Files
OpenThoughts3-random-groups…/trainer_log.jsonl
ModelHub XC 665c0870aa 初始化项目,由ModelHub XC社区提供模型
Model: cjiao/OpenThoughts3-random-groups-openthinker3-1.5B-checkpoint-375-80
Source: Original Platform
2026-04-28 10:59:02 +08:00

183 lines
32 KiB
JSON

{"current_steps": 1, "total_steps": 160, "loss": 1.2401, "lr": 0.00015998457923856519, "epoch": 0.0125, "percentage": 0.62, "elapsed_time": "0:01:36", "remaining_time": "4:16:43"}
{"current_steps": 2, "total_steps": 160, "loss": 4.0648, "lr": 0.00015993832289925785, "epoch": 0.025, "percentage": 1.25, "elapsed_time": "0:03:12", "remaining_time": "4:12:53"}
{"current_steps": 3, "total_steps": 160, "loss": 2.7044, "lr": 0.0001598612488147773, "epoch": 0.0375, "percentage": 1.88, "elapsed_time": "0:04:46", "remaining_time": "4:09:58"}
{"current_steps": 4, "total_steps": 160, "loss": 1.994, "lr": 0.00015975338669865026, "epoch": 0.05, "percentage": 2.5, "elapsed_time": "0:06:22", "remaining_time": "4:08:21"}
{"current_steps": 5, "total_steps": 160, "loss": 2.1426, "lr": 0.00015961477813377576, "epoch": 0.0625, "percentage": 3.12, "elapsed_time": "0:07:56", "remaining_time": "4:06:13"}
{"current_steps": 6, "total_steps": 160, "loss": 1.7254, "lr": 0.00015944547655639412, "epoch": 0.075, "percentage": 3.75, "elapsed_time": "0:09:32", "remaining_time": "4:04:54"}
{"current_steps": 7, "total_steps": 160, "loss": 1.5187, "lr": 0.00015924554723548617, "epoch": 0.0875, "percentage": 4.38, "elapsed_time": "0:11:09", "remaining_time": "4:03:43"}
{"current_steps": 8, "total_steps": 160, "loss": 1.5405, "lr": 0.00015901506724761103, "epoch": 0.1, "percentage": 5.0, "elapsed_time": "0:12:45", "remaining_time": "4:02:18"}
{"current_steps": 9, "total_steps": 160, "loss": 1.4493, "lr": 0.00015875412544719134, "epoch": 0.1125, "percentage": 5.62, "elapsed_time": "0:14:20", "remaining_time": "4:00:40"}
{"current_steps": 10, "total_steps": 160, "loss": 1.4103, "lr": 0.00015846282243225845, "epoch": 0.125, "percentage": 6.25, "elapsed_time": "0:15:56", "remaining_time": "3:59:09"}
{"current_steps": 11, "total_steps": 160, "loss": 1.3507, "lr": 0.0001581412705056698, "epoch": 0.1375, "percentage": 6.88, "elapsed_time": "0:17:30", "remaining_time": "3:57:11"}
{"current_steps": 12, "total_steps": 160, "loss": 1.3, "lr": 0.00015778959363181415, "epoch": 0.15, "percentage": 7.5, "elapsed_time": "0:19:06", "remaining_time": "3:55:37"}
{"current_steps": 13, "total_steps": 160, "loss": 1.2974, "lr": 0.0001574079273888208, "epoch": 0.1625, "percentage": 8.12, "elapsed_time": "0:20:41", "remaining_time": "3:53:59"}
{"current_steps": 14, "total_steps": 160, "loss": 1.2635, "lr": 0.00015699641891629178, "epoch": 0.175, "percentage": 8.75, "elapsed_time": "0:22:16", "remaining_time": "3:52:16"}
{"current_steps": 15, "total_steps": 160, "loss": 1.2119, "lr": 0.00015655522685857672, "epoch": 0.1875, "percentage": 9.38, "elapsed_time": "0:23:52", "remaining_time": "3:50:46"}
{"current_steps": 16, "total_steps": 160, "loss": 1.2337, "lr": 0.0001560845213036123, "epoch": 0.2, "percentage": 10.0, "elapsed_time": "0:25:27", "remaining_time": "3:49:07"}
{"current_steps": 17, "total_steps": 160, "loss": 1.1884, "lr": 0.00015558448371735025, "epoch": 0.2125, "percentage": 10.62, "elapsed_time": "0:27:04", "remaining_time": "3:47:45"}
{"current_steps": 18, "total_steps": 160, "loss": 1.17, "lr": 0.00015505530687379875, "epoch": 0.225, "percentage": 11.25, "elapsed_time": "0:28:40", "remaining_time": "3:46:10"}
{"current_steps": 19, "total_steps": 160, "loss": 1.1879, "lr": 0.00015449719478070428, "epoch": 0.2375, "percentage": 11.88, "elapsed_time": "0:30:15", "remaining_time": "3:44:32"}
{"current_steps": 20, "total_steps": 160, "loss": 1.1767, "lr": 0.00015391036260090294, "epoch": 0.25, "percentage": 12.5, "elapsed_time": "0:31:49", "remaining_time": "3:42:48"}
{"current_steps": 21, "total_steps": 160, "loss": 1.1726, "lr": 0.0001532950365693709, "epoch": 0.2625, "percentage": 13.12, "elapsed_time": "0:33:24", "remaining_time": "3:41:10"}
{"current_steps": 22, "total_steps": 160, "loss": 1.163, "lr": 0.00015265145390600652, "epoch": 0.275, "percentage": 13.75, "elapsed_time": "0:34:59", "remaining_time": "3:39:32"}
