train_record_1746090228 / trainer_log.jsonl
rbelanec's picture
Training in progress, step 3400
b3e639f verified
{"current_steps": 5, "total_steps": 40000, "loss": 11.9165, "lr": 0.29999999259779675, "epoch": 0.00016004097048844505, "percentage": 0.01, "elapsed_time": "0:00:04", "remaining_time": "8:56:25", "throughput": 1729.76, "total_tokens": 6960}
{"current_steps": 10, "total_steps": 40000, "loss": 10.884, "lr": 0.29999996252634736, "epoch": 0.0003200819409768901, "percentage": 0.03, "elapsed_time": "0:00:06", "remaining_time": "6:47:35", "throughput": 2244.83, "total_tokens": 13728}
{"current_steps": 15, "total_steps": 40000, "loss": 10.5376, "lr": 0.2999999093230187, "epoch": 0.0004801229114653351, "percentage": 0.04, "elapsed_time": "0:00:08", "remaining_time": "6:03:55", "throughput": 2525.61, "total_tokens": 20688}
{"current_steps": 20, "total_steps": 40000, "loss": 9.4978, "lr": 0.299999832987819, "epoch": 0.0006401638819537802, "percentage": 0.05, "elapsed_time": "0:00:10", "remaining_time": "5:42:17", "throughput": 2688.03, "total_tokens": 27616}
{"current_steps": 25, "total_steps": 40000, "loss": 9.1752, "lr": 0.29999973352076004, "epoch": 0.0008002048524422252, "percentage": 0.06, "elapsed_time": "0:00:12", "remaining_time": "5:28:45", "throughput": 2785.89, "total_tokens": 34368}
{"current_steps": 30, "total_steps": 40000, "loss": 8.3808, "lr": 0.2999996109218572, "epoch": 0.0009602458229306702, "percentage": 0.07, "elapsed_time": "0:00:14", "remaining_time": "5:21:10", "throughput": 2880.65, "total_tokens": 41664}
{"current_steps": 35, "total_steps": 40000, "loss": 8.4917, "lr": 0.2999994651911293, "epoch": 0.0011202867934191152, "percentage": 0.09, "elapsed_time": "0:00:16", "remaining_time": "5:14:47", "throughput": 2934.79, "total_tokens": 48544}
{"current_steps": 40, "total_steps": 40000, "loss": 8.1094, "lr": 0.2999992963285989, "epoch": 0.0012803277639075604, "percentage": 0.1, "elapsed_time": "0:00:18", "remaining_time": "5:09:57", "throughput": 2973.8, "total_tokens": 55360}
{"current_steps": 45, "total_steps": 40000, "loss": 6.3972, "lr": 0.29999910433429194, "epoch": 0.0014403687343960054, "percentage": 0.11, "elapsed_time": "0:00:20", "remaining_time": "5:05:42", "throughput": 3009.73, "total_tokens": 62176}
{"current_steps": 50, "total_steps": 40000, "loss": 7.7252, "lr": 0.29999888920823814, "epoch": 0.0016004097048844504, "percentage": 0.12, "elapsed_time": "0:00:22", "remaining_time": "5:02:18", "throughput": 3029.21, "total_tokens": 68768}
{"current_steps": 55, "total_steps": 40000, "loss": 7.9512, "lr": 0.29999865095047057, "epoch": 0.0017604506753728954, "percentage": 0.14, "elapsed_time": "0:00:24", "remaining_time": "4:59:14", "throughput": 3055.42, "total_tokens": 75536}
{"current_steps": 60, "total_steps": 40000, "loss": 7.1153, "lr": 0.29999838956102604, "epoch": 0.0019204916458613404, "percentage": 0.15, "elapsed_time": "0:00:26", "remaining_time": "4:56:51", "throughput": 3076.61, "total_tokens": 82320}
{"current_steps": 65, "total_steps": 40000, "loss": 7.4861, "lr": 0.29999810503994484, "epoch": 0.0020805326163497854, "percentage": 0.16, "elapsed_time": "0:00:28", "remaining_time": "4:55:24", "throughput": 3091.43, "total_tokens": 89184}
{"current_steps": 70, "total_steps": 40000, "loss": 7.1575, "lr": 0.29999779738727084, "epoch": 0.0022405735868382304, "percentage": 0.18, "elapsed_time": "0:00:30", "remaining_time": "4:54:36", "throughput": 3110.39, "total_tokens": 96384}
{"current_steps": 75, "total_steps": 40000, "loss": 7.5216, "lr": 0.29999746660305154, "epoch": 0.002400614557326676, "percentage": 0.19, "elapsed_time": "0:00:33", "remaining_time": "4:53:04", "throughput": 3116.92, "total_tokens": 102960}
{"current_steps": 80, "total_steps": 40000, "loss": 7.3122, "lr": 0.2999971126873379, "epoch": 0.002560655527815121, "percentage": 0.2, "elapsed_time": "0:00:35", "remaining_time": "4:51:37", "throughput": 3127.36, "total_tokens": 109664}
{"current_steps": 85, "total_steps": 40000, "loss": 7.248, "lr": 0.2999967356401845, "epoch": 0.002720696498303566, "percentage": 0.21, "elapsed_time": "0:00:37", "remaining_time": "4:51:04", "throughput": 3143.06, "total_tokens": 116896}
{"current_steps": 90, "total_steps": 40000, "loss": 6.5681, "lr": 0.29999633546164944, "epoch": 0.002880737468792011, "percentage": 0.22, "elapsed_time": "0:00:39", "remaining_time": "4:50:11", "throughput": 3153.27, "total_tokens": 123808}
{"current_steps": 95, "total_steps": 40000, "loss": 6.6301, "lr": 0.29999591215179444, "epoch": 0.003040778439280456, "percentage": 0.24, "elapsed_time": "0:00:41", "remaining_time": "4:49:40", "throughput": 3164.19, "total_tokens": 130928}
{"current_steps": 100, "total_steps": 40000, "loss": 6.66, "lr": 0.2999954657106849, "epoch": 0.003200819409768901, "percentage": 0.25, "elapsed_time": "0:00:43", "remaining_time": "4:49:04", "throughput": 3170.91, "total_tokens": 137840}
{"current_steps": 105, "total_steps": 40000, "loss": 7.127, "lr": 0.2999949961383896, "epoch": 0.003360860380257346, "percentage": 0.26, "elapsed_time": "0:00:45", "remaining_time": "4:48:29", "throughput": 3176.69, "total_tokens": 144720}
{"current_steps": 110, "total_steps": 40000, "loss": 7.0093, "lr": 0.2999945034349809, "epoch": 0.003520901350745791, "percentage": 0.27, "elapsed_time": "0:00:47", "remaining_time": "4:47:49", "throughput": 3181.01, "total_tokens": 151488}
{"current_steps": 115, "total_steps": 40000, "loss": 6.9485, "lr": 0.2999939876005348, "epoch": 0.003680942321234236, "percentage": 0.29, "elapsed_time": "0:00:49", "remaining_time": "4:47:15", "throughput": 3187.84, "total_tokens": 158416}
{"current_steps": 120, "total_steps": 40000, "loss": 7.0591, "lr": 0.29999344863513094, "epoch": 0.003840983291722681, "percentage": 0.3, "elapsed_time": "0:00:51", "remaining_time": "4:46:32", "throughput": 3189.91, "total_tokens": 165024}
{"current_steps": 125, "total_steps": 40000, "loss": 7.016, "lr": 0.2999928865388523, "epoch": 0.004001024262211126, "percentage": 0.31, "elapsed_time": "0:00:53", "remaining_time": "4:45:41", "throughput": 3193.49, "total_tokens": 171600}
{"current_steps": 130, "total_steps": 40000, "loss": 6.6879, "lr": 0.29999230131178567, "epoch": 0.004161065232699571, "percentage": 0.33, "elapsed_time": "0:00:55", "remaining_time": "4:45:11", "throughput": 3195.72, "total_tokens": 178304}
{"current_steps": 135, "total_steps": 40000, "loss": 6.4624, "lr": 0.2999916929540212, "epoch": 0.004321106203188016, "percentage": 0.34, "elapsed_time": "0:00:57", "remaining_time": "4:44:46", "throughput": 3200.89, "total_tokens": 185216}
{"current_steps": 140, "total_steps": 40000, "loss": 6.6082, "lr": 0.29999106146565285, "epoch": 0.004481147173676461, "percentage": 0.35, "elapsed_time": "0:00:59", "remaining_time": "4:44:06", "throughput": 3201.44, "total_tokens": 191680}
{"current_steps": 145, "total_steps": 40000, "loss": 6.5206, "lr": 0.29999040684677786, "epoch": 0.004641188144164906, "percentage": 0.36, "elapsed_time": "0:01:01", "remaining_time": "4:43:15", "throughput": 3203.45, "total_tokens": 198080}
{"current_steps": 150, "total_steps": 40000, "loss": 6.009, "lr": 0.2999897290974972, "epoch": 0.004801229114653352, "percentage": 0.38, "elapsed_time": "0:01:03", "remaining_time": "4:42:39", "throughput": 3207.31, "total_tokens": 204752}
{"current_steps": 155, "total_steps": 40000, "loss": 6.5874, "lr": 0.2999890282179155, "epoch": 0.004961270085141797, "percentage": 0.39, "elapsed_time": "0:01:05", "remaining_time": "4:42:09", "throughput": 3206.39, "total_tokens": 211168}
{"current_steps": 160, "total_steps": 40000, "loss": 6.0756, "lr": 0.29998830420814077, "epoch": 0.005121311055630242, "percentage": 0.4, "elapsed_time": "0:01:07", "remaining_time": "4:41:41", "throughput": 3205.01, "total_tokens": 217552}
{"current_steps": 165, "total_steps": 40000, "loss": 6.0557, "lr": 0.2999875570682846, "epoch": 0.005281352026118687, "percentage": 0.41, "elapsed_time": "0:01:09", "remaining_time": "4:41:22", "throughput": 3209.91, "total_tokens": 224464}
{"current_steps": 170, "total_steps": 40000, "loss": 6.1137, "lr": 0.2999867867984623, "epoch": 0.005441392996607132, "percentage": 0.43, "elapsed_time": "0:01:11", "remaining_time": "4:41:08", "throughput": 3211.62, "total_tokens": 231232}
{"current_steps": 175, "total_steps": 40000, "loss": 5.9628, "lr": 0.29998599339879267, "epoch": 0.005601433967095577, "percentage": 0.44, "elapsed_time": "0:01:14", "remaining_time": "4:41:07", "throughput": 3215.96, "total_tokens": 238368}
{"current_steps": 180, "total_steps": 40000, "loss": 6.0057, "lr": 0.29998517686939796, "epoch": 0.005761474937584022, "percentage": 0.45, "elapsed_time": "0:01:16", "remaining_time": "4:40:58", "throughput": 3218.26, "total_tokens": 245248}
{"current_steps": 185, "total_steps": 40000, "loss": 6.2583, "lr": 0.29998433721040413, "epoch": 0.005921515908072467, "percentage": 0.46, "elapsed_time": "0:01:18", "remaining_time": "4:40:43", "throughput": 3221.63, "total_tokens": 252128}
{"current_steps": 190, "total_steps": 40000, "loss": 6.6391, "lr": 0.29998347442194073, "epoch": 0.006081556878560912, "percentage": 0.47, "elapsed_time": "0:01:20", "remaining_time": "4:40:39", "throughput": 3225.5, "total_tokens": 259232}
{"current_steps": 195, "total_steps": 40000, "loss": 6.3201, "lr": 0.2999825885041407, "epoch": 0.006241597849049357, "percentage": 0.49, "elapsed_time": "0:01:22", "remaining_time": "4:40:29", "throughput": 3228.65, "total_tokens": 266192}
{"current_steps": 200, "total_steps": 40000, "loss": 7.2336, "lr": 0.29998167945714077, "epoch": 0.006401638819537802, "percentage": 0.5, "elapsed_time": "0:01:24", "remaining_time": "4:40:12", "throughput": 3231.31, "total_tokens": 272992}
{"current_steps": 200, "total_steps": 40000, "eval_loss": 6.363010406494141, "epoch": 0.006401638819537802, "percentage": 0.5, "elapsed_time": "0:12:07", "remaining_time": "1 day, 16:12:03", "throughput": 375.37, "total_tokens": 272992}
{"current_steps": 205, "total_steps": 40000, "loss": 6.6725, "lr": 0.2999807472810811, "epoch": 0.006561679790026247, "percentage": 0.51, "elapsed_time": "0:12:10", "remaining_time": "1 day, 15:22:41", "throughput": 382.85, "total_tokens": 279584}
{"current_steps": 210, "total_steps": 40000, "loss": 6.826, "lr": 0.29997979197610536, "epoch": 0.006721720760514692, "percentage": 0.53, "elapsed_time": "0:12:12", "remaining_time": "1 day, 14:32:53", "throughput": 391.45, "total_tokens": 286704}
{"current_steps": 215, "total_steps": 40000, "loss": 6.6501, "lr": 0.299978813542361, "epoch": 0.006881761731003137, "percentage": 0.54, "elapsed_time": "0:12:14", "remaining_time": "1 day, 13:45:10", "throughput": 399.64, "total_tokens": 293520}
{"current_steps": 220, "total_steps": 40000, "loss": 6.3936, "lr": 0.2999778119799988, "epoch": 0.007041802701491582, "percentage": 0.55, "elapsed_time": "0:12:16", "remaining_time": "1 day, 12:59:29", "throughput": 407.38, "total_tokens": 300032}
{"current_steps": 225, "total_steps": 40000, "loss": 6.922, "lr": 0.29997678728917326, "epoch": 0.007201843671980027, "percentage": 0.56, "elapsed_time": "0:12:18", "remaining_time": "1 day, 12:15:52", "throughput": 415.47, "total_tokens": 306832}
{"current_steps": 230, "total_steps": 40000, "loss": 6.8494, "lr": 0.2999757394700424, "epoch": 0.007361884642468472, "percentage": 0.57, "elapsed_time": "0:12:20", "remaining_time": "1 day, 11:34:11", "throughput": 423.55, "total_tokens": 313664}
{"current_steps": 235, "total_steps": 40000, "loss": 6.7042, "lr": 0.29997466852276783, "epoch": 0.007521925612956917, "percentage": 0.59, "elapsed_time": "0:12:22", "remaining_time": "1 day, 10:54:16", "throughput": 431.44, "total_tokens": 320384}
{"current_steps": 240, "total_steps": 40000, "loss": 6.9498, "lr": 0.29997357444751466, "epoch": 0.007681966583445362, "percentage": 0.6, "elapsed_time": "0:12:24", "remaining_time": "1 day, 10:15:59", "throughput": 439.01, "total_tokens": 326896}
{"current_steps": 245, "total_steps": 40000, "loss": 6.2374, "lr": 0.2999724572444516, "epoch": 0.007842007553933807, "percentage": 0.61, "elapsed_time": "0:12:26", "remaining_time": "1 day, 9:39:20", "throughput": 446.99, "total_tokens": 333760}
{"current_steps": 250, "total_steps": 40000, "loss": 6.5354, "lr": 0.29997131691375095, "epoch": 0.008002048524422252, "percentage": 0.62, "elapsed_time": "0:12:28", "remaining_time": "1 day, 9:04:00", "throughput": 454.52, "total_tokens": 340288}
{"current_steps": 255, "total_steps": 40000, "loss": 6.5011, "lr": 0.2999701534555886, "epoch": 0.008162089494910697, "percentage": 0.64, "elapsed_time": "0:12:30", "remaining_time": "1 day, 8:30:12", "throughput": 462.39, "total_tokens": 347136}
{"current_steps": 260, "total_steps": 40000, "loss": 5.8972, "lr": 0.2999689668701439, "epoch": 0.008322130465399142, "percentage": 0.65, "elapsed_time": "0:12:32", "remaining_time": "1 day, 7:57:39", "throughput": 469.81, "total_tokens": 353664}
{"current_steps": 265, "total_steps": 40000, "loss": 6.3462, "lr": 0.29996775715759993, "epoch": 0.008482171435887587, "percentage": 0.66, "elapsed_time": "0:12:34", "remaining_time": "1 day, 7:26:20", "throughput": 477.42, "total_tokens": 360368}
{"current_steps": 270, "total_steps": 40000, "loss": 6.1061, "lr": 0.2999665243181432, "epoch": 0.008642212406376032, "percentage": 0.68, "elapsed_time": "0:12:36", "remaining_time": "1 day, 6:56:09", "throughput": 484.81, "total_tokens": 366928}
{"current_steps": 275, "total_steps": 40000, "loss": 6.1097, "lr": 0.2999652683519638, "epoch": 0.008802253376864477, "percentage": 0.69, "elapsed_time": "0:12:38", "remaining_time": "1 day, 6:27:10", "throughput": 492.67, "total_tokens": 373904}
{"current_steps": 280, "total_steps": 40000, "loss": 6.6099, "lr": 0.29996398925925544, "epoch": 0.008962294347352922, "percentage": 0.7, "elapsed_time": "0:12:40", "remaining_time": "1 day, 5:59:07", "throughput": 499.94, "total_tokens": 380432}
{"current_steps": 285, "total_steps": 40000, "loss": 6.2252, "lr": 0.2999626870402154, "epoch": 0.009122335317841367, "percentage": 0.71, "elapsed_time": "0:12:43", "remaining_time": "1 day, 5:32:12", "throughput": 507.58, "total_tokens": 387312}
{"current_steps": 290, "total_steps": 40000, "loss": 6.1935, "lr": 0.29996136169504445, "epoch": 0.009282376288329812, "percentage": 0.73, "elapsed_time": "0:12:45", "remaining_time": "1 day, 5:06:05", "throughput": 514.84, "total_tokens": 393904}
{"current_steps": 295, "total_steps": 40000, "loss": 6.182, "lr": 0.29996001322394694, "epoch": 0.009442417258818258, "percentage": 0.74, "elapsed_time": "0:12:47", "remaining_time": "1 day, 4:40:57", "throughput": 522.29, "total_tokens": 400688}
{"current_steps": 300, "total_steps": 40000, "loss": 6.1859, "lr": 0.29995864162713093, "epoch": 0.009602458229306703, "percentage": 0.75, "elapsed_time": "0:12:49", "remaining_time": "1 day, 4:16:34", "throughput": 529.43, "total_tokens": 407248}
{"current_steps": 305, "total_steps": 40000, "loss": 6.3164, "lr": 0.2999572469048079, "epoch": 0.009762499199795148, "percentage": 0.76, "elapsed_time": "0:12:51", "remaining_time": "1 day, 3:53:05", "throughput": 536.87, "total_tokens": 414096}
{"current_steps": 310, "total_steps": 40000, "loss": 5.8071, "lr": 0.29995582905719287, "epoch": 0.009922540170283593, "percentage": 0.78, "elapsed_time": "0:12:53", "remaining_time": "1 day, 3:30:16", "throughput": 544.15, "total_tokens": 420832}
{"current_steps": 315, "total_steps": 40000, "loss": 5.9534, "lr": 0.2999543880845046, "epoch": 0.010082581140772038, "percentage": 0.79, "elapsed_time": "0:12:55", "remaining_time": "1 day, 3:08:06", "throughput": 551.09, "total_tokens": 427312}
{"current_steps": 320, "total_steps": 40000, "loss": 6.091, "lr": 0.2999529239869652, "epoch": 0.010242622111260483, "percentage": 0.8, "elapsed_time": "0:12:57", "remaining_time": "1 day, 2:46:34", "throughput": 557.88, "total_tokens": 433680}
{"current_steps": 325, "total_steps": 40000, "loss": 5.713, "lr": 0.2999514367648005, "epoch": 0.010402663081748928, "percentage": 0.81, "elapsed_time": "0:12:59", "remaining_time": "1 day, 2:25:49", "throughput": 564.99, "total_tokens": 440368}
{"current_steps": 330, "total_steps": 40000, "loss": 6.2723, "lr": 0.29994992641823987, "epoch": 0.010562704052237373, "percentage": 0.83, "elapsed_time": "0:13:01", "remaining_time": "1 day, 2:05:34", "throughput": 571.7, "total_tokens": 446736}
{"current_steps": 335, "total_steps": 40000, "loss": 5.9308, "lr": 0.29994839294751613, "epoch": 0.010722745022725818, "percentage": 0.84, "elapsed_time": "0:13:03", "remaining_time": "1 day, 1:45:55", "throughput": 578.41, "total_tokens": 453120}
{"current_steps": 340, "total_steps": 40000, "loss": 6.0077, "lr": 0.29994683635286584, "epoch": 0.010882785993214263, "percentage": 0.85, "elapsed_time": "0:13:05", "remaining_time": "1 day, 1:26:59", "throughput": 585.46, "total_tokens": 459840}
{"current_steps": 345, "total_steps": 40000, "loss": 6.5, "lr": 0.2999452566345291, "epoch": 0.011042826963702708, "percentage": 0.86, "elapsed_time": "0:13:07", "remaining_time": "1 day, 1:08:32", "throughput": 592.26, "total_tokens": 466384}
{"current_steps": 350, "total_steps": 40000, "loss": 6.0106, "lr": 0.2999436537927494, "epoch": 0.011202867934191153, "percentage": 0.88, "elapsed_time": "0:13:09", "remaining_time": "1 day, 0:50:42", "throughput": 599.51, "total_tokens": 473328}
{"current_steps": 355, "total_steps": 40000, "loss": 6.2192, "lr": 0.299942027827774, "epoch": 0.011362908904679598, "percentage": 0.89, "elapsed_time": "0:13:11", "remaining_time": "1 day, 0:33:27", "throughput": 606.9, "total_tokens": 480448}
{"current_steps": 360, "total_steps": 40000, "loss": 5.808, "lr": 0.29994037873985363, "epoch": 0.011522949875168043, "percentage": 0.9, "elapsed_time": "0:13:13", "remaining_time": "1 day, 0:16:39", "throughput": 614.07, "total_tokens": 487408}
{"current_steps": 365, "total_steps": 40000, "loss": 6.3348, "lr": 0.29993870652924254, "epoch": 0.011682990845656488, "percentage": 0.91, "elapsed_time": "0:13:15", "remaining_time": "1 day, 0:00:16", "throughput": 620.95, "total_tokens": 494160}
{"current_steps": 370, "total_steps": 40000, "loss": 5.495, "lr": 0.29993701119619876, "epoch": 0.011843031816144933, "percentage": 0.92, "elapsed_time": "0:13:17", "remaining_time": "23:44:11", "throughput": 627.32, "total_tokens": 500480}
{"current_steps": 375, "total_steps": 40000, "loss": 6.5543, "lr": 0.2999352927409835, "epoch": 0.012003072786633378, "percentage": 0.94, "elapsed_time": "0:13:19", "remaining_time": "23:28:39", "throughput": 634.38, "total_tokens": 507424}
{"current_steps": 380, "total_steps": 40000, "loss": 6.5024, "lr": 0.29993355116386194, "epoch": 0.012163113757121823, "percentage": 0.95, "elapsed_time": "0:13:21", "remaining_time": "23:13:30", "throughput": 641.04, "total_tokens": 514064}
{"current_steps": 385, "total_steps": 40000, "loss": 6.5898, "lr": 0.29993178646510266, "epoch": 0.012323154727610268, "percentage": 0.96, "elapsed_time": "0:13:23", "remaining_time": "22:58:43", "throughput": 647.82, "total_tokens": 520816}
{"current_steps": 390, "total_steps": 40000, "loss": 5.9479, "lr": 0.2999299986449777, "epoch": 0.012483195698098713, "percentage": 0.97, "elapsed_time": "0:13:25", "remaining_time": "22:44:14", "throughput": 654.3, "total_tokens": 527328}
{"current_steps": 395, "total_steps": 40000, "loss": 6.4728, "lr": 0.29992818770376284, "epoch": 0.012643236668587158, "percentage": 0.99, "elapsed_time": "0:13:28", "remaining_time": "22:30:24", "throughput": 661.62, "total_tokens": 534656}
{"current_steps": 400, "total_steps": 40000, "loss": 6.0652, "lr": 0.29992635364173725, "epoch": 0.012803277639075603, "percentage": 1.0, "elapsed_time": "0:13:30", "remaining_time": "22:16:46", "throughput": 668.43, "total_tokens": 541536}
{"current_steps": 400, "total_steps": 40000, "eval_loss": 6.057784080505371, "epoch": 0.012803277639075603, "percentage": 1.0, "elapsed_time": "0:24:14", "remaining_time": "1 day, 15:59:29", "throughput": 372.39, "total_tokens": 541536}
{"current_steps": 405, "total_steps": 40000, "loss": 6.159, "lr": 0.2999244964591839, "epoch": 0.012963318609564048, "percentage": 1.01, "elapsed_time": "0:24:17", "remaining_time": "1 day, 15:34:40", "throughput": 376.13, "total_tokens": 548160}
{"current_steps": 410, "total_steps": 40000, "loss": 5.9953, "lr": 0.2999226161563891, "epoch": 0.013123359580052493, "percentage": 1.03, "elapsed_time": "0:24:19", "remaining_time": "1 day, 15:08:46", "throughput": 380.3, "total_tokens": 555024}
{"current_steps": 415, "total_steps": 40000, "loss": 6.2168, "lr": 0.2999207127336429, "epoch": 0.013283400550540938, "percentage": 1.04, "elapsed_time": "0:24:21", "remaining_time": "1 day, 14:43:28", "throughput": 384.39, "total_tokens": 561792}
{"current_steps": 420, "total_steps": 40000, "loss": 6.1484, "lr": 0.2999187861912387, "epoch": 0.013443441521029383, "percentage": 1.05, "elapsed_time": "0:24:23", "remaining_time": "1 day, 14:18:44", "throughput": 388.41, "total_tokens": 568464}
{"current_steps": 425, "total_steps": 40000, "loss": 6.1495, "lr": 0.2999168365294737, "epoch": 0.013603482491517828, "percentage": 1.06, "elapsed_time": "0:24:25", "remaining_time": "1 day, 13:54:33", "throughput": 392.28, "total_tokens": 574928}
{"current_steps": 430, "total_steps": 40000, "loss": 6.0498, "lr": 0.29991486374864856, "epoch": 0.013763523462006273, "percentage": 1.07, "elapsed_time": "0:24:27", "remaining_time": "1 day, 13:30:56", "throughput": 396.42, "total_tokens": 581792}
