349.75, "total_tokens": 172368360}
{"current_steps": 3110, "total_steps": 4968, "loss": 0.3228, "lr": 3.0749043778162015e-06, "epoch": 1.252012882447665, "percentage": 62.6, "elapsed_time": "5:07:39", "remaining_time": "3:03:48", "throughput": 9354.42, "total_tokens": 172676096}
{"current_steps": 3115, "total_steps": 4968, "loss": 0.3515, "lr": 3.0603236320454195e-06, "epoch": 1.2540257648953301, "percentage": 62.7, "elapsed_time": "5:08:09", "remaining_time": "3:03:18", "throughput": 9353.2, "total_tokens": 172936224}
{"current_steps": 3120, "total_steps": 4968, "loss": 0.3425, "lr": 3.0457622775106643e-06, "epoch": 1.2560386473429952, "percentage": 62.8, "elapsed_time": "5:08:37", "remaining_time": "3:02:47", "throughput": 9354.5, "total_tokens": 173218720}
{"current_steps": 3125, "total_steps": 4968, "loss": 0.337, "lr": 3.0312204597839824e-06, "epoch": 1.2580515297906603, "percentage": 62.9, "elapsed_time": "5:09:10", "remaining_time": "3:02:20", "throughput": 9352.49, "total_tokens": 173492936}
{"current_steps": 3130, "total_steps": 4968, "loss": 0.3311, "lr": 3.01669832424211e-06, "epoch": 1.2600644122383253, "percentage": 63.0, "elapsed_time": "5:09:44", "remaining_time": "3:01:52", "throughput": 9350.34, "total_tokens": 173767880}
{"current_steps": 3135, "total_steps": 4968, "loss": 0.3308, "lr": 3.0021960160650197e-06, "epoch": 1.2620772946859904, "percentage": 63.1, "elapsed_time": "5:10:17", "remaining_time": "3:01:25", "throughput": 9348.7, "total_tokens": 174050368}
{"current_steps": 3140, "total_steps": 4968, "loss": 0.3531, "lr": 2.987713680234462e-06, "epoch": 1.2640901771336555, "percentage": 63.2, "elapsed_time": "5:10:49", "remaining_time": "3:00:57", "throughput": 9346.76, "total_tokens": 174313792}
{"current_steps": 3145, "total_steps": 4968, "loss": 0.3143, "lr": 2.973251461532527e-06, "epoch": 1.2661030595813205, "percentage": 63.31, "elapsed_time": "5:11:19", "remaining_time": "3:00:27", "throughput": 9347.37, "total_tokens": 174600328}
{"current_steps": 3150, "total_steps": 4968, "loss": 0.3245, "lr": 2.9588095045401844e-06, "epoch": 1.2681159420289856, "percentage": 63.41, "elapsed_time": "5:11:55", "remaining_time": "3:00:01", "throughput": 9344.28, "total_tokens": 174884848}
{"current_steps": 3155, "total_steps": 4968, "loss": 0.3312, "lr": 2.944387953635849e-06, "epoch": 1.2701288244766507, "percentage": 63.51, "elapsed_time": "5:12:21", "remaining_time": "2:59:29", "throughput": 9346.6, "total_tokens": 175166224}
{"current_steps": 3160, "total_steps": 4968, "loss": 0.3486, "lr": 2.929986952993933e-06, "epoch": 1.2721417069243155, "percentage": 63.61, "elapsed_time": "5:12:51", "remaining_time": "2:59:00", "throughput": 9347.76, "total_tokens": 175474184}
{"current_steps": 3165, "total_steps": 4968, "loss": 0.344, "lr": 2.9156066465833997e-06, "epoch": 1.2741545893719808, "percentage": 63.71, "elapsed_time": "5:13:25", "remaining_time": "2:58:32", "throughput": 9344.52, "total_tokens": 175728456}
{"current_steps": 3170, "total_steps": 4968, "loss": 0.318, "lr": 2.9012471781663375e-06, "epoch": 1.2761674718196456, "percentage": 63.81, "elapsed_time": "5:13:50", "remaining_time": "2:58:00", "throughput": 9345.52, "total_tokens": 175982264}
{"current_steps": 3175, "total_steps": 4968, "loss": 0.35, "lr": 2.886908691296504e-06, "epoch": 1.278180354267311, "percentage": 63.91, "elapsed_time": "5:14:23", "remaining_time": "2:57:32", "throughput": 9343.82, "total_tokens": 176253240}
{"current_steps": 3180, "total_steps": 4968, "loss": 0.3424, "lr": 2.872591329317908e-06, "epoch": 1.2801932367149758, "percentage": 64.01, "elapsed_time": "5:14:50", "remaining_time": "2:57:01", "throughput": 9345.16, "total_tokens": 176536144}
{"current_steps": 3185, "total_steps": 4968, "loss": 0.3211, "lr": 2.8582952353633708e-06, "epoch": 1.2822061191626408, "percentage": 64.11, "elapsed_time": "5:15:11", "remaining_time": "2:56:26", "throughput": 9348.47, "total_tokens": 176793320}
{"current_steps": 3190, "total_steps": 4968, "loss": 0.3323, "lr": 2.844020552353087e-06, "epoch": 1.2842190016103059, "percentage": 64.21, "elapsed_time": "5:15:44", "remaining_time": "2:55:58", "throughput": 9347.12, "total_tokens": 177074552}
{"current_steps": 3195, "total_steps": 4968, "loss": 0.3416, "lr": 2.8297674229932086e-06, "epoch": 1.286231884057971, "percentage": 64.31, "elapsed_time": "5:16:17", "remaining_time": "2:55:31", "throughput": 9345.49, "total_tokens": 177357576}
{"current_steps": 3200, "total_steps": 4968, "loss": 0.3514, "lr": 2.8155359897744117e-06, "epoch": 1.288244766505636, "percentage": 64.41, "elapsed_time": "5:16:46", "remaining_time": "2:55:00", "throughput": 9345.89, "total_tokens": 177630464}
{"current_steps": 3205, "total_steps": 4968, "loss": 0.3166, "lr": 2.8013263949704706e-06, "epoch": 1.290257648953301, "percentage": 64.51, "elapsed_time": "5:17:18", "remaining_time": "2:54:32", "throughput": 9344.83, "total_tokens": 177907472}
{"current_steps": 3210, "total_steps": 4968, "loss": 0.3416, "lr": 2.7871387806368426e-06, "epoch": 1.2922705314009661, "percentage": 64.61, "elapsed_time": "5:17:39", "remaining_time": "2:53:58", "throughput": 9350.28, "total_tokens": 178215720}
{"current_steps": 3215, "total_steps": 4968, "loss": 0.309, "lr": 2.772973288609235e-06, "epoch": 1.2942834138486312, "percentage": 64.71, "elapsed_time": "5:18:06", "remaining_time": "2:53:27", "throughput": 9351.12, "total_tokens": 178482056}
{"current_steps": 3220, "total_steps": 4968, "loss": 0.3634, "lr": 2.7588300605022007e-06, "epoch": 1.2962962962962963, "percentage": 64.81, "elapsed_time": "5:18:31", "remaining_time": "2:52:54", "throughput": 9353.3, "total_tokens": 178754976}
{"current_steps": 3225, "total_steps": 4968, "loss": 0.335, "lr": 2.744709237707717e-06, "epoch": 1.2983091787439613, "percentage": 64.92, "elapsed_time": "5:19:03", "remaining_time": "2:52:26", "throughput": 9353.5, "total_tokens": 179058256}
{"current_steps": 3230, "total_steps": 4968, "loss": 0.3362, "lr": 2.7306109613937687e-06, "epoch": 1.3003220611916264, "percentage": 65.02, "elapsed_time": "5:19:33", "remaining_time": "2:51:57", "throughput": 9353.28, "total_tokens": 179339520}
{"current_steps": 3235, "total_steps": 4968, "loss": 0.3185, "lr": 2.7165353725029454e-06, "epoch": 1.3023349436392915, "percentage": 65.12, "elapsed_time": "5:20:05", "remaining_time": "2:51:28", "throughput": 9352.81, "total_tokens": 179624536}
{"current_steps": 3240, "total_steps": 4968, "loss": 0.337, "lr": 2.7024826117510193e-06, "epoch": 1.3043478260869565, "percentage": 65.22, "elapsed_time": "5:20:32", "remaining_time": "2:50:57", "throughput": 9354.06, "total_tokens": 179905904}
{"current_steps": 3245, "total_steps": 4968, "loss": 0.3196, "lr": 2.688452819625553e-06, "epoch": 1.3063607085346216, "percentage": 65.32, "elapsed_time": "5:21:03", "remaining_time": "2:50:28", "throughput": 9355.31, "total_tokens": 180211712}
{"current_steps": 3250, "total_steps": 4968, "loss": 0.3395, "lr": 2.674446136384486e-06, "epoch": 1.3083735909822867, "percentage": 65.42, "elapsed_time": "5:21:33", "remaining_time": "2:49:58", "throughput": 9354.18, "total_tokens": 180477328}
{"current_steps": 3255, "total_steps": 4968, "loss": 0.3552, "lr": 2.6604627020547334e-06, "epoch": 1.3103864734299517, "percentage": 65.52, "elapsed_time": "5:22:08", "remaining_time": "2:49:32", "throughput": 9352.29, "total_tokens": 180770296}
{"current_steps": 3260, "total_steps": 4968, "loss": 0.3285, "lr": 2.6465026564307924e-06, "epoch": 1.3123993558776168, "percentage": 65.62, "elapsed_time": "5:22:38", "remaining_time": "2:49:02", "throughput": 9351.12, "total_tokens": 181027688}
{"current_steps": 3265, "total_steps": 4968, "loss": 0.345, "lr": 2.6325661390733303e-06, "epoch": 1.3144122383252819, "percentage": 65.72, "elapsed_time": "5:23:11", "remaining_time": "2:48:34", "throughput": 9349.88, "total_tokens": 181309080}
{"current_steps": 3270, "total_steps": 4968, "loss": 0.3342, "lr": 2.6186532893078087e-06, "epoch": 1.316425120772947, "percentage": 65.82, "elapsed_time": "5:23:42", "remaining_time": "2:48:05", "throughput": 9348.17, "total_tokens": 181569064}
{"current_steps": 3275, "total_steps": 4968, "loss": 0.3451, "lr": 2.6047642462230756e-06, "epoch": 1.318438003220612, "percentage": 65.92, "elapsed_time": "5:24:17", "remaining_time": "2:47:38", "throughput": 9345.09, "total_tokens": 181836376}
{"current_steps": 3280, "total_steps": 4968, "loss": 0.3188, "lr": 2.590899148669981e-06, "epoch": 1.320450885668277, "percentage": 66.02, "elapsed_time": "5:24:52", "remaining_time": "2:47:11", "throughput": 9342.78, "total_tokens": 182109648}
{"current_steps": 3285, "total_steps": 4968, "loss": 0.3311, "lr": 2.5770581352599876e-06, "epoch": 1.322463768115942, "percentage": 66.12, "elapsed_time": "5:25:26", "remaining_time": "2:46:43", "throughput": 9340.59, "total_tokens": 182384584}
{"current_steps": 3290, "total_steps": 4968, "loss": 0.3586, "lr": 2.5632413443637887e-06, "epoch": 1.3244766505636072, "percentage": 66.22, "elapsed_time": "5:25:56", "remaining_time": "2:46:14", "throughput": 9341.34, "total_tokens": 182680016}
{"current_steps": 3295, "total_steps": 4968, "loss": 0.3404, "lr": 2.5494489141099155e-06, "epoch": 1.326489533011272, "percentage": 66.32, "elapsed_time": "5:26:23", "remaining_time": "2:45:43", "throughput": 9342.8, "total_tokens": 182967400}
{"current_steps": 3300, "total_steps": 4968, "loss": 0.3398, "lr": 2.535680982383364e-06, "epoch": 1.3285024154589373, "percentage": 66.43, "elapsed_time": "5:26:52", "remaining_time": "2:45:13", "throughput": 9343.57, "total_tokens": 183255320}
{"current_steps": 3305, "total_steps": 4968, "loss": 0.3251, "lr": 2.5219376868242173e-06, "epoch": 1.3305152979066022, "percentage": 66.53, "elapsed_time": "5:27:19", "remaining_time": "2:44:41", "throughput": 9344.78, "total_tokens": 183522760}
{"current_steps": 3310, "total_steps": 4968, "loss": 0.3322, "lr": 2.5082191648262654e-06, "epoch": 1.3325281803542672, "percentage": 66.63, "elapsed_time": "5:27:50", "remaining_time": "2:44:13", "throughput": 9344.03, "total_tokens": 183800888}
{"current_steps": 3315, "total_steps": 4968, "loss": 0.3411, "lr": 2.4945255535356343e-06, "epoch": 1.3345410628019323, "percentage": 66.73, "elapsed_time": "5:28:22", "remaining_time": "2:43:44", "throughput": 9342.77, "total_tokens": 184077008}
{"current_steps": 3320, "total_steps": 4968, "loss": 0.3503, "lr": 2.4808569898494144e-06, "epoch": 1.3365539452495974, "percentage": 66.83, "elapsed_time": "5:28:43", "remaining_time": "2:43:10", "throughput": 9346.9, "total_tokens": 184356944}
{"current_steps": 3325, "total_steps": 4968, "loss": 0.3164, "lr": 2.467213610414286e-06, "epoch": 1.3385668276972624, "percentage": 66.93, "elapsed_time": "5:29:16", "remaining_time": "2:42:42", "throughput": 9345.99, "total_tokens": 184641776}
{"current_steps": 3330, "total_steps": 4968, "loss": 0.3492, "lr": 2.453595551625165e-06, "epoch": 1.3405797101449275, "percentage": 67.03, "elapsed_time": "5:29:47", "remaining_time": "2:42:13", "throughput": 9345.63, "total_tokens": 184926320}
{"current_steps": 3335, "total_steps": 4968, "loss": 0.328, "lr": 2.4400029496238312e-06, "epoch": 1.3425925925925926, "percentage": 67.13, "elapsed_time": "5:30:17", "remaining_time": "2:41:43", "throughput": 9346.12, "total_tokens": 185218872}
