Terminal-data_querying / trainer_log.jsonl
cuong1692001's picture
Upload folder using huggingface_hub
db187cf verified
Raw
History Blame Contribute Delete
296 kB
{"current_steps": 5, "total_steps": 11920, "loss": 0.7471, "lr": 9.999997221520572e-06, "epoch": 0.0020973154362416107, "percentage": 0.04, "elapsed_time": "0:01:02", "remaining_time": "1 day, 17:23:22", "throughput": 4609.18, "total_tokens": 288200}
{"current_steps": 10, "total_steps": 11920, "loss": 0.5871, "lr": 9.999985933953186e-06, "epoch": 0.0041946308724832215, "percentage": 0.08, "elapsed_time": "0:02:15", "remaining_time": "1 day, 20:41:30", "throughput": 4560.08, "total_tokens": 616016}
{"current_steps": 15, "total_steps": 11920, "loss": 0.575, "lr": 9.999965963662464e-06, "epoch": 0.006291946308724832, "percentage": 0.13, "elapsed_time": "0:03:12", "remaining_time": "1 day, 18:24:48", "throughput": 4758.81, "total_tokens": 915520}
{"current_steps": 20, "total_steps": 11920, "loss": 0.5182, "lr": 9.999937310683086e-06, "epoch": 0.008389261744966443, "percentage": 0.17, "elapsed_time": "0:04:17", "remaining_time": "1 day, 18:38:02", "throughput": 4823.46, "total_tokens": 1244232}
{"current_steps": 25, "total_steps": 11920, "loss": 0.5611, "lr": 9.99989997506481e-06, "epoch": 0.010486577181208054, "percentage": 0.21, "elapsed_time": "0:05:54", "remaining_time": "1 day, 22:54:45", "throughput": 4455.01, "total_tokens": 1581304}
{"current_steps": 30, "total_steps": 11920, "loss": 0.5153, "lr": 9.99985395687247e-06, "epoch": 0.012583892617449664, "percentage": 0.25, "elapsed_time": "0:07:02", "remaining_time": "1 day, 22:33:01", "throughput": 4567.22, "total_tokens": 1931152}
{"current_steps": 35, "total_steps": 11920, "loss": 0.5071, "lr": 9.999799256185978e-06, "epoch": 0.014681208053691275, "percentage": 0.29, "elapsed_time": "0:07:49", "remaining_time": "1 day, 20:15:36", "throughput": 4792.12, "total_tokens": 2248600}
{"current_steps": 40, "total_steps": 11920, "loss": 0.4721, "lr": 9.999735873100326e-06, "epoch": 0.016778523489932886, "percentage": 0.34, "elapsed_time": "0:08:36", "remaining_time": "1 day, 18:34:53", "throughput": 4908.64, "total_tokens": 2533544}
{"current_steps": 45, "total_steps": 11920, "loss": 0.4564, "lr": 9.999663807725581e-06, "epoch": 0.018875838926174497, "percentage": 0.38, "elapsed_time": "0:10:00", "remaining_time": "1 day, 19:59:20", "throughput": 4833.42, "total_tokens": 2900552}
{"current_steps": 50, "total_steps": 11920, "loss": 0.493, "lr": 9.99958306018689e-06, "epoch": 0.02097315436241611, "percentage": 0.42, "elapsed_time": "0:11:04", "remaining_time": "1 day, 19:48:49", "throughput": 4891.81, "total_tokens": 3250136}
{"current_steps": 55, "total_steps": 11920, "loss": 0.4934, "lr": 9.999493630624473e-06, "epoch": 0.02307046979865772, "percentage": 0.46, "elapsed_time": "0:12:14", "remaining_time": "1 day, 20:02:06", "throughput": 4844.26, "total_tokens": 3559784}
{"current_steps": 60, "total_steps": 11920, "loss": 0.4775, "lr": 9.99939551919363e-06, "epoch": 0.025167785234899327, "percentage": 0.5, "elapsed_time": "0:13:16", "remaining_time": "1 day, 19:43:39", "throughput": 4882.25, "total_tokens": 3888160}
{"current_steps": 65, "total_steps": 11920, "loss": 0.4657, "lr": 9.999288726064735e-06, "epoch": 0.02726510067114094, "percentage": 0.55, "elapsed_time": "0:14:28", "remaining_time": "1 day, 20:00:06", "throughput": 4828.53, "total_tokens": 4193736}
{"current_steps": 70, "total_steps": 11920, "loss": 0.4786, "lr": 9.999173251423242e-06, "epoch": 0.02936241610738255, "percentage": 0.59, "elapsed_time": "0:15:45", "remaining_time": "1 day, 20:27:10", "throughput": 4784.56, "total_tokens": 4522976}
{"current_steps": 75, "total_steps": 11920, "loss": 0.4955, "lr": 9.999049095469676e-06, "epoch": 0.031459731543624164, "percentage": 0.63, "elapsed_time": "0:17:04", "remaining_time": "1 day, 20:56:52", "throughput": 4748.54, "total_tokens": 4865168}
{"current_steps": 80, "total_steps": 11920, "loss": 0.4612, "lr": 9.99891625841964e-06, "epoch": 0.03355704697986577, "percentage": 0.67, "elapsed_time": "0:18:20", "remaining_time": "1 day, 21:13:48", "throughput": 4700.57, "total_tokens": 5171520}
{"current_steps": 85, "total_steps": 11920, "loss": 0.4503, "lr": 9.998774740503815e-06, "epoch": 0.03565436241610738, "percentage": 0.71, "elapsed_time": "0:19:58", "remaining_time": "1 day, 22:20:40", "throughput": 4606.16, "total_tokens": 5519392}
{"current_steps": 90, "total_steps": 11920, "loss": 0.4701, "lr": 9.99862454196795e-06, "epoch": 0.037751677852348994, "percentage": 0.76, "elapsed_time": "0:21:10", "remaining_time": "1 day, 22:22:43", "throughput": 4597.78, "total_tokens": 5840184}
{"current_steps": 95, "total_steps": 11920, "loss": 0.4543, "lr": 9.998465663072875e-06, "epoch": 0.0398489932885906, "percentage": 0.8, "elapsed_time": "0:22:19", "remaining_time": "1 day, 22:19:51", "throughput": 4598.12, "total_tokens": 6161368}
{"current_steps": 100, "total_steps": 11920, "loss": 0.4586, "lr": 9.998298104094491e-06, "epoch": 0.04194630872483222, "percentage": 0.84, "elapsed_time": "0:23:22", "remaining_time": "1 day, 22:02:02", "throughput": 4605.37, "total_tokens": 6456952}
{"current_steps": 105, "total_steps": 11920, "loss": 0.4328, "lr": 9.998121865323769e-06, "epoch": 0.044043624161073824, "percentage": 0.88, "elapsed_time": "0:24:51", "remaining_time": "1 day, 22:36:38", "throughput": 4583.99, "total_tokens": 6835744}
{"current_steps": 110, "total_steps": 11920, "loss": 0.4593, "lr": 9.99793694706676e-06, "epoch": 0.04614093959731544, "percentage": 0.92, "elapsed_time": "0:25:58", "remaining_time": "1 day, 22:28:15", "throughput": 4597.06, "total_tokens": 7163184}
{"current_steps": 115, "total_steps": 11920, "loss": 0.4447, "lr": 9.997743349644584e-06, "epoch": 0.04823825503355705, "percentage": 0.96, "elapsed_time": "0:27:00", "remaining_time": "1 day, 22:12:08", "throughput": 4586.69, "total_tokens": 7431872}
{"current_steps": 120, "total_steps": 11920, "loss": 0.449, "lr": 9.99754107339343e-06, "epoch": 0.050335570469798654, "percentage": 1.01, "elapsed_time": "0:27:56", "remaining_time": "1 day, 21:47:01", "throughput": 4587.41, "total_tokens": 7689200}
{"current_steps": 125, "total_steps": 11920, "loss": 0.4488, "lr": 9.997330118664563e-06, "epoch": 0.05243288590604027, "percentage": 1.05, "elapsed_time": "0:28:41", "remaining_time": "1 day, 21:07:35", "throughput": 4628.18, "total_tokens": 7968144}
{"current_steps": 130, "total_steps": 11920, "loss": 0.4226, "lr": 9.997110485824316e-06, "epoch": 0.05453020134228188, "percentage": 1.09, "elapsed_time": "0:29:39", "remaining_time": "1 day, 20:49:52", "throughput": 4660.87, "total_tokens": 8294288}
{"current_steps": 135, "total_steps": 11920, "loss": 0.4444, "lr": 9.996882175254088e-06, "epoch": 0.05662751677852349, "percentage": 1.13, "elapsed_time": "0:30:34", "remaining_time": "1 day, 20:28:36", "throughput": 4685.61, "total_tokens": 8594232}
{"current_steps": 140, "total_steps": 11920, "loss": 0.4257, "lr": 9.996645187350357e-06, "epoch": 0.0587248322147651, "percentage": 1.17, "elapsed_time": "0:31:24", "remaining_time": "1 day, 20:03:10", "throughput": 4711.17, "total_tokens": 8879496}
{"current_steps": 145, "total_steps": 11920, "loss": 0.4581, "lr": 9.996399522524664e-06, "epoch": 0.060822147651006714, "percentage": 1.22, "elapsed_time": "0:32:17", "remaining_time": "1 day, 19:42:27", "throughput": 4729.81, "total_tokens": 9164568}
{"current_steps": 150, "total_steps": 11920, "loss": 0.4013, "lr": 9.996145181203616e-06, "epoch": 0.06291946308724833, "percentage": 1.26, "elapsed_time": "0:33:16", "remaining_time": "1 day, 19:30:58", "throughput": 4727.48, "total_tokens": 9438400}
{"current_steps": 155, "total_steps": 11920, "loss": 0.4356, "lr": 9.995882163828889e-06, "epoch": 0.06501677852348993, "percentage": 1.3, "elapsed_time": "0:34:21", "remaining_time": "1 day, 19:27:44", "throughput": 4729.22, "total_tokens": 9748632}
{"current_steps": 160, "total_steps": 11920, "loss": 0.4713, "lr": 9.995610470857227e-06, "epoch": 0.06711409395973154, "percentage": 1.34, "elapsed_time": "0:35:04", "remaining_time": "1 day, 18:58:32", "throughput": 4765.73, "total_tokens": 10031520}
{"current_steps": 165, "total_steps": 11920, "loss": 0.4282, "lr": 9.995330102760437e-06, "epoch": 0.06921140939597316, "percentage": 1.38, "elapsed_time": "0:36:23", "remaining_time": "1 day, 19:12:04", "throughput": 4744.01, "total_tokens": 10356360}
{"current_steps": 170, "total_steps": 11920, "loss": 0.4393, "lr": 9.995041060025395e-06, "epoch": 0.07130872483221476, "percentage": 1.43, "elapsed_time": "0:37:34", "remaining_time": "1 day, 19:17:25", "throughput": 4750.32, "total_tokens": 10710960}
{"current_steps": 175, "total_steps": 11920, "loss": 0.4445, "lr": 9.994743343154033e-06, "epoch": 0.07340604026845637, "percentage": 1.47, "elapsed_time": "0:39:04", "remaining_time": "1 day, 19:42:32", "throughput": 4716.88, "total_tokens": 11058912}
{"current_steps": 180, "total_steps": 11920, "loss": 0.4513, "lr": 9.994436952663357e-06, "epoch": 0.07550335570469799, "percentage": 1.51, "elapsed_time": "0:40:07", "remaining_time": "1 day, 19:36:30", "throughput": 4753.17, "total_tokens": 11440896}
{"current_steps": 185, "total_steps": 11920, "loss": 0.4216, "lr": 9.994121889085426e-06, "epoch": 0.0776006711409396, "percentage": 1.55, "elapsed_time": "0:40:54", "remaining_time": "1 day, 19:15:09", "throughput": 4787.1, "total_tokens": 11751000}
{"current_steps": 190, "total_steps": 11920, "loss": 0.4361, "lr": 9.993798152967364e-06, "epoch": 0.0796979865771812, "percentage": 1.59, "elapsed_time": "0:41:58", "remaining_time": "1 day, 19:10:53", "throughput": 4779.38, "total_tokens": 12034496}
{"current_steps": 195, "total_steps": 11920, "loss": 0.4175, "lr": 9.993465744871354e-06, "epoch": 0.08179530201342282, "percentage": 1.64, "elapsed_time": "0:43:00", "remaining_time": "1 day, 19:06:08", "throughput": 4777.8, "total_tokens": 12329704}
{"current_steps": 200, "total_steps": 11920, "loss": 0.4287, "lr": 9.993124665374641e-06, "epoch": 0.08389261744966443, "percentage": 1.68, "elapsed_time": "0:43:50", "remaining_time": "1 day, 18:49:33", "throughput": 4791.5, "total_tokens": 12606200}
{"current_steps": 205, "total_steps": 11920, "loss": 0.4541, "lr": 9.992774915069523e-06, "epoch": 0.08598993288590603, "percentage": 1.72, "elapsed_time": "0:44:46", "remaining_time": "1 day, 18:38:28", "throughput": 4812.44, "total_tokens": 12927360}
{"current_steps": 210, "total_steps": 11920, "loss": 0.388, "lr": 9.992416494563363e-06, "epoch": 0.08808724832214765, "percentage": 1.76, "elapsed_time": "0:46:01", "remaining_time": "1 day, 18:46:15", "throughput": 4797.88, "total_tokens": 13248384}
{"current_steps": 215, "total_steps": 11920, "loss": 0.4301, "lr": 9.992049404478574e-06, "epoch": 0.09018456375838926, "percentage": 1.8, "elapsed_time": "0:46:58", "remaining_time": "1 day, 18:37:38", "throughput": 4820.39, "total_tokens": 13587536}
{"current_steps": 220, "total_steps": 11920, "loss": 0.4161, "lr": 9.991673645452623e-06, "epoch": 0.09228187919463088, "percentage": 1.85, "elapsed_time": "0:47:41", "remaining_time": "1 day, 18:16:11", "throughput": 4847.92, "total_tokens": 13871576}
{"current_steps": 225, "total_steps": 11920, "loss": 0.3956, "lr": 9.991289218138042e-06, "epoch": 0.09437919463087248, "percentage": 1.89, "elapsed_time": "0:48:57", "remaining_time": "1 day, 18:24:30", "throughput": 4835.74, "total_tokens": 14203648}
{"current_steps": 230, "total_steps": 11920, "loss": 0.4403, "lr": 9.990896123202401e-06, "epoch": 0.0964765100671141, "percentage": 1.93, "elapsed_time": "0:49:51", "remaining_time": "1 day, 18:14:06", "throughput": 4854.24, "total_tokens": 14521480}
{"current_steps": 235, "total_steps": 11920, "loss": 0.4422, "lr": 9.990494361328332e-06, "epoch": 0.09857382550335571, "percentage": 1.97, "elapsed_time": "0:50:47", "remaining_time": "1 day, 18:05:25", "throughput": 4866.71, "total_tokens": 14830664}
{"current_steps": 240, "total_steps": 11920, "loss": 0.4136, "lr": 9.990083933213513e-06, "epoch": 0.10067114093959731, "percentage": 2.01, "elapsed_time": "0:52:00", "remaining_time": "1 day, 18:11:22", "throughput": 4862.22, "total_tokens": 15174376}
{"current_steps": 245, "total_steps": 11920, "loss": 0.4305, "lr": 9.989664839570672e-06, "epoch": 0.10276845637583892, "percentage": 2.06, "elapsed_time": "0:53:19", "remaining_time": "1 day, 18:21:02", "throughput": 4844.28, "total_tokens": 15498912}
{"current_steps": 250, "total_steps": 11920, "loss": 0.3983, "lr": 9.98923708112759e-06, "epoch": 0.10486577181208054, "percentage": 2.1, "elapsed_time": "0:54:03", "remaining_time": "1 day, 18:03:45", "throughput": 4858.82, "total_tokens": 15761600}
{"current_steps": 255, "total_steps": 11920, "loss": 0.4088, "lr": 9.988800658627085e-06, "epoch": 0.10696308724832215, "percentage": 2.14, "elapsed_time": "0:55:16", "remaining_time": "1 day, 18:08:13", "throughput": 4857.12, "total_tokens": 16106520}
{"current_steps": 260, "total_steps": 11920, "loss": 0.4126, "lr": 9.988355572827031e-06, "epoch": 0.10906040268456375, "percentage": 2.18, "elapsed_time": "0:56:22", "remaining_time": "1 day, 18:08:32", "throughput": 4853.31, "total_tokens": 16418520}
{"current_steps": 265, "total_steps": 11920, "loss": 0.4167, "lr": 9.987901824500342e-06, "epoch": 0.11115771812080537, "percentage": 2.22, "elapsed_time": "0:57:42", "remaining_time": "1 day, 18:18:06", "throughput": 4839.39, "total_tokens": 16756536}
{"current_steps": 270, "total_steps": 11920, "loss": 0.4134, "lr": 9.98743941443497e-06, "epoch": 0.11325503355704698, "percentage": 2.27, "elapsed_time": "0:58:38", "remaining_time": "1 day, 18:10:09", "throughput": 4843.61, "total_tokens": 17041472}
{"current_steps": 275, "total_steps": 11920, "loss": 0.4024, "lr": 9.986968343433913e-06, "epoch": 0.11535234899328858, "percentage": 2.31, "elapsed_time": "0:59:53", "remaining_time": "1 day, 18:15:53", "throughput": 4839.74, "total_tokens": 17389880}
{"current_steps": 280, "total_steps": 11920, "loss": 0.4089, "lr": 9.986488612315215e-06, "epoch": 0.1174496644295302, "percentage": 2.35, "elapsed_time": "1:01:15", "remaining_time": "1 day, 18:26:21", "throughput": 4829.63, "total_tokens": 17749608}
{"current_steps": 285, "total_steps": 11920, "loss": 0.4202, "lr": 9.986000221911948e-06, "epoch": 0.11954697986577181, "percentage": 2.39, "elapsed_time": "1:02:24", "remaining_time": "1 day, 18:27:29", "throughput": 4830.65, "total_tokens": 18086176}
{"current_steps": 290, "total_steps": 11920, "loss": 0.399, "lr": 9.985503173072229e-06, "epoch": 0.12164429530201343, "percentage": 2.43, "elapsed_time": "1:03:41", "remaining_time": "1 day, 18:34:32", "throughput": 4834.46, "total_tokens": 18476920}
{"current_steps": 295, "total_steps": 11920, "loss": 0.4119, "lr": 9.984997466659203e-06, "epoch": 0.12374161073825503, "percentage": 2.47, "elapsed_time": "1:04:42", "remaining_time": "1 day, 18:29:44", "throughput": 4843.27, "total_tokens": 18802424}
{"current_steps": 300, "total_steps": 11920, "loss": 0.4397, "lr": 9.984483103551061e-06, "epoch": 0.12583892617449666, "percentage": 2.52, "elapsed_time": "1:05:41", "remaining_time": "1 day, 18:24:35", "throughput": 4843.19, "total_tokens": 19090432}
{"current_steps": 305, "total_steps": 11920, "loss": 0.4125, "lr": 9.983960084641014e-06, "epoch": 0.12793624161073824, "percentage": 2.56, "elapsed_time": "1:06:57", "remaining_time": "1 day, 18:29:55", "throughput": 4842.79, "total_tokens": 19456048}
{"current_steps": 310, "total_steps": 11920, "loss": 0.3847, "lr": 9.983428410837315e-06, "epoch": 0.13003355704697986, "percentage": 2.6, "elapsed_time": "1:08:13", "remaining_time": "1 day, 18:34:56", "throughput": 4831.51, "total_tokens": 19776288}
{"current_steps": 315, "total_steps": 11920, "loss": 0.4423, "lr": 9.982888083063238e-06, "epoch": 0.13213087248322147, "percentage": 2.64, "elapsed_time": "1:09:07", "remaining_time": "1 day, 18:26:23", "throughput": 4847.94, "total_tokens": 20104752}
{"current_steps": 320, "total_steps": 11920, "loss": 0.4033, "lr": 9.982339102257093e-06, "epoch": 0.1342281879194631, "percentage": 2.68, "elapsed_time": "1:10:19", "remaining_time": "1 day, 18:29:02", "throughput": 4837.37, "total_tokens": 20409344}
{"current_steps": 325, "total_steps": 11920, "loss": 0.4389, "lr": 9.981781469372208e-06, "epoch": 0.1363255033557047, "percentage": 2.73, "elapsed_time": "1:11:42", "remaining_time": "1 day, 18:38:17", "throughput": 4821.01, "total_tokens": 20742120}
{"current_steps": 330, "total_steps": 11920, "loss": 0.447, "lr": 9.981215185376943e-06, "epoch": 0.13842281879194632, "percentage": 2.77, "elapsed_time": "1:12:45", "remaining_time": "1 day, 18:35:13", "throughput": 4822.29, "total_tokens": 21050632}
{"current_steps": 335, "total_steps": 11920, "loss": 0.3745, "lr": 9.980640251254677e-06, "epoch": 0.14052013422818793, "percentage": 2.81, "elapsed_time": "1:13:47", "remaining_time": "1 day, 18:31:48", "throughput": 4825.16, "total_tokens": 21362888}
{"current_steps": 340, "total_steps": 11920, "loss": 0.379, "lr": 9.980056668003812e-06, "epoch": 0.14261744966442952, "percentage": 2.85, "elapsed_time": "1:15:01", "remaining_time": "1 day, 18:35:08", "throughput": 4825.4, "total_tokens": 21720448}
{"current_steps": 345, "total_steps": 11920, "loss": 0.4402, "lr": 9.979464436637771e-06, "epoch": 0.14471476510067113, "percentage": 2.89, "elapsed_time": "1:16:11", "remaining_time": "1 day, 18:36:15", "throughput": 4821.01, "total_tokens": 22039080}
{"current_steps": 350, "total_steps": 11920, "loss": 0.4061, "lr": 9.978863558184989e-06, "epoch": 0.14681208053691275, "percentage": 2.94, "elapsed_time": "1:17:08", "remaining_time": "1 day, 18:29:48", "throughput": 4822.0, "total_tokens": 22316224}
{"current_steps": 355, "total_steps": 11920, "loss": 0.4245, "lr": 9.978254033688926e-06, "epoch": 0.14890939597315436, "percentage": 2.98, "elapsed_time": "1:18:17", "remaining_time": "1 day, 18:30:26", "throughput": 4820.48, "total_tokens": 22643288}
{"current_steps": 360, "total_steps": 11920, "loss": 0.3901, "lr": 9.977635864208046e-06, "epoch": 0.15100671140939598, "percentage": 3.02, "elapsed_time": "1:19:31", "remaining_time": "1 day, 18:33:23", "throughput": 4814.51, "total_tokens": 22970216}
{"current_steps": 365, "total_steps": 11920, "loss": 0.4005, "lr": 9.977009050815837e-06, "epoch": 0.1531040268456376, "percentage": 3.06, "elapsed_time": "1:20:35", "remaining_time": "1 day, 18:31:33", "throughput": 4819.46, "total_tokens": 23306504}
{"current_steps": 370, "total_steps": 11920, "loss": 0.3851, "lr": 9.976373594600787e-06, "epoch": 0.1552013422818792, "percentage": 3.1, "elapsed_time": "1:21:55", "remaining_time": "1 day, 18:37:29", "throughput": 4805.16, "total_tokens": 23620704}
{"current_steps": 375, "total_steps": 11920, "loss": 0.4172, "lr": 9.9757294966664e-06, "epoch": 0.1572986577181208, "percentage": 3.15, "elapsed_time": "1:22:52", "remaining_time": "1 day, 18:31:22", "throughput": 4813.14, "total_tokens": 23932680}
{"current_steps": 380, "total_steps": 11920, "loss": 0.4133, "lr": 9.975076758131181e-06, "epoch": 0.1593959731543624, "percentage": 3.19, "elapsed_time": "1:23:44", "remaining_time": "1 day, 18:23:19", "throughput": 4824.01, "total_tokens": 24240280}
{"current_steps": 385, "total_steps": 11920, "loss": 0.3951, "lr": 9.974415380128646e-06, "epoch": 0.16149328859060402, "percentage": 3.23, "elapsed_time": "1:25:04", "remaining_time": "1 day, 18:28:41", "throughput": 4819.32, "total_tokens": 24597800}
{"current_steps": 390, "total_steps": 11920, "loss": 0.411, "lr": 9.973745363807309e-06, "epoch": 0.16359060402684564, "percentage": 3.27, "elapsed_time": "1:25:54", "remaining_time": "1 day, 18:19:41", "throughput": 4825.62, "total_tokens": 24872584}
{"current_steps": 395, "total_steps": 11920, "loss": 0.3823, "lr": 9.973066710330686e-06, "epoch": 0.16568791946308725, "percentage": 3.31, "elapsed_time": "1:27:02", "remaining_time": "1 day, 18:19:43", "throughput": 4825.14, "total_tokens": 25200200}
{"current_steps": 400, "total_steps": 11920, "loss": 0.3946, "lr": 9.972379420877294e-06, "epoch": 0.16778523489932887, "percentage": 3.36, "elapsed_time": "1:28:16", "remaining_time": "1 day, 18:22:14", "throughput": 4819.9, "total_tokens": 25527856}
{"current_steps": 405, "total_steps": 11920, "loss": 0.419, "lr": 9.971683496640643e-06, "epoch": 0.16988255033557048, "percentage": 3.4, "elapsed_time": "1:29:04", "remaining_time": "1 day, 18:12:33", "throughput": 4831.46, "total_tokens": 25821352}
{"current_steps": 410, "total_steps": 11920, "loss": 0.3872, "lr": 9.970978938829243e-06, "epoch": 0.17197986577181207, "percentage": 3.44, "elapsed_time": "1:29:48", "remaining_time": "1 day, 18:01:24", "throughput": 4846.2, "total_tokens": 26115880}
{"current_steps": 415, "total_steps": 11920, "loss": 0.3989, "lr": 9.970265748666592e-06, "epoch": 0.17407718120805368, "percentage": 3.48, "elapsed_time": "1:31:00", "remaining_time": "1 day, 18:02:51", "throughput": 4839.12, "total_tokens": 26422344}
{"current_steps": 420, "total_steps": 11920, "loss": 0.4193, "lr": 9.969543927391179e-06, "epoch": 0.1761744966442953, "percentage": 3.52, "elapsed_time": "1:32:05", "remaining_time": "1 day, 18:01:24", "throughput": 4836.4, "total_tokens": 26722008}
{"current_steps": 425, "total_steps": 11920, "loss": 0.3821, "lr": 9.968813476256483e-06, "epoch": 0.1782718120805369, "percentage": 3.57, "elapsed_time": "1:33:05", "remaining_time": "1 day, 17:57:40", "throughput": 4845.75, "total_tokens": 27064032}
{"current_steps": 430, "total_steps": 11920, "loss": 0.4029, "lr": 9.968074396530969e-06, "epoch": 0.18036912751677853, "percentage": 3.61, "elapsed_time": "1:34:02", "remaining_time": "1 day, 17:52:59", "throughput": 4852.52, "total_tokens": 27381472}
{"current_steps": 435, "total_steps": 11920, "loss": 0.4058, "lr": 9.967326689498085e-06, "epoch": 0.18246644295302014, "percentage": 3.65, "elapsed_time": "1:34:57", "remaining_time": "1 day, 17:47:20", "throughput": 4854.48, "total_tokens": 27660808}
{"current_steps": 440, "total_steps": 11920, "loss": 0.3946, "lr": 9.966570356456264e-06, "epoch": 0.18456375838926176, "percentage": 3.69, "elapsed_time": "1:36:16", "remaining_time": "1 day, 17:51:43", "throughput": 4850.44, "total_tokens": 28016568}
{"current_steps": 445, "total_steps": 11920, "loss": 0.4038, "lr": 9.96580539871891e-06, "epoch": 0.18666107382550334, "percentage": 3.73, "elapsed_time": "1:37:34", "remaining_time": "1 day, 17:56:07", "throughput": 4844.26, "total_tokens": 28360832}
{"current_steps": 450, "total_steps": 11920, "loss": 0.4324, "lr": 9.965031817614417e-06, "epoch": 0.18875838926174496, "percentage": 3.78, "elapsed_time": "1:38:33", "remaining_time": "1 day, 17:52:17", "throughput": 4851.79, "total_tokens": 28692872}
{"current_steps": 455, "total_steps": 11920, "loss": 0.4109, "lr": 9.964249614486143e-06, "epoch": 0.19085570469798657, "percentage": 3.82, "elapsed_time": "1:39:25", "remaining_time": "1 day, 17:45:17", "throughput": 4859.88, "total_tokens": 28991616}
{"current_steps": 460, "total_steps": 11920, "loss": 0.4019, "lr": 9.963458790692423e-06, "epoch": 0.1929530201342282, "percentage": 3.86, "elapsed_time": "1:40:25", "remaining_time": "1 day, 17:41:55", "throughput": 4861.97, "total_tokens": 29296152}
{"current_steps": 465, "total_steps": 11920, "loss": 0.4107, "lr": 9.96265934760656e-06, "epoch": 0.1950503355704698, "percentage": 3.9, "elapsed_time": "1:41:52", "remaining_time": "1 day, 17:49:45", "throughput": 4853.37, "total_tokens": 29667792}
{"current_steps": 470, "total_steps": 11920, "loss": 0.3904, "lr": 9.961851286616828e-06, "epoch": 0.19714765100671142, "percentage": 3.94, "elapsed_time": "1:43:17", "remaining_time": "1 day, 17:56:22", "throughput": 4840.83, "total_tokens": 30001168}
{"current_steps": 475, "total_steps": 11920, "loss": 0.4205, "lr": 9.961034609126468e-06, "epoch": 0.19924496644295303, "percentage": 3.98, "elapsed_time": "1:44:18", "remaining_time": "1 day, 17:53:11", "throughput": 4841.99, "total_tokens": 30302400}
{"current_steps": 480, "total_steps": 11920, "loss": 0.3999, "lr": 9.960209316553674e-06, "epoch": 0.20134228187919462, "percentage": 4.03, "elapsed_time": "1:45:21", "remaining_time": "1 day, 17:51:09", "throughput": 4844.94, "total_tokens": 30628688}
{"current_steps": 485, "total_steps": 11920, "loss": 0.3868, "lr": 9.959375410331616e-06, "epoch": 0.20343959731543623, "percentage": 4.07, "elapsed_time": "1:46:23", "remaining_time": "1 day, 17:48:34", "throughput": 4843.24, "total_tokens": 30918544}
{"current_steps": 490, "total_steps": 11920, "loss": 0.3903, "lr": 9.958532891908406e-06, "epoch": 0.20553691275167785, "percentage": 4.11, "elapsed_time": "1:47:19", "remaining_time": "1 day, 17:43:40", "throughput": 4846.17, "total_tokens": 31208784}
{"current_steps": 495, "total_steps": 11920, "loss": 0.3854, "lr": 9.957681762747124e-06, "epoch": 0.20763422818791946, "percentage": 4.15, "elapsed_time": "1:48:39", "remaining_time": "1 day, 17:47:48", "throughput": 4838.71, "total_tokens": 31544448}
{"current_steps": 500, "total_steps": 11920, "loss": 0.3951, "lr": 9.956822024325795e-06, "epoch": 0.20973154362416108, "percentage": 4.19, "elapsed_time": "1:49:49", "remaining_time": "1 day, 17:48:31", "throughput": 4835.76, "total_tokens": 31866856}
{"current_steps": 505, "total_steps": 11920, "loss": 0.4319, "lr": 9.955953678137397e-06, "epoch": 0.2118288590604027, "percentage": 4.24, "elapsed_time": "1:50:51", "remaining_time": "1 day, 17:45:52", "throughput": 4838.94, "total_tokens": 32186768}
{"current_steps": 510, "total_steps": 11920, "loss": 0.4049, "lr": 9.95507672568986e-06, "epoch": 0.2139261744966443, "percentage": 4.28, "elapsed_time": "1:51:43", "remaining_time": "1 day, 17:39:42", "throughput": 4845.48, "total_tokens": 32483376}
{"current_steps": 515, "total_steps": 11920, "loss": 0.3868, "lr": 9.954191168506052e-06, "epoch": 0.2160234899328859, "percentage": 4.32, "elapsed_time": "1:52:54", "remaining_time": "1 day, 17:40:34", "throughput": 4849.32, "total_tokens": 32853728}
{"current_steps": 520, "total_steps": 11920, "loss": 0.3751, "lr": 9.953297008123788e-06, "epoch": 0.2181208053691275, "percentage": 4.36, "elapsed_time": "1:54:02", "remaining_time": "1 day, 17:40:03", "throughput": 4852.21, "total_tokens": 33200048}
{"current_steps": 525, "total_steps": 11920, "loss": 0.3965, "lr": 9.952394246095823e-06, "epoch": 0.22021812080536912, "percentage": 4.4, "elapsed_time": "1:55:03", "remaining_time": "1 day, 17:37:12", "throughput": 4853.37, "total_tokens": 33503800}
{"current_steps": 530, "total_steps": 11920, "loss": 0.3981, "lr": 9.951482883989844e-06, "epoch": 0.22231543624161074, "percentage": 4.45, "elapsed_time": "1:56:01", "remaining_time": "1 day, 17:33:15", "throughput": 4858.32, "total_tokens": 33818800}
{"current_steps": 535, "total_steps": 11920, "loss": 0.3947, "lr": 9.95056292338848e-06, "epoch": 0.22441275167785235, "percentage": 4.49, "elapsed_time": "1:57:09", "remaining_time": "1 day, 17:33:16", "throughput": 4855.66, "total_tokens": 34134200}
{"current_steps": 540, "total_steps": 11920, "loss": 0.4098, "lr": 9.949634365889288e-06, "epoch": 0.22651006711409397, "percentage": 4.53, "elapsed_time": "1:58:34", "remaining_time": "1 day, 17:38:50", "throughput": 4849.36, "total_tokens": 34500600}
{"current_steps": 545, "total_steps": 11920, "loss": 0.4009, "lr": 9.948697213104754e-06, "epoch": 0.22860738255033558, "percentage": 4.57, "elapsed_time": "1:59:52", "remaining_time": "1 day, 17:42:03", "throughput": 4847.87, "total_tokens": 34869456}
{"current_steps": 550, "total_steps": 11920, "loss": 0.3939, "lr": 9.947751466662288e-06, "epoch": 0.23070469798657717, "percentage": 4.61, "elapsed_time": "2:00:37", "remaining_time": "1 day, 17:33:40", "throughput": 4853.48, "total_tokens": 35127360}
{"current_steps": 555, "total_steps": 11920, "loss": 0.3689, "lr": 9.946797128204228e-06, "epoch": 0.23280201342281878, "percentage": 4.66, "elapsed_time": "2:01:46", "remaining_time": "1 day, 17:33:41", "throughput": 4850.61, "total_tokens": 35441680}
{"current_steps": 560, "total_steps": 11920, "loss": 0.3871, "lr": 9.945834199387829e-06, "epoch": 0.2348993288590604, "percentage": 4.7, "elapsed_time": "2:02:54", "remaining_time": "1 day, 17:33:10", "throughput": 4849.79, "total_tokens": 35763312}
{"current_steps": 565, "total_steps": 11920, "loss": 0.3892, "lr": 9.944862681885266e-06, "epoch": 0.236996644295302, "percentage": 4.74, "elapsed_time": "2:03:52", "remaining_time": "1 day, 17:29:32", "throughput": 4856.34, "total_tokens": 36094648}
{"current_steps": 570, "total_steps": 11920, "loss": 0.3989, "lr": 9.943882577383624e-06, "epoch": 0.23909395973154363, "percentage": 4.78, "elapsed_time": "2:04:58", "remaining_time": "1 day, 17:28:24", "throughput": 4850.94, "total_tokens": 36372936}
{"current_steps": 575, "total_steps": 11920, "loss": 0.4182, "lr": 9.942893887584907e-06, "epoch": 0.24119127516778524, "percentage": 4.82, "elapsed_time": "2:06:10", "remaining_time": "1 day, 17:29:29", "throughput": 4850.86, "total_tokens": 36723520}
{"current_steps": 580, "total_steps": 11920, "loss": 0.4202, "lr": 9.94189661420602e-06, "epoch": 0.24328859060402686, "percentage": 4.87, "elapsed_time": "2:07:30", "remaining_time": "1 day, 17:32:52", "throughput": 4845.58, "total_tokens": 37069160}
{"current_steps": 585, "total_steps": 11920, "loss": 0.3818, "lr": 9.940890758978781e-06, "epoch": 0.24538590604026847, "percentage": 4.91, "elapsed_time": "2:08:59", "remaining_time": "1 day, 17:39:18", "throughput": 4833.1, "total_tokens": 37405264}
{"current_steps": 590, "total_steps": 11920, "loss": 0.3831, "lr": 9.939876323649906e-06, "epoch": 0.24748322147651006, "percentage": 4.95, "elapsed_time": "2:09:47", "remaining_time": "1 day, 17:32:18", "throughput": 4834.68, "total_tokens": 37648008}
{"current_steps": 595, "total_steps": 11920, "loss": 0.3638, "lr": 9.938853309981013e-06, "epoch": 0.24958053691275167, "percentage": 4.99, "elapsed_time": "2:11:00", "remaining_time": "1 day, 17:33:31", "throughput": 4829.7, "total_tokens": 37963384}
{"current_steps": 600, "total_steps": 11920, "loss": 0.3875, "lr": 9.937821719748614e-06, "epoch": 0.2516778523489933, "percentage": 5.03, "elapsed_time": "2:12:06", "remaining_time": "1 day, 17:32:18", "throughput": 4834.26, "total_tokens": 38316784}
{"current_steps": 605, "total_steps": 11920, "loss": 0.4061, "lr": 9.93678155474412e-06, "epoch": 0.2537751677852349, "percentage": 5.08, "elapsed_time": "2:12:54", "remaining_time": "1 day, 17:25:51", "throughput": 4839.38, "total_tokens": 38593872}
{"current_steps": 610, "total_steps": 11920, "loss": 0.4181, "lr": 9.935732816773825e-06, "epoch": 0.2558724832214765, "percentage": 5.12, "elapsed_time": "2:14:14", "remaining_time": "1 day, 17:29:05", "throughput": 4829.98, "total_tokens": 38905064}
{"current_steps": 615, "total_steps": 11920, "loss": 0.3875, "lr": 9.934675507658916e-06, "epoch": 0.25796979865771813, "percentage": 5.16, "elapsed_time": "2:15:14", "remaining_time": "1 day, 17:26:10", "throughput": 4829.94, "total_tokens": 39194816}
{"current_steps": 620, "total_steps": 11920, "loss": 0.3937, "lr": 9.933609629235463e-06, "epoch": 0.2600671140939597, "percentage": 5.2, "elapsed_time": "2:16:08", "remaining_time": "1 day, 17:21:24", "throughput": 4832.02, "total_tokens": 39472224}
{"current_steps": 625, "total_steps": 11920, "loss": 0.4131, "lr": 9.932535183354418e-06, "epoch": 0.26216442953020136, "percentage": 5.24, "elapsed_time": "2:16:53", "remaining_time": "1 day, 17:13:46", "throughput": 4839.01, "total_tokens": 39743096}
{"current_steps": 630, "total_steps": 11920, "loss": 0.3827, "lr": 9.931452171881608e-06, "epoch": 0.26426174496644295, "percentage": 5.29, "elapsed_time": "2:17:50", "remaining_time": "1 day, 17:10:05", "throughput": 4838.89, "total_tokens": 40018032}
{"current_steps": 635, "total_steps": 11920, "loss": 0.3741, "lr": 9.930360596697735e-06, "epoch": 0.2663590604026846, "percentage": 5.33, "elapsed_time": "2:18:41", "remaining_time": "1 day, 17:04:40", "throughput": 4847.59, "total_tokens": 40337576}
{"current_steps": 640, "total_steps": 11920, "loss": 0.3878, "lr": 9.929260459698376e-06, "epoch": 0.2684563758389262, "percentage": 5.37, "elapsed_time": "2:19:31", "remaining_time": "1 day, 16:59:05", "throughput": 4851.29, "total_tokens": 40612080}
{"current_steps": 645, "total_steps": 11920, "loss": 0.4081, "lr": 9.92815176279397e-06, "epoch": 0.27055369127516776, "percentage": 5.41, "elapsed_time": "2:20:20", "remaining_time": "1 day, 16:53:10", "throughput": 4858.75, "total_tokens": 40911768}
{"current_steps": 650, "total_steps": 11920, "loss": 0.4078, "lr": 9.927034507909828e-06, "epoch": 0.2726510067114094, "percentage": 5.45, "elapsed_time": "2:21:37", "remaining_time": "1 day, 16:55:35", "throughput": 4853.31, "total_tokens": 41241648}
{"current_steps": 655, "total_steps": 11920, "loss": 0.3692, "lr": 9.925908696986117e-06, "epoch": 0.274748322147651, "percentage": 5.49, "elapsed_time": "2:22:45", "remaining_time": "1 day, 16:55:10", "throughput": 4852.43, "total_tokens": 41562680}
{"current_steps": 660, "total_steps": 11920, "loss": 0.367, "lr": 9.924774331977863e-06, "epoch": 0.27684563758389263, "percentage": 5.54, "elapsed_time": "2:23:50", "remaining_time": "1 day, 16:54:04", "throughput": 4852.09, "total_tokens": 41876672}
{"current_steps": 665, "total_steps": 11920, "loss": 0.3856, "lr": 9.923631414854946e-06, "epoch": 0.2789429530201342, "percentage": 5.58, "elapsed_time": "2:25:06", "remaining_time": "1 day, 16:55:57", "throughput": 4847.06, "total_tokens": 42201352}
{"current_steps": 670, "total_steps": 11920, "loss": 0.3698, "lr": 9.9224799476021e-06, "epoch": 0.28104026845637586, "percentage": 5.62, "elapsed_time": "2:26:07", "remaining_time": "1 day, 16:53:37", "throughput": 4847.21, "total_tokens": 42498432}
{"current_steps": 675, "total_steps": 11920, "loss": 0.3991, "lr": 9.921319932218905e-06, "epoch": 0.28313758389261745, "percentage": 5.66, "elapsed_time": "2:27:24", "remaining_time": "1 day, 16:55:44", "throughput": 4842.54, "total_tokens": 42830200}
{"current_steps": 680, "total_steps": 11920, "loss": 0.4301, "lr": 9.920151370719783e-06, "epoch": 0.28523489932885904, "percentage": 5.7, "elapsed_time": "2:28:21", "remaining_time": "1 day, 16:52:24", "throughput": 4846.23, "total_tokens": 43140928}
{"current_steps": 685, "total_steps": 11920, "loss": 0.3859, "lr": 9.918974265134003e-06, "epoch": 0.2873322147651007, "percentage": 5.75, "elapsed_time": "2:29:15", "remaining_time": "1 day, 16:48:03", "throughput": 4854.5, "total_tokens": 43474584}
{"current_steps": 690, "total_steps": 11920, "loss": 0.3799, "lr": 9.91778861750566e-06, "epoch": 0.28942953020134227, "percentage": 5.79, "elapsed_time": "2:30:43", "remaining_time": "1 day, 16:53:05", "throughput": 4845.73, "total_tokens": 43821992}
{"current_steps": 695, "total_steps": 11920, "loss": 0.3961, "lr": 9.9165944298937e-06, "epoch": 0.2915268456375839, "percentage": 5.83, "elapsed_time": "2:31:40", "remaining_time": "1 day, 16:49:44", "throughput": 4850.81, "total_tokens": 44145144}
{"current_steps": 700, "total_steps": 11920, "loss": 0.3889, "lr": 9.915391704371881e-06, "epoch": 0.2936241610738255, "percentage": 5.87, "elapsed_time": "2:32:39", "remaining_time": "1 day, 16:46:56", "throughput": 4853.81, "total_tokens": 44459304}
{"current_steps": 705, "total_steps": 11920, "loss": 0.3911, "lr": 9.914180443028798e-06, "epoch": 0.29572147651006714, "percentage": 5.91, "elapsed_time": "2:33:46", "remaining_time": "1 day, 16:46:08", "throughput": 4855.43, "total_tokens": 44797056}
{"current_steps": 710, "total_steps": 11920, "loss": 0.3601, "lr": 9.912960647967867e-06, "epoch": 0.2978187919463087, "percentage": 5.96, "elapsed_time": "2:34:59", "remaining_time": "1 day, 16:47:00", "throughput": 4854.42, "total_tokens": 45141632}
{"current_steps": 715, "total_steps": 11920, "loss": 0.382, "lr": 9.91173232130732e-06, "epoch": 0.2999161073825503, "percentage": 6.0, "elapsed_time": "2:36:03", "remaining_time": "1 day, 16:45:30", "throughput": 4856.97, "total_tokens": 45475880}
{"current_steps": 720, "total_steps": 11920, "loss": 0.3863, "lr": 9.91049546518021e-06, "epoch": 0.30201342281879195, "percentage": 6.04, "elapsed_time": "2:37:03", "remaining_time": "1 day, 16:43:10", "throughput": 4859.67, "total_tokens": 45795912}
{"current_steps": 725, "total_steps": 11920, "loss": 0.3795, "lr": 9.909250081734399e-06, "epoch": 0.30411073825503354, "percentage": 6.08, "elapsed_time": "2:38:05", "remaining_time": "1 day, 16:41:10", "throughput": 4857.93, "total_tokens": 46080448}
{"current_steps": 730, "total_steps": 11920, "loss": 0.3858, "lr": 9.907996173132555e-06, "epoch": 0.3062080536912752, "percentage": 6.12, "elapsed_time": "2:39:15", "remaining_time": "1 day, 16:41:16", "throughput": 4856.26, "total_tokens": 46404704}