{"current_steps": 435, "total_steps": 40000, "loss": 5.7788, "lr": 0.29991286784906745, "epoch": 0.013923564432494718, "percentage": 1.09, "elapsed_time": "0:24:29", "remaining_time": "1 day, 13:07:55", "throughput": 400.43, "total_tokens": 588512}
{"current_steps": 440, "total_steps": 40000, "loss": 6.0932, "lr": 0.2999108488310382, "epoch": 0.014083605402983163, "percentage": 1.1, "elapsed_time": "0:24:31", "remaining_time": "1 day, 12:45:21", "throughput": 404.4, "total_tokens": 595168}
{"current_steps": 445, "total_steps": 40000, "loss": 6.2707, "lr": 0.29990880669487213, "epoch": 0.014243646373471608, "percentage": 1.11, "elapsed_time": "0:24:33", "remaining_time": "1 day, 12:23:21", "throughput": 408.45, "total_tokens": 601968}
{"current_steps": 450, "total_steps": 40000, "loss": 5.7831, "lr": 0.29990674144088425, "epoch": 0.014403687343960053, "percentage": 1.12, "elapsed_time": "0:24:35", "remaining_time": "1 day, 12:01:42", "throughput": 412.28, "total_tokens": 608432}
{"current_steps": 455, "total_steps": 40000, "loss": 6.172, "lr": 0.299904653069393, "epoch": 0.014563728314448498, "percentage": 1.14, "elapsed_time": "0:24:37", "remaining_time": "1 day, 11:40:38", "throughput": 416.33, "total_tokens": 615248}
{"current_steps": 460, "total_steps": 40000, "loss": 5.8022, "lr": 0.29990254158072044, "epoch": 0.014723769284936943, "percentage": 1.15, "elapsed_time": "0:24:39", "remaining_time": "1 day, 11:20:07", "throughput": 420.59, "total_tokens": 622432}
{"current_steps": 465, "total_steps": 40000, "loss": 5.9393, "lr": 0.2999004069751921, "epoch": 0.014883810255425388, "percentage": 1.16, "elapsed_time": "0:24:42", "remaining_time": "1 day, 11:00:04", "throughput": 424.82, "total_tokens": 629600}
{"current_steps": 470, "total_steps": 40000, "loss": 6.5825, "lr": 0.2998982492531373, "epoch": 0.015043851225913833, "percentage": 1.18, "elapsed_time": "0:24:44", "remaining_time": "1 day, 10:40:24", "throughput": 428.96, "total_tokens": 636640}
{"current_steps": 475, "total_steps": 40000, "loss": 6.216, "lr": 0.2998960684148887, "epoch": 0.015203892196402278, "percentage": 1.19, "elapsed_time": "0:24:46", "remaining_time": "1 day, 10:21:14", "throughput": 433.38, "total_tokens": 644128}
{"current_steps": 480, "total_steps": 40000, "loss": 6.3157, "lr": 0.29989386446078264, "epoch": 0.015363933166890723, "percentage": 1.2, "elapsed_time": "0:24:48", "remaining_time": "1 day, 10:02:13", "throughput": 437.03, "total_tokens": 650416}
{"current_steps": 485, "total_steps": 40000, "loss": 6.5166, "lr": 0.299891637391159, "epoch": 0.015523974137379168, "percentage": 1.21, "elapsed_time": "0:24:50", "remaining_time": "1 day, 9:43:38", "throughput": 440.79, "total_tokens": 656896}
{"current_steps": 490, "total_steps": 40000, "loss": 6.7847, "lr": 0.2998893872063612, "epoch": 0.015684015107867613, "percentage": 1.23, "elapsed_time": "0:24:52", "remaining_time": "1 day, 9:25:23", "throughput": 444.59, "total_tokens": 663440}
{"current_steps": 495, "total_steps": 40000, "loss": 6.0881, "lr": 0.2998871139067363, "epoch": 0.01584405607835606, "percentage": 1.24, "elapsed_time": "0:24:54", "remaining_time": "1 day, 9:07:37", "throughput": 448.45, "total_tokens": 670128}
{"current_steps": 500, "total_steps": 40000, "loss": 5.9906, "lr": 0.2998848174926348, "epoch": 0.016004097048844503, "percentage": 1.25, "elapsed_time": "0:24:56", "remaining_time": "1 day, 8:50:11", "throughput": 452.21, "total_tokens": 676656}
{"current_steps": 505, "total_steps": 40000, "loss": 6.0859, "lr": 0.2998824979644109, "epoch": 0.01616413801933295, "percentage": 1.26, "elapsed_time": "0:24:58", "remaining_time": "1 day, 8:33:03", "throughput": 456.09, "total_tokens": 683392}
{"current_steps": 510, "total_steps": 40000, "loss": 6.7015, "lr": 0.29988015532242224, "epoch": 0.016324178989821393, "percentage": 1.27, "elapsed_time": "0:25:00", "remaining_time": "1 day, 8:16:24", "throughput": 460.18, "total_tokens": 690496}
{"current_steps": 515, "total_steps": 40000, "loss": 5.9448, "lr": 0.29987778956703015, "epoch": 0.01648421996030984, "percentage": 1.29, "elapsed_time": "0:25:02", "remaining_time": "1 day, 8:00:04", "throughput": 464.28, "total_tokens": 697632}
{"current_steps": 520, "total_steps": 40000, "loss": 5.5329, "lr": 0.2998754006985994, "epoch": 0.016644260930798283, "percentage": 1.3, "elapsed_time": "0:25:04", "remaining_time": "1 day, 7:44:04", "throughput": 468.61, "total_tokens": 705136}
{"current_steps": 525, "total_steps": 40000, "loss": 5.9314, "lr": 0.29987298871749846, "epoch": 0.01680430190128673, "percentage": 1.31, "elapsed_time": "0:25:06", "remaining_time": "1 day, 7:28:16", "throughput": 472.34, "total_tokens": 711712}
{"current_steps": 530, "total_steps": 40000, "loss": 6.3149, "lr": 0.2998705536240992, "epoch": 0.016964342871775173, "percentage": 1.32, "elapsed_time": "0:25:08", "remaining_time": "1 day, 7:12:49", "throughput": 476.3, "total_tokens": 718688}
{"current_steps": 535, "total_steps": 40000, "loss": 6.3303, "lr": 0.2998680954187772, "epoch": 0.01712438384226362, "percentage": 1.34, "elapsed_time": "0:25:10", "remaining_time": "1 day, 6:57:38", "throughput": 480.27, "total_tokens": 725664}
{"current_steps": 540, "total_steps": 40000, "loss": 4.9277, "lr": 0.2998656141019115, "epoch": 0.017284424812752063, "percentage": 1.35, "elapsed_time": "0:25:13", "remaining_time": "1 day, 6:42:41", "throughput": 484.03, "total_tokens": 732336}
{"current_steps": 545, "total_steps": 40000, "loss": 6.3865, "lr": 0.2998631096738848, "epoch": 0.01744446578324051, "percentage": 1.36, "elapsed_time": "0:25:15", "remaining_time": "1 day, 6:28:01", "throughput": 487.79, "total_tokens": 739024}
{"current_steps": 550, "total_steps": 40000, "loss": 5.9475, "lr": 0.29986058213508326, "epoch": 0.017604506753728953, "percentage": 1.38, "elapsed_time": "0:25:17", "remaining_time": "1 day, 6:13:40", "throughput": 491.68, "total_tokens": 745952}
{"current_steps": 555, "total_steps": 40000, "loss": 5.3066, "lr": 0.29985803148589674, "epoch": 0.0177645477242174, "percentage": 1.39, "elapsed_time": "0:25:19", "remaining_time": "1 day, 5:59:27", "throughput": 495.24, "total_tokens": 752336}
{"current_steps": 560, "total_steps": 40000, "loss": 6.109, "lr": 0.2998554577267185, "epoch": 0.017924588694705843, "percentage": 1.4, "elapsed_time": "0:25:21", "remaining_time": "1 day, 5:45:41", "throughput": 499.33, "total_tokens": 759616}
{"current_steps": 565, "total_steps": 40000, "loss": 6.3165, "lr": 0.2998528608579455, "epoch": 0.01808462966519429, "percentage": 1.41, "elapsed_time": "0:25:23", "remaining_time": "1 day, 5:32:09", "throughput": 503.32, "total_tokens": 766768}
{"current_steps": 570, "total_steps": 40000, "loss": 5.5567, "lr": 0.2998502408799781, "epoch": 0.018244670635682733, "percentage": 1.43, "elapsed_time": "0:25:25", "remaining_time": "1 day, 5:18:40", "throughput": 506.88, "total_tokens": 773200}
{"current_steps": 575, "total_steps": 40000, "loss": 6.329, "lr": 0.2998475977932205, "epoch": 0.01840471160617118, "percentage": 1.44, "elapsed_time": "0:25:27", "remaining_time": "1 day, 5:05:29", "throughput": 510.6, "total_tokens": 779920}
{"current_steps": 580, "total_steps": 40000, "loss": 6.5165, "lr": 0.29984493159808023, "epoch": 0.018564752576659623, "percentage": 1.45, "elapsed_time": "0:25:29", "remaining_time": "1 day, 4:52:34", "throughput": 514.34, "total_tokens": 786688}
{"current_steps": 585, "total_steps": 40000, "loss": 6.3185, "lr": 0.29984224229496836, "epoch": 0.01872479354714807, "percentage": 1.46, "elapsed_time": "0:25:31", "remaining_time": "1 day, 4:39:56", "throughput": 518.29, "total_tokens": 793840}
{"current_steps": 590, "total_steps": 40000, "loss": 6.0073, "lr": 0.2998395298842998, "epoch": 0.018884834517636517, "percentage": 1.47, "elapsed_time": "0:25:33", "remaining_time": "1 day, 4:27:24", "throughput": 521.91, "total_tokens": 800448}
{"current_steps": 595, "total_steps": 40000, "loss": 6.2243, "lr": 0.29983679436649263, "epoch": 0.01904487548812496, "percentage": 1.49, "elapsed_time": "0:25:35", "remaining_time": "1 day, 4:15:08", "throughput": 525.77, "total_tokens": 807456}
{"current_steps": 600, "total_steps": 40000, "loss": 6.0124, "lr": 0.2998340357419689, "epoch": 0.019204916458613407, "percentage": 1.5, "elapsed_time": "0:25:37", "remaining_time": "1 day, 4:02:57", "throughput": 529.12, "total_tokens": 813648}
{"current_steps": 600, "total_steps": 40000, "eval_loss": 5.923797130584717, "epoch": 0.019204916458613407, "percentage": 1.5, "elapsed_time": "0:36:21", "remaining_time": "1 day, 15:47:26", "throughput": 372.99, "total_tokens": 813648}
{"current_steps": 605, "total_steps": 40000, "loss": 5.9844, "lr": 0.29983125401115385, "epoch": 0.01936495742910185, "percentage": 1.51, "elapsed_time": "0:36:25", "remaining_time": "1 day, 15:32:10", "throughput": 375.32, "total_tokens": 820368}
{"current_steps": 610, "total_steps": 40000, "loss": 5.9111, "lr": 0.29982844917447654, "epoch": 0.019524998399590297, "percentage": 1.52, "elapsed_time": "0:36:27", "remaining_time": "1 day, 15:14:45", "throughput": 378.34, "total_tokens": 827792}
{"current_steps": 615, "total_steps": 40000, "loss": 6.061, "lr": 0.2998256212323695, "epoch": 0.01968503937007874, "percentage": 1.54, "elapsed_time": "0:36:29", "remaining_time": "1 day, 14:57:25", "throughput": 380.95, "total_tokens": 834256}
{"current_steps": 620, "total_steps": 40000, "loss": 6.0366, "lr": 0.29982277018526887, "epoch": 0.019845080340567187, "percentage": 1.55, "elapsed_time": "0:36:31", "remaining_time": "1 day, 14:40:27", "throughput": 383.65, "total_tokens": 840960}
{"current_steps": 625, "total_steps": 40000, "loss": 6.3067, "lr": 0.2998198960336143, "epoch": 0.02000512131105563, "percentage": 1.56, "elapsed_time": "0:36:34", "remaining_time": "1 day, 14:23:42", "throughput": 386.33, "total_tokens": 847616}
{"current_steps": 630, "total_steps": 40000, "loss": 6.4021, "lr": 0.299816998777849, "epoch": 0.020165162281544077, "percentage": 1.57, "elapsed_time": "0:36:36", "remaining_time": "1 day, 14:07:16", "throughput": 389.02, "total_tokens": 854320}
{"current_steps": 635, "total_steps": 40000, "loss": 5.5552, "lr": 0.2998140784184197, "epoch": 0.02032520325203252, "percentage": 1.59, "elapsed_time": "0:36:37", "remaining_time": "1 day, 13:50:57", "throughput": 391.61, "total_tokens": 860752}
{"current_steps": 640, "total_steps": 40000, "loss": 6.1633, "lr": 0.2998111349557769, "epoch": 0.020485244222520967, "percentage": 1.6, "elapsed_time": "0:36:40", "remaining_time": "1 day, 13:35:05", "throughput": 394.43, "total_tokens": 867792}
{"current_steps": 645, "total_steps": 40000, "loss": 6.2262, "lr": 0.29980816839037444, "epoch": 0.02064528519300941, "percentage": 1.61, "elapsed_time": "0:36:42", "remaining_time": "1 day, 13:19:25", "throughput": 397.23, "total_tokens": 874768}
{"current_steps": 650, "total_steps": 40000, "loss": 6.2867, "lr": 0.2998051787226698, "epoch": 0.020805326163497857, "percentage": 1.62, "elapsed_time": "0:36:44", "remaining_time": "1 day, 13:04:00", "throughput": 400.01, "total_tokens": 881712}
{"current_steps": 655, "total_steps": 40000, "loss": 5.7027, "lr": 0.29980216595312403, "epoch": 0.0209653671339863, "percentage": 1.64, "elapsed_time": "0:36:46", "remaining_time": "1 day, 12:48:51", "throughput": 402.86, "total_tokens": 888848}
{"current_steps": 660, "total_steps": 40000, "loss": 6.1074, "lr": 0.29979913008220177, "epoch": 0.021125408104474747, "percentage": 1.65, "elapsed_time": "0:36:48", "remaining_time": "1 day, 12:33:49", "throughput": 405.36, "total_tokens": 895168}
{"current_steps": 665, "total_steps": 40000, "loss": 6.3462, "lr": 0.2997960711103711, "epoch": 0.02128544907496319, "percentage": 1.66, "elapsed_time": "0:36:50", "remaining_time": "1 day, 12:19:07", "throughput": 408.17, "total_tokens": 902224}
{"current_steps": 670, "total_steps": 40000, "loss": 5.8661, "lr": 0.29979298903810386, "epoch": 0.021445490045451637, "percentage": 1.68, "elapsed_time": "0:36:52", "remaining_time": "1 day, 12:04:37", "throughput": 410.91, "total_tokens": 909136}
{"current_steps": 675, "total_steps": 40000, "loss": 6.0312, "lr": 0.29978988386587524, "epoch": 0.02160553101594008, "percentage": 1.69, "elapsed_time": "0:36:54", "remaining_time": "1 day, 11:50:17", "throughput": 413.53, "total_tokens": 915776}
{"current_steps": 680, "total_steps": 40000, "loss": 5.8313, "lr": 0.2997867555941642, "epoch": 0.021765571986428527, "percentage": 1.7, "elapsed_time": "0:36:56", "remaining_time": "1 day, 11:36:12", "throughput": 416.19, "total_tokens": 922544}
{"current_steps": 685, "total_steps": 40000, "loss": 5.5234, "lr": 0.299783604223453, "epoch": 0.02192561295691697, "percentage": 1.71, "elapsed_time": "0:36:58", "remaining_time": "1 day, 11:22:17", "throughput": 418.78, "total_tokens": 929120}
{"current_steps": 690, "total_steps": 40000, "loss": 5.6527, "lr": 0.29978042975422786, "epoch": 0.022085653927405417, "percentage": 1.73, "elapsed_time": "0:37:00", "remaining_time": "1 day, 11:08:41", "throughput": 421.7, "total_tokens": 936528}
{"current_steps": 695, "total_steps": 40000, "loss": 5.7162, "lr": 0.29977723218697816, "epoch": 0.02224569489789386, "percentage": 1.74, "elapsed_time": "0:37:02", "remaining_time": "1 day, 10:55:12", "throughput": 424.36, "total_tokens": 943296}
{"current_steps": 700, "total_steps": 40000, "loss": 5.9624, "lr": 0.299774011522197, "epoch": 0.022405735868382307, "percentage": 1.75, "elapsed_time": "0:37:04", "remaining_time": "1 day, 10:41:47", "throughput": 426.83, "total_tokens": 949616}
{"current_steps": 705, "total_steps": 40000, "loss": 6.2864, "lr": 0.29977076776038114, "epoch": 0.02256577683887075, "percentage": 1.76, "elapsed_time": "0:37:06", "remaining_time": "1 day, 10:28:36", "throughput": 429.34, "total_tokens": 956048}
{"current_steps": 710, "total_steps": 40000, "loss": 6.2898, "lr": 0.2997675009020307, "epoch": 0.022725817809359197, "percentage": 1.77, "elapsed_time": "0:37:08", "remaining_time": "1 day, 10:15:38", "throughput": 431.95, "total_tokens": 962736}
{"current_steps": 715, "total_steps": 40000, "loss": 6.074, "lr": 0.2997642109476496, "epoch": 0.02288585877984764, "percentage": 1.79, "elapsed_time": "0:37:10", "remaining_time": "1 day, 10:02:55", "throughput": 434.73, "total_tokens": 969856}
{"current_steps": 720, "total_steps": 40000, "loss": 5.9371, "lr": 0.299760897897745, "epoch": 0.023045899750336087, "percentage": 1.8, "elapsed_time": "0:37:12", "remaining_time": "1 day, 9:50:20", "throughput": 437.39, "total_tokens": 976672}
{"current_steps": 725, "total_steps": 40000, "loss": 6.3111, "lr": 0.29975756175282803, "epoch": 0.02320594072082453, "percentage": 1.81, "elapsed_time": "0:37:15", "remaining_time": "1 day, 9:37:59", "throughput": 440.12, "total_tokens": 983696}
{"current_steps": 730, "total_steps": 40000, "loss": 5.6699, "lr": 0.29975420251341306, "epoch": 0.023365981691312977, "percentage": 1.82, "elapsed_time": "0:37:17", "remaining_time": "1 day, 9:25:44", "throughput": 442.76, "total_tokens": 990512}
{"current_steps": 735, "total_steps": 40000, "loss": 6.0272, "lr": 0.29975082018001814, "epoch": 0.02352602266180142, "percentage": 1.84, "elapsed_time": "0:37:19", "remaining_time": "1 day, 9:13:40", "throughput": 445.39, "total_tokens": 997312}
{"current_steps": 740, "total_steps": 40000, "loss": 6.0837, "lr": 0.2997474147531648, "epoch": 0.023686063632289867, "percentage": 1.85, "elapsed_time": "0:37:21", "remaining_time": "1 day, 9:01:42", "throughput": 447.85, "total_tokens": 1003712}
{"current_steps": 745, "total_steps": 40000, "loss": 6.4962, "lr": 0.29974398623337833, "epoch": 0.02384610460277831, "percentage": 1.86, "elapsed_time": "0:37:23", "remaining_time": "1 day, 8:49:58", "throughput": 450.41, "total_tokens": 1010368}
{"current_steps": 750, "total_steps": 40000, "loss": 6.3304, "lr": 0.2997405346211873, "epoch": 0.024006145573266757, "percentage": 1.88, "elapsed_time": "0:37:25", "remaining_time": "1 day, 8:38:23", "throughput": 453.02, "total_tokens": 1017152}
{"current_steps": 755, "total_steps": 40000, "loss": 5.9011, "lr": 0.2997370599171241, "epoch": 0.0241661865437552, "percentage": 1.89, "elapsed_time": "0:37:27", "remaining_time": "1 day, 8:26:55", "throughput": 455.57, "total_tokens": 1023808}
{"current_steps": 760, "total_steps": 40000, "loss": 6.4207, "lr": 0.2997335621217246, "epoch": 0.024326227514243647, "percentage": 1.9, "elapsed_time": "0:37:29", "remaining_time": "1 day, 8:15:39", "throughput": 458.19, "total_tokens": 1030656}
{"current_steps": 765, "total_steps": 40000, "loss": 5.928, "lr": 0.29973004123552816, "epoch": 0.02448626848473209, "percentage": 1.91, "elapsed_time": "0:37:31", "remaining_time": "1 day, 8:04:33", "throughput": 460.89, "total_tokens": 1037696}
{"current_steps": 770, "total_steps": 40000, "loss": 6.4596, "lr": 0.2997264972590777, "epoch": 0.024646309455220537, "percentage": 1.93, "elapsed_time": "0:37:33", "remaining_time": "1 day, 7:53:31", "throughput": 463.39, "total_tokens": 1044240}
{"current_steps": 775, "total_steps": 40000, "loss": 6.4989, "lr": 0.29972293019291973, "epoch": 0.02480635042570898, "percentage": 1.94, "elapsed_time": "0:37:35", "remaining_time": "1 day, 7:42:37", "throughput": 465.76, "total_tokens": 1050528}
{"current_steps": 780, "total_steps": 40000, "loss": 5.8248, "lr": 0.2997193400376045, "epoch": 0.024966391396197427, "percentage": 1.95, "elapsed_time": "0:37:37", "remaining_time": "1 day, 7:31:55", "throughput": 468.38, "total_tokens": 1057408}
{"current_steps": 785, "total_steps": 40000, "loss": 6.376, "lr": 0.2997157267936854, "epoch": 0.025126432366685873, "percentage": 1.96, "elapsed_time": "0:37:39", "remaining_time": "1 day, 7:21:20", "throughput": 470.87, "total_tokens": 1063984}
{"current_steps": 790, "total_steps": 40000, "loss": 5.8632, "lr": 0.2997120904617199, "epoch": 0.025286473337174317, "percentage": 1.98, "elapsed_time": "0:37:41", "remaining_time": "1 day, 7:10:50", "throughput": 473.4, "total_tokens": 1070640}
{"current_steps": 795, "total_steps": 40000, "loss": 5.9076, "lr": 0.29970843104226863, "epoch": 0.025446514307662763, "percentage": 1.99, "elapsed_time": "0:37:43", "remaining_time": "1 day, 7:00:32", "throughput": 475.98, "total_tokens": 1077456}
{"current_steps": 800, "total_steps": 40000, "loss": 5.9982, "lr": 0.2997047485358959, "epoch": 0.025606555278151207, "percentage": 2.0, "elapsed_time": "0:37:45", "remaining_time": "1 day, 6:50:22", "throughput": 478.65, "total_tokens": 1084496}
{"current_steps": 800, "total_steps": 40000, "eval_loss": 5.937355041503906, "epoch": 0.025606555278151207, "percentage": 2.0, "elapsed_time": "0:48:29", "remaining_time": "1 day, 15:36:26", "throughput": 372.69, "total_tokens": 1084496}
{"current_steps": 805, "total_steps": 40000, "loss": 6.1173, "lr": 0.2997010429431697, "epoch": 0.025766596248639653, "percentage": 2.01, "elapsed_time": "0:48:33", "remaining_time": "1 day, 15:23:52", "throughput": 374.7, "total_tokens": 1091504}
{"current_steps": 810, "total_steps": 40000, "loss": 6.168, "lr": 0.29969731426466134, "epoch": 0.025926637219128097, "percentage": 2.02, "elapsed_time": "0:48:35", "remaining_time": "1 day, 15:10:40", "throughput": 376.83, "total_tokens": 1098496}
{"current_steps": 815, "total_steps": 40000, "loss": 6.0404, "lr": 0.299693562500946, "epoch": 0.026086678189616543, "percentage": 2.04, "elapsed_time": "0:48:37", "remaining_time": "1 day, 14:57:35", "throughput": 378.8, "total_tokens": 1105024}
{"current_steps": 820, "total_steps": 40000, "loss": 6.5816, "lr": 0.29968978765260207, "epoch": 0.026246719160104987, "percentage": 2.05, "elapsed_time": "0:48:39", "remaining_time": "1 day, 14:44:37", "throughput": 380.73, "total_tokens": 1111408}
{"current_steps": 825, "total_steps": 40000, "loss": 6.3703, "lr": 0.2996859897202118, "epoch": 0.026406760130593433, "percentage": 2.06, "elapsed_time": "0:48:41", "remaining_time": "1 day, 14:31:55", "throughput": 382.88, "total_tokens": 1118496}
{"current_steps": 830, "total_steps": 40000, "loss": 6.2524, "lr": 0.2996821687043609, "epoch": 0.026566801101081877, "percentage": 2.08, "elapsed_time": "0:48:43", "remaining_time": "1 day, 14:19:20", "throughput": 385.01, "total_tokens": 1125504}
{"current_steps": 835, "total_steps": 40000, "loss": 6.4402, "lr": 0.2996783246056384, "epoch": 0.026726842071570323, "percentage": 2.09, "elapsed_time": "0:48:45", "remaining_time": "1 day, 14:06:55", "throughput": 387.14, "total_tokens": 1132544}
{"current_steps": 840, "total_steps": 40000, "loss": 6.3456, "lr": 0.29967445742463744, "epoch": 0.026886883042058767, "percentage": 2.1, "elapsed_time": "0:48:47", "remaining_time": "1 day, 13:54:38", "throughput": 389.17, "total_tokens": 1139296}
{"current_steps": 845, "total_steps": 40000, "loss": 5.8793, "lr": 0.29967056716195417, "epoch": 0.027046924012547213, "percentage": 2.11, "elapsed_time": "0:48:49", "remaining_time": "1 day, 13:42:25", "throughput": 391.09, "total_tokens": 1145696}
{"current_steps": 850, "total_steps": 40000, "loss": 6.221, "lr": 0.2996666538181885, "epoch": 0.027206964983035656, "percentage": 2.12, "elapsed_time": "0:48:51", "remaining_time": "1 day, 13:30:23", "throughput": 393.11, "total_tokens": 1152416}
{"current_steps": 855, "total_steps": 40000, "loss": 5.7838, "lr": 0.29966271739394407, "epoch": 0.027367005953524103, "percentage": 2.14, "elapsed_time": "0:48:53", "remaining_time": "1 day, 13:18:29", "throughput": 395.11, "total_tokens": 1159072}
{"current_steps": 860, "total_steps": 40000, "loss": 5.0787, "lr": 0.29965875788982776, "epoch": 0.027527046924012546, "percentage": 2.15, "elapsed_time": "0:48:55", "remaining_time": "1 day, 13:06:43", "throughput": 397.09, "total_tokens": 1165696}