{"current_steps": 3340, "total_steps": 4968, "loss": 0.3201, "lr": 2.4264359402975683e-06, "epoch": 1.3446054750402576, "percentage": 67.23, "elapsed_time": "5:30:47", "remaining_time": "2:41:14", "throughput": 9346.57, "total_tokens": 185509824}
{"current_steps": 3345, "total_steps": 4968, "loss": 0.326, "lr": 2.4128946592778086e-06, "epoch": 1.3466183574879227, "percentage": 67.33, "elapsed_time": "5:31:17", "remaining_time": "2:40:44", "throughput": 9347.76, "total_tokens": 185807552}
{"current_steps": 3350, "total_steps": 4968, "loss": 0.3266, "lr": 2.399379241938769e-06, "epoch": 1.3486312399355878, "percentage": 67.43, "elapsed_time": "5:31:51", "remaining_time": "2:40:16", "throughput": 9345.88, "total_tokens": 186086368}
{"current_steps": 3355, "total_steps": 4968, "loss": 0.3347, "lr": 2.385889823396108e-06, "epoch": 1.3506441223832528, "percentage": 67.53, "elapsed_time": "5:32:23", "remaining_time": "2:39:48", "throughput": 9344.13, "total_tokens": 186354824}
{"current_steps": 3360, "total_steps": 4968, "loss": 0.318, "lr": 2.3724265385055697e-06, "epoch": 1.3526570048309179, "percentage": 67.63, "elapsed_time": "5:32:49", "remaining_time": "2:39:16", "throughput": 9347.94, "total_tokens": 186671600}
{"current_steps": 3365, "total_steps": 4968, "loss": 0.339, "lr": 2.3589895218616356e-06, "epoch": 1.354669887278583, "percentage": 67.73, "elapsed_time": "5:33:21", "remaining_time": "2:38:48", "throughput": 9346.29, "total_tokens": 186944072}
{"current_steps": 3370, "total_steps": 4968, "loss": 0.3243, "lr": 2.3455789077961816e-06, "epoch": 1.356682769726248, "percentage": 67.83, "elapsed_time": "5:33:57", "remaining_time": "2:38:21", "throughput": 9344.73, "total_tokens": 187240712}
{"current_steps": 3375, "total_steps": 4968, "loss": 0.3372, "lr": 2.332194830377127e-06, "epoch": 1.358695652173913, "percentage": 67.93, "elapsed_time": "5:34:27", "remaining_time": "2:37:51", "throughput": 9345.16, "total_tokens": 187535336}
{"current_steps": 3380, "total_steps": 4968, "loss": 0.3206, "lr": 2.318837423407106e-06, "epoch": 1.3607085346215781, "percentage": 68.04, "elapsed_time": "5:34:56", "remaining_time": "2:37:21", "throughput": 9345.57, "total_tokens": 187812248}
{"current_steps": 3385, "total_steps": 4968, "loss": 0.3393, "lr": 2.3055068204221226e-06, "epoch": 1.3627214170692432, "percentage": 68.14, "elapsed_time": "5:35:22", "remaining_time": "2:36:50", "throughput": 9346.51, "total_tokens": 188073072}
{"current_steps": 3390, "total_steps": 4968, "loss": 0.3328, "lr": 2.292203154690218e-06, "epoch": 1.3647342995169083, "percentage": 68.24, "elapsed_time": "5:35:50", "remaining_time": "2:36:19", "throughput": 9348.36, "total_tokens": 188376696}
{"current_steps": 3395, "total_steps": 4968, "loss": 0.3264, "lr": 2.278926559210137e-06, "epoch": 1.3667471819645733, "percentage": 68.34, "elapsed_time": "5:36:19", "remaining_time": "2:35:49", "throughput": 9348.83, "total_tokens": 188653136}
{"current_steps": 3400, "total_steps": 4968, "loss": 0.3247, "lr": 2.2656771667099993e-06, "epoch": 1.3687600644122382, "percentage": 68.44, "elapsed_time": "5:36:50", "remaining_time": "2:35:20", "throughput": 9349.42, "total_tokens": 188957296}
{"current_steps": 3405, "total_steps": 4968, "loss": 0.3495, "lr": 2.2524551096459703e-06, "epoch": 1.3707729468599035, "percentage": 68.54, "elapsed_time": "5:37:14", "remaining_time": "2:34:48", "throughput": 9351.12, "total_tokens": 189219824}
{"current_steps": 3410, "total_steps": 4968, "loss": 0.3114, "lr": 2.239260520200941e-06, "epoch": 1.3727858293075683, "percentage": 68.64, "elapsed_time": "5:37:50", "remaining_time": "2:34:21", "throughput": 9347.2, "total_tokens": 189473144}
{"current_steps": 3415, "total_steps": 4968, "loss": 0.3444, "lr": 2.226093530283205e-06, "epoch": 1.3747987117552336, "percentage": 68.74, "elapsed_time": "5:38:20", "remaining_time": "2:33:51", "throughput": 9345.67, "total_tokens": 189723464}
{"current_steps": 3420, "total_steps": 4968, "loss": 0.3071, "lr": 2.21295427152514e-06, "epoch": 1.3768115942028984, "percentage": 68.84, "elapsed_time": "5:38:48", "remaining_time": "2:33:21", "throughput": 9344.66, "total_tokens": 189965672}
{"current_steps": 3425, "total_steps": 4968, "loss": 0.3403, "lr": 2.199842875281886e-06, "epoch": 1.3788244766505637, "percentage": 68.94, "elapsed_time": "5:39:16", "remaining_time": "2:32:50", "throughput": 9345.6, "total_tokens": 190245224}
{"current_steps": 3430, "total_steps": 4968, "loss": 0.3183, "lr": 2.186759472630045e-06, "epoch": 1.3808373590982286, "percentage": 69.04, "elapsed_time": "5:39:45", "remaining_time": "2:32:20", "throughput": 9346.73, "total_tokens": 190536872}
{"current_steps": 3435, "total_steps": 4968, "loss": 0.3364, "lr": 2.173704194366354e-06, "epoch": 1.3828502415458936, "percentage": 69.14, "elapsed_time": "5:40:15", "remaining_time": "2:31:51", "throughput": 9346.59, "total_tokens": 190816560}
{"current_steps": 3440, "total_steps": 4968, "loss": 0.3579, "lr": 2.1606771710063928e-06, "epoch": 1.3848631239935587, "percentage": 69.24, "elapsed_time": "5:40:46", "remaining_time": "2:31:22", "throughput": 9344.84, "total_tokens": 191069000}
{"current_steps": 3445, "total_steps": 4968, "loss": 0.3411, "lr": 2.1476785327832715e-06, "epoch": 1.3868760064412238, "percentage": 69.34, "elapsed_time": "5:41:14", "remaining_time": "2:30:51", "throughput": 9344.61, "total_tokens": 191327320}
{"current_steps": 3450, "total_steps": 4968, "loss": 0.3385, "lr": 2.1347084096463293e-06, "epoch": 1.3888888888888888, "percentage": 69.44, "elapsed_time": "5:41:45", "remaining_time": "2:30:22", "throughput": 9344.76, "total_tokens": 191614592}
{"current_steps": 3455, "total_steps": 4968, "loss": 0.3458, "lr": 2.1217669312598364e-06, "epoch": 1.390901771336554, "percentage": 69.55, "elapsed_time": "5:42:09", "remaining_time": "2:29:50", "throughput": 9347.15, "total_tokens": 191894816}
{"current_steps": 3460, "total_steps": 4968, "loss": 0.3421, "lr": 2.108854227001693e-06, "epoch": 1.392914653784219, "percentage": 69.65, "elapsed_time": "5:42:39", "remaining_time": "2:29:20", "throughput": 9347.66, "total_tokens": 192184888}
{"current_steps": 3465, "total_steps": 4968, "loss": 0.3234, "lr": 2.0959704259621457e-06, "epoch": 1.394927536231884, "percentage": 69.75, "elapsed_time": "5:43:05", "remaining_time": "2:28:49", "throughput": 9349.09, "total_tokens": 192457000}
{"current_steps": 3470, "total_steps": 4968, "loss": 0.3269, "lr": 2.0831156569424877e-06, "epoch": 1.396940418679549, "percentage": 69.85, "elapsed_time": "5:43:27", "remaining_time": "2:28:16", "throughput": 9352.26, "total_tokens": 192726472}
{"current_steps": 3475, "total_steps": 4968, "loss": 0.3272, "lr": 2.070290048453777e-06, "epoch": 1.3989533011272142, "percentage": 69.95, "elapsed_time": "5:43:56", "remaining_time": "2:27:46", "throughput": 9352.75, "total_tokens": 193004472}
{"current_steps": 3480, "total_steps": 4968, "loss": 0.3186, "lr": 2.0574937287155496e-06, "epoch": 1.4009661835748792, "percentage": 70.05, "elapsed_time": "5:44:25", "remaining_time": "2:27:16", "throughput": 9353.05, "total_tokens": 193289112}
{"current_steps": 3485, "total_steps": 4968, "loss": 0.3457, "lr": 2.0447268256545327e-06, "epoch": 1.4029790660225443, "percentage": 70.15, "elapsed_time": "5:44:49", "remaining_time": "2:26:44", "throughput": 9354.73, "total_tokens": 193544272}
{"current_steps": 3490, "total_steps": 4968, "loss": 0.3205, "lr": 2.0319894669033758e-06, "epoch": 1.4049919484702094, "percentage": 70.25, "elapsed_time": "5:45:20", "remaining_time": "2:26:15", "throughput": 9354.21, "total_tokens": 193824776}
{"current_steps": 3495, "total_steps": 4968, "loss": 0.3224, "lr": 2.0192817797993674e-06, "epoch": 1.4070048309178744, "percentage": 70.35, "elapsed_time": "5:45:54", "remaining_time": "2:25:47", "throughput": 9352.84, "total_tokens": 194114008}
{"current_steps": 3500, "total_steps": 4968, "loss": 0.3419, "lr": 2.0066038913831653e-06, "epoch": 1.4090177133655395, "percentage": 70.45, "elapsed_time": "5:46:20", "remaining_time": "2:25:16", "throughput": 9351.94, "total_tokens": 194341864}
{"current_steps": 3505, "total_steps": 4968, "loss": 0.323, "lr": 1.9939559283975237e-06, "epoch": 1.4110305958132046, "percentage": 70.55, "elapsed_time": "5:46:51", "remaining_time": "2:24:46", "throughput": 9351.09, "total_tokens": 194613464}
{"current_steps": 3510, "total_steps": 4968, "loss": 0.3141, "lr": 1.9813380172860305e-06, "epoch": 1.4130434782608696, "percentage": 70.65, "elapsed_time": "5:47:21", "remaining_time": "2:24:17", "throughput": 9352.65, "total_tokens": 194922320}
{"current_steps": 3515, "total_steps": 4968, "loss": 0.3237, "lr": 1.9687502841918345e-06, "epoch": 1.4150563607085347, "percentage": 70.75, "elapsed_time": "5:47:48", "remaining_time": "2:23:46", "throughput": 9354.29, "total_tokens": 195209048}
{"current_steps": 3520, "total_steps": 4968, "loss": 0.3181, "lr": 1.956192854956397e-06, "epoch": 1.4170692431561998, "percentage": 70.85, "elapsed_time": "5:48:15", "remaining_time": "2:23:15", "throughput": 9356.08, "total_tokens": 195495712}
{"current_steps": 3525, "total_steps": 4968, "loss": 0.3469, "lr": 1.9436658551182234e-06, "epoch": 1.4190821256038646, "percentage": 70.95, "elapsed_time": "5:48:48", "remaining_time": "2:22:47", "throughput": 9354.94, "total_tokens": 195782624}
{"current_steps": 3530, "total_steps": 4968, "loss": 0.3269, "lr": 1.9311694099116143e-06, "epoch": 1.4210950080515299, "percentage": 71.05, "elapsed_time": "5:49:16", "remaining_time": "2:22:16", "throughput": 9355.78, "total_tokens": 196062136}
{"current_steps": 3535, "total_steps": 4968, "loss": 0.3526, "lr": 1.9187036442654093e-06, "epoch": 1.4231078904991947, "percentage": 71.16, "elapsed_time": "5:49:38", "remaining_time": "2:21:44", "throughput": 9358.37, "total_tokens": 196327816}
{"current_steps": 3540, "total_steps": 4968, "loss": 0.3434, "lr": 1.906268682801739e-06, "epoch": 1.42512077294686, "percentage": 71.26, "elapsed_time": "5:50:06", "remaining_time": "2:21:13", "throughput": 9358.61, "total_tokens": 196587800}
{"current_steps": 3545, "total_steps": 4968, "loss": 0.3354, "lr": 1.893864649834783e-06, "epoch": 1.4271336553945249, "percentage": 71.36, "elapsed_time": "5:50:41", "remaining_time": "2:20:46", "throughput": 9356.26, "total_tokens": 196871416}
{"current_steps": 3550, "total_steps": 4968, "loss": 0.319, "lr": 1.881491669369519e-06, "epoch": 1.4291465378421901, "percentage": 71.46, "elapsed_time": "5:51:12", "remaining_time": "2:20:16", "throughput": 9355.25, "total_tokens": 197135528}
{"current_steps": 3555, "total_steps": 4968, "loss": 0.3186, "lr": 1.8691498651004936e-06, "epoch": 1.431159420289855, "percentage": 71.56, "elapsed_time": "5:51:45", "remaining_time": "2:19:48", "throughput": 9353.07, "total_tokens": 197398224}
{"current_steps": 3560, "total_steps": 4968, "loss": 0.3354, "lr": 1.8568393604105778e-06, "epoch": 1.43317230273752, "percentage": 71.66, "elapsed_time": "5:52:10", "remaining_time": "2:19:17", "throughput": 9354.44, "total_tokens": 197661288}
{"current_steps": 3565, "total_steps": 4968, "loss": 0.3398, "lr": 1.8445602783697375e-06, "epoch": 1.4351851851851851, "percentage": 71.76, "elapsed_time": "5:52:43", "remaining_time": "2:18:48", "throughput": 9352.36, "total_tokens": 197926592}
{"current_steps": 3570, "total_steps": 4968, "loss": 0.3395, "lr": 1.8323127417337977e-06, "epoch": 1.4371980676328502, "percentage": 71.86, "elapsed_time": "5:53:14", "remaining_time": "2:18:19", "throughput": 9351.95, "total_tokens": 198206904}