{"current_steps": 735, "total_steps": 11920, "loss": 0.3894, "lr": 9.906733741552153e-06, "epoch": 0.30830536912751677, "percentage": 6.17, "elapsed_time": "2:40:24", "remaining_time": "1 day, 16:41:01", "throughput": 4857.7, "total_tokens": 46752576}
{"current_steps": 740, "total_steps": 11920, "loss": 0.4101, "lr": 9.905462789185469e-06, "epoch": 0.3104026845637584, "percentage": 6.21, "elapsed_time": "2:41:28", "remaining_time": "1 day, 16:39:36", "throughput": 4854.18, "total_tokens": 47030248}
{"current_steps": 745, "total_steps": 11920, "loss": 0.3965, "lr": 9.904183318239573e-06, "epoch": 0.3125, "percentage": 6.25, "elapsed_time": "2:42:41", "remaining_time": "1 day, 16:40:18", "throughput": 4855.41, "total_tokens": 47394776}
{"current_steps": 750, "total_steps": 11920, "loss": 0.4011, "lr": 9.902895330936333e-06, "epoch": 0.3145973154362416, "percentage": 6.29, "elapsed_time": "2:43:59", "remaining_time": "1 day, 16:42:15", "throughput": 4850.89, "total_tokens": 47727920}
{"current_steps": 755, "total_steps": 11920, "loss": 0.4107, "lr": 9.901598829512399e-06, "epoch": 0.31669463087248323, "percentage": 6.33, "elapsed_time": "2:45:06", "remaining_time": "1 day, 16:41:32", "throughput": 4849.95, "total_tokens": 48044040}
{"current_steps": 760, "total_steps": 11920, "loss": 0.403, "lr": 9.900293816219212e-06, "epoch": 0.3187919463087248, "percentage": 6.38, "elapsed_time": "2:46:01", "remaining_time": "1 day, 16:37:55", "throughput": 4850.82, "total_tokens": 48320888}
{"current_steps": 765, "total_steps": 11920, "loss": 0.396, "lr": 9.898980293322993e-06, "epoch": 0.32088926174496646, "percentage": 6.42, "elapsed_time": "2:47:01", "remaining_time": "1 day, 16:35:37", "throughput": 4851.31, "total_tokens": 48619720}
{"current_steps": 770, "total_steps": 11920, "loss": 0.3835, "lr": 9.897658263104737e-06, "epoch": 0.32298657718120805, "percentage": 6.46, "elapsed_time": "2:48:26", "remaining_time": "1 day, 16:39:11", "throughput": 4846.19, "total_tokens": 48979432}
{"current_steps": 775, "total_steps": 11920, "loss": 0.4004, "lr": 9.896327727860217e-06, "epoch": 0.3250838926174497, "percentage": 6.5, "elapsed_time": "2:49:20", "remaining_time": "1 day, 16:35:17", "throughput": 4851.94, "total_tokens": 49298960}
{"current_steps": 780, "total_steps": 11920, "loss": 0.3442, "lr": 9.894988689899972e-06, "epoch": 0.3271812080536913, "percentage": 6.54, "elapsed_time": "2:50:13", "remaining_time": "1 day, 16:31:05", "throughput": 4854.82, "total_tokens": 49583376}
{"current_steps": 785, "total_steps": 11920, "loss": 0.3848, "lr": 9.893641151549309e-06, "epoch": 0.32927852348993286, "percentage": 6.59, "elapsed_time": "2:51:34", "remaining_time": "1 day, 16:33:43", "throughput": 4847.73, "total_tokens": 49904464}
{"current_steps": 790, "total_steps": 11920, "loss": 0.3619, "lr": 9.892285115148296e-06, "epoch": 0.3313758389261745, "percentage": 6.63, "elapsed_time": "2:52:28", "remaining_time": "1 day, 16:29:55", "throughput": 4853.59, "total_tokens": 50227416}
{"current_steps": 795, "total_steps": 11920, "loss": 0.3837, "lr": 9.890920583051755e-06, "epoch": 0.3334731543624161, "percentage": 6.67, "elapsed_time": "2:53:48", "remaining_time": "1 day, 16:32:17", "throughput": 4849.59, "total_tokens": 50575488}
{"current_steps": 800, "total_steps": 11920, "loss": 0.392, "lr": 9.889547557629265e-06, "epoch": 0.33557046979865773, "percentage": 6.71, "elapsed_time": "2:54:59", "remaining_time": "1 day, 16:32:24", "throughput": 4847.49, "total_tokens": 50896680}
{"current_steps": 805, "total_steps": 11920, "loss": 0.4045, "lr": 9.888166041265153e-06, "epoch": 0.3376677852348993, "percentage": 6.75, "elapsed_time": "2:55:56", "remaining_time": "1 day, 16:29:20", "throughput": 4850.11, "total_tokens": 51201008}
{"current_steps": 810, "total_steps": 11920, "loss": 0.3746, "lr": 9.886776036358487e-06, "epoch": 0.33976510067114096, "percentage": 6.8, "elapsed_time": "2:56:58", "remaining_time": "1 day, 16:27:26", "throughput": 4850.14, "total_tokens": 51502040}
{"current_steps": 815, "total_steps": 11920, "loss": 0.3791, "lr": 9.885377545323085e-06, "epoch": 0.34186241610738255, "percentage": 6.84, "elapsed_time": "2:58:00", "remaining_time": "1 day, 16:25:26", "throughput": 4851.58, "total_tokens": 51816040}
{"current_steps": 820, "total_steps": 11920, "loss": 0.3664, "lr": 9.883970570587494e-06, "epoch": 0.34395973154362414, "percentage": 6.88, "elapsed_time": "2:59:01", "remaining_time": "1 day, 16:23:29", "throughput": 4855.93, "total_tokens": 52162200}
{"current_steps": 825, "total_steps": 11920, "loss": 0.3676, "lr": 9.882555114594994e-06, "epoch": 0.3460570469798658, "percentage": 6.92, "elapsed_time": "3:00:22", "remaining_time": "1 day, 16:25:42", "throughput": 4850.75, "total_tokens": 52495952}
{"current_steps": 830, "total_steps": 11920, "loss": 0.3983, "lr": 9.881131179803594e-06, "epoch": 0.34815436241610737, "percentage": 6.96, "elapsed_time": "3:01:22", "remaining_time": "1 day, 16:23:19", "throughput": 4855.4, "total_tokens": 52836712}
{"current_steps": 835, "total_steps": 11920, "loss": 0.3878, "lr": 9.87969876868603e-06, "epoch": 0.350251677852349, "percentage": 7.01, "elapsed_time": "3:02:20", "remaining_time": "1 day, 16:20:42", "throughput": 4856.42, "total_tokens": 53132648}
{"current_steps": 840, "total_steps": 11920, "loss": 0.3904, "lr": 9.878257883729754e-06, "epoch": 0.3523489932885906, "percentage": 7.05, "elapsed_time": "3:03:36", "remaining_time": "1 day, 16:21:52", "throughput": 4855.06, "total_tokens": 53485432}
{"current_steps": 845, "total_steps": 11920, "loss": 0.3751, "lr": 9.876808527436932e-06, "epoch": 0.35444630872483224, "percentage": 7.09, "elapsed_time": "3:04:53", "remaining_time": "1 day, 16:23:10", "throughput": 4852.97, "total_tokens": 53834176}
{"current_steps": 850, "total_steps": 11920, "loss": 0.3941, "lr": 9.875350702324446e-06, "epoch": 0.3565436241610738, "percentage": 7.13, "elapsed_time": "3:06:04", "remaining_time": "1 day, 16:23:20", "throughput": 4850.07, "total_tokens": 54148368}
{"current_steps": 855, "total_steps": 11920, "loss": 0.3839, "lr": 9.87388441092388e-06, "epoch": 0.3586409395973154, "percentage": 7.17, "elapsed_time": "3:07:29", "remaining_time": "1 day, 16:26:29", "throughput": 4841.64, "total_tokens": 54467472}
{"current_steps": 860, "total_steps": 11920, "loss": 0.3763, "lr": 9.87240965578152e-06, "epoch": 0.36073825503355705, "percentage": 7.21, "elapsed_time": "3:08:28", "remaining_time": "1 day, 16:23:51", "throughput": 4844.44, "total_tokens": 54783000}
{"current_steps": 865, "total_steps": 11920, "loss": 0.3627, "lr": 9.870926439458355e-06, "epoch": 0.36283557046979864, "percentage": 7.26, "elapsed_time": "3:09:40", "remaining_time": "1 day, 16:24:10", "throughput": 4842.43, "total_tokens": 55110792}
{"current_steps": 870, "total_steps": 11920, "loss": 0.378, "lr": 9.86943476453006e-06, "epoch": 0.3649328859060403, "percentage": 7.3, "elapsed_time": "3:11:00", "remaining_time": "1 day, 16:25:59", "throughput": 4837.19, "total_tokens": 55435936}
{"current_steps": 875, "total_steps": 11920, "loss": 0.3755, "lr": 9.867934633587006e-06, "epoch": 0.36703020134228187, "percentage": 7.34, "elapsed_time": "3:12:00", "remaining_time": "1 day, 16:23:45", "throughput": 4838.0, "total_tokens": 55737816}
{"current_steps": 880, "total_steps": 11920, "loss": 0.3887, "lr": 9.866426049234243e-06, "epoch": 0.3691275167785235, "percentage": 7.38, "elapsed_time": "3:13:13", "remaining_time": "1 day, 16:24:04", "throughput": 4834.9, "total_tokens": 56052760}
{"current_steps": 885, "total_steps": 11920, "loss": 0.3499, "lr": 9.864909014091502e-06, "epoch": 0.3712248322147651, "percentage": 7.42, "elapsed_time": "3:14:10", "remaining_time": "1 day, 16:21:03", "throughput": 4836.51, "total_tokens": 56345720}
{"current_steps": 890, "total_steps": 11920, "loss": 0.3951, "lr": 9.86338353079319e-06, "epoch": 0.3733221476510067, "percentage": 7.47, "elapsed_time": "3:15:08", "remaining_time": "1 day, 16:18:27", "throughput": 4836.12, "total_tokens": 56623976}
{"current_steps": 895, "total_steps": 11920, "loss": 0.3827, "lr": 9.861849601988384e-06, "epoch": 0.37541946308724833, "percentage": 7.51, "elapsed_time": "3:16:16", "remaining_time": "1 day, 16:17:46", "throughput": 4837.83, "total_tokens": 56972152}
{"current_steps": 900, "total_steps": 11920, "loss": 0.3582, "lr": 9.860307230340829e-06, "epoch": 0.3775167785234899, "percentage": 7.55, "elapsed_time": "3:17:34", "remaining_time": "1 day, 16:19:13", "throughput": 4833.23, "total_tokens": 57296080}
{"current_steps": 905, "total_steps": 11920, "loss": 0.3858, "lr": 9.858756418528928e-06, "epoch": 0.37961409395973156, "percentage": 7.59, "elapsed_time": "3:18:53", "remaining_time": "1 day, 16:20:46", "throughput": 4829.36, "total_tokens": 57631232}
{"current_steps": 910, "total_steps": 11920, "loss": 0.3781, "lr": 9.857197169245743e-06, "epoch": 0.38171140939597314, "percentage": 7.63, "elapsed_time": "3:19:56", "remaining_time": "1 day, 16:19:03", "throughput": 4828.25, "total_tokens": 57921936}
{"current_steps": 915, "total_steps": 11920, "loss": 0.3941, "lr": 9.855629485198987e-06, "epoch": 0.3838087248322148, "percentage": 7.68, "elapsed_time": "3:21:24", "remaining_time": "1 day, 16:22:21", "throughput": 4822.51, "total_tokens": 58276672}
{"current_steps": 920, "total_steps": 11920, "loss": 0.3977, "lr": 9.854053369111025e-06, "epoch": 0.3859060402684564, "percentage": 7.72, "elapsed_time": "3:22:05", "remaining_time": "1 day, 16:16:19", "throughput": 4825.91, "total_tokens": 58516976}
{"current_steps": 925, "total_steps": 11920, "loss": 0.364, "lr": 9.852468823718855e-06, "epoch": 0.38800335570469796, "percentage": 7.76, "elapsed_time": "3:23:05", "remaining_time": "1 day, 16:14:03", "throughput": 4827.04, "total_tokens": 58820344}
{"current_steps": 930, "total_steps": 11920, "loss": 0.4001, "lr": 9.850875851774122e-06, "epoch": 0.3901006711409396, "percentage": 7.8, "elapsed_time": "3:24:21", "remaining_time": "1 day, 16:14:56", "throughput": 4825.93, "total_tokens": 59173224}
{"current_steps": 935, "total_steps": 11920, "loss": 0.3973, "lr": 9.849274456043099e-06, "epoch": 0.3921979865771812, "percentage": 7.84, "elapsed_time": "3:25:30", "remaining_time": "1 day, 16:14:22", "throughput": 4824.7, "total_tokens": 59489232}
{"current_steps": 940, "total_steps": 11920, "loss": 0.3857, "lr": 9.847664639306691e-06, "epoch": 0.39429530201342283, "percentage": 7.89, "elapsed_time": "3:26:12", "remaining_time": "1 day, 16:08:43", "throughput": 4831.01, "total_tokens": 59772696}
{"current_steps": 945, "total_steps": 11920, "loss": 0.3864, "lr": 9.846046404360423e-06, "epoch": 0.3963926174496644, "percentage": 7.93, "elapsed_time": "3:27:22", "remaining_time": "1 day, 16:08:22", "throughput": 4827.63, "total_tokens": 60066928}
{"current_steps": 950, "total_steps": 11920, "loss": 0.376, "lr": 9.84441975401444e-06, "epoch": 0.39848993288590606, "percentage": 7.97, "elapsed_time": "3:28:28", "remaining_time": "1 day, 16:07:23", "throughput": 4829.37, "total_tokens": 60409384}
{"current_steps": 955, "total_steps": 11920, "loss": 0.4086, "lr": 9.842784691093504e-06, "epoch": 0.40058724832214765, "percentage": 8.01, "elapsed_time": "3:29:34", "remaining_time": "1 day, 16:06:19", "throughput": 4828.27, "total_tokens": 60714256}
{"current_steps": 960, "total_steps": 11920, "loss": 0.3761, "lr": 9.841141218436978e-06, "epoch": 0.40268456375838924, "percentage": 8.05, "elapsed_time": "3:30:43", "remaining_time": "1 day, 16:05:43", "throughput": 4827.89, "total_tokens": 61040072}
{"current_steps": 965, "total_steps": 11920, "loss": 0.3869, "lr": 9.839489338898837e-06, "epoch": 0.4047818791946309, "percentage": 8.1, "elapsed_time": "3:32:13", "remaining_time": "1 day, 16:09:11", "throughput": 4819.71, "total_tokens": 61370160}
{"current_steps": 970, "total_steps": 11920, "loss": 0.3873, "lr": 9.83782905534765e-06, "epoch": 0.40687919463087246, "percentage": 8.14, "elapsed_time": "3:33:16", "remaining_time": "1 day, 16:07:34", "throughput": 4820.82, "total_tokens": 61689088}
{"current_steps": 975, "total_steps": 11920, "loss": 0.365, "lr": 9.836160370666583e-06, "epoch": 0.4089765100671141, "percentage": 8.18, "elapsed_time": "3:34:11", "remaining_time": "1 day, 16:04:25", "throughput": 4822.97, "total_tokens": 61981912}
{"current_steps": 980, "total_steps": 11920, "loss": 0.3724, "lr": 9.83448328775339e-06, "epoch": 0.4110738255033557, "percentage": 8.22, "elapsed_time": "3:35:09", "remaining_time": "1 day, 16:01:52", "throughput": 4826.41, "total_tokens": 62306800}
{"current_steps": 985, "total_steps": 11920, "loss": 0.3829, "lr": 9.832797809520404e-06, "epoch": 0.41317114093959734, "percentage": 8.26, "elapsed_time": "3:36:11", "remaining_time": "1 day, 16:00:07", "throughput": 4829.98, "total_tokens": 62654096}
{"current_steps": 990, "total_steps": 11920, "loss": 0.4193, "lr": 9.831103938894548e-06, "epoch": 0.4152684563758389, "percentage": 8.31, "elapsed_time": "3:37:38", "remaining_time": "1 day, 16:02:47", "throughput": 4823.41, "total_tokens": 62985072}
{"current_steps": 995, "total_steps": 11920, "loss": 0.3746, "lr": 9.82940167881731e-06, "epoch": 0.4173657718120805, "percentage": 8.35, "elapsed_time": "3:38:52", "remaining_time": "1 day, 16:03:13", "throughput": 4821.58, "total_tokens": 63319432}
{"current_steps": 1000, "total_steps": 11920, "loss": 0.3721, "lr": 9.827691032244746e-06, "epoch": 0.41946308724832215, "percentage": 8.39, "elapsed_time": "3:39:50", "remaining_time": "1 day, 16:00:35", "throughput": 4822.26, "total_tokens": 63606112}
{"current_steps": 1005, "total_steps": 11920, "loss": 0.379, "lr": 9.825972002147483e-06, "epoch": 0.42156040268456374, "percentage": 8.43, "elapsed_time": "3:41:00", "remaining_time": "1 day, 16:00:21", "throughput": 4820.1, "total_tokens": 63918392}
{"current_steps": 1010, "total_steps": 11920, "loss": 0.3748, "lr": 9.824244591510699e-06, "epoch": 0.4236577181208054, "percentage": 8.47, "elapsed_time": "3:41:57", "remaining_time": "1 day, 15:57:38", "throughput": 4822.35, "total_tokens": 64223168}
{"current_steps": 1015, "total_steps": 11920, "loss": 0.3569, "lr": 9.82250880333413e-06, "epoch": 0.42575503355704697, "percentage": 8.52, "elapsed_time": "3:43:16", "remaining_time": "1 day, 15:58:50", "throughput": 4820.72, "total_tokens": 64581080}
{"current_steps": 1020, "total_steps": 11920, "loss": 0.3809, "lr": 9.820764640632056e-06, "epoch": 0.4278523489932886, "percentage": 8.56, "elapsed_time": "3:44:30", "remaining_time": "1 day, 15:59:06", "throughput": 4817.17, "total_tokens": 64888288}
{"current_steps": 1025, "total_steps": 11920, "loss": 0.3843, "lr": 9.819012106433303e-06, "epoch": 0.4299496644295302, "percentage": 8.6, "elapsed_time": "3:45:35", "remaining_time": "1 day, 15:57:53", "throughput": 4815.1, "total_tokens": 65175144}
{"current_steps": 1030, "total_steps": 11920, "loss": 0.3866, "lr": 9.817251203781232e-06, "epoch": 0.4320469798657718, "percentage": 8.64, "elapsed_time": "3:46:35", "remaining_time": "1 day, 15:55:43", "throughput": 4818.29, "total_tokens": 65507256}
{"current_steps": 1035, "total_steps": 11920, "loss": 0.38, "lr": 9.815481935733742e-06, "epoch": 0.4341442953020134, "percentage": 8.68, "elapsed_time": "3:47:59", "remaining_time": "1 day, 15:57:43", "throughput": 4812.29, "total_tokens": 65828584}
{"current_steps": 1040, "total_steps": 11920, "loss": 0.3699, "lr": 9.813704305363251e-06, "epoch": 0.436241610738255, "percentage": 8.72, "elapsed_time": "3:49:03", "remaining_time": "1 day, 15:56:22", "throughput": 4810.26, "total_tokens": 66112080}
{"current_steps": 1045, "total_steps": 11920, "loss": 0.3798, "lr": 9.811918315756704e-06, "epoch": 0.43833892617449666, "percentage": 8.77, "elapsed_time": "3:50:06", "remaining_time": "1 day, 15:54:39", "throughput": 4814.42, "total_tokens": 66470208}
{"current_steps": 1050, "total_steps": 11920, "loss": 0.3738, "lr": 9.810123970015559e-06, "epoch": 0.44043624161073824, "percentage": 8.81, "elapsed_time": "3:51:16", "remaining_time": "1 day, 15:54:12", "throughput": 4814.49, "total_tokens": 66807072}
{"current_steps": 1055, "total_steps": 11920, "loss": 0.3623, "lr": 9.808321271255787e-06, "epoch": 0.4425335570469799, "percentage": 8.85, "elapsed_time": "3:52:37", "remaining_time": "1 day, 15:55:40", "throughput": 4812.61, "total_tokens": 67171416}
{"current_steps": 1060, "total_steps": 11920, "loss": 0.3611, "lr": 9.806510222607864e-06, "epoch": 0.4446308724832215, "percentage": 8.89, "elapsed_time": "3:53:45", "remaining_time": "1 day, 15:54:54", "throughput": 4810.21, "total_tokens": 67465376}
{"current_steps": 1065, "total_steps": 11920, "loss": 0.3679, "lr": 9.804690827216764e-06, "epoch": 0.44672818791946306, "percentage": 8.93, "elapsed_time": "3:54:51", "remaining_time": "1 day, 15:53:52", "throughput": 4808.5, "total_tokens": 67761360}
{"current_steps": 1070, "total_steps": 11920, "loss": 0.3972, "lr": 9.80286308824196e-06, "epoch": 0.4488255033557047, "percentage": 8.98, "elapsed_time": "3:55:43", "remaining_time": "1 day, 15:50:16", "throughput": 4810.05, "total_tokens": 68030528}
{"current_steps": 1075, "total_steps": 11920, "loss": 0.3807, "lr": 9.801027008857409e-06, "epoch": 0.4509228187919463, "percentage": 9.02, "elapsed_time": "3:56:29", "remaining_time": "1 day, 15:45:50", "throughput": 4813.44, "total_tokens": 68300920}
{"current_steps": 1080, "total_steps": 11920, "loss": 0.37, "lr": 9.799182592251554e-06, "epoch": 0.45302013422818793, "percentage": 9.06, "elapsed_time": "3:57:37", "remaining_time": "1 day, 15:45:03", "throughput": 4814.11, "total_tokens": 68637624}
{"current_steps": 1085, "total_steps": 11920, "loss": 0.3496, "lr": 9.797329841627318e-06, "epoch": 0.4551174496644295, "percentage": 9.1, "elapsed_time": "3:58:40", "remaining_time": "1 day, 15:43:29", "throughput": 4815.35, "total_tokens": 68959480}
{"current_steps": 1090, "total_steps": 11920, "loss": 0.3797, "lr": 9.795468760202094e-06, "epoch": 0.45721476510067116, "percentage": 9.14, "elapsed_time": "3:59:37", "remaining_time": "1 day, 15:40:53", "throughput": 4817.38, "total_tokens": 69262816}
{"current_steps": 1095, "total_steps": 11920, "loss": 0.379, "lr": 9.79359935120774e-06, "epoch": 0.45931208053691275, "percentage": 9.19, "elapsed_time": "4:00:55", "remaining_time": "1 day, 15:41:40", "throughput": 4814.48, "total_tokens": 69593728}
{"current_steps": 1100, "total_steps": 11920, "loss": 0.3448, "lr": 9.791721617890578e-06, "epoch": 0.46140939597315433, "percentage": 9.23, "elapsed_time": "4:02:07", "remaining_time": "1 day, 15:41:41", "throughput": 4811.06, "total_tokens": 69894672}
{"current_steps": 1105, "total_steps": 11920, "loss": 0.3863, "lr": 9.789835563511385e-06, "epoch": 0.463506711409396, "percentage": 9.27, "elapsed_time": "4:03:28", "remaining_time": "1 day, 15:43:00", "throughput": 4805.44, "total_tokens": 70201480}
{"current_steps": 1110, "total_steps": 11920, "loss": 0.3751, "lr": 9.787941191345389e-06, "epoch": 0.46560402684563756, "percentage": 9.31, "elapsed_time": "4:04:20", "remaining_time": "1 day, 15:39:34", "throughput": 4810.13, "total_tokens": 70518816}
{"current_steps": 1115, "total_steps": 11920, "loss": 0.3623, "lr": 9.786038504682259e-06, "epoch": 0.4677013422818792, "percentage": 9.35, "elapsed_time": "4:05:25", "remaining_time": "1 day, 15:38:23", "throughput": 4810.76, "total_tokens": 70843104}
{"current_steps": 1120, "total_steps": 11920, "loss": 0.3588, "lr": 9.784127506826107e-06, "epoch": 0.4697986577181208, "percentage": 9.4, "elapsed_time": "4:06:19", "remaining_time": "1 day, 15:35:13", "throughput": 4812.35, "total_tokens": 71122424}
{"current_steps": 1125, "total_steps": 11920, "loss": 0.3595, "lr": 9.782208201095474e-06, "epoch": 0.47189597315436244, "percentage": 9.44, "elapsed_time": "4:07:23", "remaining_time": "1 day, 15:33:48", "throughput": 4810.93, "total_tokens": 71409584}
{"current_steps": 1130, "total_steps": 11920, "loss": 0.3696, "lr": 9.78028059082333e-06, "epoch": 0.473993288590604, "percentage": 9.48, "elapsed_time": "4:08:31", "remaining_time": "1 day, 15:33:08", "throughput": 4810.31, "total_tokens": 71730480}
{"current_steps": 1135, "total_steps": 11920, "loss": 0.3775, "lr": 9.778344679357066e-06, "epoch": 0.47609060402684567, "percentage": 9.52, "elapsed_time": "4:10:00", "remaining_time": "1 day, 15:35:34", "throughput": 4804.2, "total_tokens": 72063744}
{"current_steps": 1140, "total_steps": 11920, "loss": 0.4062, "lr": 9.776400470058486e-06, "epoch": 0.47818791946308725, "percentage": 9.56, "elapsed_time": "4:10:52", "remaining_time": "1 day, 15:32:15", "throughput": 4806.11, "total_tokens": 72342408}
{"current_steps": 1145, "total_steps": 11920, "loss": 0.3686, "lr": 9.77444796630381e-06, "epoch": 0.48028523489932884, "percentage": 9.61, "elapsed_time": "4:11:39", "remaining_time": "1 day, 15:28:16", "throughput": 4809.08, "total_tokens": 72616184}
{"current_steps": 1150, "total_steps": 11920, "loss": 0.3583, "lr": 9.772487171483654e-06, "epoch": 0.4823825503355705, "percentage": 9.65, "elapsed_time": "4:12:51", "remaining_time": "1 day, 15:28:07", "throughput": 4806.2, "total_tokens": 72918728}
{"current_steps": 1155, "total_steps": 11920, "loss": 0.3707, "lr": 9.770518089003037e-06, "epoch": 0.48447986577181207, "percentage": 9.69, "elapsed_time": "4:13:53", "remaining_time": "1 day, 15:26:20", "throughput": 4806.71, "total_tokens": 73222384}
{"current_steps": 1160, "total_steps": 11920, "loss": 0.3815, "lr": 9.768540722281368e-06, "epoch": 0.4865771812080537, "percentage": 9.73, "elapsed_time": "4:14:43", "remaining_time": "1 day, 15:22:46", "throughput": 4809.71, "total_tokens": 73508504}
{"current_steps": 1165, "total_steps": 11920, "loss": 0.3459, "lr": 9.766555074752442e-06, "epoch": 0.4886744966442953, "percentage": 9.77, "elapsed_time": "4:15:47", "remaining_time": "1 day, 15:21:24", "throughput": 4810.41, "total_tokens": 73827544}
{"current_steps": 1170, "total_steps": 11920, "loss": 0.3753, "lr": 9.764561149864436e-06, "epoch": 0.49077181208053694, "percentage": 9.82, "elapsed_time": "4:17:05", "remaining_time": "1 day, 15:22:07", "throughput": 4805.91, "total_tokens": 74132240}
{"current_steps": 1175, "total_steps": 11920, "loss": 0.3888, "lr": 9.762558951079895e-06, "epoch": 0.4928691275167785, "percentage": 9.86, "elapsed_time": "4:18:05", "remaining_time": "1 day, 15:20:08", "throughput": 4807.77, "total_tokens": 74449888}
{"current_steps": 1180, "total_steps": 11920, "loss": 0.3563, "lr": 9.76054848187574e-06, "epoch": 0.4949664429530201, "percentage": 9.9, "elapsed_time": "4:19:12", "remaining_time": "1 day, 15:19:10", "throughput": 4807.0, "total_tokens": 74759216}
{"current_steps": 1185, "total_steps": 11920, "loss": 0.3842, "lr": 9.75852974574325e-06, "epoch": 0.49706375838926176, "percentage": 9.94, "elapsed_time": "4:20:16", "remaining_time": "1 day, 15:17:49", "throughput": 4807.83, "total_tokens": 75080840}
{"current_steps": 1190, "total_steps": 11920, "loss": 0.3804, "lr": 9.756502746188062e-06, "epoch": 0.49916107382550334, "percentage": 9.98, "elapsed_time": "4:21:20", "remaining_time": "1 day, 15:16:25", "throughput": 4805.42, "total_tokens": 75349840}
{"current_steps": 1195, "total_steps": 11920, "loss": 0.3694, "lr": 9.754467486730157e-06, "epoch": 0.5012583892617449, "percentage": 10.03, "elapsed_time": "4:22:33", "remaining_time": "1 day, 15:16:22", "throughput": 4804.9, "total_tokens": 75692248}
{"current_steps": 1200, "total_steps": 11920, "loss": 0.3747, "lr": 9.752423970903867e-06, "epoch": 0.5033557046979866, "percentage": 10.07, "elapsed_time": "4:23:45", "remaining_time": "1 day, 15:16:12", "throughput": 4805.74, "total_tokens": 76052208}
{"current_steps": 1205, "total_steps": 11920, "loss": 0.3912, "lr": 9.750372202257857e-06, "epoch": 0.5054530201342282, "percentage": 10.11, "elapsed_time": "4:24:57", "remaining_time": "1 day, 15:16:03", "throughput": 4806.22, "total_tokens": 76407520}
{"current_steps": 1210, "total_steps": 11920, "loss": 0.3902, "lr": 9.748312184355126e-06, "epoch": 0.5075503355704698, "percentage": 10.15, "elapsed_time": "4:25:56", "remaining_time": "1 day, 15:13:54", "throughput": 4808.51, "total_tokens": 76726584}
{"current_steps": 1215, "total_steps": 11920, "loss": 0.3754, "lr": 9.746243920772996e-06, "epoch": 0.5096476510067114, "percentage": 10.19, "elapsed_time": "4:27:00", "remaining_time": "1 day, 15:12:31", "throughput": 4808.82, "total_tokens": 77039592}
{"current_steps": 1220, "total_steps": 11920, "loss": 0.3414, "lr": 9.74416741510311e-06, "epoch": 0.511744966442953, "percentage": 10.23, "elapsed_time": "4:28:34", "remaining_time": "1 day, 15:15:29", "throughput": 4804.55, "total_tokens": 77421448}
{"current_steps": 1225, "total_steps": 11920, "loss": 0.3834, "lr": 9.742082670951423e-06, "epoch": 0.5138422818791947, "percentage": 10.28, "elapsed_time": "4:29:25", "remaining_time": "1 day, 15:12:14", "throughput": 4807.98, "total_tokens": 77723192}
{"current_steps": 1230, "total_steps": 11920, "loss": 0.3922, "lr": 9.739989691938196e-06, "epoch": 0.5159395973154363, "percentage": 10.32, "elapsed_time": "4:30:32", "remaining_time": "1 day, 15:11:14", "throughput": 4805.22, "total_tokens": 77998776}
{"current_steps": 1235, "total_steps": 11920, "loss": 0.4019, "lr": 9.73788848169799e-06, "epoch": 0.5180369127516778, "percentage": 10.36, "elapsed_time": "4:31:49", "remaining_time": "1 day, 15:11:46", "throughput": 4801.97, "total_tokens": 78317608}
{"current_steps": 1240, "total_steps": 11920, "loss": 0.388, "lr": 9.735779043879664e-06, "epoch": 0.5201342281879194, "percentage": 10.4, "elapsed_time": "4:32:52", "remaining_time": "1 day, 15:10:17", "throughput": 4800.55, "total_tokens": 78598512}
{"current_steps": 5, "total_steps": 4768, "loss": 0.7613, "lr": 9.999982634512015e-06, "epoch": 0.0020973154362416107, "percentage": 0.1, "elapsed_time": "0:00:39", "remaining_time": "10:24:17", "throughput": 6754.2, "total_tokens": 265584}
{"current_steps": 10, "total_steps": 4768, "loss": 0.6113, "lr": 9.99991208742381e-06, "epoch": 0.0041946308724832215, "percentage": 0.21, "elapsed_time": "0:01:13", "remaining_time": "9:44:04", "throughput": 7430.34, "total_tokens": 547280}
{"current_steps": 15, "total_steps": 4768, "loss": 0.5919, "lr": 9.999787274157475e-06, "epoch": 0.006291946308724832, "percentage": 0.31, "elapsed_time": "0:01:44", "remaining_time": "9:12:51", "throughput": 7803.45, "total_tokens": 816920}
{"current_steps": 20, "total_steps": 4768, "loss": 0.5286, "lr": 9.99960819606766e-06, "epoch": 0.008389261744966443, "percentage": 0.42, "elapsed_time": "0:02:18", "remaining_time": "9:07:35", "throughput": 8019.25, "total_tokens": 1109840}
{"current_steps": 25, "total_steps": 4768, "loss": 0.5701, "lr": 9.999374855097978e-06, "epoch": 0.010486577181208054, "percentage": 0.52, "elapsed_time": "0:02:44", "remaining_time": "8:39:52", "throughput": 8401.07, "total_tokens": 1381240}
{"current_steps": 30, "total_steps": 4768, "loss": 0.5163, "lr": 9.999087253780976e-06, "epoch": 0.012583892617449664, "percentage": 0.63, "elapsed_time": "0:03:12", "remaining_time": "8:26:32", "throughput": 8674.8, "total_tokens": 1669392}
{"current_steps": 35, "total_steps": 4768, "loss": 0.5224, "lr": 9.998745395238115e-06, "epoch": 0.014681208053691275, "percentage": 0.73, "elapsed_time": "0:03:41", "remaining_time": "8:18:40", "throughput": 8847.04, "total_tokens": 1957496}
{"current_steps": 40, "total_steps": 4768, "loss": 0.473, "lr": 9.998349283179731e-06, "epoch": 0.016778523489932886, "percentage": 0.84, "elapsed_time": "0:04:08", "remaining_time": "8:09:25", "throughput": 8939.17, "total_tokens": 2220816}
{"current_steps": 45, "total_steps": 4768, "loss": 0.4748, "lr": 9.997898921904999e-06, "epoch": 0.018875838926174497, "percentage": 0.94, "elapsed_time": "0:04:36", "remaining_time": "8:04:31", "throughput": 9046.69, "total_tokens": 2505816}
{"current_steps": 50, "total_steps": 4768, "loss": 0.5127, "lr": 9.997394316301878e-06, "epoch": 0.02097315436241611, "percentage": 1.05, "elapsed_time": "0:04:58", "remaining_time": "7:48:53", "throughput": 9399.58, "total_tokens": 2802512}
{"current_steps": 55, "total_steps": 4768, "loss": 0.5038, "lr": 9.99683547184707e-06, "epoch": 0.02307046979865772, "percentage": 1.15, "elapsed_time": "0:05:24", "remaining_time": "7:43:36", "throughput": 9461.28, "total_tokens": 3071272}
{"current_steps": 60, "total_steps": 4768, "loss": 0.4908, "lr": 9.996222394605954e-06, "epoch": 0.025167785234899327, "percentage": 1.26, "elapsed_time": "0:05:48", "remaining_time": "7:36:03", "throughput": 9578.14, "total_tokens": 3340120}
{"current_steps": 65, "total_steps": 4768, "loss": 0.4603, "lr": 9.995555091232516e-06, "epoch": 0.02726510067114094, "percentage": 1.36, "elapsed_time": "0:06:12", "remaining_time": "7:29:00", "throughput": 9653.44, "total_tokens": 3594408}
{"current_steps": 70, "total_steps": 4768, "loss": 0.4847, "lr": 9.994833568969286e-06, "epoch": 0.02936241610738255, "percentage": 1.47, "elapsed_time": "0:06:40", "remaining_time": "7:27:40", "throughput": 9679.28, "total_tokens": 3873856}
{"current_steps": 75, "total_steps": 4768, "loss": 0.5083, "lr": 9.994057835647251e-06, "epoch": 0.031459731543624164, "percentage": 1.57, "elapsed_time": "0:07:11", "remaining_time": "7:30:12", "throughput": 9618.22, "total_tokens": 4152112}
{"current_steps": 80, "total_steps": 4768, "loss": 0.4829, "lr": 9.993227899685777e-06, "epoch": 0.03355704697986577, "percentage": 1.68, "elapsed_time": "0:07:34", "remaining_time": "7:23:33", "throughput": 9709.35, "total_tokens": 4409536}
{"current_steps": 85, "total_steps": 4768, "loss": 0.4681, "lr": 9.992343770092513e-06, "epoch": 0.03565436241610738, "percentage": 1.78, "elapsed_time": "0:08:03", "remaining_time": "7:23:39", "throughput": 9696.72, "total_tokens": 4685192}
{"current_steps": 90, "total_steps": 4768, "loss": 0.4921, "lr": 9.991405456463293e-06, "epoch": 0.037751677852348994, "percentage": 1.89, "elapsed_time": "0:08:25", "remaining_time": "7:17:54", "throughput": 9793.13, "total_tokens": 4950288}
{"current_steps": 95, "total_steps": 4768, "loss": 0.4711, "lr": 9.990412968982037e-06, "epoch": 0.0398489932885906, "percentage": 1.99, "elapsed_time": "0:08:58", "remaining_time": "7:21:22", "throughput": 9720.39, "total_tokens": 5233216}
{"current_steps": 100, "total_steps": 4768, "loss": 0.4702, "lr": 9.989366318420632e-06, "epoch": 0.04194630872483222, "percentage": 2.1, "elapsed_time": "0:09:28", "remaining_time": "7:22:20", "throughput": 9668.69, "total_tokens": 5497216}
{"current_steps": 105, "total_steps": 4768, "loss": 0.4489, "lr": 9.988265516138827e-06, "epoch": 0.044043624161073824, "percentage": 2.2, "elapsed_time": "0:09:58", "remaining_time": "7:22:44", "throughput": 9696.78, "total_tokens": 5800408}
{"current_steps": 110, "total_steps": 4768, "loss": 0.4598, "lr": 9.987110574084095e-06, "epoch": 0.04614093959731544, "percentage": 2.31, "elapsed_time": "0:10:25", "remaining_time": "7:21:14", "throughput": 9709.39, "total_tokens": 6070288}
{"current_steps": 115, "total_steps": 4768, "loss": 0.4527, "lr": 9.985901504791516e-06, "epoch": 0.04823825503355705, "percentage": 2.41, "elapsed_time": "0:10:55", "remaining_time": "7:22:06", "throughput": 9634.6, "total_tokens": 6316624}
{"current_steps": 120, "total_steps": 4768, "loss": 0.4506, "lr": 9.984638321383634e-06, "epoch": 0.050335570469798654, "percentage": 2.52, "elapsed_time": "0:11:26", "remaining_time": "7:22:58", "throughput": 9545.58, "total_tokens": 6550120}
{"current_steps": 125, "total_steps": 4768, "loss": 0.4531, "lr": 9.98332103757032e-06, "epoch": 0.05243288590604027, "percentage": 2.62, "elapsed_time": "0:11:54", "remaining_time": "7:22:25", "throughput": 9530.12, "total_tokens": 6810960}
{"current_steps": 130, "total_steps": 4768, "loss": 0.4407, "lr": 9.981949667648614e-06, "epoch": 0.05453020134228188, "percentage": 2.73, "elapsed_time": "0:12:21", "remaining_time": "7:21:07", "throughput": 9551.58, "total_tokens": 7085912}
{"current_steps": 135, "total_steps": 4768, "loss": 0.4534, "lr": 9.98052422650258e-06, "epoch": 0.05662751677852349, "percentage": 2.83, "elapsed_time": "0:12:52", "remaining_time": "7:22:06", "throughput": 9521.14, "total_tokens": 7359320}
{"current_steps": 140, "total_steps": 4768, "loss": 0.4311, "lr": 9.979044729603136e-06, "epoch": 0.0587248322147651, "percentage": 2.94, "elapsed_time": "0:13:18", "remaining_time": "7:19:43", "throughput": 9544.69, "total_tokens": 7617792}
{"current_steps": 145, "total_steps": 4768, "loss": 0.4679, "lr": 9.977511193007896e-06, "epoch": 0.060822147651006714, "percentage": 3.04, "elapsed_time": "0:13:50", "remaining_time": "7:21:21", "throughput": 9493.13, "total_tokens": 7884768}
{"current_steps": 150, "total_steps": 4768, "loss": 0.3999, "lr": 9.975923633360985e-06, "epoch": 0.06291946308724833, "percentage": 3.15, "elapsed_time": "0:14:17", "remaining_time": "7:20:02", "throughput": 9485.24, "total_tokens": 8134416}
{"current_steps": 155, "total_steps": 4768, "loss": 0.4406, "lr": 9.974282067892867e-06, "epoch": 0.06501677852348993, "percentage": 3.25, "elapsed_time": "0:14:43", "remaining_time": "7:17:59", "throughput": 9525.09, "total_tokens": 8410704}
{"current_steps": 160, "total_steps": 4768, "loss": 0.48, "lr": 9.972586514420148e-06, "epoch": 0.06711409395973154, "percentage": 3.36, "elapsed_time": "0:15:16", "remaining_time": "7:20:09", "throughput": 9454.03, "total_tokens": 8669152}
{"current_steps": 165, "total_steps": 4768, "loss": 0.4468, "lr": 9.970836991345398e-06, "epoch": 0.06921140939597316, "percentage": 3.46, "elapsed_time": "0:15:49", "remaining_time": "7:21:19", "throughput": 9426.1, "total_tokens": 8947264}
{"current_steps": 170, "total_steps": 4768, "loss": 0.4367, "lr": 9.969033517656933e-06, "epoch": 0.07130872483221476, "percentage": 3.57, "elapsed_time": "0:16:14", "remaining_time": "7:19:12", "throughput": 9484.92, "total_tokens": 9241264}
{"current_steps": 175, "total_steps": 4768, "loss": 0.4574, "lr": 9.967176112928622e-06, "epoch": 0.07340604026845637, "percentage": 3.67, "elapsed_time": "0:16:45", "remaining_time": "7:19:41", "throughput": 9476.7, "total_tokens": 9525624}
{"current_steps": 180, "total_steps": 4768, "loss": 0.4566, "lr": 9.965264797319675e-06, "epoch": 0.07550335570469799, "percentage": 3.78, "elapsed_time": "0:17:10", "remaining_time": "7:17:55", "throughput": 9525.12, "total_tokens": 9819112}
{"current_steps": 185, "total_steps": 4768, "loss": 0.4323, "lr": 9.963299591574411e-06, "epoch": 0.0776006711409396, "percentage": 3.88, "elapsed_time": "0:17:44", "remaining_time": "7:19:42", "throughput": 9477.42, "total_tokens": 10093360}
{"current_steps": 190, "total_steps": 4768, "loss": 0.4426, "lr": 9.961280517022048e-06, "epoch": 0.0796979865771812, "percentage": 3.98, "elapsed_time": "0:18:15", "remaining_time": "7:19:51", "throughput": 9446.57, "total_tokens": 10346968}
{"current_steps": 195, "total_steps": 4768, "loss": 0.4296, "lr": 9.959207595576464e-06, "epoch": 0.08179530201342282, "percentage": 4.09, "elapsed_time": "0:18:42", "remaining_time": "7:18:34", "throughput": 9444.29, "total_tokens": 10597208}
{"current_steps": 200, "total_steps": 4768, "loss": 0.4317, "lr": 9.957080849735955e-06, "epoch": 0.08389261744966443, "percentage": 4.19, "elapsed_time": "0:19:11", "remaining_time": "7:18:26", "throughput": 9429.15, "total_tokens": 10860136}
{"current_steps": 205, "total_steps": 4768, "loss": 0.4608, "lr": 9.954900302583007e-06, "epoch": 0.08598993288590603, "percentage": 4.3, "elapsed_time": "0:19:37", "remaining_time": "7:16:44", "throughput": 9457.41, "total_tokens": 11133816}
{"current_steps": 210, "total_steps": 4768, "loss": 0.3996, "lr": 9.952665977784022e-06, "epoch": 0.08808724832214765, "percentage": 4.4, "elapsed_time": "0:20:07", "remaining_time": "7:16:45", "throughput": 9453.69, "total_tokens": 11413952}
{"current_steps": 215, "total_steps": 4768, "loss": 0.4334, "lr": 9.950377899589083e-06, "epoch": 0.09018456375838926, "percentage": 4.51, "elapsed_time": "0:20:27", "remaining_time": "7:13:07", "throughput": 9537.69, "total_tokens": 11704272}
{"current_steps": 220, "total_steps": 4768, "loss": 0.4211, "lr": 9.948036092831679e-06, "epoch": 0.09228187919463088, "percentage": 4.61, "elapsed_time": "0:21:01", "remaining_time": "7:14:39", "throughput": 9491.77, "total_tokens": 11974192}
{"current_steps": 225, "total_steps": 4768, "loss": 0.4205, "lr": 9.945640582928438e-06, "epoch": 0.09437919463087248, "percentage": 4.72, "elapsed_time": "0:21:29", "remaining_time": "7:13:57", "throughput": 9502.8, "total_tokens": 12254464}
{"current_steps": 230, "total_steps": 4768, "loss": 0.4442, "lr": 9.943191395878848e-06, "epoch": 0.0964765100671141, "percentage": 4.82, "elapsed_time": "0:21:57", "remaining_time": "7:13:22", "throughput": 9517.22, "total_tokens": 12542824}
{"current_steps": 235, "total_steps": 4768, "loss": 0.4534, "lr": 9.940688558264982e-06, "epoch": 0.09857382550335571, "percentage": 4.93, "elapsed_time": "0:22:28", "remaining_time": "7:13:37", "throughput": 9511.87, "total_tokens": 12829488}
