Agent-STAR-SFT-7B / trainer_log.jsonl
xxwu's picture
Upload folder using huggingface_hub
552bd67 verified
{"current_steps": 1, "total_steps": 152, "loss": 0.5539, "lr": 0.0, "epoch": 0.02666666666666667, "percentage": 0.66, "elapsed_time": "0:01:05", "remaining_time": "2:45:16"}
{"current_steps": 2, "total_steps": 152, "loss": 0.596, "lr": 3.125e-07, "epoch": 0.05333333333333334, "percentage": 1.32, "elapsed_time": "0:01:47", "remaining_time": "2:13:48"}
{"current_steps": 3, "total_steps": 152, "loss": 0.5657, "lr": 6.25e-07, "epoch": 0.08, "percentage": 1.97, "elapsed_time": "0:02:38", "remaining_time": "2:11:01"}
{"current_steps": 4, "total_steps": 152, "loss": 0.6052, "lr": 9.375000000000001e-07, "epoch": 0.10666666666666667, "percentage": 2.63, "elapsed_time": "0:03:14", "remaining_time": "1:59:49"}
{"current_steps": 5, "total_steps": 152, "loss": 0.5724, "lr": 1.25e-06, "epoch": 0.13333333333333333, "percentage": 3.29, "elapsed_time": "0:04:02", "remaining_time": "1:58:47"}
{"current_steps": 6, "total_steps": 152, "loss": 0.5528, "lr": 1.5625e-06, "epoch": 0.16, "percentage": 3.95, "elapsed_time": "0:04:54", "remaining_time": "1:59:17"}
{"current_steps": 7, "total_steps": 152, "loss": 0.5296, "lr": 1.8750000000000003e-06, "epoch": 0.18666666666666668, "percentage": 4.61, "elapsed_time": "0:05:35", "remaining_time": "1:55:57"}
{"current_steps": 8, "total_steps": 152, "loss": 0.5367, "lr": 2.1875000000000002e-06, "epoch": 0.21333333333333335, "percentage": 5.26, "elapsed_time": "0:06:20", "remaining_time": "1:54:17"}
{"current_steps": 9, "total_steps": 152, "loss": 0.4852, "lr": 2.5e-06, "epoch": 0.24, "percentage": 5.92, "elapsed_time": "0:07:08", "remaining_time": "1:53:32"}
{"current_steps": 10, "total_steps": 152, "loss": 0.4687, "lr": 2.8125e-06, "epoch": 0.26666666666666666, "percentage": 6.58, "elapsed_time": "0:07:47", "remaining_time": "1:50:36"}
{"current_steps": 11, "total_steps": 152, "loss": 0.4737, "lr": 3.125e-06, "epoch": 0.29333333333333333, "percentage": 7.24, "elapsed_time": "0:08:25", "remaining_time": "1:47:58"}
{"current_steps": 12, "total_steps": 152, "loss": 0.4416, "lr": 3.4375e-06, "epoch": 0.32, "percentage": 7.89, "elapsed_time": "0:09:07", "remaining_time": "1:46:33"}
{"current_steps": 13, "total_steps": 152, "loss": 0.4033, "lr": 3.7500000000000005e-06, "epoch": 0.3466666666666667, "percentage": 8.55, "elapsed_time": "0:09:55", "remaining_time": "1:46:01"}
{"current_steps": 14, "total_steps": 152, "loss": 0.4057, "lr": 4.0625000000000005e-06, "epoch": 0.37333333333333335, "percentage": 9.21, "elapsed_time": "0:10:34", "remaining_time": "1:44:12"}
{"current_steps": 15, "total_steps": 152, "loss": 0.3857, "lr": 4.3750000000000005e-06, "epoch": 0.4, "percentage": 9.87, "elapsed_time": "0:11:20", "remaining_time": "1:43:32"}
{"current_steps": 16, "total_steps": 152, "loss": 0.3529, "lr": 4.6875000000000004e-06, "epoch": 0.4266666666666667, "percentage": 10.53, "elapsed_time": "0:12:03", "remaining_time": "1:42:28"}
{"current_steps": 17, "total_steps": 152, "loss": 0.3415, "lr": 5e-06, "epoch": 0.4533333333333333, "percentage": 11.18, "elapsed_time": "0:12:54", "remaining_time": "1:42:29"}
{"current_steps": 18, "total_steps": 152, "loss": 0.3598, "lr": 4.999333020279094e-06, "epoch": 0.48, "percentage": 11.84, "elapsed_time": "0:13:32", "remaining_time": "1:40:49"}
{"current_steps": 19, "total_steps": 152, "loss": 0.3343, "lr": 4.997332437005932e-06, "epoch": 0.5066666666666667, "percentage": 12.5, "elapsed_time": "0:14:13", "remaining_time": "1:39:34"}