{"current_steps": 3575, "total_steps": 4968, "loss": 0.342, "lr": 1.8200968729432233e-06, "epoch": 1.4392109500805152, "percentage": 71.96, "elapsed_time": "5:53:49", "remaining_time": "2:17:52", "throughput": 9348.75, "total_tokens": 198469936}
{"current_steps": 3580, "total_steps": 4968, "loss": 0.3365, "lr": 1.8079127941218894e-06, "epoch": 1.4412238325281803, "percentage": 72.06, "elapsed_time": "5:54:12", "remaining_time": "2:17:19", "throughput": 9351.46, "total_tokens": 198741632}
{"current_steps": 3585, "total_steps": 4968, "loss": 0.3311, "lr": 1.7957606270758626e-06, "epoch": 1.4432367149758454, "percentage": 72.16, "elapsed_time": "5:54:38", "remaining_time": "2:16:48", "throughput": 9353.04, "total_tokens": 199015992}
{"current_steps": 3590, "total_steps": 4968, "loss": 0.3381, "lr": 1.7836404932921842e-06, "epoch": 1.4452495974235104, "percentage": 72.26, "elapsed_time": "5:55:01", "remaining_time": "2:16:16", "throughput": 9354.99, "total_tokens": 199274512}
{"current_steps": 3595, "total_steps": 4968, "loss": 0.3316, "lr": 1.7715525139376482e-06, "epoch": 1.4472624798711755, "percentage": 72.36, "elapsed_time": "5:55:27", "remaining_time": "2:15:45", "throughput": 9356.5, "total_tokens": 199553176}
{"current_steps": 3600, "total_steps": 4968, "loss": 0.3249, "lr": 1.7594968098576027e-06, "epoch": 1.4492753623188406, "percentage": 72.46, "elapsed_time": "5:55:55", "remaining_time": "2:15:14", "throughput": 9356.87, "total_tokens": 199817680}
{"current_steps": 3605, "total_steps": 4968, "loss": 0.323, "lr": 1.7474735015747312e-06, "epoch": 1.4512882447665056, "percentage": 72.56, "elapsed_time": "5:56:20", "remaining_time": "2:14:43", "throughput": 9358.61, "total_tokens": 200090712}
{"current_steps": 3610, "total_steps": 4968, "loss": 0.3295, "lr": 1.735482709287854e-06, "epoch": 1.4533011272141707, "percentage": 72.67, "elapsed_time": "5:56:48", "remaining_time": "2:14:13", "throughput": 9358.76, "total_tokens": 200356408}
{"current_steps": 3615, "total_steps": 4968, "loss": 0.3279, "lr": 1.723524552870724e-06, "epoch": 1.4553140096618358, "percentage": 72.77, "elapsed_time": "5:57:19", "remaining_time": "2:13:44", "throughput": 9358.45, "total_tokens": 200644032}
{"current_steps": 3620, "total_steps": 4968, "loss": 0.3332, "lr": 1.711599151870823e-06, "epoch": 1.4573268921095008, "percentage": 72.87, "elapsed_time": "5:57:40", "remaining_time": "2:13:11", "throughput": 9362.14, "total_tokens": 200918008}
{"current_steps": 3625, "total_steps": 4968, "loss": 0.3413, "lr": 1.6997066255081795e-06, "epoch": 1.459339774557166, "percentage": 72.97, "elapsed_time": "5:58:12", "remaining_time": "2:12:42", "throughput": 9362.17, "total_tokens": 201217456}
{"current_steps": 3630, "total_steps": 4968, "loss": 0.3363, "lr": 1.6878470926741646e-06, "epoch": 1.461352657004831, "percentage": 73.07, "elapsed_time": "5:58:50", "remaining_time": "2:12:16", "throughput": 9357.8, "total_tokens": 201481680}
{"current_steps": 3635, "total_steps": 4968, "loss": 0.3297, "lr": 1.6760206719303107e-06, "epoch": 1.463365539452496, "percentage": 73.17, "elapsed_time": "5:59:22", "remaining_time": "2:11:47", "throughput": 9356.95, "total_tokens": 201762592}
{"current_steps": 3640, "total_steps": 4968, "loss": 0.3243, "lr": 1.6642274815071213e-06, "epoch": 1.465378421900161, "percentage": 73.27, "elapsed_time": "5:59:56", "remaining_time": "2:11:19", "throughput": 9355.59, "total_tokens": 202049912}
{"current_steps": 3645, "total_steps": 4968, "loss": 0.3416, "lr": 1.6524676393028955e-06, "epoch": 1.4673913043478262, "percentage": 73.37, "elapsed_time": "6:00:28", "remaining_time": "2:10:50", "throughput": 9355.12, "total_tokens": 202333320}
{"current_steps": 3650, "total_steps": 4968, "loss": 0.3344, "lr": 1.640741262882538e-06, "epoch": 1.469404186795491, "percentage": 73.47, "elapsed_time": "6:00:52", "remaining_time": "2:10:18", "throughput": 9356.38, "total_tokens": 202592424}
{"current_steps": 3655, "total_steps": 4968, "loss": 0.318, "lr": 1.629048469476398e-06, "epoch": 1.4714170692431563, "percentage": 73.57, "elapsed_time": "6:01:18", "remaining_time": "2:09:47", "throughput": 9358.02, "total_tokens": 202863200}
{"current_steps": 3660, "total_steps": 4968, "loss": 0.3243, "lr": 1.6173893759790871e-06, "epoch": 1.4734299516908211, "percentage": 73.67, "elapsed_time": "6:01:51", "remaining_time": "2:09:19", "throughput": 9357.7, "total_tokens": 203166800}
{"current_steps": 3665, "total_steps": 4968, "loss": 0.3158, "lr": 1.6057640989483158e-06, "epoch": 1.4754428341384864, "percentage": 73.77, "elapsed_time": "6:02:23", "remaining_time": "2:08:50", "throughput": 9356.01, "total_tokens": 203436976}
{"current_steps": 3670, "total_steps": 4968, "loss": 0.3177, "lr": 1.5941727546037223e-06, "epoch": 1.4774557165861513, "percentage": 73.87, "elapsed_time": "6:02:53", "remaining_time": "2:08:20", "throughput": 9355.38, "total_tokens": 203699416}
{"current_steps": 3675, "total_steps": 4968, "loss": 0.3176, "lr": 1.5826154588257204e-06, "epoch": 1.4794685990338166, "percentage": 73.97, "elapsed_time": "6:03:16", "remaining_time": "2:07:48", "throughput": 9357.87, "total_tokens": 203972208}
{"current_steps": 3680, "total_steps": 4968, "loss": 0.32, "lr": 1.5710923271543282e-06, "epoch": 1.4814814814814814, "percentage": 74.07, "elapsed_time": "6:03:45", "remaining_time": "2:07:19", "throughput": 9357.46, "total_tokens": 204233264}
{"current_steps": 3685, "total_steps": 4968, "loss": 0.3355, "lr": 1.5596034747880263e-06, "epoch": 1.4834943639291465, "percentage": 74.17, "elapsed_time": "6:04:21", "remaining_time": "2:06:51", "throughput": 9354.2, "total_tokens": 204494824}
{"current_steps": 3690, "total_steps": 4968, "loss": 0.3288, "lr": 1.5481490165825969e-06, "epoch": 1.4855072463768115, "percentage": 74.28, "elapsed_time": "6:04:54", "remaining_time": "2:06:22", "throughput": 9353.99, "total_tokens": 204799728}
{"current_steps": 3695, "total_steps": 4968, "loss": 0.3284, "lr": 1.5367290670499802e-06, "epoch": 1.4875201288244766, "percentage": 74.38, "elapsed_time": "6:05:21", "remaining_time": "2:05:52", "throughput": 9354.89, "total_tokens": 205070904}
{"current_steps": 3700, "total_steps": 4968, "loss": 0.3319, "lr": 1.525343740357128e-06, "epoch": 1.4895330112721417, "percentage": 74.48, "elapsed_time": "6:05:55", "remaining_time": "2:05:24", "throughput": 9352.78, "total_tokens": 205343752}
{"current_steps": 3705, "total_steps": 4968, "loss": 0.3266, "lr": 1.5139931503248595e-06, "epoch": 1.4915458937198067, "percentage": 74.58, "elapsed_time": "6:06:24", "remaining_time": "2:04:54", "throughput": 9353.48, "total_tokens": 205628256}
{"current_steps": 3710, "total_steps": 4968, "loss": 0.3226, "lr": 1.5026774104267289e-06, "epoch": 1.4935587761674718, "percentage": 74.68, "elapsed_time": "6:06:55", "remaining_time": "2:04:24", "throughput": 9353.2, "total_tokens": 205912760}
{"current_steps": 3715, "total_steps": 4968, "loss": 0.3201, "lr": 1.4913966337878876e-06, "epoch": 1.4955716586151369, "percentage": 74.78, "elapsed_time": "6:07:21", "remaining_time": "2:03:54", "throughput": 9353.9, "total_tokens": 206174696}
{"current_steps": 3720, "total_steps": 4968, "loss": 0.3276, "lr": 1.4801509331839553e-06, "epoch": 1.497584541062802, "percentage": 74.88, "elapsed_time": "6:07:53", "remaining_time": "2:03:25", "throughput": 9352.86, "total_tokens": 206447872}
{"current_steps": 3725, "total_steps": 4968, "loss": 0.3371, "lr": 1.4689404210398906e-06, "epoch": 1.499597423510467, "percentage": 74.98, "elapsed_time": "6:08:15", "remaining_time": "2:02:53", "throughput": 9356.37, "total_tokens": 206738232}
{"current_steps": 3730, "total_steps": 4968, "loss": 0.3509, "lr": 1.4577652094288652e-06, "epoch": 1.501610305958132, "percentage": 75.08, "elapsed_time": "6:08:48", "remaining_time": "2:02:24", "throughput": 9354.99, "total_tokens": 207007936}
{"current_steps": 3735, "total_steps": 4968, "loss": 0.329, "lr": 1.4466254100711496e-06, "epoch": 1.5036231884057971, "percentage": 75.18, "elapsed_time": "6:09:22", "remaining_time": "2:01:56", "throughput": 9352.36, "total_tokens": 207275768}
{"current_steps": 3740, "total_steps": 4968, "loss": 0.3273, "lr": 1.4355211343329912e-06, "epoch": 1.5056360708534622, "percentage": 75.28, "elapsed_time": "6:09:42", "remaining_time": "2:01:23", "throughput": 9356.26, "total_tokens": 207542112}
{"current_steps": 3745, "total_steps": 4968, "loss": 0.2991, "lr": 1.4244524932255026e-06, "epoch": 1.5076489533011272, "percentage": 75.38, "elapsed_time": "6:10:09", "remaining_time": "2:00:52", "throughput": 9357.27, "total_tokens": 207818368}
{"current_steps": 3750, "total_steps": 4968, "loss": 0.3412, "lr": 1.4134195974035525e-06, "epoch": 1.5096618357487923, "percentage": 75.48, "elapsed_time": "6:10:43", "remaining_time": "2:00:24", "throughput": 9356.41, "total_tokens": 208118848}
{"current_steps": 3755, "total_steps": 4968, "loss": 0.3414, "lr": 1.4024225571646582e-06, "epoch": 1.5116747181964574, "percentage": 75.58, "elapsed_time": "6:11:10", "remaining_time": "1:59:54", "throughput": 9357.72, "total_tokens": 208398136}
{"current_steps": 3760, "total_steps": 4968, "loss": 0.3437, "lr": 1.39146148244788e-06, "epoch": 1.5136876006441224, "percentage": 75.68, "elapsed_time": "6:11:38", "remaining_time": "1:59:23", "throughput": 9357.88, "total_tokens": 208662024}
{"current_steps": 3765, "total_steps": 4968, "loss": 0.3299, "lr": 1.3805364828327305e-06, "epoch": 1.5157004830917873, "percentage": 75.79, "elapsed_time": "6:12:04", "remaining_time": "1:58:53", "throughput": 9359.55, "total_tokens": 208943320}
{"current_steps": 3770, "total_steps": 4968, "loss": 0.3327, "lr": 1.3696476675380722e-06, "epoch": 1.5177133655394526, "percentage": 75.89, "elapsed_time": "6:12:37", "remaining_time": "1:58:24", "throughput": 9357.86, "total_tokens": 209217648}
{"current_steps": 3775, "total_steps": 4968, "loss": 0.3271, "lr": 1.3587951454210256e-06, "epoch": 1.5197262479871174, "percentage": 75.99, "elapsed_time": "6:13:06", "remaining_time": "1:57:54", "throughput": 9359.01, "total_tokens": 209517184}
{"current_steps": 3780, "total_steps": 4968, "loss": 0.3213, "lr": 1.3479790249758885e-06, "epoch": 1.5217391304347827, "percentage": 76.09, "elapsed_time": "6:13:35", "remaining_time": "1:57:24", "throughput": 9359.59, "total_tokens": 209801536}
{"current_steps": 3785, "total_steps": 4968, "loss": 0.3166, "lr": 1.337199414333037e-06, "epoch": 1.5237520128824475, "percentage": 76.19, "elapsed_time": "6:14:07", "remaining_time": "1:56:55", "throughput": 9359.26, "total_tokens": 210091416}
{"current_steps": 3790, "total_steps": 4968, "loss": 0.3243, "lr": 1.3264564212578613e-06, "epoch": 1.5257648953301128, "percentage": 76.29, "elapsed_time": "6:14:32", "remaining_time": "1:56:24", "throughput": 9361.02, "total_tokens": 210368136}
{"current_steps": 3795, "total_steps": 4968, "loss": 0.3485, "lr": 1.3157501531496746e-06, "epoch": 1.5277777777777777, "percentage": 76.39, "elapsed_time": "6:15:03", "remaining_time": "1:55:55", "throughput": 9361.44, "total_tokens": 210669744}
{"current_steps": 3800, "total_steps": 4968, "loss": 0.336, "lr": 1.3050807170406483e-06, "epoch": 1.529790660225443, "percentage": 76.49, "elapsed_time": "6:15:30", "remaining_time": "1:55:25", "throughput": 9362.57, "total_tokens": 210944912}
{"current_steps": 3805, "total_steps": 4968, "loss": 0.3453, "lr": 1.2944482195947384e-06, "epoch": 1.5318035426731078, "percentage": 76.59, "elapsed_time": "6:16:01", "remaining_time": "1:54:55", "throughput": 9362.46, "total_tokens": 211230096}
