sft-Math-7B / trainer_log.jsonl
ChillingDream's picture
Upload folder using huggingface_hub
204479a verified
{"current_steps": 10, "total_steps": 516, "loss": 0.4976, "lr": 1.9230769230769234e-06, "epoch": 0.05813953488372093, "percentage": 1.94, "elapsed_time": "0:03:43", "remaining_time": "3:08:04"}
{"current_steps": 20, "total_steps": 516, "loss": 0.4336, "lr": 3.846153846153847e-06, "epoch": 0.11627906976744186, "percentage": 3.88, "elapsed_time": "0:07:20", "remaining_time": "3:02:02"}
{"current_steps": 30, "total_steps": 516, "loss": 0.3589, "lr": 5.769230769230769e-06, "epoch": 0.1744186046511628, "percentage": 5.81, "elapsed_time": "0:10:59", "remaining_time": "2:57:58"}
{"current_steps": 40, "total_steps": 516, "loss": 0.3252, "lr": 7.692307692307694e-06, "epoch": 0.23255813953488372, "percentage": 7.75, "elapsed_time": "0:14:37", "remaining_time": "2:54:02"}
{"current_steps": 50, "total_steps": 516, "loss": 0.3045, "lr": 9.615384615384616e-06, "epoch": 0.29069767441860467, "percentage": 9.69, "elapsed_time": "0:18:18", "remaining_time": "2:50:34"}
{"current_steps": 60, "total_steps": 516, "loss": 0.3052, "lr": 9.99266706925562e-06, "epoch": 0.3488372093023256, "percentage": 11.63, "elapsed_time": "0:21:53", "remaining_time": "2:46:23"}
{"current_steps": 70, "total_steps": 516, "loss": 0.2958, "lr": 9.962913897416029e-06, "epoch": 0.4069767441860465, "percentage": 13.57, "elapsed_time": "0:25:25", "remaining_time": "2:41:59"}
{"current_steps": 80, "total_steps": 516, "loss": 0.2955, "lr": 9.91041841371078e-06, "epoch": 0.46511627906976744, "percentage": 15.5, "elapsed_time": "0:29:07", "remaining_time": "2:38:43"}
{"current_steps": 90, "total_steps": 516, "loss": 0.2919, "lr": 9.835421176144035e-06, "epoch": 0.5232558139534884, "percentage": 17.44, "elapsed_time": "0:32:48", "remaining_time": "2:35:17"}
{"current_steps": 100, "total_steps": 516, "loss": 0.2884, "lr": 9.738265855914014e-06, "epoch": 0.5813953488372093, "percentage": 19.38, "elapsed_time": "0:36:32", "remaining_time": "2:31:59"}
{"current_steps": 110, "total_steps": 516, "loss": 0.2862, "lr": 9.619397662556434e-06, "epoch": 0.6395348837209303, "percentage": 21.32, "elapsed_time": "0:40:03", "remaining_time": "2:27:50"}
{"current_steps": 120, "total_steps": 516, "loss": 0.282, "lr": 9.479361303793441e-06, "epoch": 0.6976744186046512, "percentage": 23.26, "elapsed_time": "0:43:36", "remaining_time": "2:23:55"}
{"current_steps": 130, "total_steps": 516, "loss": 0.2834, "lr": 9.318798489436917e-06, "epoch": 0.7558139534883721, "percentage": 25.19, "elapsed_time": "0:47:20", "remaining_time": "2:20:34"}
{"current_steps": 140, "total_steps": 516, "loss": 0.2789, "lr": 9.138444990784455e-06, "epoch": 0.813953488372093, "percentage": 27.13, "elapsed_time": "0:50:55", "remaining_time": "2:16:45"}
{"current_steps": 150, "total_steps": 516, "loss": 0.2759, "lr": 8.93912726898311e-06, "epoch": 0.872093023255814, "percentage": 29.07, "elapsed_time": "0:54:25", "remaining_time": "2:12:48"}
{"current_steps": 160, "total_steps": 516, "loss": 0.2791, "lr": 8.721758687811353e-06, "epoch": 0.9302325581395349, "percentage": 31.01, "elapsed_time": "0:58:07", "remaining_time": "2:09:19"}
{"current_steps": 170, "total_steps": 516, "loss": 0.2738, "lr": 8.487335328233912e-06, "epoch": 0.9883720930232558, "percentage": 32.95, "elapsed_time": "1:01:49", "remaining_time": "2:05:50"}