{"current_steps": 20, "total_steps": 152, "loss": 0.3312, "lr": 4.993999317659293e-06, "epoch": 0.5333333333333333, "percentage": 13.16, "elapsed_time": "0:14:55", "remaining_time": "1:38:33"}
{"current_steps": 21, "total_steps": 152, "loss": 0.3239, "lr": 4.989335440737587e-06, "epoch": 0.56, "percentage": 13.82, "elapsed_time": "0:15:38", "remaining_time": "1:37:31"}
{"current_steps": 22, "total_steps": 152, "loss": 0.3215, "lr": 4.983343294809875e-06, "epoch": 0.5866666666666667, "percentage": 14.47, "elapsed_time": "0:16:16", "remaining_time": "1:36:10"}
{"current_steps": 23, "total_steps": 152, "loss": 0.2982, "lr": 4.976026077188013e-06, "epoch": 0.6133333333333333, "percentage": 15.13, "elapsed_time": "0:17:03", "remaining_time": "1:35:42"}
{"current_steps": 24, "total_steps": 152, "loss": 0.2975, "lr": 4.967387692220615e-06, "epoch": 0.64, "percentage": 15.79, "elapsed_time": "0:17:42", "remaining_time": "1:34:25"}
{"current_steps": 25, "total_steps": 152, "loss": 0.287, "lr": 4.957432749209755e-06, "epoch": 0.6666666666666666, "percentage": 16.45, "elapsed_time": "0:18:28", "remaining_time": "1:33:50"}
{"current_steps": 26, "total_steps": 152, "loss": 0.2837, "lr": 4.946166559951523e-06, "epoch": 0.6933333333333334, "percentage": 17.11, "elapsed_time": "0:19:10", "remaining_time": "1:32:54"}
{"current_steps": 27, "total_steps": 152, "loss": 0.2952, "lr": 4.933595135901733e-06, "epoch": 0.72, "percentage": 17.76, "elapsed_time": "0:19:46", "remaining_time": "1:31:33"}
{"current_steps": 28, "total_steps": 152, "loss": 0.2731, "lr": 4.919725184968307e-06, "epoch": 0.7466666666666667, "percentage": 18.42, "elapsed_time": "0:20:31", "remaining_time": "1:30:54"}
{"current_steps": 29, "total_steps": 152, "loss": 0.2994, "lr": 4.904564107932048e-06, "epoch": 0.7733333333333333, "percentage": 19.08, "elapsed_time": "0:21:17", "remaining_time": "1:30:17"}
{"current_steps": 30, "total_steps": 152, "loss": 0.2726, "lr": 4.888119994497701e-06, "epoch": 0.8, "percentage": 19.74, "elapsed_time": "0:22:00", "remaining_time": "1:29:29"}
{"current_steps": 31, "total_steps": 152, "loss": 0.2892, "lr": 4.870401618977415e-06, "epoch": 0.8266666666666667, "percentage": 20.39, "elapsed_time": "0:22:41", "remaining_time": "1:28:34"}
{"current_steps": 32, "total_steps": 152, "loss": 0.2935, "lr": 4.851418435608919e-06, "epoch": 0.8533333333333334, "percentage": 21.05, "elapsed_time": "0:23:17", "remaining_time": "1:27:22"}
{"current_steps": 33, "total_steps": 152, "loss": 0.2663, "lr": 4.83118057351089e-06, "epoch": 0.88, "percentage": 21.71, "elapsed_time": "0:23:58", "remaining_time": "1:26:26"}
{"current_steps": 34, "total_steps": 152, "loss": 0.2406, "lr": 4.809698831278217e-06, "epoch": 0.9066666666666666, "percentage": 22.37, "elapsed_time": "0:24:41", "remaining_time": "1:25:43"}
{"current_steps": 35, "total_steps": 152, "loss": 0.2674, "lr": 4.786984671220053e-06, "epoch": 0.9333333333333333, "percentage": 23.03, "elapsed_time": "0:25:26", "remaining_time": "1:25:03"}
{"current_steps": 36, "total_steps": 152, "loss": 0.2574, "lr": 4.763050213243705e-06, "epoch": 0.96, "percentage": 23.68, "elapsed_time": "0:26:07", "remaining_time": "1:24:11"}
{"current_steps": 37, "total_steps": 152, "loss": 0.2627, "lr": 4.737908228387656e-06, "epoch": 0.9866666666666667, "percentage": 24.34, "elapsed_time": "0:26:56", "remaining_time": "1:23:43"}
{"current_steps": 38, "total_steps": 152, "loss": 0.2676, "lr": 4.711572132007139e-06, "epoch": 1.0, "percentage": 25.0, "elapsed_time": "0:27:17", "remaining_time": "1:21:51"}