{"current_steps": 240, "total_steps": 4768, "loss": 0.4379, "lr": 9.938132097251202e-06, "epoch": 0.10067114093959731, "percentage": 5.03, "elapsed_time": "0:22:59", "remaining_time": "7:13:49", "throughput": 9498.62, "total_tokens": 13104904}
{"current_steps": 245, "total_steps": 4768, "loss": 0.442, "lr": 9.935522040583871e-06, "epoch": 0.10276845637583892, "percentage": 5.14, "elapsed_time": "0:23:33", "remaining_time": "7:14:53", "throughput": 9469.89, "total_tokens": 13385128}
{"current_steps": 250, "total_steps": 4768, "loss": 0.4123, "lr": 9.93285841659105e-06, "epoch": 0.10486577181208054, "percentage": 5.24, "elapsed_time": "0:23:59", "remaining_time": "7:13:26", "throughput": 9470.65, "total_tokens": 13628968}
{"current_steps": 255, "total_steps": 4768, "loss": 0.4254, "lr": 9.930141254182182e-06, "epoch": 0.10696308724832215, "percentage": 5.35, "elapsed_time": "0:24:26", "remaining_time": "7:12:31", "throughput": 9491.74, "total_tokens": 13917968}
{"current_steps": 260, "total_steps": 4768, "loss": 0.4171, "lr": 9.927370582847791e-06, "epoch": 0.10906040268456375, "percentage": 5.45, "elapsed_time": "0:24:49", "remaining_time": "7:10:32", "throughput": 9523.15, "total_tokens": 14188760}
{"current_steps": 265, "total_steps": 4768, "loss": 0.4383, "lr": 9.924546432659155e-06, "epoch": 0.11115771812080537, "percentage": 5.56, "elapsed_time": "0:25:17", "remaining_time": "7:09:49", "throughput": 9526.79, "total_tokens": 14458952}
{"current_steps": 270, "total_steps": 4768, "loss": 0.4185, "lr": 9.921668834267979e-06, "epoch": 0.11325503355704698, "percentage": 5.66, "elapsed_time": "0:25:49", "remaining_time": "7:10:07", "throughput": 9503.14, "total_tokens": 14721776}
{"current_steps": 275, "total_steps": 4768, "loss": 0.4147, "lr": 9.918737818906066e-06, "epoch": 0.11535234899328858, "percentage": 5.77, "elapsed_time": "0:26:15", "remaining_time": "7:09:05", "throughput": 9525.88, "total_tokens": 15010920}
{"current_steps": 280, "total_steps": 4768, "loss": 0.4209, "lr": 9.915753418384978e-06, "epoch": 0.1174496644295302, "percentage": 5.87, "elapsed_time": "0:26:43", "remaining_time": "7:08:16", "throughput": 9541.27, "total_tokens": 15296360}
{"current_steps": 285, "total_steps": 4768, "loss": 0.428, "lr": 9.912715665095683e-06, "epoch": 0.11954697986577181, "percentage": 5.98, "elapsed_time": "0:27:10", "remaining_time": "7:07:33", "throughput": 9557.0, "total_tokens": 15586088}
{"current_steps": 290, "total_steps": 4768, "loss": 0.4118, "lr": 9.909624592008213e-06, "epoch": 0.12164429530201343, "percentage": 6.08, "elapsed_time": "0:27:40", "remaining_time": "7:07:15", "throughput": 9578.36, "total_tokens": 15901872}
{"current_steps": 295, "total_steps": 4768, "loss": 0.4247, "lr": 9.906480232671305e-06, "epoch": 0.12374161073825503, "percentage": 6.19, "elapsed_time": "0:28:06", "remaining_time": "7:06:14", "throughput": 9591.72, "total_tokens": 16178168}
{"current_steps": 300, "total_steps": 4768, "loss": 0.4485, "lr": 9.903282621212032e-06, "epoch": 0.12583892617449666, "percentage": 6.29, "elapsed_time": "0:28:37", "remaining_time": "7:06:13", "throughput": 9573.92, "total_tokens": 16439584}
{"current_steps": 305, "total_steps": 4768, "loss": 0.4185, "lr": 9.900031792335432e-06, "epoch": 0.12793624161073824, "percentage": 6.4, "elapsed_time": "0:28:58", "remaining_time": "7:04:03", "throughput": 9619.06, "total_tokens": 16725632}
{"current_steps": 310, "total_steps": 4768, "loss": 0.3945, "lr": 9.896727781324138e-06, "epoch": 0.13003355704697986, "percentage": 6.5, "elapsed_time": "0:29:32", "remaining_time": "7:04:45", "throughput": 9593.5, "total_tokens": 17001792}
{"current_steps": 315, "total_steps": 4768, "loss": 0.4561, "lr": 9.893370624037992e-06, "epoch": 0.13213087248322147, "percentage": 6.61, "elapsed_time": "0:30:00", "remaining_time": "7:04:12", "throughput": 9602.76, "total_tokens": 17289624}
{"current_steps": 320, "total_steps": 4768, "loss": 0.416, "lr": 9.889960356913654e-06, "epoch": 0.1342281879194631, "percentage": 6.71, "elapsed_time": "0:30:25", "remaining_time": "7:02:49", "throughput": 9608.82, "total_tokens": 17537824}
{"current_steps": 325, "total_steps": 4768, "loss": 0.452, "lr": 9.886497016964204e-06, "epoch": 0.1363255033557047, "percentage": 6.82, "elapsed_time": "0:30:52", "remaining_time": "7:02:01", "throughput": 9621.21, "total_tokens": 17820448}
{"current_steps": 330, "total_steps": 4768, "loss": 0.454, "lr": 9.882980641778752e-06, "epoch": 0.13842281879194632, "percentage": 6.92, "elapsed_time": "0:31:21", "remaining_time": "7:01:49", "throughput": 9616.26, "total_tokens": 18097568}
{"current_steps": 335, "total_steps": 4768, "loss": 0.3719, "lr": 9.879411269522015e-06, "epoch": 0.14052013422818793, "percentage": 7.03, "elapsed_time": "0:31:56", "remaining_time": "7:02:34", "throughput": 9589.38, "total_tokens": 18373568}
{"current_steps": 340, "total_steps": 4768, "loss": 0.3836, "lr": 9.875788938933911e-06, "epoch": 0.14261744966442952, "percentage": 7.13, "elapsed_time": "0:32:20", "remaining_time": "7:01:06", "throughput": 9620.73, "total_tokens": 18664920}
{"current_steps": 345, "total_steps": 4768, "loss": 0.4396, "lr": 9.872113689329142e-06, "epoch": 0.14471476510067113, "percentage": 7.24, "elapsed_time": "0:32:48", "remaining_time": "7:00:40", "throughput": 9619.46, "total_tokens": 18938760}
{"current_steps": 350, "total_steps": 4768, "loss": 0.4202, "lr": 9.868385560596756e-06, "epoch": 0.14681208053691275, "percentage": 7.34, "elapsed_time": "0:33:15", "remaining_time": "6:59:52", "throughput": 9611.87, "total_tokens": 19183256}
{"current_steps": 355, "total_steps": 4768, "loss": 0.4278, "lr": 9.864604593199724e-06, "epoch": 0.14890939597315436, "percentage": 7.45, "elapsed_time": "0:33:39", "remaining_time": "6:58:24", "throughput": 9636.0, "total_tokens": 19459744}
{"current_steps": 360, "total_steps": 4768, "loss": 0.4049, "lr": 9.860770828174502e-06, "epoch": 0.15100671140939598, "percentage": 7.55, "elapsed_time": "0:34:12", "remaining_time": "6:58:50", "throughput": 9613.95, "total_tokens": 19731560}
{"current_steps": 365, "total_steps": 4768, "loss": 0.4084, "lr": 9.856884307130572e-06, "epoch": 0.1531040268456376, "percentage": 7.66, "elapsed_time": "0:34:44", "remaining_time": "6:59:00", "throughput": 9609.43, "total_tokens": 20027032}
{"current_steps": 370, "total_steps": 4768, "loss": 0.401, "lr": 9.852945072250006e-06, "epoch": 0.1552013422818792, "percentage": 7.76, "elapsed_time": "0:35:12", "remaining_time": "6:58:31", "throughput": 9603.74, "total_tokens": 20289072}
{"current_steps": 375, "total_steps": 4768, "loss": 0.4247, "lr": 9.848953166287003e-06, "epoch": 0.1572986577181208, "percentage": 7.86, "elapsed_time": "0:35:40", "remaining_time": "6:57:56", "throughput": 9610.82, "total_tokens": 20572928}
{"current_steps": 380, "total_steps": 4768, "loss": 0.4186, "lr": 9.844908632567415e-06, "epoch": 0.1593959731543624, "percentage": 7.97, "elapsed_time": "0:36:17", "remaining_time": "6:59:01", "throughput": 9578.88, "total_tokens": 20855840}
{"current_steps": 385, "total_steps": 4768, "loss": 0.4049, "lr": 9.840811514988294e-06, "epoch": 0.16149328859060402, "percentage": 8.07, "elapsed_time": "0:36:40", "remaining_time": "6:57:26", "throughput": 9611.34, "total_tokens": 21145488}
{"current_steps": 390, "total_steps": 4768, "loss": 0.4099, "lr": 9.836661858017406e-06, "epoch": 0.16359060402684564, "percentage": 8.18, "elapsed_time": "0:37:12", "remaining_time": "6:57:39", "throughput": 9589.28, "total_tokens": 21406184}
{"current_steps": 395, "total_steps": 4768, "loss": 0.3998, "lr": 9.832459706692745e-06, "epoch": 0.16568791946308725, "percentage": 8.28, "elapsed_time": "0:37:40", "remaining_time": "6:57:03", "throughput": 9596.15, "total_tokens": 21690352}
{"current_steps": 400, "total_steps": 4768, "loss": 0.4086, "lr": 9.828205106622055e-06, "epoch": 0.16778523489932887, "percentage": 8.39, "elapsed_time": "0:38:07", "remaining_time": "6:56:17", "throughput": 9604.48, "total_tokens": 21968760}
{"current_steps": 405, "total_steps": 4768, "loss": 0.4277, "lr": 9.82389810398232e-06, "epoch": 0.16988255033557048, "percentage": 8.49, "elapsed_time": "0:38:37", "remaining_time": "6:56:03", "throughput": 9599.65, "total_tokens": 22244792}
{"current_steps": 410, "total_steps": 4768, "loss": 0.3891, "lr": 9.819538745519281e-06, "epoch": 0.17197986577181207, "percentage": 8.6, "elapsed_time": "0:39:12", "remaining_time": "6:56:48", "throughput": 9573.79, "total_tokens": 22525216}
{"current_steps": 415, "total_steps": 4768, "loss": 0.4081, "lr": 9.815127078546911e-06, "epoch": 0.17407718120805368, "percentage": 8.7, "elapsed_time": "0:39:41", "remaining_time": "6:56:15", "throughput": 9570.87, "total_tokens": 22788904}
{"current_steps": 420, "total_steps": 4768, "loss": 0.4335, "lr": 9.810663150946915e-06, "epoch": 0.1761744966442953, "percentage": 8.81, "elapsed_time": "0:40:02", "remaining_time": "6:54:30", "throughput": 9596.76, "total_tokens": 23054832}
{"current_steps": 425, "total_steps": 4768, "loss": 0.3992, "lr": 9.806147011168203e-06, "epoch": 0.1782718120805369, "percentage": 8.91, "elapsed_time": "0:40:23", "remaining_time": "6:52:49", "throughput": 9632.94, "total_tokens": 23349128}
{"current_steps": 430, "total_steps": 4768, "loss": 0.4017, "lr": 9.801578708226366e-06, "epoch": 0.18036912751677853, "percentage": 9.02, "elapsed_time": "0:40:57", "remaining_time": "6:53:07", "throughput": 9619.69, "total_tokens": 23636024}
{"current_steps": 435, "total_steps": 4768, "loss": 0.4045, "lr": 9.796958291703142e-06, "epoch": 0.18246644295302014, "percentage": 9.12, "elapsed_time": "0:41:30", "remaining_time": "6:53:29", "throughput": 9593.47, "total_tokens": 23894616}
{"current_steps": 440, "total_steps": 4768, "loss": 0.3978, "lr": 9.792285811745883e-06, "epoch": 0.18456375838926176, "percentage": 9.23, "elapsed_time": "0:42:03", "remaining_time": "6:53:44", "throughput": 9584.66, "total_tokens": 24189024}
{"current_steps": 445, "total_steps": 4768, "loss": 0.4146, "lr": 9.787561319067009e-06, "epoch": 0.18666107382550334, "percentage": 9.33, "elapsed_time": "0:42:28", "remaining_time": "6:52:41", "throughput": 9605.68, "total_tokens": 24484136}
{"current_steps": 450, "total_steps": 4768, "loss": 0.4394, "lr": 9.78278486494345e-06, "epoch": 0.18875838926174496, "percentage": 9.44, "elapsed_time": "0:42:56", "remaining_time": "6:52:00", "throughput": 9618.97, "total_tokens": 24780424}
{"current_steps": 455, "total_steps": 4768, "loss": 0.416, "lr": 9.777956501216103e-06, "epoch": 0.19085570469798657, "percentage": 9.54, "elapsed_time": "0:43:25", "remaining_time": "6:51:41", "throughput": 9609.56, "total_tokens": 25040968}
{"current_steps": 460, "total_steps": 4768, "loss": 0.4154, "lr": 9.773076280289256e-06, "epoch": 0.1929530201342282, "percentage": 9.65, "elapsed_time": "0:44:00", "remaining_time": "6:52:09", "throughput": 9586.46, "total_tokens": 25313472}
{"current_steps": 465, "total_steps": 4768, "loss": 0.4132, "lr": 9.76814425513003e-06, "epoch": 0.1950503355704698, "percentage": 9.75, "elapsed_time": "0:44:24", "remaining_time": "6:50:55", "throughput": 9609.96, "total_tokens": 25604248}
{"current_steps": 470, "total_steps": 4768, "loss": 0.4001, "lr": 9.763160479267795e-06, "epoch": 0.19714765100671142, "percentage": 9.86, "elapsed_time": "0:44:48", "remaining_time": "6:49:43", "throughput": 9625.34, "total_tokens": 25875224}
{"current_steps": 475, "total_steps": 4768, "loss": 0.4267, "lr": 9.758125006793596e-06, "epoch": 0.19924496644295303, "percentage": 9.96, "elapsed_time": "0:45:19", "remaining_time": "6:49:37", "throughput": 9616.03, "total_tokens": 26149984}
{"current_steps": 480, "total_steps": 4768, "loss": 0.4159, "lr": 9.753037892359565e-06, "epoch": 0.20134228187919462, "percentage": 10.07, "elapsed_time": "0:45:49", "remaining_time": "6:49:22", "throughput": 9617.99, "total_tokens": 26445456}
{"current_steps": 485, "total_steps": 4768, "loss": 0.3864, "lr": 9.747899191178325e-06, "epoch": 0.20343959731543623, "percentage": 10.17, "elapsed_time": "0:46:15", "remaining_time": "6:48:32", "throughput": 9620.39, "total_tokens": 26703632}
{"current_steps": 490, "total_steps": 4768, "loss": 0.3972, "lr": 9.74270895902239e-06, "epoch": 0.20553691275167785, "percentage": 10.28, "elapsed_time": "0:46:47", "remaining_time": "6:48:32", "throughput": 9604.83, "total_tokens": 26966632}
{"current_steps": 495, "total_steps": 4768, "loss": 0.3849, "lr": 9.73746725222356e-06, "epoch": 0.20763422818791946, "percentage": 10.38, "elapsed_time": "0:47:12", "remaining_time": "6:47:30", "throughput": 9620.23, "total_tokens": 27248856}
{"current_steps": 500, "total_steps": 4768, "loss": 0.3966, "lr": 9.732174127672321e-06, "epoch": 0.20973154362416108, "percentage": 10.49, "elapsed_time": "0:47:38", "remaining_time": "6:46:42", "throughput": 9628.43, "total_tokens": 27525360}
{"current_steps": 505, "total_steps": 4768, "loss": 0.436, "lr": 9.726829642817204e-06, "epoch": 0.2118288590604027, "percentage": 10.59, "elapsed_time": "0:48:09", "remaining_time": "6:46:34", "throughput": 9622.14, "total_tokens": 27806120}
{"current_steps": 510, "total_steps": 4768, "loss": 0.4075, "lr": 9.721433855664186e-06, "epoch": 0.2139261744966443, "percentage": 10.7, "elapsed_time": "0:48:40", "remaining_time": "6:46:27", "throughput": 9613.78, "total_tokens": 28081744}
{"current_steps": 515, "total_steps": 4768, "loss": 0.3956, "lr": 9.715986824776047e-06, "epoch": 0.2160234899328859, "percentage": 10.8, "elapsed_time": "0:49:06", "remaining_time": "6:45:36", "throughput": 9633.81, "total_tokens": 28390080}
{"current_steps": 520, "total_steps": 4768, "loss": 0.381, "lr": 9.710488609271734e-06, "epoch": 0.2181208053691275, "percentage": 10.91, "elapsed_time": "0:49:40", "remaining_time": "6:45:51", "throughput": 9620.27, "total_tokens": 28676720}
{"current_steps": 525, "total_steps": 4768, "loss": 0.3985, "lr": 9.704939268825726e-06, "epoch": 0.22021812080536912, "percentage": 11.01, "elapsed_time": "0:50:07", "remaining_time": "6:45:09", "throughput": 9625.59, "total_tokens": 28952552}
{"current_steps": 530, "total_steps": 4768, "loss": 0.398, "lr": 9.69933886366738e-06, "epoch": 0.22231543624161074, "percentage": 11.12, "elapsed_time": "0:50:28", "remaining_time": "6:43:37", "throughput": 9649.88, "total_tokens": 29225608}
{"current_steps": 535, "total_steps": 4768, "loss": 0.3996, "lr": 9.693687454580283e-06, "epoch": 0.22441275167785235, "percentage": 11.22, "elapsed_time": "0:50:56", "remaining_time": "6:42:59", "throughput": 9653.08, "total_tokens": 29500056}
{"current_steps": 540, "total_steps": 4768, "loss": 0.4183, "lr": 9.687985102901588e-06, "epoch": 0.22651006711409397, "percentage": 11.33, "elapsed_time": "0:51:25", "remaining_time": "6:42:37", "throughput": 9659.39, "total_tokens": 29803616}
{"current_steps": 545, "total_steps": 4768, "loss": 0.4198, "lr": 9.682231870521347e-06, "epoch": 0.22860738255033558, "percentage": 11.43, "elapsed_time": "0:51:52", "remaining_time": "6:41:57", "throughput": 9670.76, "total_tokens": 30099616}
{"current_steps": 550, "total_steps": 4768, "loss": 0.3944, "lr": 9.676427819881846e-06, "epoch": 0.23070469798657717, "percentage": 11.54, "elapsed_time": "0:52:21", "remaining_time": "6:41:34", "throughput": 9660.67, "total_tokens": 30351744}
{"current_steps": 555, "total_steps": 4768, "loss": 0.3805, "lr": 9.670573013976924e-06, "epoch": 0.23280201342281878, "percentage": 11.64, "elapsed_time": "0:52:53", "remaining_time": "6:41:26", "throughput": 9652.9, "total_tokens": 30629064}
{"current_steps": 560, "total_steps": 4768, "loss": 0.3994, "lr": 9.664667516351282e-06, "epoch": 0.2348993288590604, "percentage": 11.74, "elapsed_time": "0:53:24", "remaining_time": "6:41:18", "throughput": 9646.2, "total_tokens": 30909904}
{"current_steps": 565, "total_steps": 4768, "loss": 0.3971, "lr": 9.65871139109981e-06, "epoch": 0.236996644295302, "percentage": 11.85, "elapsed_time": "0:53:48", "remaining_time": "6:40:19", "throughput": 9663.18, "total_tokens": 31200880}
{"current_steps": 570, "total_steps": 4768, "loss": 0.412, "lr": 9.652704702866868e-06, "epoch": 0.23909395973154363, "percentage": 11.95, "elapsed_time": "0:54:10", "remaining_time": "6:38:57", "throughput": 9673.75, "total_tokens": 31442088}
{"current_steps": 575, "total_steps": 4768, "loss": 0.4325, "lr": 9.646647516845612e-06, "epoch": 0.24119127516778524, "percentage": 12.06, "elapsed_time": "0:54:39", "remaining_time": "6:38:36", "throughput": 9678.59, "total_tokens": 31743640}
{"current_steps": 580, "total_steps": 4768, "loss": 0.4311, "lr": 9.64053989877726e-06, "epoch": 0.24328859060402686, "percentage": 12.16, "elapsed_time": "0:55:06", "remaining_time": "6:37:57", "throughput": 9685.26, "total_tokens": 32028000}
{"current_steps": 585, "total_steps": 4768, "loss": 0.3939, "lr": 9.634381914950399e-06, "epoch": 0.24538590604026847, "percentage": 12.27, "elapsed_time": "0:55:41", "remaining_time": "6:38:11", "throughput": 9668.79, "total_tokens": 32306576}
{"current_steps": 590, "total_steps": 4768, "loss": 0.389, "lr": 9.62817363220025e-06, "epoch": 0.24748322147651006, "percentage": 12.37, "elapsed_time": "0:56:05", "remaining_time": "6:37:09", "throughput": 9668.57, "total_tokens": 32535072}
{"current_steps": 595, "total_steps": 4768, "loss": 0.3778, "lr": 9.621915117907956e-06, "epoch": 0.24958053691275167, "percentage": 12.48, "elapsed_time": "0:56:39", "remaining_time": "6:37:25", "throughput": 9651.62, "total_tokens": 32815176}
{"current_steps": 600, "total_steps": 4768, "loss": 0.3886, "lr": 9.615606439999843e-06, "epoch": 0.2516778523489933, "percentage": 12.58, "elapsed_time": "0:57:08", "remaining_time": "6:36:56", "throughput": 9658.38, "total_tokens": 33114040}
{"current_steps": 605, "total_steps": 4768, "loss": 0.4092, "lr": 9.60924766694668e-06, "epoch": 0.2537751677852349, "percentage": 12.69, "elapsed_time": "0:57:40", "remaining_time": "6:36:53", "throughput": 9643.99, "total_tokens": 33376096}
{"current_steps": 610, "total_steps": 4768, "loss": 0.4228, "lr": 9.602838867762941e-06, "epoch": 0.2558724832214765, "percentage": 12.79, "elapsed_time": "0:58:09", "remaining_time": "6:36:23", "throughput": 9641.93, "total_tokens": 33642840}
{"current_steps": 615, "total_steps": 4768, "loss": 0.4072, "lr": 9.59638011200606e-06, "epoch": 0.25796979865771813, "percentage": 12.9, "elapsed_time": "0:58:33", "remaining_time": "6:35:25", "throughput": 9648.34, "total_tokens": 33898736}
{"current_steps": 620, "total_steps": 4768, "loss": 0.3962, "lr": 9.589871469775667e-06, "epoch": 0.2600671140939597, "percentage": 13.0, "elapsed_time": "0:59:03", "remaining_time": "6:35:04", "throughput": 9638.93, "total_tokens": 34151760}
{"current_steps": 625, "total_steps": 4768, "loss": 0.4172, "lr": 9.583313011712832e-06, "epoch": 0.26216442953020136, "percentage": 13.11, "elapsed_time": "0:59:31", "remaining_time": "6:34:37", "throughput": 9632.49, "total_tokens": 34406504}
{"current_steps": 630, "total_steps": 4768, "loss": 0.3887, "lr": 9.576704808999295e-06, "epoch": 0.26426174496644295, "percentage": 13.21, "elapsed_time": "0:59:58", "remaining_time": "6:33:57", "throughput": 9631.78, "total_tokens": 34662216}
{"current_steps": 635, "total_steps": 4768, "loss": 0.3773, "lr": 9.5700469333567e-06, "epoch": 0.2663590604026846, "percentage": 13.32, "elapsed_time": "1:00:31", "remaining_time": "6:33:58", "throughput": 9621.66, "total_tokens": 34944128}
{"current_steps": 640, "total_steps": 4768, "loss": 0.3859, "lr": 9.56333945704581e-06, "epoch": 0.2684563758389262, "percentage": 13.42, "elapsed_time": "1:01:00", "remaining_time": "6:33:33", "throughput": 9614.19, "total_tokens": 35197296}
{"current_steps": 645, "total_steps": 4768, "loss": 0.4082, "lr": 9.556582452865728e-06, "epoch": 0.27055369127516776, "percentage": 13.53, "elapsed_time": "1:01:33", "remaining_time": "6:33:26", "throughput": 9607.09, "total_tokens": 35479312}
{"current_steps": 650, "total_steps": 4768, "loss": 0.4143, "lr": 9.549775994153098e-06, "epoch": 0.2726510067114094, "percentage": 13.63, "elapsed_time": "1:01:58", "remaining_time": "6:32:40", "throughput": 9612.87, "total_tokens": 35748560}
{"current_steps": 655, "total_steps": 4768, "loss": 0.3763, "lr": 9.542920154781323e-06, "epoch": 0.274748322147651, "percentage": 13.74, "elapsed_time": "1:02:23", "remaining_time": "6:31:48", "throughput": 9619.3, "total_tokens": 36011616}
{"current_steps": 660, "total_steps": 4768, "loss": 0.3824, "lr": 9.536015009159749e-06, "epoch": 0.27684563758389263, "percentage": 13.84, "elapsed_time": "1:02:52", "remaining_time": "6:31:20", "throughput": 9619.86, "total_tokens": 36289696}
{"current_steps": 665, "total_steps": 4768, "loss": 0.3862, "lr": 9.529060632232867e-06, "epoch": 0.2789429530201342, "percentage": 13.95, "elapsed_time": "1:03:24", "remaining_time": "6:31:10", "throughput": 9610.52, "total_tokens": 36559104}
{"current_steps": 670, "total_steps": 4768, "loss": 0.3682, "lr": 9.522057099479495e-06, "epoch": 0.28104026845637586, "percentage": 14.05, "elapsed_time": "1:03:49", "remaining_time": "6:30:20", "throughput": 9616.35, "total_tokens": 36821376}
{"current_steps": 675, "total_steps": 4768, "loss": 0.3991, "lr": 9.51500448691196e-06, "epoch": 0.28313758389261745, "percentage": 14.16, "elapsed_time": "1:04:22", "remaining_time": "6:30:18", "throughput": 9608.28, "total_tokens": 37108256}
{"current_steps": 680, "total_steps": 4768, "loss": 0.4353, "lr": 9.507902871075278e-06, "epoch": 0.28523489932885904, "percentage": 14.26, "elapsed_time": "1:04:50", "remaining_time": "6:29:46", "throughput": 9609.45, "total_tokens": 37382456}
{"current_steps": 685, "total_steps": 4768, "loss": 0.3922, "lr": 9.500752329046307e-06, "epoch": 0.2873322147651007, "percentage": 14.37, "elapsed_time": "1:05:23", "remaining_time": "6:29:47", "throughput": 9601.12, "total_tokens": 37672400}
{"current_steps": 690, "total_steps": 4768, "loss": 0.3967, "lr": 9.493552938432937e-06, "epoch": 0.28942953020134227, "percentage": 14.47, "elapsed_time": "1:05:53", "remaining_time": "6:29:26", "throughput": 9599.37, "total_tokens": 37952152}
{"current_steps": 695, "total_steps": 4768, "loss": 0.3978, "lr": 9.486304777373219e-06, "epoch": 0.2915268456375839, "percentage": 14.58, "elapsed_time": "1:06:24", "remaining_time": "6:29:13", "throughput": 9591.58, "total_tokens": 38222352}
{"current_steps": 700, "total_steps": 4768, "loss": 0.3999, "lr": 9.479007924534537e-06, "epoch": 0.2936241610738255, "percentage": 14.68, "elapsed_time": "1:06:55", "remaining_time": "6:28:56", "throughput": 9588.34, "total_tokens": 38503200}
{"current_steps": 705, "total_steps": 4768, "loss": 0.4023, "lr": 9.471662459112747e-06, "epoch": 0.29572147651006714, "percentage": 14.79, "elapsed_time": "1:07:18", "remaining_time": "6:27:55", "throughput": 9602.89, "total_tokens": 38783440}
{"current_steps": 710, "total_steps": 4768, "loss": 0.3711, "lr": 9.464268460831318e-06, "epoch": 0.2978187919463087, "percentage": 14.89, "elapsed_time": "1:07:47", "remaining_time": "6:27:28", "throughput": 9607.95, "total_tokens": 39080848}
{"current_steps": 715, "total_steps": 4768, "loss": 0.3884, "lr": 9.456826009940469e-06, "epoch": 0.2999161073825503, "percentage": 15.0, "elapsed_time": "1:08:13", "remaining_time": "6:26:42", "throughput": 9617.2, "total_tokens": 39364744}
{"current_steps": 720, "total_steps": 4768, "loss": 0.3964, "lr": 9.44933518721629e-06, "epoch": 0.30201342281879195, "percentage": 15.1, "elapsed_time": "1:08:43", "remaining_time": "6:26:22", "throughput": 9616.78, "total_tokens": 39654184}
{"current_steps": 725, "total_steps": 4768, "loss": 0.3923, "lr": 9.441796073959875e-06, "epoch": 0.30411073825503354, "percentage": 15.21, "elapsed_time": "1:09:13", "remaining_time": "6:26:02", "throughput": 9609.57, "total_tokens": 39914496}
{"current_steps": 730, "total_steps": 4768, "loss": 0.3904, "lr": 9.434208751996434e-06, "epoch": 0.3062080536912752, "percentage": 15.31, "elapsed_time": "1:09:44", "remaining_time": "6:25:45", "throughput": 9607.91, "total_tokens": 40201888}
{"current_steps": 735, "total_steps": 4768, "loss": 0.3883, "lr": 9.426573303674412e-06, "epoch": 0.30830536912751677, "percentage": 15.42, "elapsed_time": "1:10:11", "remaining_time": "6:25:10", "throughput": 9612.71, "total_tokens": 40486104}
{"current_steps": 740, "total_steps": 4768, "loss": 0.4092, "lr": 9.418889811864584e-06, "epoch": 0.3104026845637584, "percentage": 15.52, "elapsed_time": "1:10:40", "remaining_time": "6:24:40", "throughput": 9606.03, "total_tokens": 40731112}
{"current_steps": 745, "total_steps": 4768, "loss": 0.3974, "lr": 9.41115835995916e-06, "epoch": 0.3125, "percentage": 15.62, "elapsed_time": "1:11:02", "remaining_time": "6:23:35", "throughput": 9623.41, "total_tokens": 41016992}
{"current_steps": 750, "total_steps": 4768, "loss": 0.4142, "lr": 9.40337903187089e-06, "epoch": 0.3145973154362416, "percentage": 15.73, "elapsed_time": "1:11:27", "remaining_time": "6:22:48", "throughput": 9633.06, "total_tokens": 41300392}
{"current_steps": 755, "total_steps": 4768, "loss": 0.4137, "lr": 9.395551912032138e-06, "epoch": 0.31669463087248323, "percentage": 15.83, "elapsed_time": "1:11:50", "remaining_time": "6:21:52", "throughput": 9643.28, "total_tokens": 41569272}
{"current_steps": 760, "total_steps": 4768, "loss": 0.4008, "lr": 9.387677085393969e-06, "epoch": 0.3187919463087248, "percentage": 15.94, "elapsed_time": "1:12:16", "remaining_time": "6:21:07", "throughput": 9643.89, "total_tokens": 41817352}
{"current_steps": 765, "total_steps": 4768, "loss": 0.4096, "lr": 9.37975463742524e-06, "epoch": 0.32088926174496646, "percentage": 16.04, "elapsed_time": "1:12:43", "remaining_time": "6:20:30", "throughput": 9646.17, "total_tokens": 42087160}
{"current_steps": 770, "total_steps": 4768, "loss": 0.4045, "lr": 9.371784654111656e-06, "epoch": 0.32298657718120805, "percentage": 16.15, "elapsed_time": "1:13:08", "remaining_time": "6:19:45", "throughput": 9652.33, "total_tokens": 42358792}
{"current_steps": 775, "total_steps": 4768, "loss": 0.4043, "lr": 9.363767221954843e-06, "epoch": 0.3250838926174497, "percentage": 16.25, "elapsed_time": "1:13:33", "remaining_time": "6:19:01", "throughput": 9659.66, "total_tokens": 42636032}
{"current_steps": 780, "total_steps": 4768, "loss": 0.3542, "lr": 9.355702427971414e-06, "epoch": 0.3271812080536913, "percentage": 16.36, "elapsed_time": "1:14:02", "remaining_time": "6:18:34", "throughput": 9655.36, "total_tokens": 42896064}
{"current_steps": 785, "total_steps": 4768, "loss": 0.38, "lr": 9.347590359692015e-06, "epoch": 0.32927852348993286, "percentage": 16.46, "elapsed_time": "1:14:33", "remaining_time": "6:18:16", "throughput": 9649.64, "total_tokens": 43165240}
{"current_steps": 790, "total_steps": 4768, "loss": 0.3709, "lr": 9.339431105160384e-06, "epoch": 0.3313758389261745, "percentage": 16.57, "elapsed_time": "1:15:03", "remaining_time": "6:17:57", "throughput": 9646.98, "total_tokens": 43445080}
{"current_steps": 795, "total_steps": 4768, "loss": 0.403, "lr": 9.331224752932388e-06, "epoch": 0.3334731543624161, "percentage": 16.67, "elapsed_time": "1:15:28", "remaining_time": "6:17:13", "throughput": 9657.01, "total_tokens": 43736112}
{"current_steps": 800, "total_steps": 4768, "loss": 0.3927, "lr": 9.32297139207507e-06, "epoch": 0.33557046979865773, "percentage": 16.78, "elapsed_time": "1:15:58", "remaining_time": "6:16:49", "throughput": 9655.36, "total_tokens": 44013560}
{"current_steps": 805, "total_steps": 4768, "loss": 0.4019, "lr": 9.314671112165675e-06, "epoch": 0.3376677852348993, "percentage": 16.88, "elapsed_time": "1:16:33", "remaining_time": "6:16:53", "throughput": 9640.36, "total_tokens": 44282976}
{"current_steps": 810, "total_steps": 4768, "loss": 0.3787, "lr": 9.306324003290677e-06, "epoch": 0.33976510067114096, "percentage": 16.99, "elapsed_time": "1:17:02", "remaining_time": "6:16:25", "throughput": 9639.17, "total_tokens": 44552888}
{"current_steps": 815, "total_steps": 4768, "loss": 0.3922, "lr": 9.297930156044812e-06, "epoch": 0.34186241610738255, "percentage": 17.09, "elapsed_time": "1:17:27", "remaining_time": "6:15:43", "throughput": 9643.87, "total_tokens": 44823976}
{"current_steps": 820, "total_steps": 4768, "loss": 0.3874, "lr": 9.289489661530082e-06, "epoch": 0.34395973154362414, "percentage": 17.2, "elapsed_time": "1:17:56", "remaining_time": "6:15:15", "throughput": 9648.18, "total_tokens": 45118848}
{"current_steps": 825, "total_steps": 4768, "loss": 0.3849, "lr": 9.281002611354775e-06, "epoch": 0.3460570469798658, "percentage": 17.3, "elapsed_time": "1:18:21", "remaining_time": "6:14:28", "throughput": 9656.89, "total_tokens": 45398128}
{"current_steps": 830, "total_steps": 4768, "loss": 0.4048, "lr": 9.272469097632465e-06, "epoch": 0.34815436241610737, "percentage": 17.41, "elapsed_time": "1:18:48", "remaining_time": "6:13:56", "throughput": 9662.29, "total_tokens": 45690872}
{"current_steps": 835, "total_steps": 4768, "loss": 0.3943, "lr": 9.263889212981015e-06, "epoch": 0.350251677852349, "percentage": 17.51, "elapsed_time": "1:19:19", "remaining_time": "6:13:40", "throughput": 9653.46, "total_tokens": 45949720}
{"current_steps": 840, "total_steps": 4768, "loss": 0.4044, "lr": 9.255263050521573e-06, "epoch": 0.3523489932885906, "percentage": 17.62, "elapsed_time": "1:19:48", "remaining_time": "6:13:12", "throughput": 9656.76, "total_tokens": 46242520}
{"current_steps": 845, "total_steps": 4768, "loss": 0.3808, "lr": 9.246590703877559e-06, "epoch": 0.35444630872483224, "percentage": 17.72, "elapsed_time": "1:20:15", "remaining_time": "6:12:38", "throughput": 9661.65, "total_tokens": 46530208}
{"current_steps": 850, "total_steps": 4768, "loss": 0.4045, "lr": 9.237872267173646e-06, "epoch": 0.3565436241610738, "percentage": 17.83, "elapsed_time": "1:20:42", "remaining_time": "6:11:59", "throughput": 9666.68, "total_tokens": 46807360}
{"current_steps": 855, "total_steps": 4768, "loss": 0.385, "lr": 9.229107835034751e-06, "epoch": 0.3586409395973154, "percentage": 17.93, "elapsed_time": "1:21:13", "remaining_time": "6:11:42", "throughput": 9659.3, "total_tokens": 47072240}
{"current_steps": 860, "total_steps": 4768, "loss": 0.3896, "lr": 9.220297502584992e-06, "epoch": 0.36073825503355705, "percentage": 18.04, "elapsed_time": "1:21:39", "remaining_time": "6:11:05", "throughput": 9664.5, "total_tokens": 47354896}
{"current_steps": 865, "total_steps": 4768, "loss": 0.3754, "lr": 9.211441365446661e-06, "epoch": 0.36283557046979864, "percentage": 18.14, "elapsed_time": "1:22:08", "remaining_time": "6:10:36", "throughput": 9666.55, "total_tokens": 47638696}
{"current_steps": 870, "total_steps": 4768, "loss": 0.3821, "lr": 9.202539519739195e-06, "epoch": 0.3649328859060403, "percentage": 18.25, "elapsed_time": "1:22:34", "remaining_time": "6:09:58", "throughput": 9671.47, "total_tokens": 47916672}
{"current_steps": 875, "total_steps": 4768, "loss": 0.3837, "lr": 9.19359206207812e-06, "epoch": 0.36703020134228187, "percentage": 18.35, "elapsed_time": "1:23:01", "remaining_time": "6:09:21", "throughput": 9673.52, "total_tokens": 48183816}
{"current_steps": 880, "total_steps": 4768, "loss": 0.3978, "lr": 9.184599089574011e-06, "epoch": 0.3691275167785235, "percentage": 18.46, "elapsed_time": "1:23:27", "remaining_time": "6:08:43", "throughput": 9676.34, "total_tokens": 48453928}
{"current_steps": 885, "total_steps": 4768, "loss": 0.357, "lr": 9.175560699831431e-06, "epoch": 0.3712248322147651, "percentage": 18.56, "elapsed_time": "1:23:53", "remaining_time": "6:08:04", "throughput": 9677.84, "total_tokens": 48713176}
{"current_steps": 890, "total_steps": 4768, "loss": 0.4029, "lr": 9.16647699094788e-06, "epoch": 0.3733221476510067, "percentage": 18.67, "elapsed_time": "1:24:17", "remaining_time": "6:07:17", "throughput": 9681.86, "total_tokens": 48967112}
{"current_steps": 895, "total_steps": 4768, "loss": 0.3901, "lr": 9.157348061512728e-06, "epoch": 0.37541946308724833, "percentage": 18.77, "elapsed_time": "1:24:46", "remaining_time": "6:06:49", "throughput": 9684.48, "total_tokens": 49255736}
{"current_steps": 900, "total_steps": 4768, "loss": 0.3716, "lr": 9.148174010606132e-06, "epoch": 0.3775167785234899, "percentage": 18.88, "elapsed_time": "1:25:07", "remaining_time": "6:05:52", "throughput": 9695.86, "total_tokens": 49526144}
{"current_steps": 905, "total_steps": 4768, "loss": 0.3855, "lr": 9.138954937797983e-06, "epoch": 0.37961409395973156, "percentage": 18.98, "elapsed_time": "1:25:37", "remaining_time": "6:05:31", "throughput": 9694.81, "total_tokens": 49811896}
{"current_steps": 910, "total_steps": 4768, "loss": 0.374, "lr": 9.12969094314681e-06, "epoch": 0.38171140939597314, "percentage": 19.09, "elapsed_time": "1:26:10", "remaining_time": "6:05:21", "throughput": 9684.3, "total_tokens": 50075336}
{"current_steps": 915, "total_steps": 4768, "loss": 0.4129, "lr": 9.120382127198696e-06, "epoch": 0.3838087248322148, "percentage": 19.19, "elapsed_time": "1:26:37", "remaining_time": "6:04:47", "throughput": 9689.24, "total_tokens": 50363680}
{"current_steps": 920, "total_steps": 4768, "loss": 0.4031, "lr": 9.111028590986193e-06, "epoch": 0.3859060402684564, "percentage": 19.3, "elapsed_time": "1:27:07", "remaining_time": "6:04:26", "throughput": 9678.98, "total_tokens": 50600184}
{"current_steps": 925, "total_steps": 4768, "loss": 0.3682, "lr": 9.101630436027216e-06, "epoch": 0.38800335570469796, "percentage": 19.4, "elapsed_time": "1:27:33", "remaining_time": "6:03:45", "throughput": 9684.47, "total_tokens": 50876168}
{"current_steps": 930, "total_steps": 4768, "loss": 0.4125, "lr": 9.092187764323948e-06, "epoch": 0.3901006711409396, "percentage": 19.51, "elapsed_time": "1:27:53", "remaining_time": "6:02:44", "throughput": 9702.16, "total_tokens": 51168248}
{"current_steps": 935, "total_steps": 4768, "loss": 0.3973, "lr": 9.082700678361733e-06, "epoch": 0.3921979865771812, "percentage": 19.61, "elapsed_time": "1:28:17", "remaining_time": "6:01:58", "throughput": 9709.28, "total_tokens": 51438960}
{"current_steps": 940, "total_steps": 4768, "loss": 0.3839, "lr": 9.073169281107963e-06, "epoch": 0.39429530201342283, "percentage": 19.71, "elapsed_time": "1:28:50", "remaining_time": "6:01:46", "throughput": 9698.58, "total_tokens": 51696632}
{"current_steps": 945, "total_steps": 4768, "loss": 0.3955, "lr": 9.063593676010954e-06, "epoch": 0.3963926174496644, "percentage": 19.82, "elapsed_time": "1:29:18", "remaining_time": "6:01:18", "throughput": 9695.06, "total_tokens": 51952184}
{"current_steps": 950, "total_steps": 4768, "loss": 0.3792, "lr": 9.053973966998831e-06, "epoch": 0.39848993288590606, "percentage": 19.92, "elapsed_time": "1:29:38", "remaining_time": "6:00:14", "throughput": 9714.89, "total_tokens": 52248968}
{"current_steps": 955, "total_steps": 4768, "loss": 0.4232, "lr": 9.044310258478402e-06, "epoch": 0.40058724832214765, "percentage": 20.03, "elapsed_time": "1:30:05", "remaining_time": "5:59:43", "throughput": 9713.56, "total_tokens": 52509408}
{"current_steps": 960, "total_steps": 4768, "loss": 0.3827, "lr": 9.034602655334013e-06, "epoch": 0.40268456375838924, "percentage": 20.13, "elapsed_time": "1:30:33", "remaining_time": "5:59:13", "throughput": 9714.43, "total_tokens": 52784304}
{"current_steps": 965, "total_steps": 4768, "loss": 0.3881, "lr": 9.024851262926425e-06, "epoch": 0.4047818791946309, "percentage": 20.24, "elapsed_time": "1:31:01", "remaining_time": "5:58:43", "throughput": 9713.96, "total_tokens": 53052976}
{"current_steps": 970, "total_steps": 4768, "loss": 0.3945, "lr": 9.015056187091654e-06, "epoch": 0.40687919463087246, "percentage": 20.34, "elapsed_time": "1:31:31", "remaining_time": "5:58:22", "throughput": 9710.12, "total_tokens": 53323896}
{"current_steps": 975, "total_steps": 4768, "loss": 0.3708, "lr": 9.005217534139837e-06, "epoch": 0.4089765100671141, "percentage": 20.45, "elapsed_time": "1:31:56", "remaining_time": "5:57:40", "throughput": 9714.92, "total_tokens": 53591360}
{"current_steps": 980, "total_steps": 4768, "loss": 0.3742, "lr": 8.99533541085407e-06, "epoch": 0.4110738255033557, "percentage": 20.55, "elapsed_time": "1:32:29", "remaining_time": "5:57:30", "throughput": 9707.29, "total_tokens": 53870160}
{"current_steps": 985, "total_steps": 4768, "loss": 0.3899, "lr": 8.985409924489252e-06, "epoch": 0.41317114093959734, "percentage": 20.66, "elapsed_time": "1:32:55", "remaining_time": "5:56:54", "throughput": 9713.26, "total_tokens": 54158864}
{"current_steps": 990, "total_steps": 4768, "loss": 0.4225, "lr": 8.97544118277092e-06, "epoch": 0.4152684563758389, "percentage": 20.76, "elapsed_time": "1:33:27", "remaining_time": "5:56:37", "throughput": 9706.74, "total_tokens": 54426272}
{"current_steps": 995, "total_steps": 4768, "loss": 0.3942, "lr": 8.965429293894078e-06, "epoch": 0.4173657718120805, "percentage": 20.87, "elapsed_time": "1:34:00", "remaining_time": "5:56:27", "throughput": 9701.57, "total_tokens": 54717896}