{"current_steps": 3810, "total_steps": 4968, "loss": 0.3462, "lr": 1.2838527671066198e-06, "epoch": 1.533816425120773, "percentage": 76.69, "elapsed_time": "6:16:34", "remaining_time": "1:54:27", "throughput": 9361.59, "total_tokens": 211519208}
{"current_steps": 3815, "total_steps": 4968, "loss": 0.335, "lr": 1.2732944655006203e-06, "epoch": 1.535829307568438, "percentage": 76.79, "elapsed_time": "6:16:59", "remaining_time": "1:53:56", "throughput": 9362.42, "total_tokens": 211775088}
{"current_steps": 3820, "total_steps": 4968, "loss": 0.3482, "lr": 1.2627734203296688e-06, "epoch": 1.537842190016103, "percentage": 76.89, "elapsed_time": "6:17:28", "remaining_time": "1:53:26", "throughput": 9361.9, "total_tokens": 212032792}
{"current_steps": 3825, "total_steps": 4968, "loss": 0.3465, "lr": 1.2522897367742337e-06, "epoch": 1.539855072463768, "percentage": 76.99, "elapsed_time": "6:17:58", "remaining_time": "1:52:56", "throughput": 9362.84, "total_tokens": 212334584}
{"current_steps": 3830, "total_steps": 4968, "loss": 0.3228, "lr": 1.2418435196412754e-06, "epoch": 1.5418679549114331, "percentage": 77.09, "elapsed_time": "6:18:27", "remaining_time": "1:52:26", "throughput": 9362.19, "total_tokens": 212589368}
{"current_steps": 3835, "total_steps": 4968, "loss": 0.3262, "lr": 1.2314348733631958e-06, "epoch": 1.5438808373590982, "percentage": 77.19, "elapsed_time": "6:18:53", "remaining_time": "1:51:56", "throughput": 9363.44, "total_tokens": 212859664}
{"current_steps": 3840, "total_steps": 4968, "loss": 0.3386, "lr": 1.2210639019967929e-06, "epoch": 1.5458937198067633, "percentage": 77.29, "elapsed_time": "6:19:26", "remaining_time": "1:51:27", "throughput": 9362.76, "total_tokens": 213157880}
{"current_steps": 3845, "total_steps": 4968, "loss": 0.3254, "lr": 1.2107307092222276e-06, "epoch": 1.5479066022544283, "percentage": 77.4, "elapsed_time": "6:19:55", "remaining_time": "1:50:57", "throughput": 9363.06, "total_tokens": 213432864}
{"current_steps": 3850, "total_steps": 4968, "loss": 0.33, "lr": 1.2004353983419797e-06, "epoch": 1.5499194847020934, "percentage": 77.5, "elapsed_time": "6:20:33", "remaining_time": "1:50:30", "throughput": 9360.6, "total_tokens": 213735872}
{"current_steps": 3855, "total_steps": 4968, "loss": 0.3211, "lr": 1.1901780722798183e-06, "epoch": 1.5519323671497585, "percentage": 77.6, "elapsed_time": "6:20:56", "remaining_time": "1:49:58", "throughput": 9365.2, "total_tokens": 214051832}
{"current_steps": 3860, "total_steps": 4968, "loss": 0.3384, "lr": 1.1799588335797735e-06, "epoch": 1.5539452495974235, "percentage": 77.7, "elapsed_time": "6:21:21", "remaining_time": "1:49:28", "throughput": 9366.52, "total_tokens": 214322768}
{"current_steps": 3865, "total_steps": 4968, "loss": 0.3353, "lr": 1.1697777844051105e-06, "epoch": 1.5559581320450886, "percentage": 77.8, "elapsed_time": "6:21:48", "remaining_time": "1:48:57", "throughput": 9367.67, "total_tokens": 214597800}
{"current_steps": 3870, "total_steps": 4968, "loss": 0.3411, "lr": 1.1596350265373053e-06, "epoch": 1.5579710144927537, "percentage": 77.9, "elapsed_time": "6:22:20", "remaining_time": "1:48:28", "throughput": 9367.17, "total_tokens": 214891392}
{"current_steps": 3875, "total_steps": 4968, "loss": 0.3228, "lr": 1.1495306613750324e-06, "epoch": 1.5599838969404187, "percentage": 78.0, "elapsed_time": "6:22:52", "remaining_time": "1:47:59", "throughput": 9366.71, "total_tokens": 215175696}
{"current_steps": 3880, "total_steps": 4968, "loss": 0.3163, "lr": 1.1394647899331484e-06, "epoch": 1.5619967793880838, "percentage": 78.1, "elapsed_time": "6:23:15", "remaining_time": "1:47:28", "throughput": 9369.4, "total_tokens": 215451904}
{"current_steps": 3885, "total_steps": 4968, "loss": 0.3331, "lr": 1.129437512841683e-06, "epoch": 1.5640096618357489, "percentage": 78.2, "elapsed_time": "6:23:45", "remaining_time": "1:46:58", "throughput": 9369.23, "total_tokens": 215733512}
{"current_steps": 3890, "total_steps": 4968, "loss": 0.3652, "lr": 1.1194489303448318e-06, "epoch": 1.5660225442834137, "percentage": 78.3, "elapsed_time": "6:24:09", "remaining_time": "1:46:27", "throughput": 9370.92, "total_tokens": 215993512}
{"current_steps": 3895, "total_steps": 4968, "loss": 0.3255, "lr": 1.109499142299953e-06, "epoch": 1.568035426731079, "percentage": 78.4, "elapsed_time": "6:24:37", "remaining_time": "1:45:57", "throughput": 9371.43, "total_tokens": 216268800}
{"current_steps": 3900, "total_steps": 4968, "loss": 0.3361, "lr": 1.0995882481765724e-06, "epoch": 1.5700483091787438, "percentage": 78.5, "elapsed_time": "6:25:10", "remaining_time": "1:45:28", "throughput": 9371.48, "total_tokens": 216575512}
{"current_steps": 3905, "total_steps": 4968, "loss": 0.3162, "lr": 1.089716347055388e-06, "epoch": 1.5720611916264091, "percentage": 78.6, "elapsed_time": "6:25:37", "remaining_time": "1:44:58", "throughput": 9371.85, "total_tokens": 216837920}
{"current_steps": 3910, "total_steps": 4968, "loss": 0.33, "lr": 1.0798835376272782e-06, "epoch": 1.574074074074074, "percentage": 78.7, "elapsed_time": "6:26:13", "remaining_time": "1:44:30", "throughput": 9369.44, "total_tokens": 217123624}
{"current_steps": 3915, "total_steps": 4968, "loss": 0.3347, "lr": 1.070089918192317e-06, "epoch": 1.5760869565217392, "percentage": 78.8, "elapsed_time": "6:26:35", "remaining_time": "1:43:58", "throughput": 9372.07, "total_tokens": 217391624}
{"current_steps": 3920, "total_steps": 4968, "loss": 0.3253, "lr": 1.0603355866587883e-06, "epoch": 1.578099838969404, "percentage": 78.9, "elapsed_time": "6:27:08", "remaining_time": "1:43:30", "throughput": 9370.6, "total_tokens": 217662616}
{"current_steps": 3925, "total_steps": 4968, "loss": 0.3248, "lr": 1.050620640542208e-06, "epoch": 1.5801127214170694, "percentage": 79.01, "elapsed_time": "6:27:45", "remaining_time": "1:43:02", "throughput": 9367.85, "total_tokens": 217949272}
{"current_steps": 3930, "total_steps": 4968, "loss": 0.3256, "lr": 1.040945176964353e-06, "epoch": 1.5821256038647342, "percentage": 79.11, "elapsed_time": "6:28:16", "remaining_time": "1:42:33", "throughput": 9367.87, "total_tokens": 218237752}
{"current_steps": 3935, "total_steps": 4968, "loss": 0.3177, "lr": 1.0313092926522865e-06, "epoch": 1.5841384863123995, "percentage": 79.21, "elapsed_time": "6:28:45", "remaining_time": "1:42:03", "throughput": 9368.74, "total_tokens": 218526008}
{"current_steps": 3940, "total_steps": 4968, "loss": 0.3283, "lr": 1.0217130839373913e-06, "epoch": 1.5861513687600644, "percentage": 79.31, "elapsed_time": "6:29:14", "remaining_time": "1:41:33", "throughput": 9368.83, "total_tokens": 218801648}
{"current_steps": 3945, "total_steps": 4968, "loss": 0.3361, "lr": 1.0121566467544085e-06, "epoch": 1.5881642512077294, "percentage": 79.41, "elapsed_time": "6:29:47", "remaining_time": "1:41:04", "throughput": 9367.52, "total_tokens": 219080992}
{"current_steps": 3950, "total_steps": 4968, "loss": 0.3334, "lr": 1.0026400766404736e-06, "epoch": 1.5901771336553945, "percentage": 79.51, "elapsed_time": "6:30:17", "remaining_time": "1:40:35", "throughput": 9367.95, "total_tokens": 219374736}
{"current_steps": 3955, "total_steps": 4968, "loss": 0.3289, "lr": 9.931634687341695e-07, "epoch": 1.5921900161030595, "percentage": 79.61, "elapsed_time": "6:30:46", "remaining_time": "1:40:05", "throughput": 9368.06, "total_tokens": 219645792}
{"current_steps": 3960, "total_steps": 4968, "loss": 0.3211, "lr": 9.837269177745683e-07, "epoch": 1.5942028985507246, "percentage": 79.71, "elapsed_time": "6:31:11", "remaining_time": "1:39:34", "throughput": 9370.44, "total_tokens": 219942200}
{"current_steps": 3965, "total_steps": 4968, "loss": 0.3075, "lr": 9.743305181002877e-07, "epoch": 1.5962157809983897, "percentage": 79.81, "elapsed_time": "6:31:39", "remaining_time": "1:39:04", "throughput": 9370.92, "total_tokens": 220214488}
{"current_steps": 3970, "total_steps": 4968, "loss": 0.3209, "lr": 9.64974363648548e-07, "epoch": 1.5982286634460547, "percentage": 79.91, "elapsed_time": "6:32:08", "remaining_time": "1:38:34", "throughput": 9370.31, "total_tokens": 220469832}
{"current_steps": 3975, "total_steps": 4968, "loss": 0.3333, "lr": 9.556585479542285e-07, "epoch": 1.6002415458937198, "percentage": 80.01, "elapsed_time": "6:32:36", "remaining_time": "1:38:04", "throughput": 9372.04, "total_tokens": 220769464}
{"current_steps": 3980, "total_steps": 4968, "loss": 0.3282, "lr": 9.463831641489391e-07, "epoch": 1.6022544283413849, "percentage": 80.11, "elapsed_time": "6:33:10", "remaining_time": "1:37:36", "throughput": 9370.61, "total_tokens": 221056816}
{"current_steps": 3985, "total_steps": 4968, "loss": 0.3326, "lr": 9.371483049600849e-07, "epoch": 1.60426731078905, "percentage": 80.21, "elapsed_time": "6:33:43", "remaining_time": "1:37:07", "throughput": 9369.47, "total_tokens": 221336336}
{"current_steps": 3990, "total_steps": 4968, "loss": 0.3372, "lr": 9.279540627099409e-07, "epoch": 1.606280193236715, "percentage": 80.31, "elapsed_time": "6:34:12", "remaining_time": "1:36:37", "throughput": 9369.87, "total_tokens": 221624032}
{"current_steps": 3995, "total_steps": 4968, "loss": 0.3426, "lr": 9.188005293147273e-07, "epoch": 1.60829307568438, "percentage": 80.41, "elapsed_time": "6:34:36", "remaining_time": "1:36:06", "throughput": 9373.3, "total_tokens": 221924728}
{"current_steps": 4000, "total_steps": 4968, "loss": 0.3322, "lr": 9.096877962836941e-07, "epoch": 1.6103059581320451, "percentage": 80.52, "elapsed_time": "6:35:07", "remaining_time": "1:35:37", "throughput": 9373.03, "total_tokens": 222209696}
{"current_steps": 4005, "total_steps": 4968, "loss": 0.3283, "lr": 9.006159547182003e-07, "epoch": 1.6123188405797102, "percentage": 80.62, "elapsed_time": "6:35:31", "remaining_time": "1:35:06", "throughput": 9375.66, "total_tokens": 222501176}
{"current_steps": 4010, "total_steps": 4968, "loss": 0.3212, "lr": 8.915850953108096e-07, "epoch": 1.6143317230273753, "percentage": 80.72, "elapsed_time": "6:35:54", "remaining_time": "1:34:35", "throughput": 9378.1, "total_tokens": 222774880}
{"current_steps": 4015, "total_steps": 4968, "loss": 0.3271, "lr": 8.8259530834438e-07, "epoch": 1.61634460547504, "percentage": 80.82, "elapsed_time": "6:36:27", "remaining_time": "1:34:06", "throughput": 9377.08, "total_tokens": 223056112}
{"current_steps": 4020, "total_steps": 4968, "loss": 0.3276, "lr": 8.736466836911622e-07, "epoch": 1.6183574879227054, "percentage": 80.92, "elapsed_time": "6:36:51", "remaining_time": "1:33:35", "throughput": 9378.54, "total_tokens": 223315064}
{"current_steps": 4025, "total_steps": 4968, "loss": 0.3239, "lr": 8.647393108119023e-07, "epoch": 1.6203703703703702, "percentage": 81.02, "elapsed_time": "6:37:23", "remaining_time": "1:33:06", "throughput": 9378.09, "total_tokens": 223605536}
{"current_steps": 4030, "total_steps": 4968, "loss": 0.3307, "lr": 8.558732787549429e-07, "epoch": 1.6223832528180355, "percentage": 81.12, "elapsed_time": "6:37:49", "remaining_time": "1:32:35", "throughput": 9378.84, "total_tokens": 223864176}
{"current_steps": 4035, "total_steps": 4968, "loss": 0.3482, "lr": 8.470486761553398e-07, "epoch": 1.6243961352657004, "percentage": 81.22, "elapsed_time": "6:38:17", "remaining_time": "1:32:05", "throughput": 9379.89, "total_tokens": 224156968}