{"current_steps": 180, "total_steps": 516, "loss": 0.2461, "lr": 8.23693142390914e-06, "epoch": 1.0465116279069768, "percentage": 34.88, "elapsed_time": "1:05:27", "remaining_time": "2:02:12"}
{"current_steps": 190, "total_steps": 516, "loss": 0.2321, "lr": 7.97169443856545e-06, "epoch": 1.1046511627906976, "percentage": 36.82, "elapsed_time": "1:09:04", "remaining_time": "1:58:30"}
{"current_steps": 200, "total_steps": 516, "loss": 0.2334, "lr": 7.692839807804522e-06, "epoch": 1.1627906976744187, "percentage": 38.76, "elapsed_time": "1:12:50", "remaining_time": "1:55:06"}
{"current_steps": 210, "total_steps": 516, "loss": 0.2314, "lr": 7.401645369426697e-06, "epoch": 1.2209302325581395, "percentage": 40.7, "elapsed_time": "1:16:29", "remaining_time": "1:51:27"}
{"current_steps": 220, "total_steps": 516, "loss": 0.233, "lr": 7.099445507801324e-06, "epoch": 1.2790697674418605, "percentage": 42.64, "elapsed_time": "1:20:05", "remaining_time": "1:47:46"}
{"current_steps": 230, "total_steps": 516, "loss": 0.2328, "lr": 6.7876250391152e-06, "epoch": 1.3372093023255813, "percentage": 44.57, "elapsed_time": "1:23:35", "remaining_time": "1:43:57"}
{"current_steps": 240, "total_steps": 516, "loss": 0.2316, "lr": 6.467612865519674e-06, "epoch": 1.3953488372093024, "percentage": 46.51, "elapsed_time": "1:27:18", "remaining_time": "1:40:23"}
{"current_steps": 250, "total_steps": 516, "loss": 0.2323, "lr": 6.14087542725593e-06, "epoch": 1.4534883720930232, "percentage": 48.45, "elapsed_time": "1:30:59", "remaining_time": "1:36:48"}
{"current_steps": 260, "total_steps": 516, "loss": 0.2283, "lr": 5.808909982763825e-06, "epoch": 1.5116279069767442, "percentage": 50.39, "elapsed_time": "1:34:38", "remaining_time": "1:33:11"}
{"current_steps": 270, "total_steps": 516, "loss": 0.2309, "lr": 5.473237747567805e-06, "epoch": 1.5697674418604652, "percentage": 52.33, "elapsed_time": "1:38:18", "remaining_time": "1:29:33"}
{"current_steps": 280, "total_steps": 516, "loss": 0.2317, "lr": 5.1353969233806735e-06, "epoch": 1.627906976744186, "percentage": 54.26, "elapsed_time": "1:41:55", "remaining_time": "1:25:54"}
{"current_steps": 290, "total_steps": 516, "loss": 0.2272, "lr": 4.796935649368936e-06, "epoch": 1.6860465116279069, "percentage": 56.2, "elapsed_time": "1:45:33", "remaining_time": "1:22:16"}
{"current_steps": 300, "total_steps": 516, "loss": 0.2319, "lr": 4.459404907880293e-06, "epoch": 1.744186046511628, "percentage": 58.14, "elapsed_time": "1:49:12", "remaining_time": "1:18:37"}
{"current_steps": 310, "total_steps": 516, "loss": 0.227, "lr": 4.1243514171423465e-06, "epoch": 1.802325581395349, "percentage": 60.08, "elapsed_time": "1:52:57", "remaining_time": "1:15:03"}
{"current_steps": 320, "total_steps": 516, "loss": 0.2288, "lr": 3.7933105435014727e-06, "epoch": 1.8604651162790697, "percentage": 62.02, "elapsed_time": "1:56:37", "remaining_time": "1:11:26"}
{"current_steps": 330, "total_steps": 516, "loss": 0.224, "lr": 3.4677992656811054e-06, "epoch": 1.9186046511627906, "percentage": 63.95, "elapsed_time": "2:00:23", "remaining_time": "1:07:51"}
{"current_steps": 340, "total_steps": 516, "loss": 0.2293, "lr": 3.149309223300428e-06, "epoch": 1.9767441860465116, "percentage": 65.89, "elapsed_time": "2:04:01", "remaining_time": "1:04:12"}