{"current_steps": 1000, "total_steps": 4768, "loss": 0.3793, "lr": 8.955374366522025e-06, "epoch": 0.41946308724832215, "percentage": 20.97, "elapsed_time": "1:34:24", "remaining_time": "5:55:42", "throughput": 9703.82, "total_tokens": 54964168}
{"current_steps": 1005, "total_steps": 4768, "loss": 0.3859, "lr": 8.945276509785177e-06, "epoch": 0.42156040268456374, "percentage": 21.08, "elapsed_time": "1:34:53", "remaining_time": "5:55:19", "throughput": 9700.07, "total_tokens": 55231656}
{"current_steps": 1010, "total_steps": 4768, "loss": 0.3851, "lr": 8.935135833279878e-06, "epoch": 0.4236577181208054, "percentage": 21.18, "elapsed_time": "1:35:27", "remaining_time": "5:55:10", "throughput": 9691.17, "total_tokens": 55505168}
{"current_steps": 1015, "total_steps": 4768, "loss": 0.3617, "lr": 8.924952447067216e-06, "epoch": 0.42575503355704697, "percentage": 21.29, "elapsed_time": "1:35:51", "remaining_time": "5:54:24", "throughput": 9701.27, "total_tokens": 55792296}
{"current_steps": 1020, "total_steps": 4768, "loss": 0.3833, "lr": 8.914726461671824e-06, "epoch": 0.4278523489932886, "percentage": 21.39, "elapsed_time": "1:36:18", "remaining_time": "5:53:53", "throughput": 9700.44, "total_tokens": 56055616}
{"current_steps": 1025, "total_steps": 4768, "loss": 0.3832, "lr": 8.904457988080682e-06, "epoch": 0.4299496644295302, "percentage": 21.5, "elapsed_time": "1:36:50", "remaining_time": "5:53:38", "throughput": 9691.7, "total_tokens": 56314760}
{"current_steps": 1030, "total_steps": 4768, "loss": 0.3977, "lr": 8.894147137741913e-06, "epoch": 0.4320469798657718, "percentage": 21.6, "elapsed_time": "1:37:24", "remaining_time": "5:53:28", "throughput": 9686.24, "total_tokens": 56607416}
{"current_steps": 1035, "total_steps": 4768, "loss": 0.3818, "lr": 8.883794022563575e-06, "epoch": 0.4341442953020134, "percentage": 21.71, "elapsed_time": "1:37:53", "remaining_time": "5:53:03", "throughput": 9684.37, "total_tokens": 56879368}
{"current_steps": 1040, "total_steps": 4768, "loss": 0.3781, "lr": 8.873398754912437e-06, "epoch": 0.436241610738255, "percentage": 21.81, "elapsed_time": "1:38:23", "remaining_time": "5:52:41", "throughput": 9677.9, "total_tokens": 57131800}
{"current_steps": 1045, "total_steps": 4768, "loss": 0.3863, "lr": 8.862961447612777e-06, "epoch": 0.43833892617449666, "percentage": 21.92, "elapsed_time": "1:38:47", "remaining_time": "5:51:58", "throughput": 9690.16, "total_tokens": 57439864}
{"current_steps": 1050, "total_steps": 4768, "loss": 0.386, "lr": 8.852482213945142e-06, "epoch": 0.44043624161073824, "percentage": 22.02, "elapsed_time": "1:39:13", "remaining_time": "5:51:20", "throughput": 9696.7, "total_tokens": 57728312}
{"current_steps": 1055, "total_steps": 4768, "loss": 0.3733, "lr": 8.84196116764512e-06, "epoch": 0.4425335570469799, "percentage": 22.13, "elapsed_time": "1:39:36", "remaining_time": "5:50:34", "throughput": 9707.61, "total_tokens": 58020072}
{"current_steps": 1060, "total_steps": 4768, "loss": 0.3709, "lr": 8.831398422902118e-06, "epoch": 0.4446308724832215, "percentage": 22.23, "elapsed_time": "1:40:00", "remaining_time": "5:49:50", "throughput": 9712.28, "total_tokens": 58279480}
{"current_steps": 1065, "total_steps": 4768, "loss": 0.3759, "lr": 8.820794094358105e-06, "epoch": 0.44672818791946306, "percentage": 22.34, "elapsed_time": "1:40:33", "remaining_time": "5:49:38", "throughput": 9703.52, "total_tokens": 58545144}
{"current_steps": 1070, "total_steps": 4768, "loss": 0.4011, "lr": 8.810148297106383e-06, "epoch": 0.4488255033557047, "percentage": 22.44, "elapsed_time": "1:41:09", "remaining_time": "5:49:34", "throughput": 9688.42, "total_tokens": 58799160}
{"current_steps": 1075, "total_steps": 4768, "loss": 0.3879, "lr": 8.79946114669033e-06, "epoch": 0.4509228187919463, "percentage": 22.55, "elapsed_time": "1:41:38", "remaining_time": "5:49:10", "throughput": 9683.45, "total_tokens": 59055296}
{"current_steps": 1080, "total_steps": 4768, "loss": 0.388, "lr": 8.788732759102146e-06, "epoch": 0.45302013422818793, "percentage": 22.65, "elapsed_time": "1:42:05", "remaining_time": "5:48:35", "throughput": 9689.83, "total_tokens": 59350440}
{"current_steps": 1085, "total_steps": 4768, "loss": 0.3558, "lr": 8.777963250781599e-06, "epoch": 0.4551174496644295, "percentage": 22.76, "elapsed_time": "1:42:33", "remaining_time": "5:48:08", "throughput": 9691.21, "total_tokens": 59637312}
{"current_steps": 1090, "total_steps": 4768, "loss": 0.3896, "lr": 8.767152738614751e-06, "epoch": 0.45721476510067116, "percentage": 22.86, "elapsed_time": "1:43:02", "remaining_time": "5:47:43", "throughput": 9688.79, "total_tokens": 59904976}
{"current_steps": 1095, "total_steps": 4768, "loss": 0.382, "lr": 8.756301339932705e-06, "epoch": 0.45931208053691275, "percentage": 22.97, "elapsed_time": "1:43:28", "remaining_time": "5:47:05", "throughput": 9692.84, "total_tokens": 60178608}
{"current_steps": 1100, "total_steps": 4768, "loss": 0.3689, "lr": 8.745409172510315e-06, "epoch": 0.46140939597315433, "percentage": 23.07, "elapsed_time": "1:43:52", "remaining_time": "5:46:23", "throughput": 9694.09, "total_tokens": 60422376}
{"current_steps": 1105, "total_steps": 4768, "loss": 0.4005, "lr": 8.734476354564924e-06, "epoch": 0.463506711409396, "percentage": 23.18, "elapsed_time": "1:44:21", "remaining_time": "5:45:55", "throughput": 9691.96, "total_tokens": 60683256}
{"current_steps": 1110, "total_steps": 4768, "loss": 0.3847, "lr": 8.723503004755064e-06, "epoch": 0.46560402684563756, "percentage": 23.28, "elapsed_time": "1:44:50", "remaining_time": "5:45:31", "throughput": 9692.64, "total_tokens": 60974624}
{"current_steps": 1115, "total_steps": 4768, "loss": 0.3722, "lr": 8.71248924217918e-06, "epoch": 0.4677013422818792, "percentage": 23.39, "elapsed_time": "1:45:15", "remaining_time": "5:44:51", "throughput": 9700.26, "total_tokens": 61262752}
{"current_steps": 1120, "total_steps": 4768, "loss": 0.3603, "lr": 8.701435186374333e-06, "epoch": 0.4697986577181208, "percentage": 23.49, "elapsed_time": "1:45:48", "remaining_time": "5:44:38", "throughput": 9689.48, "total_tokens": 61516168}
{"current_steps": 1125, "total_steps": 4768, "loss": 0.3632, "lr": 8.69034095731491e-06, "epoch": 0.47189597315436244, "percentage": 23.59, "elapsed_time": "1:46:12", "remaining_time": "5:43:54", "throughput": 9693.21, "total_tokens": 61766648}
{"current_steps": 1130, "total_steps": 4768, "loss": 0.3782, "lr": 8.679206675411305e-06, "epoch": 0.473993288590604, "percentage": 23.7, "elapsed_time": "1:46:34", "remaining_time": "5:43:06", "throughput": 9702.07, "total_tokens": 62040064}
{"current_steps": 1135, "total_steps": 4768, "loss": 0.3856, "lr": 8.66803246150863e-06, "epoch": 0.47609060402684567, "percentage": 23.8, "elapsed_time": "1:47:02", "remaining_time": "5:42:38", "throughput": 9701.52, "total_tokens": 62311976}
{"current_steps": 1140, "total_steps": 4768, "loss": 0.4017, "lr": 8.656818436885395e-06, "epoch": 0.47818791946308725, "percentage": 23.91, "elapsed_time": "1:47:37", "remaining_time": "5:42:31", "throughput": 9689.84, "total_tokens": 62573384}
{"current_steps": 1145, "total_steps": 4768, "loss": 0.3695, "lr": 8.645564723252188e-06, "epoch": 0.48028523489932884, "percentage": 24.01, "elapsed_time": "1:48:05", "remaining_time": "5:42:02", "throughput": 9687.53, "total_tokens": 62832704}
{"current_steps": 1150, "total_steps": 4768, "loss": 0.3587, "lr": 8.634271442750364e-06, "epoch": 0.4823825503355705, "percentage": 24.12, "elapsed_time": "1:48:35", "remaining_time": "5:41:37", "throughput": 9684.58, "total_tokens": 63097216}
{"current_steps": 1155, "total_steps": 4768, "loss": 0.3727, "lr": 8.622938717950714e-06, "epoch": 0.48447986577181207, "percentage": 24.22, "elapsed_time": "1:49:00", "remaining_time": "5:41:00", "throughput": 9688.32, "total_tokens": 63369088}
{"current_steps": 1160, "total_steps": 4768, "loss": 0.3862, "lr": 8.61156667185213e-06, "epoch": 0.4865771812080537, "percentage": 24.33, "elapsed_time": "1:49:28", "remaining_time": "5:40:28", "throughput": 9687.44, "total_tokens": 63627712}
{"current_steps": 1165, "total_steps": 4768, "loss": 0.3575, "lr": 8.600155427880282e-06, "epoch": 0.4886744966442953, "percentage": 24.43, "elapsed_time": "1:49:57", "remaining_time": "5:40:03", "throughput": 9688.04, "total_tokens": 63914064}
{"current_steps": 1170, "total_steps": 4768, "loss": 0.3868, "lr": 8.588705109886264e-06, "epoch": 0.49077181208053694, "percentage": 24.54, "elapsed_time": "1:50:18", "remaining_time": "5:39:12", "throughput": 9694.69, "total_tokens": 64162848}
{"current_steps": 1175, "total_steps": 4768, "loss": 0.3891, "lr": 8.57721584214526e-06, "epoch": 0.4928691275167785, "percentage": 24.64, "elapsed_time": "1:50:45", "remaining_time": "5:38:39", "throughput": 9699.12, "total_tokens": 64450688}
{"current_steps": 1180, "total_steps": 4768, "loss": 0.3577, "lr": 8.565687749355194e-06, "epoch": 0.4949664429530201, "percentage": 24.75, "elapsed_time": "1:51:16", "remaining_time": "5:38:20", "throughput": 9694.98, "total_tokens": 64726704}
{"current_steps": 1185, "total_steps": 4768, "loss": 0.3884, "lr": 8.554120956635375e-06, "epoch": 0.49706375838926176, "percentage": 24.85, "elapsed_time": "1:51:50", "remaining_time": "5:38:10", "throughput": 9688.07, "total_tokens": 65013152}
{"current_steps": 1190, "total_steps": 4768, "loss": 0.389, "lr": 8.542515589525134e-06, "epoch": 0.49916107382550334, "percentage": 24.96, "elapsed_time": "1:52:21", "remaining_time": "5:37:50", "throughput": 9679.76, "total_tokens": 65258696}
{"current_steps": 1195, "total_steps": 4768, "loss": 0.3713, "lr": 8.53087177398247e-06, "epoch": 0.5012583892617449, "percentage": 25.06, "elapsed_time": "1:52:48", "remaining_time": "5:37:17", "throughput": 9684.7, "total_tokens": 65551056}
{"current_steps": 1200, "total_steps": 4768, "loss": 0.3808, "lr": 8.519189636382678e-06, "epoch": 0.5033557046979866, "percentage": 25.17, "elapsed_time": "1:53:16", "remaining_time": "5:36:49", "throughput": 9685.35, "total_tokens": 65829400}
{"current_steps": 1205, "total_steps": 4768, "loss": 0.4043, "lr": 8.507469303516984e-06, "epoch": 0.5054530201342282, "percentage": 25.27, "elapsed_time": "1:53:50", "remaining_time": "5:36:38", "throughput": 9681.63, "total_tokens": 66135056}
{"current_steps": 1210, "total_steps": 4768, "loss": 0.3926, "lr": 8.495710902591153e-06, "epoch": 0.5075503355704698, "percentage": 25.38, "elapsed_time": "1:54:19", "remaining_time": "5:36:11", "throughput": 9682.69, "total_tokens": 66422216}
{"current_steps": 1215, "total_steps": 4768, "loss": 0.3837, "lr": 8.483914561224127e-06, "epoch": 0.5096476510067114, "percentage": 25.48, "elapsed_time": "1:54:42", "remaining_time": "5:35:26", "throughput": 9690.96, "total_tokens": 66697632}
{"current_steps": 1220, "total_steps": 4768, "loss": 0.3513, "lr": 8.47208040744663e-06, "epoch": 0.511744966442953, "percentage": 25.59, "elapsed_time": "1:55:07", "remaining_time": "5:34:47", "throughput": 9698.81, "total_tokens": 66991224}
{"current_steps": 1225, "total_steps": 4768, "loss": 0.3932, "lr": 8.460208569699779e-06, "epoch": 0.5138422818791947, "percentage": 25.69, "elapsed_time": "1:55:39", "remaining_time": "5:34:29", "throughput": 9694.43, "total_tokens": 67269920}
{"current_steps": 1230, "total_steps": 4768, "loss": 0.3974, "lr": 8.448299176833692e-06, "epoch": 0.5159395973154363, "percentage": 25.8, "elapsed_time": "1:56:08", "remaining_time": "5:34:05", "throughput": 9688.29, "total_tokens": 67517144}
{"current_steps": 1235, "total_steps": 4768, "loss": 0.4041, "lr": 8.436352358106089e-06, "epoch": 0.5180369127516778, "percentage": 25.9, "elapsed_time": "1:56:30", "remaining_time": "5:33:19", "throughput": 9694.94, "total_tokens": 67777104}
{"current_steps": 1240, "total_steps": 4768, "loss": 0.3945, "lr": 8.424368243180888e-06, "epoch": 0.5201342281879194, "percentage": 26.01, "elapsed_time": "1:56:58", "remaining_time": "5:32:49", "throughput": 9692.26, "total_tokens": 68028560}
{"current_steps": 1245, "total_steps": 4768, "loss": 0.404, "lr": 8.412346962126798e-06, "epoch": 0.522231543624161, "percentage": 26.11, "elapsed_time": "1:57:20", "remaining_time": "5:32:03", "throughput": 9702.82, "total_tokens": 68313968}
{"current_steps": 1250, "total_steps": 4768, "loss": 0.3652, "lr": 8.400288645415913e-06, "epoch": 0.5243288590604027, "percentage": 26.22, "elapsed_time": "1:57:48", "remaining_time": "5:31:33", "throughput": 9699.95, "total_tokens": 68564256}
{"current_steps": 1255, "total_steps": 4768, "loss": 0.3732, "lr": 8.388193423922282e-06, "epoch": 0.5264261744966443, "percentage": 26.32, "elapsed_time": "1:58:12", "remaining_time": "5:30:52", "throughput": 9706.27, "total_tokens": 68838864}
{"current_steps": 1260, "total_steps": 4768, "loss": 0.3653, "lr": 8.376061428920502e-06, "epoch": 0.5285234899328859, "percentage": 26.43, "elapsed_time": "1:58:33", "remaining_time": "5:30:05", "throughput": 9714.33, "total_tokens": 69106600}
{"current_steps": 1265, "total_steps": 4768, "loss": 0.3793, "lr": 8.363892792084291e-06, "epoch": 0.5306208053691275, "percentage": 26.53, "elapsed_time": "1:59:03", "remaining_time": "5:29:41", "throughput": 9711.93, "total_tokens": 69376448}
{"current_steps": 1270, "total_steps": 4768, "loss": 0.3742, "lr": 8.351687645485053e-06, "epoch": 0.5327181208053692, "percentage": 26.64, "elapsed_time": "1:59:33", "remaining_time": "5:29:16", "throughput": 9709.53, "total_tokens": 69646952}
{"current_steps": 1275, "total_steps": 4768, "loss": 0.3909, "lr": 8.33944612159045e-06, "epoch": 0.5348154362416108, "percentage": 26.74, "elapsed_time": "2:00:04", "remaining_time": "5:28:58", "throughput": 9705.88, "total_tokens": 69930000}
{"current_steps": 1280, "total_steps": 4768, "loss": 0.4012, "lr": 8.32716835326296e-06, "epoch": 0.5369127516778524, "percentage": 26.85, "elapsed_time": "2:00:37", "remaining_time": "5:28:40", "throughput": 9704.34, "total_tokens": 70230744}
{"current_steps": 1285, "total_steps": 4768, "loss": 0.391, "lr": 8.314854473758438e-06, "epoch": 0.5390100671140939, "percentage": 26.95, "elapsed_time": "2:00:58", "remaining_time": "5:27:53", "throughput": 9713.82, "total_tokens": 70504184}
{"current_steps": 1290, "total_steps": 4768, "loss": 0.3631, "lr": 8.302504616724672e-06, "epoch": 0.5411073825503355, "percentage": 27.06, "elapsed_time": "2:01:24", "remaining_time": "5:27:19", "throughput": 9714.55, "total_tokens": 70764312}
{"current_steps": 1295, "total_steps": 4768, "loss": 0.3867, "lr": 8.290118916199924e-06, "epoch": 0.5432046979865772, "percentage": 27.16, "elapsed_time": "2:01:54", "remaining_time": "5:26:55", "throughput": 9714.78, "total_tokens": 71054544}
{"current_steps": 1300, "total_steps": 4768, "loss": 0.3684, "lr": 8.277697506611489e-06, "epoch": 0.5453020134228188, "percentage": 27.27, "elapsed_time": "2:02:22", "remaining_time": "5:26:26", "throughput": 9716.25, "total_tokens": 71338848}
{"current_steps": 1305, "total_steps": 4768, "loss": 0.3641, "lr": 8.265240522774213e-06, "epoch": 0.5473993288590604, "percentage": 27.37, "elapsed_time": "2:02:51", "remaining_time": "5:26:01", "throughput": 9714.32, "total_tokens": 71611304}
{"current_steps": 1310, "total_steps": 4768, "loss": 0.3808, "lr": 8.252748099889065e-06, "epoch": 0.549496644295302, "percentage": 27.47, "elapsed_time": "2:03:21", "remaining_time": "5:25:36", "throughput": 9716.98, "total_tokens": 71917312}
{"current_steps": 1315, "total_steps": 4768, "loss": 0.3871, "lr": 8.24022037354163e-06, "epoch": 0.5515939597315436, "percentage": 27.58, "elapsed_time": "2:03:50", "remaining_time": "5:25:12", "throughput": 9711.53, "total_tokens": 72165744}
{"current_steps": 1320, "total_steps": 4768, "loss": 0.4087, "lr": 8.227657479700669e-06, "epoch": 0.5536912751677853, "percentage": 27.68, "elapsed_time": "2:04:16", "remaining_time": "5:24:36", "throughput": 9716.92, "total_tokens": 72451344}
{"current_steps": 1325, "total_steps": 4768, "loss": 0.3912, "lr": 8.215059554716624e-06, "epoch": 0.5557885906040269, "percentage": 27.79, "elapsed_time": "2:04:43", "remaining_time": "5:24:05", "throughput": 9720.34, "total_tokens": 72741944}
{"current_steps": 1330, "total_steps": 4768, "loss": 0.3748, "lr": 8.202426735320148e-06, "epoch": 0.5578859060402684, "percentage": 27.89, "elapsed_time": "2:05:14", "remaining_time": "5:23:44", "throughput": 9717.27, "total_tokens": 73017880}
{"current_steps": 1335, "total_steps": 4768, "loss": 0.3955, "lr": 8.189759158620618e-06, "epoch": 0.55998322147651, "percentage": 28.0, "elapsed_time": "2:05:41", "remaining_time": "5:23:13", "throughput": 9719.23, "total_tokens": 73296736}
{"current_steps": 1340, "total_steps": 4768, "loss": 0.3889, "lr": 8.177056962104645e-06, "epoch": 0.5620805369127517, "percentage": 28.1, "elapsed_time": "2:06:15", "remaining_time": "5:22:59", "throughput": 9710.9, "total_tokens": 73562992}
{"current_steps": 1345, "total_steps": 4768, "loss": 0.3758, "lr": 8.164320283634585e-06, "epoch": 0.5641778523489933, "percentage": 28.21, "elapsed_time": "2:06:47", "remaining_time": "5:22:41", "throughput": 9705.56, "total_tokens": 73835624}
{"current_steps": 1350, "total_steps": 4768, "loss": 0.365, "lr": 8.15154926144704e-06, "epoch": 0.5662751677852349, "percentage": 28.31, "elapsed_time": "2:07:17", "remaining_time": "5:22:16", "throughput": 9704.2, "total_tokens": 74115312}
{"current_steps": 1355, "total_steps": 4768, "loss": 0.3849, "lr": 8.138744034151365e-06, "epoch": 0.5683724832214765, "percentage": 28.42, "elapsed_time": "2:07:37", "remaining_time": "5:21:27", "throughput": 9712.69, "total_tokens": 74375360}
{"current_steps": 1360, "total_steps": 4768, "loss": 0.4002, "lr": 8.125904740728146e-06, "epoch": 0.5704697986577181, "percentage": 28.52, "elapsed_time": "2:08:04", "remaining_time": "5:20:56", "throughput": 9714.49, "total_tokens": 74651816}
{"current_steps": 1365, "total_steps": 4768, "loss": 0.3786, "lr": 8.113031520527714e-06, "epoch": 0.5725671140939598, "percentage": 28.63, "elapsed_time": "2:08:36", "remaining_time": "5:20:38", "throughput": 9708.24, "total_tokens": 74915792}
{"current_steps": 1370, "total_steps": 4768, "loss": 0.3779, "lr": 8.100124513268616e-06, "epoch": 0.5746644295302014, "percentage": 28.73, "elapsed_time": "2:09:06", "remaining_time": "5:20:14", "throughput": 9705.62, "total_tokens": 75186856}
{"current_steps": 1375, "total_steps": 4768, "loss": 0.3686, "lr": 8.087183859036107e-06, "epoch": 0.576761744966443, "percentage": 28.84, "elapsed_time": "2:09:36", "remaining_time": "5:19:50", "throughput": 9704.16, "total_tokens": 75469264}
{"current_steps": 1380, "total_steps": 4768, "loss": 0.3487, "lr": 8.074209698280627e-06, "epoch": 0.5788590604026845, "percentage": 28.94, "elapsed_time": "2:09:58", "remaining_time": "5:19:05", "throughput": 9711.15, "total_tokens": 75728952}
{"current_steps": 1385, "total_steps": 4768, "loss": 0.372, "lr": 8.061202171816273e-06, "epoch": 0.5809563758389261, "percentage": 29.05, "elapsed_time": "2:10:22", "remaining_time": "5:18:26", "throughput": 9716.7, "total_tokens": 76005320}
{"current_steps": 1390, "total_steps": 4768, "loss": 0.3461, "lr": 8.04816142081928e-06, "epoch": 0.5830536912751678, "percentage": 29.15, "elapsed_time": "2:10:49", "remaining_time": "5:17:56", "throughput": 9712.42, "total_tokens": 76239992}
{"current_steps": 1395, "total_steps": 4768, "loss": 0.3639, "lr": 8.035087586826477e-06, "epoch": 0.5851510067114094, "percentage": 29.26, "elapsed_time": "2:11:15", "remaining_time": "5:17:22", "throughput": 9716.77, "total_tokens": 76524048}
{"current_steps": 1400, "total_steps": 4768, "loss": 0.3697, "lr": 8.021980811733761e-06, "epoch": 0.587248322147651, "percentage": 29.36, "elapsed_time": "2:11:49", "remaining_time": "5:17:08", "throughput": 9712.63, "total_tokens": 76825256}
{"current_steps": 1405, "total_steps": 4768, "loss": 0.3697, "lr": 8.008841237794551e-06, "epoch": 0.5893456375838926, "percentage": 29.47, "elapsed_time": "2:12:15", "remaining_time": "5:16:33", "throughput": 9715.79, "total_tokens": 77096800}
{"current_steps": 1410, "total_steps": 4768, "loss": 0.3488, "lr": 7.995669007618247e-06, "epoch": 0.5914429530201343, "percentage": 29.57, "elapsed_time": "2:12:41", "remaining_time": "5:16:01", "throughput": 9718.86, "total_tokens": 77378672}
{"current_steps": 1415, "total_steps": 4768, "loss": 0.3835, "lr": 7.982464264168682e-06, "epoch": 0.5935402684563759, "percentage": 29.68, "elapsed_time": "2:13:14", "remaining_time": "5:15:44", "throughput": 9714.25, "total_tokens": 77663136}
{"current_steps": 1420, "total_steps": 4768, "loss": 0.3834, "lr": 7.969227150762563e-06, "epoch": 0.5956375838926175, "percentage": 29.78, "elapsed_time": "2:13:41", "remaining_time": "5:15:13", "throughput": 9714.3, "total_tokens": 77927448}
{"current_steps": 1425, "total_steps": 4768, "loss": 0.3817, "lr": 7.955957811067932e-06, "epoch": 0.597734899328859, "percentage": 29.89, "elapsed_time": "2:14:08", "remaining_time": "5:14:40", "throughput": 9719.51, "total_tokens": 78224808}
{"current_steps": 1430, "total_steps": 4768, "loss": 0.3651, "lr": 7.94265638910259e-06, "epoch": 0.5998322147651006, "percentage": 29.99, "elapsed_time": "2:14:40", "remaining_time": "5:14:21", "throughput": 9715.93, "total_tokens": 78505328}
{"current_steps": 1435, "total_steps": 4768, "loss": 0.359, "lr": 7.92932302923254e-06, "epoch": 0.6019295302013423, "percentage": 30.1, "elapsed_time": "2:15:06", "remaining_time": "5:13:48", "throughput": 9719.24, "total_tokens": 78786832}
{"current_steps": 1440, "total_steps": 4768, "loss": 0.3692, "lr": 7.915957876170427e-06, "epoch": 0.6040268456375839, "percentage": 30.2, "elapsed_time": "2:15:33", "remaining_time": "5:13:17", "throughput": 9720.17, "total_tokens": 79058464}
{"current_steps": 1445, "total_steps": 4768, "loss": 0.3556, "lr": 7.902561074973952e-06, "epoch": 0.6061241610738255, "percentage": 30.31, "elapsed_time": "2:16:04", "remaining_time": "5:12:56", "throughput": 9713.67, "total_tokens": 79309560}
{"current_steps": 1450, "total_steps": 4768, "loss": 0.3666, "lr": 7.889132771044315e-06, "epoch": 0.6082214765100671, "percentage": 30.41, "elapsed_time": "2:16:37", "remaining_time": "5:12:37", "throughput": 9709.15, "total_tokens": 79590016}
{"current_steps": 1455, "total_steps": 4768, "loss": 0.362, "lr": 7.875673110124625e-06, "epoch": 0.6103187919463087, "percentage": 30.52, "elapsed_time": "2:17:01", "remaining_time": "5:12:01", "throughput": 9714.01, "total_tokens": 79867768}
{"current_steps": 1460, "total_steps": 4768, "loss": 0.3659, "lr": 7.862182238298318e-06, "epoch": 0.6124161073825504, "percentage": 30.62, "elapsed_time": "2:17:26", "remaining_time": "5:11:24", "throughput": 9719.11, "total_tokens": 80150352}
{"current_steps": 1465, "total_steps": 4768, "loss": 0.3711, "lr": 7.848660301987585e-06, "epoch": 0.614513422818792, "percentage": 30.73, "elapsed_time": "2:17:53", "remaining_time": "5:10:53", "throughput": 9722.48, "total_tokens": 80440752}
{"current_steps": 1470, "total_steps": 4768, "loss": 0.3977, "lr": 7.835107447951761e-06, "epoch": 0.6166107382550335, "percentage": 30.83, "elapsed_time": "2:18:20", "remaining_time": "5:10:22", "throughput": 9725.59, "total_tokens": 80728528}
{"current_steps": 1475, "total_steps": 4768, "loss": 0.3696, "lr": 7.821523823285758e-06, "epoch": 0.6187080536912751, "percentage": 30.94, "elapsed_time": "2:18:50", "remaining_time": "5:09:58", "throughput": 9723.05, "total_tokens": 81000232}
{"current_steps": 1480, "total_steps": 4768, "loss": 0.3884, "lr": 7.80790957541844e-06, "epoch": 0.6208053691275168, "percentage": 31.04, "elapsed_time": "2:19:18", "remaining_time": "5:09:28", "throughput": 9722.86, "total_tokens": 81264824}
{"current_steps": 1485, "total_steps": 4768, "loss": 0.3472, "lr": 7.79426485211105e-06, "epoch": 0.6229026845637584, "percentage": 31.15, "elapsed_time": "2:19:46", "remaining_time": "5:09:01", "throughput": 9718.82, "total_tokens": 81508736}
{"current_steps": 1490, "total_steps": 4768, "loss": 0.4002, "lr": 7.780589801455586e-06, "epoch": 0.625, "percentage": 31.25, "elapsed_time": "2:20:12", "remaining_time": "5:08:26", "throughput": 9721.8, "total_tokens": 81781976}
{"current_steps": 1495, "total_steps": 4768, "loss": 0.352, "lr": 7.766884571873208e-06, "epoch": 0.6270973154362416, "percentage": 31.35, "elapsed_time": "2:20:37", "remaining_time": "5:07:51", "throughput": 9722.81, "total_tokens": 82033120}
{"current_steps": 1500, "total_steps": 4768, "loss": 0.3815, "lr": 7.753149312112613e-06, "epoch": 0.6291946308724832, "percentage": 31.46, "elapsed_time": "2:21:01", "remaining_time": "5:07:14", "throughput": 9728.08, "total_tokens": 82314312}
{"current_steps": 1505, "total_steps": 4768, "loss": 0.3823, "lr": 7.739384171248436e-06, "epoch": 0.6312919463087249, "percentage": 31.56, "elapsed_time": "2:21:27", "remaining_time": "5:06:41", "throughput": 9730.14, "total_tokens": 82583560}
{"current_steps": 1510, "total_steps": 4768, "loss": 0.3928, "lr": 7.725589298679619e-06, "epoch": 0.6333892617449665, "percentage": 31.67, "elapsed_time": "2:21:55", "remaining_time": "5:06:14", "throughput": 9728.45, "total_tokens": 82847040}
{"current_steps": 1515, "total_steps": 4768, "loss": 0.3496, "lr": 7.711764844127796e-06, "epoch": 0.635486577181208, "percentage": 31.77, "elapsed_time": "2:22:26", "remaining_time": "5:05:51", "throughput": 9728.42, "total_tokens": 83146816}
{"current_steps": 1520, "total_steps": 4768, "loss": 0.3982, "lr": 7.697910957635672e-06, "epoch": 0.6375838926174496, "percentage": 31.88, "elapsed_time": "2:22:55", "remaining_time": "5:05:24", "throughput": 9726.66, "total_tokens": 83410984}
{"current_steps": 1525, "total_steps": 4768, "loss": 0.3748, "lr": 7.684027789565384e-06, "epoch": 0.6396812080536913, "percentage": 31.98, "elapsed_time": "2:23:21", "remaining_time": "5:04:52", "throughput": 9729.45, "total_tokens": 83692280}
{"current_steps": 1530, "total_steps": 4768, "loss": 0.3838, "lr": 7.670115490596872e-06, "epoch": 0.6417785234899329, "percentage": 32.09, "elapsed_time": "2:23:47", "remaining_time": "5:04:18", "throughput": 9731.06, "total_tokens": 83955256}
{"current_steps": 1535, "total_steps": 4768, "loss": 0.3771, "lr": 7.656174211726253e-06, "epoch": 0.6438758389261745, "percentage": 32.19, "elapsed_time": "2:24:18", "remaining_time": "5:03:56", "throughput": 9727.49, "total_tokens": 84225232}
{"current_steps": 1540, "total_steps": 4768, "loss": 0.3852, "lr": 7.642204104264171e-06, "epoch": 0.6459731543624161, "percentage": 32.3, "elapsed_time": "2:24:41", "remaining_time": "5:03:17", "throughput": 9730.94, "total_tokens": 84477872}
{"current_steps": 1545, "total_steps": 4768, "loss": 0.3553, "lr": 7.6282053198341585e-06, "epoch": 0.6480704697986577, "percentage": 32.4, "elapsed_time": "2:25:04", "remaining_time": "5:02:38", "throughput": 9735.61, "total_tokens": 84746400}
{"current_steps": 1550, "total_steps": 4768, "loss": 0.3772, "lr": 7.614178010370996e-06, "epoch": 0.6501677852348994, "percentage": 32.51, "elapsed_time": "2:25:30", "remaining_time": "5:02:06", "throughput": 9735.39, "total_tokens": 84997120}
{"current_steps": 1555, "total_steps": 4768, "loss": 0.3644, "lr": 7.600122328119053e-06, "epoch": 0.652265100671141, "percentage": 32.61, "elapsed_time": "2:25:56", "remaining_time": "5:01:32", "throughput": 9738.1, "total_tokens": 85267232}
{"current_steps": 1560, "total_steps": 4768, "loss": 0.3598, "lr": 7.586038425630642e-06, "epoch": 0.6543624161073825, "percentage": 32.72, "elapsed_time": "2:26:26", "remaining_time": "5:01:09", "throughput": 9735.19, "total_tokens": 85542392}
{"current_steps": 1565, "total_steps": 4768, "loss": 0.3685, "lr": 7.5719264557643645e-06, "epoch": 0.6564597315436241, "percentage": 32.82, "elapsed_time": "2:26:54", "remaining_time": "5:00:39", "throughput": 9735.37, "total_tokens": 85811368}
{"current_steps": 1570, "total_steps": 4768, "loss": 0.3763, "lr": 7.55778657168345e-06, "epoch": 0.6585570469798657, "percentage": 32.93, "elapsed_time": "2:27:29", "remaining_time": "5:00:25", "throughput": 9731.08, "total_tokens": 86112880}
{"current_steps": 1575, "total_steps": 4768, "loss": 0.385, "lr": 7.543618926854086e-06, "epoch": 0.6606543624161074, "percentage": 33.03, "elapsed_time": "2:28:03", "remaining_time": "5:00:08", "throughput": 9725.36, "total_tokens": 86391840}
{"current_steps": 1580, "total_steps": 4768, "loss": 0.3729, "lr": 7.529423675043765e-06, "epoch": 0.662751677852349, "percentage": 33.14, "elapsed_time": "2:28:33", "remaining_time": "4:59:45", "throughput": 9720.93, "total_tokens": 86649376}
{"current_steps": 1585, "total_steps": 4768, "loss": 0.3649, "lr": 7.5152009703196105e-06, "epoch": 0.6648489932885906, "percentage": 33.24, "elapsed_time": "2:28:57", "remaining_time": "4:59:07", "throughput": 9728.57, "total_tokens": 86945312}
{"current_steps": 1590, "total_steps": 4768, "loss": 0.3587, "lr": 7.500950967046701e-06, "epoch": 0.6669463087248322, "percentage": 33.35, "elapsed_time": "2:29:24", "remaining_time": "4:58:37", "throughput": 9728.67, "total_tokens": 87212032}
{"current_steps": 1595, "total_steps": 4768, "loss": 0.3847, "lr": 7.486673819886398e-06, "epoch": 0.6690436241610739, "percentage": 33.45, "elapsed_time": "2:29:52", "remaining_time": "4:58:08", "throughput": 9728.71, "total_tokens": 87481144}
{"current_steps": 1600, "total_steps": 4768, "loss": 0.3784, "lr": 7.47236968379467e-06, "epoch": 0.6711409395973155, "percentage": 33.56, "elapsed_time": "2:30:24", "remaining_time": "4:57:48", "throughput": 9721.47, "total_tokens": 87730032}
{"current_steps": 1605, "total_steps": 4768, "loss": 0.3651, "lr": 7.458038714020406e-06, "epoch": 0.673238255033557, "percentage": 33.66, "elapsed_time": "2:30:49", "remaining_time": "4:57:13", "throughput": 9729.35, "total_tokens": 88042536}
{"current_steps": 1610, "total_steps": 4768, "loss": 0.3545, "lr": 7.4436810661037295e-06, "epoch": 0.6753355704697986, "percentage": 33.77, "elapsed_time": "2:31:15", "remaining_time": "4:56:40", "throughput": 9730.83, "total_tokens": 88308024}
{"current_steps": 1615, "total_steps": 4768, "loss": 0.3775, "lr": 7.429296895874318e-06, "epoch": 0.6774328859060402, "percentage": 33.87, "elapsed_time": "2:31:45", "remaining_time": "4:56:16", "throughput": 9728.28, "total_tokens": 88576904}
{"current_steps": 1620, "total_steps": 4768, "loss": 0.3516, "lr": 7.4148863594497085e-06, "epoch": 0.6795302013422819, "percentage": 33.98, "elapsed_time": "2:32:20", "remaining_time": "4:56:01", "throughput": 9720.93, "total_tokens": 88850344}
{"current_steps": 1625, "total_steps": 4768, "loss": 0.3877, "lr": 7.400449613233595e-06, "epoch": 0.6816275167785235, "percentage": 34.08, "elapsed_time": "2:32:52", "remaining_time": "4:55:41", "throughput": 9716.11, "total_tokens": 89123528}
{"current_steps": 1630, "total_steps": 4768, "loss": 0.3537, "lr": 7.385986813914141e-06, "epoch": 0.6837248322147651, "percentage": 34.19, "elapsed_time": "2:33:16", "remaining_time": "4:55:05", "throughput": 9716.77, "total_tokens": 89363512}
{"current_steps": 1635, "total_steps": 4768, "loss": 0.3582, "lr": 7.371498118462276e-06, "epoch": 0.6858221476510067, "percentage": 34.29, "elapsed_time": "2:33:47", "remaining_time": "4:54:41", "throughput": 9715.36, "total_tokens": 89645744}
{"current_steps": 1640, "total_steps": 4768, "loss": 0.3959, "lr": 7.3569836841299905e-06, "epoch": 0.6879194630872483, "percentage": 34.4, "elapsed_time": "2:34:17", "remaining_time": "4:54:17", "throughput": 9713.26, "total_tokens": 89923776}
{"current_steps": 1645, "total_steps": 4768, "loss": 0.3787, "lr": 7.342443668448627e-06, "epoch": 0.69001677852349, "percentage": 34.5, "elapsed_time": "2:34:45", "remaining_time": "4:53:48", "throughput": 9712.98, "total_tokens": 90192584}
{"current_steps": 1650, "total_steps": 4768, "loss": 0.3419, "lr": 7.327878229227182e-06, "epoch": 0.6921140939597316, "percentage": 34.61, "elapsed_time": "2:35:10", "remaining_time": "4:53:14", "throughput": 9717.21, "total_tokens": 90473912}
{"current_steps": 1655, "total_steps": 4768, "loss": 0.3825, "lr": 7.313287524550574e-06, "epoch": 0.6942114093959731, "percentage": 34.71, "elapsed_time": "2:35:45", "remaining_time": "4:52:58", "throughput": 9711.76, "total_tokens": 90760912}
{"current_steps": 1660, "total_steps": 4768, "loss": 0.3851, "lr": 7.298671712777947e-06, "epoch": 0.6963087248322147, "percentage": 34.82, "elapsed_time": "2:36:07", "remaining_time": "4:52:18", "throughput": 9716.95, "total_tokens": 91023552}
{"current_steps": 1665, "total_steps": 4768, "loss": 0.3995, "lr": 7.284030952540937e-06, "epoch": 0.6984060402684564, "percentage": 34.92, "elapsed_time": "2:36:35", "remaining_time": "4:51:50", "throughput": 9719.25, "total_tokens": 91319648}
{"current_steps": 1670, "total_steps": 4768, "loss": 0.3527, "lr": 7.269365402741959e-06, "epoch": 0.700503355704698, "percentage": 35.03, "elapsed_time": "2:37:09", "remaining_time": "4:51:32", "throughput": 9714.71, "total_tokens": 91603112}
{"current_steps": 1675, "total_steps": 4768, "loss": 0.3367, "lr": 7.2546752225524775e-06, "epoch": 0.7026006711409396, "percentage": 35.13, "elapsed_time": "2:37:37", "remaining_time": "4:51:04", "throughput": 9711.66, "total_tokens": 91849176}
{"current_steps": 1680, "total_steps": 4768, "loss": 0.3832, "lr": 7.2399605714112865e-06, "epoch": 0.7046979865771812, "percentage": 35.23, "elapsed_time": "2:37:59", "remaining_time": "4:50:24", "throughput": 9715.98, "total_tokens": 92105848}
{"current_steps": 1685, "total_steps": 4768, "loss": 0.3918, "lr": 7.225221609022766e-06, "epoch": 0.7067953020134228, "percentage": 35.34, "elapsed_time": "2:38:32", "remaining_time": "4:50:05", "throughput": 9711.17, "total_tokens": 92379504}
{"current_steps": 1690, "total_steps": 4768, "loss": 0.4009, "lr": 7.210458495355165e-06, "epoch": 0.7088926174496645, "percentage": 35.44, "elapsed_time": "2:39:06", "remaining_time": "4:49:47", "throughput": 9708.6, "total_tokens": 92687048}
{"current_steps": 1695, "total_steps": 4768, "loss": 0.3944, "lr": 7.195671390638847e-06, "epoch": 0.7109899328859061, "percentage": 35.55, "elapsed_time": "2:39:29", "remaining_time": "4:49:09", "throughput": 9716.26, "total_tokens": 92980456}
{"current_steps": 1700, "total_steps": 4768, "loss": 0.3776, "lr": 7.180860455364567e-06, "epoch": 0.7130872483221476, "percentage": 35.65, "elapsed_time": "2:39:55", "remaining_time": "4:48:36", "throughput": 9718.15, "total_tokens": 93247472}
{"current_steps": 1705, "total_steps": 4768, "loss": 0.3656, "lr": 7.166025850281724e-06, "epoch": 0.7151845637583892, "percentage": 35.76, "elapsed_time": "2:40:22", "remaining_time": "4:48:06", "throughput": 9718.95, "total_tokens": 93518192}
{"current_steps": 1710, "total_steps": 4768, "loss": 0.3741, "lr": 7.151167736396611e-06, "epoch": 0.7172818791946308, "percentage": 35.86, "elapsed_time": "2:40:58", "remaining_time": "4:47:51", "throughput": 9711.87, "total_tokens": 93797608}
{"current_steps": 1715, "total_steps": 4768, "loss": 0.3826, "lr": 7.136286274970677e-06, "epoch": 0.7193791946308725, "percentage": 35.97, "elapsed_time": "2:41:35", "remaining_time": "4:47:40", "throughput": 9704.8, "total_tokens": 94096920}
{"current_steps": 1720, "total_steps": 4768, "loss": 0.3833, "lr": 7.121381627518764e-06, "epoch": 0.7214765100671141, "percentage": 36.07, "elapsed_time": "2:42:05", "remaining_time": "4:47:14", "throughput": 9706.01, "total_tokens": 94398320}
{"current_steps": 1725, "total_steps": 4768, "loss": 0.3645, "lr": 7.106453955807372e-06, "epoch": 0.7235738255033557, "percentage": 36.18, "elapsed_time": "2:42:38", "remaining_time": "4:46:53", "throughput": 9701.45, "total_tokens": 94667672}
{"current_steps": 1730, "total_steps": 4768, "loss": 0.4054, "lr": 7.091503421852887e-06, "epoch": 0.7256711409395973, "percentage": 36.28, "elapsed_time": "2:43:05", "remaining_time": "4:46:23", "throughput": 9704.07, "total_tokens": 94954944}
{"current_steps": 1735, "total_steps": 4768, "loss": 0.3534, "lr": 7.076530187919828e-06, "epoch": 0.727768456375839, "percentage": 36.39, "elapsed_time": "2:43:27", "remaining_time": "4:45:44", "throughput": 9711.55, "total_tokens": 95244664}
{"current_steps": 1740, "total_steps": 4768, "loss": 0.3622, "lr": 7.06153441651909e-06, "epoch": 0.7298657718120806, "percentage": 36.49, "elapsed_time": "2:43:56", "remaining_time": "4:45:17", "throughput": 9710.96, "total_tokens": 95519032}
{"current_steps": 1745, "total_steps": 4768, "loss": 0.359, "lr": 7.046516270406174e-06, "epoch": 0.7319630872483222, "percentage": 36.6, "elapsed_time": "2:44:25", "remaining_time": "4:44:50", "throughput": 9707.28, "total_tokens": 95765576}
{"current_steps": 1750, "total_steps": 4768, "loss": 0.3682, "lr": 7.031475912579424e-06, "epoch": 0.7340604026845637, "percentage": 36.7, "elapsed_time": "2:44:47", "remaining_time": "4:44:12", "throughput": 9714.43, "total_tokens": 96055472}
{"current_steps": 1755, "total_steps": 4768, "loss": 0.3732, "lr": 7.01641350627826e-06, "epoch": 0.7361577181208053, "percentage": 36.81, "elapsed_time": "2:45:15", "remaining_time": "4:43:43", "throughput": 9713.28, "total_tokens": 96316056}