{"current_steps": 39, "total_steps": 152, "loss": 0.2356, "lr": 4.684055976615924e-06, "epoch": 1.0266666666666666, "percentage": 25.66, "elapsed_time": "0:28:02", "remaining_time": "1:21:15"}
{"current_steps": 40, "total_steps": 152, "loss": 0.2263, "lr": 4.655374444388127e-06, "epoch": 1.0533333333333332, "percentage": 26.32, "elapsed_time": "0:28:43", "remaining_time": "1:20:24"}
{"current_steps": 41, "total_steps": 152, "loss": 0.2413, "lr": 4.625542839324036e-06, "epoch": 1.08, "percentage": 26.97, "elapsed_time": "0:29:21", "remaining_time": "1:19:29"}
{"current_steps": 42, "total_steps": 152, "loss": 0.2387, "lr": 4.594577079084146e-06, "epoch": 1.1066666666666667, "percentage": 27.63, "elapsed_time": "0:30:03", "remaining_time": "1:18:42"}
{"current_steps": 43, "total_steps": 152, "loss": 0.2438, "lr": 4.562493686495756e-06, "epoch": 1.1333333333333333, "percentage": 28.29, "elapsed_time": "0:30:47", "remaining_time": "1:18:03"}
{"current_steps": 44, "total_steps": 152, "loss": 0.2304, "lr": 4.529309780736654e-06, "epoch": 1.16, "percentage": 28.95, "elapsed_time": "0:31:33", "remaining_time": "1:17:27"}
{"current_steps": 45, "total_steps": 152, "loss": 0.2266, "lr": 4.4950430682005995e-06, "epoch": 1.1866666666666668, "percentage": 29.61, "elapsed_time": "0:32:17", "remaining_time": "1:16:47"}
{"current_steps": 46, "total_steps": 152, "loss": 0.237, "lr": 4.459711833049485e-06, "epoch": 1.2133333333333334, "percentage": 30.26, "elapsed_time": "0:32:58", "remaining_time": "1:15:58"}
{"current_steps": 47, "total_steps": 152, "loss": 0.2336, "lr": 4.423334927457198e-06, "epoch": 1.24, "percentage": 30.92, "elapsed_time": "0:33:40", "remaining_time": "1:15:14"}
{"current_steps": 48, "total_steps": 152, "loss": 0.2245, "lr": 4.385931761550411e-06, "epoch": 1.2666666666666666, "percentage": 31.58, "elapsed_time": "0:34:21", "remaining_time": "1:14:25"}
{"current_steps": 49, "total_steps": 152, "loss": 0.224, "lr": 4.3475222930516484e-06, "epoch": 1.2933333333333334, "percentage": 32.24, "elapsed_time": "0:35:05", "remaining_time": "1:13:44"}
{"current_steps": 50, "total_steps": 152, "loss": 0.2125, "lr": 4.308127016630176e-06, "epoch": 1.32, "percentage": 32.89, "elapsed_time": "0:35:52", "remaining_time": "1:13:11"}
{"current_steps": 51, "total_steps": 152, "loss": 0.2251, "lr": 4.267766952966369e-06, "epoch": 1.3466666666666667, "percentage": 33.55, "elapsed_time": "0:36:41", "remaining_time": "1:12:40"}
{"current_steps": 52, "total_steps": 152, "loss": 0.2252, "lr": 4.226463637535429e-06, "epoch": 1.3733333333333333, "percentage": 34.21, "elapsed_time": "0:37:20", "remaining_time": "1:11:48"}
{"current_steps": 53, "total_steps": 152, "loss": 0.2299, "lr": 4.184239109116393e-06, "epoch": 1.4, "percentage": 34.87, "elapsed_time": "0:38:04", "remaining_time": "1:11:06"}
{"current_steps": 54, "total_steps": 152, "loss": 0.2038, "lr": 4.141115898032607e-06, "epoch": 1.4266666666666667, "percentage": 35.53, "elapsed_time": "0:38:49", "remaining_time": "1:10:27"}
{"current_steps": 55, "total_steps": 152, "loss": 0.2065, "lr": 4.097117014129903e-06, "epoch": 1.4533333333333334, "percentage": 36.18, "elapsed_time": "0:39:37", "remaining_time": "1:09:53"}
{"current_steps": 56, "total_steps": 152, "loss": 0.2023, "lr": 4.052265934498929e-06, "epoch": 1.48, "percentage": 36.84, "elapsed_time": "0:40:24", "remaining_time": "1:09:15"}
{"current_steps": 57, "total_steps": 152, "loss": 0.2129, "lr": 4.006586590948141e-06, "epoch": 1.5066666666666668, "percentage": 37.5, "elapsed_time": "0:41:06", "remaining_time": "1:08:31"}
{"current_steps": 58, "total_steps": 152, "loss": 0.2322, "lr": 3.960103357234192e-06, "epoch": 1.5333333333333332, "percentage": 38.16, "elapsed_time": "0:41:53", "remaining_time": "1:07:54"}