{"current_steps": 865, "total_steps": 40000, "loss": 6.0417, "lr": 0.2996547753064503, "epoch": 0.027687087894500993, "percentage": 2.16, "elapsed_time": "0:48:57", "remaining_time": "1 day, 12:55:06", "throughput": 399.1, "total_tokens": 1172416}
{"current_steps": 870, "total_steps": 40000, "loss": 5.5992, "lr": 0.29965076964442583, "epoch": 0.027847128864989436, "percentage": 2.17, "elapsed_time": "0:48:59", "remaining_time": "1 day, 12:43:38", "throughput": 401.11, "total_tokens": 1179136}
{"current_steps": 875, "total_steps": 40000, "loss": 6.2912, "lr": 0.299646740904372, "epoch": 0.028007169835477883, "percentage": 2.19, "elapsed_time": "0:49:01", "remaining_time": "1 day, 12:32:19", "throughput": 403.21, "total_tokens": 1186144}
{"current_steps": 880, "total_steps": 40000, "loss": 6.7373, "lr": 0.29964268908691016, "epoch": 0.028167210805966326, "percentage": 2.2, "elapsed_time": "0:49:03", "remaining_time": "1 day, 12:21:04", "throughput": 405.13, "total_tokens": 1192624}
{"current_steps": 885, "total_steps": 40000, "loss": 5.8581, "lr": 0.29963861419266513, "epoch": 0.028327251776454773, "percentage": 2.21, "elapsed_time": "0:49:05", "remaining_time": "1 day, 12:09:56", "throughput": 407.05, "total_tokens": 1199088}
{"current_steps": 890, "total_steps": 40000, "loss": 6.1912, "lr": 0.29963451622226533, "epoch": 0.028487292746943216, "percentage": 2.23, "elapsed_time": "0:49:07", "remaining_time": "1 day, 11:58:55", "throughput": 408.96, "total_tokens": 1205520}
{"current_steps": 895, "total_steps": 40000, "loss": 6.0144, "lr": 0.29963039517634277, "epoch": 0.028647333717431663, "percentage": 2.24, "elapsed_time": "0:49:09", "remaining_time": "1 day, 11:48:05", "throughput": 410.97, "total_tokens": 1212288}
{"current_steps": 900, "total_steps": 40000, "loss": 6.1498, "lr": 0.2996262510555328, "epoch": 0.028807374687920106, "percentage": 2.25, "elapsed_time": "0:49:11", "remaining_time": "1 day, 11:37:23", "throughput": 412.99, "total_tokens": 1219104}
{"current_steps": 905, "total_steps": 40000, "loss": 5.4508, "lr": 0.2996220838604746, "epoch": 0.028967415658408553, "percentage": 2.26, "elapsed_time": "0:49:13", "remaining_time": "1 day, 11:26:46", "throughput": 414.95, "total_tokens": 1225728}
{"current_steps": 910, "total_steps": 40000, "loss": 6.9999, "lr": 0.29961789359181085, "epoch": 0.029127456628896996, "percentage": 2.27, "elapsed_time": "0:49:16", "remaining_time": "1 day, 11:16:18", "throughput": 416.98, "total_tokens": 1232592}
{"current_steps": 915, "total_steps": 40000, "loss": 5.9145, "lr": 0.29961368025018764, "epoch": 0.029287497599385443, "percentage": 2.29, "elapsed_time": "0:49:17", "remaining_time": "1 day, 11:05:53", "throughput": 418.88, "total_tokens": 1239056}
{"current_steps": 920, "total_steps": 40000, "loss": 5.9653, "lr": 0.2996094438362548, "epoch": 0.029447538569873886, "percentage": 2.3, "elapsed_time": "0:49:20", "remaining_time": "1 day, 10:55:37", "throughput": 420.86, "total_tokens": 1245776}
{"current_steps": 925, "total_steps": 40000, "loss": 6.7053, "lr": 0.2996051843506657, "epoch": 0.029607579540362333, "percentage": 2.31, "elapsed_time": "0:49:22", "remaining_time": "1 day, 10:45:30", "throughput": 422.97, "total_tokens": 1252896}
{"current_steps": 930, "total_steps": 40000, "loss": 6.3535, "lr": 0.299600901794077, "epoch": 0.029767620510850776, "percentage": 2.33, "elapsed_time": "0:49:24", "remaining_time": "1 day, 10:35:28", "throughput": 425.02, "total_tokens": 1259840}
{"current_steps": 935, "total_steps": 40000, "loss": 6.496, "lr": 0.29959659616714923, "epoch": 0.029927661481339223, "percentage": 2.34, "elapsed_time": "0:49:26", "remaining_time": "1 day, 10:25:31", "throughput": 426.92, "total_tokens": 1266336}
{"current_steps": 940, "total_steps": 40000, "loss": 5.7261, "lr": 0.2995922674705464, "epoch": 0.030087702451827666, "percentage": 2.35, "elapsed_time": "0:49:28", "remaining_time": "1 day, 10:15:37", "throughput": 428.79, "total_tokens": 1272720}
{"current_steps": 945, "total_steps": 40000, "loss": 5.6111, "lr": 0.2995879157049361, "epoch": 0.030247743422316113, "percentage": 2.36, "elapsed_time": "0:49:30", "remaining_time": "1 day, 10:05:50", "throughput": 430.64, "total_tokens": 1279072}
{"current_steps": 950, "total_steps": 40000, "loss": 6.616, "lr": 0.2995835408709893, "epoch": 0.030407784392804556, "percentage": 2.38, "elapsed_time": "0:49:32", "remaining_time": "1 day, 9:56:12", "throughput": 432.58, "total_tokens": 1285712}
{"current_steps": 955, "total_steps": 40000, "loss": 5.4233, "lr": 0.29957914296938076, "epoch": 0.030567825363293003, "percentage": 2.39, "elapsed_time": "0:49:34", "remaining_time": "1 day, 9:46:48", "throughput": 434.87, "total_tokens": 1293488}
{"current_steps": 960, "total_steps": 40000, "loss": 6.2832, "lr": 0.2995747220007886, "epoch": 0.030727866333781446, "percentage": 2.4, "elapsed_time": "0:49:36", "remaining_time": "1 day, 9:37:25", "throughput": 436.9, "total_tokens": 1300432}
{"current_steps": 965, "total_steps": 40000, "loss": 6.276, "lr": 0.2995702779658947, "epoch": 0.030887907304269893, "percentage": 2.41, "elapsed_time": "0:49:38", "remaining_time": "1 day, 9:28:08", "throughput": 438.98, "total_tokens": 1307568}
{"current_steps": 970, "total_steps": 40000, "loss": 6.6504, "lr": 0.29956581086538425, "epoch": 0.031047948274758336, "percentage": 2.43, "elapsed_time": "0:49:40", "remaining_time": "1 day, 9:18:53", "throughput": 441.0, "total_tokens": 1314464}
{"current_steps": 975, "total_steps": 40000, "loss": 6.1431, "lr": 0.2995613206999462, "epoch": 0.031207989245246783, "percentage": 2.44, "elapsed_time": "0:49:42", "remaining_time": "1 day, 9:09:44", "throughput": 442.93, "total_tokens": 1321120}
{"current_steps": 980, "total_steps": 40000, "loss": 5.2442, "lr": 0.29955680747027297, "epoch": 0.031368030215735226, "percentage": 2.45, "elapsed_time": "0:49:44", "remaining_time": "1 day, 9:00:38", "throughput": 444.83, "total_tokens": 1327680}
{"current_steps": 985, "total_steps": 40000, "loss": 5.6796, "lr": 0.2995522711770607, "epoch": 0.03152807118622367, "percentage": 2.46, "elapsed_time": "0:49:46", "remaining_time": "1 day, 8:51:41", "throughput": 446.83, "total_tokens": 1334576}
{"current_steps": 990, "total_steps": 40000, "loss": 6.1717, "lr": 0.2995477118210087, "epoch": 0.03168811215671212, "percentage": 2.48, "elapsed_time": "0:49:48", "remaining_time": "1 day, 8:42:53", "throughput": 448.94, "total_tokens": 1341824}
{"current_steps": 995, "total_steps": 40000, "loss": 5.7895, "lr": 0.29954312940282024, "epoch": 0.03184815312720057, "percentage": 2.49, "elapsed_time": "0:49:50", "remaining_time": "1 day, 8:34:06", "throughput": 450.87, "total_tokens": 1348512}
{"current_steps": 1000, "total_steps": 40000, "loss": 6.5736, "lr": 0.29953852392320196, "epoch": 0.032008194097689006, "percentage": 2.5, "elapsed_time": "0:49:52", "remaining_time": "1 day, 8:25:26", "throughput": 452.88, "total_tokens": 1355472}
{"current_steps": 1000, "total_steps": 40000, "eval_loss": 5.864815711975098, "epoch": 0.032008194097689006, "percentage": 2.5, "elapsed_time": "1:00:36", "remaining_time": "1 day, 15:23:47", "throughput": 372.73, "total_tokens": 1355472}
{"current_steps": 1005, "total_steps": 40000, "loss": 5.7538, "lr": 0.2995338953828641, "epoch": 0.03216823506817745, "percentage": 2.51, "elapsed_time": "1:00:39", "remaining_time": "1 day, 15:13:43", "throughput": 374.26, "total_tokens": 1362192}
{"current_steps": 1010, "total_steps": 40000, "loss": 6.4775, "lr": 0.2995292437825204, "epoch": 0.0323282760386659, "percentage": 2.53, "elapsed_time": "1:00:41", "remaining_time": "1 day, 15:03:05", "throughput": 375.93, "total_tokens": 1369040}
{"current_steps": 1015, "total_steps": 40000, "loss": 5.9905, "lr": 0.29952456912288816, "epoch": 0.03248831700915435, "percentage": 2.54, "elapsed_time": "1:00:43", "remaining_time": "1 day, 14:52:33", "throughput": 377.52, "total_tokens": 1375616}
{"current_steps": 1020, "total_steps": 40000, "loss": 5.4039, "lr": 0.2995198714046884, "epoch": 0.032648357979642786, "percentage": 2.55, "elapsed_time": "1:00:45", "remaining_time": "1 day, 14:42:06", "throughput": 379.13, "total_tokens": 1382240}
{"current_steps": 1025, "total_steps": 40000, "loss": 6.079, "lr": 0.2995151506286454, "epoch": 0.03280839895013123, "percentage": 2.56, "elapsed_time": "1:00:47", "remaining_time": "1 day, 14:31:45", "throughput": 380.71, "total_tokens": 1388752}
{"current_steps": 1030, "total_steps": 40000, "loss": 6.5728, "lr": 0.2995104067954873, "epoch": 0.03296843992061968, "percentage": 2.57, "elapsed_time": "1:00:49", "remaining_time": "1 day, 14:21:32", "throughput": 382.38, "total_tokens": 1395648}
{"current_steps": 1035, "total_steps": 40000, "loss": 5.4822, "lr": 0.2995056399059456, "epoch": 0.03312848089110813, "percentage": 2.59, "elapsed_time": "1:00:51", "remaining_time": "1 day, 14:11:25", "throughput": 384.04, "total_tokens": 1402480}
{"current_steps": 1040, "total_steps": 40000, "loss": 6.1204, "lr": 0.2995008499607554, "epoch": 0.033288521861596566, "percentage": 2.6, "elapsed_time": "1:00:53", "remaining_time": "1 day, 14:01:24", "throughput": 385.76, "total_tokens": 1409552}
{"current_steps": 1045, "total_steps": 40000, "loss": 6.0821, "lr": 0.2994960369606554, "epoch": 0.03344856283208501, "percentage": 2.61, "elapsed_time": "1:00:56", "remaining_time": "1 day, 13:51:26", "throughput": 387.35, "total_tokens": 1416160}
{"current_steps": 1050, "total_steps": 40000, "loss": 6.1388, "lr": 0.2994912009063878, "epoch": 0.03360860380257346, "percentage": 2.62, "elapsed_time": "1:00:58", "remaining_time": "1 day, 13:41:38", "throughput": 389.02, "total_tokens": 1423072}
{"current_steps": 1055, "total_steps": 40000, "loss": 6.0049, "lr": 0.29948634179869843, "epoch": 0.03376864477306191, "percentage": 2.64, "elapsed_time": "1:01:00", "remaining_time": "1 day, 13:31:52", "throughput": 390.61, "total_tokens": 1429680}
{"current_steps": 1060, "total_steps": 40000, "loss": 6.1984, "lr": 0.29948145963833656, "epoch": 0.033928685743550346, "percentage": 2.65, "elapsed_time": "1:01:02", "remaining_time": "1 day, 13:22:11", "throughput": 392.15, "total_tokens": 1436096}
{"current_steps": 1065, "total_steps": 40000, "loss": 5.9294, "lr": 0.29947655442605514, "epoch": 0.03408872671403879, "percentage": 2.66, "elapsed_time": "1:01:04", "remaining_time": "1 day, 13:12:36", "throughput": 393.74, "total_tokens": 1442704}
{"current_steps": 1070, "total_steps": 40000, "loss": 6.155, "lr": 0.2994716261626106, "epoch": 0.03424876768452724, "percentage": 2.67, "elapsed_time": "1:01:06", "remaining_time": "1 day, 13:03:08", "throughput": 395.36, "total_tokens": 1449472}
{"current_steps": 1075, "total_steps": 40000, "loss": 5.4923, "lr": 0.2994666748487629, "epoch": 0.03440880865501569, "percentage": 2.69, "elapsed_time": "1:01:08", "remaining_time": "1 day, 12:53:47", "throughput": 397.06, "total_tokens": 1456560}
{"current_steps": 1080, "total_steps": 40000, "loss": 6.3139, "lr": 0.2994617004852756, "epoch": 0.034568849625504126, "percentage": 2.7, "elapsed_time": "1:01:10", "remaining_time": "1 day, 12:44:28", "throughput": 398.66, "total_tokens": 1463232}
{"current_steps": 1085, "total_steps": 40000, "loss": 5.7105, "lr": 0.2994567030729159, "epoch": 0.03472889059599257, "percentage": 2.71, "elapsed_time": "1:01:12", "remaining_time": "1 day, 12:35:15", "throughput": 400.26, "total_tokens": 1469904}
{"current_steps": 1090, "total_steps": 40000, "loss": 6.352, "lr": 0.29945168261245436, "epoch": 0.03488893156648102, "percentage": 2.73, "elapsed_time": "1:01:14", "remaining_time": "1 day, 12:26:05", "throughput": 401.82, "total_tokens": 1476464}
{"current_steps": 1095, "total_steps": 40000, "loss": 6.0966, "lr": 0.29944663910466524, "epoch": 0.03504897253696947, "percentage": 2.74, "elapsed_time": "1:01:16", "remaining_time": "1 day, 12:17:03", "throughput": 403.44, "total_tokens": 1483248}
{"current_steps": 1100, "total_steps": 40000, "loss": 6.0573, "lr": 0.2994415725503263, "epoch": 0.035209013507457906, "percentage": 2.75, "elapsed_time": "1:01:18", "remaining_time": "1 day, 12:08:08", "throughput": 405.17, "total_tokens": 1490464}
{"current_steps": 1105, "total_steps": 40000, "loss": 5.8477, "lr": 0.29943648295021885, "epoch": 0.03536905447794635, "percentage": 2.76, "elapsed_time": "1:01:20", "remaining_time": "1 day, 11:59:17", "throughput": 406.81, "total_tokens": 1497328}
{"current_steps": 1110, "total_steps": 40000, "loss": 6.1648, "lr": 0.2994313703051278, "epoch": 0.0355290954484348, "percentage": 2.77, "elapsed_time": "1:01:22", "remaining_time": "1 day, 11:50:28", "throughput": 408.34, "total_tokens": 1503808}
{"current_steps": 1115, "total_steps": 40000, "loss": 6.7749, "lr": 0.29942623461584156, "epoch": 0.03568913641892325, "percentage": 2.79, "elapsed_time": "1:01:24", "remaining_time": "1 day, 11:41:43", "throughput": 409.89, "total_tokens": 1510336}
{"current_steps": 1120, "total_steps": 40000, "loss": 5.7975, "lr": 0.29942107588315214, "epoch": 0.035849177389411686, "percentage": 2.8, "elapsed_time": "1:01:26", "remaining_time": "1 day, 11:33:06", "throughput": 411.57, "total_tokens": 1517392}
{"current_steps": 1125, "total_steps": 40000, "loss": 6.2529, "lr": 0.29941589410785513, "epoch": 0.03600921835990013, "percentage": 2.81, "elapsed_time": "1:01:28", "remaining_time": "1 day, 11:24:31", "throughput": 413.14, "total_tokens": 1524032}
{"current_steps": 1130, "total_steps": 40000, "loss": 5.5087, "lr": 0.29941068929074954, "epoch": 0.03616925933038858, "percentage": 2.83, "elapsed_time": "1:01:30", "remaining_time": "1 day, 11:16:02", "throughput": 414.78, "total_tokens": 1530944}
{"current_steps": 1135, "total_steps": 40000, "loss": 5.3815, "lr": 0.2994054614326381, "epoch": 0.03632930030087703, "percentage": 2.84, "elapsed_time": "1:01:32", "remaining_time": "1 day, 11:07:34", "throughput": 416.29, "total_tokens": 1537328}
{"current_steps": 1140, "total_steps": 40000, "loss": 5.6154, "lr": 0.29940021053432686, "epoch": 0.036489341271365466, "percentage": 2.85, "elapsed_time": "1:01:35", "remaining_time": "1 day, 10:59:14", "throughput": 417.89, "total_tokens": 1544112}
{"current_steps": 1145, "total_steps": 40000, "loss": 6.087, "lr": 0.29939493659662575, "epoch": 0.03664938224185391, "percentage": 2.86, "elapsed_time": "1:01:37", "remaining_time": "1 day, 10:50:56", "throughput": 419.43, "total_tokens": 1550640}
{"current_steps": 1150, "total_steps": 40000, "loss": 5.9035, "lr": 0.299389639620348, "epoch": 0.03680942321234236, "percentage": 2.88, "elapsed_time": "1:01:39", "remaining_time": "1 day, 10:42:44", "throughput": 421.04, "total_tokens": 1557440}
{"current_steps": 1155, "total_steps": 40000, "loss": 6.2354, "lr": 0.29938431960631046, "epoch": 0.03696946418283081, "percentage": 2.89, "elapsed_time": "1:01:41", "remaining_time": "1 day, 10:34:36", "throughput": 422.55, "total_tokens": 1563920}
{"current_steps": 1160, "total_steps": 40000, "loss": 6.1267, "lr": 0.2993789765553335, "epoch": 0.037129505153319246, "percentage": 2.9, "elapsed_time": "1:01:43", "remaining_time": "1 day, 10:26:31", "throughput": 424.18, "total_tokens": 1570800}
{"current_steps": 1165, "total_steps": 40000, "loss": 6.2919, "lr": 0.2993736104682412, "epoch": 0.03728954612380769, "percentage": 2.91, "elapsed_time": "1:01:45", "remaining_time": "1 day, 10:18:31", "throughput": 425.73, "total_tokens": 1577408}
{"current_steps": 1170, "total_steps": 40000, "loss": 6.1275, "lr": 0.299368221345861, "epoch": 0.03744958709429614, "percentage": 2.93, "elapsed_time": "1:01:47", "remaining_time": "1 day, 10:10:33", "throughput": 427.22, "total_tokens": 1583792}
{"current_steps": 1175, "total_steps": 40000, "loss": 5.5909, "lr": 0.29936280918902397, "epoch": 0.03760962806478459, "percentage": 2.94, "elapsed_time": "1:01:49", "remaining_time": "1 day, 10:02:41", "throughput": 428.78, "total_tokens": 1590432}
{"current_steps": 1180, "total_steps": 40000, "loss": 5.6471, "lr": 0.2993573739985648, "epoch": 0.03776966903527303, "percentage": 2.95, "elapsed_time": "1:01:51", "remaining_time": "1 day, 9:54:53", "throughput": 430.38, "total_tokens": 1597248}
{"current_steps": 1185, "total_steps": 40000, "loss": 5.8858, "lr": 0.2993519157753216, "epoch": 0.03792971000576147, "percentage": 2.96, "elapsed_time": "1:01:53", "remaining_time": "1 day, 9:47:10", "throughput": 431.95, "total_tokens": 1603952}
{"current_steps": 1190, "total_steps": 40000, "loss": 6.1018, "lr": 0.2993464345201361, "epoch": 0.03808975097624992, "percentage": 2.97, "elapsed_time": "1:01:55", "remaining_time": "1 day, 9:39:30", "throughput": 433.52, "total_tokens": 1610672}
{"current_steps": 1195, "total_steps": 40000, "loss": 6.3043, "lr": 0.2993409302338536, "epoch": 0.038249791946738367, "percentage": 2.99, "elapsed_time": "1:01:57", "remaining_time": "1 day, 9:31:55", "throughput": 435.12, "total_tokens": 1617520}
{"current_steps": 1200, "total_steps": 40000, "loss": 6.5922, "lr": 0.2993354029173229, "epoch": 0.03840983291722681, "percentage": 3.0, "elapsed_time": "1:01:59", "remaining_time": "1 day, 9:24:21", "throughput": 436.64, "total_tokens": 1624048}
{"current_steps": 1200, "total_steps": 40000, "eval_loss": 5.943019866943359, "epoch": 0.03840983291722681, "percentage": 3.0, "elapsed_time": "1:12:43", "remaining_time": "1 day, 15:11:22", "throughput": 372.2, "total_tokens": 1624048}
{"current_steps": 1205, "total_steps": 40000, "loss": 5.9517, "lr": 0.2993298525713965, "epoch": 0.03856987388771525, "percentage": 3.01, "elapsed_time": "1:12:46", "remaining_time": "1 day, 15:02:58", "throughput": 373.49, "total_tokens": 1630848}
{"current_steps": 1210, "total_steps": 40000, "loss": 6.0087, "lr": 0.29932427919693017, "epoch": 0.0387299148582037, "percentage": 3.02, "elapsed_time": "1:12:48", "remaining_time": "1 day, 14:54:04", "throughput": 374.84, "total_tokens": 1637504}
{"current_steps": 1215, "total_steps": 40000, "loss": 5.8937, "lr": 0.2993186827947834, "epoch": 0.038889955828692147, "percentage": 3.04, "elapsed_time": "1:12:50", "remaining_time": "1 day, 14:45:16", "throughput": 376.21, "total_tokens": 1644272}
{"current_steps": 1220, "total_steps": 40000, "loss": 5.4694, "lr": 0.2993130633658194, "epoch": 0.03904999679918059, "percentage": 3.05, "elapsed_time": "1:12:52", "remaining_time": "1 day, 14:36:31", "throughput": 377.58, "total_tokens": 1650992}
{"current_steps": 1225, "total_steps": 40000, "loss": 6.226, "lr": 0.29930742091090456, "epoch": 0.03921003776966903, "percentage": 3.06, "elapsed_time": "1:12:54", "remaining_time": "1 day, 14:27:52", "throughput": 378.96, "total_tokens": 1657840}
{"current_steps": 1230, "total_steps": 40000, "loss": 5.7968, "lr": 0.29930175543090914, "epoch": 0.03937007874015748, "percentage": 3.08, "elapsed_time": "1:12:56", "remaining_time": "1 day, 14:19:16", "throughput": 380.33, "total_tokens": 1664608}
{"current_steps": 1235, "total_steps": 40000, "loss": 6.0157, "lr": 0.2992960669267068, "epoch": 0.039530119710645927, "percentage": 3.09, "elapsed_time": "1:12:58", "remaining_time": "1 day, 14:10:46", "throughput": 381.74, "total_tokens": 1671568}
{"current_steps": 1240, "total_steps": 40000, "loss": 5.1418, "lr": 0.29929035539917476, "epoch": 0.03969016068113437, "percentage": 3.1, "elapsed_time": "1:13:00", "remaining_time": "1 day, 14:02:17", "throughput": 383.04, "total_tokens": 1678048}
{"current_steps": 1245, "total_steps": 40000, "loss": 5.8786, "lr": 0.2992846208491938, "epoch": 0.03985020165162281, "percentage": 3.11, "elapsed_time": "1:13:02", "remaining_time": "1 day, 13:53:53", "throughput": 384.38, "total_tokens": 1684688}
{"current_steps": 1250, "total_steps": 40000, "loss": 5.5978, "lr": 0.2992788632776483, "epoch": 0.04001024262211126, "percentage": 3.12, "elapsed_time": "1:13:04", "remaining_time": "1 day, 13:45:34", "throughput": 385.72, "total_tokens": 1691360}
{"current_steps": 1255, "total_steps": 40000, "loss": 5.687, "lr": 0.29927308268542613, "epoch": 0.040170283592599706, "percentage": 3.14, "elapsed_time": "1:13:07", "remaining_time": "1 day, 13:37:17", "throughput": 387.07, "total_tokens": 1698064}
{"current_steps": 1260, "total_steps": 40000, "loss": 6.2085, "lr": 0.2992672790734187, "epoch": 0.04033032456308815, "percentage": 3.15, "elapsed_time": "1:13:09", "remaining_time": "1 day, 13:29:07", "throughput": 388.47, "total_tokens": 1705040}
{"current_steps": 1265, "total_steps": 40000, "loss": 6.8377, "lr": 0.299261452442521, "epoch": 0.04049036553357659, "percentage": 3.16, "elapsed_time": "1:13:11", "remaining_time": "1 day, 13:21:00", "throughput": 389.86, "total_tokens": 1711952}
{"current_steps": 1270, "total_steps": 40000, "loss": 6.2772, "lr": 0.29925560279363167, "epoch": 0.04065040650406504, "percentage": 3.17, "elapsed_time": "1:13:13", "remaining_time": "1 day, 13:12:55", "throughput": 391.17, "total_tokens": 1718480}
{"current_steps": 1275, "total_steps": 40000, "loss": 5.695, "lr": 0.29924973012765266, "epoch": 0.040810447474553486, "percentage": 3.19, "elapsed_time": "1:13:15", "remaining_time": "1 day, 13:04:55", "throughput": 392.53, "total_tokens": 1725264}
{"current_steps": 1280, "total_steps": 40000, "loss": 5.6216, "lr": 0.29924383444548974, "epoch": 0.04097048844504193, "percentage": 3.2, "elapsed_time": "1:13:17", "remaining_time": "1 day, 12:56:57", "throughput": 393.83, "total_tokens": 1731792}
{"current_steps": 1285, "total_steps": 40000, "loss": 6.1586, "lr": 0.299237915748052, "epoch": 0.04113052941553037, "percentage": 3.21, "elapsed_time": "1:13:19", "remaining_time": "1 day, 12:49:05", "throughput": 395.26, "total_tokens": 1738880}