{"current_steps": 1760, "total_steps": 4768, "loss": 0.3781, "lr": 7.001329214981398e-06, "epoch": 0.738255033557047, "percentage": 36.91, "elapsed_time": "2:45:40", "remaining_time": "4:43:08", "throughput": 9717.26, "total_tokens": 96590168}
{"current_steps": 1765, "total_steps": 4768, "loss": 0.3888, "lr": 6.986223202405088e-06, "epoch": 0.7403523489932886, "percentage": 37.02, "elapsed_time": "2:46:04", "remaining_time": "4:42:33", "throughput": 9723.49, "total_tokens": 96885608}
{"current_steps": 1770, "total_steps": 4768, "loss": 0.3782, "lr": 6.971095632501321e-06, "epoch": 0.7424496644295302, "percentage": 37.12, "elapsed_time": "2:46:31", "remaining_time": "4:42:03", "throughput": 9722.34, "total_tokens": 97140216}
{"current_steps": 1775, "total_steps": 4768, "loss": 0.399, "lr": 6.955946669456071e-06, "epoch": 0.7445469798657718, "percentage": 37.23, "elapsed_time": "2:46:58", "remaining_time": "4:41:33", "throughput": 9722.45, "total_tokens": 97408064}
{"current_steps": 1780, "total_steps": 4768, "loss": 0.3511, "lr": 6.940776477687487e-06, "epoch": 0.7466442953020134, "percentage": 37.33, "elapsed_time": "2:47:26", "remaining_time": "4:41:03", "throughput": 9722.25, "total_tokens": 97670904}
{"current_steps": 1785, "total_steps": 4768, "loss": 0.3814, "lr": 6.925585221844137e-06, "epoch": 0.7487416107382551, "percentage": 37.44, "elapsed_time": "2:47:50", "remaining_time": "4:40:29", "throughput": 9724.54, "total_tokens": 97932384}
{"current_steps": 1790, "total_steps": 4768, "loss": 0.3783, "lr": 6.910373066803194e-06, "epoch": 0.7508389261744967, "percentage": 37.54, "elapsed_time": "2:48:21", "remaining_time": "4:40:05", "throughput": 9720.2, "total_tokens": 98189384}
{"current_steps": 1795, "total_steps": 4768, "loss": 0.372, "lr": 6.895140177668666e-06, "epoch": 0.7529362416107382, "percentage": 37.65, "elapsed_time": "2:48:48", "remaining_time": "4:39:35", "throughput": 9722.36, "total_tokens": 98472024}
{"current_steps": 1800, "total_steps": 4768, "loss": 0.3894, "lr": 6.879886719769595e-06, "epoch": 0.7550335570469798, "percentage": 37.75, "elapsed_time": "2:49:17", "remaining_time": "4:39:08", "throughput": 9723.63, "total_tokens": 98769360}
{"current_steps": 1805, "total_steps": 4768, "loss": 0.3429, "lr": 6.864612858658264e-06, "epoch": 0.7571308724832215, "percentage": 37.86, "elapsed_time": "2:49:44", "remaining_time": "4:38:38", "throughput": 9725.35, "total_tokens": 99048720}
{"current_steps": 1810, "total_steps": 4768, "loss": 0.3648, "lr": 6.849318760108401e-06, "epoch": 0.7592281879194631, "percentage": 37.96, "elapsed_time": "2:50:13", "remaining_time": "4:38:10", "throughput": 9723.64, "total_tokens": 99309584}
{"current_steps": 1815, "total_steps": 4768, "loss": 0.3624, "lr": 6.83400459011338e-06, "epoch": 0.7613255033557047, "percentage": 38.07, "elapsed_time": "2:50:39", "remaining_time": "4:37:40", "throughput": 9725.21, "total_tokens": 99584352}
{"current_steps": 1820, "total_steps": 4768, "loss": 0.3753, "lr": 6.81867051488442e-06, "epoch": 0.7634228187919463, "percentage": 38.17, "elapsed_time": "2:51:09", "remaining_time": "4:37:14", "throughput": 9721.35, "total_tokens": 99835712}
{"current_steps": 1825, "total_steps": 4768, "loss": 0.3295, "lr": 6.8033167008487784e-06, "epoch": 0.7655201342281879, "percentage": 38.28, "elapsed_time": "2:51:36", "remaining_time": "4:36:44", "throughput": 9724.5, "total_tokens": 100130768}
{"current_steps": 1830, "total_steps": 4768, "loss": 0.3662, "lr": 6.787943314647945e-06, "epoch": 0.7676174496644296, "percentage": 38.38, "elapsed_time": "2:52:08", "remaining_time": "4:36:21", "throughput": 9721.4, "total_tokens": 100405104}
{"current_steps": 1835, "total_steps": 4768, "loss": 0.3585, "lr": 6.7725505231358365e-06, "epoch": 0.7697147651006712, "percentage": 38.49, "elapsed_time": "2:52:37", "remaining_time": "4:35:55", "throughput": 9719.93, "total_tokens": 100675416}
{"current_steps": 1840, "total_steps": 4768, "loss": 0.3504, "lr": 6.757138493376985e-06, "epoch": 0.7718120805369127, "percentage": 38.59, "elapsed_time": "2:53:05", "remaining_time": "4:35:25", "throughput": 9718.01, "total_tokens": 100923008}
{"current_steps": 1845, "total_steps": 4768, "loss": 0.3487, "lr": 6.741707392644723e-06, "epoch": 0.7739093959731543, "percentage": 38.7, "elapsed_time": "2:53:37", "remaining_time": "4:35:04", "throughput": 9714.08, "total_tokens": 101196688}
{"current_steps": 1850, "total_steps": 4768, "loss": 0.3744, "lr": 6.726257388419365e-06, "epoch": 0.7760067114093959, "percentage": 38.8, "elapsed_time": "2:54:05", "remaining_time": "4:34:35", "throughput": 9715.23, "total_tokens": 101477392}
{"current_steps": 1855, "total_steps": 4768, "loss": 0.3574, "lr": 6.7107886483863975e-06, "epoch": 0.7781040268456376, "percentage": 38.91, "elapsed_time": "2:54:28", "remaining_time": "4:33:59", "throughput": 9720.65, "total_tokens": 101764488}
{"current_steps": 1860, "total_steps": 4768, "loss": 0.3891, "lr": 6.69530134043465e-06, "epoch": 0.7802013422818792, "percentage": 39.01, "elapsed_time": "2:55:04", "remaining_time": "4:33:43", "throughput": 9712.74, "total_tokens": 102027040}
{"current_steps": 1865, "total_steps": 4768, "loss": 0.331, "lr": 6.679795632654482e-06, "epoch": 0.7822986577181208, "percentage": 39.11, "elapsed_time": "2:55:30", "remaining_time": "4:33:11", "throughput": 9713.41, "total_tokens": 102285608}
{"current_steps": 1870, "total_steps": 4768, "loss": 0.3382, "lr": 6.664271693335954e-06, "epoch": 0.7843959731543624, "percentage": 39.22, "elapsed_time": "2:56:01", "remaining_time": "4:32:47", "throughput": 9711.84, "total_tokens": 102572960}
{"current_steps": 1875, "total_steps": 4768, "loss": 0.3334, "lr": 6.648729690966999e-06, "epoch": 0.7864932885906041, "percentage": 39.32, "elapsed_time": "2:56:30", "remaining_time": "4:32:20", "throughput": 9711.31, "total_tokens": 102851128}
{"current_steps": 1880, "total_steps": 4768, "loss": 0.349, "lr": 6.6331697942315955e-06, "epoch": 0.7885906040268457, "percentage": 39.43, "elapsed_time": "2:56:58", "remaining_time": "4:31:51", "throughput": 9713.41, "total_tokens": 103139024}
{"current_steps": 1885, "total_steps": 4768, "loss": 0.4236, "lr": 6.617592172007938e-06, "epoch": 0.7906879194630873, "percentage": 39.53, "elapsed_time": "2:57:24", "remaining_time": "4:31:19", "throughput": 9717.97, "total_tokens": 103439352}
{"current_steps": 1890, "total_steps": 4768, "loss": 0.3704, "lr": 6.601996993366606e-06, "epoch": 0.7927852348993288, "percentage": 39.64, "elapsed_time": "2:57:47", "remaining_time": "4:30:43", "throughput": 9722.92, "total_tokens": 103715904}
{"current_steps": 1895, "total_steps": 4768, "loss": 0.3695, "lr": 6.586384427568723e-06, "epoch": 0.7948825503355704, "percentage": 39.74, "elapsed_time": "2:58:18", "remaining_time": "4:30:20", "throughput": 9719.79, "total_tokens": 103990824}
{"current_steps": 1900, "total_steps": 4768, "loss": 0.3766, "lr": 6.570754644064124e-06, "epoch": 0.7969798657718121, "percentage": 39.85, "elapsed_time": "2:58:43", "remaining_time": "4:29:47", "throughput": 9722.89, "total_tokens": 104267464}
{"current_steps": 1905, "total_steps": 4768, "loss": 0.3837, "lr": 6.555107812489513e-06, "epoch": 0.7990771812080537, "percentage": 39.95, "elapsed_time": "2:59:12", "remaining_time": "4:29:19", "throughput": 9720.74, "total_tokens": 104519568}
{"current_steps": 1910, "total_steps": 4768, "loss": 0.3805, "lr": 6.539444102666626e-06, "epoch": 0.8011744966442953, "percentage": 40.06, "elapsed_time": "2:59:43", "remaining_time": "4:28:55", "throughput": 9716.91, "total_tokens": 104780952}
{"current_steps": 1915, "total_steps": 4768, "loss": 0.3241, "lr": 6.523763684600387e-06, "epoch": 0.8032718120805369, "percentage": 40.16, "elapsed_time": "3:00:06", "remaining_time": "4:28:19", "throughput": 9720.44, "total_tokens": 105042656}
{"current_steps": 1920, "total_steps": 4768, "loss": 0.3625, "lr": 6.508066728477062e-06, "epoch": 0.8053691275167785, "percentage": 40.27, "elapsed_time": "3:00:30", "remaining_time": "4:27:45", "throughput": 9722.18, "total_tokens": 105295752}
{"current_steps": 1925, "total_steps": 4768, "loss": 0.3623, "lr": 6.492353404662406e-06, "epoch": 0.8074664429530202, "percentage": 40.37, "elapsed_time": "3:00:58", "remaining_time": "4:27:16", "throughput": 9722.88, "total_tokens": 105575056}
{"current_steps": 1930, "total_steps": 4768, "loss": 0.3433, "lr": 6.4766238836998265e-06, "epoch": 0.8095637583892618, "percentage": 40.48, "elapsed_time": "3:01:22", "remaining_time": "4:26:42", "throughput": 9728.59, "total_tokens": 105874016}
{"current_steps": 1935, "total_steps": 4768, "loss": 0.3673, "lr": 6.4608783363085195e-06, "epoch": 0.8116610738255033, "percentage": 40.58, "elapsed_time": "3:01:48", "remaining_time": "4:26:10", "throughput": 9733.31, "total_tokens": 106171584}
{"current_steps": 1940, "total_steps": 4768, "loss": 0.3458, "lr": 6.445116933381626e-06, "epoch": 0.8137583892617449, "percentage": 40.69, "elapsed_time": "3:02:10", "remaining_time": "4:25:33", "throughput": 9738.48, "total_tokens": 106442272}
{"current_steps": 1945, "total_steps": 4768, "loss": 0.3701, "lr": 6.429339845984377e-06, "epoch": 0.8158557046979866, "percentage": 40.79, "elapsed_time": "3:02:37", "remaining_time": "4:25:03", "throughput": 9738.72, "total_tokens": 106708408}
{"current_steps": 1950, "total_steps": 4768, "loss": 0.3546, "lr": 6.413547245352228e-06, "epoch": 0.8179530201342282, "percentage": 40.9, "elapsed_time": "3:03:06", "remaining_time": "4:24:37", "throughput": 9738.66, "total_tokens": 106995160}
{"current_steps": 1955, "total_steps": 4768, "loss": 0.3552, "lr": 6.397739302889008e-06, "epoch": 0.8200503355704698, "percentage": 41.0, "elapsed_time": "3:03:35", "remaining_time": "4:24:10", "throughput": 9739.68, "total_tokens": 107291640}
{"current_steps": 1960, "total_steps": 4768, "loss": 0.3614, "lr": 6.381916190165059e-06, "epoch": 0.8221476510067114, "percentage": 41.11, "elapsed_time": "3:04:03", "remaining_time": "4:23:41", "throughput": 9742.13, "total_tokens": 107583848}
{"current_steps": 1965, "total_steps": 4768, "loss": 0.3659, "lr": 6.366078078915372e-06, "epoch": 0.824244966442953, "percentage": 41.21, "elapsed_time": "3:04:26", "remaining_time": "4:23:06", "throughput": 9744.7, "total_tokens": 107841856}
{"current_steps": 1970, "total_steps": 4768, "loss": 0.3681, "lr": 6.3502251410377195e-06, "epoch": 0.8263422818791947, "percentage": 41.32, "elapsed_time": "3:04:56", "remaining_time": "4:22:39", "throughput": 9741.37, "total_tokens": 108091336}
{"current_steps": 1975, "total_steps": 4768, "loss": 0.3607, "lr": 6.334357548590799e-06, "epoch": 0.8284395973154363, "percentage": 41.42, "elapsed_time": "3:05:25", "remaining_time": "4:22:13", "throughput": 9739.55, "total_tokens": 108356096}
{"current_steps": 1980, "total_steps": 4768, "loss": 0.3495, "lr": 6.318475473792358e-06, "epoch": 0.8305369127516778, "percentage": 41.53, "elapsed_time": "3:05:51", "remaining_time": "4:21:42", "throughput": 9740.71, "total_tokens": 108626832}
{"current_steps": 1985, "total_steps": 4768, "loss": 0.396, "lr": 6.302579089017328e-06, "epoch": 0.8326342281879194, "percentage": 41.63, "elapsed_time": "3:06:13", "remaining_time": "4:21:06", "throughput": 9748.93, "total_tokens": 108933800}
{"current_steps": 1990, "total_steps": 4768, "loss": 0.345, "lr": 6.286668566795952e-06, "epoch": 0.834731543624161, "percentage": 41.74, "elapsed_time": "3:06:39", "remaining_time": "4:20:34", "throughput": 9751.45, "total_tokens": 109213784}
{"current_steps": 1995, "total_steps": 4768, "loss": 0.3468, "lr": 6.27074407981191e-06, "epoch": 0.8368288590604027, "percentage": 41.84, "elapsed_time": "3:07:03", "remaining_time": "4:20:00", "throughput": 9751.8, "total_tokens": 109450928}
{"current_steps": 2000, "total_steps": 4768, "loss": 0.3741, "lr": 6.254805800900454e-06, "epoch": 0.8389261744966443, "percentage": 41.95, "elapsed_time": "3:07:24", "remaining_time": "4:19:22", "throughput": 9759.58, "total_tokens": 109743848}
{"current_steps": 2005, "total_steps": 4768, "loss": 0.3831, "lr": 6.23885390304652e-06, "epoch": 0.8410234899328859, "percentage": 42.05, "elapsed_time": "3:07:52", "remaining_time": "4:18:53", "throughput": 9760.88, "total_tokens": 110025936}
{"current_steps": 2010, "total_steps": 4768, "loss": 0.3691, "lr": 6.22288855938286e-06, "epoch": 0.8431208053691275, "percentage": 42.16, "elapsed_time": "3:08:18", "remaining_time": "4:18:23", "throughput": 9761.93, "total_tokens": 110297504}
{"current_steps": 2015, "total_steps": 4768, "loss": 0.3609, "lr": 6.206909943188154e-06, "epoch": 0.8452181208053692, "percentage": 42.26, "elapsed_time": "3:08:44", "remaining_time": "4:17:52", "throughput": 9763.2, "total_tokens": 110564488}
{"current_steps": 2020, "total_steps": 4768, "loss": 0.3829, "lr": 6.1909182278851406e-06, "epoch": 0.8473154362416108, "percentage": 42.37, "elapsed_time": "3:09:14", "remaining_time": "4:17:26", "throughput": 9762.94, "total_tokens": 110854656}
{"current_steps": 2025, "total_steps": 4768, "loss": 0.3551, "lr": 6.174913587038725e-06, "epoch": 0.8494127516778524, "percentage": 42.47, "elapsed_time": "3:09:46", "remaining_time": "4:17:03", "throughput": 9759.88, "total_tokens": 111132032}
{"current_steps": 2030, "total_steps": 4768, "loss": 0.3848, "lr": 6.1588961943541e-06, "epoch": 0.8515100671140939, "percentage": 42.58, "elapsed_time": "3:10:16", "remaining_time": "4:16:38", "throughput": 9758.44, "total_tokens": 111406864}
{"current_steps": 2035, "total_steps": 4768, "loss": 0.3583, "lr": 6.142866223674859e-06, "epoch": 0.8536073825503355, "percentage": 42.68, "elapsed_time": "3:10:44", "remaining_time": "4:16:09", "throughput": 9759.91, "total_tokens": 111692968}
{"current_steps": 2040, "total_steps": 4768, "loss": 0.3625, "lr": 6.126823848981109e-06, "epoch": 0.8557046979865772, "percentage": 42.79, "elapsed_time": "3:11:09", "remaining_time": "4:15:36", "throughput": 9762.13, "total_tokens": 111961968}
{"current_steps": 2045, "total_steps": 4768, "loss": 0.3594, "lr": 6.110769244387584e-06, "epoch": 0.8578020134228188, "percentage": 42.89, "elapsed_time": "3:11:41", "remaining_time": "4:15:14", "throughput": 9758.01, "total_tokens": 112232208}
{"current_steps": 2050, "total_steps": 4768, "loss": 0.3755, "lr": 6.094702584141755e-06, "epoch": 0.8598993288590604, "percentage": 42.99, "elapsed_time": "3:12:07", "remaining_time": "4:14:44", "throughput": 9758.89, "total_tokens": 112500120}
{"current_steps": 2055, "total_steps": 4768, "loss": 0.3441, "lr": 6.078624042621938e-06, "epoch": 0.861996644295302, "percentage": 43.1, "elapsed_time": "3:12:40", "remaining_time": "4:14:22", "throughput": 9754.8, "total_tokens": 112774944}
{"current_steps": 2060, "total_steps": 4768, "loss": 0.3632, "lr": 6.062533794335399e-06, "epoch": 0.8640939597315436, "percentage": 43.2, "elapsed_time": "3:13:08", "remaining_time": "4:13:54", "throughput": 9755.71, "total_tokens": 113058040}
{"current_steps": 2065, "total_steps": 4768, "loss": 0.3568, "lr": 6.046432013916467e-06, "epoch": 0.8661912751677853, "percentage": 43.31, "elapsed_time": "3:13:41", "remaining_time": "4:13:32", "throughput": 9751.17, "total_tokens": 113325752}
{"current_steps": 2070, "total_steps": 4768, "loss": 0.3827, "lr": 6.030318876124629e-06, "epoch": 0.8682885906040269, "percentage": 43.41, "elapsed_time": "3:14:14", "remaining_time": "4:13:10", "throughput": 9747.11, "total_tokens": 113602096}
{"current_steps": 2075, "total_steps": 4768, "loss": 0.3644, "lr": 6.014194555842642e-06, "epoch": 0.8703859060402684, "percentage": 43.52, "elapsed_time": "3:14:43", "remaining_time": "4:12:43", "throughput": 9745.97, "total_tokens": 113866280}
{"current_steps": 2080, "total_steps": 4768, "loss": 0.3486, "lr": 5.998059228074629e-06, "epoch": 0.87248322147651, "percentage": 43.62, "elapsed_time": "3:15:08", "remaining_time": "4:12:10", "throughput": 9749.95, "total_tokens": 114155624}
{"current_steps": 2085, "total_steps": 4768, "loss": 0.3713, "lr": 5.981913067944187e-06, "epoch": 0.8745805369127517, "percentage": 43.73, "elapsed_time": "3:15:37", "remaining_time": "4:11:43", "throughput": 9747.42, "total_tokens": 114405504}
{"current_steps": 2090, "total_steps": 4768, "loss": 0.366, "lr": 5.965756250692475e-06, "epoch": 0.8766778523489933, "percentage": 43.83, "elapsed_time": "3:16:05", "remaining_time": "4:11:15", "throughput": 9749.57, "total_tokens": 114709744}
{"current_steps": 2095, "total_steps": 4768, "loss": 0.3559, "lr": 5.949588951676319e-06, "epoch": 0.8787751677852349, "percentage": 43.94, "elapsed_time": "3:16:35", "remaining_time": "4:10:50", "throughput": 9747.86, "total_tokens": 114985664}
{"current_steps": 2100, "total_steps": 4768, "loss": 0.388, "lr": 5.933411346366315e-06, "epoch": 0.8808724832214765, "percentage": 44.04, "elapsed_time": "3:17:02", "remaining_time": "4:10:20", "throughput": 9750.03, "total_tokens": 115270440}
{"current_steps": 2105, "total_steps": 4768, "loss": 0.3525, "lr": 5.9172236103449065e-06, "epoch": 0.8829697986577181, "percentage": 44.15, "elapsed_time": "3:17:30", "remaining_time": "4:09:51", "throughput": 9751.55, "total_tokens": 115558176}
{"current_steps": 2110, "total_steps": 4768, "loss": 0.3532, "lr": 5.9010259193045e-06, "epoch": 0.8850671140939598, "percentage": 44.25, "elapsed_time": "3:17:57", "remaining_time": "4:09:22", "throughput": 9752.55, "total_tokens": 115838936}
{"current_steps": 2115, "total_steps": 4768, "loss": 0.3762, "lr": 5.884818449045544e-06, "epoch": 0.8871644295302014, "percentage": 44.36, "elapsed_time": "3:18:22", "remaining_time": "4:08:49", "throughput": 9757.39, "total_tokens": 116134264}
{"current_steps": 2120, "total_steps": 4768, "loss": 0.3599, "lr": 5.868601375474622e-06, "epoch": 0.889261744966443, "percentage": 44.46, "elapsed_time": "3:18:52", "remaining_time": "4:08:24", "throughput": 9757.88, "total_tokens": 116438928}
{"current_steps": 2125, "total_steps": 4768, "loss": 0.3508, "lr": 5.852374874602552e-06, "epoch": 0.8913590604026845, "percentage": 44.57, "elapsed_time": "3:19:17", "remaining_time": "4:07:51", "throughput": 9759.78, "total_tokens": 116699808}
{"current_steps": 2130, "total_steps": 4768, "loss": 0.3792, "lr": 5.8361391225424655e-06, "epoch": 0.8934563758389261, "percentage": 44.67, "elapsed_time": "3:19:48", "remaining_time": "4:07:27", "throughput": 9757.35, "total_tokens": 116976528}
{"current_steps": 2135, "total_steps": 4768, "loss": 0.3592, "lr": 5.819894295507907e-06, "epoch": 0.8955536912751678, "percentage": 44.78, "elapsed_time": "3:20:14", "remaining_time": "4:06:56", "throughput": 9762.14, "total_tokens": 117283256}
{"current_steps": 2140, "total_steps": 4768, "loss": 0.3805, "lr": 5.80364056981091e-06, "epoch": 0.8976510067114094, "percentage": 44.88, "elapsed_time": "3:20:39", "remaining_time": "4:06:25", "throughput": 9764.76, "total_tokens": 117566056}
{"current_steps": 2145, "total_steps": 4768, "loss": 0.371, "lr": 5.78737812186009e-06, "epoch": 0.899748322147651, "percentage": 44.99, "elapsed_time": "3:21:11", "remaining_time": "4:06:02", "throughput": 9762.53, "total_tokens": 117852440}
{"current_steps": 2150, "total_steps": 4768, "loss": 0.3676, "lr": 5.771107128158731e-06, "epoch": 0.9018456375838926, "percentage": 45.09, "elapsed_time": "3:21:41", "remaining_time": "4:05:36", "throughput": 9761.42, "total_tokens": 118131472}
{"current_steps": 2155, "total_steps": 4768, "loss": 0.3691, "lr": 5.754827765302866e-06, "epoch": 0.9039429530201343, "percentage": 45.2, "elapsed_time": "3:22:15", "remaining_time": "4:05:14", "throughput": 9757.78, "total_tokens": 118414352}
{"current_steps": 2160, "total_steps": 4768, "loss": 0.3787, "lr": 5.738540209979363e-06, "epoch": 0.9060402684563759, "percentage": 45.3, "elapsed_time": "3:22:46", "remaining_time": "4:04:50", "throughput": 9757.05, "total_tokens": 118711200}
{"current_steps": 2165, "total_steps": 4768, "loss": 0.3739, "lr": 5.722244638964005e-06, "epoch": 0.9081375838926175, "percentage": 45.41, "elapsed_time": "3:23:18", "remaining_time": "4:04:26", "throughput": 9754.38, "total_tokens": 118992520}
{"current_steps": 2170, "total_steps": 4768, "loss": 0.3517, "lr": 5.705941229119576e-06, "epoch": 0.910234899328859, "percentage": 45.51, "elapsed_time": "3:23:50", "remaining_time": "4:04:02", "throughput": 9753.53, "total_tokens": 119291728}
{"current_steps": 2175, "total_steps": 4768, "loss": 0.3531, "lr": 5.6896301573939336e-06, "epoch": 0.9123322147651006, "percentage": 45.62, "elapsed_time": "3:24:15", "remaining_time": "4:03:31", "throughput": 9753.66, "total_tokens": 119538056}
{"current_steps": 2180, "total_steps": 4768, "loss": 0.3552, "lr": 5.673311600818096e-06, "epoch": 0.9144295302013423, "percentage": 45.72, "elapsed_time": "3:24:42", "remaining_time": "4:03:00", "throughput": 9755.18, "total_tokens": 119813840}
{"current_steps": 2185, "total_steps": 4768, "loss": 0.3556, "lr": 5.656985736504314e-06, "epoch": 0.9165268456375839, "percentage": 45.83, "elapsed_time": "3:25:06", "remaining_time": "4:02:27", "throughput": 9759.13, "total_tokens": 120097928}
{"current_steps": 2190, "total_steps": 4768, "loss": 0.3495, "lr": 5.6406527416441605e-06, "epoch": 0.9186241610738255, "percentage": 45.93, "elapsed_time": "3:25:32", "remaining_time": "4:01:57", "throughput": 9760.74, "total_tokens": 120377784}
{"current_steps": 2195, "total_steps": 4768, "loss": 0.3307, "lr": 5.62431279350659e-06, "epoch": 0.9207214765100671, "percentage": 46.04, "elapsed_time": "3:25:59", "remaining_time": "4:01:28", "throughput": 9762.23, "total_tokens": 120659448}
{"current_steps": 2200, "total_steps": 4768, "loss": 0.3525, "lr": 5.6079660694360305e-06, "epoch": 0.9228187919463087, "percentage": 46.14, "elapsed_time": "3:26:29", "remaining_time": "4:01:01", "throughput": 9759.26, "total_tokens": 120910272}
{"current_steps": 2205, "total_steps": 4768, "loss": 0.3622, "lr": 5.591612746850448e-06, "epoch": 0.9249161073825504, "percentage": 46.25, "elapsed_time": "3:27:00", "remaining_time": "4:00:37", "throughput": 9755.08, "total_tokens": 121167584}
{"current_steps": 2210, "total_steps": 4768, "loss": 0.3566, "lr": 5.5752530032394245e-06, "epoch": 0.927013422818792, "percentage": 46.35, "elapsed_time": "3:27:30", "remaining_time": "4:00:11", "throughput": 9755.63, "total_tokens": 121464672}
{"current_steps": 2215, "total_steps": 4768, "loss": 0.3563, "lr": 5.558887016162238e-06, "epoch": 0.9291107382550335, "percentage": 46.46, "elapsed_time": "3:27:59", "remaining_time": "3:59:44", "throughput": 9754.54, "total_tokens": 121733560}
{"current_steps": 2220, "total_steps": 4768, "loss": 0.3781, "lr": 5.542514963245924e-06, "epoch": 0.9312080536912751, "percentage": 46.56, "elapsed_time": "3:28:24", "remaining_time": "3:59:11", "throughput": 9754.65, "total_tokens": 121973784}
{"current_steps": 2225, "total_steps": 4768, "loss": 0.3784, "lr": 5.526137022183356e-06, "epoch": 0.9333053691275168, "percentage": 46.67, "elapsed_time": "3:28:53", "remaining_time": "3:58:44", "throughput": 9752.03, "total_tokens": 122225480}
{"current_steps": 2230, "total_steps": 4768, "loss": 0.3686, "lr": 5.50975337073131e-06, "epoch": 0.9354026845637584, "percentage": 46.77, "elapsed_time": "3:29:26", "remaining_time": "3:58:22", "throughput": 9746.64, "total_tokens": 122485480}
{"current_steps": 2235, "total_steps": 4768, "loss": 0.3611, "lr": 5.493364186708544e-06, "epoch": 0.9375, "percentage": 46.88, "elapsed_time": "3:29:57", "remaining_time": "3:57:57", "throughput": 9744.61, "total_tokens": 122762392}
{"current_steps": 2240, "total_steps": 4768, "loss": 0.3516, "lr": 5.476969647993861e-06, "epoch": 0.9395973154362416, "percentage": 46.98, "elapsed_time": "3:30:21", "remaining_time": "3:57:24", "throughput": 9748.92, "total_tokens": 123046920}
{"current_steps": 2245, "total_steps": 4768, "loss": 0.3455, "lr": 5.460569932524181e-06, "epoch": 0.9416946308724832, "percentage": 47.08, "elapsed_time": "3:30:53", "remaining_time": "3:56:59", "throughput": 9747.08, "total_tokens": 123330960}
{"current_steps": 2250, "total_steps": 4768, "loss": 0.3306, "lr": 5.444165218292612e-06, "epoch": 0.9437919463087249, "percentage": 47.19, "elapsed_time": "3:31:27", "remaining_time": "3:56:38", "throughput": 9742.19, "total_tokens": 123601096}
{"current_steps": 2255, "total_steps": 4768, "loss": 0.3468, "lr": 5.42775568334651e-06, "epoch": 0.9458892617449665, "percentage": 47.29, "elapsed_time": "3:31:54", "remaining_time": "3:56:09", "throughput": 9742.69, "total_tokens": 123876808}
{"current_steps": 2260, "total_steps": 4768, "loss": 0.358, "lr": 5.411341505785559e-06, "epoch": 0.947986577181208, "percentage": 47.4, "elapsed_time": "3:32:29", "remaining_time": "3:55:49", "throughput": 9735.4, "total_tokens": 124125848}
{"current_steps": 2265, "total_steps": 4768, "loss": 0.336, "lr": 5.3949228637598235e-06, "epoch": 0.9500838926174496, "percentage": 47.5, "elapsed_time": "3:32:55", "remaining_time": "3:55:17", "throughput": 9737.45, "total_tokens": 124400608}
{"current_steps": 2270, "total_steps": 4768, "loss": 0.3522, "lr": 5.378499935467834e-06, "epoch": 0.9521812080536913, "percentage": 47.61, "elapsed_time": "3:33:18", "remaining_time": "3:54:43", "throughput": 9741.61, "total_tokens": 124676784}
{"current_steps": 2275, "total_steps": 4768, "loss": 0.3487, "lr": 5.362072899154629e-06, "epoch": 0.9542785234899329, "percentage": 47.71, "elapsed_time": "3:33:45", "remaining_time": "3:54:14", "throughput": 9741.76, "total_tokens": 124946680}
{"current_steps": 2280, "total_steps": 4768, "loss": 0.3777, "lr": 5.345641933109841e-06, "epoch": 0.9563758389261745, "percentage": 47.82, "elapsed_time": "3:34:14", "remaining_time": "3:53:47", "throughput": 9743.4, "total_tokens": 125246288}
{"current_steps": 2285, "total_steps": 4768, "loss": 0.3571, "lr": 5.329207215665751e-06, "epoch": 0.9584731543624161, "percentage": 47.92, "elapsed_time": "3:34:41", "remaining_time": "3:53:17", "throughput": 9744.22, "total_tokens": 125520136}
{"current_steps": 2290, "total_steps": 4768, "loss": 0.349, "lr": 5.312768925195359e-06, "epoch": 0.9605704697986577, "percentage": 48.03, "elapsed_time": "3:35:10", "remaining_time": "3:52:50", "throughput": 9743.53, "total_tokens": 125794104}
{"current_steps": 2295, "total_steps": 4768, "loss": 0.3402, "lr": 5.296327240110437e-06, "epoch": 0.9626677852348994, "percentage": 48.13, "elapsed_time": "3:35:39", "remaining_time": "3:52:23", "throughput": 9742.6, "total_tokens": 126065880}
{"current_steps": 2300, "total_steps": 4768, "loss": 0.3541, "lr": 5.279882338859609e-06, "epoch": 0.964765100671141, "percentage": 48.24, "elapsed_time": "3:36:07", "remaining_time": "3:51:54", "throughput": 9744.56, "total_tokens": 126358456}
{"current_steps": 2305, "total_steps": 4768, "loss": 0.3632, "lr": 5.2634343999263985e-06, "epoch": 0.9668624161073825, "percentage": 48.34, "elapsed_time": "3:36:33", "remaining_time": "3:51:23", "throughput": 9745.51, "total_tokens": 126624952}
{"current_steps": 2310, "total_steps": 4768, "loss": 0.3681, "lr": 5.246983601827302e-06, "epoch": 0.9689597315436241, "percentage": 48.45, "elapsed_time": "3:37:01", "remaining_time": "3:50:56", "throughput": 9744.24, "total_tokens": 126888696}
{"current_steps": 2315, "total_steps": 4768, "loss": 0.3547, "lr": 5.230530123109849e-06, "epoch": 0.9710570469798657, "percentage": 48.55, "elapsed_time": "3:37:27", "remaining_time": "3:50:24", "throughput": 9747.09, "total_tokens": 127170608}
{"current_steps": 2320, "total_steps": 4768, "loss": 0.3773, "lr": 5.214074142350657e-06, "epoch": 0.9731543624161074, "percentage": 48.66, "elapsed_time": "3:37:54", "remaining_time": "3:49:56", "throughput": 9748.03, "total_tokens": 127453496}
{"current_steps": 2325, "total_steps": 4768, "loss": 0.3512, "lr": 5.197615838153506e-06, "epoch": 0.975251677852349, "percentage": 48.76, "elapsed_time": "3:38:23", "remaining_time": "3:49:28", "throughput": 9747.22, "total_tokens": 127718840}
{"current_steps": 2330, "total_steps": 4768, "loss": 0.3522, "lr": 5.1811553891473874e-06, "epoch": 0.9773489932885906, "percentage": 48.87, "elapsed_time": "3:38:50", "remaining_time": "3:48:59", "throughput": 9746.03, "total_tokens": 127969776}
{"current_steps": 2335, "total_steps": 4768, "loss": 0.3317, "lr": 5.164692973984577e-06, "epoch": 0.9794463087248322, "percentage": 48.97, "elapsed_time": "3:39:20", "remaining_time": "3:48:33", "throughput": 9746.24, "total_tokens": 128267536}
{"current_steps": 2340, "total_steps": 4768, "loss": 0.3294, "lr": 5.148228771338686e-06, "epoch": 0.9815436241610739, "percentage": 49.08, "elapsed_time": "3:39:57", "remaining_time": "3:48:13", "throughput": 9741.72, "total_tokens": 128562888}
{"current_steps": 2345, "total_steps": 4768, "loss": 0.3568, "lr": 5.131762959902724e-06, "epoch": 0.9836409395973155, "percentage": 49.18, "elapsed_time": "3:40:23", "remaining_time": "3:47:43", "throughput": 9743.61, "total_tokens": 128842592}
{"current_steps": 2350, "total_steps": 4768, "loss": 0.3764, "lr": 5.1152957183871685e-06, "epoch": 0.985738255033557, "percentage": 49.29, "elapsed_time": "3:40:56", "remaining_time": "3:47:19", "throughput": 9740.69, "total_tokens": 129122664}
{"current_steps": 2355, "total_steps": 4768, "loss": 0.3716, "lr": 5.0988272255180125e-06, "epoch": 0.9878355704697986, "percentage": 49.39, "elapsed_time": "3:41:26", "remaining_time": "3:46:53", "throughput": 9738.56, "total_tokens": 129390832}
{"current_steps": 2360, "total_steps": 4768, "loss": 0.347, "lr": 5.082357660034833e-06, "epoch": 0.9899328859060402, "percentage": 49.5, "elapsed_time": "3:41:51", "remaining_time": "3:46:22", "throughput": 9739.83, "total_tokens": 129653448}
{"current_steps": 2365, "total_steps": 4768, "loss": 0.3475, "lr": 5.065887200688847e-06, "epoch": 0.9920302013422819, "percentage": 49.6, "elapsed_time": "3:42:21", "remaining_time": "3:45:56", "throughput": 9737.66, "total_tokens": 129919288}
{"current_steps": 2370, "total_steps": 4768, "loss": 0.3469, "lr": 5.049416026240973e-06, "epoch": 0.9941275167785235, "percentage": 49.71, "elapsed_time": "3:42:45", "remaining_time": "3:45:23", "throughput": 9739.67, "total_tokens": 130174440}
{"current_steps": 2375, "total_steps": 4768, "loss": 0.3631, "lr": 5.032944315459892e-06, "epoch": 0.9962248322147651, "percentage": 49.81, "elapsed_time": "3:43:18", "remaining_time": "3:44:59", "throughput": 9736.13, "total_tokens": 130445928}
{"current_steps": 2380, "total_steps": 4768, "loss": 0.3429, "lr": 5.0164722471201075e-06, "epoch": 0.9983221476510067, "percentage": 49.92, "elapsed_time": "3:43:52", "remaining_time": "3:44:38", "throughput": 9731.96, "total_tokens": 130728448}
{"current_steps": 2385, "total_steps": 4768, "loss": 0.3219, "lr": 5e-06, "epoch": 1.0004194630872483, "percentage": 50.02, "elapsed_time": "3:44:19", "remaining_time": "3:44:08", "throughput": 9732.52, "total_tokens": 130994144}
{"current_steps": 2390, "total_steps": 4768, "loss": 0.2976, "lr": 4.983527752879893e-06, "epoch": 1.0025167785234899, "percentage": 50.13, "elapsed_time": "3:44:42", "remaining_time": "3:43:35", "throughput": 9735.06, "total_tokens": 131256680}
{"current_steps": 2395, "total_steps": 4768, "loss": 0.3204, "lr": 4.967055684540109e-06, "epoch": 1.0046140939597314, "percentage": 50.23, "elapsed_time": "3:45:08", "remaining_time": "3:43:04", "throughput": 9736.28, "total_tokens": 131526592}
{"current_steps": 2400, "total_steps": 4768, "loss": 0.3081, "lr": 4.950583973759029e-06, "epoch": 1.0067114093959733, "percentage": 50.34, "elapsed_time": "3:45:34", "remaining_time": "3:42:33", "throughput": 9738.78, "total_tokens": 131808000}
{"current_steps": 2405, "total_steps": 4768, "loss": 0.3224, "lr": 4.934112799311155e-06, "epoch": 1.0088087248322148, "percentage": 50.44, "elapsed_time": "3:45:56", "remaining_time": "3:41:59", "throughput": 9743.01, "total_tokens": 132082072}
{"current_steps": 2410, "total_steps": 4768, "loss": 0.2875, "lr": 4.9176423399651675e-06, "epoch": 1.0109060402684564, "percentage": 50.55, "elapsed_time": "3:46:24", "remaining_time": "3:41:31", "throughput": 9743.0, "total_tokens": 132358432}
{"current_steps": 2415, "total_steps": 4768, "loss": 0.3157, "lr": 4.901172774481988e-06, "epoch": 1.013003355704698, "percentage": 50.65, "elapsed_time": "3:46:51", "remaining_time": "3:41:01", "throughput": 9745.69, "total_tokens": 132652912}
{"current_steps": 2420, "total_steps": 4768, "loss": 0.2856, "lr": 4.884704281612832e-06, "epoch": 1.0151006711409396, "percentage": 50.76, "elapsed_time": "3:47:17", "remaining_time": "3:40:31", "throughput": 9746.4, "total_tokens": 132913856}
{"current_steps": 2425, "total_steps": 4768, "loss": 0.3145, "lr": 4.8682370400972774e-06, "epoch": 1.0171979865771812, "percentage": 50.86, "elapsed_time": "3:47:43", "remaining_time": "3:40:01", "throughput": 9748.15, "total_tokens": 133190432}
{"current_steps": 2430, "total_steps": 4768, "loss": 0.3268, "lr": 4.851771228661316e-06, "epoch": 1.0192953020134228, "percentage": 50.96, "elapsed_time": "3:48:06", "remaining_time": "3:39:28", "throughput": 9752.76, "total_tokens": 133478560}
{"current_steps": 2435, "total_steps": 4768, "loss": 0.3132, "lr": 4.8353070260154244e-06, "epoch": 1.0213926174496644, "percentage": 51.07, "elapsed_time": "3:48:35", "remaining_time": "3:39:00", "throughput": 9750.86, "total_tokens": 133733920}
{"current_steps": 2440, "total_steps": 4768, "loss": 0.3145, "lr": 4.818844610852613e-06, "epoch": 1.023489932885906, "percentage": 51.17, "elapsed_time": "3:49:04", "remaining_time": "3:38:33", "throughput": 9750.0, "total_tokens": 134009288}
{"current_steps": 2445, "total_steps": 4768, "loss": 0.3215, "lr": 4.802384161846496e-06, "epoch": 1.0255872483221478, "percentage": 51.28, "elapsed_time": "3:49:38", "remaining_time": "3:38:11", "throughput": 9746.69, "total_tokens": 134298360}
{"current_steps": 2450, "total_steps": 4768, "loss": 0.3177, "lr": 4.785925857649344e-06, "epoch": 1.0276845637583893, "percentage": 51.38, "elapsed_time": "3:50:07", "remaining_time": "3:37:43", "throughput": 9747.6, "total_tokens": 134589128}
{"current_steps": 2455, "total_steps": 4768, "loss": 0.3004, "lr": 4.769469876890152e-06, "epoch": 1.029781879194631, "percentage": 51.49, "elapsed_time": "3:50:37", "remaining_time": "3:37:17", "throughput": 9745.09, "total_tokens": 134851744}
{"current_steps": 2460, "total_steps": 4768, "loss": 0.3095, "lr": 4.753016398172697e-06, "epoch": 1.0318791946308725, "percentage": 51.59, "elapsed_time": "3:51:02", "remaining_time": "3:36:46", "throughput": 9748.4, "total_tokens": 135140728}
{"current_steps": 2465, "total_steps": 4768, "loss": 0.3281, "lr": 4.736565600073602e-06, "epoch": 1.033976510067114, "percentage": 51.7, "elapsed_time": "3:51:33", "remaining_time": "3:36:20", "throughput": 9746.46, "total_tokens": 135412664}
{"current_steps": 2470, "total_steps": 4768, "loss": 0.3223, "lr": 4.7201176611403935e-06, "epoch": 1.0360738255033557, "percentage": 51.8, "elapsed_time": "3:52:01", "remaining_time": "3:35:51", "throughput": 9746.08, "total_tokens": 135676848}
{"current_steps": 2475, "total_steps": 4768, "loss": 0.298, "lr": 4.7036727598895645e-06, "epoch": 1.0381711409395973, "percentage": 51.91, "elapsed_time": "3:52:31", "remaining_time": "3:35:25", "throughput": 9744.22, "total_tokens": 135943072}
{"current_steps": 2480, "total_steps": 4768, "loss": 0.3127, "lr": 4.687231074804643e-06, "epoch": 1.0402684563758389, "percentage": 52.01, "elapsed_time": "3:53:00", "remaining_time": "3:34:58", "throughput": 9742.49, "total_tokens": 136205664}
{"current_steps": 2485, "total_steps": 4768, "loss": 0.3041, "lr": 4.6707927843342505e-06, "epoch": 1.0423657718120805, "percentage": 52.12, "elapsed_time": "3:53:26", "remaining_time": "3:34:27", "throughput": 9746.64, "total_tokens": 136512584}
{"current_steps": 2490, "total_steps": 4768, "loss": 0.3248, "lr": 4.654358066890161e-06, "epoch": 1.044463087248322, "percentage": 52.22, "elapsed_time": "3:53:52", "remaining_time": "3:33:57", "throughput": 9747.56, "total_tokens": 136782648}
{"current_steps": 2495, "total_steps": 4768, "loss": 0.3117, "lr": 4.637927100845374e-06, "epoch": 1.0465604026845639, "percentage": 52.33, "elapsed_time": "3:54:20", "remaining_time": "3:33:29", "throughput": 9749.22, "total_tokens": 137082912}
{"current_steps": 2500, "total_steps": 4768, "loss": 0.3006, "lr": 4.6215000645321696e-06, "epoch": 1.0486577181208054, "percentage": 52.43, "elapsed_time": "3:54:45", "remaining_time": "3:32:58", "throughput": 9750.91, "total_tokens": 137348120}
{"current_steps": 2505, "total_steps": 4768, "loss": 0.3175, "lr": 4.6050771362401764e-06, "epoch": 1.050755033557047, "percentage": 52.54, "elapsed_time": "3:55:10", "remaining_time": "3:32:27", "throughput": 9753.35, "total_tokens": 137623472}