{"current_steps": 59, "total_steps": 152, "loss": 0.2167, "lr": 3.91284103605648e-06, "epoch": 1.56, "percentage": 38.82, "elapsed_time": "0:42:36", "remaining_time": "1:07:09"}
{"current_steps": 60, "total_steps": 152, "loss": 0.2144, "lr": 3.864824845822837e-06, "epoch": 1.5866666666666667, "percentage": 39.47, "elapsed_time": "0:43:19", "remaining_time": "1:06:25"}
{"current_steps": 61, "total_steps": 152, "loss": 0.2085, "lr": 3.81608040719339e-06, "epoch": 1.6133333333333333, "percentage": 40.13, "elapsed_time": "0:44:00", "remaining_time": "1:05:38"}
{"current_steps": 62, "total_steps": 152, "loss": 0.2161, "lr": 3.7666337294097987e-06, "epoch": 1.6400000000000001, "percentage": 40.79, "elapsed_time": "0:44:42", "remaining_time": "1:04:54"}
{"current_steps": 63, "total_steps": 152, "loss": 0.2045, "lr": 3.7165111964171407e-06, "epoch": 1.6666666666666665, "percentage": 41.45, "elapsed_time": "0:45:24", "remaining_time": "1:04:08"}
{"current_steps": 64, "total_steps": 152, "loss": 0.2048, "lr": 3.66573955278587e-06, "epoch": 1.6933333333333334, "percentage": 42.11, "elapsed_time": "0:46:05", "remaining_time": "1:03:22"}
{"current_steps": 65, "total_steps": 152, "loss": 0.216, "lr": 3.6143458894413463e-06, "epoch": 1.72, "percentage": 42.76, "elapsed_time": "0:46:51", "remaining_time": "1:02:43"}
{"current_steps": 66, "total_steps": 152, "loss": 0.2145, "lr": 3.5623576292085555e-06, "epoch": 1.7466666666666666, "percentage": 43.42, "elapsed_time": "0:47:30", "remaining_time": "1:01:54"}
{"current_steps": 67, "total_steps": 152, "loss": 0.2059, "lr": 3.5098025121797375e-06, "epoch": 1.7733333333333334, "percentage": 44.08, "elapsed_time": "0:48:20", "remaining_time": "1:01:19"}
{"current_steps": 68, "total_steps": 152, "loss": 0.1993, "lr": 3.4567085809127247e-06, "epoch": 1.8, "percentage": 44.74, "elapsed_time": "0:49:10", "remaining_time": "1:00:44"}
{"current_steps": 69, "total_steps": 152, "loss": 0.2018, "lr": 3.403104165467883e-06, "epoch": 1.8266666666666667, "percentage": 45.39, "elapsed_time": "0:50:00", "remaining_time": "1:00:09"}
{"current_steps": 70, "total_steps": 152, "loss": 0.2033, "lr": 3.3490178682916534e-06, "epoch": 1.8533333333333335, "percentage": 46.05, "elapsed_time": "0:50:45", "remaining_time": "0:59:27"}
{"current_steps": 71, "total_steps": 152, "loss": 0.222, "lr": 3.2944785489547544e-06, "epoch": 1.88, "percentage": 46.71, "elapsed_time": "0:51:26", "remaining_time": "0:58:40"}
{"current_steps": 72, "total_steps": 152, "loss": 0.2059, "lr": 3.2395153087531767e-06, "epoch": 1.9066666666666667, "percentage": 47.37, "elapsed_time": "0:52:09", "remaining_time": "0:57:57"}
{"current_steps": 73, "total_steps": 152, "loss": 0.1999, "lr": 3.184157475180208e-06, "epoch": 1.9333333333333333, "percentage": 48.03, "elapsed_time": "0:52:49", "remaining_time": "0:57:09"}
{"current_steps": 74, "total_steps": 152, "loss": 0.2032, "lr": 3.1284345862777572e-06, "epoch": 1.96, "percentage": 48.68, "elapsed_time": "0:53:34", "remaining_time": "0:56:27"}
{"current_steps": 75, "total_steps": 152, "loss": 0.1966, "lr": 3.0723763748753354e-06, "epoch": 1.9866666666666668, "percentage": 49.34, "elapsed_time": "0:54:23", "remaining_time": "0:55:50"}
{"current_steps": 76, "total_steps": 152, "loss": 0.2035, "lr": 3.0160127527250993e-06, "epoch": 2.0, "percentage": 50.0, "elapsed_time": "0:54:45", "remaining_time": "0:54:45"}
{"current_steps": 77, "total_steps": 152, "loss": 0.1812, "lr": 2.9593737945414264e-06, "epoch": 2.026666666666667, "percentage": 50.66, "elapsed_time": "0:55:23", "remaining_time": "0:53:56"}