{"current_steps": 1290, "total_steps": 40000, "loss": 6.1083, "lr": 0.2992319740362522, "epoch": 0.04129057038601882, "percentage": 3.23, "elapsed_time": "1:13:21", "remaining_time": "1 day, 12:41:17", "throughput": 396.62, "total_tokens": 1745712}
{"current_steps": 1295, "total_steps": 40000, "loss": 6.0153, "lr": 0.2992260093110066, "epoch": 0.041450611356507266, "percentage": 3.24, "elapsed_time": "1:13:23", "remaining_time": "1 day, 12:33:31", "throughput": 397.96, "total_tokens": 1752400}
{"current_steps": 1300, "total_steps": 40000, "loss": 6.0426, "lr": 0.2992200215732352, "epoch": 0.04161065232699571, "percentage": 3.25, "elapsed_time": "1:13:25", "remaining_time": "1 day, 12:25:49", "throughput": 399.26, "total_tokens": 1758960}
{"current_steps": 1305, "total_steps": 40000, "loss": 5.2834, "lr": 0.2992140108238611, "epoch": 0.04177069329748415, "percentage": 3.26, "elapsed_time": "1:13:27", "remaining_time": "1 day, 12:18:10", "throughput": 400.64, "total_tokens": 1765840}
{"current_steps": 1310, "total_steps": 40000, "loss": 6.3927, "lr": 0.2992079770638115, "epoch": 0.0419307342679726, "percentage": 3.28, "elapsed_time": "1:13:29", "remaining_time": "1 day, 12:10:33", "throughput": 401.9, "total_tokens": 1772208}
{"current_steps": 1315, "total_steps": 40000, "loss": 6.3595, "lr": 0.29920192029401677, "epoch": 0.042090775238461046, "percentage": 3.29, "elapsed_time": "1:13:31", "remaining_time": "1 day, 12:03:01", "throughput": 403.25, "total_tokens": 1778976}
{"current_steps": 1320, "total_steps": 40000, "loss": 6.2804, "lr": 0.2991958405154109, "epoch": 0.04225081620894949, "percentage": 3.3, "elapsed_time": "1:13:33", "remaining_time": "1 day, 11:55:36", "throughput": 404.74, "total_tokens": 1786400}
{"current_steps": 1325, "total_steps": 40000, "loss": 5.6378, "lr": 0.29918973772893154, "epoch": 0.04241085717943793, "percentage": 3.31, "elapsed_time": "1:13:35", "remaining_time": "1 day, 11:48:11", "throughput": 406.09, "total_tokens": 1793200}
{"current_steps": 1330, "total_steps": 40000, "loss": 5.8995, "lr": 0.29918361193551973, "epoch": 0.04257089814992638, "percentage": 3.33, "elapsed_time": "1:13:37", "remaining_time": "1 day, 11:40:50", "throughput": 407.4, "total_tokens": 1799824}
{"current_steps": 1335, "total_steps": 40000, "loss": 6.0197, "lr": 0.29917746313612026, "epoch": 0.042730939120414826, "percentage": 3.34, "elapsed_time": "1:13:39", "remaining_time": "1 day, 11:33:33", "throughput": 408.8, "total_tokens": 1806880}
{"current_steps": 1340, "total_steps": 40000, "loss": 6.5575, "lr": 0.29917129133168124, "epoch": 0.04289098009090327, "percentage": 3.35, "elapsed_time": "1:13:41", "remaining_time": "1 day, 11:26:17", "throughput": 410.07, "total_tokens": 1813328}
{"current_steps": 1345, "total_steps": 40000, "loss": 5.842, "lr": 0.2991650965231546, "epoch": 0.04305102106139171, "percentage": 3.36, "elapsed_time": "1:13:43", "remaining_time": "1 day, 11:19:04", "throughput": 411.37, "total_tokens": 1819904}
{"current_steps": 1350, "total_steps": 40000, "loss": 6.4853, "lr": 0.29915887871149544, "epoch": 0.04321106203188016, "percentage": 3.38, "elapsed_time": "1:13:46", "remaining_time": "1 day, 11:11:57", "throughput": 412.76, "total_tokens": 1826896}
{"current_steps": 1355, "total_steps": 40000, "loss": 5.8503, "lr": 0.2991526378976628, "epoch": 0.043371103002368606, "percentage": 3.39, "elapsed_time": "1:13:48", "remaining_time": "1 day, 11:04:51", "throughput": 414.06, "total_tokens": 1833520}
{"current_steps": 1360, "total_steps": 40000, "loss": 6.1874, "lr": 0.29914637408261896, "epoch": 0.04353114397285705, "percentage": 3.4, "elapsed_time": "1:13:50", "remaining_time": "1 day, 10:57:47", "throughput": 415.34, "total_tokens": 1840032}
{"current_steps": 1365, "total_steps": 40000, "loss": 5.3418, "lr": 0.29914008726733, "epoch": 0.0436911849433455, "percentage": 3.41, "elapsed_time": "1:13:52", "remaining_time": "1 day, 10:50:46", "throughput": 416.61, "total_tokens": 1846464}
{"current_steps": 1370, "total_steps": 40000, "loss": 6.4209, "lr": 0.2991337774527653, "epoch": 0.04385122591383394, "percentage": 3.43, "elapsed_time": "1:13:54", "remaining_time": "1 day, 10:43:50", "throughput": 417.96, "total_tokens": 1853296}
{"current_steps": 1375, "total_steps": 40000, "loss": 5.3773, "lr": 0.2991274446398981, "epoch": 0.044011266884322386, "percentage": 3.44, "elapsed_time": "1:13:56", "remaining_time": "1 day, 10:36:56", "throughput": 419.26, "total_tokens": 1859904}
{"current_steps": 1380, "total_steps": 40000, "loss": 5.7545, "lr": 0.29912108882970484, "epoch": 0.04417130785481083, "percentage": 3.45, "elapsed_time": "1:13:58", "remaining_time": "1 day, 10:30:08", "throughput": 420.66, "total_tokens": 1867024}
{"current_steps": 1385, "total_steps": 40000, "loss": 5.7576, "lr": 0.2991147100231657, "epoch": 0.04433134882529928, "percentage": 3.46, "elapsed_time": "1:14:00", "remaining_time": "1 day, 10:23:21", "throughput": 421.96, "total_tokens": 1873664}
{"current_steps": 1390, "total_steps": 40000, "loss": 5.5732, "lr": 0.2991083082212644, "epoch": 0.04449138979578772, "percentage": 3.48, "elapsed_time": "1:14:02", "remaining_time": "1 day, 10:16:35", "throughput": 423.27, "total_tokens": 1880320}
{"current_steps": 1395, "total_steps": 40000, "loss": 5.9022, "lr": 0.2991018834249881, "epoch": 0.044651430766276166, "percentage": 3.49, "elapsed_time": "1:14:04", "remaining_time": "1 day, 10:09:55", "throughput": 424.61, "total_tokens": 1887168}
{"current_steps": 1400, "total_steps": 40000, "loss": 6.3551, "lr": 0.29909543563532764, "epoch": 0.04481147173676461, "percentage": 3.5, "elapsed_time": "1:14:06", "remaining_time": "1 day, 10:03:17", "throughput": 425.94, "total_tokens": 1893968}
{"current_steps": 1400, "total_steps": 40000, "eval_loss": 5.784642219543457, "epoch": 0.04481147173676461, "percentage": 3.5, "elapsed_time": "1:24:50", "remaining_time": "1 day, 14:59:04", "throughput": 372.08, "total_tokens": 1893968}
{"current_steps": 1405, "total_steps": 40000, "loss": 5.8254, "lr": 0.29908896485327746, "epoch": 0.04497151270725306, "percentage": 3.51, "elapsed_time": "1:24:53", "remaining_time": "1 day, 14:51:57", "throughput": 373.12, "total_tokens": 1900480}
{"current_steps": 1410, "total_steps": 40000, "loss": 5.9586, "lr": 0.29908247107983527, "epoch": 0.0451315536777415, "percentage": 3.52, "elapsed_time": "1:24:55", "remaining_time": "1 day, 14:44:19", "throughput": 374.31, "total_tokens": 1907296}
{"current_steps": 1415, "total_steps": 40000, "loss": 6.359, "lr": 0.29907595431600253, "epoch": 0.045291594648229946, "percentage": 3.54, "elapsed_time": "1:24:57", "remaining_time": "1 day, 14:36:42", "throughput": 375.43, "total_tokens": 1913744}
{"current_steps": 1420, "total_steps": 40000, "loss": 6.269, "lr": 0.29906941456278424, "epoch": 0.04545163561871839, "percentage": 3.55, "elapsed_time": "1:24:59", "remaining_time": "1 day, 14:29:10", "throughput": 376.56, "total_tokens": 1920304}
{"current_steps": 1425, "total_steps": 40000, "loss": 6.5303, "lr": 0.2990628518211889, "epoch": 0.04561167658920684, "percentage": 3.56, "elapsed_time": "1:25:01", "remaining_time": "1 day, 14:21:39", "throughput": 377.68, "total_tokens": 1926736}
{"current_steps": 1430, "total_steps": 40000, "loss": 6.5047, "lr": 0.2990562660922286, "epoch": 0.04577171755969528, "percentage": 3.57, "elapsed_time": "1:25:03", "remaining_time": "1 day, 14:14:15", "throughput": 378.91, "total_tokens": 1933792}
{"current_steps": 1435, "total_steps": 40000, "loss": 5.8582, "lr": 0.2990496573769189, "epoch": 0.045931758530183726, "percentage": 3.59, "elapsed_time": "1:25:05", "remaining_time": "1 day, 14:06:51", "throughput": 380.01, "total_tokens": 1940176}
{"current_steps": 1440, "total_steps": 40000, "loss": 5.9197, "lr": 0.29904302567627894, "epoch": 0.04609179950067217, "percentage": 3.6, "elapsed_time": "1:25:07", "remaining_time": "1 day, 13:59:31", "throughput": 381.15, "total_tokens": 1946784}
{"current_steps": 1445, "total_steps": 40000, "loss": 6.2213, "lr": 0.2990363709913314, "epoch": 0.04625184047116062, "percentage": 3.61, "elapsed_time": "1:25:09", "remaining_time": "1 day, 13:52:16", "throughput": 382.37, "total_tokens": 1953792}
{"current_steps": 1450, "total_steps": 40000, "loss": 6.0304, "lr": 0.29902969332310264, "epoch": 0.04641188144164906, "percentage": 3.62, "elapsed_time": "1:25:11", "remaining_time": "1 day, 13:45:03", "throughput": 383.56, "total_tokens": 1960704}
{"current_steps": 1455, "total_steps": 40000, "loss": 5.9521, "lr": 0.2990229926726223, "epoch": 0.046571922412137506, "percentage": 3.64, "elapsed_time": "1:25:13", "remaining_time": "1 day, 13:37:52", "throughput": 384.7, "total_tokens": 1967280}
{"current_steps": 1460, "total_steps": 40000, "loss": 5.8971, "lr": 0.29901626904092365, "epoch": 0.04673196338262595, "percentage": 3.65, "elapsed_time": "1:25:15", "remaining_time": "1 day, 13:30:45", "throughput": 385.84, "total_tokens": 1973936}
{"current_steps": 1465, "total_steps": 40000, "loss": 6.739, "lr": 0.2990095224290438, "epoch": 0.0468920043531144, "percentage": 3.66, "elapsed_time": "1:25:17", "remaining_time": "1 day, 13:23:40", "throughput": 387.0, "total_tokens": 1980624}
{"current_steps": 1470, "total_steps": 40000, "loss": 6.6148, "lr": 0.29900275283802297, "epoch": 0.04705204532360284, "percentage": 3.67, "elapsed_time": "1:25:19", "remaining_time": "1 day, 13:16:37", "throughput": 388.1, "total_tokens": 1987056}
{"current_steps": 1475, "total_steps": 40000, "loss": 4.6056, "lr": 0.2989959602689051, "epoch": 0.047212086294091286, "percentage": 3.69, "elapsed_time": "1:25:22", "remaining_time": "1 day, 13:09:40", "throughput": 389.28, "total_tokens": 1993888}
{"current_steps": 1480, "total_steps": 40000, "loss": 5.8078, "lr": 0.2989891447227379, "epoch": 0.04737212726457973, "percentage": 3.7, "elapsed_time": "1:25:24", "remaining_time": "1 day, 13:02:45", "throughput": 390.51, "total_tokens": 2001008}
{"current_steps": 1485, "total_steps": 40000, "loss": 6.5346, "lr": 0.29898230620057215, "epoch": 0.04753216823506818, "percentage": 3.71, "elapsed_time": "1:25:26", "remaining_time": "1 day, 12:55:49", "throughput": 391.59, "total_tokens": 2007312}
{"current_steps": 1490, "total_steps": 40000, "loss": 5.711, "lr": 0.2989754447034626, "epoch": 0.04769220920555662, "percentage": 3.72, "elapsed_time": "1:25:28", "remaining_time": "1 day, 12:48:59", "throughput": 392.72, "total_tokens": 2013904}
{"current_steps": 1495, "total_steps": 40000, "loss": 5.7954, "lr": 0.2989685602324673, "epoch": 0.047852250176045066, "percentage": 3.74, "elapsed_time": "1:25:30", "remaining_time": "1 day, 12:42:11", "throughput": 393.83, "total_tokens": 2020384}
{"current_steps": 1500, "total_steps": 40000, "loss": 5.6315, "lr": 0.298961652788648, "epoch": 0.04801229114653351, "percentage": 3.75, "elapsed_time": "1:25:32", "remaining_time": "1 day, 12:35:26", "throughput": 394.98, "total_tokens": 2027104}
{"current_steps": 1505, "total_steps": 40000, "loss": 5.5858, "lr": 0.29895472237306986, "epoch": 0.04817233211702196, "percentage": 3.76, "elapsed_time": "1:25:34", "remaining_time": "1 day, 12:28:46", "throughput": 396.2, "total_tokens": 2034240}
{"current_steps": 1510, "total_steps": 40000, "loss": 5.5016, "lr": 0.29894776898680164, "epoch": 0.0483323730875104, "percentage": 3.77, "elapsed_time": "1:25:36", "remaining_time": "1 day, 12:22:05", "throughput": 397.3, "total_tokens": 2040672}
{"current_steps": 1515, "total_steps": 40000, "loss": 5.4309, "lr": 0.29894079263091566, "epoch": 0.048492414057998846, "percentage": 3.79, "elapsed_time": "1:25:38", "remaining_time": "1 day, 12:15:27", "throughput": 398.4, "total_tokens": 2047136}
{"current_steps": 1520, "total_steps": 40000, "loss": 5.3383, "lr": 0.2989337933064877, "epoch": 0.04865245502848729, "percentage": 3.8, "elapsed_time": "1:25:40", "remaining_time": "1 day, 12:08:51", "throughput": 399.49, "total_tokens": 2053520}
{"current_steps": 1525, "total_steps": 40000, "loss": 6.0541, "lr": 0.29892677101459725, "epoch": 0.04881249599897574, "percentage": 3.81, "elapsed_time": "1:25:42", "remaining_time": "1 day, 12:02:22", "throughput": 400.76, "total_tokens": 2060896}
{"current_steps": 1530, "total_steps": 40000, "loss": 5.676, "lr": 0.2989197257563272, "epoch": 0.04897253696946418, "percentage": 3.82, "elapsed_time": "1:25:44", "remaining_time": "1 day, 11:55:49", "throughput": 401.82, "total_tokens": 2067136}
{"current_steps": 1535, "total_steps": 40000, "loss": 5.6381, "lr": 0.2989126575327639, "epoch": 0.049132577939952626, "percentage": 3.84, "elapsed_time": "1:25:46", "remaining_time": "1 day, 11:49:22", "throughput": 403.01, "total_tokens": 2074048}
{"current_steps": 1540, "total_steps": 40000, "loss": 5.3685, "lr": 0.29890556634499754, "epoch": 0.04929261891044107, "percentage": 3.85, "elapsed_time": "1:25:48", "remaining_time": "1 day, 11:42:55", "throughput": 404.09, "total_tokens": 2080416}
{"current_steps": 1545, "total_steps": 40000, "loss": 6.3811, "lr": 0.2988984521941216, "epoch": 0.04945265988092952, "percentage": 3.86, "elapsed_time": "1:25:50", "remaining_time": "1 day, 11:36:33", "throughput": 405.22, "total_tokens": 2087072}
{"current_steps": 1550, "total_steps": 40000, "loss": 6.309, "lr": 0.29889131508123307, "epoch": 0.04961270085141796, "percentage": 3.88, "elapsed_time": "1:25:52", "remaining_time": "1 day, 11:30:14", "throughput": 406.38, "total_tokens": 2093872}
{"current_steps": 1555, "total_steps": 40000, "loss": 5.9608, "lr": 0.2988841550074327, "epoch": 0.049772741821906406, "percentage": 3.89, "elapsed_time": "1:25:54", "remaining_time": "1 day, 11:23:57", "throughput": 407.56, "total_tokens": 2100784}
{"current_steps": 1560, "total_steps": 40000, "loss": 6.1617, "lr": 0.2988769719738246, "epoch": 0.04993278279239485, "percentage": 3.9, "elapsed_time": "1:25:56", "remaining_time": "1 day, 11:17:42", "throughput": 408.7, "total_tokens": 2107488}
{"current_steps": 1565, "total_steps": 40000, "loss": 6.0348, "lr": 0.29886976598151666, "epoch": 0.0500928237628833, "percentage": 3.91, "elapsed_time": "1:25:58", "remaining_time": "1 day, 11:11:30", "throughput": 409.85, "total_tokens": 2114224}
{"current_steps": 1570, "total_steps": 40000, "loss": 5.4202, "lr": 0.29886253703161986, "epoch": 0.05025286473337175, "percentage": 3.92, "elapsed_time": "1:26:00", "remaining_time": "1 day, 11:05:20", "throughput": 410.97, "total_tokens": 2120880}
{"current_steps": 1575, "total_steps": 40000, "loss": 5.6578, "lr": 0.29885528512524917, "epoch": 0.050412905703860186, "percentage": 3.94, "elapsed_time": "1:26:02", "remaining_time": "1 day, 10:59:15", "throughput": 412.2, "total_tokens": 2128112}
{"current_steps": 1580, "total_steps": 40000, "loss": 6.0957, "lr": 0.29884801026352287, "epoch": 0.05057294667434863, "percentage": 3.95, "elapsed_time": "1:26:04", "remaining_time": "1 day, 10:53:10", "throughput": 413.36, "total_tokens": 2134928}
{"current_steps": 1585, "total_steps": 40000, "loss": 5.526, "lr": 0.2988407124475629, "epoch": 0.05073298764483708, "percentage": 3.96, "elapsed_time": "1:26:06", "remaining_time": "1 day, 10:47:07", "throughput": 414.53, "total_tokens": 2141808}
{"current_steps": 1590, "total_steps": 40000, "loss": 6.2933, "lr": 0.2988333916784945, "epoch": 0.050893028615325527, "percentage": 3.98, "elapsed_time": "1:26:09", "remaining_time": "1 day, 10:41:10", "throughput": 415.82, "total_tokens": 2149376}
{"current_steps": 1595, "total_steps": 40000, "loss": 5.3781, "lr": 0.2988260479574468, "epoch": 0.051053069585813966, "percentage": 3.99, "elapsed_time": "1:26:11", "remaining_time": "1 day, 10:35:13", "throughput": 417.0, "total_tokens": 2156352}
{"current_steps": 1600, "total_steps": 40000, "loss": 5.8648, "lr": 0.2988186812855523, "epoch": 0.05121311055630241, "percentage": 4.0, "elapsed_time": "1:26:13", "remaining_time": "1 day, 10:29:17", "throughput": 418.12, "total_tokens": 2163024}
{"current_steps": 1600, "total_steps": 40000, "eval_loss": 5.778336048126221, "epoch": 0.05121311055630241, "percentage": 4.0, "elapsed_time": "1:36:57", "remaining_time": "1 day, 14:46:55", "throughput": 371.83, "total_tokens": 2163024}
{"current_steps": 1605, "total_steps": 40000, "loss": 5.9466, "lr": 0.29881129166394693, "epoch": 0.05137315152679086, "percentage": 4.01, "elapsed_time": "1:37:01", "remaining_time": "1 day, 14:41:10", "throughput": 372.69, "total_tokens": 2169744}
{"current_steps": 1610, "total_steps": 40000, "loss": 5.7912, "lr": 0.29880387909377026, "epoch": 0.051533192497279307, "percentage": 4.03, "elapsed_time": "1:37:03", "remaining_time": "1 day, 14:34:30", "throughput": 373.78, "total_tokens": 2176896}
{"current_steps": 1615, "total_steps": 40000, "loss": 5.9032, "lr": 0.2987964435761655, "epoch": 0.051693233467767746, "percentage": 4.04, "elapsed_time": "1:37:05", "remaining_time": "1 day, 14:27:51", "throughput": 374.82, "total_tokens": 2183696}
{"current_steps": 1620, "total_steps": 40000, "loss": 5.6758, "lr": 0.29878898511227925, "epoch": 0.05185327443825619, "percentage": 4.05, "elapsed_time": "1:37:08", "remaining_time": "1 day, 14:21:13", "throughput": 375.84, "total_tokens": 2190400}
{"current_steps": 1625, "total_steps": 40000, "loss": 5.9929, "lr": 0.2987815037032617, "epoch": 0.05201331540874464, "percentage": 4.06, "elapsed_time": "1:37:10", "remaining_time": "1 day, 14:14:38", "throughput": 376.86, "total_tokens": 2197088}
{"current_steps": 1630, "total_steps": 40000, "loss": 6.0121, "lr": 0.29877399935026655, "epoch": 0.052173356379233086, "percentage": 4.08, "elapsed_time": "1:37:12", "remaining_time": "1 day, 14:08:06", "throughput": 377.92, "total_tokens": 2204064}
{"current_steps": 1635, "total_steps": 40000, "loss": 5.5645, "lr": 0.2987664720544511, "epoch": 0.052333397349721526, "percentage": 4.09, "elapsed_time": "1:37:14", "remaining_time": "1 day, 14:01:36", "throughput": 378.93, "total_tokens": 2210704}
{"current_steps": 1640, "total_steps": 40000, "loss": 5.9876, "lr": 0.2987589218169761, "epoch": 0.05249343832020997, "percentage": 4.1, "elapsed_time": "1:37:16", "remaining_time": "1 day, 13:55:10", "throughput": 379.96, "total_tokens": 2217536}
{"current_steps": 1645, "total_steps": 40000, "loss": 5.3529, "lr": 0.29875134863900604, "epoch": 0.05265347929069842, "percentage": 4.11, "elapsed_time": "1:37:18", "remaining_time": "1 day, 13:48:44", "throughput": 380.95, "total_tokens": 2224080}
{"current_steps": 1650, "total_steps": 40000, "loss": 5.6928, "lr": 0.29874375252170865, "epoch": 0.052813520261186866, "percentage": 4.12, "elapsed_time": "1:37:20", "remaining_time": "1 day, 13:42:22", "throughput": 381.98, "total_tokens": 2230848}
{"current_steps": 1655, "total_steps": 40000, "loss": 5.988, "lr": 0.2987361334662553, "epoch": 0.052973561231675306, "percentage": 4.14, "elapsed_time": "1:37:22", "remaining_time": "1 day, 13:36:03", "throughput": 383.04, "total_tokens": 2237888}
{"current_steps": 1660, "total_steps": 40000, "loss": 5.3, "lr": 0.29872849147382113, "epoch": 0.05313360220216375, "percentage": 4.15, "elapsed_time": "1:37:24", "remaining_time": "1 day, 13:29:45", "throughput": 384.06, "total_tokens": 2244640}
{"current_steps": 1665, "total_steps": 40000, "loss": 6.2018, "lr": 0.2987208265455845, "epoch": 0.0532936431726522, "percentage": 4.16, "elapsed_time": "1:37:26", "remaining_time": "1 day, 13:23:31", "throughput": 385.14, "total_tokens": 2251760}
{"current_steps": 1670, "total_steps": 40000, "loss": 6.0184, "lr": 0.29871313868272753, "epoch": 0.053453684143140646, "percentage": 4.17, "elapsed_time": "1:37:28", "remaining_time": "1 day, 13:17:16", "throughput": 386.11, "total_tokens": 2258208}
{"current_steps": 1675, "total_steps": 40000, "loss": 6.3351, "lr": 0.29870542788643567, "epoch": 0.053613725113629086, "percentage": 4.19, "elapsed_time": "1:37:30", "remaining_time": "1 day, 13:11:05", "throughput": 387.15, "total_tokens": 2265088}
{"current_steps": 1680, "total_steps": 40000, "loss": 6.4825, "lr": 0.2986976941578981, "epoch": 0.05377376608411753, "percentage": 4.2, "elapsed_time": "1:37:32", "remaining_time": "1 day, 13:04:57", "throughput": 388.18, "total_tokens": 2271888}
{"current_steps": 1685, "total_steps": 40000, "loss": 5.4204, "lr": 0.29868993749830747, "epoch": 0.05393380705460598, "percentage": 4.21, "elapsed_time": "1:37:34", "remaining_time": "1 day, 12:58:52", "throughput": 389.25, "total_tokens": 2278976}
{"current_steps": 1690, "total_steps": 40000, "loss": 5.7602, "lr": 0.2986821579088598, "epoch": 0.054093848025094426, "percentage": 4.23, "elapsed_time": "1:37:36", "remaining_time": "1 day, 12:52:45", "throughput": 390.23, "total_tokens": 2285520}
{"current_steps": 1695, "total_steps": 40000, "loss": 6.3245, "lr": 0.29867435539075504, "epoch": 0.054253888995582866, "percentage": 4.24, "elapsed_time": "1:37:38", "remaining_time": "1 day, 12:46:43", "throughput": 391.26, "total_tokens": 2292352}
{"current_steps": 1700, "total_steps": 40000, "loss": 5.647, "lr": 0.2986665299451963, "epoch": 0.05441392996607131, "percentage": 4.25, "elapsed_time": "1:37:41", "remaining_time": "1 day, 12:40:45", "throughput": 392.37, "total_tokens": 2299696}
{"current_steps": 1705, "total_steps": 40000, "loss": 6.5028, "lr": 0.29865868157339037, "epoch": 0.05457397093655976, "percentage": 4.26, "elapsed_time": "1:37:43", "remaining_time": "1 day, 12:34:48", "throughput": 393.39, "total_tokens": 2306496}