{"current_steps": 4040, "total_steps": 4968, "loss": 0.3196, "lr": 8.38265591233971e-07, "epoch": 1.6264090177133657, "percentage": 81.32, "elapsed_time": "6:38:42", "remaining_time": "1:31:35", "throughput": 9380.81, "total_tokens": 224410576}
{"current_steps": 4045, "total_steps": 4968, "loss": 0.3344, "lr": 8.29524111796654e-07, "epoch": 1.6284219001610305, "percentage": 81.42, "elapsed_time": "6:39:18", "remaining_time": "1:31:07", "throughput": 9378.56, "total_tokens": 224700560}
{"current_steps": 4050, "total_steps": 4968, "loss": 0.3346, "lr": 8.208243252332737e-07, "epoch": 1.6304347826086958, "percentage": 81.52, "elapsed_time": "6:39:52", "remaining_time": "1:30:38", "throughput": 9377.28, "total_tokens": 224988920}
{"current_steps": 4055, "total_steps": 4968, "loss": 0.3399, "lr": 8.121663185169032e-07, "epoch": 1.6324476650563606, "percentage": 81.62, "elapsed_time": "6:40:24", "remaining_time": "1:30:09", "throughput": 9375.29, "total_tokens": 225239008}
{"current_steps": 4060, "total_steps": 4968, "loss": 0.3128, "lr": 8.035501782029348e-07, "epoch": 1.634460547504026, "percentage": 81.72, "elapsed_time": "6:40:54", "remaining_time": "1:29:39", "throughput": 9375.04, "total_tokens": 225516448}
{"current_steps": 4065, "total_steps": 4968, "loss": 0.3354, "lr": 7.949759904282184e-07, "epoch": 1.6364734299516908, "percentage": 81.82, "elapsed_time": "6:41:24", "remaining_time": "1:29:10", "throughput": 9375.47, "total_tokens": 225807880}
{"current_steps": 4070, "total_steps": 4968, "loss": 0.3235, "lr": 7.864438409101971e-07, "epoch": 1.6384863123993558, "percentage": 81.92, "elapsed_time": "6:41:51", "remaining_time": "1:28:39", "throughput": 9376.28, "total_tokens": 226078456}
{"current_steps": 4075, "total_steps": 4968, "loss": 0.3356, "lr": 7.779538149460514e-07, "epoch": 1.640499194847021, "percentage": 82.02, "elapsed_time": "6:42:20", "remaining_time": "1:28:10", "throughput": 9376.07, "total_tokens": 226347576}
{"current_steps": 4080, "total_steps": 4968, "loss": 0.3289, "lr": 7.695059974118468e-07, "epoch": 1.642512077294686, "percentage": 82.13, "elapsed_time": "6:42:49", "remaining_time": "1:27:40", "throughput": 9376.67, "total_tokens": 226625696}
{"current_steps": 4085, "total_steps": 4968, "loss": 0.3237, "lr": 7.611004727616833e-07, "epoch": 1.644524959742351, "percentage": 82.23, "elapsed_time": "6:43:25", "remaining_time": "1:27:12", "throughput": 9374.74, "total_tokens": 226918856}
{"current_steps": 4090, "total_steps": 4968, "loss": 0.3288, "lr": 7.527373250268533e-07, "epoch": 1.646537842190016, "percentage": 82.33, "elapsed_time": "6:43:58", "remaining_time": "1:26:43", "throughput": 9373.37, "total_tokens": 227197600}
{"current_steps": 4095, "total_steps": 4968, "loss": 0.3396, "lr": 7.444166378150014e-07, "epoch": 1.6485507246376812, "percentage": 82.43, "elapsed_time": "6:44:29", "remaining_time": "1:26:13", "throughput": 9371.87, "total_tokens": 227453160}
{"current_steps": 4100, "total_steps": 4968, "loss": 0.3122, "lr": 7.361384943092881e-07, "epoch": 1.6505636070853462, "percentage": 82.53, "elapsed_time": "6:45:03", "remaining_time": "1:25:45", "throughput": 9370.54, "total_tokens": 227735952}
{"current_steps": 4105, "total_steps": 4968, "loss": 0.332, "lr": 7.279029772675572e-07, "epoch": 1.6525764895330113, "percentage": 82.63, "elapsed_time": "6:45:35", "remaining_time": "1:25:15", "throughput": 9370.21, "total_tokens": 228024336}
{"current_steps": 4110, "total_steps": 4968, "loss": 0.3354, "lr": 7.197101690215103e-07, "epoch": 1.6545893719806763, "percentage": 82.73, "elapsed_time": "6:46:10", "remaining_time": "1:24:47", "throughput": 9367.84, "total_tokens": 228295336}
{"current_steps": 4115, "total_steps": 4968, "loss": 0.3193, "lr": 7.115601514758808e-07, "epoch": 1.6566022544283414, "percentage": 82.83, "elapsed_time": "6:46:40", "remaining_time": "1:24:17", "throughput": 9367.37, "total_tokens": 228565976}
{"current_steps": 4120, "total_steps": 4968, "loss": 0.3357, "lr": 7.034530061076183e-07, "epoch": 1.6586151368760065, "percentage": 82.93, "elapsed_time": "6:47:10", "remaining_time": "1:23:48", "throughput": 9366.33, "total_tokens": 228823480}
{"current_steps": 4125, "total_steps": 4968, "loss": 0.3249, "lr": 6.953888139650744e-07, "epoch": 1.6606280193236715, "percentage": 83.03, "elapsed_time": "6:47:41", "remaining_time": "1:23:18", "throughput": 9366.39, "total_tokens": 229111408}
{"current_steps": 4130, "total_steps": 4968, "loss": 0.3366, "lr": 6.873676556671882e-07, "epoch": 1.6626409017713364, "percentage": 83.13, "elapsed_time": "6:48:11", "remaining_time": "1:22:49", "throughput": 9364.53, "total_tokens": 229354968}
{"current_steps": 4135, "total_steps": 4968, "loss": 0.2955, "lr": 6.79389611402686e-07, "epoch": 1.6646537842190017, "percentage": 83.23, "elapsed_time": "6:48:43", "remaining_time": "1:22:20", "throughput": 9363.49, "total_tokens": 229622848}
{"current_steps": 4140, "total_steps": 4968, "loss": 0.3385, "lr": 6.714547609292715e-07, "epoch": 1.6666666666666665, "percentage": 83.33, "elapsed_time": "6:49:13", "remaining_time": "1:21:50", "throughput": 9362.61, "total_tokens": 229881872}
{"current_steps": 4145, "total_steps": 4968, "loss": 0.3363, "lr": 6.63563183572839e-07, "epoch": 1.6686795491143318, "percentage": 83.43, "elapsed_time": "6:49:42", "remaining_time": "1:21:20", "throughput": 9362.28, "total_tokens": 230150944}
{"current_steps": 4150, "total_steps": 4968, "loss": 0.3226, "lr": 6.557149582266726e-07, "epoch": 1.6706924315619966, "percentage": 83.53, "elapsed_time": "6:50:09", "remaining_time": "1:20:50", "throughput": 9362.42, "total_tokens": 230404984}
{"current_steps": 4155, "total_steps": 4968, "loss": 0.3501, "lr": 6.479101633506596e-07, "epoch": 1.672705314009662, "percentage": 83.64, "elapsed_time": "6:50:38", "remaining_time": "1:20:20", "throughput": 9362.23, "total_tokens": 230671544}
{"current_steps": 4160, "total_steps": 4968, "loss": 0.3308, "lr": 6.401488769705083e-07, "epoch": 1.6747181964573268, "percentage": 83.74, "elapsed_time": "6:51:11", "remaining_time": "1:19:51", "throughput": 9361.98, "total_tokens": 230970448}
{"current_steps": 4165, "total_steps": 4968, "loss": 0.3248, "lr": 6.324311766769631e-07, "epoch": 1.676731078904992, "percentage": 83.84, "elapsed_time": "6:51:37", "remaining_time": "1:19:21", "throughput": 9363.5, "total_tokens": 231258312}
{"current_steps": 4170, "total_steps": 4968, "loss": 0.3268, "lr": 6.247571396250318e-07, "epoch": 1.678743961352657, "percentage": 83.94, "elapsed_time": "6:52:03", "remaining_time": "1:18:51", "throughput": 9364.88, "total_tokens": 231531768}
{"current_steps": 4175, "total_steps": 4968, "loss": 0.3205, "lr": 6.171268425332178e-07, "epoch": 1.6807568438003222, "percentage": 84.04, "elapsed_time": "6:52:32", "remaining_time": "1:18:21", "throughput": 9365.64, "total_tokens": 231824216}
{"current_steps": 4180, "total_steps": 4968, "loss": 0.3325, "lr": 6.095403616827467e-07, "epoch": 1.682769726247987, "percentage": 84.14, "elapsed_time": "6:53:03", "remaining_time": "1:17:52", "throughput": 9364.5, "total_tokens": 232086976}
{"current_steps": 4185, "total_steps": 4968, "loss": 0.3303, "lr": 6.01997772916807e-07, "epoch": 1.6847826086956523, "percentage": 84.24, "elapsed_time": "6:53:35", "remaining_time": "1:17:22", "throughput": 9363.42, "total_tokens": 232356456}
{"current_steps": 4190, "total_steps": 4968, "loss": 0.3449, "lr": 5.944991516397924e-07, "epoch": 1.6867954911433172, "percentage": 84.34, "elapsed_time": "6:54:11", "remaining_time": "1:16:54", "throughput": 9360.25, "total_tokens": 232613080}
{"current_steps": 4195, "total_steps": 4968, "loss": 0.3337, "lr": 5.870445728165447e-07, "epoch": 1.6888083735909822, "percentage": 84.44, "elapsed_time": "6:54:36", "remaining_time": "1:16:23", "throughput": 9362.74, "total_tokens": 232913968}
{"current_steps": 4200, "total_steps": 4968, "loss": 0.3187, "lr": 5.796341109716097e-07, "epoch": 1.6908212560386473, "percentage": 84.54, "elapsed_time": "6:55:04", "remaining_time": "1:15:54", "throughput": 9364.23, "total_tokens": 233215016}
{"current_steps": 4205, "total_steps": 4968, "loss": 0.3306, "lr": 5.722678401884868e-07, "epoch": 1.6928341384863124, "percentage": 84.64, "elapsed_time": "6:55:34", "remaining_time": "1:15:24", "throughput": 9365.22, "total_tokens": 233517040}
{"current_steps": 4210, "total_steps": 4968, "loss": 0.3318, "lr": 5.649458341088915e-07, "epoch": 1.6948470209339774, "percentage": 84.74, "elapsed_time": "6:55:59", "remaining_time": "1:14:53", "throughput": 9366.81, "total_tokens": 233795160}
{"current_steps": 4215, "total_steps": 4968, "loss": 0.299, "lr": 5.576681659320199e-07, "epoch": 1.6968599033816425, "percentage": 84.84, "elapsed_time": "6:56:30", "remaining_time": "1:14:24", "throughput": 9366.28, "total_tokens": 234065480}
{"current_steps": 4220, "total_steps": 4968, "loss": 0.3062, "lr": 5.504349084138122e-07, "epoch": 1.6988727858293076, "percentage": 84.94, "elapsed_time": "6:57:05", "remaining_time": "1:13:55", "throughput": 9364.18, "total_tokens": 234341016}
{"current_steps": 4225, "total_steps": 4968, "loss": 0.3353, "lr": 5.43246133866231e-07, "epoch": 1.7008856682769726, "percentage": 85.04, "elapsed_time": "6:57:34", "remaining_time": "1:13:26", "throughput": 9364.57, "total_tokens": 234623672}
{"current_steps": 4230, "total_steps": 4968, "loss": 0.348, "lr": 5.361019141565355e-07, "epoch": 1.7028985507246377, "percentage": 85.14, "elapsed_time": "6:58:02", "remaining_time": "1:12:56", "throughput": 9366.24, "total_tokens": 234924992}
{"current_steps": 4235, "total_steps": 4968, "loss": 0.319, "lr": 5.290023207065631e-07, "epoch": 1.7049114331723028, "percentage": 85.25, "elapsed_time": "6:58:33", "remaining_time": "1:12:26", "throughput": 9365.51, "total_tokens": 235200872}
{"current_steps": 4240, "total_steps": 4968, "loss": 0.3158, "lr": 5.219474244920164e-07, "epoch": 1.7069243156199678, "percentage": 85.35, "elapsed_time": "6:58:59", "remaining_time": "1:11:56", "throughput": 9367.93, "total_tokens": 235501128}
{"current_steps": 4245, "total_steps": 4968, "loss": 0.3312, "lr": 5.149372960417537e-07, "epoch": 1.708937198067633, "percentage": 85.45, "elapsed_time": "6:59:35", "remaining_time": "1:11:27", "throughput": 9364.81, "total_tokens": 235765184}
{"current_steps": 4250, "total_steps": 4968, "loss": 0.3168, "lr": 5.07972005437079e-07, "epoch": 1.710950080515298, "percentage": 85.55, "elapsed_time": "7:00:05", "remaining_time": "1:10:58", "throughput": 9364.49, "total_tokens": 236038880}
{"current_steps": 4255, "total_steps": 4968, "loss": 0.3157, "lr": 5.010516223110512e-07, "epoch": 1.7129629629629628, "percentage": 85.65, "elapsed_time": "7:00:35", "remaining_time": "1:10:28", "throughput": 9364.14, "total_tokens": 236312816}
{"current_steps": 4260, "total_steps": 4968, "loss": 0.3085, "lr": 4.941762158477798e-07, "epoch": 1.714975845410628, "percentage": 85.75, "elapsed_time": "7:01:10", "remaining_time": "1:09:59", "throughput": 9361.59, "total_tokens": 236568240}
{"current_steps": 4265, "total_steps": 4968, "loss": 0.3295, "lr": 4.87345854781735e-07, "epoch": 1.716988727858293, "percentage": 85.85, "elapsed_time": "7:01:38", "remaining_time": "1:09:29", "throughput": 9362.47, "total_tokens": 236857840}
{"current_steps": 4270, "total_steps": 4968, "loss": 0.3152, "lr": 4.805606073970642e-07, "epoch": 1.7190016103059582, "percentage": 85.95, "elapsed_time": "7:02:06", "remaining_time": "1:08:59", "throughput": 9362.31, "total_tokens": 237112384}