{"current_steps": 78, "total_steps": 152, "loss": 0.1755, "lr": 2.9024897219535326e-06, "epoch": 2.0533333333333332, "percentage": 51.32, "elapsed_time": "0:56:08", "remaining_time": "0:53:15"}
{"current_steps": 79, "total_steps": 152, "loss": 0.1793, "lr": 2.845390887379706e-06, "epoch": 2.08, "percentage": 51.97, "elapsed_time": "0:56:53", "remaining_time": "0:52:34"}
{"current_steps": 80, "total_steps": 152, "loss": 0.1739, "lr": 2.7881077578317445e-06, "epoch": 2.1066666666666665, "percentage": 52.63, "elapsed_time": "0:57:47", "remaining_time": "0:52:01"}
{"current_steps": 81, "total_steps": 152, "loss": 0.1893, "lr": 2.730670898658255e-06, "epoch": 2.1333333333333333, "percentage": 53.29, "elapsed_time": "0:58:30", "remaining_time": "0:51:17"}
{"current_steps": 82, "total_steps": 152, "loss": 0.1746, "lr": 2.6731109572354795e-06, "epoch": 2.16, "percentage": 53.95, "elapsed_time": "0:59:14", "remaining_time": "0:50:33"}
{"current_steps": 83, "total_steps": 152, "loss": 0.1921, "lr": 2.6154586466143495e-06, "epoch": 2.1866666666666665, "percentage": 54.61, "elapsed_time": "0:59:49", "remaining_time": "0:49:44"}
{"current_steps": 84, "total_steps": 152, "loss": 0.1909, "lr": 2.557744729132503e-06, "epoch": 2.2133333333333334, "percentage": 55.26, "elapsed_time": "1:00:31", "remaining_time": "0:48:59"}
{"current_steps": 85, "total_steps": 152, "loss": 0.1776, "lr": 2.5e-06, "epoch": 2.24, "percentage": 55.92, "elapsed_time": "1:01:18", "remaining_time": "0:48:19"}
{"current_steps": 86, "total_steps": 152, "loss": 0.1724, "lr": 2.4422552708674977e-06, "epoch": 2.2666666666666666, "percentage": 56.58, "elapsed_time": "1:02:07", "remaining_time": "0:47:40"}
{"current_steps": 87, "total_steps": 152, "loss": 0.1942, "lr": 2.3845413533856517e-06, "epoch": 2.2933333333333334, "percentage": 57.24, "elapsed_time": "1:02:50", "remaining_time": "0:46:57"}
{"current_steps": 88, "total_steps": 152, "loss": 0.1838, "lr": 2.3268890427645213e-06, "epoch": 2.32, "percentage": 57.89, "elapsed_time": "1:03:33", "remaining_time": "0:46:13"}
{"current_steps": 89, "total_steps": 152, "loss": 0.171, "lr": 2.269329101341745e-06, "epoch": 2.3466666666666667, "percentage": 58.55, "elapsed_time": "1:04:19", "remaining_time": "0:45:31"}
{"current_steps": 90, "total_steps": 152, "loss": 0.1811, "lr": 2.2118922421682563e-06, "epoch": 2.3733333333333335, "percentage": 59.21, "elapsed_time": "1:05:18", "remaining_time": "0:44:59"}
{"current_steps": 91, "total_steps": 152, "loss": 0.1788, "lr": 2.1546091126202955e-06, "epoch": 2.4, "percentage": 59.87, "elapsed_time": "1:06:02", "remaining_time": "0:44:16"}
{"current_steps": 92, "total_steps": 152, "loss": 0.1844, "lr": 2.0975102780464674e-06, "epoch": 2.4266666666666667, "percentage": 60.53, "elapsed_time": "1:06:48", "remaining_time": "0:43:34"}
{"current_steps": 93, "total_steps": 152, "loss": 0.1832, "lr": 2.040626205458574e-06, "epoch": 2.453333333333333, "percentage": 61.18, "elapsed_time": "1:07:32", "remaining_time": "0:42:51"}
{"current_steps": 94, "total_steps": 152, "loss": 0.1834, "lr": 1.9839872472749016e-06, "epoch": 2.48, "percentage": 61.84, "elapsed_time": "1:08:25", "remaining_time": "0:42:12"}
{"current_steps": 95, "total_steps": 152, "loss": 0.1863, "lr": 1.9276236251246655e-06, "epoch": 2.506666666666667, "percentage": 62.5, "elapsed_time": "1:09:04", "remaining_time": "0:41:26"}
{"current_steps": 96, "total_steps": 152, "loss": 0.1843, "lr": 1.8715654137222434e-06, "epoch": 2.533333333333333, "percentage": 63.16, "elapsed_time": "1:09:44", "remaining_time": "0:40:41"}