{"current_steps": 1710, "total_steps": 40000, "loss": 6.3855, "lr": 0.2986508102765476, "epoch": 0.054734011907048206, "percentage": 4.28, "elapsed_time": "1:37:45", "remaining_time": "1 day, 12:28:52", "throughput": 394.46, "total_tokens": 2313600}
{"current_steps": 1715, "total_steps": 40000, "loss": 5.8195, "lr": 0.2986429160558818, "epoch": 0.054894052877536646, "percentage": 4.29, "elapsed_time": "1:37:47", "remaining_time": "1 day, 12:22:59", "throughput": 395.49, "total_tokens": 2320480}
{"current_steps": 1720, "total_steps": 40000, "loss": 5.6512, "lr": 0.2986349989126104, "epoch": 0.05505409384802509, "percentage": 4.3, "elapsed_time": "1:37:49", "remaining_time": "1 day, 12:17:09", "throughput": 396.61, "total_tokens": 2327904}
{"current_steps": 1725, "total_steps": 40000, "loss": 5.9995, "lr": 0.29862705884795426, "epoch": 0.05521413481851354, "percentage": 4.31, "elapsed_time": "1:37:51", "remaining_time": "1 day, 12:11:18", "throughput": 397.58, "total_tokens": 2334400}
{"current_steps": 1730, "total_steps": 40000, "loss": 6.4449, "lr": 0.2986190958631379, "epoch": 0.055374175789001986, "percentage": 4.32, "elapsed_time": "1:37:53", "remaining_time": "1 day, 12:05:31", "throughput": 398.61, "total_tokens": 2341264}
{"current_steps": 1735, "total_steps": 40000, "loss": 6.0496, "lr": 0.29861110995938933, "epoch": 0.055534216759490426, "percentage": 4.34, "elapsed_time": "1:37:55", "remaining_time": "1 day, 11:59:44", "throughput": 399.63, "total_tokens": 2348080}
{"current_steps": 1740, "total_steps": 40000, "loss": 5.5927, "lr": 0.29860310113794, "epoch": 0.05569425772997887, "percentage": 4.35, "elapsed_time": "1:37:57", "remaining_time": "1 day, 11:54:00", "throughput": 400.64, "total_tokens": 2354800}
{"current_steps": 1745, "total_steps": 40000, "loss": 6.4068, "lr": 0.29859506940002506, "epoch": 0.05585429870046732, "percentage": 4.36, "elapsed_time": "1:37:59", "remaining_time": "1 day, 11:48:19", "throughput": 401.71, "total_tokens": 2361968}
{"current_steps": 1750, "total_steps": 40000, "loss": 6.1486, "lr": 0.298587014746883, "epoch": 0.056014339670955766, "percentage": 4.38, "elapsed_time": "1:38:01", "remaining_time": "1 day, 11:42:38", "throughput": 402.68, "total_tokens": 2368448}
{"current_steps": 1755, "total_steps": 40000, "loss": 6.6435, "lr": 0.298578937179756, "epoch": 0.05617438064144421, "percentage": 4.39, "elapsed_time": "1:38:03", "remaining_time": "1 day, 11:36:59", "throughput": 403.69, "total_tokens": 2375248}
{"current_steps": 1760, "total_steps": 40000, "loss": 5.6438, "lr": 0.29857083669988976, "epoch": 0.05633442161193265, "percentage": 4.4, "elapsed_time": "1:38:05", "remaining_time": "1 day, 11:31:23", "throughput": 404.69, "total_tokens": 2381920}
{"current_steps": 1765, "total_steps": 40000, "loss": 5.9011, "lr": 0.29856271330853346, "epoch": 0.0564944625824211, "percentage": 4.41, "elapsed_time": "1:38:07", "remaining_time": "1 day, 11:25:48", "throughput": 405.63, "total_tokens": 2388320}
{"current_steps": 1770, "total_steps": 40000, "loss": 5.8485, "lr": 0.2985545670069398, "epoch": 0.056654503552909546, "percentage": 4.42, "elapsed_time": "1:38:09", "remaining_time": "1 day, 11:20:16", "throughput": 406.66, "total_tokens": 2395200}
{"current_steps": 1775, "total_steps": 40000, "loss": 5.8066, "lr": 0.29854639779636505, "epoch": 0.05681454452339799, "percentage": 4.44, "elapsed_time": "1:38:12", "remaining_time": "1 day, 11:14:45", "throughput": 407.68, "total_tokens": 2402032}
{"current_steps": 1780, "total_steps": 40000, "loss": 5.598, "lr": 0.298538205678069, "epoch": 0.05697458549388643, "percentage": 4.45, "elapsed_time": "1:38:14", "remaining_time": "1 day, 11:09:18", "throughput": 408.76, "total_tokens": 2409296}
{"current_steps": 1785, "total_steps": 40000, "loss": 5.871, "lr": 0.298529990653315, "epoch": 0.05713462646437488, "percentage": 4.46, "elapsed_time": "1:38:16", "remaining_time": "1 day, 11:03:51", "throughput": 409.77, "total_tokens": 2416096}
{"current_steps": 1790, "total_steps": 40000, "loss": 5.572, "lr": 0.29852175272336984, "epoch": 0.057294667434863326, "percentage": 4.47, "elapsed_time": "1:38:18", "remaining_time": "1 day, 10:58:27", "throughput": 410.8, "total_tokens": 2422992}
{"current_steps": 1795, "total_steps": 40000, "loss": 5.2033, "lr": 0.29851349188950405, "epoch": 0.05745470840535177, "percentage": 4.49, "elapsed_time": "1:38:20", "remaining_time": "1 day, 10:53:00", "throughput": 411.73, "total_tokens": 2429280}
{"current_steps": 1800, "total_steps": 40000, "loss": 6.5723, "lr": 0.2985052081529914, "epoch": 0.05761474937584021, "percentage": 4.5, "elapsed_time": "1:38:22", "remaining_time": "1 day, 10:47:38", "throughput": 412.73, "total_tokens": 2436032}
{"current_steps": 1800, "total_steps": 40000, "eval_loss": 5.795552730560303, "epoch": 0.05761474937584021, "percentage": 4.5, "elapsed_time": "1:49:06", "remaining_time": "1 day, 14:35:28", "throughput": 372.12, "total_tokens": 2436032}
{"current_steps": 1805, "total_steps": 40000, "loss": 6.1439, "lr": 0.29849690151510944, "epoch": 0.05777479034632866, "percentage": 4.51, "elapsed_time": "1:49:10", "remaining_time": "1 day, 14:30:05", "throughput": 372.9, "total_tokens": 2442544}
{"current_steps": 1810, "total_steps": 40000, "loss": 6.0189, "lr": 0.2984885719771392, "epoch": 0.057934831316817106, "percentage": 4.52, "elapsed_time": "1:49:12", "remaining_time": "1 day, 14:24:08", "throughput": 373.81, "total_tokens": 2449312}
{"current_steps": 1815, "total_steps": 40000, "loss": 6.0766, "lr": 0.2984802195403651, "epoch": 0.05809487228730555, "percentage": 4.54, "elapsed_time": "1:49:14", "remaining_time": "1 day, 14:18:12", "throughput": 374.75, "total_tokens": 2456208}
{"current_steps": 1820, "total_steps": 40000, "loss": 5.5989, "lr": 0.2984718442060752, "epoch": 0.05825491325779399, "percentage": 4.55, "elapsed_time": "1:49:16", "remaining_time": "1 day, 14:12:18", "throughput": 375.65, "total_tokens": 2462896}
{"current_steps": 1825, "total_steps": 40000, "loss": 5.7493, "lr": 0.2984634459755611, "epoch": 0.05841495422828244, "percentage": 4.56, "elapsed_time": "1:49:18", "remaining_time": "1 day, 14:06:25", "throughput": 376.51, "total_tokens": 2469296}
{"current_steps": 1830, "total_steps": 40000, "loss": 5.6128, "lr": 0.29845502485011793, "epoch": 0.058574995198770886, "percentage": 4.58, "elapsed_time": "1:49:20", "remaining_time": "1 day, 14:00:35", "throughput": 377.43, "total_tokens": 2476064}
{"current_steps": 1835, "total_steps": 40000, "loss": 6.0635, "lr": 0.2984465808310444, "epoch": 0.05873503616925933, "percentage": 4.59, "elapsed_time": "1:49:22", "remaining_time": "1 day, 13:54:47", "throughput": 378.34, "total_tokens": 2482832}
{"current_steps": 1840, "total_steps": 40000, "loss": 5.7222, "lr": 0.29843811391964253, "epoch": 0.05889507713974777, "percentage": 4.6, "elapsed_time": "1:49:24", "remaining_time": "1 day, 13:49:01", "throughput": 379.23, "total_tokens": 2489472}
{"current_steps": 1845, "total_steps": 40000, "loss": 6.1649, "lr": 0.2984296241172182, "epoch": 0.05905511811023622, "percentage": 4.61, "elapsed_time": "1:49:26", "remaining_time": "1 day, 13:43:18", "throughput": 380.19, "total_tokens": 2496528}
{"current_steps": 1850, "total_steps": 40000, "loss": 5.7466, "lr": 0.29842111142508043, "epoch": 0.059215159080724666, "percentage": 4.62, "elapsed_time": "1:49:28", "remaining_time": "1 day, 13:37:35", "throughput": 381.08, "total_tokens": 2503184}
{"current_steps": 1855, "total_steps": 40000, "loss": 5.3153, "lr": 0.29841257584454217, "epoch": 0.05937520005121311, "percentage": 4.64, "elapsed_time": "1:49:30", "remaining_time": "1 day, 13:31:53", "throughput": 381.93, "total_tokens": 2509504}
{"current_steps": 1860, "total_steps": 40000, "loss": 6.0742, "lr": 0.29840401737691963, "epoch": 0.05953524102170155, "percentage": 4.65, "elapsed_time": "1:49:32", "remaining_time": "1 day, 13:26:14", "throughput": 382.85, "total_tokens": 2516304}
{"current_steps": 1865, "total_steps": 40000, "loss": 5.9167, "lr": 0.29839543602353263, "epoch": 0.05969528199219, "percentage": 4.66, "elapsed_time": "1:49:34", "remaining_time": "1 day, 13:20:36", "throughput": 383.71, "total_tokens": 2522736}
{"current_steps": 1870, "total_steps": 40000, "loss": 5.9255, "lr": 0.2983868317857046, "epoch": 0.059855322962678446, "percentage": 4.67, "elapsed_time": "1:49:36", "remaining_time": "1 day, 13:15:03", "throughput": 384.7, "total_tokens": 2530128}
{"current_steps": 1875, "total_steps": 40000, "loss": 6.0868, "lr": 0.2983782046647623, "epoch": 0.06001536393316689, "percentage": 4.69, "elapsed_time": "1:49:38", "remaining_time": "1 day, 13:09:29", "throughput": 385.59, "total_tokens": 2536752}
{"current_steps": 1880, "total_steps": 40000, "loss": 7.0271, "lr": 0.2983695546620362, "epoch": 0.06017540490365533, "percentage": 4.7, "elapsed_time": "1:49:40", "remaining_time": "1 day, 13:03:59", "throughput": 386.56, "total_tokens": 2543920}
{"current_steps": 1885, "total_steps": 40000, "loss": 5.6167, "lr": 0.2983608817788603, "epoch": 0.06033544587414378, "percentage": 4.71, "elapsed_time": "1:49:43", "remaining_time": "1 day, 12:58:29", "throughput": 387.44, "total_tokens": 2550528}
{"current_steps": 1890, "total_steps": 40000, "loss": 5.9605, "lr": 0.29835218601657193, "epoch": 0.060495486844632226, "percentage": 4.72, "elapsed_time": "1:49:45", "remaining_time": "1 day, 12:53:01", "throughput": 388.33, "total_tokens": 2557184}
{"current_steps": 1895, "total_steps": 40000, "loss": 5.9618, "lr": 0.29834346737651224, "epoch": 0.06065552781512067, "percentage": 4.74, "elapsed_time": "1:49:47", "remaining_time": "1 day, 12:47:33", "throughput": 389.18, "total_tokens": 2563536}
{"current_steps": 1900, "total_steps": 40000, "loss": 6.0546, "lr": 0.29833472586002563, "epoch": 0.06081556878560911, "percentage": 4.75, "elapsed_time": "1:49:49", "remaining_time": "1 day, 12:42:09", "throughput": 390.14, "total_tokens": 2570656}
{"current_steps": 1905, "total_steps": 40000, "loss": 5.2869, "lr": 0.29832596146846024, "epoch": 0.06097560975609756, "percentage": 4.76, "elapsed_time": "1:49:51", "remaining_time": "1 day, 12:36:46", "throughput": 391.01, "total_tokens": 2577248}
{"current_steps": 1910, "total_steps": 40000, "loss": 6.5013, "lr": 0.2983171742031676, "epoch": 0.061135650726586006, "percentage": 4.78, "elapsed_time": "1:49:53", "remaining_time": "1 day, 12:31:24", "throughput": 391.9, "total_tokens": 2583904}
{"current_steps": 1915, "total_steps": 40000, "loss": 6.3664, "lr": 0.2983083640655028, "epoch": 0.06129569169707445, "percentage": 4.79, "elapsed_time": "1:49:55", "remaining_time": "1 day, 12:26:06", "throughput": 392.83, "total_tokens": 2590848}
{"current_steps": 1920, "total_steps": 40000, "loss": 6.2895, "lr": 0.29829953105682455, "epoch": 0.06145573266756289, "percentage": 4.8, "elapsed_time": "1:49:57", "remaining_time": "1 day, 12:20:47", "throughput": 393.7, "total_tokens": 2597392}
{"current_steps": 1925, "total_steps": 40000, "loss": 6.1172, "lr": 0.29829067517849495, "epoch": 0.06161577363805134, "percentage": 4.81, "elapsed_time": "1:49:59", "remaining_time": "1 day, 12:15:29", "throughput": 394.54, "total_tokens": 2603712}
{"current_steps": 1930, "total_steps": 40000, "loss": 5.8947, "lr": 0.2982817964318797, "epoch": 0.061775814608539786, "percentage": 4.83, "elapsed_time": "1:50:01", "remaining_time": "1 day, 12:10:14", "throughput": 395.45, "total_tokens": 2610528}
{"current_steps": 1935, "total_steps": 40000, "loss": 5.9502, "lr": 0.298272894818348, "epoch": 0.06193585557902823, "percentage": 4.84, "elapsed_time": "1:50:03", "remaining_time": "1 day, 12:05:02", "throughput": 396.38, "total_tokens": 2617456}
{"current_steps": 1940, "total_steps": 40000, "loss": 5.9667, "lr": 0.2982639703392726, "epoch": 0.06209589654951667, "percentage": 4.85, "elapsed_time": "1:50:05", "remaining_time": "1 day, 11:59:51", "throughput": 397.3, "total_tokens": 2624384}
{"current_steps": 1945, "total_steps": 40000, "loss": 5.4257, "lr": 0.29825502299602974, "epoch": 0.06225593752000512, "percentage": 4.86, "elapsed_time": "1:50:07", "remaining_time": "1 day, 11:54:41", "throughput": 398.18, "total_tokens": 2630992}
{"current_steps": 1950, "total_steps": 40000, "loss": 5.876, "lr": 0.2982460527899993, "epoch": 0.062415978490493566, "percentage": 4.88, "elapsed_time": "1:50:09", "remaining_time": "1 day, 11:49:33", "throughput": 399.08, "total_tokens": 2637808}
{"current_steps": 1955, "total_steps": 40000, "loss": 6.1468, "lr": 0.29823705972256453, "epoch": 0.06257601946098201, "percentage": 4.89, "elapsed_time": "1:50:11", "remaining_time": "1 day, 11:44:27", "throughput": 400.0, "total_tokens": 2644688}
{"current_steps": 1960, "total_steps": 40000, "loss": 5.6643, "lr": 0.2982280437951123, "epoch": 0.06273606043147045, "percentage": 4.9, "elapsed_time": "1:50:13", "remaining_time": "1 day, 11:39:21", "throughput": 400.88, "total_tokens": 2651328}
{"current_steps": 1965, "total_steps": 40000, "loss": 6.0283, "lr": 0.298219005009033, "epoch": 0.0628961014019589, "percentage": 4.91, "elapsed_time": "1:50:15", "remaining_time": "1 day, 11:34:16", "throughput": 401.73, "total_tokens": 2657760}
{"current_steps": 1970, "total_steps": 40000, "loss": 5.8923, "lr": 0.29820994336572043, "epoch": 0.06305614237244735, "percentage": 4.92, "elapsed_time": "1:50:18", "remaining_time": "1 day, 11:29:20", "throughput": 402.83, "total_tokens": 2666016}
{"current_steps": 1975, "total_steps": 40000, "loss": 5.8406, "lr": 0.2982008588665721, "epoch": 0.06321618334293579, "percentage": 4.94, "elapsed_time": "1:50:20", "remaining_time": "1 day, 11:24:21", "throughput": 403.76, "total_tokens": 2673008}
{"current_steps": 1980, "total_steps": 40000, "loss": 5.6709, "lr": 0.2981917515129889, "epoch": 0.06337622431342424, "percentage": 4.95, "elapsed_time": "1:50:22", "remaining_time": "1 day, 11:19:22", "throughput": 404.66, "total_tokens": 2679808}
{"current_steps": 1985, "total_steps": 40000, "loss": 5.7233, "lr": 0.2981826213063753, "epoch": 0.06353626528391268, "percentage": 4.96, "elapsed_time": "1:50:24", "remaining_time": "1 day, 11:14:24", "throughput": 405.57, "total_tokens": 2686640}
{"current_steps": 1990, "total_steps": 40000, "loss": 5.7815, "lr": 0.2981734682481394, "epoch": 0.06369630625440113, "percentage": 4.98, "elapsed_time": "1:50:26", "remaining_time": "1 day, 11:09:28", "throughput": 406.51, "total_tokens": 2693696}
{"current_steps": 1995, "total_steps": 40000, "loss": 5.2976, "lr": 0.29816429233969255, "epoch": 0.06385634722488957, "percentage": 4.99, "elapsed_time": "1:50:28", "remaining_time": "1 day, 11:04:32", "throughput": 407.37, "total_tokens": 2700240}
{"current_steps": 2000, "total_steps": 40000, "loss": 6.2159, "lr": 0.2981550935824499, "epoch": 0.06401638819537801, "percentage": 5.0, "elapsed_time": "1:50:30", "remaining_time": "1 day, 10:59:39", "throughput": 408.26, "total_tokens": 2706960}
{"current_steps": 2000, "total_steps": 40000, "eval_loss": 5.724799156188965, "epoch": 0.06401638819537801, "percentage": 5.0, "elapsed_time": "2:01:14", "remaining_time": "1 day, 14:23:43", "throughput": 372.1, "total_tokens": 2706960}
{"current_steps": 2005, "total_steps": 40000, "loss": 5.4959, "lr": 0.29814587197783, "epoch": 0.06417642916586647, "percentage": 5.01, "elapsed_time": "2:01:18", "remaining_time": "1 day, 14:18:39", "throughput": 372.9, "total_tokens": 2714000}
{"current_steps": 2010, "total_steps": 40000, "loss": 5.7697, "lr": 0.29813662752725495, "epoch": 0.0643364701363549, "percentage": 5.03, "elapsed_time": "2:01:20", "remaining_time": "1 day, 14:13:17", "throughput": 373.73, "total_tokens": 2720784}
{"current_steps": 2015, "total_steps": 40000, "loss": 5.2562, "lr": 0.29812736023215025, "epoch": 0.06449651110684335, "percentage": 5.04, "elapsed_time": "2:01:22", "remaining_time": "1 day, 14:07:55", "throughput": 374.5, "total_tokens": 2727136}
{"current_steps": 2020, "total_steps": 40000, "loss": 5.8312, "lr": 0.29811807009394514, "epoch": 0.0646565520773318, "percentage": 5.05, "elapsed_time": "2:01:24", "remaining_time": "1 day, 14:02:36", "throughput": 375.31, "total_tokens": 2733776}
{"current_steps": 2025, "total_steps": 40000, "loss": 6.3852, "lr": 0.2981087571140723, "epoch": 0.06481659304782024, "percentage": 5.06, "elapsed_time": "2:01:26", "remaining_time": "1 day, 13:57:18", "throughput": 376.12, "total_tokens": 2740512}
{"current_steps": 2030, "total_steps": 40000, "loss": 6.0788, "lr": 0.2980994212939678, "epoch": 0.0649766340183087, "percentage": 5.08, "elapsed_time": "2:01:28", "remaining_time": "1 day, 13:52:01", "throughput": 376.94, "total_tokens": 2747200}
{"current_steps": 2035, "total_steps": 40000, "loss": 6.4222, "lr": 0.2980900626350715, "epoch": 0.06513667498879713, "percentage": 5.09, "elapsed_time": "2:01:30", "remaining_time": "1 day, 13:46:46", "throughput": 377.74, "total_tokens": 2753824}
{"current_steps": 2040, "total_steps": 40000, "loss": 5.7658, "lr": 0.29808068113882646, "epoch": 0.06529671595928557, "percentage": 5.1, "elapsed_time": "2:01:32", "remaining_time": "1 day, 13:41:32", "throughput": 378.54, "total_tokens": 2760384}
{"current_steps": 2045, "total_steps": 40000, "loss": 6.4238, "lr": 0.2980712768066795, "epoch": 0.06545675692977403, "percentage": 5.11, "elapsed_time": "2:01:34", "remaining_time": "1 day, 13:36:22", "throughput": 379.38, "total_tokens": 2767312}
{"current_steps": 2050, "total_steps": 40000, "loss": 5.687, "lr": 0.2980618496400809, "epoch": 0.06561679790026247, "percentage": 5.12, "elapsed_time": "2:01:36", "remaining_time": "1 day, 13:31:13", "throughput": 380.26, "total_tokens": 2774544}
{"current_steps": 2055, "total_steps": 40000, "loss": 6.1899, "lr": 0.2980523996404844, "epoch": 0.0657768388707509, "percentage": 5.14, "elapsed_time": "2:01:38", "remaining_time": "1 day, 13:26:05", "throughput": 381.07, "total_tokens": 2781280}
{"current_steps": 2060, "total_steps": 40000, "loss": 5.8268, "lr": 0.2980429268093473, "epoch": 0.06593687984123936, "percentage": 5.15, "elapsed_time": "2:01:40", "remaining_time": "1 day, 13:20:59", "throughput": 381.94, "total_tokens": 2788416}
{"current_steps": 2065, "total_steps": 40000, "loss": 5.1528, "lr": 0.29803343114813047, "epoch": 0.0660969208117278, "percentage": 5.16, "elapsed_time": "2:01:42", "remaining_time": "1 day, 13:15:52", "throughput": 382.71, "total_tokens": 2794752}
{"current_steps": 2070, "total_steps": 40000, "loss": 5.6115, "lr": 0.2980239126582983, "epoch": 0.06625696178221625, "percentage": 5.17, "elapsed_time": "2:01:44", "remaining_time": "1 day, 13:10:47", "throughput": 383.5, "total_tokens": 2801328}
{"current_steps": 2075, "total_steps": 40000, "loss": 6.1348, "lr": 0.2980143713413186, "epoch": 0.06641700275270469, "percentage": 5.19, "elapsed_time": "2:01:46", "remaining_time": "1 day, 13:05:45", "throughput": 384.33, "total_tokens": 2808224}
{"current_steps": 2080, "total_steps": 40000, "loss": 6.1211, "lr": 0.29800480719866274, "epoch": 0.06657704372319313, "percentage": 5.2, "elapsed_time": "2:01:48", "remaining_time": "1 day, 13:00:45", "throughput": 385.18, "total_tokens": 2815184}
{"current_steps": 2085, "total_steps": 40000, "loss": 6.0302, "lr": 0.2979952202318057, "epoch": 0.06673708469368159, "percentage": 5.21, "elapsed_time": "2:01:50", "remaining_time": "1 day, 12:55:46", "throughput": 386.0, "total_tokens": 2822032}
{"current_steps": 2090, "total_steps": 40000, "loss": 6.0009, "lr": 0.2979856104422259, "epoch": 0.06689712566417003, "percentage": 5.22, "elapsed_time": "2:01:53", "remaining_time": "1 day, 12:50:49", "throughput": 386.88, "total_tokens": 2829248}
{"current_steps": 2095, "total_steps": 40000, "loss": 5.6267, "lr": 0.2979759778314052, "epoch": 0.06705716663465847, "percentage": 5.24, "elapsed_time": "2:01:54", "remaining_time": "1 day, 12:45:49", "throughput": 387.64, "total_tokens": 2835568}
{"current_steps": 2100, "total_steps": 40000, "loss": 5.3375, "lr": 0.2979663224008292, "epoch": 0.06721720760514692, "percentage": 5.25, "elapsed_time": "2:01:56", "remaining_time": "1 day, 12:40:54", "throughput": 388.44, "total_tokens": 2842224}
{"current_steps": 2105, "total_steps": 40000, "loss": 6.0105, "lr": 0.2979566441519868, "epoch": 0.06737724857563536, "percentage": 5.26, "elapsed_time": "2:01:59", "remaining_time": "1 day, 12:35:59", "throughput": 389.24, "total_tokens": 2848880}
{"current_steps": 2110, "total_steps": 40000, "loss": 5.6196, "lr": 0.29794694308637054, "epoch": 0.06753728954612381, "percentage": 5.27, "elapsed_time": "2:02:01", "remaining_time": "1 day, 12:31:06", "throughput": 390.06, "total_tokens": 2855664}
{"current_steps": 2115, "total_steps": 40000, "loss": 5.5918, "lr": 0.2979372192054764, "epoch": 0.06769733051661225, "percentage": 5.29, "elapsed_time": "2:02:03", "remaining_time": "1 day, 12:26:16", "throughput": 390.91, "total_tokens": 2862720}
{"current_steps": 2120, "total_steps": 40000, "loss": 5.8644, "lr": 0.297927472510804, "epoch": 0.06785737148710069, "percentage": 5.3, "elapsed_time": "2:02:05", "remaining_time": "1 day, 12:21:26", "throughput": 391.71, "total_tokens": 2869376}
{"current_steps": 2125, "total_steps": 40000, "loss": 5.7049, "lr": 0.29791770300385634, "epoch": 0.06801741245758915, "percentage": 5.31, "elapsed_time": "2:02:07", "remaining_time": "1 day, 12:16:38", "throughput": 392.54, "total_tokens": 2876272}
{"current_steps": 2130, "total_steps": 40000, "loss": 5.7544, "lr": 0.29790791068614003, "epoch": 0.06817745342807759, "percentage": 5.33, "elapsed_time": "2:02:09", "remaining_time": "1 day, 12:11:51", "throughput": 393.33, "total_tokens": 2882848}