{"current_steps": 4275, "total_steps": 4968, "loss": 0.3575, "lr": 4.7382054152690314e-07, "epoch": 1.721014492753623, "percentage": 86.05, "elapsed_time": "7:02:32", "remaining_time": "1:08:29", "throughput": 9363.65, "total_tokens": 237393616}
{"current_steps": 4280, "total_steps": 4968, "loss": 0.3518, "lr": 4.671257245527028e-07, "epoch": 1.7230273752012883, "percentage": 86.15, "elapsed_time": "7:03:02", "remaining_time": "1:08:00", "throughput": 9364.58, "total_tokens": 237692784}
{"current_steps": 4285, "total_steps": 4968, "loss": 0.326, "lr": 4.604762234035548e-07, "epoch": 1.7250402576489532, "percentage": 86.25, "elapsed_time": "7:03:35", "remaining_time": "1:07:31", "throughput": 9363.8, "total_tokens": 237983312}
{"current_steps": 4290, "total_steps": 4968, "loss": 0.3273, "lr": 4.538721045555222e-07, "epoch": 1.7270531400966185, "percentage": 86.35, "elapsed_time": "7:04:06", "remaining_time": "1:07:01", "throughput": 9362.98, "total_tokens": 238255928}
{"current_steps": 4295, "total_steps": 4968, "loss": 0.3142, "lr": 4.473134340309704e-07, "epoch": 1.7290660225442833, "percentage": 86.45, "elapsed_time": "7:04:29", "remaining_time": "1:06:30", "throughput": 9365.17, "total_tokens": 238523560}
{"current_steps": 4300, "total_steps": 4968, "loss": 0.3126, "lr": 4.408002773979164e-07, "epoch": 1.7310789049919486, "percentage": 86.55, "elapsed_time": "7:04:58", "remaining_time": "1:06:01", "throughput": 9363.58, "total_tokens": 238761784}
{"current_steps": 4305, "total_steps": 4968, "loss": 0.3103, "lr": 4.343326997693637e-07, "epoch": 1.7330917874396135, "percentage": 86.65, "elapsed_time": "7:05:28", "remaining_time": "1:05:31", "throughput": 9363.93, "total_tokens": 239045784}
{"current_steps": 4310, "total_steps": 4968, "loss": 0.3187, "lr": 4.279107658026582e-07, "epoch": 1.7351046698872787, "percentage": 86.76, "elapsed_time": "7:06:04", "remaining_time": "1:05:02", "throughput": 9361.43, "total_tokens": 239322384}
{"current_steps": 4315, "total_steps": 4968, "loss": 0.3283, "lr": 4.2153453969883796e-07, "epoch": 1.7371175523349436, "percentage": 86.86, "elapsed_time": "7:06:36", "remaining_time": "1:04:33", "throughput": 9359.87, "total_tokens": 239575784}
{"current_steps": 4320, "total_steps": 4968, "loss": 0.3374, "lr": 4.1520408520199397e-07, "epoch": 1.7391304347826086, "percentage": 86.96, "elapsed_time": "7:07:05", "remaining_time": "1:04:03", "throughput": 9360.14, "total_tokens": 239857624}
{"current_steps": 4325, "total_steps": 4968, "loss": 0.3162, "lr": 4.089194655986306e-07, "epoch": 1.7411433172302737, "percentage": 87.06, "elapsed_time": "7:07:30", "remaining_time": "1:03:33", "throughput": 9362.21, "total_tokens": 240148600}
{"current_steps": 4330, "total_steps": 4968, "loss": 0.3197, "lr": 4.0268074371703324e-07, "epoch": 1.7431561996779388, "percentage": 87.16, "elapsed_time": "7:07:58", "remaining_time": "1:03:03", "throughput": 9362.39, "total_tokens": 240414752}
{"current_steps": 4335, "total_steps": 4968, "loss": 0.3329, "lr": 3.964879819266426e-07, "epoch": 1.7451690821256038, "percentage": 87.26, "elapsed_time": "7:08:29", "remaining_time": "1:02:34", "throughput": 9360.75, "total_tokens": 240660528}
{"current_steps": 4340, "total_steps": 4968, "loss": 0.3115, "lr": 3.9034124213742807e-07, "epoch": 1.747181964573269, "percentage": 87.36, "elapsed_time": "7:08:55", "remaining_time": "1:02:04", "throughput": 9362.46, "total_tokens": 240951984}
{"current_steps": 4345, "total_steps": 4968, "loss": 0.3121, "lr": 3.8424058579927147e-07, "epoch": 1.749194847020934, "percentage": 87.46, "elapsed_time": "7:09:26", "remaining_time": "1:01:34", "throughput": 9361.87, "total_tokens": 241224008}
{"current_steps": 4350, "total_steps": 4968, "loss": 0.3097, "lr": 3.7818607390134933e-07, "epoch": 1.751207729468599, "percentage": 87.56, "elapsed_time": "7:10:01", "remaining_time": "1:01:05", "throughput": 9360.36, "total_tokens": 241507016}
{"current_steps": 4355, "total_steps": 4968, "loss": 0.3327, "lr": 3.721777669715287e-07, "epoch": 1.753220611916264, "percentage": 87.66, "elapsed_time": "7:10:26", "remaining_time": "1:00:35", "throughput": 9362.15, "total_tokens": 241789352}
{"current_steps": 4360, "total_steps": 4968, "loss": 0.3182, "lr": 3.662157250757542e-07, "epoch": 1.7552334943639292, "percentage": 87.76, "elapsed_time": "7:10:55", "remaining_time": "1:00:05", "throughput": 9362.6, "total_tokens": 242073264}
{"current_steps": 4365, "total_steps": 4968, "loss": 0.3143, "lr": 3.6030000781745513e-07, "epoch": 1.7572463768115942, "percentage": 87.86, "elapsed_time": "7:11:24", "remaining_time": "0:59:35", "throughput": 9362.64, "total_tokens": 242347328}
{"current_steps": 4370, "total_steps": 4968, "loss": 0.3052, "lr": 3.5443067433694525e-07, "epoch": 1.7592592592592593, "percentage": 87.96, "elapsed_time": "7:11:58", "remaining_time": "0:59:06", "throughput": 9360.7, "total_tokens": 242613888}
{"current_steps": 4375, "total_steps": 4968, "loss": 0.3258, "lr": 3.486077833108342e-07, "epoch": 1.7612721417069244, "percentage": 88.06, "elapsed_time": "7:12:31", "remaining_time": "0:58:37", "throughput": 9358.88, "total_tokens": 242873240}
{"current_steps": 4380, "total_steps": 4968, "loss": 0.3296, "lr": 3.428313929514376e-07, "epoch": 1.7632850241545892, "percentage": 88.16, "elapsed_time": "7:13:02", "remaining_time": "0:58:08", "throughput": 9357.64, "total_tokens": 243138080}
{"current_steps": 4385, "total_steps": 4968, "loss": 0.3167, "lr": 3.371015610061973e-07, "epoch": 1.7652979066022545, "percentage": 88.26, "elapsed_time": "7:13:34", "remaining_time": "0:57:38", "throughput": 9357.72, "total_tokens": 243439728}
{"current_steps": 4390, "total_steps": 4968, "loss": 0.3228, "lr": 3.31418344757104e-07, "epoch": 1.7673107890499193, "percentage": 88.37, "elapsed_time": "7:14:03", "remaining_time": "0:57:09", "throughput": 9357.69, "total_tokens": 243711576}
{"current_steps": 4395, "total_steps": 4968, "loss": 0.3347, "lr": 3.2578180102012414e-07, "epoch": 1.7693236714975846, "percentage": 88.47, "elapsed_time": "7:14:31", "remaining_time": "0:56:39", "throughput": 9357.65, "total_tokens": 243969600}
{"current_steps": 4400, "total_steps": 4968, "loss": 0.3305, "lr": 3.2019198614463285e-07, "epoch": 1.7713365539452495, "percentage": 88.57, "elapsed_time": "7:15:05", "remaining_time": "0:56:09", "throughput": 9356.6, "total_tokens": 244257824}
{"current_steps": 4405, "total_steps": 4968, "loss": 0.3511, "lr": 3.146489560128496e-07, "epoch": 1.7733494363929148, "percentage": 88.67, "elapsed_time": "7:15:31", "remaining_time": "0:55:39", "throughput": 9357.87, "total_tokens": 244538784}
{"current_steps": 4410, "total_steps": 4968, "loss": 0.3185, "lr": 3.091527660392779e-07, "epoch": 1.7753623188405796, "percentage": 88.77, "elapsed_time": "7:15:57", "remaining_time": "0:55:09", "throughput": 9359.13, "total_tokens": 244812552}
{"current_steps": 4415, "total_steps": 4968, "loss": 0.3341, "lr": 3.037034711701553e-07, "epoch": 1.7773752012882449, "percentage": 88.87, "elapsed_time": "7:16:26", "remaining_time": "0:54:39", "throughput": 9360.11, "total_tokens": 245105832}
{"current_steps": 4420, "total_steps": 4968, "loss": 0.3258, "lr": 2.983011258829005e-07, "epoch": 1.7793880837359097, "percentage": 88.97, "elapsed_time": "7:17:03", "remaining_time": "0:54:11", "throughput": 9357.86, "total_tokens": 245393776}
{"current_steps": 4425, "total_steps": 4968, "loss": 0.3164, "lr": 2.929457841855715e-07, "epoch": 1.781400966183575, "percentage": 89.07, "elapsed_time": "7:17:36", "remaining_time": "0:53:42", "throughput": 9356.43, "total_tokens": 245668688}
{"current_steps": 4430, "total_steps": 4968, "loss": 0.3247, "lr": 2.876374996163239e-07, "epoch": 1.7834138486312399, "percentage": 89.17, "elapsed_time": "7:18:04", "remaining_time": "0:53:12", "throughput": 9355.91, "total_tokens": 245916384}
{"current_steps": 4435, "total_steps": 4968, "loss": 0.3312, "lr": 2.823763252428757e-07, "epoch": 1.7854267310789051, "percentage": 89.27, "elapsed_time": "7:18:39", "remaining_time": "0:52:43", "throughput": 9353.91, "total_tokens": 246190864}
{"current_steps": 4440, "total_steps": 4968, "loss": 0.3166, "lr": 2.7716231366197663e-07, "epoch": 1.78743961352657, "percentage": 89.37, "elapsed_time": "7:19:04", "remaining_time": "0:52:12", "throughput": 9355.42, "total_tokens": 246467664}
{"current_steps": 4445, "total_steps": 4968, "loss": 0.3282, "lr": 2.719955169988847e-07, "epoch": 1.789452495974235, "percentage": 89.47, "elapsed_time": "7:19:35", "remaining_time": "0:51:43", "throughput": 9353.69, "total_tokens": 246710208}
{"current_steps": 4450, "total_steps": 4968, "loss": 0.332, "lr": 2.668759869068421e-07, "epoch": 1.7914653784219001, "percentage": 89.57, "elapsed_time": "7:20:06", "remaining_time": "0:51:13", "throughput": 9353.07, "total_tokens": 246977928}
{"current_steps": 4455, "total_steps": 4968, "loss": 0.3244, "lr": 2.6180377456656023e-07, "epoch": 1.7934782608695652, "percentage": 89.67, "elapsed_time": "7:20:37", "remaining_time": "0:50:44", "throughput": 9353.12, "total_tokens": 247269376}
{"current_steps": 4460, "total_steps": 4968, "loss": 0.3083, "lr": 2.5677893068570767e-07, "epoch": 1.7954911433172303, "percentage": 89.77, "elapsed_time": "7:21:07", "remaining_time": "0:50:14", "throughput": 9352.53, "total_tokens": 247539224}
{"current_steps": 4465, "total_steps": 4968, "loss": 0.3287, "lr": 2.518015054984041e-07, "epoch": 1.7975040257648953, "percentage": 89.88, "elapsed_time": "7:21:33", "remaining_time": "0:49:44", "throughput": 9354.33, "total_tokens": 247826880}
{"current_steps": 4470, "total_steps": 4968, "loss": 0.3203, "lr": 2.468715487647155e-07, "epoch": 1.7995169082125604, "percentage": 89.98, "elapsed_time": "7:21:58", "remaining_time": "0:49:14", "throughput": 9355.77, "total_tokens": 248099328}
{"current_steps": 4475, "total_steps": 4968, "loss": 0.3274, "lr": 2.41989109770161e-07, "epoch": 1.8015297906602254, "percentage": 90.08, "elapsed_time": "7:22:24", "remaining_time": "0:48:44", "throughput": 9357.9, "total_tokens": 248403448}
{"current_steps": 4480, "total_steps": 4968, "loss": 0.3112, "lr": 2.371542373252156e-07, "epoch": 1.8035426731078905, "percentage": 90.18, "elapsed_time": "7:22:48", "remaining_time": "0:48:14", "throughput": 9358.99, "total_tokens": 248654000}
{"current_steps": 4485, "total_steps": 4968, "loss": 0.3243, "lr": 2.3236697976482703e-07, "epoch": 1.8055555555555556, "percentage": 90.28, "elapsed_time": "7:23:21", "remaining_time": "0:47:44", "throughput": 9358.42, "total_tokens": 248948704}
{"current_steps": 4490, "total_steps": 4968, "loss": 0.3363, "lr": 2.276273849479277e-07, "epoch": 1.8075684380032206, "percentage": 90.38, "elapsed_time": "7:23:49", "remaining_time": "0:47:14", "throughput": 9358.57, "total_tokens": 249209968}
{"current_steps": 4495, "total_steps": 4968, "loss": 0.3168, "lr": 2.2293550025695776e-07, "epoch": 1.8095813204508857, "percentage": 90.48, "elapsed_time": "7:24:19", "remaining_time": "0:46:45", "throughput": 9358.24, "total_tokens": 249486336}
{"current_steps": 4500, "total_steps": 4968, "loss": 0.354, "lr": 2.1829137259739453e-07, "epoch": 1.8115942028985508, "percentage": 90.58, "elapsed_time": "7:24:51", "remaining_time": "0:46:15", "throughput": 9358.32, "total_tokens": 249789232}
{"current_steps": 4505, "total_steps": 4968, "loss": 0.3329, "lr": 2.136950483972794e-07, "epoch": 1.8136070853462156, "percentage": 90.68, "elapsed_time": "7:25:26", "remaining_time": "0:45:46", "throughput": 9356.51, "total_tokens": 250062680}