{"current_steps": 2510, "total_steps": 4768, "loss": 0.2994, "lr": 4.588658494214443e-06, "epoch": 1.0528523489932886, "percentage": 52.64, "elapsed_time": "3:55:36", "remaining_time": "3:31:56", "throughput": 9755.0, "total_tokens": 137897016}
{"current_steps": 2515, "total_steps": 4768, "loss": 0.3303, "lr": 4.5722443166534904e-06, "epoch": 1.0549496644295302, "percentage": 52.75, "elapsed_time": "3:56:07", "remaining_time": "3:31:31", "throughput": 9752.83, "total_tokens": 138175592}
{"current_steps": 2520, "total_steps": 4768, "loss": 0.3114, "lr": 4.55583478170739e-06, "epoch": 1.0570469798657718, "percentage": 52.85, "elapsed_time": "3:56:41", "remaining_time": "3:31:08", "throughput": 9748.67, "total_tokens": 138442664}
{"current_steps": 2525, "total_steps": 4768, "loss": 0.2945, "lr": 4.53943006747582e-06, "epoch": 1.0591442953020134, "percentage": 52.96, "elapsed_time": "3:57:08", "remaining_time": "3:30:39", "throughput": 9748.65, "total_tokens": 138713048}
{"current_steps": 2530, "total_steps": 4768, "loss": 0.2927, "lr": 4.523030352006141e-06, "epoch": 1.061241610738255, "percentage": 53.06, "elapsed_time": "3:57:31", "remaining_time": "3:30:07", "throughput": 9751.93, "total_tokens": 138983832}
{"current_steps": 2535, "total_steps": 4768, "loss": 0.3324, "lr": 4.506635813291458e-06, "epoch": 1.0633389261744965, "percentage": 53.17, "elapsed_time": "3:57:53", "remaining_time": "3:29:33", "throughput": 9755.74, "total_tokens": 139251408}
{"current_steps": 2540, "total_steps": 4768, "loss": 0.2862, "lr": 4.490246629268692e-06, "epoch": 1.0654362416107384, "percentage": 53.27, "elapsed_time": "3:58:17", "remaining_time": "3:29:00", "throughput": 9759.91, "total_tokens": 139537568}
{"current_steps": 2545, "total_steps": 4768, "loss": 0.3313, "lr": 4.473862977816647e-06, "epoch": 1.06753355704698, "percentage": 53.38, "elapsed_time": "3:58:39", "remaining_time": "3:28:27", "throughput": 9763.39, "total_tokens": 139809368}
{"current_steps": 2550, "total_steps": 4768, "loss": 0.34, "lr": 4.457485036754076e-06, "epoch": 1.0696308724832215, "percentage": 53.48, "elapsed_time": "3:59:10", "remaining_time": "3:28:02", "throughput": 9760.95, "total_tokens": 140078064}
{"current_steps": 2555, "total_steps": 4768, "loss": 0.3042, "lr": 4.441112983837763e-06, "epoch": 1.0717281879194631, "percentage": 53.59, "elapsed_time": "3:59:39", "remaining_time": "3:27:34", "throughput": 9760.89, "total_tokens": 140359384}
{"current_steps": 2560, "total_steps": 4768, "loss": 0.279, "lr": 4.424746996760576e-06, "epoch": 1.0738255033557047, "percentage": 53.69, "elapsed_time": "4:00:10", "remaining_time": "3:27:08", "throughput": 9760.68, "total_tokens": 140651920}
{"current_steps": 2565, "total_steps": 4768, "loss": 0.3002, "lr": 4.408387253149553e-06, "epoch": 1.0759228187919463, "percentage": 53.8, "elapsed_time": "4:00:42", "remaining_time": "3:26:44", "throughput": 9758.98, "total_tokens": 140946536}
{"current_steps": 2570, "total_steps": 4768, "loss": 0.3025, "lr": 4.392033930563971e-06, "epoch": 1.0780201342281879, "percentage": 53.9, "elapsed_time": "4:01:11", "remaining_time": "3:26:16", "throughput": 9757.92, "total_tokens": 141207464}
{"current_steps": 2575, "total_steps": 4768, "loss": 0.3052, "lr": 4.375687206493411e-06, "epoch": 1.0801174496644295, "percentage": 54.01, "elapsed_time": "4:01:39", "remaining_time": "3:25:48", "throughput": 9757.54, "total_tokens": 141481520}
{"current_steps": 2580, "total_steps": 4768, "loss": 0.3101, "lr": 4.359347258355842e-06, "epoch": 1.082214765100671, "percentage": 54.11, "elapsed_time": "4:02:06", "remaining_time": "3:25:19", "throughput": 9760.0, "total_tokens": 141776872}
{"current_steps": 2585, "total_steps": 4768, "loss": 0.3345, "lr": 4.3430142634956866e-06, "epoch": 1.0843120805369129, "percentage": 54.22, "elapsed_time": "4:02:33", "remaining_time": "3:24:50", "throughput": 9761.49, "total_tokens": 142064872}
{"current_steps": 2590, "total_steps": 4768, "loss": 0.3042, "lr": 4.326688399181907e-06, "epoch": 1.0864093959731544, "percentage": 54.32, "elapsed_time": "4:03:00", "remaining_time": "3:24:21", "throughput": 9760.63, "total_tokens": 142318544}
{"current_steps": 2595, "total_steps": 4768, "loss": 0.3058, "lr": 4.310369842606066e-06, "epoch": 1.088506711409396, "percentage": 54.43, "elapsed_time": "4:03:28", "remaining_time": "3:23:52", "throughput": 9759.82, "total_tokens": 142574008}
{"current_steps": 2600, "total_steps": 4768, "loss": 0.3055, "lr": 4.294058770880424e-06, "epoch": 1.0906040268456376, "percentage": 54.53, "elapsed_time": "4:03:57", "remaining_time": "3:23:25", "throughput": 9759.27, "total_tokens": 142847384}
{"current_steps": 2605, "total_steps": 4768, "loss": 0.287, "lr": 4.277755361035995e-06, "epoch": 1.0927013422818792, "percentage": 54.64, "elapsed_time": "4:04:21", "remaining_time": "3:22:53", "throughput": 9761.17, "total_tokens": 143110936}
{"current_steps": 2610, "total_steps": 4768, "loss": 0.302, "lr": 4.261459790020638e-06, "epoch": 1.0947986577181208, "percentage": 54.74, "elapsed_time": "4:04:53", "remaining_time": "3:22:29", "throughput": 9758.29, "total_tokens": 143386016}
{"current_steps": 2615, "total_steps": 4768, "loss": 0.3037, "lr": 4.2451722346971355e-06, "epoch": 1.0968959731543624, "percentage": 54.84, "elapsed_time": "4:05:24", "remaining_time": "3:22:03", "throughput": 9757.15, "total_tokens": 143670680}
{"current_steps": 2620, "total_steps": 4768, "loss": 0.2993, "lr": 4.22889287184127e-06, "epoch": 1.098993288590604, "percentage": 54.95, "elapsed_time": "4:05:52", "remaining_time": "3:21:35", "throughput": 9758.12, "total_tokens": 143959232}
{"current_steps": 2625, "total_steps": 4768, "loss": 0.2986, "lr": 4.212621878139912e-06, "epoch": 1.1010906040268456, "percentage": 55.05, "elapsed_time": "4:06:21", "remaining_time": "3:21:07", "throughput": 9757.14, "total_tokens": 144227512}
{"current_steps": 2630, "total_steps": 4768, "loss": 0.2975, "lr": 4.196359430189092e-06, "epoch": 1.1031879194630871, "percentage": 55.16, "elapsed_time": "4:06:50", "remaining_time": "3:20:40", "throughput": 9757.22, "total_tokens": 144513160}
{"current_steps": 2635, "total_steps": 4768, "loss": 0.2917, "lr": 4.180105704492096e-06, "epoch": 1.105285234899329, "percentage": 55.26, "elapsed_time": "4:07:19", "remaining_time": "3:20:12", "throughput": 9756.65, "total_tokens": 144784408}
{"current_steps": 2640, "total_steps": 4768, "loss": 0.3087, "lr": 4.163860877457535e-06, "epoch": 1.1073825503355705, "percentage": 55.37, "elapsed_time": "4:07:50", "remaining_time": "3:19:46", "throughput": 9753.63, "total_tokens": 145040896}
{"current_steps": 2645, "total_steps": 4768, "loss": 0.2937, "lr": 4.14762512539745e-06, "epoch": 1.1094798657718121, "percentage": 55.47, "elapsed_time": "4:08:17", "remaining_time": "3:19:17", "throughput": 9755.02, "total_tokens": 145326632}
{"current_steps": 2650, "total_steps": 4768, "loss": 0.3097, "lr": 4.131398624525379e-06, "epoch": 1.1115771812080537, "percentage": 55.58, "elapsed_time": "4:08:42", "remaining_time": "3:18:47", "throughput": 9756.4, "total_tokens": 145594432}
{"current_steps": 2655, "total_steps": 4768, "loss": 0.3068, "lr": 4.115181550954458e-06, "epoch": 1.1136744966442953, "percentage": 55.68, "elapsed_time": "4:09:11", "remaining_time": "3:18:19", "throughput": 9757.01, "total_tokens": 145884360}
{"current_steps": 2660, "total_steps": 4768, "loss": 0.316, "lr": 4.098974080695501e-06, "epoch": 1.1157718120805369, "percentage": 55.79, "elapsed_time": "4:09:35", "remaining_time": "3:17:47", "throughput": 9761.07, "total_tokens": 146178464}
{"current_steps": 2665, "total_steps": 4768, "loss": 0.3014, "lr": 4.082776389655095e-06, "epoch": 1.1178691275167785, "percentage": 55.89, "elapsed_time": "4:10:01", "remaining_time": "3:17:18", "throughput": 9761.77, "total_tokens": 146442200}
{"current_steps": 2670, "total_steps": 4768, "loss": 0.312, "lr": 4.066588653633688e-06, "epoch": 1.11996644295302, "percentage": 56.0, "elapsed_time": "4:10:33", "remaining_time": "3:16:52", "throughput": 9759.21, "total_tokens": 146716872}
{"current_steps": 2675, "total_steps": 4768, "loss": 0.3025, "lr": 4.050411048323682e-06, "epoch": 1.1220637583892616, "percentage": 56.1, "elapsed_time": "4:11:02", "remaining_time": "3:16:25", "throughput": 9760.11, "total_tokens": 147013632}
{"current_steps": 2680, "total_steps": 4768, "loss": 0.301, "lr": 4.0342437493075285e-06, "epoch": 1.1241610738255035, "percentage": 56.21, "elapsed_time": "4:11:30", "remaining_time": "3:15:56", "throughput": 9761.0, "total_tokens": 147294112}
{"current_steps": 2685, "total_steps": 4768, "loss": 0.3134, "lr": 4.018086932055815e-06, "epoch": 1.126258389261745, "percentage": 56.31, "elapsed_time": "4:11:57", "remaining_time": "3:15:27", "throughput": 9762.55, "total_tokens": 147583376}
{"current_steps": 2690, "total_steps": 4768, "loss": 0.293, "lr": 4.001940771925371e-06, "epoch": 1.1283557046979866, "percentage": 56.42, "elapsed_time": "4:12:24", "remaining_time": "3:14:59", "throughput": 9760.53, "total_tokens": 147822480}
{"current_steps": 2695, "total_steps": 4768, "loss": 0.3171, "lr": 3.98580544415736e-06, "epoch": 1.1304530201342282, "percentage": 56.52, "elapsed_time": "4:12:55", "remaining_time": "3:14:32", "throughput": 9758.21, "total_tokens": 148085096}
{"current_steps": 2700, "total_steps": 4768, "loss": 0.3084, "lr": 3.969681123875373e-06, "epoch": 1.1325503355704698, "percentage": 56.63, "elapsed_time": "4:13:24", "remaining_time": "3:14:05", "throughput": 9754.75, "total_tokens": 148314560}
{"current_steps": 2705, "total_steps": 4768, "loss": 0.3083, "lr": 3.953567986083535e-06, "epoch": 1.1346476510067114, "percentage": 56.73, "elapsed_time": "4:13:52", "remaining_time": "3:13:36", "throughput": 9757.13, "total_tokens": 148621416}
{"current_steps": 2710, "total_steps": 4768, "loss": 0.2994, "lr": 3.937466205664602e-06, "epoch": 1.136744966442953, "percentage": 56.84, "elapsed_time": "4:14:15", "remaining_time": "3:13:04", "throughput": 9760.13, "total_tokens": 148893168}
{"current_steps": 2715, "total_steps": 4768, "loss": 0.308, "lr": 3.921375957378064e-06, "epoch": 1.1388422818791946, "percentage": 56.94, "elapsed_time": "4:14:45", "remaining_time": "3:12:38", "throughput": 9756.97, "total_tokens": 149141168}
{"current_steps": 2720, "total_steps": 4768, "loss": 0.3088, "lr": 3.905297415858247e-06, "epoch": 1.1409395973154361, "percentage": 57.05, "elapsed_time": "4:15:13", "remaining_time": "3:12:10", "throughput": 9754.76, "total_tokens": 149380976}
{"current_steps": 2725, "total_steps": 4768, "loss": 0.3074, "lr": 3.889230755612417e-06, "epoch": 1.1430369127516777, "percentage": 57.15, "elapsed_time": "4:15:40", "remaining_time": "3:11:41", "throughput": 9755.03, "total_tokens": 149651248}
{"current_steps": 2730, "total_steps": 4768, "loss": 0.2876, "lr": 3.873176151018893e-06, "epoch": 1.1451342281879195, "percentage": 57.26, "elapsed_time": "4:16:06", "remaining_time": "3:11:11", "throughput": 9756.16, "total_tokens": 149921312}
{"current_steps": 2735, "total_steps": 4768, "loss": 0.3037, "lr": 3.857133776325142e-06, "epoch": 1.1472315436241611, "percentage": 57.36, "elapsed_time": "4:16:32", "remaining_time": "3:10:41", "throughput": 9757.72, "total_tokens": 150191784}
{"current_steps": 2740, "total_steps": 4768, "loss": 0.3032, "lr": 3.8411038056459e-06, "epoch": 1.1493288590604027, "percentage": 57.47, "elapsed_time": "4:16:58", "remaining_time": "3:10:12", "throughput": 9758.57, "total_tokens": 150463296}
{"current_steps": 2745, "total_steps": 4768, "loss": 0.3108, "lr": 3.825086412961275e-06, "epoch": 1.1514261744966443, "percentage": 57.57, "elapsed_time": "4:17:25", "remaining_time": "3:09:43", "throughput": 9757.89, "total_tokens": 150717640}
{"current_steps": 2750, "total_steps": 4768, "loss": 0.3017, "lr": 3.809081772114861e-06, "epoch": 1.153523489932886, "percentage": 57.68, "elapsed_time": "4:17:54", "remaining_time": "3:09:15", "throughput": 9756.94, "total_tokens": 150979832}
{"current_steps": 2755, "total_steps": 4768, "loss": 0.2943, "lr": 3.793090056811847e-06, "epoch": 1.1556208053691275, "percentage": 57.78, "elapsed_time": "4:18:15", "remaining_time": "3:08:41", "throughput": 9760.85, "total_tokens": 151247456}
{"current_steps": 2760, "total_steps": 4768, "loss": 0.2863, "lr": 3.777111440617142e-06, "epoch": 1.157718120805369, "percentage": 57.89, "elapsed_time": "4:18:41", "remaining_time": "3:08:12", "throughput": 9761.83, "total_tokens": 151514496}
{"current_steps": 2765, "total_steps": 4768, "loss": 0.3137, "lr": 3.761146096953482e-06, "epoch": 1.1598154362416107, "percentage": 57.99, "elapsed_time": "4:19:12", "remaining_time": "3:07:46", "throughput": 9759.04, "total_tokens": 151774208}
{"current_steps": 2770, "total_steps": 4768, "loss": 0.315, "lr": 3.745194199099549e-06, "epoch": 1.1619127516778525, "percentage": 58.1, "elapsed_time": "4:19:37", "remaining_time": "3:07:16", "throughput": 9761.64, "total_tokens": 152063608}
{"current_steps": 2775, "total_steps": 4768, "loss": 0.2996, "lr": 3.729255920188092e-06, "epoch": 1.164010067114094, "percentage": 58.2, "elapsed_time": "4:20:08", "remaining_time": "3:06:49", "throughput": 9759.83, "total_tokens": 152333200}
{"current_steps": 2780, "total_steps": 4768, "loss": 0.3046, "lr": 3.7133314332040516e-06, "epoch": 1.1661073825503356, "percentage": 58.31, "elapsed_time": "4:20:35", "remaining_time": "3:06:20", "throughput": 9761.17, "total_tokens": 152617984}
{"current_steps": 2785, "total_steps": 4768, "loss": 0.2987, "lr": 3.6974209109826724e-06, "epoch": 1.1682046979865772, "percentage": 58.41, "elapsed_time": "4:21:02", "remaining_time": "3:05:52", "throughput": 9763.35, "total_tokens": 152919904}
{"current_steps": 2790, "total_steps": 4768, "loss": 0.3134, "lr": 3.6815245262076426e-06, "epoch": 1.1703020134228188, "percentage": 58.52, "elapsed_time": "4:21:27", "remaining_time": "3:05:21", "throughput": 9766.09, "total_tokens": 153204776}
{"current_steps": 2795, "total_steps": 4768, "loss": 0.2936, "lr": 3.6656424514092025e-06, "epoch": 1.1723993288590604, "percentage": 58.62, "elapsed_time": "4:21:55", "remaining_time": "3:04:53", "throughput": 9765.66, "total_tokens": 153476632}
{"current_steps": 2800, "total_steps": 4768, "loss": 0.3042, "lr": 3.6497748589622826e-06, "epoch": 1.174496644295302, "percentage": 58.72, "elapsed_time": "4:22:20", "remaining_time": "3:04:23", "throughput": 9768.82, "total_tokens": 153765256}
{"current_steps": 2805, "total_steps": 4768, "loss": 0.299, "lr": 3.63392192108463e-06, "epoch": 1.1765939597315436, "percentage": 58.83, "elapsed_time": "4:22:50", "remaining_time": "3:03:56", "throughput": 9767.51, "total_tokens": 154034536}
{"current_steps": 2810, "total_steps": 4768, "loss": 0.2976, "lr": 3.6180838098349417e-06, "epoch": 1.1786912751677852, "percentage": 58.93, "elapsed_time": "4:23:14", "remaining_time": "3:03:25", "throughput": 9771.45, "total_tokens": 154331000}
{"current_steps": 2815, "total_steps": 4768, "loss": 0.3186, "lr": 3.602260697110993e-06, "epoch": 1.1807885906040267, "percentage": 59.04, "elapsed_time": "4:23:38", "remaining_time": "3:02:54", "throughput": 9775.17, "total_tokens": 154632024}
{"current_steps": 2820, "total_steps": 4768, "loss": 0.3007, "lr": 3.5864527546477733e-06, "epoch": 1.1828859060402686, "percentage": 59.14, "elapsed_time": "4:24:14", "remaining_time": "3:02:31", "throughput": 9771.01, "total_tokens": 154911816}
{"current_steps": 2825, "total_steps": 4768, "loss": 0.3115, "lr": 3.570660154015625e-06, "epoch": 1.1849832214765101, "percentage": 59.25, "elapsed_time": "4:24:43", "remaining_time": "3:02:04", "throughput": 9769.64, "total_tokens": 155175000}
{"current_steps": 2830, "total_steps": 4768, "loss": 0.3237, "lr": 3.5548830666183737e-06, "epoch": 1.1870805369127517, "percentage": 59.35, "elapsed_time": "4:25:15", "remaining_time": "3:01:39", "throughput": 9766.73, "total_tokens": 155443192}
{"current_steps": 2835, "total_steps": 4768, "loss": 0.3163, "lr": 3.5391216636914826e-06, "epoch": 1.1891778523489933, "percentage": 59.46, "elapsed_time": "4:25:48", "remaining_time": "3:01:14", "throughput": 9764.82, "total_tokens": 155733000}
{"current_steps": 2840, "total_steps": 4768, "loss": 0.3143, "lr": 3.5233761163001755e-06, "epoch": 1.191275167785235, "percentage": 59.56, "elapsed_time": "4:26:14", "remaining_time": "3:00:44", "throughput": 9766.82, "total_tokens": 156023960}
{"current_steps": 2845, "total_steps": 4768, "loss": 0.3271, "lr": 3.5076465953375954e-06, "epoch": 1.1933724832214765, "percentage": 59.67, "elapsed_time": "4:26:46", "remaining_time": "3:00:19", "throughput": 9763.09, "total_tokens": 156273480}
{"current_steps": 2850, "total_steps": 4768, "loss": 0.3054, "lr": 3.4919332715229404e-06, "epoch": 1.195469798657718, "percentage": 59.77, "elapsed_time": "4:27:15", "remaining_time": "2:59:51", "throughput": 9763.09, "total_tokens": 156559008}
{"current_steps": 2855, "total_steps": 4768, "loss": 0.3239, "lr": 3.4762363153996136e-06, "epoch": 1.1975671140939597, "percentage": 59.88, "elapsed_time": "4:27:44", "remaining_time": "2:59:24", "throughput": 9763.02, "total_tokens": 156838856}
{"current_steps": 2860, "total_steps": 4768, "loss": 0.328, "lr": 3.460555897333375e-06, "epoch": 1.1996644295302012, "percentage": 59.98, "elapsed_time": "4:28:07", "remaining_time": "2:58:52", "throughput": 9767.35, "total_tokens": 157131920}
{"current_steps": 2865, "total_steps": 4768, "loss": 0.3047, "lr": 3.4448921875104898e-06, "epoch": 1.201761744966443, "percentage": 60.09, "elapsed_time": "4:28:32", "remaining_time": "2:58:22", "throughput": 9766.38, "total_tokens": 157363024}
{"current_steps": 2870, "total_steps": 4768, "loss": 0.3131, "lr": 3.4292453559358795e-06, "epoch": 1.2038590604026846, "percentage": 60.19, "elapsed_time": "4:28:58", "remaining_time": "2:57:52", "throughput": 9766.18, "total_tokens": 157607424}
{"current_steps": 2875, "total_steps": 4768, "loss": 0.2945, "lr": 3.4136155724312774e-06, "epoch": 1.2059563758389262, "percentage": 60.3, "elapsed_time": "4:29:26", "remaining_time": "2:57:24", "throughput": 9765.92, "total_tokens": 157878944}
{"current_steps": 2880, "total_steps": 4768, "loss": 0.31, "lr": 3.3980030066333947e-06, "epoch": 1.2080536912751678, "percentage": 60.4, "elapsed_time": "4:29:59", "remaining_time": "2:56:59", "throughput": 9763.18, "total_tokens": 158155048}
{"current_steps": 2885, "total_steps": 4768, "loss": 0.3029, "lr": 3.3824078279920625e-06, "epoch": 1.2101510067114094, "percentage": 60.51, "elapsed_time": "4:30:24", "remaining_time": "2:56:29", "throughput": 9765.47, "total_tokens": 158438304}
{"current_steps": 2890, "total_steps": 4768, "loss": 0.3284, "lr": 3.3668302057684053e-06, "epoch": 1.212248322147651, "percentage": 60.61, "elapsed_time": "4:30:57", "remaining_time": "2:56:04", "throughput": 9761.88, "total_tokens": 158700368}
{"current_steps": 2895, "total_steps": 4768, "loss": 0.3135, "lr": 3.3512703090330023e-06, "epoch": 1.2143456375838926, "percentage": 60.72, "elapsed_time": "4:31:29", "remaining_time": "2:55:38", "throughput": 9760.41, "total_tokens": 158991528}
{"current_steps": 2900, "total_steps": 4768, "loss": 0.2896, "lr": 3.3357283066640472e-06, "epoch": 1.2164429530201342, "percentage": 60.82, "elapsed_time": "4:31:57", "remaining_time": "2:55:10", "throughput": 9760.66, "total_tokens": 159271952}
{"current_steps": 2905, "total_steps": 4768, "loss": 0.2813, "lr": 3.3202043673455194e-06, "epoch": 1.2185402684563758, "percentage": 60.93, "elapsed_time": "4:32:27", "remaining_time": "2:54:43", "throughput": 9760.07, "total_tokens": 159549168}
{"current_steps": 2910, "total_steps": 4768, "loss": 0.2939, "lr": 3.3046986595653528e-06, "epoch": 1.2206375838926173, "percentage": 61.03, "elapsed_time": "4:33:00", "remaining_time": "2:54:18", "throughput": 9757.45, "total_tokens": 159834544}
{"current_steps": 2915, "total_steps": 4768, "loss": 0.2968, "lr": 3.2892113516136055e-06, "epoch": 1.2227348993288591, "percentage": 61.14, "elapsed_time": "4:33:32", "remaining_time": "2:53:53", "throughput": 9755.06, "total_tokens": 160108616}
{"current_steps": 2920, "total_steps": 4768, "loss": 0.302, "lr": 3.273742611580637e-06, "epoch": 1.2248322147651007, "percentage": 61.24, "elapsed_time": "4:34:02", "remaining_time": "2:53:26", "throughput": 9753.0, "total_tokens": 160367928}
{"current_steps": 2925, "total_steps": 4768, "loss": 0.2862, "lr": 3.258292607355277e-06, "epoch": 1.2269295302013423, "percentage": 61.35, "elapsed_time": "4:34:29", "remaining_time": "2:52:57", "throughput": 9754.78, "total_tokens": 160660352}
{"current_steps": 2930, "total_steps": 4768, "loss": 0.3021, "lr": 3.242861506623015e-06, "epoch": 1.229026845637584, "percentage": 61.45, "elapsed_time": "4:34:58", "remaining_time": "2:52:29", "throughput": 9754.99, "total_tokens": 160940504}
{"current_steps": 2935, "total_steps": 4768, "loss": 0.2791, "lr": 3.227449476864164e-06, "epoch": 1.2311241610738255, "percentage": 61.56, "elapsed_time": "4:35:29", "remaining_time": "2:52:03", "throughput": 9753.11, "total_tokens": 161214096}
{"current_steps": 2940, "total_steps": 4768, "loss": 0.2995, "lr": 3.2120566853520574e-06, "epoch": 1.233221476510067, "percentage": 61.66, "elapsed_time": "4:35:59", "remaining_time": "2:51:36", "throughput": 9752.01, "total_tokens": 161491560}
{"current_steps": 2945, "total_steps": 4768, "loss": 0.2808, "lr": 3.1966832991512232e-06, "epoch": 1.2353187919463087, "percentage": 61.77, "elapsed_time": "4:36:26", "remaining_time": "2:51:07", "throughput": 9752.91, "total_tokens": 161763968}
{"current_steps": 2950, "total_steps": 4768, "loss": 0.2951, "lr": 3.1813294851155807e-06, "epoch": 1.2374161073825503, "percentage": 61.87, "elapsed_time": "4:36:54", "remaining_time": "2:50:38", "throughput": 9753.58, "total_tokens": 162049552}
{"current_steps": 2955, "total_steps": 4768, "loss": 0.2804, "lr": 3.1659954098866207e-06, "epoch": 1.239513422818792, "percentage": 61.98, "elapsed_time": "4:37:24", "remaining_time": "2:50:12", "throughput": 9752.85, "total_tokens": 162334584}
{"current_steps": 2960, "total_steps": 4768, "loss": 0.2814, "lr": 3.150681239891601e-06, "epoch": 1.2416107382550337, "percentage": 62.08, "elapsed_time": "4:37:53", "remaining_time": "2:49:44", "throughput": 9753.17, "total_tokens": 162615336}
{"current_steps": 2965, "total_steps": 4768, "loss": 0.3228, "lr": 3.135387141341738e-06, "epoch": 1.2437080536912752, "percentage": 62.19, "elapsed_time": "4:38:19", "remaining_time": "2:49:14", "throughput": 9754.2, "total_tokens": 162888392}
{"current_steps": 2970, "total_steps": 4768, "loss": 0.3037, "lr": 3.1201132802304056e-06, "epoch": 1.2458053691275168, "percentage": 62.29, "elapsed_time": "4:38:51", "remaining_time": "2:48:48", "throughput": 9752.91, "total_tokens": 163176384}
{"current_steps": 2975, "total_steps": 4768, "loss": 0.2811, "lr": 3.104859822331334e-06, "epoch": 1.2479026845637584, "percentage": 62.4, "elapsed_time": "4:39:15", "remaining_time": "2:48:18", "throughput": 9756.81, "total_tokens": 163475624}
{"current_steps": 2980, "total_steps": 4768, "loss": 0.2768, "lr": 3.0896269331968066e-06, "epoch": 1.25, "percentage": 62.5, "elapsed_time": "4:39:45", "remaining_time": "2:47:51", "throughput": 9755.22, "total_tokens": 163744288}
{"current_steps": 2985, "total_steps": 4768, "loss": 0.3136, "lr": 3.074414778155864e-06, "epoch": 1.2520973154362416, "percentage": 62.6, "elapsed_time": "4:40:16", "remaining_time": "2:47:24", "throughput": 9753.55, "total_tokens": 164022016}
{"current_steps": 2990, "total_steps": 4768, "loss": 0.311, "lr": 3.0592235223125135e-06, "epoch": 1.2541946308724832, "percentage": 62.71, "elapsed_time": "4:40:47", "remaining_time": "2:46:58", "throughput": 9751.66, "total_tokens": 164287808}
{"current_steps": 2995, "total_steps": 4768, "loss": 0.2986, "lr": 3.0440533305439312e-06, "epoch": 1.2562919463087248, "percentage": 62.81, "elapsed_time": "4:41:17", "remaining_time": "2:46:31", "throughput": 9749.36, "total_tokens": 164545552}
{"current_steps": 3000, "total_steps": 4768, "loss": 0.2984, "lr": 3.0289043674986794e-06, "epoch": 1.2583892617449663, "percentage": 62.92, "elapsed_time": "4:41:46", "remaining_time": "2:46:03", "throughput": 9747.49, "total_tokens": 164794064}
{"current_steps": 3005, "total_steps": 4768, "loss": 0.3261, "lr": 3.013776797594915e-06, "epoch": 1.260486577181208, "percentage": 63.02, "elapsed_time": "4:42:13", "remaining_time": "2:45:34", "throughput": 9747.72, "total_tokens": 165064848}
{"current_steps": 3010, "total_steps": 4768, "loss": 0.3053, "lr": 2.998670785018604e-06, "epoch": 1.2625838926174497, "percentage": 63.13, "elapsed_time": "4:42:42", "remaining_time": "2:45:07", "throughput": 9745.99, "total_tokens": 165317704}
{"current_steps": 3015, "total_steps": 4768, "loss": 0.3046, "lr": 2.983586493721741e-06, "epoch": 1.2646812080536913, "percentage": 63.23, "elapsed_time": "4:43:16", "remaining_time": "2:44:41", "throughput": 9743.67, "total_tokens": 165604096}
{"current_steps": 3020, "total_steps": 4768, "loss": 0.3048, "lr": 2.9685240874205767e-06, "epoch": 1.266778523489933, "percentage": 63.34, "elapsed_time": "4:43:38", "remaining_time": "2:44:10", "throughput": 9746.3, "total_tokens": 165871440}
{"current_steps": 3025, "total_steps": 4768, "loss": 0.3079, "lr": 2.9534837295938268e-06, "epoch": 1.2688758389261745, "percentage": 63.44, "elapsed_time": "4:44:07", "remaining_time": "2:43:42", "throughput": 9744.97, "total_tokens": 166130400}
{"current_steps": 3030, "total_steps": 4768, "loss": 0.3084, "lr": 2.9384655834809115e-06, "epoch": 1.270973154362416, "percentage": 63.55, "elapsed_time": "4:44:32", "remaining_time": "2:43:12", "throughput": 9745.31, "total_tokens": 166379376}
{"current_steps": 3035, "total_steps": 4768, "loss": 0.2882, "lr": 2.923469812080173e-06, "epoch": 1.2730704697986577, "percentage": 63.65, "elapsed_time": "4:45:01", "remaining_time": "2:42:45", "throughput": 9744.82, "total_tokens": 166655248}
{"current_steps": 3040, "total_steps": 4768, "loss": 0.3006, "lr": 2.908496578147115e-06, "epoch": 1.2751677852348993, "percentage": 63.76, "elapsed_time": "4:45:33", "remaining_time": "2:42:18", "throughput": 9743.22, "total_tokens": 166931784}
{"current_steps": 3045, "total_steps": 4768, "loss": 0.3113, "lr": 2.8935460441926298e-06, "epoch": 1.277265100671141, "percentage": 63.86, "elapsed_time": "4:46:00", "remaining_time": "2:41:50", "throughput": 9744.98, "total_tokens": 167225728}
{"current_steps": 3050, "total_steps": 4768, "loss": 0.3015, "lr": 2.878618372481238e-06, "epoch": 1.2793624161073827, "percentage": 63.97, "elapsed_time": "4:46:29", "remaining_time": "2:41:22", "throughput": 9742.26, "total_tokens": 167467040}
{"current_steps": 3055, "total_steps": 4768, "loss": 0.2936, "lr": 2.8637137250293267e-06, "epoch": 1.2814597315436242, "percentage": 64.07, "elapsed_time": "4:47:00", "remaining_time": "2:40:55", "throughput": 9740.69, "total_tokens": 167739728}
{"current_steps": 3060, "total_steps": 4768, "loss": 0.3042, "lr": 2.84883226360339e-06, "epoch": 1.2835570469798658, "percentage": 64.18, "elapsed_time": "4:47:28", "remaining_time": "2:40:27", "throughput": 9740.92, "total_tokens": 168016560}
{"current_steps": 3065, "total_steps": 4768, "loss": 0.3085, "lr": 2.8339741497182776e-06, "epoch": 1.2856543624161074, "percentage": 64.28, "elapsed_time": "4:48:01", "remaining_time": "2:40:02", "throughput": 9738.01, "total_tokens": 168288640}
{"current_steps": 3070, "total_steps": 4768, "loss": 0.3117, "lr": 2.8191395446354332e-06, "epoch": 1.287751677852349, "percentage": 64.39, "elapsed_time": "4:48:26", "remaining_time": "2:39:32", "throughput": 9739.81, "total_tokens": 168559912}
{"current_steps": 3075, "total_steps": 4768, "loss": 0.3051, "lr": 2.8043286093611544e-06, "epoch": 1.2898489932885906, "percentage": 64.49, "elapsed_time": "4:49:01", "remaining_time": "2:39:07", "throughput": 9735.59, "total_tokens": 168831096}
{"current_steps": 3080, "total_steps": 4768, "loss": 0.2779, "lr": 2.7895415046448372e-06, "epoch": 1.2919463087248322, "percentage": 64.6, "elapsed_time": "4:49:28", "remaining_time": "2:38:38", "throughput": 9736.59, "total_tokens": 169111592}
{"current_steps": 3085, "total_steps": 4768, "loss": 0.2842, "lr": 2.774778390977234e-06, "epoch": 1.2940436241610738, "percentage": 64.7, "elapsed_time": "4:49:57", "remaining_time": "2:38:11", "throughput": 9736.59, "total_tokens": 169397112}
{"current_steps": 3090, "total_steps": 4768, "loss": 0.3051, "lr": 2.7600394285887156e-06, "epoch": 1.2961409395973154, "percentage": 64.81, "elapsed_time": "4:50:29", "remaining_time": "2:37:44", "throughput": 9735.43, "total_tokens": 169681568}
{"current_steps": 3095, "total_steps": 4768, "loss": 0.327, "lr": 2.7453247774475237e-06, "epoch": 1.298238255033557, "percentage": 64.91, "elapsed_time": "4:50:57", "remaining_time": "2:37:16", "throughput": 9736.45, "total_tokens": 169974624}
{"current_steps": 3100, "total_steps": 4768, "loss": 0.2883, "lr": 2.730634597258044e-06, "epoch": 1.3003355704697985, "percentage": 65.02, "elapsed_time": "4:51:26", "remaining_time": "2:36:48", "throughput": 9736.61, "total_tokens": 170257600}
{"current_steps": 3105, "total_steps": 4768, "loss": 0.296, "lr": 2.715969047459066e-06, "epoch": 1.3024328859060403, "percentage": 65.12, "elapsed_time": "4:51:51", "remaining_time": "2:36:18", "throughput": 9737.94, "total_tokens": 170523024}
{"current_steps": 3110, "total_steps": 4768, "loss": 0.2922, "lr": 2.701328287222054e-06, "epoch": 1.304530201342282, "percentage": 65.23, "elapsed_time": "4:52:23", "remaining_time": "2:35:52", "throughput": 9736.14, "total_tokens": 170803176}
{"current_steps": 3115, "total_steps": 4768, "loss": 0.2984, "lr": 2.686712475449427e-06, "epoch": 1.3066275167785235, "percentage": 65.33, "elapsed_time": "4:52:55", "remaining_time": "2:35:26", "throughput": 9733.67, "total_tokens": 171076608}
{"current_steps": 3120, "total_steps": 4768, "loss": 0.3064, "lr": 2.6721217707728187e-06, "epoch": 1.308724832214765, "percentage": 65.44, "elapsed_time": "4:53:24", "remaining_time": "2:34:58", "throughput": 9732.35, "total_tokens": 171330520}
{"current_steps": 3125, "total_steps": 4768, "loss": 0.3091, "lr": 2.657556331551373e-06, "epoch": 1.3108221476510067, "percentage": 65.54, "elapsed_time": "4:53:52", "remaining_time": "2:34:30", "throughput": 9732.13, "total_tokens": 171605544}
{"current_steps": 3130, "total_steps": 4768, "loss": 0.2984, "lr": 2.6430163158700116e-06, "epoch": 1.3129194630872483, "percentage": 65.65, "elapsed_time": "4:54:18", "remaining_time": "2:34:01", "throughput": 9732.73, "total_tokens": 171864112}
{"current_steps": 3135, "total_steps": 4768, "loss": 0.3, "lr": 2.628501881537726e-06, "epoch": 1.3150167785234899, "percentage": 65.75, "elapsed_time": "4:54:45", "remaining_time": "2:33:32", "throughput": 9731.94, "total_tokens": 172117368}
{"current_steps": 3140, "total_steps": 4768, "loss": 0.307, "lr": 2.614013186085861e-06, "epoch": 1.3171140939597317, "percentage": 65.86, "elapsed_time": "4:55:18", "remaining_time": "2:33:06", "throughput": 9730.66, "total_tokens": 172408920}
{"current_steps": 3145, "total_steps": 4768, "loss": 0.3134, "lr": 2.5995503867664076e-06, "epoch": 1.3192114093959733, "percentage": 65.96, "elapsed_time": "4:55:42", "remaining_time": "2:32:36", "throughput": 9731.67, "total_tokens": 172667296}
{"current_steps": 3150, "total_steps": 4768, "loss": 0.2977, "lr": 2.5851136405502935e-06, "epoch": 1.3213087248322148, "percentage": 66.07, "elapsed_time": "4:56:10", "remaining_time": "2:32:07", "throughput": 9731.74, "total_tokens": 172934880}
{"current_steps": 3155, "total_steps": 4768, "loss": 0.292, "lr": 2.5707031041256815e-06, "epoch": 1.3234060402684564, "percentage": 66.17, "elapsed_time": "4:56:36", "remaining_time": "2:31:38", "throughput": 9732.72, "total_tokens": 173209976}
{"current_steps": 3160, "total_steps": 4768, "loss": 0.2829, "lr": 2.556318933896272e-06, "epoch": 1.325503355704698, "percentage": 66.28, "elapsed_time": "4:56:56", "remaining_time": "2:31:06", "throughput": 9738.62, "total_tokens": 173509272}
{"current_steps": 3165, "total_steps": 4768, "loss": 0.3031, "lr": 2.541961285979597e-06, "epoch": 1.3276006711409396, "percentage": 66.38, "elapsed_time": "4:57:28", "remaining_time": "2:30:39", "throughput": 9735.95, "total_tokens": 173767688}
{"current_steps": 3170, "total_steps": 4768, "loss": 0.3137, "lr": 2.5276303162053327e-06, "epoch": 1.3296979865771812, "percentage": 66.48, "elapsed_time": "4:57:56", "remaining_time": "2:30:11", "throughput": 9734.17, "total_tokens": 174016072}
{"current_steps": 3175, "total_steps": 4768, "loss": 0.309, "lr": 2.5133261801136026e-06, "epoch": 1.3317953020134228, "percentage": 66.59, "elapsed_time": "4:58:22", "remaining_time": "2:29:42", "throughput": 9734.84, "total_tokens": 174281568}
{"current_steps": 3180, "total_steps": 4768, "loss": 0.311, "lr": 2.4990490329533005e-06, "epoch": 1.3338926174496644, "percentage": 66.69, "elapsed_time": "4:58:51", "remaining_time": "2:29:14", "throughput": 9734.33, "total_tokens": 174554032}
{"current_steps": 3185, "total_steps": 4768, "loss": 0.3114, "lr": 2.4847990296803907e-06, "epoch": 1.335989932885906, "percentage": 66.8, "elapsed_time": "4:59:19", "remaining_time": "2:28:46", "throughput": 9735.21, "total_tokens": 174841368}
{"current_steps": 3190, "total_steps": 4768, "loss": 0.3003, "lr": 2.4705763249562364e-06, "epoch": 1.3380872483221475, "percentage": 66.9, "elapsed_time": "4:59:47", "remaining_time": "2:28:17", "throughput": 9736.53, "total_tokens": 175136432}
{"current_steps": 3195, "total_steps": 4768, "loss": 0.2866, "lr": 2.4563810731459164e-06, "epoch": 1.3401845637583891, "percentage": 67.01, "elapsed_time": "5:00:19", "remaining_time": "2:27:51", "throughput": 9733.65, "total_tokens": 175393440}
{"current_steps": 3200, "total_steps": 4768, "loss": 0.2984, "lr": 2.442213428316551e-06, "epoch": 1.342281879194631, "percentage": 67.11, "elapsed_time": "5:00:45", "remaining_time": "2:27:22", "throughput": 9735.73, "total_tokens": 175683688}
{"current_steps": 3205, "total_steps": 4768, "loss": 0.3181, "lr": 2.4280735442356355e-06, "epoch": 1.3443791946308725, "percentage": 67.22, "elapsed_time": "5:01:07", "remaining_time": "2:26:51", "throughput": 9738.1, "total_tokens": 175945592}
{"current_steps": 3210, "total_steps": 4768, "loss": 0.286, "lr": 2.413961574369359e-06, "epoch": 1.346476510067114, "percentage": 67.32, "elapsed_time": "5:01:32", "remaining_time": "2:26:21", "throughput": 9737.84, "total_tokens": 176181320}
{"current_steps": 3215, "total_steps": 4768, "loss": 0.3262, "lr": 2.3998776718809495e-06, "epoch": 1.3485738255033557, "percentage": 67.43, "elapsed_time": "5:01:58", "remaining_time": "2:25:52", "throughput": 9738.0, "total_tokens": 176442272}
{"current_steps": 3220, "total_steps": 4768, "loss": 0.3019, "lr": 2.3858219896290064e-06, "epoch": 1.3506711409395973, "percentage": 67.53, "elapsed_time": "5:02:31", "remaining_time": "2:25:26", "throughput": 9735.64, "total_tokens": 176715760}
{"current_steps": 3225, "total_steps": 4768, "loss": 0.2832, "lr": 2.3717946801658415e-06, "epoch": 1.3527684563758389, "percentage": 67.64, "elapsed_time": "5:02:58", "remaining_time": "2:24:57", "throughput": 9737.08, "total_tokens": 177003536}
{"current_steps": 3230, "total_steps": 4768, "loss": 0.2933, "lr": 2.3577958957358304e-06, "epoch": 1.3548657718120805, "percentage": 67.74, "elapsed_time": "5:03:33", "remaining_time": "2:24:32", "throughput": 9733.99, "total_tokens": 177286504}
{"current_steps": 3235, "total_steps": 4768, "loss": 0.3324, "lr": 2.3438257882737486e-06, "epoch": 1.3569630872483223, "percentage": 67.85, "elapsed_time": "5:04:05", "remaining_time": "2:24:06", "throughput": 9732.43, "total_tokens": 177577840}
{"current_steps": 3240, "total_steps": 4768, "loss": 0.3076, "lr": 2.3298845094031296e-06, "epoch": 1.3590604026845639, "percentage": 67.95, "elapsed_time": "5:04:36", "remaining_time": "2:23:39", "throughput": 9731.24, "total_tokens": 177849368}
{"current_steps": 3245, "total_steps": 4768, "loss": 0.3098, "lr": 2.3159722104346187e-06, "epoch": 1.3611577181208054, "percentage": 68.06, "elapsed_time": "5:05:00", "remaining_time": "2:23:08", "throughput": 9733.25, "total_tokens": 178119872}
{"current_steps": 3250, "total_steps": 4768, "loss": 0.2829, "lr": 2.3020890423643273e-06, "epoch": 1.363255033557047, "percentage": 68.16, "elapsed_time": "5:05:30", "remaining_time": "2:22:41", "throughput": 9733.09, "total_tokens": 178415000}
{"current_steps": 3255, "total_steps": 4768, "loss": 0.2813, "lr": 2.288235155872203e-06, "epoch": 1.3653523489932886, "percentage": 68.27, "elapsed_time": "5:06:00", "remaining_time": "2:22:14", "throughput": 9733.79, "total_tokens": 178717048}
{"current_steps": 3260, "total_steps": 4768, "loss": 0.306, "lr": 2.2744107013203825e-06, "epoch": 1.3674496644295302, "percentage": 68.37, "elapsed_time": "5:06:27", "remaining_time": "2:21:45", "throughput": 9734.77, "total_tokens": 178998536}