{"current_steps": 2135, "total_steps": 40000, "loss": 5.6885, "lr": 0.2978980955591652, "epoch": 0.06833749439856603, "percentage": 5.34, "elapsed_time": "2:02:11", "remaining_time": "1 day, 12:07:05", "throughput": 394.17, "total_tokens": 2889856}
{"current_steps": 2140, "total_steps": 40000, "loss": 6.1739, "lr": 0.2978882576244454, "epoch": 0.06849753536905448, "percentage": 5.35, "elapsed_time": "2:02:13", "remaining_time": "1 day, 12:02:20", "throughput": 395.01, "total_tokens": 2896768}
{"current_steps": 2145, "total_steps": 40000, "loss": 5.6601, "lr": 0.2978783968834978, "epoch": 0.06865757633954292, "percentage": 5.36, "elapsed_time": "2:02:15", "remaining_time": "1 day, 11:57:37", "throughput": 395.79, "total_tokens": 2903344}
{"current_steps": 2150, "total_steps": 40000, "loss": 5.696, "lr": 0.29786851333784303, "epoch": 0.06881761731003137, "percentage": 5.38, "elapsed_time": "2:02:17", "remaining_time": "1 day, 11:52:55", "throughput": 396.6, "total_tokens": 2910080}
{"current_steps": 2155, "total_steps": 40000, "loss": 5.2635, "lr": 0.2978586069890053, "epoch": 0.06897765828051981, "percentage": 5.39, "elapsed_time": "2:02:19", "remaining_time": "1 day, 11:48:14", "throughput": 397.39, "total_tokens": 2916688}
{"current_steps": 2160, "total_steps": 40000, "loss": 6.3386, "lr": 0.29784867783851227, "epoch": 0.06913769925100825, "percentage": 5.4, "elapsed_time": "2:02:21", "remaining_time": "1 day, 11:43:34", "throughput": 398.16, "total_tokens": 2923168}
{"current_steps": 2165, "total_steps": 40000, "loss": 5.9454, "lr": 0.2978387258878951, "epoch": 0.0692977402214967, "percentage": 5.41, "elapsed_time": "2:02:23", "remaining_time": "1 day, 11:38:56", "throughput": 398.99, "total_tokens": 2930032}
{"current_steps": 2170, "total_steps": 40000, "loss": 5.267, "lr": 0.29782875113868856, "epoch": 0.06945778119198515, "percentage": 5.42, "elapsed_time": "2:02:25", "remaining_time": "1 day, 11:34:19", "throughput": 399.78, "total_tokens": 2936640}
{"current_steps": 2175, "total_steps": 40000, "loss": 5.6725, "lr": 0.2978187535924309, "epoch": 0.0696178221624736, "percentage": 5.44, "elapsed_time": "2:02:27", "remaining_time": "1 day, 11:29:44", "throughput": 400.6, "total_tokens": 2943536}
{"current_steps": 2180, "total_steps": 40000, "loss": 5.9411, "lr": 0.29780873325066376, "epoch": 0.06977786313296204, "percentage": 5.45, "elapsed_time": "2:02:29", "remaining_time": "1 day, 11:25:09", "throughput": 401.37, "total_tokens": 2950016}
{"current_steps": 2185, "total_steps": 40000, "loss": 5.9377, "lr": 0.2977986901149325, "epoch": 0.06993790410345048, "percentage": 5.46, "elapsed_time": "2:02:31", "remaining_time": "1 day, 11:20:35", "throughput": 402.15, "total_tokens": 2956528}
{"current_steps": 2190, "total_steps": 40000, "loss": 5.5794, "lr": 0.29778862418678587, "epoch": 0.07009794507393893, "percentage": 5.47, "elapsed_time": "2:02:33", "remaining_time": "1 day, 11:16:01", "throughput": 402.9, "total_tokens": 2962848}
{"current_steps": 2195, "total_steps": 40000, "loss": 6.2336, "lr": 0.29777853546777616, "epoch": 0.07025798604442737, "percentage": 5.49, "elapsed_time": "2:02:35", "remaining_time": "1 day, 11:11:30", "throughput": 403.66, "total_tokens": 2969248}
{"current_steps": 2200, "total_steps": 40000, "loss": 5.382, "lr": 0.2977684239594592, "epoch": 0.07041802701491581, "percentage": 5.5, "elapsed_time": "2:02:37", "remaining_time": "1 day, 11:07:01", "throughput": 404.48, "total_tokens": 2976144}
{"current_steps": 2200, "total_steps": 40000, "eval_loss": 5.690195083618164, "epoch": 0.07041802701491581, "percentage": 5.5, "elapsed_time": "2:13:22", "remaining_time": "1 day, 14:11:34", "throughput": 371.91, "total_tokens": 2976144}
{"current_steps": 2205, "total_steps": 40000, "loss": 6.4809, "lr": 0.29775828966339424, "epoch": 0.07057806798540427, "percentage": 5.51, "elapsed_time": "2:13:25", "remaining_time": "1 day, 14:06:58", "throughput": 372.62, "total_tokens": 2982992}
{"current_steps": 2210, "total_steps": 40000, "loss": 6.4765, "lr": 0.29774813258114424, "epoch": 0.0707381089558927, "percentage": 5.53, "elapsed_time": "2:13:27", "remaining_time": "1 day, 14:02:04", "throughput": 373.35, "total_tokens": 2989568}
{"current_steps": 2215, "total_steps": 40000, "loss": 5.9031, "lr": 0.29773795271427544, "epoch": 0.07089814992638116, "percentage": 5.54, "elapsed_time": "2:13:29", "remaining_time": "1 day, 13:57:12", "throughput": 374.1, "total_tokens": 2996336}
{"current_steps": 2220, "total_steps": 40000, "loss": 5.5033, "lr": 0.2977277500643577, "epoch": 0.0710581908968696, "percentage": 5.55, "elapsed_time": "2:13:31", "remaining_time": "1 day, 13:52:21", "throughput": 374.86, "total_tokens": 3003232}
{"current_steps": 2225, "total_steps": 40000, "loss": 6.4344, "lr": 0.29771752463296447, "epoch": 0.07121823186735804, "percentage": 5.56, "elapsed_time": "2:13:33", "remaining_time": "1 day, 13:47:33", "throughput": 375.62, "total_tokens": 3010144}
{"current_steps": 2230, "total_steps": 40000, "loss": 5.5129, "lr": 0.29770727642167266, "epoch": 0.0713782728378465, "percentage": 5.58, "elapsed_time": "2:13:35", "remaining_time": "1 day, 13:42:45", "throughput": 376.41, "total_tokens": 3017264}
{"current_steps": 2235, "total_steps": 40000, "loss": 5.4468, "lr": 0.29769700543206257, "epoch": 0.07153831380833493, "percentage": 5.59, "elapsed_time": "2:13:37", "remaining_time": "1 day, 13:37:58", "throughput": 377.15, "total_tokens": 3023968}
{"current_steps": 2240, "total_steps": 40000, "loss": 6.1032, "lr": 0.2976867116657182, "epoch": 0.07169835477882337, "percentage": 5.6, "elapsed_time": "2:13:39", "remaining_time": "1 day, 13:33:12", "throughput": 377.87, "total_tokens": 3030480}
{"current_steps": 2245, "total_steps": 40000, "loss": 6.6463, "lr": 0.2976763951242269, "epoch": 0.07185839574931183, "percentage": 5.61, "elapsed_time": "2:13:42", "remaining_time": "1 day, 13:28:29", "throughput": 378.65, "total_tokens": 3037520}
{"current_steps": 2250, "total_steps": 40000, "loss": 5.7327, "lr": 0.29766605580917965, "epoch": 0.07201843671980027, "percentage": 5.62, "elapsed_time": "2:13:43", "remaining_time": "1 day, 13:23:44", "throughput": 379.34, "total_tokens": 3043808}
{"current_steps": 2255, "total_steps": 40000, "loss": 5.8616, "lr": 0.29765569372217093, "epoch": 0.07217847769028872, "percentage": 5.64, "elapsed_time": "2:13:45", "remaining_time": "1 day, 13:19:01", "throughput": 380.08, "total_tokens": 3050544}
{"current_steps": 2260, "total_steps": 40000, "loss": 6.2037, "lr": 0.2976453088647987, "epoch": 0.07233851866077716, "percentage": 5.65, "elapsed_time": "2:13:48", "remaining_time": "1 day, 13:14:21", "throughput": 380.84, "total_tokens": 3057408}
{"current_steps": 2265, "total_steps": 40000, "loss": 6.6201, "lr": 0.2976349012386644, "epoch": 0.0724985596312656, "percentage": 5.66, "elapsed_time": "2:13:50", "remaining_time": "1 day, 13:09:40", "throughput": 381.54, "total_tokens": 3063792}
{"current_steps": 2270, "total_steps": 40000, "loss": 5.3298, "lr": 0.29762447084537297, "epoch": 0.07265860060175405, "percentage": 5.67, "elapsed_time": "2:13:52", "remaining_time": "1 day, 13:05:03", "throughput": 382.3, "total_tokens": 3070672}
{"current_steps": 2275, "total_steps": 40000, "loss": 5.4273, "lr": 0.29761401768653306, "epoch": 0.07281864157224249, "percentage": 5.69, "elapsed_time": "2:13:54", "remaining_time": "1 day, 13:00:24", "throughput": 383.02, "total_tokens": 3077200}
{"current_steps": 2280, "total_steps": 40000, "loss": 5.4821, "lr": 0.29760354176375653, "epoch": 0.07297868254273093, "percentage": 5.7, "elapsed_time": "2:13:56", "remaining_time": "1 day, 12:55:50", "throughput": 383.86, "total_tokens": 3084784}
{"current_steps": 2285, "total_steps": 40000, "loss": 6.0694, "lr": 0.29759304307865897, "epoch": 0.07313872351321939, "percentage": 5.71, "elapsed_time": "2:13:58", "remaining_time": "1 day, 12:51:15", "throughput": 384.62, "total_tokens": 3091712}
{"current_steps": 2290, "total_steps": 40000, "loss": 5.5123, "lr": 0.2975825216328594, "epoch": 0.07329876448370783, "percentage": 5.73, "elapsed_time": "2:14:00", "remaining_time": "1 day, 12:46:42", "throughput": 385.37, "total_tokens": 3098512}
{"current_steps": 2295, "total_steps": 40000, "loss": 5.416, "lr": 0.2975719774279804, "epoch": 0.07345880545419628, "percentage": 5.74, "elapsed_time": "2:14:02", "remaining_time": "1 day, 12:42:11", "throughput": 386.16, "total_tokens": 3105648}
{"current_steps": 2300, "total_steps": 40000, "loss": 5.3865, "lr": 0.29756141046564794, "epoch": 0.07361884642468472, "percentage": 5.75, "elapsed_time": "2:14:04", "remaining_time": "1 day, 12:37:40", "throughput": 386.92, "total_tokens": 3112608}
{"current_steps": 2305, "total_steps": 40000, "loss": 5.2424, "lr": 0.2975508207474916, "epoch": 0.07377888739517316, "percentage": 5.76, "elapsed_time": "2:14:06", "remaining_time": "1 day, 12:33:09", "throughput": 387.63, "total_tokens": 3119088}
{"current_steps": 2310, "total_steps": 40000, "loss": 5.4992, "lr": 0.2975402082751445, "epoch": 0.07393892836566161, "percentage": 5.78, "elapsed_time": "2:14:08", "remaining_time": "1 day, 12:28:42", "throughput": 388.43, "total_tokens": 3126336}
{"current_steps": 2315, "total_steps": 40000, "loss": 5.8193, "lr": 0.29752957305024313, "epoch": 0.07409896933615005, "percentage": 5.79, "elapsed_time": "2:14:10", "remaining_time": "1 day, 12:24:15", "throughput": 389.18, "total_tokens": 3133200}
{"current_steps": 2320, "total_steps": 40000, "loss": 6.1511, "lr": 0.2975189150744277, "epoch": 0.07425901030663849, "percentage": 5.8, "elapsed_time": "2:14:12", "remaining_time": "1 day, 12:19:49", "throughput": 389.94, "total_tokens": 3140096}
{"current_steps": 2325, "total_steps": 40000, "loss": 5.5468, "lr": 0.29750823434934165, "epoch": 0.07441905127712695, "percentage": 5.81, "elapsed_time": "2:14:14", "remaining_time": "1 day, 12:15:24", "throughput": 390.68, "total_tokens": 3146880}
{"current_steps": 2330, "total_steps": 40000, "loss": 6.124, "lr": 0.29749753087663217, "epoch": 0.07457909224761539, "percentage": 5.83, "elapsed_time": "2:14:16", "remaining_time": "1 day, 12:11:00", "throughput": 391.44, "total_tokens": 3153808}
{"current_steps": 2335, "total_steps": 40000, "loss": 6.2702, "lr": 0.29748680465794985, "epoch": 0.07473913321810384, "percentage": 5.84, "elapsed_time": "2:14:18", "remaining_time": "1 day, 12:06:36", "throughput": 392.14, "total_tokens": 3160288}
{"current_steps": 2340, "total_steps": 40000, "loss": 5.5116, "lr": 0.29747605569494884, "epoch": 0.07489917418859228, "percentage": 5.85, "elapsed_time": "2:14:20", "remaining_time": "1 day, 12:02:13", "throughput": 392.83, "total_tokens": 3166624}
{"current_steps": 2345, "total_steps": 40000, "loss": 6.406, "lr": 0.29746528398928673, "epoch": 0.07505921515908072, "percentage": 5.86, "elapsed_time": "2:14:23", "remaining_time": "1 day, 11:57:52", "throughput": 393.55, "total_tokens": 3173232}
{"current_steps": 2350, "total_steps": 40000, "loss": 6.1292, "lr": 0.2974544895426247, "epoch": 0.07521925612956917, "percentage": 5.88, "elapsed_time": "2:14:25", "remaining_time": "1 day, 11:53:32", "throughput": 394.29, "total_tokens": 3180000}
{"current_steps": 2355, "total_steps": 40000, "loss": 5.5655, "lr": 0.29744367235662733, "epoch": 0.07537929710005761, "percentage": 5.89, "elapsed_time": "2:14:27", "remaining_time": "1 day, 11:49:14", "throughput": 395.0, "total_tokens": 3186544}
{"current_steps": 2360, "total_steps": 40000, "loss": 5.9452, "lr": 0.29743283243296276, "epoch": 0.07553933807054607, "percentage": 5.9, "elapsed_time": "2:14:29", "remaining_time": "1 day, 11:44:56", "throughput": 395.75, "total_tokens": 3193376}
{"current_steps": 2365, "total_steps": 40000, "loss": 6.1654, "lr": 0.29742196977330276, "epoch": 0.0756993790410345, "percentage": 5.91, "elapsed_time": "2:14:31", "remaining_time": "1 day, 11:40:40", "throughput": 396.47, "total_tokens": 3200000}
{"current_steps": 2370, "total_steps": 40000, "loss": 5.4603, "lr": 0.2974110843793223, "epoch": 0.07585942001152295, "percentage": 5.92, "elapsed_time": "2:14:33", "remaining_time": "1 day, 11:36:24", "throughput": 397.2, "total_tokens": 3206720}
{"current_steps": 2375, "total_steps": 40000, "loss": 6.1316, "lr": 0.2974001762527002, "epoch": 0.0760194609820114, "percentage": 5.94, "elapsed_time": "2:14:35", "remaining_time": "1 day, 11:32:10", "throughput": 397.91, "total_tokens": 3213248}
{"current_steps": 2380, "total_steps": 40000, "loss": 6.2149, "lr": 0.2973892453951186, "epoch": 0.07617950195249984, "percentage": 5.95, "elapsed_time": "2:14:37", "remaining_time": "1 day, 11:27:59", "throughput": 398.72, "total_tokens": 3220704}
{"current_steps": 2385, "total_steps": 40000, "loss": 6.3855, "lr": 0.2973782918082631, "epoch": 0.07633954292298828, "percentage": 5.96, "elapsed_time": "2:14:39", "remaining_time": "1 day, 11:23:48", "throughput": 399.53, "total_tokens": 3228048}
{"current_steps": 2390, "total_steps": 40000, "loss": 6.1413, "lr": 0.29736731549382295, "epoch": 0.07649958389347673, "percentage": 5.97, "elapsed_time": "2:14:41", "remaining_time": "1 day, 11:19:37", "throughput": 400.26, "total_tokens": 3234832}
{"current_steps": 2395, "total_steps": 40000, "loss": 6.3851, "lr": 0.2973563164534908, "epoch": 0.07665962486396517, "percentage": 5.99, "elapsed_time": "2:14:43", "remaining_time": "1 day, 11:15:28", "throughput": 401.04, "total_tokens": 3241952}
{"current_steps": 2400, "total_steps": 40000, "loss": 6.3383, "lr": 0.29734529468896287, "epoch": 0.07681966583445363, "percentage": 6.0, "elapsed_time": "2:14:45", "remaining_time": "1 day, 11:11:18", "throughput": 401.74, "total_tokens": 3248384}
{"current_steps": 2400, "total_steps": 40000, "eval_loss": 5.696970462799072, "epoch": 0.07681966583445363, "percentage": 6.0, "elapsed_time": "2:25:29", "remaining_time": "1 day, 13:59:25", "throughput": 372.11, "total_tokens": 3248384}
{"current_steps": 2405, "total_steps": 40000, "loss": 5.7425, "lr": 0.2973342502019388, "epoch": 0.07697970680494207, "percentage": 6.01, "elapsed_time": "2:25:32", "remaining_time": "1 day, 13:55:09", "throughput": 372.71, "total_tokens": 3254784}
{"current_steps": 2410, "total_steps": 40000, "loss": 5.7637, "lr": 0.2973231829941219, "epoch": 0.0771397477754305, "percentage": 6.02, "elapsed_time": "2:25:34", "remaining_time": "1 day, 13:50:40", "throughput": 373.39, "total_tokens": 3261504}
{"current_steps": 2415, "total_steps": 40000, "loss": 5.8767, "lr": 0.2973120930672188, "epoch": 0.07729978874591896, "percentage": 6.04, "elapsed_time": "2:25:36", "remaining_time": "1 day, 13:46:12", "throughput": 374.07, "total_tokens": 3268160}
{"current_steps": 2420, "total_steps": 40000, "loss": 5.9183, "lr": 0.2973009804229397, "epoch": 0.0774598297164074, "percentage": 6.05, "elapsed_time": "2:25:38", "remaining_time": "1 day, 13:41:45", "throughput": 374.78, "total_tokens": 3275184}
{"current_steps": 2425, "total_steps": 40000, "loss": 6.5237, "lr": 0.29728984506299827, "epoch": 0.07761987068689584, "percentage": 6.06, "elapsed_time": "2:25:40", "remaining_time": "1 day, 13:37:20", "throughput": 375.48, "total_tokens": 3282064}
{"current_steps": 2430, "total_steps": 40000, "loss": 5.6449, "lr": 0.2972786869891118, "epoch": 0.07777991165738429, "percentage": 6.08, "elapsed_time": "2:25:43", "remaining_time": "1 day, 13:32:55", "throughput": 376.15, "total_tokens": 3288704}
{"current_steps": 2435, "total_steps": 40000, "loss": 6.1052, "lr": 0.29726750620300096, "epoch": 0.07793995262787273, "percentage": 6.09, "elapsed_time": "2:25:45", "remaining_time": "1 day, 13:28:32", "throughput": 376.89, "total_tokens": 3295984}
{"current_steps": 2440, "total_steps": 40000, "loss": 5.5089, "lr": 0.29725630270639003, "epoch": 0.07809999359836119, "percentage": 6.1, "elapsed_time": "2:25:47", "remaining_time": "1 day, 13:24:09", "throughput": 377.56, "total_tokens": 3302592}
{"current_steps": 2445, "total_steps": 40000, "loss": 5.4937, "lr": 0.2972450765010067, "epoch": 0.07826003456884963, "percentage": 6.11, "elapsed_time": "2:25:49", "remaining_time": "1 day, 13:19:48", "throughput": 378.25, "total_tokens": 3309424}
{"current_steps": 2450, "total_steps": 40000, "loss": 5.4997, "lr": 0.29723382758858213, "epoch": 0.07842007553933807, "percentage": 6.12, "elapsed_time": "2:25:51", "remaining_time": "1 day, 13:15:25", "throughput": 378.89, "total_tokens": 3315728}
{"current_steps": 2455, "total_steps": 40000, "loss": 5.898, "lr": 0.29722255597085107, "epoch": 0.07858011650982652, "percentage": 6.14, "elapsed_time": "2:25:53", "remaining_time": "1 day, 13:11:06", "throughput": 379.57, "total_tokens": 3322448}
{"current_steps": 2460, "total_steps": 40000, "loss": 5.4308, "lr": 0.2972112616495518, "epoch": 0.07874015748031496, "percentage": 6.15, "elapsed_time": "2:25:55", "remaining_time": "1 day, 13:06:48", "throughput": 380.28, "total_tokens": 3329456}
{"current_steps": 2465, "total_steps": 40000, "loss": 5.978, "lr": 0.297199944626426, "epoch": 0.0789001984508034, "percentage": 6.16, "elapsed_time": "2:25:57", "remaining_time": "1 day, 13:02:30", "throughput": 380.98, "total_tokens": 3336368}
{"current_steps": 2470, "total_steps": 40000, "loss": 5.4907, "lr": 0.2971886049032189, "epoch": 0.07906023942129185, "percentage": 6.17, "elapsed_time": "2:25:59", "remaining_time": "1 day, 12:58:14", "throughput": 381.67, "total_tokens": 3343280}
{"current_steps": 2475, "total_steps": 40000, "loss": 6.3919, "lr": 0.29717724248167926, "epoch": 0.07922028039178029, "percentage": 6.19, "elapsed_time": "2:26:01", "remaining_time": "1 day, 12:53:59", "throughput": 382.37, "total_tokens": 3350112}
{"current_steps": 2480, "total_steps": 40000, "loss": 5.7264, "lr": 0.29716585736355927, "epoch": 0.07938032136226875, "percentage": 6.2, "elapsed_time": "2:26:03", "remaining_time": "1 day, 12:49:44", "throughput": 383.01, "total_tokens": 3356528}
{"current_steps": 2485, "total_steps": 40000, "loss": 5.1019, "lr": 0.2971544495506147, "epoch": 0.07954036233275719, "percentage": 6.21, "elapsed_time": "2:26:05", "remaining_time": "1 day, 12:45:29", "throughput": 383.66, "total_tokens": 3363024}
{"current_steps": 2490, "total_steps": 40000, "loss": 5.8342, "lr": 0.2971430190446048, "epoch": 0.07970040330324563, "percentage": 6.22, "elapsed_time": "2:26:07", "remaining_time": "1 day, 12:41:17", "throughput": 384.37, "total_tokens": 3370016}
{"current_steps": 2495, "total_steps": 40000, "loss": 5.5735, "lr": 0.2971315658472921, "epoch": 0.07986044427373408, "percentage": 6.24, "elapsed_time": "2:26:09", "remaining_time": "1 day, 12:37:07", "throughput": 385.09, "total_tokens": 3377120}
{"current_steps": 2500, "total_steps": 40000, "loss": 5.9188, "lr": 0.2971200899604431, "epoch": 0.08002048524422252, "percentage": 6.25, "elapsed_time": "2:26:11", "remaining_time": "1 day, 12:32:56", "throughput": 385.75, "total_tokens": 3383760}
{"current_steps": 2505, "total_steps": 40000, "loss": 6.0949, "lr": 0.29710859138582735, "epoch": 0.08018052621471096, "percentage": 6.26, "elapsed_time": "2:26:13", "remaining_time": "1 day, 12:28:46", "throughput": 386.42, "total_tokens": 3390400}
{"current_steps": 2510, "total_steps": 40000, "loss": 5.7635, "lr": 0.29709707012521813, "epoch": 0.08034056718519941, "percentage": 6.28, "elapsed_time": "2:26:15", "remaining_time": "1 day, 12:24:38", "throughput": 387.1, "total_tokens": 3397168}
{"current_steps": 2515, "total_steps": 40000, "loss": 7.0196, "lr": 0.29708552618039213, "epoch": 0.08050060815568785, "percentage": 6.29, "elapsed_time": "2:26:17", "remaining_time": "1 day, 12:20:30", "throughput": 387.77, "total_tokens": 3403824}
{"current_steps": 2520, "total_steps": 40000, "loss": 5.7339, "lr": 0.2970739595531296, "epoch": 0.0806606491261763, "percentage": 6.3, "elapsed_time": "2:26:19", "remaining_time": "1 day, 12:16:22", "throughput": 388.42, "total_tokens": 3410288}
{"current_steps": 2525, "total_steps": 40000, "loss": 5.3516, "lr": 0.2970623702452143, "epoch": 0.08082069009666475, "percentage": 6.31, "elapsed_time": "2:26:21", "remaining_time": "1 day, 12:12:17", "throughput": 389.08, "total_tokens": 3416864}
{"current_steps": 2530, "total_steps": 40000, "loss": 5.3941, "lr": 0.2970507582584334, "epoch": 0.08098073106715319, "percentage": 6.33, "elapsed_time": "2:26:23", "remaining_time": "1 day, 12:08:12", "throughput": 389.75, "total_tokens": 3423568}
{"current_steps": 2535, "total_steps": 40000, "loss": 6.2043, "lr": 0.2970391235945776, "epoch": 0.08114077203764164, "percentage": 6.34, "elapsed_time": "2:26:26", "remaining_time": "1 day, 12:04:11", "throughput": 390.51, "total_tokens": 3431104}
{"current_steps": 2540, "total_steps": 40000, "loss": 5.9449, "lr": 0.2970274662554412, "epoch": 0.08130081300813008, "percentage": 6.35, "elapsed_time": "2:26:28", "remaining_time": "1 day, 12:00:07", "throughput": 391.17, "total_tokens": 3437680}
{"current_steps": 2545, "total_steps": 40000, "loss": 5.3874, "lr": 0.2970157862428218, "epoch": 0.08146085397861853, "percentage": 6.36, "elapsed_time": "2:26:30", "remaining_time": "1 day, 11:56:05", "throughput": 391.82, "total_tokens": 3444208}
{"current_steps": 2550, "total_steps": 40000, "loss": 5.8154, "lr": 0.2970040835585206, "epoch": 0.08162089494910697, "percentage": 6.38, "elapsed_time": "2:26:32", "remaining_time": "1 day, 11:52:05", "throughput": 392.49, "total_tokens": 3450864}
{"current_steps": 2555, "total_steps": 40000, "loss": 6.1497, "lr": 0.2969923582043424, "epoch": 0.08178093591959541, "percentage": 6.39, "elapsed_time": "2:26:34", "remaining_time": "1 day, 11:48:04", "throughput": 393.13, "total_tokens": 3457312}