{"current_steps": 4510, "total_steps": 4968, "loss": 0.3381, "lr": 2.0914657360675606e-07, "epoch": 1.815619967793881, "percentage": 90.78, "elapsed_time": "7:25:58", "remaining_time": "0:45:17", "throughput": 9354.85, "total_tokens": 250323856}
{"current_steps": 4515, "total_steps": 4968, "loss": 0.3317, "lr": 2.046459936976103e-07, "epoch": 1.8176328502415457, "percentage": 90.88, "elapsed_time": "7:26:23", "remaining_time": "0:44:47", "throughput": 9357.84, "total_tokens": 250632152}
{"current_steps": 4520, "total_steps": 4968, "loss": 0.3124, "lr": 2.0019335366281533e-07, "epoch": 1.819645732689211, "percentage": 90.98, "elapsed_time": "7:26:53", "remaining_time": "0:44:17", "throughput": 9357.97, "total_tokens": 250923760}
{"current_steps": 4525, "total_steps": 4968, "loss": 0.3024, "lr": 1.9578869801608168e-07, "epoch": 1.8216586151368759, "percentage": 91.08, "elapsed_time": "7:27:25", "remaining_time": "0:43:48", "throughput": 9357.95, "total_tokens": 251214576}
{"current_steps": 4530, "total_steps": 4968, "loss": 0.3285, "lr": 1.9143207079141523e-07, "epoch": 1.8236714975845412, "percentage": 91.18, "elapsed_time": "7:28:01", "remaining_time": "0:43:19", "throughput": 9355.83, "total_tokens": 251498880}
{"current_steps": 4535, "total_steps": 4968, "loss": 0.3196, "lr": 1.8712351554267206e-07, "epoch": 1.825684380032206, "percentage": 91.28, "elapsed_time": "7:28:27", "remaining_time": "0:42:49", "throughput": 9356.3, "total_tokens": 251758600}
{"current_steps": 4540, "total_steps": 4968, "loss": 0.3165, "lr": 1.8286307534312542e-07, "epoch": 1.8276972624798713, "percentage": 91.38, "elapsed_time": "7:28:58", "remaining_time": "0:42:19", "throughput": 9356.61, "total_tokens": 252052760}
{"current_steps": 4545, "total_steps": 4968, "loss": 0.3352, "lr": 1.7865079278503727e-07, "epoch": 1.8297101449275361, "percentage": 91.49, "elapsed_time": "7:29:32", "remaining_time": "0:41:50", "throughput": 9354.74, "total_tokens": 252319768}
{"current_steps": 4550, "total_steps": 4968, "loss": 0.3314, "lr": 1.74486709979228e-07, "epoch": 1.8317230273752014, "percentage": 91.59, "elapsed_time": "7:30:05", "remaining_time": "0:41:20", "throughput": 9354.17, "total_tokens": 252613568}
{"current_steps": 4555, "total_steps": 4968, "loss": 0.3308, "lr": 1.7037086855465902e-07, "epoch": 1.8337359098228663, "percentage": 91.69, "elapsed_time": "7:30:36", "remaining_time": "0:40:51", "throughput": 9353.85, "total_tokens": 252891568}
{"current_steps": 4560, "total_steps": 4968, "loss": 0.3132, "lr": 1.6630330965801578e-07, "epoch": 1.8357487922705316, "percentage": 91.79, "elapsed_time": "7:31:01", "remaining_time": "0:40:21", "throughput": 9355.77, "total_tokens": 253180104}
{"current_steps": 4565, "total_steps": 4968, "loss": 0.3253, "lr": 1.6228407395329548e-07, "epoch": 1.8377616747181964, "percentage": 91.89, "elapsed_time": "7:31:31", "remaining_time": "0:39:51", "throughput": 9356.12, "total_tokens": 253471976}
{"current_steps": 4570, "total_steps": 4968, "loss": 0.3179, "lr": 1.5831320162140172e-07, "epoch": 1.8397745571658615, "percentage": 91.99, "elapsed_time": "7:31:53", "remaining_time": "0:39:21", "throughput": 9359.4, "total_tokens": 253767792}
{"current_steps": 4575, "total_steps": 4968, "loss": 0.3261, "lr": 1.54390732359741e-07, "epoch": 1.8417874396135265, "percentage": 92.09, "elapsed_time": "7:32:26", "remaining_time": "0:38:51", "throughput": 9358.77, "total_tokens": 254059848}
{"current_steps": 4580, "total_steps": 4968, "loss": 0.3079, "lr": 1.5051670538182793e-07, "epoch": 1.8438003220611916, "percentage": 92.19, "elapsed_time": "7:32:44", "remaining_time": "0:38:21", "throughput": 9362.7, "total_tokens": 254334200}
{"current_steps": 4585, "total_steps": 4968, "loss": 0.3138, "lr": 1.4669115941689182e-07, "epoch": 1.8458132045088567, "percentage": 92.29, "elapsed_time": "7:33:13", "remaining_time": "0:37:51", "throughput": 9362.5, "total_tokens": 254598752}
{"current_steps": 4590, "total_steps": 4968, "loss": 0.2999, "lr": 1.429141327094913e-07, "epoch": 1.8478260869565217, "percentage": 92.39, "elapsed_time": "7:33:39", "remaining_time": "0:37:21", "throughput": 9364.16, "total_tokens": 254888928}
{"current_steps": 4595, "total_steps": 4968, "loss": 0.336, "lr": 1.391856630191285e-07, "epoch": 1.8498389694041868, "percentage": 92.49, "elapsed_time": "7:34:11", "remaining_time": "0:36:52", "throughput": 9363.59, "total_tokens": 255168480}
{"current_steps": 4600, "total_steps": 4968, "loss": 0.3083, "lr": 1.3550578761987675e-07, "epoch": 1.8518518518518519, "percentage": 92.59, "elapsed_time": "7:34:36", "remaining_time": "0:36:22", "throughput": 9364.61, "total_tokens": 255438072}
{"current_steps": 4605, "total_steps": 4968, "loss": 0.3302, "lr": 1.3187454330000127e-07, "epoch": 1.853864734299517, "percentage": 92.69, "elapsed_time": "7:35:07", "remaining_time": "0:35:52", "throughput": 9364.89, "total_tokens": 255733000}
{"current_steps": 4610, "total_steps": 4968, "loss": 0.3355, "lr": 1.282919663615978e-07, "epoch": 1.855877616747182, "percentage": 92.79, "elapsed_time": "7:35:42", "remaining_time": "0:35:23", "throughput": 9362.28, "total_tokens": 255990800}
{"current_steps": 4615, "total_steps": 4968, "loss": 0.3115, "lr": 1.2475809262022632e-07, "epoch": 1.857890499194847, "percentage": 92.89, "elapsed_time": "7:36:09", "remaining_time": "0:34:53", "throughput": 9363.49, "total_tokens": 256269840}
{"current_steps": 4620, "total_steps": 4968, "loss": 0.3056, "lr": 1.2127295740455348e-07, "epoch": 1.8599033816425121, "percentage": 93.0, "elapsed_time": "7:36:40", "remaining_time": "0:34:23", "throughput": 9363.04, "total_tokens": 256551224}
{"current_steps": 4625, "total_steps": 4968, "loss": 0.3297, "lr": 1.1783659555600013e-07, "epoch": 1.8619162640901772, "percentage": 93.1, "elapsed_time": "7:37:03", "remaining_time": "0:33:53", "throughput": 9364.85, "total_tokens": 256821232}
{"current_steps": 4630, "total_steps": 4968, "loss": 0.3261, "lr": 1.1444904142838997e-07, "epoch": 1.863929146537842, "percentage": 93.2, "elapsed_time": "7:37:29", "remaining_time": "0:33:23", "throughput": 9366.23, "total_tokens": 257102072}
{"current_steps": 4635, "total_steps": 4968, "loss": 0.3321, "lr": 1.1111032888761253e-07, "epoch": 1.8659420289855073, "percentage": 93.3, "elapsed_time": "7:37:57", "remaining_time": "0:32:54", "throughput": 9366.66, "total_tokens": 257376384}
{"current_steps": 4640, "total_steps": 4968, "loss": 0.3354, "lr": 1.0782049131127736e-07, "epoch": 1.8679549114331722, "percentage": 93.4, "elapsed_time": "7:38:29", "remaining_time": "0:32:24", "throughput": 9366.1, "total_tokens": 257658656}
{"current_steps": 4645, "total_steps": 4968, "loss": 0.3342, "lr": 1.0457956158838545e-07, "epoch": 1.8699677938808374, "percentage": 93.5, "elapsed_time": "7:38:59", "remaining_time": "0:31:54", "throughput": 9365.88, "total_tokens": 257927704}
{"current_steps": 4650, "total_steps": 4968, "loss": 0.3161, "lr": 1.013875721189983e-07, "epoch": 1.8719806763285023, "percentage": 93.6, "elapsed_time": "7:39:23", "remaining_time": "0:31:24", "throughput": 9367.15, "total_tokens": 258190216}
{"current_steps": 4655, "total_steps": 4968, "loss": 0.3312, "lr": 9.824455481391381e-08, "epoch": 1.8739935587761676, "percentage": 93.7, "elapsed_time": "7:39:45", "remaining_time": "0:30:54", "throughput": 9369.26, "total_tokens": 258452600}
{"current_steps": 4660, "total_steps": 4968, "loss": 0.31, "lr": 9.515054109434819e-08, "epoch": 1.8760064412238324, "percentage": 93.8, "elapsed_time": "7:40:06", "remaining_time": "0:30:24", "throughput": 9371.85, "total_tokens": 258721912}
{"current_steps": 4665, "total_steps": 4968, "loss": 0.3236, "lr": 9.210556189162056e-08, "epoch": 1.8780193236714977, "percentage": 93.9, "elapsed_time": "7:40:32", "remaining_time": "0:29:54", "throughput": 9371.99, "total_tokens": 258969488}
{"current_steps": 4670, "total_steps": 4968, "loss": 0.3096, "lr": 8.910964764684671e-08, "epoch": 1.8800322061191626, "percentage": 94.0, "elapsed_time": "7:41:08", "remaining_time": "0:29:25", "throughput": 9370.25, "total_tokens": 259258480}
{"current_steps": 4675, "total_steps": 4968, "loss": 0.3162, "lr": 8.616282831063083e-08, "epoch": 1.8820450885668278, "percentage": 94.1, "elapsed_time": "7:41:35", "remaining_time": "0:28:55", "throughput": 9371.43, "total_tokens": 259548968}
{"current_steps": 4680, "total_steps": 4968, "loss": 0.2966, "lr": 8.326513334276864e-08, "epoch": 1.8840579710144927, "percentage": 94.2, "elapsed_time": "7:42:08", "remaining_time": "0:28:26", "throughput": 9370.28, "total_tokens": 259821040}
{"current_steps": 4685, "total_steps": 4968, "loss": 0.3256, "lr": 8.041659171195149e-08, "epoch": 1.886070853462158, "percentage": 94.3, "elapsed_time": "7:42:31", "remaining_time": "0:27:56", "throughput": 9371.2, "total_tokens": 260064200}
{"current_steps": 4690, "total_steps": 4968, "loss": 0.3395, "lr": 7.76172318954782e-08, "epoch": 1.8880837359098228, "percentage": 94.4, "elapsed_time": "7:42:59", "remaining_time": "0:27:26", "throughput": 9371.88, "total_tokens": 260343640}
{"current_steps": 4695, "total_steps": 4968, "loss": 0.3217, "lr": 7.486708187896986e-08, "epoch": 1.8900966183574879, "percentage": 94.5, "elapsed_time": "7:43:27", "remaining_time": "0:26:56", "throughput": 9371.78, "total_tokens": 260608136}
{"current_steps": 4700, "total_steps": 4968, "loss": 0.3216, "lr": 7.216616915608876e-08, "epoch": 1.892109500805153, "percentage": 94.61, "elapsed_time": "7:44:02", "remaining_time": "0:26:27", "throughput": 9371.1, "total_tokens": 260913592}
{"current_steps": 4705, "total_steps": 4968, "loss": 0.3356, "lr": 6.951452072826547e-08, "epoch": 1.894122383252818, "percentage": 94.71, "elapsed_time": "7:44:22", "remaining_time": "0:25:57", "throughput": 9375.26, "total_tokens": 261219328}
{"current_steps": 4710, "total_steps": 4968, "loss": 0.3169, "lr": 6.691216310442783e-08, "epoch": 1.896135265700483, "percentage": 94.81, "elapsed_time": "7:44:53", "remaining_time": "0:25:27", "throughput": 9374.49, "total_tokens": 261484544}
{"current_steps": 4715, "total_steps": 4968, "loss": 0.336, "lr": 6.435912230073504e-08, "epoch": 1.8981481481481481, "percentage": 94.91, "elapsed_time": "7:45:28", "remaining_time": "0:24:58", "throughput": 9372.05, "total_tokens": 261745496}
{"current_steps": 4720, "total_steps": 4968, "loss": 0.315, "lr": 6.185542384032018e-08, "epoch": 1.9001610305958132, "percentage": 95.01, "elapsed_time": "7:45:58", "remaining_time": "0:24:29", "throughput": 9371.82, "total_tokens": 262023384}
{"current_steps": 4725, "total_steps": 4968, "loss": 0.3182, "lr": 5.9401092753033075e-08, "epoch": 1.9021739130434783, "percentage": 95.11, "elapsed_time": "7:46:23", "remaining_time": "0:23:59", "throughput": 9372.34, "total_tokens": 262274224}
{"current_steps": 4730, "total_steps": 4968, "loss": 0.3039, "lr": 5.6996153575189504e-08, "epoch": 1.9041867954911433, "percentage": 95.21, "elapsed_time": "7:46:52", "remaining_time": "0:23:29", "throughput": 9371.56, "total_tokens": 262520656}
{"current_steps": 4735, "total_steps": 4968, "loss": 0.3147, "lr": 5.4640630349329094e-08, "epoch": 1.9061996779388084, "percentage": 95.31, "elapsed_time": "7:47:17", "remaining_time": "0:22:59", "throughput": 9372.72, "total_tokens": 262787184}