{"current_steps": 350, "total_steps": 516, "loss": 0.1976, "lr": 2.839299881508272e-06, "epoch": 2.0348837209302326, "percentage": 67.83, "elapsed_time": "2:07:40", "remaining_time": "1:00:33"}
{"current_steps": 360, "total_steps": 516, "loss": 0.1831, "lr": 2.5391918430549635e-06, "epoch": 2.0930232558139537, "percentage": 69.77, "elapsed_time": "2:11:27", "remaining_time": "0:56:57"}
{"current_steps": 370, "total_steps": 516, "loss": 0.1833, "lr": 2.250360338449226e-06, "epoch": 2.1511627906976742, "percentage": 71.71, "elapsed_time": "2:14:56", "remaining_time": "0:53:14"}
{"current_steps": 380, "total_steps": 516, "loss": 0.187, "lr": 1.9741289240311757e-06, "epoch": 2.2093023255813953, "percentage": 73.64, "elapsed_time": "2:18:35", "remaining_time": "0:49:36"}
{"current_steps": 390, "total_steps": 516, "loss": 0.1856, "lr": 1.7117634168396774e-06, "epoch": 2.2674418604651163, "percentage": 75.58, "elapsed_time": "2:22:15", "remaining_time": "0:45:57"}
{"current_steps": 400, "total_steps": 516, "loss": 0.1812, "lr": 1.4644660940672628e-06, "epoch": 2.3255813953488373, "percentage": 77.52, "elapsed_time": "2:25:52", "remaining_time": "0:42:18"}
{"current_steps": 410, "total_steps": 516, "loss": 0.183, "lr": 1.2333701836832812e-06, "epoch": 2.383720930232558, "percentage": 79.46, "elapsed_time": "2:29:34", "remaining_time": "0:38:40"}
{"current_steps": 420, "total_steps": 516, "loss": 0.1825, "lr": 1.0195346714717813e-06, "epoch": 2.441860465116279, "percentage": 81.4, "elapsed_time": "2:33:16", "remaining_time": "0:35:01"}
{"current_steps": 430, "total_steps": 516, "loss": 0.181, "lr": 8.239394482805996e-07, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "2:37:01", "remaining_time": "0:31:24"}
{"current_steps": 440, "total_steps": 516, "loss": 0.1856, "lr": 6.474808197191401e-07, "epoch": 2.558139534883721, "percentage": 85.27, "elapsed_time": "2:40:39", "remaining_time": "0:27:45"}
{"current_steps": 450, "total_steps": 516, "loss": 0.18, "lr": 4.9096739888146e-07, "epoch": 2.616279069767442, "percentage": 87.21, "elapsed_time": "2:44:14", "remaining_time": "0:24:05"}
{"current_steps": 460, "total_steps": 516, "loss": 0.1845, "lr": 3.5511640091604293e-07, "epoch": 2.6744186046511627, "percentage": 89.15, "elapsed_time": "2:47:55", "remaining_time": "0:20:26"}
{"current_steps": 470, "total_steps": 516, "loss": 0.185, "lr": 2.4055035642222225e-07, "epoch": 2.7325581395348837, "percentage": 91.09, "elapsed_time": "2:51:33", "remaining_time": "0:16:47"}
{"current_steps": 480, "total_steps": 516, "loss": 0.1811, "lr": 1.477942587339426e-07, "epoch": 2.7906976744186047, "percentage": 93.02, "elapsed_time": "2:55:14", "remaining_time": "0:13:08"}
{"current_steps": 490, "total_steps": 516, "loss": 0.1841, "lr": 7.727315816331515e-08, "epoch": 2.8488372093023253, "percentage": 94.96, "elapsed_time": "2:58:55", "remaining_time": "0:09:29"}
{"current_steps": 500, "total_steps": 516, "loss": 0.183, "lr": 2.9310214228202016e-08, "epoch": 2.9069767441860463, "percentage": 96.9, "elapsed_time": "3:02:28", "remaining_time": "0:05:50"}
{"current_steps": 510, "total_steps": 516, "loss": 0.1837, "lr": 4.125214789427734e-09, "epoch": 2.9651162790697674, "percentage": 98.84, "elapsed_time": "3:07:40", "remaining_time": "0:02:12"}
{"current_steps": 516, "total_steps": 516, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "3:10:55", "remaining_time": "0:00:00"}