{"current_steps": 2560, "total_steps": 40000, "loss": 6.0381, "lr": 0.2969806101820953, "epoch": 0.08194097689008387, "percentage": 6.4, "elapsed_time": "2:26:36", "remaining_time": "1 day, 11:44:06", "throughput": 393.83, "total_tokens": 3464272}
{"current_steps": 2565, "total_steps": 40000, "loss": 5.8238, "lr": 0.2969688394935911, "epoch": 0.0821010178605723, "percentage": 6.41, "elapsed_time": "2:26:38", "remaining_time": "1 day, 11:40:07", "throughput": 394.48, "total_tokens": 3470720}
{"current_steps": 2570, "total_steps": 40000, "loss": 5.5374, "lr": 0.2969570461406449, "epoch": 0.08226105883106075, "percentage": 6.42, "elapsed_time": "2:26:40", "remaining_time": "1 day, 11:36:11", "throughput": 395.18, "total_tokens": 3477744}
{"current_steps": 2575, "total_steps": 40000, "loss": 5.8425, "lr": 0.29694523012507534, "epoch": 0.0824210998015492, "percentage": 6.44, "elapsed_time": "2:26:42", "remaining_time": "1 day, 11:32:15", "throughput": 395.87, "total_tokens": 3484688}
{"current_steps": 2580, "total_steps": 40000, "loss": 4.918, "lr": 0.2969333914487048, "epoch": 0.08258114077203764, "percentage": 6.45, "elapsed_time": "2:26:44", "remaining_time": "1 day, 11:28:22", "throughput": 396.62, "total_tokens": 3492096}
{"current_steps": 2585, "total_steps": 40000, "loss": 5.5627, "lr": 0.2969215301133587, "epoch": 0.0827411817425261, "percentage": 6.46, "elapsed_time": "2:26:46", "remaining_time": "1 day, 11:24:27", "throughput": 397.28, "total_tokens": 3498784}
{"current_steps": 2590, "total_steps": 40000, "loss": 5.588, "lr": 0.29690964612086634, "epoch": 0.08290122271301453, "percentage": 6.48, "elapsed_time": "2:26:48", "remaining_time": "1 day, 11:20:35", "throughput": 397.97, "total_tokens": 3505648}
{"current_steps": 2595, "total_steps": 40000, "loss": 4.872, "lr": 0.2968977394730604, "epoch": 0.08306126368350297, "percentage": 6.49, "elapsed_time": "2:26:50", "remaining_time": "1 day, 11:16:41", "throughput": 398.63, "total_tokens": 3512272}
{"current_steps": 2600, "total_steps": 40000, "loss": 6.3703, "lr": 0.296885810171777, "epoch": 0.08322130465399143, "percentage": 6.5, "elapsed_time": "2:26:52", "remaining_time": "1 day, 11:12:50", "throughput": 399.31, "total_tokens": 3519088}
{"current_steps": 2600, "total_steps": 40000, "eval_loss": 5.652227401733398, "epoch": 0.08322130465399143, "percentage": 6.5, "elapsed_time": "2:37:36", "remaining_time": "1 day, 13:47:08", "throughput": 372.13, "total_tokens": 3519088}
{"current_steps": 2605, "total_steps": 40000, "loss": 5.4857, "lr": 0.2968738582188558, "epoch": 0.08338134562447987, "percentage": 6.51, "elapsed_time": "2:37:39", "remaining_time": "1 day, 13:43:17", "throughput": 372.7, "total_tokens": 3525696}
{"current_steps": 2610, "total_steps": 40000, "loss": 5.3359, "lr": 0.2968618836161399, "epoch": 0.0835413865949683, "percentage": 6.53, "elapsed_time": "2:37:41", "remaining_time": "1 day, 13:39:09", "throughput": 373.35, "total_tokens": 3532640}
{"current_steps": 2615, "total_steps": 40000, "loss": 5.884, "lr": 0.296849886365476, "epoch": 0.08370142756545676, "percentage": 6.54, "elapsed_time": "2:37:44", "remaining_time": "1 day, 13:35:02", "throughput": 374.03, "total_tokens": 3539840}
{"current_steps": 2620, "total_steps": 40000, "loss": 5.2221, "lr": 0.2968378664687142, "epoch": 0.0838614685359452, "percentage": 6.55, "elapsed_time": "2:37:46", "remaining_time": "1 day, 13:30:55", "throughput": 374.65, "total_tokens": 3546544}
{"current_steps": 2625, "total_steps": 40000, "loss": 5.7659, "lr": 0.296825823927708, "epoch": 0.08402150950643365, "percentage": 6.56, "elapsed_time": "2:37:48", "remaining_time": "1 day, 13:26:49", "throughput": 375.32, "total_tokens": 3553584}
{"current_steps": 2630, "total_steps": 40000, "loss": 6.0172, "lr": 0.29681375874431476, "epoch": 0.08418155047692209, "percentage": 6.58, "elapsed_time": "2:37:50", "remaining_time": "1 day, 13:22:44", "throughput": 375.95, "total_tokens": 3560368}
{"current_steps": 2635, "total_steps": 40000, "loss": 5.6754, "lr": 0.29680167092039483, "epoch": 0.08434159144741053, "percentage": 6.59, "elapsed_time": "2:37:52", "remaining_time": "1 day, 13:18:39", "throughput": 376.55, "total_tokens": 3566768}
{"current_steps": 2640, "total_steps": 40000, "loss": 6.1026, "lr": 0.2967895604578125, "epoch": 0.08450163241789899, "percentage": 6.6, "elapsed_time": "2:37:54", "remaining_time": "1 day, 13:14:37", "throughput": 377.24, "total_tokens": 3574112}
{"current_steps": 2645, "total_steps": 40000, "loss": 5.8592, "lr": 0.2967774273584352, "epoch": 0.08466167338838743, "percentage": 6.61, "elapsed_time": "2:37:56", "remaining_time": "1 day, 13:10:35", "throughput": 377.89, "total_tokens": 3581024}
{"current_steps": 2650, "total_steps": 40000, "loss": 5.628, "lr": 0.2967652716241342, "epoch": 0.08482171435887587, "percentage": 6.62, "elapsed_time": "2:37:58", "remaining_time": "1 day, 13:06:33", "throughput": 378.54, "total_tokens": 3588016}
{"current_steps": 2655, "total_steps": 40000, "loss": 5.8414, "lr": 0.29675309325678384, "epoch": 0.08498175532936432, "percentage": 6.64, "elapsed_time": "2:38:00", "remaining_time": "1 day, 13:02:32", "throughput": 379.14, "total_tokens": 3594416}
{"current_steps": 2660, "total_steps": 40000, "loss": 6.6577, "lr": 0.29674089225826233, "epoch": 0.08514179629985276, "percentage": 6.65, "elapsed_time": "2:38:02", "remaining_time": "1 day, 12:58:32", "throughput": 379.76, "total_tokens": 3601072}
{"current_steps": 2665, "total_steps": 40000, "loss": 5.3667, "lr": 0.29672866863045116, "epoch": 0.08530183727034121, "percentage": 6.66, "elapsed_time": "2:38:04", "remaining_time": "1 day, 12:54:33", "throughput": 380.35, "total_tokens": 3607456}
{"current_steps": 2670, "total_steps": 40000, "loss": 5.4181, "lr": 0.2967164223752354, "epoch": 0.08546187824082965, "percentage": 6.68, "elapsed_time": "2:38:06", "remaining_time": "1 day, 12:50:35", "throughput": 380.99, "total_tokens": 3614352}
{"current_steps": 2675, "total_steps": 40000, "loss": 6.2128, "lr": 0.2967041534945035, "epoch": 0.08562191921131809, "percentage": 6.69, "elapsed_time": "2:38:08", "remaining_time": "1 day, 12:46:39", "throughput": 381.65, "total_tokens": 3621376}
{"current_steps": 2680, "total_steps": 40000, "loss": 6.0776, "lr": 0.2966918619901476, "epoch": 0.08578196018180655, "percentage": 6.7, "elapsed_time": "2:38:10", "remaining_time": "1 day, 12:42:43", "throughput": 382.28, "total_tokens": 3628176}
{"current_steps": 2685, "total_steps": 40000, "loss": 6.3295, "lr": 0.2966795478640631, "epoch": 0.08594200115229499, "percentage": 6.71, "elapsed_time": "2:38:12", "remaining_time": "1 day, 12:38:47", "throughput": 382.9, "total_tokens": 3634832}
{"current_steps": 2690, "total_steps": 40000, "loss": 6.0091, "lr": 0.29666721111814903, "epoch": 0.08610204212278343, "percentage": 6.73, "elapsed_time": "2:38:14", "remaining_time": "1 day, 12:34:52", "throughput": 383.51, "total_tokens": 3641360}
{"current_steps": 2695, "total_steps": 40000, "loss": 6.3964, "lr": 0.2966548517543079, "epoch": 0.08626208309327188, "percentage": 6.74, "elapsed_time": "2:38:17", "remaining_time": "1 day, 12:31:00", "throughput": 384.18, "total_tokens": 3648560}
{"current_steps": 2700, "total_steps": 40000, "loss": 5.2787, "lr": 0.29664246977444564, "epoch": 0.08642212406376032, "percentage": 6.75, "elapsed_time": "2:38:19", "remaining_time": "1 day, 12:27:07", "throughput": 384.79, "total_tokens": 3655088}
{"current_steps": 2705, "total_steps": 40000, "loss": 5.8703, "lr": 0.2966300651804717, "epoch": 0.08658216503424877, "percentage": 6.76, "elapsed_time": "2:38:21", "remaining_time": "1 day, 12:23:15", "throughput": 385.4, "total_tokens": 3661744}
{"current_steps": 2710, "total_steps": 40000, "loss": 6.8377, "lr": 0.296617637974299, "epoch": 0.08674220600473721, "percentage": 6.78, "elapsed_time": "2:38:23", "remaining_time": "1 day, 12:19:24", "throughput": 386.02, "total_tokens": 3668448}
{"current_steps": 2715, "total_steps": 40000, "loss": 6.2903, "lr": 0.2966051881578441, "epoch": 0.08690224697522565, "percentage": 6.79, "elapsed_time": "2:38:25", "remaining_time": "1 day, 12:15:34", "throughput": 386.63, "total_tokens": 3674944}
{"current_steps": 2720, "total_steps": 40000, "loss": 5.8123, "lr": 0.29659271573302676, "epoch": 0.0870622879457141, "percentage": 6.8, "elapsed_time": "2:38:27", "remaining_time": "1 day, 12:11:45", "throughput": 387.3, "total_tokens": 3682128}
{"current_steps": 2725, "total_steps": 40000, "loss": 6.1133, "lr": 0.2965802207017705, "epoch": 0.08722232891620255, "percentage": 6.81, "elapsed_time": "2:38:29", "remaining_time": "1 day, 12:07:57", "throughput": 387.95, "total_tokens": 3689152}
{"current_steps": 2730, "total_steps": 40000, "loss": 5.9073, "lr": 0.2965677030660021, "epoch": 0.087382369886691, "percentage": 6.83, "elapsed_time": "2:38:31", "remaining_time": "1 day, 12:04:10", "throughput": 388.6, "total_tokens": 3696144}
{"current_steps": 2735, "total_steps": 40000, "loss": 5.6049, "lr": 0.2965551628276521, "epoch": 0.08754241085717944, "percentage": 6.84, "elapsed_time": "2:38:33", "remaining_time": "1 day, 12:00:22", "throughput": 389.19, "total_tokens": 3702512}
{"current_steps": 2740, "total_steps": 40000, "loss": 6.1472, "lr": 0.29654259998865423, "epoch": 0.08770245182766788, "percentage": 6.85, "elapsed_time": "2:38:35", "remaining_time": "1 day, 11:56:37", "throughput": 389.86, "total_tokens": 3709744}
{"current_steps": 2745, "total_steps": 40000, "loss": 6.3939, "lr": 0.2965300145509458, "epoch": 0.08786249279815633, "percentage": 6.86, "elapsed_time": "2:38:37", "remaining_time": "1 day, 11:52:51", "throughput": 390.46, "total_tokens": 3716176}
{"current_steps": 2750, "total_steps": 40000, "loss": 6.2415, "lr": 0.2965174065164678, "epoch": 0.08802253376864477, "percentage": 6.88, "elapsed_time": "2:38:39", "remaining_time": "1 day, 11:49:08", "throughput": 391.1, "total_tokens": 3723168}
{"current_steps": 2755, "total_steps": 40000, "loss": 5.6963, "lr": 0.2965047758871644, "epoch": 0.08818257473913321, "percentage": 6.89, "elapsed_time": "2:38:41", "remaining_time": "1 day, 11:45:23", "throughput": 391.69, "total_tokens": 3729584}
{"current_steps": 2760, "total_steps": 40000, "loss": 6.1632, "lr": 0.2964921226649835, "epoch": 0.08834261570962167, "percentage": 6.9, "elapsed_time": "2:38:43", "remaining_time": "1 day, 11:41:40", "throughput": 392.32, "total_tokens": 3736304}
{"current_steps": 2765, "total_steps": 40000, "loss": 5.7423, "lr": 0.2964794468518763, "epoch": 0.0885026566801101, "percentage": 6.91, "elapsed_time": "2:38:45", "remaining_time": "1 day, 11:37:58", "throughput": 392.95, "total_tokens": 3743088}
{"current_steps": 2770, "total_steps": 40000, "loss": 6.0225, "lr": 0.2964667484497977, "epoch": 0.08866269765059856, "percentage": 6.93, "elapsed_time": "2:38:47", "remaining_time": "1 day, 11:34:16", "throughput": 393.56, "total_tokens": 3749776}
{"current_steps": 2775, "total_steps": 40000, "loss": 5.7348, "lr": 0.29645402746070587, "epoch": 0.088822738621087, "percentage": 6.94, "elapsed_time": "2:38:49", "remaining_time": "1 day, 11:30:35", "throughput": 394.18, "total_tokens": 3756464}
{"current_steps": 2780, "total_steps": 40000, "loss": 6.0902, "lr": 0.2964412838865625, "epoch": 0.08898277959157544, "percentage": 6.95, "elapsed_time": "2:38:51", "remaining_time": "1 day, 11:26:55", "throughput": 394.8, "total_tokens": 3763136}
{"current_steps": 2785, "total_steps": 40000, "loss": 4.7347, "lr": 0.29642851772933293, "epoch": 0.08914282056206389, "percentage": 6.96, "elapsed_time": "2:38:53", "remaining_time": "1 day, 11:23:15", "throughput": 395.4, "total_tokens": 3769680}
{"current_steps": 2790, "total_steps": 40000, "loss": 5.8191, "lr": 0.29641572899098567, "epoch": 0.08930286153255233, "percentage": 6.98, "elapsed_time": "2:38:55", "remaining_time": "1 day, 11:19:38", "throughput": 396.04, "total_tokens": 3776512}
{"current_steps": 2795, "total_steps": 40000, "loss": 5.0134, "lr": 0.29640291767349314, "epoch": 0.08946290250304077, "percentage": 6.99, "elapsed_time": "2:38:57", "remaining_time": "1 day, 11:16:01", "throughput": 396.67, "total_tokens": 3783424}
{"current_steps": 2800, "total_steps": 40000, "loss": 6.9759, "lr": 0.2963900837788308, "epoch": 0.08962294347352923, "percentage": 7.0, "elapsed_time": "2:38:59", "remaining_time": "1 day, 11:12:24", "throughput": 397.3, "total_tokens": 3790208}
{"current_steps": 2800, "total_steps": 40000, "eval_loss": 5.861382484436035, "epoch": 0.08962294347352923, "percentage": 7.0, "elapsed_time": "2:49:43", "remaining_time": "1 day, 13:34:57", "throughput": 372.18, "total_tokens": 3790208}
{"current_steps": 2805, "total_steps": 40000, "loss": 5.9766, "lr": 0.2963772273089779, "epoch": 0.08978298444401767, "percentage": 7.01, "elapsed_time": "2:49:47", "remaining_time": "1 day, 13:31:24", "throughput": 372.71, "total_tokens": 3796864}
{"current_steps": 2810, "total_steps": 40000, "loss": 5.8586, "lr": 0.2963643482659171, "epoch": 0.08994302541450612, "percentage": 7.03, "elapsed_time": "2:49:49", "remaining_time": "1 day, 13:27:33", "throughput": 373.3, "total_tokens": 3803632}
{"current_steps": 2815, "total_steps": 40000, "loss": 6.3051, "lr": 0.2963514466516345, "epoch": 0.09010306638499456, "percentage": 7.04, "elapsed_time": "2:49:51", "remaining_time": "1 day, 13:23:42", "throughput": 373.87, "total_tokens": 3810224}
{"current_steps": 2820, "total_steps": 40000, "loss": 5.9599, "lr": 0.2963385224681196, "epoch": 0.090263107355483, "percentage": 7.05, "elapsed_time": "2:49:53", "remaining_time": "1 day, 13:19:53", "throughput": 374.46, "total_tokens": 3817040}
{"current_steps": 2825, "total_steps": 40000, "loss": 5.8482, "lr": 0.29632557571736556, "epoch": 0.09042314832597145, "percentage": 7.06, "elapsed_time": "2:49:55", "remaining_time": "1 day, 13:16:04", "throughput": 375.05, "total_tokens": 3823760}
{"current_steps": 2830, "total_steps": 40000, "loss": 5.3774, "lr": 0.2963126064013689, "epoch": 0.09058318929645989, "percentage": 7.07, "elapsed_time": "2:49:57", "remaining_time": "1 day, 13:12:16", "throughput": 375.67, "total_tokens": 3830864}
{"current_steps": 2835, "total_steps": 40000, "loss": 5.8548, "lr": 0.29629961452212966, "epoch": 0.09074323026694833, "percentage": 7.09, "elapsed_time": "2:49:59", "remaining_time": "1 day, 13:08:29", "throughput": 376.25, "total_tokens": 3837616}
{"current_steps": 2840, "total_steps": 40000, "loss": 5.2482, "lr": 0.2962866000816513, "epoch": 0.09090327123743679, "percentage": 7.1, "elapsed_time": "2:50:01", "remaining_time": "1 day, 13:04:42", "throughput": 376.81, "total_tokens": 3844080}
{"current_steps": 2845, "total_steps": 40000, "loss": 6.085, "lr": 0.2962735630819409, "epoch": 0.09106331220792523, "percentage": 7.11, "elapsed_time": "2:50:03", "remaining_time": "1 day, 13:00:56", "throughput": 377.4, "total_tokens": 3850848}
{"current_steps": 2850, "total_steps": 40000, "loss": 5.6049, "lr": 0.2962605035250089, "epoch": 0.09122335317841368, "percentage": 7.12, "elapsed_time": "2:50:05", "remaining_time": "1 day, 12:57:11", "throughput": 377.96, "total_tokens": 3857344}
{"current_steps": 2855, "total_steps": 40000, "loss": 5.7104, "lr": 0.29624742141286914, "epoch": 0.09138339414890212, "percentage": 7.14, "elapsed_time": "2:50:07", "remaining_time": "1 day, 12:53:27", "throughput": 378.55, "total_tokens": 3864144}
{"current_steps": 2860, "total_steps": 40000, "loss": 5.368, "lr": 0.29623431674753925, "epoch": 0.09154343511939056, "percentage": 7.15, "elapsed_time": "2:50:09", "remaining_time": "1 day, 12:49:43", "throughput": 379.12, "total_tokens": 3870672}
{"current_steps": 2865, "total_steps": 40000, "loss": 5.4045, "lr": 0.29622118953103993, "epoch": 0.09170347608987901, "percentage": 7.16, "elapsed_time": "2:50:11", "remaining_time": "1 day, 12:46:01", "throughput": 379.72, "total_tokens": 3877664}
{"current_steps": 2870, "total_steps": 40000, "loss": 5.7514, "lr": 0.2962080397653957, "epoch": 0.09186351706036745, "percentage": 7.17, "elapsed_time": "2:50:13", "remaining_time": "1 day, 12:42:19", "throughput": 380.3, "total_tokens": 3884336}
{"current_steps": 2875, "total_steps": 40000, "loss": 6.2245, "lr": 0.29619486745263435, "epoch": 0.09202355803085589, "percentage": 7.19, "elapsed_time": "2:50:15", "remaining_time": "1 day, 12:38:39", "throughput": 380.9, "total_tokens": 3891280}
{"current_steps": 2880, "total_steps": 40000, "loss": 6.3008, "lr": 0.2961816725947873, "epoch": 0.09218359900134435, "percentage": 7.2, "elapsed_time": "2:50:17", "remaining_time": "1 day, 12:34:57", "throughput": 381.44, "total_tokens": 3897536}
{"current_steps": 2885, "total_steps": 40000, "loss": 5.8261, "lr": 0.29616845519388924, "epoch": 0.09234363997183279, "percentage": 7.21, "elapsed_time": "2:50:20", "remaining_time": "1 day, 12:31:18", "throughput": 382.06, "total_tokens": 3904624}
{"current_steps": 2890, "total_steps": 40000, "loss": 6.0665, "lr": 0.2961552152519785, "epoch": 0.09250368094232124, "percentage": 7.22, "elapsed_time": "2:50:22", "remaining_time": "1 day, 12:27:39", "throughput": 382.61, "total_tokens": 3911040}
{"current_steps": 2895, "total_steps": 40000, "loss": 5.5694, "lr": 0.29614195277109695, "epoch": 0.09266372191280968, "percentage": 7.24, "elapsed_time": "2:50:24", "remaining_time": "1 day, 12:24:00", "throughput": 383.18, "total_tokens": 3917680}
{"current_steps": 2900, "total_steps": 40000, "loss": 5.9821, "lr": 0.2961286677532897, "epoch": 0.09282376288329812, "percentage": 7.25, "elapsed_time": "2:50:26", "remaining_time": "1 day, 12:20:22", "throughput": 383.74, "total_tokens": 3924112}
{"current_steps": 2905, "total_steps": 40000, "loss": 5.6765, "lr": 0.2961153602006055, "epoch": 0.09298380385378657, "percentage": 7.26, "elapsed_time": "2:50:28", "remaining_time": "1 day, 12:16:46", "throughput": 384.32, "total_tokens": 3930816}
{"current_steps": 2910, "total_steps": 40000, "loss": 6.4234, "lr": 0.29610203011509656, "epoch": 0.09314384482427501, "percentage": 7.27, "elapsed_time": "2:50:30", "remaining_time": "1 day, 12:13:10", "throughput": 384.91, "total_tokens": 3937744}
{"current_steps": 2915, "total_steps": 40000, "loss": 6.2658, "lr": 0.29608867749881856, "epoch": 0.09330388579476345, "percentage": 7.29, "elapsed_time": "2:50:32", "remaining_time": "1 day, 12:09:35", "throughput": 385.48, "total_tokens": 3944272}
{"current_steps": 2920, "total_steps": 40000, "loss": 5.6659, "lr": 0.29607530235383067, "epoch": 0.0934639267652519, "percentage": 7.3, "elapsed_time": "2:50:34", "remaining_time": "1 day, 12:06:00", "throughput": 386.06, "total_tokens": 3951024}
{"current_steps": 2925, "total_steps": 40000, "loss": 5.4645, "lr": 0.2960619046821954, "epoch": 0.09362396773574035, "percentage": 7.31, "elapsed_time": "2:50:36", "remaining_time": "1 day, 12:02:26", "throughput": 386.61, "total_tokens": 3957456}
{"current_steps": 2930, "total_steps": 40000, "loss": 5.7631, "lr": 0.2960484844859789, "epoch": 0.0937840087062288, "percentage": 7.32, "elapsed_time": "2:50:38", "remaining_time": "1 day, 11:58:51", "throughput": 387.17, "total_tokens": 3963856}
{"current_steps": 2935, "total_steps": 40000, "loss": 5.7667, "lr": 0.29603504176725076, "epoch": 0.09394404967671724, "percentage": 7.34, "elapsed_time": "2:50:40", "remaining_time": "1 day, 11:55:19", "throughput": 387.74, "total_tokens": 3970528}
{"current_steps": 2940, "total_steps": 40000, "loss": 5.5143, "lr": 0.296021576528084, "epoch": 0.09410409064720568, "percentage": 7.35, "elapsed_time": "2:50:42", "remaining_time": "1 day, 11:51:47", "throughput": 388.3, "total_tokens": 3977056}
{"current_steps": 2945, "total_steps": 40000, "loss": 5.9656, "lr": 0.29600808877055507, "epoch": 0.09426413161769413, "percentage": 7.36, "elapsed_time": "2:50:44", "remaining_time": "1 day, 11:48:17", "throughput": 388.89, "total_tokens": 3983952}
{"current_steps": 2950, "total_steps": 40000, "loss": 5.9815, "lr": 0.29599457849674404, "epoch": 0.09442417258818257, "percentage": 7.38, "elapsed_time": "2:50:46", "remaining_time": "1 day, 11:44:48", "throughput": 389.48, "total_tokens": 3990752}
{"current_steps": 2955, "total_steps": 40000, "loss": 5.8076, "lr": 0.2959810457087343, "epoch": 0.09458421355867103, "percentage": 7.39, "elapsed_time": "2:50:48", "remaining_time": "1 day, 11:41:18", "throughput": 390.04, "total_tokens": 3997344}
{"current_steps": 2960, "total_steps": 40000, "loss": 5.4185, "lr": 0.2959674904086128, "epoch": 0.09474425452915947, "percentage": 7.4, "elapsed_time": "2:50:50", "remaining_time": "1 day, 11:37:49", "throughput": 390.62, "total_tokens": 4004016}
{"current_steps": 2965, "total_steps": 40000, "loss": 5.1767, "lr": 0.2959539125984699, "epoch": 0.0949042954996479, "percentage": 7.41, "elapsed_time": "2:50:52", "remaining_time": "1 day, 11:34:22", "throughput": 391.21, "total_tokens": 4010912}
{"current_steps": 2970, "total_steps": 40000, "loss": 6.1263, "lr": 0.2959403122803996, "epoch": 0.09506433647013636, "percentage": 7.42, "elapsed_time": "2:50:54", "remaining_time": "1 day, 11:30:54", "throughput": 391.78, "total_tokens": 4017536}
{"current_steps": 2975, "total_steps": 40000, "loss": 5.8685, "lr": 0.2959266894564991, "epoch": 0.0952243774406248, "percentage": 7.44, "elapsed_time": "2:50:56", "remaining_time": "1 day, 11:27:28", "throughput": 392.39, "total_tokens": 4024624}
{"current_steps": 2980, "total_steps": 40000, "loss": 6.3186, "lr": 0.2959130441288692, "epoch": 0.09538441841111324, "percentage": 7.45, "elapsed_time": "2:50:58", "remaining_time": "1 day, 11:24:03", "throughput": 393.01, "total_tokens": 4031776}