{"current_steps": 4740, "total_steps": 4968, "loss": 0.3426, "lr": 5.233454662396942e-08, "epoch": 1.9082125603864735, "percentage": 95.41, "elapsed_time": "7:47:43", "remaining_time": "0:22:29", "throughput": 9374.77, "total_tokens": 263085176}
{"current_steps": 4745, "total_steps": 4968, "loss": 0.3203, "lr": 5.0077925453377865e-08, "epoch": 1.9102254428341385, "percentage": 95.51, "elapsed_time": "7:48:05", "remaining_time": "0:21:59", "throughput": 9375.83, "total_tokens": 263326152}
{"current_steps": 4750, "total_steps": 4968, "loss": 0.3336, "lr": 4.7870789397333475e-08, "epoch": 1.9122383252818036, "percentage": 95.61, "elapsed_time": "7:48:34", "remaining_time": "0:21:30", "throughput": 9376.26, "total_tokens": 263611048}
{"current_steps": 4755, "total_steps": 4968, "loss": 0.3316, "lr": 4.571316052090824e-08, "epoch": 1.9142512077294684, "percentage": 95.71, "elapsed_time": "7:49:03", "remaining_time": "0:21:00", "throughput": 9376.51, "total_tokens": 263884712}
{"current_steps": 4760, "total_steps": 4968, "loss": 0.3297, "lr": 4.360506039424173e-08, "epoch": 1.9162640901771337, "percentage": 95.81, "elapsed_time": "7:49:34", "remaining_time": "0:20:31", "throughput": 9376.71, "total_tokens": 264180136}
{"current_steps": 4765, "total_steps": 4968, "loss": 0.3101, "lr": 4.1546510092327906e-08, "epoch": 1.9182769726247986, "percentage": 95.91, "elapsed_time": "7:50:06", "remaining_time": "0:20:01", "throughput": 9376.26, "total_tokens": 264471000}
{"current_steps": 4770, "total_steps": 4968, "loss": 0.3268, "lr": 3.953753019480255e-08, "epoch": 1.9202898550724639, "percentage": 96.01, "elapsed_time": "7:50:28", "remaining_time": "0:19:31", "throughput": 9378.56, "total_tokens": 264745232}
{"current_steps": 4775, "total_steps": 4968, "loss": 0.3308, "lr": 3.757814078574007e-08, "epoch": 1.9223027375201287, "percentage": 96.12, "elapsed_time": "7:51:02", "remaining_time": "0:19:02", "throughput": 9376.47, "total_tokens": 264997920}
{"current_steps": 4780, "total_steps": 4968, "loss": 0.3295, "lr": 3.566836145345032e-08, "epoch": 1.924315619967794, "percentage": 96.22, "elapsed_time": "7:51:34", "remaining_time": "0:18:32", "throughput": 9375.32, "total_tokens": 265267704}
{"current_steps": 4785, "total_steps": 4968, "loss": 0.3288, "lr": 3.3808211290284886e-08, "epoch": 1.9263285024154588, "percentage": 96.32, "elapsed_time": "7:52:00", "remaining_time": "0:18:03", "throughput": 9375.64, "total_tokens": 265527112}
{"current_steps": 4790, "total_steps": 4968, "loss": 0.3264, "lr": 3.199770889244447e-08, "epoch": 1.9283413848631241, "percentage": 96.42, "elapsed_time": "7:52:31", "remaining_time": "0:17:33", "throughput": 9374.84, "total_tokens": 265786448}
{"current_steps": 4795, "total_steps": 4968, "loss": 0.3347, "lr": 3.023687235979233e-08, "epoch": 1.930354267310789, "percentage": 96.52, "elapsed_time": "7:53:07", "remaining_time": "0:17:04", "throughput": 9373.18, "total_tokens": 266082088}
{"current_steps": 4800, "total_steps": 4968, "loss": 0.3256, "lr": 2.8525719295676712e-08, "epoch": 1.9323671497584543, "percentage": 96.62, "elapsed_time": "7:53:31", "remaining_time": "0:16:34", "throughput": 9374.77, "total_tokens": 266349272}
{"current_steps": 4805, "total_steps": 4968, "loss": 0.3252, "lr": 2.6864266806751472e-08, "epoch": 1.934380032206119, "percentage": 96.72, "elapsed_time": "7:53:54", "remaining_time": "0:16:04", "throughput": 9377.55, "total_tokens": 266649048}
{"current_steps": 4810, "total_steps": 4968, "loss": 0.3257, "lr": 2.525253150280682e-08, "epoch": 1.9363929146537844, "percentage": 96.82, "elapsed_time": "7:54:24", "remaining_time": "0:15:34", "throughput": 9377.61, "total_tokens": 266924600}
{"current_steps": 4815, "total_steps": 4968, "loss": 0.3108, "lr": 2.3690529496602777e-08, "epoch": 1.9384057971014492, "percentage": 96.92, "elapsed_time": "7:54:55", "remaining_time": "0:15:05", "throughput": 9378.4, "total_tokens": 267238432}
{"current_steps": 4820, "total_steps": 4968, "loss": 0.3388, "lr": 2.2178276403708175e-08, "epoch": 1.9404186795491143, "percentage": 97.02, "elapsed_time": "7:55:26", "remaining_time": "0:14:35", "throughput": 9378.76, "total_tokens": 267542320}
{"current_steps": 4825, "total_steps": 4968, "loss": 0.3038, "lr": 2.0715787342343586e-08, "epoch": 1.9424315619967794, "percentage": 97.12, "elapsed_time": "7:55:57", "remaining_time": "0:14:06", "throughput": 9378.61, "total_tokens": 267830064}
{"current_steps": 4830, "total_steps": 4968, "loss": 0.3134, "lr": 1.9303076933233077e-08, "epoch": 1.9444444444444444, "percentage": 97.22, "elapsed_time": "7:56:27", "remaining_time": "0:13:36", "throughput": 9378.06, "total_tokens": 268093680}
{"current_steps": 4835, "total_steps": 4968, "loss": 0.3522, "lr": 1.7940159299453806e-08, "epoch": 1.9464573268921095, "percentage": 97.32, "elapsed_time": "7:57:03", "remaining_time": "0:13:07", "throughput": 9376.19, "total_tokens": 268380248}
{"current_steps": 4840, "total_steps": 4968, "loss": 0.3252, "lr": 1.662704806629889e-08, "epoch": 1.9484702093397746, "percentage": 97.42, "elapsed_time": "7:57:34", "remaining_time": "0:12:37", "throughput": 9376.69, "total_tokens": 268685488}
{"current_steps": 4845, "total_steps": 4968, "loss": 0.3122, "lr": 1.5363756361138072e-08, "epoch": 1.9504830917874396, "percentage": 97.52, "elapsed_time": "7:58:01", "remaining_time": "0:12:08", "throughput": 9377.92, "total_tokens": 268971544}
{"current_steps": 4850, "total_steps": 4968, "loss": 0.2881, "lr": 1.4150296813288388e-08, "epoch": 1.9524959742351047, "percentage": 97.62, "elapsed_time": "7:58:29", "remaining_time": "0:11:38", "throughput": 9378.51, "total_tokens": 269253440}
{"current_steps": 4855, "total_steps": 4968, "loss": 0.3183, "lr": 1.2986681553887048e-08, "epoch": 1.9545088566827697, "percentage": 97.73, "elapsed_time": "7:58:54", "remaining_time": "0:11:08", "throughput": 9380.29, "total_tokens": 269536808}
{"current_steps": 4860, "total_steps": 4968, "loss": 0.3394, "lr": 1.1872922215770966e-08, "epoch": 1.9565217391304348, "percentage": 97.83, "elapsed_time": "7:59:18", "remaining_time": "0:10:39", "throughput": 9382.01, "total_tokens": 269814056}
{"current_steps": 4865, "total_steps": 4968, "loss": 0.3203, "lr": 1.0809029933359083e-08, "epoch": 1.9585346215780999, "percentage": 97.93, "elapsed_time": "7:59:54", "remaining_time": "0:10:09", "throughput": 9380.02, "total_tokens": 270093208}
{"current_steps": 4870, "total_steps": 4968, "loss": 0.3311, "lr": 9.795015342543013e-09, "epoch": 1.960547504025765, "percentage": 98.03, "elapsed_time": "8:00:25", "remaining_time": "0:09:40", "throughput": 9379.52, "total_tokens": 270367160}
{"current_steps": 4875, "total_steps": 4968, "loss": 0.3031, "lr": 8.830888580578233e-09, "epoch": 1.96256038647343, "percentage": 98.13, "elapsed_time": "8:00:55", "remaining_time": "0:09:10", "throughput": 9378.79, "total_tokens": 270625544}
{"current_steps": 4880, "total_steps": 4968, "loss": 0.3299, "lr": 7.916659285985284e-09, "epoch": 1.9645732689210949, "percentage": 98.23, "elapsed_time": "8:01:25", "remaining_time": "0:08:40", "throughput": 9378.55, "total_tokens": 270901192}
{"current_steps": 4885, "total_steps": 4968, "loss": 0.322, "lr": 7.052336598451504e-09, "epoch": 1.9665861513687601, "percentage": 98.33, "elapsed_time": "8:01:55", "remaining_time": "0:08:11", "throughput": 9377.81, "total_tokens": 271164784}
{"current_steps": 4890, "total_steps": 4968, "loss": 0.3202, "lr": 6.237929158741107e-09, "epoch": 1.968599033816425, "percentage": 98.43, "elapsed_time": "8:02:27", "remaining_time": "0:07:41", "throughput": 9376.75, "total_tokens": 271434272}
{"current_steps": 4895, "total_steps": 4968, "loss": 0.3268, "lr": 5.473445108606923e-09, "epoch": 1.9706119162640903, "percentage": 98.53, "elapsed_time": "8:02:59", "remaining_time": "0:07:12", "throughput": 9375.61, "total_tokens": 271697952}
{"current_steps": 4900, "total_steps": 4968, "loss": 0.3295, "lr": 4.758892090711009e-09, "epoch": 1.9726247987117551, "percentage": 98.63, "elapsed_time": "8:03:21", "remaining_time": "0:06:42", "throughput": 9377.77, "total_tokens": 271967552}
{"current_steps": 4905, "total_steps": 4968, "loss": 0.3407, "lr": 4.094277248548051e-09, "epoch": 1.9746376811594204, "percentage": 98.73, "elapsed_time": "8:03:44", "remaining_time": "0:06:12", "throughput": 9379.45, "total_tokens": 272234544}
{"current_steps": 4910, "total_steps": 4968, "loss": 0.3148, "lr": 3.4796072263715284e-09, "epoch": 1.9766505636070852, "percentage": 98.83, "elapsed_time": "8:04:10", "remaining_time": "0:05:43", "throughput": 9380.16, "total_tokens": 272495800}
{"current_steps": 4915, "total_steps": 4968, "loss": 0.3233, "lr": 2.9148881691298812e-09, "epoch": 1.9786634460547505, "percentage": 98.93, "elapsed_time": "8:04:41", "remaining_time": "0:05:13", "throughput": 9379.59, "total_tokens": 272773144}
{"current_steps": 4920, "total_steps": 4968, "loss": 0.3301, "lr": 2.400125722404889e-09, "epoch": 1.9806763285024154, "percentage": 99.03, "elapsed_time": "8:05:04", "remaining_time": "0:04:43", "throughput": 9381.7, "total_tokens": 273044976}
{"current_steps": 4925, "total_steps": 4968, "loss": 0.3379, "lr": 1.9353250323539407e-09, "epoch": 1.9826892109500807, "percentage": 99.13, "elapsed_time": "8:05:39", "remaining_time": "0:04:14", "throughput": 9379.57, "total_tokens": 273314184}
{"current_steps": 4930, "total_steps": 4968, "loss": 0.3203, "lr": 1.5204907456595197e-09, "epoch": 1.9847020933977455, "percentage": 99.24, "elapsed_time": "8:06:07", "remaining_time": "0:03:44", "throughput": 9381.36, "total_tokens": 273634520}
{"current_steps": 4935, "total_steps": 4968, "loss": 0.3264, "lr": 1.1556270094820189e-09, "epoch": 1.9867149758454108, "percentage": 99.34, "elapsed_time": "8:06:41", "remaining_time": "0:03:15", "throughput": 9379.74, "total_tokens": 273902336}
{"current_steps": 4940, "total_steps": 4968, "loss": 0.3399, "lr": 8.407374714192174e-10, "epoch": 1.9887278582930756, "percentage": 99.44, "elapsed_time": "8:07:19", "remaining_time": "0:02:45", "throughput": 9377.29, "total_tokens": 274183168}
{"current_steps": 4945, "total_steps": 4968, "loss": 0.3314, "lr": 5.758252794690888e-10, "epoch": 1.9907407407407407, "percentage": 99.54, "elapsed_time": "8:07:45", "remaining_time": "0:02:16", "throughput": 9378.23, "total_tokens": 274462280}
{"current_steps": 4950, "total_steps": 4968, "loss": 0.3105, "lr": 3.608930819981593e-10, "epoch": 1.9927536231884058, "percentage": 99.64, "elapsed_time": "8:08:14", "remaining_time": "0:01:46", "throughput": 9377.47, "total_tokens": 274708976}
{"current_steps": 4955, "total_steps": 4968, "loss": 0.3266, "lr": 1.9594302771652752e-10, "epoch": 1.9947665056360708, "percentage": 99.74, "elapsed_time": "8:08:43", "remaining_time": "0:01:16", "throughput": 9378.28, "total_tokens": 274999376}
{"current_steps": 4960, "total_steps": 4968, "loss": 0.301, "lr": 8.097676565399504e-11, "epoch": 1.996779388083736, "percentage": 99.84, "elapsed_time": "8:09:14", "remaining_time": "0:00:47", "throughput": 9376.35, "total_tokens": 275242304}
{"current_steps": 4965, "total_steps": 4968, "loss": 0.3388, "lr": 1.599544514674367e-11, "epoch": 1.998792270531401, "percentage": 99.94, "elapsed_time": "8:09:48", "remaining_time": "0:00:17", "throughput": 9375.16, "total_tokens": 275524496}
{"current_steps": 4968, "total_steps": 4968, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "8:11:57", "remaining_time": "0:00:00", "throughput": 9339.88, "total_tokens": 275688256}