{"current_steps": 97, "total_steps": 152, "loss": 0.1765, "lr": 1.8158425248197931e-06, "epoch": 2.56, "percentage": 63.82, "elapsed_time": "1:10:30", "remaining_time": "0:39:58"}
{"current_steps": 98, "total_steps": 152, "loss": 0.1683, "lr": 1.7604846912468243e-06, "epoch": 2.586666666666667, "percentage": 64.47, "elapsed_time": "1:11:13", "remaining_time": "0:39:14"}
{"current_steps": 99, "total_steps": 152, "loss": 0.1763, "lr": 1.7055214510452462e-06, "epoch": 2.6133333333333333, "percentage": 65.13, "elapsed_time": "1:12:04", "remaining_time": "0:38:35"}
{"current_steps": 100, "total_steps": 152, "loss": 0.1872, "lr": 1.6509821317083466e-06, "epoch": 2.64, "percentage": 65.79, "elapsed_time": "1:12:43", "remaining_time": "0:37:49"}
{"current_steps": 101, "total_steps": 152, "loss": 0.1844, "lr": 1.5968958345321178e-06, "epoch": 2.6666666666666665, "percentage": 66.45, "elapsed_time": "1:13:33", "remaining_time": "0:37:08"}
{"current_steps": 102, "total_steps": 152, "loss": 0.1791, "lr": 1.5432914190872757e-06, "epoch": 2.6933333333333334, "percentage": 67.11, "elapsed_time": "1:14:17", "remaining_time": "0:36:25"}
{"current_steps": 103, "total_steps": 152, "loss": 0.184, "lr": 1.490197487820263e-06, "epoch": 2.7199999999999998, "percentage": 67.76, "elapsed_time": "1:15:00", "remaining_time": "0:35:40"}
{"current_steps": 104, "total_steps": 152, "loss": 0.1808, "lr": 1.4376423707914462e-06, "epoch": 2.7466666666666666, "percentage": 68.42, "elapsed_time": "1:15:43", "remaining_time": "0:34:57"}
{"current_steps": 105, "total_steps": 152, "loss": 0.168, "lr": 1.3856541105586545e-06, "epoch": 2.7733333333333334, "percentage": 69.08, "elapsed_time": "1:16:25", "remaining_time": "0:34:12"}
{"current_steps": 106, "total_steps": 152, "loss": 0.1714, "lr": 1.3342604472141296e-06, "epoch": 2.8, "percentage": 69.74, "elapsed_time": "1:17:05", "remaining_time": "0:33:27"}
{"current_steps": 107, "total_steps": 152, "loss": 0.1784, "lr": 1.2834888035828597e-06, "epoch": 2.8266666666666667, "percentage": 70.39, "elapsed_time": "1:17:54", "remaining_time": "0:32:46"}
{"current_steps": 108, "total_steps": 152, "loss": 0.1672, "lr": 1.233366270590202e-06, "epoch": 2.8533333333333335, "percentage": 71.05, "elapsed_time": "1:18:37", "remaining_time": "0:32:01"}
{"current_steps": 109, "total_steps": 152, "loss": 0.1876, "lr": 1.1839195928066101e-06, "epoch": 2.88, "percentage": 71.71, "elapsed_time": "1:19:16", "remaining_time": "0:31:16"}
{"current_steps": 110, "total_steps": 152, "loss": 0.1884, "lr": 1.1351751541771644e-06, "epoch": 2.9066666666666667, "percentage": 72.37, "elapsed_time": "1:19:50", "remaining_time": "0:30:29"}
{"current_steps": 111, "total_steps": 152, "loss": 0.1747, "lr": 1.0871589639435204e-06, "epoch": 2.9333333333333336, "percentage": 73.03, "elapsed_time": "1:20:37", "remaining_time": "0:29:46"}
{"current_steps": 112, "total_steps": 152, "loss": 0.1715, "lr": 1.0398966427658091e-06, "epoch": 2.96, "percentage": 73.68, "elapsed_time": "1:21:15", "remaining_time": "0:29:01"}
{"current_steps": 113, "total_steps": 152, "loss": 0.1795, "lr": 9.934134090518593e-07, "epoch": 2.986666666666667, "percentage": 74.34, "elapsed_time": "1:22:01", "remaining_time": "0:28:18"}
{"current_steps": 114, "total_steps": 152, "loss": 0.1818, "lr": 9.477340655010717e-07, "epoch": 3.0, "percentage": 75.0, "elapsed_time": "1:22:22", "remaining_time": "0:27:27"}
{"current_steps": 115, "total_steps": 152, "loss": 0.1533, "lr": 9.028829858700974e-07, "epoch": 3.026666666666667, "percentage": 75.66, "elapsed_time": "1:23:16", "remaining_time": "0:26:47"}