{"current_steps": 2985, "total_steps": 40000, "loss": 4.9775, "lr": 0.2958993762996143, "epoch": 0.09554445938160169, "percentage": 7.46, "elapsed_time": "2:51:00", "remaining_time": "1 day, 11:20:39", "throughput": 393.64, "total_tokens": 4039104}
{"current_steps": 2990, "total_steps": 40000, "loss": 6.1918, "lr": 0.2958856859708421, "epoch": 0.09570450035209013, "percentage": 7.47, "elapsed_time": "2:51:03", "remaining_time": "1 day, 11:17:15", "throughput": 394.24, "total_tokens": 4046048}
{"current_steps": 2995, "total_steps": 40000, "loss": 6.3373, "lr": 0.2958719731446638, "epoch": 0.09586454132257859, "percentage": 7.49, "elapsed_time": "2:51:05", "remaining_time": "1 day, 11:13:50", "throughput": 394.79, "total_tokens": 4052512}
{"current_steps": 3000, "total_steps": 40000, "loss": 6.1517, "lr": 0.29585823782319404, "epoch": 0.09602458229306703, "percentage": 7.5, "elapsed_time": "2:51:07", "remaining_time": "1 day, 11:10:27", "throughput": 395.39, "total_tokens": 4059472}
{"current_steps": 3000, "total_steps": 40000, "eval_loss": 5.674954414367676, "epoch": 0.09602458229306703, "percentage": 7.5, "elapsed_time": "3:01:51", "remaining_time": "1 day, 13:22:55", "throughput": 372.04, "total_tokens": 4059472}
{"current_steps": 3005, "total_steps": 40000, "loss": 5.2191, "lr": 0.2958444800085511, "epoch": 0.09618462326355547, "percentage": 7.51, "elapsed_time": "3:01:54", "remaining_time": "1 day, 13:19:31", "throughput": 372.56, "total_tokens": 4066288}
{"current_steps": 3010, "total_steps": 40000, "loss": 6.2363, "lr": 0.2958306997028565, "epoch": 0.09634466423404392, "percentage": 7.52, "elapsed_time": "3:01:56", "remaining_time": "1 day, 13:15:54", "throughput": 373.09, "total_tokens": 4072912}
{"current_steps": 3015, "total_steps": 40000, "loss": 6.2786, "lr": 0.2958168969082354, "epoch": 0.09650470520453236, "percentage": 7.54, "elapsed_time": "3:01:58", "remaining_time": "1 day, 13:12:20", "throughput": 373.68, "total_tokens": 4080160}
{"current_steps": 3020, "total_steps": 40000, "loss": 6.0518, "lr": 0.2958030716268164, "epoch": 0.0966647461750208, "percentage": 7.55, "elapsed_time": "3:02:00", "remaining_time": "1 day, 13:08:45", "throughput": 374.23, "total_tokens": 4086848}
{"current_steps": 3025, "total_steps": 40000, "loss": 5.8631, "lr": 0.2957892238607314, "epoch": 0.09682478714550925, "percentage": 7.56, "elapsed_time": "3:02:02", "remaining_time": "1 day, 13:05:10", "throughput": 374.76, "total_tokens": 4093392}
{"current_steps": 3030, "total_steps": 40000, "loss": 5.7461, "lr": 0.2957753536121161, "epoch": 0.09698482811599769, "percentage": 7.58, "elapsed_time": "3:02:04", "remaining_time": "1 day, 13:01:37", "throughput": 375.31, "total_tokens": 4100160}
{"current_steps": 3035, "total_steps": 40000, "loss": 6.2945, "lr": 0.29576146088310923, "epoch": 0.09714486908648615, "percentage": 7.59, "elapsed_time": "3:02:06", "remaining_time": "1 day, 12:58:05", "throughput": 375.88, "total_tokens": 4107232}
{"current_steps": 3040, "total_steps": 40000, "loss": 5.6345, "lr": 0.2957475456758533, "epoch": 0.09730491005697459, "percentage": 7.6, "elapsed_time": "3:02:08", "remaining_time": "1 day, 12:54:33", "throughput": 376.42, "total_tokens": 4113856}
{"current_steps": 3045, "total_steps": 40000, "loss": 5.9592, "lr": 0.2957336079924944, "epoch": 0.09746495102746303, "percentage": 7.61, "elapsed_time": "3:02:11", "remaining_time": "1 day, 12:51:02", "throughput": 376.96, "total_tokens": 4120528}
{"current_steps": 3050, "total_steps": 40000, "loss": 5.2554, "lr": 0.2957196478351816, "epoch": 0.09762499199795148, "percentage": 7.62, "elapsed_time": "3:02:13", "remaining_time": "1 day, 12:47:31", "throughput": 377.49, "total_tokens": 4127088}
{"current_steps": 3055, "total_steps": 40000, "loss": 5.6449, "lr": 0.295705665206068, "epoch": 0.09778503296843992, "percentage": 7.64, "elapsed_time": "3:02:14", "remaining_time": "1 day, 12:43:59", "throughput": 378.0, "total_tokens": 4133392}
{"current_steps": 3060, "total_steps": 40000, "loss": 5.5927, "lr": 0.2956916601073097, "epoch": 0.09794507393892836, "percentage": 7.65, "elapsed_time": "3:02:17", "remaining_time": "1 day, 12:40:31", "throughput": 378.56, "total_tokens": 4140320}
{"current_steps": 3065, "total_steps": 40000, "loss": 5.482, "lr": 0.29567763254106655, "epoch": 0.09810511490941681, "percentage": 7.66, "elapsed_time": "3:02:19", "remaining_time": "1 day, 12:37:02", "throughput": 379.11, "total_tokens": 4147104}
{"current_steps": 3070, "total_steps": 40000, "loss": 6.0879, "lr": 0.29566358250950175, "epoch": 0.09826515587990525, "percentage": 7.67, "elapsed_time": "3:02:21", "remaining_time": "1 day, 12:33:33", "throughput": 379.61, "total_tokens": 4153360}
{"current_steps": 3075, "total_steps": 40000, "loss": 6.2504, "lr": 0.295649510014782, "epoch": 0.0984251968503937, "percentage": 7.69, "elapsed_time": "3:02:23", "remaining_time": "1 day, 12:30:06", "throughput": 380.15, "total_tokens": 4160000}
{"current_steps": 3080, "total_steps": 40000, "loss": 5.6629, "lr": 0.2956354150590775, "epoch": 0.09858523782088215, "percentage": 7.7, "elapsed_time": "3:02:25", "remaining_time": "1 day, 12:26:40", "throughput": 380.7, "total_tokens": 4166880}
{"current_steps": 3085, "total_steps": 40000, "loss": 6.3508, "lr": 0.2956212976445618, "epoch": 0.09874527879137059, "percentage": 7.71, "elapsed_time": "3:02:27", "remaining_time": "1 day, 12:23:14", "throughput": 381.24, "total_tokens": 4173568}
{"current_steps": 3090, "total_steps": 40000, "loss": 6.3762, "lr": 0.295607157773412, "epoch": 0.09890531976185904, "percentage": 7.72, "elapsed_time": "3:02:29", "remaining_time": "1 day, 12:19:48", "throughput": 381.76, "total_tokens": 4180000}
{"current_steps": 3095, "total_steps": 40000, "loss": 5.492, "lr": 0.2955929954478087, "epoch": 0.09906536073234748, "percentage": 7.74, "elapsed_time": "3:02:31", "remaining_time": "1 day, 12:16:23", "throughput": 382.31, "total_tokens": 4186736}
{"current_steps": 3100, "total_steps": 40000, "loss": 6.0287, "lr": 0.29557881066993585, "epoch": 0.09922540170283592, "percentage": 7.75, "elapsed_time": "3:02:33", "remaining_time": "1 day, 12:13:00", "throughput": 382.84, "total_tokens": 4193344}
{"current_steps": 3105, "total_steps": 40000, "loss": 5.5515, "lr": 0.29556460344198093, "epoch": 0.09938544267332437, "percentage": 7.76, "elapsed_time": "3:02:35", "remaining_time": "1 day, 12:09:37", "throughput": 383.42, "total_tokens": 4200512}
{"current_steps": 3110, "total_steps": 40000, "loss": 5.8572, "lr": 0.29555037376613486, "epoch": 0.09954548364381281, "percentage": 7.78, "elapsed_time": "3:02:37", "remaining_time": "1 day, 12:06:15", "throughput": 383.95, "total_tokens": 4207104}
{"current_steps": 3115, "total_steps": 40000, "loss": 5.6875, "lr": 0.29553612164459203, "epoch": 0.09970552461430127, "percentage": 7.79, "elapsed_time": "3:02:39", "remaining_time": "1 day, 12:02:54", "throughput": 384.52, "total_tokens": 4214240}
{"current_steps": 3120, "total_steps": 40000, "loss": 5.8525, "lr": 0.29552184707955037, "epoch": 0.0998655655847897, "percentage": 7.8, "elapsed_time": "3:02:41", "remaining_time": "1 day, 11:59:32", "throughput": 385.05, "total_tokens": 4220784}
{"current_steps": 3125, "total_steps": 40000, "loss": 5.3882, "lr": 0.29550755007321117, "epoch": 0.10002560655527815, "percentage": 7.81, "elapsed_time": "3:02:43", "remaining_time": "1 day, 11:56:12", "throughput": 385.61, "total_tokens": 4227728}
{"current_steps": 3130, "total_steps": 40000, "loss": 4.9609, "lr": 0.29549323062777916, "epoch": 0.1001856475257666, "percentage": 7.83, "elapsed_time": "3:02:45", "remaining_time": "1 day, 11:52:52", "throughput": 386.16, "total_tokens": 4234544}
{"current_steps": 3135, "total_steps": 40000, "loss": 6.0065, "lr": 0.29547888874546263, "epoch": 0.10034568849625504, "percentage": 7.84, "elapsed_time": "3:02:47", "remaining_time": "1 day, 11:49:32", "throughput": 386.68, "total_tokens": 4241024}
{"current_steps": 3140, "total_steps": 40000, "loss": 6.3719, "lr": 0.2954645244284732, "epoch": 0.1005057294667435, "percentage": 7.85, "elapsed_time": "3:02:49", "remaining_time": "1 day, 11:46:14", "throughput": 387.27, "total_tokens": 4248288}
{"current_steps": 3145, "total_steps": 40000, "loss": 6.0419, "lr": 0.2954501376790261, "epoch": 0.10066577043723193, "percentage": 7.86, "elapsed_time": "3:02:51", "remaining_time": "1 day, 11:42:56", "throughput": 387.81, "total_tokens": 4255104}
{"current_steps": 3150, "total_steps": 40000, "loss": 5.3043, "lr": 0.29543572849933997, "epoch": 0.10082581140772037, "percentage": 7.88, "elapsed_time": "3:02:54", "remaining_time": "1 day, 11:39:40", "throughput": 388.4, "total_tokens": 4262400}
{"current_steps": 3155, "total_steps": 40000, "loss": 5.9963, "lr": 0.2954212968916368, "epoch": 0.10098585237820883, "percentage": 7.89, "elapsed_time": "3:02:56", "remaining_time": "1 day, 11:36:24", "throughput": 388.98, "total_tokens": 4269504}
{"current_steps": 3160, "total_steps": 40000, "loss": 5.1201, "lr": 0.29540684285814217, "epoch": 0.10114589334869727, "percentage": 7.9, "elapsed_time": "3:02:58", "remaining_time": "1 day, 11:33:08", "throughput": 389.52, "total_tokens": 4276320}
{"current_steps": 3165, "total_steps": 40000, "loss": 6.2646, "lr": 0.2953923664010851, "epoch": 0.1013059343191857, "percentage": 7.91, "elapsed_time": "3:03:00", "remaining_time": "1 day, 11:29:53", "throughput": 390.09, "total_tokens": 4283392}
{"current_steps": 3170, "total_steps": 40000, "loss": 6.2386, "lr": 0.295377867522698, "epoch": 0.10146597528967416, "percentage": 7.92, "elapsed_time": "3:03:02", "remaining_time": "1 day, 11:26:38", "throughput": 390.63, "total_tokens": 4290080}
{"current_steps": 3175, "total_steps": 40000, "loss": 6.0521, "lr": 0.2953633462252168, "epoch": 0.1016260162601626, "percentage": 7.94, "elapsed_time": "3:03:04", "remaining_time": "1 day, 11:23:22", "throughput": 391.16, "total_tokens": 4296688}
{"current_steps": 3180, "total_steps": 40000, "loss": 5.0591, "lr": 0.2953488025108809, "epoch": 0.10178605723065105, "percentage": 7.95, "elapsed_time": "3:03:06", "remaining_time": "1 day, 11:20:09", "throughput": 391.73, "total_tokens": 4303792}
{"current_steps": 3185, "total_steps": 40000, "loss": 6.3099, "lr": 0.295334236381933, "epoch": 0.10194609820113949, "percentage": 7.96, "elapsed_time": "3:03:08", "remaining_time": "1 day, 11:16:56", "throughput": 392.29, "total_tokens": 4310784}
{"current_steps": 3190, "total_steps": 40000, "loss": 5.6338, "lr": 0.29531964784061954, "epoch": 0.10210613917162793, "percentage": 7.98, "elapsed_time": "3:03:10", "remaining_time": "1 day, 11:13:44", "throughput": 392.85, "total_tokens": 4317680}
{"current_steps": 3195, "total_steps": 40000, "loss": 6.0947, "lr": 0.2953050368891902, "epoch": 0.10226618014211639, "percentage": 7.99, "elapsed_time": "3:03:12", "remaining_time": "1 day, 11:10:32", "throughput": 393.38, "total_tokens": 4324368}
{"current_steps": 3200, "total_steps": 40000, "loss": 6.6672, "lr": 0.29529040352989805, "epoch": 0.10242622111260483, "percentage": 8.0, "elapsed_time": "3:03:14", "remaining_time": "1 day, 11:07:20", "throughput": 393.92, "total_tokens": 4331088}
{"current_steps": 3200, "total_steps": 40000, "eval_loss": 5.711532115936279, "epoch": 0.10242622111260483, "percentage": 8.0, "elapsed_time": "3:13:58", "remaining_time": "1 day, 13:10:39", "throughput": 372.14, "total_tokens": 4331088}
{"current_steps": 3205, "total_steps": 40000, "loss": 6.3491, "lr": 0.29527574776499993, "epoch": 0.10258626208309327, "percentage": 8.01, "elapsed_time": "3:14:01", "remaining_time": "1 day, 13:07:30", "throughput": 372.61, "total_tokens": 4337776}
{"current_steps": 3210, "total_steps": 40000, "loss": 5.5269, "lr": 0.2952610695967558, "epoch": 0.10274630305358172, "percentage": 8.03, "elapsed_time": "3:14:03", "remaining_time": "1 day, 13:04:08", "throughput": 373.13, "total_tokens": 4344624}
{"current_steps": 3215, "total_steps": 40000, "loss": 6.3063, "lr": 0.29524636902742935, "epoch": 0.10290634402407016, "percentage": 8.04, "elapsed_time": "3:14:05", "remaining_time": "1 day, 13:00:46", "throughput": 373.67, "total_tokens": 4351664}
{"current_steps": 3220, "total_steps": 40000, "loss": 6.1282, "lr": 0.2952316460592875, "epoch": 0.10306638499455861, "percentage": 8.05, "elapsed_time": "3:14:07", "remaining_time": "1 day, 12:57:25", "throughput": 374.2, "total_tokens": 4358576}
{"current_steps": 3225, "total_steps": 40000, "loss": 5.7549, "lr": 0.29521690069460066, "epoch": 0.10322642596504705, "percentage": 8.06, "elapsed_time": "3:14:09", "remaining_time": "1 day, 12:54:04", "throughput": 374.7, "total_tokens": 4365216}
{"current_steps": 3230, "total_steps": 40000, "loss": 5.9063, "lr": 0.29520213293564285, "epoch": 0.10338646693553549, "percentage": 8.08, "elapsed_time": "3:14:11", "remaining_time": "1 day, 12:50:44", "throughput": 375.21, "total_tokens": 4371936}
{"current_steps": 3235, "total_steps": 40000, "loss": 5.0874, "lr": 0.29518734278469144, "epoch": 0.10354650790602395, "percentage": 8.09, "elapsed_time": "3:14:13", "remaining_time": "1 day, 12:47:24", "throughput": 375.72, "total_tokens": 4378640}
{"current_steps": 3240, "total_steps": 40000, "loss": 4.9757, "lr": 0.29517253024402723, "epoch": 0.10370654887651239, "percentage": 8.1, "elapsed_time": "3:14:15", "remaining_time": "1 day, 12:44:05", "throughput": 376.22, "total_tokens": 4385248}
{"current_steps": 3245, "total_steps": 40000, "loss": 5.3763, "lr": 0.2951576953159345, "epoch": 0.10386658984700083, "percentage": 8.11, "elapsed_time": "3:14:18", "remaining_time": "1 day, 12:40:46", "throughput": 376.74, "total_tokens": 4392080}
{"current_steps": 3250, "total_steps": 40000, "loss": 5.6235, "lr": 0.29514283800270097, "epoch": 0.10402663081748928, "percentage": 8.12, "elapsed_time": "3:14:20", "remaining_time": "1 day, 12:37:28", "throughput": 377.25, "total_tokens": 4398784}
{"current_steps": 3255, "total_steps": 40000, "loss": 5.7336, "lr": 0.2951279583066179, "epoch": 0.10418667178797772, "percentage": 8.14, "elapsed_time": "3:14:22", "remaining_time": "1 day, 12:34:11", "throughput": 377.75, "total_tokens": 4405376}
{"current_steps": 3260, "total_steps": 40000, "loss": 4.9623, "lr": 0.2951130562299798, "epoch": 0.10434671275846617, "percentage": 8.15, "elapsed_time": "3:14:24", "remaining_time": "1 day, 12:30:54", "throughput": 378.26, "total_tokens": 4412112}
{"current_steps": 3265, "total_steps": 40000, "loss": 6.2228, "lr": 0.29509813177508487, "epoch": 0.10450675372895461, "percentage": 8.16, "elapsed_time": "3:14:26", "remaining_time": "1 day, 12:27:38", "throughput": 378.77, "total_tokens": 4418816}
{"current_steps": 3270, "total_steps": 40000, "loss": 5.5275, "lr": 0.2950831849442346, "epoch": 0.10466679469944305, "percentage": 8.18, "elapsed_time": "3:14:28", "remaining_time": "1 day, 12:24:23", "throughput": 379.27, "total_tokens": 4425472}
{"current_steps": 3275, "total_steps": 40000, "loss": 5.694, "lr": 0.2950682157397339, "epoch": 0.1048268356699315, "percentage": 8.19, "elapsed_time": "3:14:30", "remaining_time": "1 day, 12:21:08", "throughput": 379.78, "total_tokens": 4432176}
{"current_steps": 3280, "total_steps": 40000, "loss": 6.2268, "lr": 0.2950532241638914, "epoch": 0.10498687664041995, "percentage": 8.2, "elapsed_time": "3:14:32", "remaining_time": "1 day, 12:17:53", "throughput": 380.29, "total_tokens": 4438928}
{"current_steps": 3285, "total_steps": 40000, "loss": 6.0347, "lr": 0.2950382102190188, "epoch": 0.10514691761090839, "percentage": 8.21, "elapsed_time": "3:14:34", "remaining_time": "1 day, 12:14:39", "throughput": 380.77, "total_tokens": 4445216}
{"current_steps": 3290, "total_steps": 40000, "loss": 5.4231, "lr": 0.2950231739074316, "epoch": 0.10530695858139684, "percentage": 8.22, "elapsed_time": "3:14:36", "remaining_time": "1 day, 12:11:26", "throughput": 381.26, "total_tokens": 4451760}
{"current_steps": 3295, "total_steps": 40000, "loss": 5.4835, "lr": 0.29500811523144843, "epoch": 0.10546699955188528, "percentage": 8.24, "elapsed_time": "3:14:38", "remaining_time": "1 day, 12:08:14", "throughput": 381.79, "total_tokens": 4458752}
{"current_steps": 3300, "total_steps": 40000, "loss": 6.0333, "lr": 0.2949930341933917, "epoch": 0.10562704052237373, "percentage": 8.25, "elapsed_time": "3:14:40", "remaining_time": "1 day, 12:05:02", "throughput": 382.31, "total_tokens": 4465632}
{"current_steps": 3305, "total_steps": 40000, "loss": 6.0783, "lr": 0.29497793079558693, "epoch": 0.10578708149286217, "percentage": 8.26, "elapsed_time": "3:14:42", "remaining_time": "1 day, 12:01:50", "throughput": 382.81, "total_tokens": 4472224}
{"current_steps": 3310, "total_steps": 40000, "loss": 5.506, "lr": 0.2949628050403633, "epoch": 0.10594712246335061, "percentage": 8.28, "elapsed_time": "3:14:44", "remaining_time": "1 day, 11:58:38", "throughput": 383.29, "total_tokens": 4478624}
{"current_steps": 3315, "total_steps": 40000, "loss": 5.1095, "lr": 0.2949476569300535, "epoch": 0.10610716343383907, "percentage": 8.29, "elapsed_time": "3:14:46", "remaining_time": "1 day, 11:55:28", "throughput": 383.81, "total_tokens": 4485488}
{"current_steps": 3320, "total_steps": 40000, "loss": 6.4218, "lr": 0.29493248646699344, "epoch": 0.1062672044043275, "percentage": 8.3, "elapsed_time": "3:14:48", "remaining_time": "1 day, 11:52:20", "throughput": 384.36, "total_tokens": 4492736}
{"current_steps": 3325, "total_steps": 40000, "loss": 5.7727, "lr": 0.29491729365352265, "epoch": 0.10642724537481596, "percentage": 8.31, "elapsed_time": "3:14:50", "remaining_time": "1 day, 11:49:11", "throughput": 384.87, "total_tokens": 4499504}
{"current_steps": 3330, "total_steps": 40000, "loss": 5.8368, "lr": 0.29490207849198397, "epoch": 0.1065872863453044, "percentage": 8.33, "elapsed_time": "3:14:52", "remaining_time": "1 day, 11:46:02", "throughput": 385.38, "total_tokens": 4506192}
{"current_steps": 3335, "total_steps": 40000, "loss": 5.4325, "lr": 0.29488684098472384, "epoch": 0.10674732731579284, "percentage": 8.34, "elapsed_time": "3:14:54", "remaining_time": "1 day, 11:42:54", "throughput": 385.88, "total_tokens": 4512880}
{"current_steps": 3340, "total_steps": 40000, "loss": 5.2622, "lr": 0.2948715811340921, "epoch": 0.10690736828628129, "percentage": 8.35, "elapsed_time": "3:14:57", "remaining_time": "1 day, 11:39:47", "throughput": 386.41, "total_tokens": 4519824}
{"current_steps": 3345, "total_steps": 40000, "loss": 6.3227, "lr": 0.294856298942442, "epoch": 0.10706740925676973, "percentage": 8.36, "elapsed_time": "3:14:59", "remaining_time": "1 day, 11:36:41", "throughput": 386.94, "total_tokens": 4526880}
{"current_steps": 3350, "total_steps": 40000, "loss": 5.5516, "lr": 0.2948409944121302, "epoch": 0.10722745022725817, "percentage": 8.38, "elapsed_time": "3:15:01", "remaining_time": "1 day, 11:33:35", "throughput": 387.5, "total_tokens": 4534304}
{"current_steps": 3355, "total_steps": 40000, "loss": 5.4318, "lr": 0.29482566754551687, "epoch": 0.10738749119774663, "percentage": 8.39, "elapsed_time": "3:15:03", "remaining_time": "1 day, 11:30:29", "throughput": 388.0, "total_tokens": 4540880}
{"current_steps": 3360, "total_steps": 40000, "loss": 5.9571, "lr": 0.2948103183449656, "epoch": 0.10754753216823507, "percentage": 8.4, "elapsed_time": "3:15:05", "remaining_time": "1 day, 11:27:24", "throughput": 388.5, "total_tokens": 4547520}
{"current_steps": 3365, "total_steps": 40000, "loss": 6.1462, "lr": 0.2947949468128435, "epoch": 0.10770757313872352, "percentage": 8.41, "elapsed_time": "3:15:07", "remaining_time": "1 day, 11:24:19", "throughput": 389.0, "total_tokens": 4554240}
{"current_steps": 3370, "total_steps": 40000, "loss": 6.0525, "lr": 0.2947795529515209, "epoch": 0.10786761410921196, "percentage": 8.43, "elapsed_time": "3:15:09", "remaining_time": "1 day, 11:21:15", "throughput": 389.52, "total_tokens": 4561040}
{"current_steps": 3375, "total_steps": 40000, "loss": 5.5309, "lr": 0.29476413676337193, "epoch": 0.1080276550797004, "percentage": 8.44, "elapsed_time": "3:15:11", "remaining_time": "1 day, 11:18:12", "throughput": 390.03, "total_tokens": 4567920}
{"current_steps": 3380, "total_steps": 40000, "loss": 5.2485, "lr": 0.2947486982507738, "epoch": 0.10818769605018885, "percentage": 8.45, "elapsed_time": "3:15:13", "remaining_time": "1 day, 11:15:09", "throughput": 390.54, "total_tokens": 4574592}
{"current_steps": 3385, "total_steps": 40000, "loss": 6.0799, "lr": 0.29473323741610735, "epoch": 0.10834773702067729, "percentage": 8.46, "elapsed_time": "3:15:15", "remaining_time": "1 day, 11:12:06", "throughput": 391.03, "total_tokens": 4581184}
{"current_steps": 3390, "total_steps": 40000, "loss": 6.0579, "lr": 0.2947177542617569, "epoch": 0.10850777799116573, "percentage": 8.48, "elapsed_time": "3:15:17", "remaining_time": "1 day, 11:09:04", "throughput": 391.54, "total_tokens": 4587968}
{"current_steps": 3395, "total_steps": 40000, "loss": 5.4002, "lr": 0.2947022487901101, "epoch": 0.10866781896165419, "percentage": 8.49, "elapsed_time": "3:15:19", "remaining_time": "1 day, 11:06:02", "throughput": 392.02, "total_tokens": 4594368}
{"current_steps": 3400, "total_steps": 40000, "loss": 6.1049, "lr": 0.2946867210035581, "epoch": 0.10882785993214263, "percentage": 8.5, "elapsed_time": "3:15:21", "remaining_time": "1 day, 11:03:02", "throughput": 392.58, "total_tokens": 4601728}
{"current_steps": 3400, "total_steps": 40000, "eval_loss": 5.739169597625732, "epoch": 0.10882785993214263, "percentage": 8.5, "elapsed_time": "3:26:06", "remaining_time": "1 day, 12:58:37", "throughput": 372.12, "total_tokens": 4601728}