{"current_steps": 3265, "total_steps": 4768, "loss": 0.3293, "lr": 2.2606158287515662e-06, "epoch": 1.3695469798657718, "percentage": 68.48, "elapsed_time": "5:06:57", "remaining_time": "2:21:18", "throughput": 9733.23, "total_tokens": 179262016}
{"current_steps": 3270, "total_steps": 4768, "loss": 0.2754, "lr": 2.246850687887389e-06, "epoch": 1.3716442953020134, "percentage": 68.58, "elapsed_time": "5:07:20", "remaining_time": "2:20:47", "throughput": 9735.75, "total_tokens": 179532592}
{"current_steps": 3275, "total_steps": 4768, "loss": 0.3185, "lr": 2.2331154281267952e-06, "epoch": 1.373741610738255, "percentage": 68.69, "elapsed_time": "5:07:51", "remaining_time": "2:20:20", "throughput": 9731.78, "total_tokens": 179763872}
{"current_steps": 3280, "total_steps": 4768, "loss": 0.2905, "lr": 2.2194101985444146e-06, "epoch": 1.3758389261744965, "percentage": 68.79, "elapsed_time": "5:08:17", "remaining_time": "2:19:51", "throughput": 9733.28, "total_tokens": 180046152}
{"current_steps": 3285, "total_steps": 4768, "loss": 0.289, "lr": 2.205735147888952e-06, "epoch": 1.3779362416107381, "percentage": 68.9, "elapsed_time": "5:08:43", "remaining_time": "2:19:22", "throughput": 9732.98, "total_tokens": 180287088}
{"current_steps": 3290, "total_steps": 4768, "loss": 0.2889, "lr": 2.192090424581561e-06, "epoch": 1.38003355704698, "percentage": 69.0, "elapsed_time": "5:09:07", "remaining_time": "2:18:52", "throughput": 9735.0, "total_tokens": 180556520}
{"current_steps": 3295, "total_steps": 4768, "loss": 0.2887, "lr": 2.178476176714243e-06, "epoch": 1.3821308724832215, "percentage": 69.11, "elapsed_time": "5:09:38", "remaining_time": "2:18:25", "throughput": 9733.76, "total_tokens": 180837552}
{"current_steps": 3300, "total_steps": 4768, "loss": 0.303, "lr": 2.1648925520482384e-06, "epoch": 1.3842281879194631, "percentage": 69.21, "elapsed_time": "5:10:08", "remaining_time": "2:17:58", "throughput": 9733.26, "total_tokens": 181124048}
{"current_steps": 3305, "total_steps": 4768, "loss": 0.2994, "lr": 2.151339698012417e-06, "epoch": 1.3863255033557047, "percentage": 69.32, "elapsed_time": "5:10:41", "remaining_time": "2:17:31", "throughput": 9730.94, "total_tokens": 181395600}
{"current_steps": 3310, "total_steps": 4768, "loss": 0.3078, "lr": 2.1378177617016834e-06, "epoch": 1.3884228187919463, "percentage": 69.42, "elapsed_time": "5:11:10", "remaining_time": "2:17:04", "throughput": 9729.92, "total_tokens": 181663816}
{"current_steps": 3315, "total_steps": 4768, "loss": 0.3148, "lr": 2.124326889875378e-06, "epoch": 1.3905201342281879, "percentage": 69.53, "elapsed_time": "5:11:37", "remaining_time": "2:16:35", "throughput": 9730.92, "total_tokens": 181942136}
{"current_steps": 3320, "total_steps": 4768, "loss": 0.3139, "lr": 2.110867228955687e-06, "epoch": 1.3926174496644295, "percentage": 69.63, "elapsed_time": "5:12:06", "remaining_time": "2:16:07", "throughput": 9730.34, "total_tokens": 182212976}
{"current_steps": 3325, "total_steps": 4768, "loss": 0.2867, "lr": 2.09743892502605e-06, "epoch": 1.3947147651006713, "percentage": 69.74, "elapsed_time": "5:12:40", "remaining_time": "2:15:41", "throughput": 9726.69, "total_tokens": 182476616}
{"current_steps": 3330, "total_steps": 4768, "loss": 0.3007, "lr": 2.0840421238295742e-06, "epoch": 1.3968120805369129, "percentage": 69.84, "elapsed_time": "5:13:05", "remaining_time": "2:15:12", "throughput": 9729.33, "total_tokens": 182773464}
{"current_steps": 3335, "total_steps": 4768, "loss": 0.3271, "lr": 2.07067697076746e-06, "epoch": 1.3989093959731544, "percentage": 69.95, "elapsed_time": "5:13:30", "remaining_time": "2:14:42", "throughput": 9730.75, "total_tokens": 183043880}
{"current_steps": 3340, "total_steps": 4768, "loss": 0.3166, "lr": 2.05734361089741e-06, "epoch": 1.401006711409396, "percentage": 70.05, "elapsed_time": "5:14:00", "remaining_time": "2:14:15", "throughput": 9731.07, "total_tokens": 183338424}
{"current_steps": 3345, "total_steps": 4768, "loss": 0.2919, "lr": 2.044042188932068e-06, "epoch": 1.4031040268456376, "percentage": 70.16, "elapsed_time": "5:14:28", "remaining_time": "2:13:46", "throughput": 9733.12, "total_tokens": 183650952}
{"current_steps": 3350, "total_steps": 4768, "loss": 0.3033, "lr": 2.0307728492374375e-06, "epoch": 1.4052013422818792, "percentage": 70.26, "elapsed_time": "5:14:58", "remaining_time": "2:13:19", "throughput": 9732.73, "total_tokens": 183935440}
{"current_steps": 3355, "total_steps": 4768, "loss": 0.2989, "lr": 2.0175357358313204e-06, "epoch": 1.4072986577181208, "percentage": 70.36, "elapsed_time": "5:15:24", "remaining_time": "2:12:50", "throughput": 9735.14, "total_tokens": 184229448}
{"current_steps": 3360, "total_steps": 4768, "loss": 0.3129, "lr": 2.0043309923817537e-06, "epoch": 1.4093959731543624, "percentage": 70.47, "elapsed_time": "5:15:59", "remaining_time": "2:12:24", "throughput": 9732.9, "total_tokens": 184528016}
{"current_steps": 3365, "total_steps": 4768, "loss": 0.3049, "lr": 1.9911587622054506e-06, "epoch": 1.411493288590604, "percentage": 70.57, "elapsed_time": "5:16:29", "remaining_time": "2:11:57", "throughput": 9731.62, "total_tokens": 184799328}
{"current_steps": 3370, "total_steps": 4768, "loss": 0.3079, "lr": 1.978019188266241e-06, "epoch": 1.4135906040268456, "percentage": 70.68, "elapsed_time": "5:16:54", "remaining_time": "2:11:28", "throughput": 9733.18, "total_tokens": 185074856}
{"current_steps": 3375, "total_steps": 4768, "loss": 0.2799, "lr": 1.9649124131735253e-06, "epoch": 1.4156879194630871, "percentage": 70.78, "elapsed_time": "5:17:26", "remaining_time": "2:11:01", "throughput": 9731.07, "total_tokens": 185344416}
{"current_steps": 3380, "total_steps": 4768, "loss": 0.2949, "lr": 1.9518385791807225e-06, "epoch": 1.4177852348993287, "percentage": 70.89, "elapsed_time": "5:17:53", "remaining_time": "2:10:32", "throughput": 9731.3, "total_tokens": 185611192}
{"current_steps": 3385, "total_steps": 4768, "loss": 0.3018, "lr": 1.938797828183727e-06, "epoch": 1.4198825503355705, "percentage": 70.99, "elapsed_time": "5:18:20", "remaining_time": "2:10:03", "throughput": 9732.72, "total_tokens": 185897432}
{"current_steps": 3390, "total_steps": 4768, "loss": 0.2901, "lr": 1.925790301719374e-06, "epoch": 1.4219798657718121, "percentage": 71.1, "elapsed_time": "5:18:55", "remaining_time": "2:09:38", "throughput": 9730.25, "total_tokens": 186194200}
{"current_steps": 3395, "total_steps": 4768, "loss": 0.2959, "lr": 1.912816140963892e-06, "epoch": 1.4240771812080537, "percentage": 71.2, "elapsed_time": "5:19:26", "remaining_time": "2:09:11", "throughput": 9729.58, "total_tokens": 186479840}
{"current_steps": 3400, "total_steps": 4768, "loss": 0.2843, "lr": 1.899875486731384e-06, "epoch": 1.4261744966442953, "percentage": 71.31, "elapsed_time": "5:19:59", "remaining_time": "2:08:44", "throughput": 9727.2, "total_tokens": 186756088}
{"current_steps": 3405, "total_steps": 4768, "loss": 0.3195, "lr": 1.886968479472287e-06, "epoch": 1.4282718120805369, "percentage": 71.41, "elapsed_time": "5:20:28", "remaining_time": "2:08:16", "throughput": 9727.82, "total_tokens": 187049568}
{"current_steps": 3410, "total_steps": 4768, "loss": 0.2836, "lr": 1.8740952592718553e-06, "epoch": 1.4303691275167785, "percentage": 71.52, "elapsed_time": "5:20:55", "remaining_time": "2:07:48", "throughput": 9728.61, "total_tokens": 187328240}
{"current_steps": 3415, "total_steps": 4768, "loss": 0.3021, "lr": 1.8612559658486373e-06, "epoch": 1.43246644295302, "percentage": 71.62, "elapsed_time": "5:21:30", "remaining_time": "2:07:22", "throughput": 9725.07, "total_tokens": 187603168}
{"current_steps": 3420, "total_steps": 4768, "loss": 0.3025, "lr": 1.8484507385529605e-06, "epoch": 1.4345637583892619, "percentage": 71.73, "elapsed_time": "5:21:58", "remaining_time": "2:06:54", "throughput": 9724.93, "total_tokens": 187874864}
{"current_steps": 3425, "total_steps": 4768, "loss": 0.3143, "lr": 1.8356797163654172e-06, "epoch": 1.4366610738255035, "percentage": 71.83, "elapsed_time": "5:22:24", "remaining_time": "2:06:25", "throughput": 9726.01, "total_tokens": 188147240}
{"current_steps": 3430, "total_steps": 4768, "loss": 0.2753, "lr": 1.8229430378953578e-06, "epoch": 1.438758389261745, "percentage": 71.94, "elapsed_time": "5:22:51", "remaining_time": "2:05:56", "throughput": 9726.12, "total_tokens": 188410520}
{"current_steps": 3435, "total_steps": 4768, "loss": 0.2992, "lr": 1.8102408413793838e-06, "epoch": 1.4408557046979866, "percentage": 72.04, "elapsed_time": "5:23:19", "remaining_time": "2:05:28", "throughput": 9725.44, "total_tokens": 188665784}
{"current_steps": 3440, "total_steps": 4768, "loss": 0.2938, "lr": 1.7975732646798534e-06, "epoch": 1.4429530201342282, "percentage": 72.15, "elapsed_time": "5:23:55", "remaining_time": "2:05:03", "throughput": 9721.03, "total_tokens": 188935928}
{"current_steps": 3445, "total_steps": 4768, "loss": 0.3024, "lr": 1.7849404452833763e-06, "epoch": 1.4450503355704698, "percentage": 72.25, "elapsed_time": "5:24:22", "remaining_time": "2:04:34", "throughput": 9720.97, "total_tokens": 189193448}
{"current_steps": 3450, "total_steps": 4768, "loss": 0.2955, "lr": 1.7723425202993315e-06, "epoch": 1.4471476510067114, "percentage": 72.36, "elapsed_time": "5:24:46", "remaining_time": "2:04:04", "throughput": 9722.4, "total_tokens": 189459904}
{"current_steps": 3455, "total_steps": 4768, "loss": 0.3007, "lr": 1.75977962645837e-06, "epoch": 1.449244966442953, "percentage": 72.46, "elapsed_time": "5:25:14", "remaining_time": "2:03:35", "throughput": 9722.78, "total_tokens": 189732856}
{"current_steps": 3460, "total_steps": 4768, "loss": 0.2919, "lr": 1.747251900110936e-06, "epoch": 1.4513422818791946, "percentage": 72.57, "elapsed_time": "5:25:43", "remaining_time": "2:03:08", "throughput": 9721.27, "total_tokens": 189986368}
{"current_steps": 3465, "total_steps": 4768, "loss": 0.297, "lr": 1.7347594772257863e-06, "epoch": 1.4534395973154361, "percentage": 72.67, "elapsed_time": "5:26:16", "remaining_time": "2:02:41", "throughput": 9718.51, "total_tokens": 190250816}
{"current_steps": 3470, "total_steps": 4768, "loss": 0.2895, "lr": 1.7223024933885142e-06, "epoch": 1.4555369127516777, "percentage": 72.78, "elapsed_time": "5:26:42", "remaining_time": "2:02:12", "throughput": 9719.73, "total_tokens": 190527928}
{"current_steps": 3475, "total_steps": 4768, "loss": 0.2978, "lr": 1.7098810838000768e-06, "epoch": 1.4576342281879195, "percentage": 72.88, "elapsed_time": "5:27:09", "remaining_time": "2:01:43", "throughput": 9720.22, "total_tokens": 190798232}
{"current_steps": 3480, "total_steps": 4768, "loss": 0.3088, "lr": 1.6974953832753282e-06, "epoch": 1.4597315436241611, "percentage": 72.99, "elapsed_time": "5:27:32", "remaining_time": "2:01:13", "throughput": 9723.23, "total_tokens": 191083456}
{"current_steps": 3485, "total_steps": 4768, "loss": 0.3105, "lr": 1.6851455262415623e-06, "epoch": 1.4618288590604027, "percentage": 73.09, "elapsed_time": "5:28:01", "remaining_time": "2:00:45", "throughput": 9722.78, "total_tokens": 191363136}
{"current_steps": 3490, "total_steps": 4768, "loss": 0.283, "lr": 1.6728316467370414e-06, "epoch": 1.4639261744966443, "percentage": 73.2, "elapsed_time": "5:28:31", "remaining_time": "2:00:18", "throughput": 9721.39, "total_tokens": 191627640}
{"current_steps": 3495, "total_steps": 4768, "loss": 0.3086, "lr": 1.6605538784095515e-06, "epoch": 1.466023489932886, "percentage": 73.3, "elapsed_time": "5:29:01", "remaining_time": "1:59:50", "throughput": 9720.68, "total_tokens": 191896264}
{"current_steps": 3500, "total_steps": 4768, "loss": 0.2916, "lr": 1.6483123545149466e-06, "epoch": 1.4681208053691275, "percentage": 73.41, "elapsed_time": "5:29:29", "remaining_time": "1:59:22", "throughput": 9720.78, "total_tokens": 192170944}
{"current_steps": 3505, "total_steps": 4768, "loss": 0.2849, "lr": 1.6361072079157092e-06, "epoch": 1.470218120805369, "percentage": 73.51, "elapsed_time": "5:29:57", "remaining_time": "1:58:54", "throughput": 9720.99, "total_tokens": 192455464}
{"current_steps": 3510, "total_steps": 4768, "loss": 0.3121, "lr": 1.6239385710794986e-06, "epoch": 1.4723154362416109, "percentage": 73.62, "elapsed_time": "5:30:32", "remaining_time": "1:58:28", "throughput": 9718.79, "total_tokens": 192750728}
{"current_steps": 3515, "total_steps": 4768, "loss": 0.2824, "lr": 1.6118065760777202e-06, "epoch": 1.4744127516778525, "percentage": 73.72, "elapsed_time": "5:30:59", "remaining_time": "1:57:59", "throughput": 9719.84, "total_tokens": 193035544}
{"current_steps": 3520, "total_steps": 4768, "loss": 0.2911, "lr": 1.5997113545840892e-06, "epoch": 1.476510067114094, "percentage": 73.83, "elapsed_time": "5:31:28", "remaining_time": "1:57:31", "throughput": 9718.36, "total_tokens": 193284160}
{"current_steps": 3525, "total_steps": 4768, "loss": 0.2746, "lr": 1.587653037873203e-06, "epoch": 1.4786073825503356, "percentage": 73.93, "elapsed_time": "5:31:56", "remaining_time": "1:57:03", "throughput": 9717.51, "total_tokens": 193537744}
{"current_steps": 3530, "total_steps": 4768, "loss": 0.2898, "lr": 1.5756317568191126e-06, "epoch": 1.4807046979865772, "percentage": 74.04, "elapsed_time": "5:32:15", "remaining_time": "1:56:31", "throughput": 9721.14, "total_tokens": 193799296}
{"current_steps": 3535, "total_steps": 4768, "loss": 0.2969, "lr": 1.5636476418939123e-06, "epoch": 1.4828020134228188, "percentage": 74.14, "elapsed_time": "5:32:42", "remaining_time": "1:56:02", "throughput": 9721.85, "total_tokens": 194068016}
{"current_steps": 3540, "total_steps": 4768, "loss": 0.2977, "lr": 1.5517008231663094e-06, "epoch": 1.4848993288590604, "percentage": 74.24, "elapsed_time": "5:33:14", "remaining_time": "1:55:36", "throughput": 9720.11, "total_tokens": 194350432}
{"current_steps": 3545, "total_steps": 4768, "loss": 0.2919, "lr": 1.5397914303002227e-06, "epoch": 1.486996644295302, "percentage": 74.35, "elapsed_time": "5:33:41", "remaining_time": "1:55:07", "throughput": 9720.28, "total_tokens": 194613944}
{"current_steps": 3550, "total_steps": 4768, "loss": 0.2955, "lr": 1.5279195925533708e-06, "epoch": 1.4890939597315436, "percentage": 74.45, "elapsed_time": "5:34:08", "remaining_time": "1:54:38", "throughput": 9721.02, "total_tokens": 194895960}
{"current_steps": 3555, "total_steps": 4768, "loss": 0.2829, "lr": 1.5160854387758738e-06, "epoch": 1.4911912751677852, "percentage": 74.56, "elapsed_time": "5:34:34", "remaining_time": "1:54:09", "throughput": 9722.75, "total_tokens": 195178792}
{"current_steps": 3560, "total_steps": 4768, "loss": 0.2765, "lr": 1.5042890974088487e-06, "epoch": 1.4932885906040267, "percentage": 74.66, "elapsed_time": "5:35:01", "remaining_time": "1:53:40", "throughput": 9723.45, "total_tokens": 195453800}
{"current_steps": 3565, "total_steps": 4768, "loss": 0.3313, "lr": 1.4925306964830183e-06, "epoch": 1.4953859060402683, "percentage": 74.77, "elapsed_time": "5:35:31", "remaining_time": "1:53:13", "throughput": 9722.49, "total_tokens": 195725768}
{"current_steps": 3570, "total_steps": 4768, "loss": 0.3069, "lr": 1.4808103636173226e-06, "epoch": 1.4974832214765101, "percentage": 74.87, "elapsed_time": "5:36:01", "remaining_time": "1:52:45", "throughput": 9721.31, "total_tokens": 195991904}
{"current_steps": 3575, "total_steps": 4768, "loss": 0.2634, "lr": 1.469128226017531e-06, "epoch": 1.4995805369127517, "percentage": 74.98, "elapsed_time": "5:36:22", "remaining_time": "1:52:15", "throughput": 9724.99, "total_tokens": 196278040}
{"current_steps": 3580, "total_steps": 4768, "loss": 0.3085, "lr": 1.4574844104748676e-06, "epoch": 1.5016778523489933, "percentage": 75.08, "elapsed_time": "5:36:49", "remaining_time": "1:51:46", "throughput": 9725.07, "total_tokens": 196540896}
{"current_steps": 3585, "total_steps": 4768, "loss": 0.3004, "lr": 1.4458790433646264e-06, "epoch": 1.503775167785235, "percentage": 75.19, "elapsed_time": "5:37:19", "remaining_time": "1:51:18", "throughput": 9724.95, "total_tokens": 196832760}
{"current_steps": 3590, "total_steps": 4768, "loss": 0.2748, "lr": 1.4343122506448065e-06, "epoch": 1.5058724832214765, "percentage": 75.29, "elapsed_time": "5:37:41", "remaining_time": "1:50:48", "throughput": 9727.51, "total_tokens": 197093168}
{"current_steps": 3595, "total_steps": 4768, "loss": 0.304, "lr": 1.4227841578547413e-06, "epoch": 1.507969798657718, "percentage": 75.4, "elapsed_time": "5:38:06", "remaining_time": "1:50:19", "throughput": 9730.24, "total_tokens": 197396800}
{"current_steps": 3600, "total_steps": 4768, "loss": 0.2839, "lr": 1.4112948901137392e-06, "epoch": 1.5100671140939599, "percentage": 75.5, "elapsed_time": "5:38:37", "remaining_time": "1:49:51", "throughput": 9730.05, "total_tokens": 197688248}
{"current_steps": 3605, "total_steps": 4768, "loss": 0.3272, "lr": 1.3998445721197197e-06, "epoch": 1.5121644295302015, "percentage": 75.61, "elapsed_time": "5:39:06", "remaining_time": "1:49:23", "throughput": 9729.49, "total_tokens": 197956712}
{"current_steps": 3610, "total_steps": 4768, "loss": 0.2725, "lr": 1.3884333281478707e-06, "epoch": 1.514261744966443, "percentage": 75.71, "elapsed_time": "5:39:27", "remaining_time": "1:48:53", "throughput": 9732.45, "total_tokens": 198227880}
{"current_steps": 3615, "total_steps": 4768, "loss": 0.2952, "lr": 1.3770612820492879e-06, "epoch": 1.5163590604026846, "percentage": 75.82, "elapsed_time": "5:39:56", "remaining_time": "1:48:25", "throughput": 9733.08, "total_tokens": 198521216}
{"current_steps": 3620, "total_steps": 4768, "loss": 0.2972, "lr": 1.365728557249636e-06, "epoch": 1.5184563758389262, "percentage": 75.92, "elapsed_time": "5:40:26", "remaining_time": "1:47:57", "throughput": 9733.27, "total_tokens": 198814072}
{"current_steps": 3625, "total_steps": 4768, "loss": 0.3125, "lr": 1.354435276747813e-06, "epoch": 1.5205536912751678, "percentage": 76.03, "elapsed_time": "5:40:53", "remaining_time": "1:47:29", "throughput": 9733.74, "total_tokens": 199085608}
{"current_steps": 3630, "total_steps": 4768, "loss": 0.2869, "lr": 1.3431815631146068e-06, "epoch": 1.5226510067114094, "percentage": 76.13, "elapsed_time": "5:41:20", "remaining_time": "1:47:00", "throughput": 9734.17, "total_tokens": 199363880}
{"current_steps": 3635, "total_steps": 4768, "loss": 0.2999, "lr": 1.3319675384913705e-06, "epoch": 1.524748322147651, "percentage": 76.24, "elapsed_time": "5:41:49", "remaining_time": "1:46:32", "throughput": 9733.87, "total_tokens": 199640608}
{"current_steps": 3640, "total_steps": 4768, "loss": 0.3043, "lr": 1.3207933245886956e-06, "epoch": 1.5268456375838926, "percentage": 76.34, "elapsed_time": "5:42:14", "remaining_time": "1:46:03", "throughput": 9735.02, "total_tokens": 199903400}
{"current_steps": 3645, "total_steps": 4768, "loss": 0.2839, "lr": 1.3096590426850913e-06, "epoch": 1.5289429530201342, "percentage": 76.45, "elapsed_time": "5:42:40", "remaining_time": "1:45:34", "throughput": 9736.66, "total_tokens": 200189480}
{"current_steps": 3650, "total_steps": 4768, "loss": 0.3015, "lr": 1.2985648136256673e-06, "epoch": 1.5310402684563758, "percentage": 76.55, "elapsed_time": "5:43:04", "remaining_time": "1:45:05", "throughput": 9738.38, "total_tokens": 200459560}
{"current_steps": 3655, "total_steps": 4768, "loss": 0.2878, "lr": 1.287510757820823e-06, "epoch": 1.5331375838926173, "percentage": 76.66, "elapsed_time": "5:43:32", "remaining_time": "1:44:36", "throughput": 9738.21, "total_tokens": 200728264}
{"current_steps": 3660, "total_steps": 4768, "loss": 0.3082, "lr": 1.276496995244938e-06, "epoch": 1.535234899328859, "percentage": 76.76, "elapsed_time": "5:43:59", "remaining_time": "1:44:08", "throughput": 9738.82, "total_tokens": 201001792}
{"current_steps": 3665, "total_steps": 4768, "loss": 0.3121, "lr": 1.2655236454350777e-06, "epoch": 1.5373322147651005, "percentage": 76.87, "elapsed_time": "5:44:28", "remaining_time": "1:43:40", "throughput": 9738.9, "total_tokens": 201292912}
{"current_steps": 3670, "total_steps": 4768, "loss": 0.3101, "lr": 1.254590827489684e-06, "epoch": 1.5394295302013423, "percentage": 76.97, "elapsed_time": "5:44:49", "remaining_time": "1:43:09", "throughput": 9743.22, "total_tokens": 201583168}
{"current_steps": 3675, "total_steps": 4768, "loss": 0.2847, "lr": 1.2436986600672962e-06, "epoch": 1.541526845637584, "percentage": 77.08, "elapsed_time": "5:45:15", "remaining_time": "1:42:41", "throughput": 9744.55, "total_tokens": 201866960}
{"current_steps": 3680, "total_steps": 4768, "loss": 0.2893, "lr": 1.23284726138525e-06, "epoch": 1.5436241610738255, "percentage": 77.18, "elapsed_time": "5:45:48", "remaining_time": "1:42:14", "throughput": 9742.76, "total_tokens": 202150640}
{"current_steps": 3685, "total_steps": 4768, "loss": 0.3039, "lr": 1.2220367492184038e-06, "epoch": 1.545721476510067, "percentage": 77.29, "elapsed_time": "5:46:17", "remaining_time": "1:41:46", "throughput": 9742.34, "total_tokens": 202422928}
{"current_steps": 3690, "total_steps": 4768, "loss": 0.291, "lr": 1.2112672408978555e-06, "epoch": 1.5478187919463087, "percentage": 77.39, "elapsed_time": "5:46:38", "remaining_time": "1:41:16", "throughput": 9746.26, "total_tokens": 202706216}
{"current_steps": 3695, "total_steps": 4768, "loss": 0.2919, "lr": 1.2005388533096719e-06, "epoch": 1.5499161073825505, "percentage": 77.5, "elapsed_time": "5:47:07", "remaining_time": "1:40:48", "throughput": 9746.89, "total_tokens": 203001376}
{"current_steps": 3700, "total_steps": 4768, "loss": 0.3205, "lr": 1.189851702893619e-06, "epoch": 1.552013422818792, "percentage": 77.6, "elapsed_time": "5:47:34", "remaining_time": "1:40:19", "throughput": 9747.22, "total_tokens": 203269776}
{"current_steps": 3705, "total_steps": 4768, "loss": 0.2992, "lr": 1.179205905641898e-06, "epoch": 1.5541107382550337, "percentage": 77.71, "elapsed_time": "5:48:04", "remaining_time": "1:39:52", "throughput": 9745.48, "total_tokens": 203532696}
{"current_steps": 3710, "total_steps": 4768, "loss": 0.2883, "lr": 1.1686015770978842e-06, "epoch": 1.5562080536912752, "percentage": 77.81, "elapsed_time": "5:48:36", "remaining_time": "1:39:24", "throughput": 9744.7, "total_tokens": 203824936}
{"current_steps": 3715, "total_steps": 4768, "loss": 0.2989, "lr": 1.1580388323548814e-06, "epoch": 1.5583053691275168, "percentage": 77.92, "elapsed_time": "5:49:10", "remaining_time": "1:38:58", "throughput": 9741.2, "total_tokens": 204084440}
{"current_steps": 3720, "total_steps": 4768, "loss": 0.3013, "lr": 1.147517786054859e-06, "epoch": 1.5604026845637584, "percentage": 78.02, "elapsed_time": "5:49:37", "remaining_time": "1:38:29", "throughput": 9740.69, "total_tokens": 204338816}
{"current_steps": 3725, "total_steps": 4768, "loss": 0.3029, "lr": 1.137038552387223e-06, "epoch": 1.5625, "percentage": 78.12, "elapsed_time": "5:50:04", "remaining_time": "1:38:01", "throughput": 9741.7, "total_tokens": 204623000}
{"current_steps": 3730, "total_steps": 4768, "loss": 0.3104, "lr": 1.1266012450875636e-06, "epoch": 1.5645973154362416, "percentage": 78.23, "elapsed_time": "5:50:31", "remaining_time": "1:37:32", "throughput": 9741.42, "total_tokens": 204877480}
{"current_steps": 3735, "total_steps": 4768, "loss": 0.2953, "lr": 1.1162059774364276e-06, "epoch": 1.5666946308724832, "percentage": 78.33, "elapsed_time": "5:51:02", "remaining_time": "1:37:05", "throughput": 9740.5, "total_tokens": 205156864}
{"current_steps": 3740, "total_steps": 4768, "loss": 0.2908, "lr": 1.1058528622580884e-06, "epoch": 1.5687919463087248, "percentage": 78.44, "elapsed_time": "5:51:28", "remaining_time": "1:36:36", "throughput": 9742.08, "total_tokens": 205442032}
{"current_steps": 3745, "total_steps": 4768, "loss": 0.3125, "lr": 1.09554201191932e-06, "epoch": 1.5708892617449663, "percentage": 78.54, "elapsed_time": "5:51:55", "remaining_time": "1:36:08", "throughput": 9741.84, "total_tokens": 205708304}
{"current_steps": 3750, "total_steps": 4768, "loss": 0.2996, "lr": 1.0852735383281786e-06, "epoch": 1.572986577181208, "percentage": 78.65, "elapsed_time": "5:52:26", "remaining_time": "1:35:40", "throughput": 9741.8, "total_tokens": 206001152}
{"current_steps": 3755, "total_steps": 4768, "loss": 0.3061, "lr": 1.0750475529327863e-06, "epoch": 1.5750838926174495, "percentage": 78.75, "elapsed_time": "5:52:51", "remaining_time": "1:35:11", "throughput": 9742.61, "total_tokens": 206270616}
{"current_steps": 3760, "total_steps": 4768, "loss": 0.3057, "lr": 1.0648641667201237e-06, "epoch": 1.5771812080536913, "percentage": 78.86, "elapsed_time": "5:53:30", "remaining_time": "1:34:46", "throughput": 9737.83, "total_tokens": 206541888}
{"current_steps": 3765, "total_steps": 4768, "loss": 0.2855, "lr": 1.054723490214825e-06, "epoch": 1.579278523489933, "percentage": 78.96, "elapsed_time": "5:53:56", "remaining_time": "1:34:17", "throughput": 9739.75, "total_tokens": 206839896}
{"current_steps": 3770, "total_steps": 4768, "loss": 0.2972, "lr": 1.0446256334779752e-06, "epoch": 1.5813758389261745, "percentage": 79.07, "elapsed_time": "5:54:27", "remaining_time": "1:33:49", "throughput": 9738.88, "total_tokens": 207122592}
{"current_steps": 3775, "total_steps": 4768, "loss": 0.2938, "lr": 1.034570706105923e-06, "epoch": 1.583473154362416, "percentage": 79.17, "elapsed_time": "5:55:01", "remaining_time": "1:33:23", "throughput": 9736.53, "total_tokens": 207402456}
{"current_steps": 3780, "total_steps": 4768, "loss": 0.2729, "lr": 1.0245588172290804e-06, "epoch": 1.5855704697986577, "percentage": 79.28, "elapsed_time": "5:55:27", "remaining_time": "1:32:54", "throughput": 9737.32, "total_tokens": 207676216}
{"current_steps": 3785, "total_steps": 4768, "loss": 0.3111, "lr": 1.014590075510748e-06, "epoch": 1.5876677852348995, "percentage": 79.38, "elapsed_time": "5:55:51", "remaining_time": "1:32:25", "throughput": 9739.31, "total_tokens": 207943936}
{"current_steps": 3790, "total_steps": 4768, "loss": 0.2893, "lr": 1.0046645891459305e-06, "epoch": 1.589765100671141, "percentage": 79.49, "elapsed_time": "5:56:16", "remaining_time": "1:31:56", "throughput": 9741.13, "total_tokens": 208229168}
{"current_steps": 3795, "total_steps": 4768, "loss": 0.286, "lr": 9.947824658601645e-07, "epoch": 1.5918624161073827, "percentage": 79.59, "elapsed_time": "5:56:50", "remaining_time": "1:31:29", "throughput": 9738.14, "total_tokens": 208497736}
{"current_steps": 3800, "total_steps": 4768, "loss": 0.3098, "lr": 9.849438129083484e-07, "epoch": 1.5939597315436242, "percentage": 79.7, "elapsed_time": "5:57:13", "remaining_time": "1:30:59", "throughput": 9739.05, "total_tokens": 208738696}
{"current_steps": 3805, "total_steps": 4768, "loss": 0.3036, "lr": 9.75148737073578e-07, "epoch": 1.5960570469798658, "percentage": 79.8, "elapsed_time": "5:57:40", "remaining_time": "1:30:31", "throughput": 9739.56, "total_tokens": 209012152}
{"current_steps": 3810, "total_steps": 4768, "loss": 0.2835, "lr": 9.653973446659875e-07, "epoch": 1.5981543624161074, "percentage": 79.91, "elapsed_time": "5:58:07", "remaining_time": "1:30:02", "throughput": 9740.88, "total_tokens": 209310328}
{"current_steps": 3815, "total_steps": 4768, "loss": 0.3026, "lr": 9.556897415215999e-07, "epoch": 1.600251677852349, "percentage": 80.01, "elapsed_time": "5:58:38", "remaining_time": "1:29:35", "throughput": 9740.38, "total_tokens": 209598432}
{"current_steps": 3820, "total_steps": 4768, "loss": 0.2924, "lr": 9.460260330011706e-07, "epoch": 1.6023489932885906, "percentage": 80.12, "elapsed_time": "5:59:09", "remaining_time": "1:29:07", "throughput": 9739.08, "total_tokens": 209869144}
{"current_steps": 3825, "total_steps": 4768, "loss": 0.2861, "lr": 9.364063239890476e-07, "epoch": 1.6044463087248322, "percentage": 80.22, "elapsed_time": "5:59:40", "remaining_time": "1:28:40", "throughput": 9737.53, "total_tokens": 210140504}
{"current_steps": 3830, "total_steps": 4768, "loss": 0.3088, "lr": 9.268307188920384e-07, "epoch": 1.6065436241610738, "percentage": 80.33, "elapsed_time": "6:00:10", "remaining_time": "1:28:12", "throughput": 9737.0, "total_tokens": 210424160}
{"current_steps": 3835, "total_steps": 4768, "loss": 0.2981, "lr": 9.172993216382669e-07, "epoch": 1.6086409395973154, "percentage": 80.43, "elapsed_time": "6:00:31", "remaining_time": "1:27:42", "throughput": 9739.65, "total_tokens": 210685864}
{"current_steps": 3840, "total_steps": 4768, "loss": 0.2888, "lr": 9.078122356760532e-07, "epoch": 1.610738255033557, "percentage": 80.54, "elapsed_time": "6:01:01", "remaining_time": "1:27:14", "throughput": 9738.78, "total_tokens": 210960936}
{"current_steps": 3845, "total_steps": 4768, "loss": 0.2954, "lr": 8.983695639727858e-07, "epoch": 1.6128355704697985, "percentage": 80.64, "elapsed_time": "6:01:28", "remaining_time": "1:26:46", "throughput": 9739.61, "total_tokens": 211238896}
{"current_steps": 3850, "total_steps": 4768, "loss": 0.3006, "lr": 8.889714090138085e-07, "epoch": 1.6149328859060401, "percentage": 80.75, "elapsed_time": "6:02:02", "remaining_time": "1:26:19", "throughput": 9736.72, "total_tokens": 211504112}
{"current_steps": 3855, "total_steps": 4768, "loss": 0.3209, "lr": 8.796178728013033e-07, "epoch": 1.617030201342282, "percentage": 80.85, "elapsed_time": "6:02:34", "remaining_time": "1:25:52", "throughput": 9735.31, "total_tokens": 211787368}
{"current_steps": 3860, "total_steps": 4768, "loss": 0.2914, "lr": 8.703090568531902e-07, "epoch": 1.6191275167785235, "percentage": 80.96, "elapsed_time": "6:03:02", "remaining_time": "1:25:24", "throughput": 9734.81, "total_tokens": 212051184}
{"current_steps": 3865, "total_steps": 4768, "loss": 0.3153, "lr": 8.610450622020178e-07, "epoch": 1.621224832214765, "percentage": 81.06, "elapsed_time": "6:03:24", "remaining_time": "1:24:54", "throughput": 9737.3, "total_tokens": 212315840}
{"current_steps": 3870, "total_steps": 4768, "loss": 0.3077, "lr": 8.518259893938697e-07, "epoch": 1.6233221476510067, "percentage": 81.17, "elapsed_time": "6:03:57", "remaining_time": "1:24:27", "throughput": 9735.25, "total_tokens": 212589256}
{"current_steps": 3875, "total_steps": 4768, "loss": 0.3027, "lr": 8.426519384872733e-07, "epoch": 1.6254194630872483, "percentage": 81.27, "elapsed_time": "6:04:25", "remaining_time": "1:23:58", "throughput": 9735.35, "total_tokens": 212869312}
{"current_steps": 3880, "total_steps": 4768, "loss": 0.2866, "lr": 8.335230090521191e-07, "epoch": 1.62751677852349, "percentage": 81.38, "elapsed_time": "6:04:50", "remaining_time": "1:23:29", "throughput": 9736.79, "total_tokens": 213142584}
{"current_steps": 3885, "total_steps": 4768, "loss": 0.2829, "lr": 8.244393001685697e-07, "epoch": 1.6296140939597317, "percentage": 81.48, "elapsed_time": "6:05:16", "remaining_time": "1:23:01", "throughput": 9736.87, "total_tokens": 213402088}
{"current_steps": 3890, "total_steps": 4768, "loss": 0.289, "lr": 8.154009104259907e-07, "epoch": 1.6317114093959733, "percentage": 81.59, "elapsed_time": "6:05:45", "remaining_time": "1:22:33", "throughput": 9736.28, "total_tokens": 213668520}
{"current_steps": 3895, "total_steps": 4768, "loss": 0.3046, "lr": 8.064079379218815e-07, "epoch": 1.6338087248322148, "percentage": 81.69, "elapsed_time": "6:06:18", "remaining_time": "1:22:06", "throughput": 9734.55, "total_tokens": 213955440}
{"current_steps": 3900, "total_steps": 4768, "loss": 0.2979, "lr": 7.974604802608055e-07, "epoch": 1.6359060402684564, "percentage": 81.8, "elapsed_time": "6:06:52", "remaining_time": "1:21:39", "throughput": 9731.63, "total_tokens": 214220256}
{"current_steps": 3905, "total_steps": 4768, "loss": 0.2971, "lr": 7.885586345533397e-07, "epoch": 1.638003355704698, "percentage": 81.9, "elapsed_time": "6:07:18", "remaining_time": "1:21:10", "throughput": 9732.25, "total_tokens": 214483880}
{"current_steps": 3910, "total_steps": 4768, "loss": 0.3178, "lr": 7.797024974150102e-07, "epoch": 1.6401006711409396, "percentage": 82.01, "elapsed_time": "6:07:48", "remaining_time": "1:20:42", "throughput": 9731.76, "total_tokens": 214762960}
{"current_steps": 3915, "total_steps": 4768, "loss": 0.3121, "lr": 7.708921649652501e-07, "epoch": 1.6421979865771812, "percentage": 82.11, "elapsed_time": "6:08:20", "remaining_time": "1:20:15", "throughput": 9730.7, "total_tokens": 215049064}
{"current_steps": 3920, "total_steps": 4768, "loss": 0.2919, "lr": 7.621277328263548e-07, "epoch": 1.6442953020134228, "percentage": 82.21, "elapsed_time": "6:08:51", "remaining_time": "1:19:47", "throughput": 9729.77, "total_tokens": 215331416}
{"current_steps": 3925, "total_steps": 4768, "loss": 0.2848, "lr": 7.534092961224443e-07, "epoch": 1.6463926174496644, "percentage": 82.32, "elapsed_time": "6:09:22", "remaining_time": "1:19:19", "throughput": 9729.21, "total_tokens": 215618952}
{"current_steps": 3930, "total_steps": 4768, "loss": 0.3112, "lr": 7.447369494784285e-07, "epoch": 1.648489932885906, "percentage": 82.42, "elapsed_time": "6:09:43", "remaining_time": "1:18:50", "throughput": 9732.33, "total_tokens": 215900768}
{"current_steps": 3935, "total_steps": 4768, "loss": 0.3071, "lr": 7.36110787018986e-07, "epoch": 1.6505872483221475, "percentage": 82.53, "elapsed_time": "6:10:14", "remaining_time": "1:18:22", "throughput": 9732.18, "total_tokens": 216193600}
{"current_steps": 3940, "total_steps": 4768, "loss": 0.2871, "lr": 7.275309023675364e-07, "epoch": 1.6526845637583891, "percentage": 82.63, "elapsed_time": "6:10:44", "remaining_time": "1:17:54", "throughput": 9731.69, "total_tokens": 216480520}
{"current_steps": 3945, "total_steps": 4768, "loss": 0.2935, "lr": 7.189973886452251e-07, "epoch": 1.6547818791946307, "percentage": 82.74, "elapsed_time": "6:11:11", "remaining_time": "1:17:26", "throughput": 9732.06, "total_tokens": 216750304}
{"current_steps": 3950, "total_steps": 4768, "loss": 0.3045, "lr": 7.105103384699175e-07, "epoch": 1.6568791946308725, "percentage": 82.84, "elapsed_time": "6:11:38", "remaining_time": "1:16:57", "throughput": 9732.73, "total_tokens": 217027832}
{"current_steps": 3955, "total_steps": 4768, "loss": 0.2859, "lr": 7.020698439551881e-07, "epoch": 1.658976510067114, "percentage": 82.95, "elapsed_time": "6:12:01", "remaining_time": "1:16:28", "throughput": 9733.62, "total_tokens": 217273920}
{"current_steps": 3960, "total_steps": 4768, "loss": 0.2799, "lr": 6.936759967093237e-07, "epoch": 1.6610738255033557, "percentage": 83.05, "elapsed_time": "6:12:28", "remaining_time": "1:16:00", "throughput": 9734.1, "total_tokens": 217544344}
{"current_steps": 3965, "total_steps": 4768, "loss": 0.2825, "lr": 6.853288878343272e-07, "epoch": 1.6631711409395973, "percentage": 83.16, "elapsed_time": "6:12:58", "remaining_time": "1:15:32", "throughput": 9734.09, "total_tokens": 217830456}
{"current_steps": 3970, "total_steps": 4768, "loss": 0.2926, "lr": 6.770286079249311e-07, "epoch": 1.665268456375839, "percentage": 83.26, "elapsed_time": "6:13:30", "remaining_time": "1:15:04", "throughput": 9732.96, "total_tokens": 218118376}
{"current_steps": 3975, "total_steps": 4768, "loss": 0.3223, "lr": 6.687752470676129e-07, "epoch": 1.6673657718120807, "percentage": 83.37, "elapsed_time": "6:13:54", "remaining_time": "1:14:35", "throughput": 9733.93, "total_tokens": 218374488}
{"current_steps": 3980, "total_steps": 4768, "loss": 0.2836, "lr": 6.605688948396182e-07, "epoch": 1.6694630872483223, "percentage": 83.47, "elapsed_time": "6:14:19", "remaining_time": "1:14:06", "throughput": 9735.22, "total_tokens": 218643344}
{"current_steps": 3985, "total_steps": 4768, "loss": 0.2947, "lr": 6.524096403079861e-07, "epoch": 1.6715604026845639, "percentage": 83.58, "elapsed_time": "6:14:44", "remaining_time": "1:13:37", "throughput": 9736.63, "total_tokens": 218919152}
{"current_steps": 3990, "total_steps": 4768, "loss": 0.3025, "lr": 6.442975720285871e-07, "epoch": 1.6736577181208054, "percentage": 83.68, "elapsed_time": "6:15:16", "remaining_time": "1:13:10", "throughput": 9734.63, "total_tokens": 219188776}
{"current_steps": 3995, "total_steps": 4768, "loss": 0.2785, "lr": 6.362327780451566e-07, "epoch": 1.675755033557047, "percentage": 83.79, "elapsed_time": "6:15:49", "remaining_time": "1:12:43", "throughput": 9732.77, "total_tokens": 219472024}
{"current_steps": 4000, "total_steps": 4768, "loss": 0.3049, "lr": 6.282153458883444e-07, "epoch": 1.6778523489932886, "percentage": 83.89, "elapsed_time": "6:16:19", "remaining_time": "1:12:15", "throughput": 9732.41, "total_tokens": 219748896}
{"current_steps": 4005, "total_steps": 4768, "loss": 0.3112, "lr": 6.2024536257476e-07, "epoch": 1.6799496644295302, "percentage": 84.0, "elapsed_time": "6:16:47", "remaining_time": "1:11:46", "throughput": 9732.55, "total_tokens": 220025688}
{"current_steps": 4010, "total_steps": 4768, "loss": 0.2858, "lr": 6.123229146060311e-07, "epoch": 1.6820469798657718, "percentage": 84.1, "elapsed_time": "6:17:15", "remaining_time": "1:11:18", "throughput": 9732.96, "total_tokens": 220306704}
{"current_steps": 4015, "total_steps": 4768, "loss": 0.2978, "lr": 6.044480879678644e-07, "epoch": 1.6841442953020134, "percentage": 84.21, "elapsed_time": "6:17:44", "remaining_time": "1:10:50", "throughput": 9732.63, "total_tokens": 220582216}