{"current_steps": 116, "total_steps": 152, "loss": 0.1629, "lr": 8.588841019673938e-07, "epoch": 3.0533333333333332, "percentage": 76.32, "elapsed_time": "1:24:01", "remaining_time": "0:26:04"}
{"current_steps": 117, "total_steps": 152, "loss": 0.1608, "lr": 8.157608908836071e-07, "epoch": 3.08, "percentage": 76.97, "elapsed_time": "1:24:46", "remaining_time": "0:25:21"}
{"current_steps": 118, "total_steps": 152, "loss": 0.1683, "lr": 7.735363624645712e-07, "epoch": 3.1066666666666665, "percentage": 77.63, "elapsed_time": "1:25:29", "remaining_time": "0:24:37"}
{"current_steps": 119, "total_steps": 152, "loss": 0.1672, "lr": 7.322330470336314e-07, "epoch": 3.1333333333333333, "percentage": 78.29, "elapsed_time": "1:26:05", "remaining_time": "0:23:52"}
{"current_steps": 120, "total_steps": 152, "loss": 0.1561, "lr": 6.91872983369826e-07, "epoch": 3.16, "percentage": 78.95, "elapsed_time": "1:26:49", "remaining_time": "0:23:09"}
{"current_steps": 121, "total_steps": 152, "loss": 0.1567, "lr": 6.524777069483526e-07, "epoch": 3.1866666666666665, "percentage": 79.61, "elapsed_time": "1:27:29", "remaining_time": "0:22:24"}
{"current_steps": 122, "total_steps": 152, "loss": 0.163, "lr": 6.140682384495902e-07, "epoch": 3.2133333333333334, "percentage": 80.26, "elapsed_time": "1:28:19", "remaining_time": "0:21:43"}
{"current_steps": 123, "total_steps": 152, "loss": 0.1525, "lr": 5.766650725428027e-07, "epoch": 3.24, "percentage": 80.92, "elapsed_time": "1:29:06", "remaining_time": "0:21:00"}
{"current_steps": 124, "total_steps": 152, "loss": 0.1575, "lr": 5.402881669505164e-07, "epoch": 3.2666666666666666, "percentage": 81.58, "elapsed_time": "1:29:51", "remaining_time": "0:20:17"}
{"current_steps": 125, "total_steps": 152, "loss": 0.1736, "lr": 5.049569317994013e-07, "epoch": 3.2933333333333334, "percentage": 82.24, "elapsed_time": "1:30:36", "remaining_time": "0:19:34"}
{"current_steps": 126, "total_steps": 152, "loss": 0.1681, "lr": 4.70690219263347e-07, "epoch": 3.32, "percentage": 82.89, "elapsed_time": "1:31:20", "remaining_time": "0:18:50"}
{"current_steps": 127, "total_steps": 152, "loss": 0.1601, "lr": 4.3750631350424456e-07, "epoch": 3.3466666666666667, "percentage": 83.55, "elapsed_time": "1:32:04", "remaining_time": "0:18:07"}
{"current_steps": 128, "total_steps": 152, "loss": 0.1597, "lr": 4.0542292091585447e-07, "epoch": 3.3733333333333335, "percentage": 84.21, "elapsed_time": "1:32:49", "remaining_time": "0:17:24"}
{"current_steps": 129, "total_steps": 152, "loss": 0.1645, "lr": 3.7445716067596506e-07, "epoch": 3.4, "percentage": 84.87, "elapsed_time": "1:33:26", "remaining_time": "0:16:39"}
{"current_steps": 130, "total_steps": 152, "loss": 0.1682, "lr": 3.446255556118736e-07, "epoch": 3.4266666666666667, "percentage": 85.53, "elapsed_time": "1:34:18", "remaining_time": "0:15:57"}
{"current_steps": 131, "total_steps": 152, "loss": 0.1584, "lr": 3.1594402338407633e-07, "epoch": 3.453333333333333, "percentage": 86.18, "elapsed_time": "1:35:05", "remaining_time": "0:15:14"}
{"current_steps": 132, "total_steps": 152, "loss": 0.1552, "lr": 2.8842786799286204e-07, "epoch": 3.48, "percentage": 86.84, "elapsed_time": "1:35:45", "remaining_time": "0:14:30"}
{"current_steps": 133, "total_steps": 152, "loss": 0.1689, "lr": 2.620917716123444e-07, "epoch": 3.506666666666667, "percentage": 87.5, "elapsed_time": "1:36:39", "remaining_time": "0:13:48"}
{"current_steps": 134, "total_steps": 152, "loss": 0.1546, "lr": 2.3694978675629476e-07, "epoch": 3.533333333333333, "percentage": 88.16, "elapsed_time": "1:37:16", "remaining_time": "0:13:04"}