{"current_steps": 4020, "total_steps": 4768, "loss": 0.3, "lr": 5.966209681291108e-07, "epoch": 1.686241610738255, "percentage": 84.31, "elapsed_time": "6:18:13", "remaining_time": "1:10:22", "throughput": 9733.36, "total_tokens": 220885376}
{"current_steps": 4025, "total_steps": 4768, "loss": 0.2861, "lr": 5.888416400408404e-07, "epoch": 1.6883389261744965, "percentage": 84.42, "elapsed_time": "6:18:44", "remaining_time": "1:09:54", "throughput": 9732.45, "total_tokens": 221164784}
{"current_steps": 4030, "total_steps": 4768, "loss": 0.2934, "lr": 5.811101881354187e-07, "epoch": 1.6904362416107381, "percentage": 84.52, "elapsed_time": "6:19:13", "remaining_time": "1:09:26", "throughput": 9732.02, "total_tokens": 221439832}
{"current_steps": 4035, "total_steps": 4768, "loss": 0.3013, "lr": 5.734266963255891e-07, "epoch": 1.6925335570469797, "percentage": 84.63, "elapsed_time": "6:19:46", "remaining_time": "1:08:59", "throughput": 9730.27, "total_tokens": 221714544}
{"current_steps": 4040, "total_steps": 4768, "loss": 0.2911, "lr": 5.657912480035665e-07, "epoch": 1.6946308724832215, "percentage": 84.73, "elapsed_time": "6:20:14", "remaining_time": "1:08:31", "throughput": 9729.54, "total_tokens": 221972744}
{"current_steps": 4045, "total_steps": 4768, "loss": 0.2973, "lr": 5.582039260401268e-07, "epoch": 1.6967281879194631, "percentage": 84.84, "elapsed_time": "6:20:43", "remaining_time": "1:08:03", "throughput": 9729.09, "total_tokens": 222245928}
{"current_steps": 4050, "total_steps": 4768, "loss": 0.3024, "lr": 5.506648127837116e-07, "epoch": 1.6988255033557047, "percentage": 84.94, "elapsed_time": "6:21:09", "remaining_time": "1:07:34", "throughput": 9730.84, "total_tokens": 222544328}
{"current_steps": 4055, "total_steps": 4768, "loss": 0.2984, "lr": 5.431739900595323e-07, "epoch": 1.7009228187919463, "percentage": 85.05, "elapsed_time": "6:21:37", "remaining_time": "1:07:06", "throughput": 9731.63, "total_tokens": 222834896}
{"current_steps": 4060, "total_steps": 4768, "loss": 0.3149, "lr": 5.357315391686818e-07, "epoch": 1.7030201342281879, "percentage": 85.15, "elapsed_time": "6:22:10", "remaining_time": "1:06:38", "throughput": 9730.03, "total_tokens": 223115968}
{"current_steps": 4065, "total_steps": 4768, "loss": 0.2983, "lr": 5.283375408872538e-07, "epoch": 1.7051174496644297, "percentage": 85.26, "elapsed_time": "6:22:32", "remaining_time": "1:06:09", "throughput": 9732.44, "total_tokens": 223387552}
{"current_steps": 4070, "total_steps": 4768, "loss": 0.3039, "lr": 5.209920754654646e-07, "epoch": 1.7072147651006713, "percentage": 85.36, "elapsed_time": "6:23:00", "remaining_time": "1:05:41", "throughput": 9732.08, "total_tokens": 223644352}
{"current_steps": 4075, "total_steps": 4768, "loss": 0.2898, "lr": 5.136952226267833e-07, "epoch": 1.7093120805369129, "percentage": 85.47, "elapsed_time": "6:23:24", "remaining_time": "1:05:12", "throughput": 9733.82, "total_tokens": 223919792}
{"current_steps": 4080, "total_steps": 4768, "loss": 0.3158, "lr": 5.064470615670652e-07, "epoch": 1.7114093959731544, "percentage": 85.57, "elapsed_time": "6:23:55", "remaining_time": "1:04:44", "throughput": 9732.99, "total_tokens": 224199688}
{"current_steps": 4085, "total_steps": 4768, "loss": 0.302, "lr": 4.992476709536925e-07, "epoch": 1.713506711409396, "percentage": 85.68, "elapsed_time": "6:24:26", "remaining_time": "1:04:16", "throughput": 9731.69, "total_tokens": 224476120}
{"current_steps": 4090, "total_steps": 4768, "loss": 0.2842, "lr": 4.92097128924724e-07, "epoch": 1.7156040268456376, "percentage": 85.78, "elapsed_time": "6:24:52", "remaining_time": "1:03:48", "throughput": 9732.34, "total_tokens": 224744352}
{"current_steps": 4095, "total_steps": 4768, "loss": 0.3091, "lr": 4.849955130880391e-07, "epoch": 1.7177013422818792, "percentage": 85.89, "elapsed_time": "6:25:21", "remaining_time": "1:03:19", "throughput": 9731.7, "total_tokens": 225006760}
{"current_steps": 4100, "total_steps": 4768, "loss": 0.2971, "lr": 4.779429005205055e-07, "epoch": 1.7197986577181208, "percentage": 85.99, "elapsed_time": "6:25:51", "remaining_time": "1:02:52", "throughput": 9731.1, "total_tokens": 225290736}
{"current_steps": 4105, "total_steps": 4768, "loss": 0.3045, "lr": 4.709393677671337e-07, "epoch": 1.7218959731543624, "percentage": 86.09, "elapsed_time": "6:26:17", "remaining_time": "1:02:23", "throughput": 9733.06, "total_tokens": 225590904}
{"current_steps": 4110, "total_steps": 4768, "loss": 0.2752, "lr": 4.639849908402516e-07, "epoch": 1.723993288590604, "percentage": 86.2, "elapsed_time": "6:26:46", "remaining_time": "1:01:55", "throughput": 9731.96, "total_tokens": 225844576}
{"current_steps": 4115, "total_steps": 4768, "loss": 0.3133, "lr": 4.570798452186775e-07, "epoch": 1.7260906040268456, "percentage": 86.3, "elapsed_time": "6:27:19", "remaining_time": "1:01:27", "throughput": 9730.33, "total_tokens": 226130472}
{"current_steps": 4120, "total_steps": 4768, "loss": 0.3005, "lr": 4.5022400584690207e-07, "epoch": 1.7281879194630871, "percentage": 86.41, "elapsed_time": "6:27:43", "remaining_time": "1:00:58", "throughput": 9731.84, "total_tokens": 226394656}
{"current_steps": 4125, "total_steps": 4768, "loss": 0.3038, "lr": 4.4341754713427334e-07, "epoch": 1.7302852348993287, "percentage": 86.51, "elapsed_time": "6:28:11", "remaining_time": "1:00:30", "throughput": 9731.99, "total_tokens": 226672784}
{"current_steps": 4130, "total_steps": 4768, "loss": 0.3141, "lr": 4.3666054295419035e-07, "epoch": 1.7323825503355703, "percentage": 86.62, "elapsed_time": "6:28:39", "remaining_time": "1:00:02", "throughput": 9732.55, "total_tokens": 226959960}
{"current_steps": 4135, "total_steps": 4768, "loss": 0.3181, "lr": 4.299530666433005e-07, "epoch": 1.7344798657718121, "percentage": 86.72, "elapsed_time": "6:29:05", "remaining_time": "0:59:33", "throughput": 9732.55, "total_tokens": 227214248}
{"current_steps": 4140, "total_steps": 4768, "loss": 0.2925, "lr": 4.2329519100070607e-07, "epoch": 1.7365771812080537, "percentage": 86.83, "elapsed_time": "6:29:30", "remaining_time": "0:59:05", "throughput": 9733.81, "total_tokens": 227488192}
{"current_steps": 4145, "total_steps": 4768, "loss": 0.2745, "lr": 4.1668698828716994e-07, "epoch": 1.7386744966442953, "percentage": 86.93, "elapsed_time": "6:29:58", "remaining_time": "0:58:36", "throughput": 9735.31, "total_tokens": 227791312}
{"current_steps": 4150, "total_steps": 4768, "loss": 0.2889, "lr": 4.101285302243335e-07, "epoch": 1.7407718120805369, "percentage": 87.04, "elapsed_time": "6:30:29", "remaining_time": "0:58:08", "throughput": 9734.24, "total_tokens": 228064408}
{"current_steps": 4155, "total_steps": 4768, "loss": 0.2979, "lr": 4.0361988799394014e-07, "epoch": 1.7428691275167785, "percentage": 87.14, "elapsed_time": "6:30:54", "remaining_time": "0:57:40", "throughput": 9734.64, "total_tokens": 228322552}
{"current_steps": 4160, "total_steps": 4768, "loss": 0.2963, "lr": 3.9716113223705945e-07, "epoch": 1.7449664429530203, "percentage": 87.25, "elapsed_time": "6:31:30", "remaining_time": "0:57:13", "throughput": 9732.32, "total_tokens": 228613776}
{"current_steps": 4165, "total_steps": 4768, "loss": 0.2945, "lr": 3.9075233305332196e-07, "epoch": 1.7470637583892619, "percentage": 87.35, "elapsed_time": "6:31:53", "remaining_time": "0:56:44", "throughput": 9735.7, "total_tokens": 228919384}
{"current_steps": 4170, "total_steps": 4768, "loss": 0.286, "lr": 3.843935600001586e-07, "epoch": 1.7491610738255035, "percentage": 87.46, "elapsed_time": "6:32:15", "remaining_time": "0:56:15", "throughput": 9738.23, "total_tokens": 229195344}
{"current_steps": 4175, "total_steps": 4768, "loss": 0.3106, "lr": 3.780848820920441e-07, "epoch": 1.751258389261745, "percentage": 87.56, "elapsed_time": "6:32:44", "remaining_time": "0:55:47", "throughput": 9738.11, "total_tokens": 229475688}
{"current_steps": 4180, "total_steps": 4768, "loss": 0.3034, "lr": 3.718263677997497e-07, "epoch": 1.7533557046979866, "percentage": 87.67, "elapsed_time": "6:33:17", "remaining_time": "0:55:19", "throughput": 9737.0, "total_tokens": 229768096}
{"current_steps": 4185, "total_steps": 4768, "loss": 0.2749, "lr": 3.6561808504960215e-07, "epoch": 1.7554530201342282, "percentage": 87.77, "elapsed_time": "6:33:41", "remaining_time": "0:54:50", "throughput": 9738.0, "total_tokens": 230028336}
{"current_steps": 4190, "total_steps": 4768, "loss": 0.2965, "lr": 3.5946010122274056e-07, "epoch": 1.7575503355704698, "percentage": 87.88, "elapsed_time": "6:34:07", "remaining_time": "0:54:22", "throughput": 9738.6, "total_tokens": 230295984}
{"current_steps": 4195, "total_steps": 4768, "loss": 0.2941, "lr": 3.533524831543894e-07, "epoch": 1.7596476510067114, "percentage": 87.98, "elapsed_time": "6:34:35", "remaining_time": "0:53:53", "throughput": 9738.92, "total_tokens": 230574400}
{"current_steps": 4200, "total_steps": 4768, "loss": 0.2878, "lr": 3.472952971331323e-07, "epoch": 1.761744966442953, "percentage": 88.09, "elapsed_time": "6:35:08", "remaining_time": "0:53:26", "throughput": 9736.87, "total_tokens": 230850480}
{"current_steps": 4205, "total_steps": 4768, "loss": 0.285, "lr": 3.4128860890019156e-07, "epoch": 1.7638422818791946, "percentage": 88.19, "elapsed_time": "6:35:37", "remaining_time": "0:52:58", "throughput": 9737.87, "total_tokens": 231157088}
{"current_steps": 4210, "total_steps": 4768, "loss": 0.2927, "lr": 3.3533248364871763e-07, "epoch": 1.7659395973154361, "percentage": 88.3, "elapsed_time": "6:36:04", "remaining_time": "0:52:29", "throughput": 9739.51, "total_tokens": 231458880}
{"current_steps": 4215, "total_steps": 4768, "loss": 0.3109, "lr": 3.2942698602307755e-07, "epoch": 1.7680369127516777, "percentage": 88.4, "elapsed_time": "6:36:28", "remaining_time": "0:52:00", "throughput": 9741.04, "total_tokens": 231723544}
{"current_steps": 4220, "total_steps": 4768, "loss": 0.2997, "lr": 3.2357218011815464e-07, "epoch": 1.7701342281879193, "percentage": 88.51, "elapsed_time": "6:36:53", "remaining_time": "0:51:32", "throughput": 9741.64, "total_tokens": 231981712}
{"current_steps": 4225, "total_steps": 4768, "loss": 0.3031, "lr": 3.177681294786539e-07, "epoch": 1.772231543624161, "percentage": 88.61, "elapsed_time": "6:37:26", "remaining_time": "0:51:04", "throughput": 9738.65, "total_tokens": 232230376}
{"current_steps": 4230, "total_steps": 4768, "loss": 0.3021, "lr": 3.120148970984138e-07, "epoch": 1.7743288590604027, "percentage": 88.72, "elapsed_time": "6:37:46", "remaining_time": "0:50:35", "throughput": 9742.64, "total_tokens": 232521784}
{"current_steps": 4235, "total_steps": 4768, "loss": 0.3058, "lr": 3.06312545419718e-07, "epoch": 1.7764261744966443, "percentage": 88.82, "elapsed_time": "6:38:14", "remaining_time": "0:50:07", "throughput": 9741.87, "total_tokens": 232776224}
{"current_steps": 4240, "total_steps": 4768, "loss": 0.3, "lr": 3.006611363326206e-07, "epoch": 1.778523489932886, "percentage": 88.93, "elapsed_time": "6:38:44", "remaining_time": "0:49:39", "throughput": 9739.94, "total_tokens": 233024192}
{"current_steps": 4245, "total_steps": 4768, "loss": 0.2907, "lr": 2.9506073117427534e-07, "epoch": 1.7806208053691275, "percentage": 89.03, "elapsed_time": "6:39:10", "remaining_time": "0:49:10", "throughput": 9739.8, "total_tokens": 233274136}
{"current_steps": 4250, "total_steps": 4768, "loss": 0.3, "lr": 2.895113907282671e-07, "epoch": 1.7827181208053693, "percentage": 89.14, "elapsed_time": "6:39:45", "remaining_time": "0:48:43", "throughput": 9736.96, "total_tokens": 233544960}
{"current_steps": 4255, "total_steps": 4768, "loss": 0.2876, "lr": 2.8401317522395333e-07, "epoch": 1.7848154362416109, "percentage": 89.24, "elapsed_time": "6:40:10", "remaining_time": "0:48:14", "throughput": 9739.15, "total_tokens": 233840288}
{"current_steps": 4260, "total_steps": 4768, "loss": 0.2873, "lr": 2.7856614433581397e-07, "epoch": 1.7869127516778525, "percentage": 89.35, "elapsed_time": "6:40:39", "remaining_time": "0:47:46", "throughput": 9737.45, "total_tokens": 234083912}
{"current_steps": 4265, "total_steps": 4768, "loss": 0.3028, "lr": 2.7317035718279704e-07, "epoch": 1.789010067114094, "percentage": 89.45, "elapsed_time": "6:41:10", "remaining_time": "0:47:18", "throughput": 9735.31, "total_tokens": 234332560}
{"current_steps": 4270, "total_steps": 4768, "loss": 0.3039, "lr": 2.678258723276816e-07, "epoch": 1.7911073825503356, "percentage": 89.56, "elapsed_time": "6:41:39", "remaining_time": "0:46:50", "throughput": 9735.69, "total_tokens": 234624136}
{"current_steps": 4275, "total_steps": 4768, "loss": 0.2957, "lr": 2.6253274777644e-07, "epoch": 1.7932046979865772, "percentage": 89.66, "elapsed_time": "6:42:09", "remaining_time": "0:46:22", "throughput": 9734.61, "total_tokens": 234892712}
{"current_steps": 4280, "total_steps": 4768, "loss": 0.3011, "lr": 2.5729104097761193e-07, "epoch": 1.7953020134228188, "percentage": 89.77, "elapsed_time": "6:42:33", "remaining_time": "0:45:53", "throughput": 9737.21, "total_tokens": 235183192}
{"current_steps": 4285, "total_steps": 4768, "loss": 0.2704, "lr": 2.5210080882167644e-07, "epoch": 1.7973993288590604, "percentage": 89.87, "elapsed_time": "6:42:56", "remaining_time": "0:45:25", "throughput": 9739.47, "total_tokens": 235470776}
{"current_steps": 4290, "total_steps": 4768, "loss": 0.3232, "lr": 2.4696210764043547e-07, "epoch": 1.799496644295302, "percentage": 89.97, "elapsed_time": "6:43:29", "remaining_time": "0:44:57", "throughput": 9737.51, "total_tokens": 235738944}
{"current_steps": 4295, "total_steps": 4768, "loss": 0.2844, "lr": 2.418749932064052e-07, "epoch": 1.8015939597315436, "percentage": 90.08, "elapsed_time": "6:43:52", "remaining_time": "0:44:28", "throughput": 9739.67, "total_tokens": 236019944}
{"current_steps": 4300, "total_steps": 4768, "loss": 0.2938, "lr": 2.3683952073220718e-07, "epoch": 1.8036912751677852, "percentage": 90.18, "elapsed_time": "6:44:18", "remaining_time": "0:44:00", "throughput": 9740.07, "total_tokens": 236282304}
{"current_steps": 4305, "total_steps": 4768, "loss": 0.3108, "lr": 2.3185574486997264e-07, "epoch": 1.8057885906040267, "percentage": 90.29, "elapsed_time": "6:44:46", "remaining_time": "0:43:31", "throughput": 9739.68, "total_tokens": 236542272}
{"current_steps": 4310, "total_steps": 4768, "loss": 0.2946, "lr": 2.2692371971074488e-07, "epoch": 1.8078859060402683, "percentage": 90.39, "elapsed_time": "6:45:20", "remaining_time": "0:43:04", "throughput": 9736.99, "total_tokens": 236805848}
{"current_steps": 4315, "total_steps": 4768, "loss": 0.3122, "lr": 2.220434987838982e-07, "epoch": 1.80998322147651, "percentage": 90.5, "elapsed_time": "6:45:52", "remaining_time": "0:42:36", "throughput": 9735.17, "total_tokens": 237073920}
{"current_steps": 4320, "total_steps": 4768, "loss": 0.2899, "lr": 2.172151350565499e-07, "epoch": 1.8120805369127517, "percentage": 90.6, "elapsed_time": "6:46:20", "remaining_time": "0:42:08", "throughput": 9734.57, "total_tokens": 237337800}
{"current_steps": 4325, "total_steps": 4768, "loss": 0.2896, "lr": 2.1243868093299148e-07, "epoch": 1.8141778523489933, "percentage": 90.71, "elapsed_time": "6:46:43", "remaining_time": "0:41:39", "throughput": 9736.0, "total_tokens": 237592656}
{"current_steps": 4330, "total_steps": 4768, "loss": 0.2883, "lr": 2.077141882541167e-07, "epoch": 1.816275167785235, "percentage": 90.81, "elapsed_time": "6:47:10", "remaining_time": "0:41:11", "throughput": 9736.62, "total_tokens": 237868792}
{"current_steps": 4335, "total_steps": 4768, "loss": 0.2958, "lr": 2.0304170829685887e-07, "epoch": 1.8183724832214765, "percentage": 90.92, "elapsed_time": "6:47:36", "remaining_time": "0:40:42", "throughput": 9736.43, "total_tokens": 238118648}
{"current_steps": 4340, "total_steps": 4768, "loss": 0.2999, "lr": 1.9842129177363555e-07, "epoch": 1.820469798657718, "percentage": 91.02, "elapsed_time": "6:48:05", "remaining_time": "0:40:14", "throughput": 9734.25, "total_tokens": 238350464}
{"current_steps": 4345, "total_steps": 4768, "loss": 0.3028, "lr": 1.938529888317975e-07, "epoch": 1.8225671140939599, "percentage": 91.13, "elapsed_time": "6:48:36", "remaining_time": "0:39:46", "throughput": 9733.71, "total_tokens": 238637976}
{"current_steps": 4350, "total_steps": 4768, "loss": 0.2916, "lr": 1.8933684905308557e-07, "epoch": 1.8246644295302015, "percentage": 91.23, "elapsed_time": "6:49:05", "remaining_time": "0:39:18", "throughput": 9733.49, "total_tokens": 238910120}
{"current_steps": 4355, "total_steps": 4768, "loss": 0.2948, "lr": 1.8487292145308978e-07, "epoch": 1.826761744966443, "percentage": 91.34, "elapsed_time": "6:49:42", "remaining_time": "0:38:51", "throughput": 9729.94, "total_tokens": 239189688}
{"current_steps": 4360, "total_steps": 4768, "loss": 0.3109, "lr": 1.8046125448071993e-07, "epoch": 1.8288590604026846, "percentage": 91.44, "elapsed_time": "6:50:08", "remaining_time": "0:38:22", "throughput": 9731.01, "total_tokens": 239463856}
{"current_steps": 4365, "total_steps": 4768, "loss": 0.3041, "lr": 1.7610189601768024e-07, "epoch": 1.8309563758389262, "percentage": 91.55, "elapsed_time": "6:50:40", "remaining_time": "0:37:54", "throughput": 9730.26, "total_tokens": 239760648}
{"current_steps": 4370, "total_steps": 4768, "loss": 0.2951, "lr": 1.717948933779462e-07, "epoch": 1.8330536912751678, "percentage": 91.65, "elapsed_time": "6:51:09", "remaining_time": "0:37:26", "throughput": 9730.15, "total_tokens": 240041120}
{"current_steps": 4375, "total_steps": 4768, "loss": 0.2953, "lr": 1.675402933072545e-07, "epoch": 1.8351510067114094, "percentage": 91.76, "elapsed_time": "6:51:34", "remaining_time": "0:36:58", "throughput": 9730.72, "total_tokens": 240298864}
{"current_steps": 4380, "total_steps": 4768, "loss": 0.2913, "lr": 1.6333814198259468e-07, "epoch": 1.837248322147651, "percentage": 91.86, "elapsed_time": "6:52:01", "remaining_time": "0:36:29", "throughput": 9732.21, "total_tokens": 240593360}
{"current_steps": 4385, "total_steps": 4768, "loss": 0.2944, "lr": 1.5918848501170647e-07, "epoch": 1.8393456375838926, "percentage": 91.97, "elapsed_time": "6:52:25", "remaining_time": "0:36:01", "throughput": 9734.95, "total_tokens": 240893920}
{"current_steps": 4390, "total_steps": 4768, "loss": 0.3117, "lr": 1.5509136743258656e-07, "epoch": 1.8414429530201342, "percentage": 92.07, "elapsed_time": "6:52:50", "remaining_time": "0:35:32", "throughput": 9735.58, "total_tokens": 241152096}
{"current_steps": 4395, "total_steps": 4768, "loss": 0.3135, "lr": 1.5104683371299945e-07, "epoch": 1.8435402684563758, "percentage": 92.18, "elapsed_time": "6:53:16", "remaining_time": "0:35:04", "throughput": 9735.93, "total_tokens": 241421688}
{"current_steps": 4400, "total_steps": 4768, "loss": 0.2976, "lr": 1.4705492774999385e-07, "epoch": 1.8456375838926173, "percentage": 92.28, "elapsed_time": "6:53:45", "remaining_time": "0:34:36", "throughput": 9735.84, "total_tokens": 241694320}
{"current_steps": 4405, "total_steps": 4768, "loss": 0.2901, "lr": 1.4311569286942883e-07, "epoch": 1.847734899328859, "percentage": 92.39, "elapsed_time": "6:54:10", "remaining_time": "0:34:07", "throughput": 9736.07, "total_tokens": 241942608}
{"current_steps": 4410, "total_steps": 4768, "loss": 0.3047, "lr": 1.3922917182549956e-07, "epoch": 1.8498322147651005, "percentage": 92.49, "elapsed_time": "6:54:41", "remaining_time": "0:33:39", "throughput": 9734.26, "total_tokens": 242205264}
{"current_steps": 4415, "total_steps": 4768, "loss": 0.2966, "lr": 1.3539540680027553e-07, "epoch": 1.8519295302013423, "percentage": 92.6, "elapsed_time": "6:55:11", "remaining_time": "0:33:11", "throughput": 9734.41, "total_tokens": 242496520}
{"current_steps": 4420, "total_steps": 4768, "loss": 0.3058, "lr": 1.3161443940324537e-07, "epoch": 1.854026845637584, "percentage": 92.7, "elapsed_time": "6:55:37", "remaining_time": "0:32:43", "throughput": 9734.14, "total_tokens": 242749680}
{"current_steps": 4425, "total_steps": 4768, "loss": 0.3131, "lr": 1.2788631067085944e-07, "epoch": 1.8561241610738255, "percentage": 92.81, "elapsed_time": "6:56:06", "remaining_time": "0:32:15", "throughput": 9733.64, "total_tokens": 243015024}
{"current_steps": 4430, "total_steps": 4768, "loss": 0.2874, "lr": 1.242110610660896e-07, "epoch": 1.858221476510067, "percentage": 92.91, "elapsed_time": "6:56:36", "remaining_time": "0:31:47", "throughput": 9732.49, "total_tokens": 243273296}
{"current_steps": 4435, "total_steps": 4768, "loss": 0.2984, "lr": 1.2058873047798625e-07, "epoch": 1.8603187919463087, "percentage": 93.02, "elapsed_time": "6:57:05", "remaining_time": "0:31:19", "throughput": 9731.73, "total_tokens": 243541800}
{"current_steps": 4440, "total_steps": 4768, "loss": 0.3132, "lr": 1.1701935822124866e-07, "epoch": 1.8624161073825505, "percentage": 93.12, "elapsed_time": "6:57:31", "remaining_time": "0:30:50", "throughput": 9733.3, "total_tokens": 243837624}
{"current_steps": 4445, "total_steps": 4768, "loss": 0.2889, "lr": 1.1350298303579588e-07, "epoch": 1.864513422818792, "percentage": 93.23, "elapsed_time": "6:57:57", "remaining_time": "0:30:22", "throughput": 9735.02, "total_tokens": 244129760}
{"current_steps": 4450, "total_steps": 4768, "loss": 0.2857, "lr": 1.1003964308634707e-07, "epoch": 1.8666107382550337, "percentage": 93.33, "elapsed_time": "6:58:16", "remaining_time": "0:29:53", "throughput": 9737.83, "total_tokens": 244385272}
{"current_steps": 4455, "total_steps": 4768, "loss": 0.3229, "lr": 1.066293759620085e-07, "epoch": 1.8687080536912752, "percentage": 93.44, "elapsed_time": "6:58:40", "remaining_time": "0:29:24", "throughput": 9739.44, "total_tokens": 244658624}
{"current_steps": 4460, "total_steps": 4768, "loss": 0.2849, "lr": 1.0327221867586224e-07, "epoch": 1.8708053691275168, "percentage": 93.54, "elapsed_time": "6:59:06", "remaining_time": "0:28:56", "throughput": 9740.52, "total_tokens": 244935528}
{"current_steps": 4465, "total_steps": 4768, "loss": 0.2875, "lr": 9.996820766456916e-08, "epoch": 1.8729026845637584, "percentage": 93.65, "elapsed_time": "6:59:35", "remaining_time": "0:28:28", "throughput": 9739.91, "total_tokens": 245207328}
{"current_steps": 4470, "total_steps": 4768, "loss": 0.29, "lr": 9.671737878796994e-08, "epoch": 1.875, "percentage": 93.75, "elapsed_time": "7:00:06", "remaining_time": "0:28:00", "throughput": 9738.84, "total_tokens": 245483776}
{"current_steps": 4475, "total_steps": 4768, "loss": 0.2815, "lr": 9.351976732869527e-08, "epoch": 1.8770973154362416, "percentage": 93.85, "elapsed_time": "7:00:32", "remaining_time": "0:27:32", "throughput": 9739.18, "total_tokens": 245748192}
{"current_steps": 4480, "total_steps": 4768, "loss": 0.2836, "lr": 9.03754079917879e-08, "epoch": 1.8791946308724832, "percentage": 93.96, "elapsed_time": "7:00:56", "remaining_time": "0:27:03", "throughput": 9741.17, "total_tokens": 246030184}
{"current_steps": 4485, "total_steps": 4768, "loss": 0.304, "lr": 8.728433490431897e-08, "epoch": 1.8812919463087248, "percentage": 94.06, "elapsed_time": "7:01:23", "remaining_time": "0:26:35", "throughput": 9742.44, "total_tokens": 246321568}
{"current_steps": 4490, "total_steps": 4768, "loss": 0.293, "lr": 8.424658161502397e-08, "epoch": 1.8833892617449663, "percentage": 94.17, "elapsed_time": "7:01:50", "remaining_time": "0:26:07", "throughput": 9743.77, "total_tokens": 246618720}
{"current_steps": 4495, "total_steps": 4768, "loss": 0.2857, "lr": 8.126218109393458e-08, "epoch": 1.885486577181208, "percentage": 94.27, "elapsed_time": "7:02:13", "remaining_time": "0:25:38", "throughput": 9745.63, "total_tokens": 246893080}
{"current_steps": 4500, "total_steps": 4768, "loss": 0.2928, "lr": 7.833116573202237e-08, "epoch": 1.8875838926174495, "percentage": 94.38, "elapsed_time": "7:02:44", "remaining_time": "0:25:10", "throughput": 9743.88, "total_tokens": 247150424}
{"current_steps": 4505, "total_steps": 4768, "loss": 0.2804, "lr": 7.54535673408463e-08, "epoch": 1.8896812080536913, "percentage": 94.48, "elapsed_time": "7:03:09", "remaining_time": "0:24:42", "throughput": 9745.46, "total_tokens": 247432680}
{"current_steps": 4510, "total_steps": 4768, "loss": 0.2931, "lr": 7.262941715220961e-08, "epoch": 1.891778523489933, "percentage": 94.59, "elapsed_time": "7:03:31", "remaining_time": "0:24:13", "throughput": 9747.85, "total_tokens": 247708592}
{"current_steps": 4515, "total_steps": 4768, "loss": 0.3057, "lr": 6.985874581781848e-08, "epoch": 1.8938758389261745, "percentage": 94.69, "elapsed_time": "7:03:59", "remaining_time": "0:23:45", "throughput": 9748.67, "total_tokens": 248005616}
{"current_steps": 4520, "total_steps": 4768, "loss": 0.3061, "lr": 6.714158340895116e-08, "epoch": 1.895973154362416, "percentage": 94.8, "elapsed_time": "7:04:35", "remaining_time": "0:23:17", "throughput": 9745.27, "total_tokens": 248266432}
{"current_steps": 4525, "total_steps": 4768, "loss": 0.3287, "lr": 6.447795941612877e-08, "epoch": 1.8980704697986577, "percentage": 94.9, "elapsed_time": "7:05:06", "remaining_time": "0:22:49", "throughput": 9744.31, "total_tokens": 248547312}
{"current_steps": 4530, "total_steps": 4768, "loss": 0.301, "lr": 6.186790274879895e-08, "epoch": 1.9001677852348995, "percentage": 95.01, "elapsed_time": "7:05:40", "remaining_time": "0:22:21", "throughput": 9741.7, "total_tokens": 248810984}
{"current_steps": 4535, "total_steps": 4768, "loss": 0.3033, "lr": 5.9311441735020456e-08, "epoch": 1.902265100671141, "percentage": 95.11, "elapsed_time": "7:06:14", "remaining_time": "0:21:53", "throughput": 9740.12, "total_tokens": 249099368}
{"current_steps": 4540, "total_steps": 4768, "loss": 0.2812, "lr": 5.680860412115352e-08, "epoch": 1.9043624161073827, "percentage": 95.22, "elapsed_time": "7:06:38", "remaining_time": "0:21:25", "throughput": 9742.14, "total_tokens": 249385912}
{"current_steps": 4545, "total_steps": 4768, "loss": 0.3058, "lr": 5.435941707156389e-08, "epoch": 1.9064597315436242, "percentage": 95.32, "elapsed_time": "7:07:07", "remaining_time": "0:20:57", "throughput": 9741.52, "total_tokens": 249652752}
{"current_steps": 4550, "total_steps": 4768, "loss": 0.2889, "lr": 5.196390716832145e-08, "epoch": 1.9085570469798658, "percentage": 95.43, "elapsed_time": "7:07:39", "remaining_time": "0:20:29", "throughput": 9739.98, "total_tokens": 249922680}
{"current_steps": 4555, "total_steps": 4768, "loss": 0.3085, "lr": 4.962210041091708e-08, "epoch": 1.9106543624161074, "percentage": 95.53, "elapsed_time": "7:08:12", "remaining_time": "0:20:01", "throughput": 9738.49, "total_tokens": 250201704}
{"current_steps": 4560, "total_steps": 4768, "loss": 0.2876, "lr": 4.733402221597905e-08, "epoch": 1.912751677852349, "percentage": 95.64, "elapsed_time": "7:08:36", "remaining_time": "0:19:33", "throughput": 9738.74, "total_tokens": 250450792}
{"current_steps": 4565, "total_steps": 4768, "loss": 0.3209, "lr": 4.509969741699538e-08, "epoch": 1.9148489932885906, "percentage": 95.74, "elapsed_time": "7:09:06", "remaining_time": "0:19:04", "throughput": 9738.67, "total_tokens": 250741424}
{"current_steps": 4570, "total_steps": 4768, "loss": 0.3038, "lr": 4.29191502640458e-08, "epoch": 1.9169463087248322, "percentage": 95.85, "elapsed_time": "7:09:34", "remaining_time": "0:18:36", "throughput": 9738.61, "total_tokens": 251008296}
{"current_steps": 4575, "total_steps": 4768, "loss": 0.2942, "lr": 4.07924044235386e-08, "epoch": 1.9190436241610738, "percentage": 95.95, "elapsed_time": "7:10:07", "remaining_time": "0:18:08", "throughput": 9736.81, "total_tokens": 251284184}
{"current_steps": 4580, "total_steps": 4768, "loss": 0.2732, "lr": 3.8719482977953025e-08, "epoch": 1.9211409395973154, "percentage": 96.06, "elapsed_time": "7:10:38", "remaining_time": "0:17:40", "throughput": 9737.26, "total_tokens": 251600456}
{"current_steps": 4585, "total_steps": 4768, "loss": 0.2889, "lr": 3.670040842558953e-08, "epoch": 1.923238255033557, "percentage": 96.16, "elapsed_time": "7:11:08", "remaining_time": "0:17:12", "throughput": 9737.17, "total_tokens": 251888600}
{"current_steps": 4590, "total_steps": 4768, "loss": 0.2946, "lr": 3.473520268032604e-08, "epoch": 1.9253355704697985, "percentage": 96.27, "elapsed_time": "7:11:34", "remaining_time": "0:16:44", "throughput": 9738.27, "total_tokens": 252163880}
{"current_steps": 4595, "total_steps": 4768, "loss": 0.3105, "lr": 3.2823887071377624e-08, "epoch": 1.9274328859060401, "percentage": 96.37, "elapsed_time": "7:12:03", "remaining_time": "0:16:16", "throughput": 9738.09, "total_tokens": 252449080}
{"current_steps": 4600, "total_steps": 4768, "loss": 0.2894, "lr": 3.096648234306832e-08, "epoch": 1.929530201342282, "percentage": 96.48, "elapsed_time": "7:12:27", "remaining_time": "0:15:47", "throughput": 9740.15, "total_tokens": 252732240}
{"current_steps": 4605, "total_steps": 4768, "loss": 0.2954, "lr": 2.916300865460353e-08, "epoch": 1.9316275167785235, "percentage": 96.58, "elapsed_time": "7:12:58", "remaining_time": "0:15:19", "throughput": 9739.44, "total_tokens": 253013368}
{"current_steps": 4610, "total_steps": 4768, "loss": 0.2981, "lr": 2.7413485579852462e-08, "epoch": 1.933724832214765, "percentage": 96.69, "elapsed_time": "7:13:29", "remaining_time": "0:14:51", "throughput": 9738.36, "total_tokens": 253288968}
{"current_steps": 4615, "total_steps": 4768, "loss": 0.2992, "lr": 2.571793210713491e-08, "epoch": 1.9358221476510067, "percentage": 96.79, "elapsed_time": "7:14:02", "remaining_time": "0:14:23", "throughput": 9735.62, "total_tokens": 253540712}
{"current_steps": 4620, "total_steps": 4768, "loss": 0.2988, "lr": 2.4076366639015914e-08, "epoch": 1.9379194630872483, "percentage": 96.9, "elapsed_time": "7:14:31", "remaining_time": "0:13:55", "throughput": 9734.46, "total_tokens": 253791576}
{"current_steps": 4625, "total_steps": 4768, "loss": 0.3034, "lr": 2.2488806992105317e-08, "epoch": 1.94001677852349, "percentage": 97.0, "elapsed_time": "7:14:53", "remaining_time": "0:13:26", "throughput": 9737.21, "total_tokens": 254079832}
{"current_steps": 4630, "total_steps": 4768, "loss": 0.3136, "lr": 2.095527039686518e-08, "epoch": 1.9421140939597317, "percentage": 97.11, "elapsed_time": "7:15:23", "remaining_time": "0:12:58", "throughput": 9736.88, "total_tokens": 254365112}
{"current_steps": 4635, "total_steps": 4768, "loss": 0.2784, "lr": 1.9475773497422135e-08, "epoch": 1.9442114093959733, "percentage": 97.21, "elapsed_time": "7:15:55", "remaining_time": "0:12:30", "throughput": 9735.69, "total_tokens": 254637944}
{"current_steps": 4640, "total_steps": 4768, "loss": 0.2976, "lr": 1.8050332351387535e-08, "epoch": 1.9463087248322148, "percentage": 97.32, "elapsed_time": "7:16:20", "remaining_time": "0:12:02", "throughput": 9736.57, "total_tokens": 254908256}
{"current_steps": 4645, "total_steps": 4768, "loss": 0.2855, "lr": 1.6678962429680922e-08, "epoch": 1.9484060402684564, "percentage": 97.42, "elapsed_time": "7:16:49", "remaining_time": "0:11:34", "throughput": 9735.74, "total_tokens": 255170784}
{"current_steps": 4650, "total_steps": 4768, "loss": 0.3127, "lr": 1.5361678616365728e-08, "epoch": 1.950503355704698, "percentage": 97.53, "elapsed_time": "7:17:19", "remaining_time": "0:11:05", "throughput": 9734.7, "total_tokens": 255436592}
{"current_steps": 4655, "total_steps": 4768, "loss": 0.2863, "lr": 1.4098495208484386e-08, "epoch": 1.9526006711409396, "percentage": 97.63, "elapsed_time": "7:17:39", "remaining_time": "0:10:37", "throughput": 9737.89, "total_tokens": 255713952}
{"current_steps": 4660, "total_steps": 4768, "loss": 0.2996, "lr": 1.2889425915905696e-08, "epoch": 1.9546979865771812, "percentage": 97.73, "elapsed_time": "7:18:08", "remaining_time": "0:10:09", "throughput": 9737.84, "total_tokens": 255992128}
{"current_steps": 4665, "total_steps": 4768, "loss": 0.3023, "lr": 1.1734483861173818e-08, "epoch": 1.9567953020134228, "percentage": 97.84, "elapsed_time": "7:18:35", "remaining_time": "0:09:41", "throughput": 9738.62, "total_tokens": 256272976}
{"current_steps": 4670, "total_steps": 4768, "loss": 0.305, "lr": 1.0633681579367838e-08, "epoch": 1.9588926174496644, "percentage": 97.94, "elapsed_time": "7:18:59", "remaining_time": "0:09:12", "throughput": 9739.1, "total_tokens": 256522472}
{"current_steps": 4675, "total_steps": 4768, "loss": 0.3003, "lr": 9.5870310179641e-09, "epoch": 1.960989932885906, "percentage": 98.05, "elapsed_time": "7:19:28", "remaining_time": "0:08:44", "throughput": 9740.15, "total_tokens": 256832104}
{"current_steps": 4680, "total_steps": 4768, "loss": 0.3, "lr": 8.594543536707966e-09, "epoch": 1.9630872483221475, "percentage": 98.15, "elapsed_time": "7:19:49", "remaining_time": "0:08:16", "throughput": 9742.43, "total_tokens": 257100736}
{"current_steps": 4685, "total_steps": 4768, "loss": 0.2964, "lr": 7.656229907487822e-09, "epoch": 1.9651845637583891, "percentage": 98.26, "elapsed_time": "7:20:16", "remaining_time": "0:07:47", "throughput": 9743.48, "total_tokens": 257384400}
{"current_steps": 4690, "total_steps": 4768, "loss": 0.2966, "lr": 6.772100314223484e-09, "epoch": 1.9672818791946307, "percentage": 98.36, "elapsed_time": "7:20:47", "remaining_time": "0:07:19", "throughput": 9741.67, "total_tokens": 257645120}
{"current_steps": 4695, "total_steps": 4768, "loss": 0.3066, "lr": 5.942164352749635e-09, "epoch": 1.9693791946308725, "percentage": 98.47, "elapsed_time": "7:21:13", "remaining_time": "0:06:51", "throughput": 9741.92, "total_tokens": 257898192}
{"current_steps": 4700, "total_steps": 4768, "loss": 0.2923, "lr": 5.166431030714792e-09, "epoch": 1.971476510067114, "percentage": 98.57, "elapsed_time": "7:21:39", "remaining_time": "0:06:23", "throughput": 9742.32, "total_tokens": 258165992}
{"current_steps": 4705, "total_steps": 4768, "loss": 0.2852, "lr": 4.444908767484712e-09, "epoch": 1.9735738255033557, "percentage": 98.68, "elapsed_time": "7:22:03", "remaining_time": "0:05:55", "throughput": 9743.83, "total_tokens": 258440664}
{"current_steps": 4710, "total_steps": 4768, "loss": 0.2968, "lr": 3.777605394046923e-09, "epoch": 1.9756711409395973, "percentage": 98.78, "elapsed_time": "7:22:30", "remaining_time": "0:05:26", "throughput": 9744.28, "total_tokens": 258715000}
{"current_steps": 4715, "total_steps": 4768, "loss": 0.3018, "lr": 3.164528152930224e-09, "epoch": 1.977768456375839, "percentage": 98.89, "elapsed_time": "7:22:59", "remaining_time": "0:04:58", "throughput": 9743.81, "total_tokens": 258986904}
{"current_steps": 4720, "total_steps": 4768, "loss": 0.3193, "lr": 2.605683698123085e-09, "epoch": 1.9798657718120807, "percentage": 98.99, "elapsed_time": "7:23:33", "remaining_time": "0:04:30", "throughput": 9741.38, "total_tokens": 259250568}
{"current_steps": 4725, "total_steps": 4768, "loss": 0.2988, "lr": 2.1010780950031506e-09, "epoch": 1.9819630872483223, "percentage": 99.1, "elapsed_time": "7:23:59", "remaining_time": "0:04:02", "throughput": 9740.88, "total_tokens": 259491944}
{"current_steps": 4730, "total_steps": 4768, "loss": 0.3295, "lr": 1.6507168202695157e-09, "epoch": 1.9840604026845639, "percentage": 99.2, "elapsed_time": "7:24:26", "remaining_time": "0:03:34", "throughput": 9742.1, "total_tokens": 259787424}
{"current_steps": 4735, "total_steps": 4768, "loss": 0.2951, "lr": 1.2546047618861024e-09, "epoch": 1.9861577181208054, "percentage": 99.31, "elapsed_time": "7:24:49", "remaining_time": "0:03:06", "throughput": 9744.63, "total_tokens": 260078032}
{"current_steps": 4740, "total_steps": 4768, "loss": 0.3121, "lr": 9.127462190244851e-10, "epoch": 1.988255033557047, "percentage": 99.41, "elapsed_time": "7:25:25", "remaining_time": "0:02:37", "throughput": 9742.33, "total_tokens": 260366400}
{"current_steps": 4745, "total_steps": 4768, "loss": 0.3056, "lr": 6.251449020228118e-10, "epoch": 1.9903523489932886, "percentage": 99.52, "elapsed_time": "7:25:57", "remaining_time": "0:02:09", "throughput": 9740.2, "total_tokens": 260624856}
{"current_steps": 4750, "total_steps": 4768, "loss": 0.2822, "lr": 3.918039323402845e-10, "epoch": 1.9924496644295302, "percentage": 99.62, "elapsed_time": "7:26:29", "remaining_time": "0:01:41", "throughput": 9738.01, "total_tokens": 260875472}
{"current_steps": 4755, "total_steps": 4768, "loss": 0.2859, "lr": 2.1272584252551853e-10, "epoch": 1.9945469798657718, "percentage": 99.73, "elapsed_time": "7:26:50", "remaining_time": "0:01:13", "throughput": 9740.51, "total_tokens": 261149224}
{"current_steps": 4760, "total_steps": 4768, "loss": 0.2997, "lr": 8.79125761898969e-11, "epoch": 1.9966442953020134, "percentage": 99.83, "elapsed_time": "7:27:20", "remaining_time": "0:00:45", "throughput": 9740.3, "total_tokens": 261431696}
{"current_steps": 4765, "total_steps": 4768, "loss": 0.3174, "lr": 1.7365487984810638e-11, "epoch": 1.998741610738255, "percentage": 99.94, "elapsed_time": "7:27:50", "remaining_time": "0:00:16", "throughput": 9739.42, "total_tokens": 261703896}
{"current_steps": 4768, "total_steps": 4768, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "7:29:58", "remaining_time": "0:00:00", "throughput": 9699.27, "total_tokens": 261863352}