{"current_steps": 135, "total_steps": 152, "loss": 0.1573, "lr": 2.1301532877994747e-07, "epoch": 3.56, "percentage": 88.82, "elapsed_time": "1:38:03", "remaining_time": "0:12:20"}
{"current_steps": 136, "total_steps": 152, "loss": 0.1667, "lr": 1.9030116872178317e-07, "epoch": 3.586666666666667, "percentage": 89.47, "elapsed_time": "1:38:42", "remaining_time": "0:11:36"}
{"current_steps": 137, "total_steps": 152, "loss": 0.1715, "lr": 1.6881942648911077e-07, "epoch": 3.6133333333333333, "percentage": 90.13, "elapsed_time": "1:39:23", "remaining_time": "0:10:52"}
{"current_steps": 138, "total_steps": 152, "loss": 0.1635, "lr": 1.4858156439108097e-07, "epoch": 3.64, "percentage": 90.79, "elapsed_time": "1:40:03", "remaining_time": "0:10:09"}
{"current_steps": 139, "total_steps": 152, "loss": 0.1622, "lr": 1.2959838102258537e-07, "epoch": 3.6666666666666665, "percentage": 91.45, "elapsed_time": "1:40:46", "remaining_time": "0:09:25"}
{"current_steps": 140, "total_steps": 152, "loss": 0.1608, "lr": 1.1188000550230005e-07, "epoch": 3.6933333333333334, "percentage": 92.11, "elapsed_time": "1:41:31", "remaining_time": "0:08:42"}
{"current_steps": 141, "total_steps": 152, "loss": 0.1596, "lr": 9.54358920679524e-08, "epoch": 3.7199999999999998, "percentage": 92.76, "elapsed_time": "1:42:16", "remaining_time": "0:07:58"}
{"current_steps": 142, "total_steps": 152, "loss": 0.1734, "lr": 8.027481503169371e-08, "epoch": 3.7466666666666666, "percentage": 93.42, "elapsed_time": "1:43:02", "remaining_time": "0:07:15"}
{"current_steps": 143, "total_steps": 152, "loss": 0.1621, "lr": 6.640486409826785e-08, "epoch": 3.7733333333333334, "percentage": 94.08, "elapsed_time": "1:43:44", "remaining_time": "0:06:31"}
{"current_steps": 144, "total_steps": 152, "loss": 0.1588, "lr": 5.383344004847774e-08, "epoch": 3.8, "percentage": 94.74, "elapsed_time": "1:44:30", "remaining_time": "0:05:48"}
{"current_steps": 145, "total_steps": 152, "loss": 0.1711, "lr": 4.256725079024554e-08, "epoch": 3.8266666666666667, "percentage": 95.39, "elapsed_time": "1:45:15", "remaining_time": "0:05:04"}
{"current_steps": 146, "total_steps": 152, "loss": 0.1681, "lr": 3.261230777938607e-08, "epoch": 3.8533333333333335, "percentage": 96.05, "elapsed_time": "1:46:06", "remaining_time": "0:04:21"}
{"current_steps": 147, "total_steps": 152, "loss": 0.16, "lr": 2.3973922811987295e-08, "epoch": 3.88, "percentage": 96.71, "elapsed_time": "1:46:49", "remaining_time": "0:03:38"}
{"current_steps": 148, "total_steps": 152, "loss": 0.171, "lr": 1.6656705190125078e-08, "epoch": 3.9066666666666667, "percentage": 97.37, "elapsed_time": "1:47:34", "remaining_time": "0:02:54"}
{"current_steps": 149, "total_steps": 152, "loss": 0.1521, "lr": 1.0664559262413831e-08, "epoch": 3.9333333333333336, "percentage": 98.03, "elapsed_time": "1:48:26", "remaining_time": "0:02:11"}
{"current_steps": 150, "total_steps": 152, "loss": 0.1625, "lr": 6.00068234070772e-09, "epoch": 3.96, "percentage": 98.68, "elapsed_time": "1:49:07", "remaining_time": "0:01:27"}
{"current_steps": 151, "total_steps": 152, "loss": 0.1631, "lr": 2.6675629940689508e-09, "epoch": 3.986666666666667, "percentage": 99.34, "elapsed_time": "1:49:53", "remaining_time": "0:00:43"}
{"current_steps": 152, "total_steps": 152, "loss": 0.1455, "lr": 6.669797209069018e-10, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "1:50:13", "remaining_time": "0:00:00"}
{"current_steps": 152, "total_steps": 152, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "1:50:59", "remaining_time": "0:00:00"}