{"current_steps": 23, "total_steps": 160, "loss": 1.1839, "lr": 0.00015197986272417774, "epoch": 0.2875, "percentage": 14.37, "elapsed_time": "0:36:36", "remaining_time": "3:38:03"}
{"current_steps": 24, "total_steps": 160, "loss": 1.1642, "lr": 0.00015128052193506944, "epoch": 0.3, "percentage": 15.0, "elapsed_time": "0:38:11", "remaining_time": "3:36:26"}
{"current_steps": 25, "total_steps": 160, "loss": 1.1495, "lr": 0.0001505537011478684, "epoch": 0.3125, "percentage": 15.62, "elapsed_time": "0:39:48", "remaining_time": "3:34:57"}
{"current_steps": 26, "total_steps": 160, "loss": 1.1257, "lr": 0.0001497996805658238, "epoch": 0.325, "percentage": 16.25, "elapsed_time": "0:41:23", "remaining_time": "3:33:18"}
{"current_steps": 27, "total_steps": 160, "loss": 1.1463, "lr": 0.00014901875087822337, "epoch": 0.3375, "percentage": 16.88, "elapsed_time": "0:42:58", "remaining_time": "3:31:43"}
{"current_steps": 28, "total_steps": 160, "loss": 1.141, "lr": 0.0001482112131483274, "epoch": 0.35, "percentage": 17.5, "elapsed_time": "0:44:35", "remaining_time": "3:30:11"}
{"current_steps": 29, "total_steps": 160, "loss": 1.1414, "lr": 0.00014737737869730292, "epoch": 0.3625, "percentage": 18.12, "elapsed_time": "0:46:12", "remaining_time": "3:28:43"}
{"current_steps": 30, "total_steps": 160, "loss": 1.1352, "lr": 0.00014651756898420365, "epoch": 0.375, "percentage": 18.75, "elapsed_time": "0:47:47", "remaining_time": "3:27:07"}
{"current_steps": 31, "total_steps": 160, "loss": 1.1167, "lr": 0.0001456321154820411, "epoch": 0.3875, "percentage": 19.38, "elapsed_time": "0:49:24", "remaining_time": "3:25:34"}
{"current_steps": 32, "total_steps": 160, "loss": 1.113, "lr": 0.00014472135954999581, "epoch": 0.4, "percentage": 20.0, "elapsed_time": "0:50:59", "remaining_time": "3:23:56"}
{"current_steps": 33, "total_steps": 160, "loss": 1.1201, "lr": 0.00014378565230181657, "epoch": 0.4125, "percentage": 20.62, "elapsed_time": "0:52:34", "remaining_time": "3:22:21"}
{"current_steps": 34, "total_steps": 160, "loss": 1.1303, "lr": 0.0001428253544704596, "epoch": 0.425, "percentage": 21.25, "elapsed_time": "0:54:09", "remaining_time": "3:20:41"}
{"current_steps": 35, "total_steps": 160, "loss": 1.135, "lr": 0.00014184083626901897, "epoch": 0.4375, "percentage": 21.88, "elapsed_time": "0:55:44", "remaining_time": "3:19:04"}
{"current_steps": 36, "total_steps": 160, "loss": 1.1413, "lr": 0.0001408324772480025, "epoch": 0.45, "percentage": 22.5, "elapsed_time": "0:57:20", "remaining_time": "3:17:30"}
{"current_steps": 37, "total_steps": 160, "loss": 1.1406, "lr": 0.00013980066614900776, "epoch": 0.4625, "percentage": 23.12, "elapsed_time": "0:58:56", "remaining_time": "3:15:55"}
{"current_steps": 38, "total_steps": 160, "loss": 1.1421, "lr": 0.00013874580075485485, "epoch": 0.475, "percentage": 23.75, "elapsed_time": "1:00:32", "remaining_time": "3:14:21"}
{"current_steps": 39, "total_steps": 160, "loss": 1.1298, "lr": 0.00013766828773623352, "epoch": 0.4875, "percentage": 24.38, "elapsed_time": "1:02:09", "remaining_time": "3:12:51"}
{"current_steps": 40, "total_steps": 160, "loss": 1.1052, "lr": 0.00013656854249492382, "epoch": 0.5, "percentage": 25.0, "elapsed_time": "1:03:45", "remaining_time": "3:11:15"}
{"current_steps": 41, "total_steps": 160, "loss": 1.1124, "lr": 0.0001354469890036509, "epoch": 0.5125, "percentage": 25.62, "elapsed_time": "1:05:49", "remaining_time": "3:11:04"}
{"current_steps": 42, "total_steps": 160, "loss": 1.1164, "lr": 0.00013430405964263536, "epoch": 0.525, "percentage": 26.25, "elapsed_time": "1:07:24", "remaining_time": "3:09:23"}
{"current_steps": 43, "total_steps": 160, "loss": 1.1379, "lr": 0.00013314019503290255, "epoch": 0.5375, "percentage": 26.88, "elapsed_time": "1:08:59", "remaining_time": "3:07:44"}
{"current_steps": 44, "total_steps": 160, "loss": 1.0963, "lr": 0.00013195584386641469, "epoch": 0.55, "percentage": 27.5, "elapsed_time": "1:10:36", "remaining_time": "3:06:09"}
{"current_steps": 45, "total_steps": 160, "loss": 1.1089, "lr": 0.00013075146273309164, "epoch": 0.5625, "percentage": 28.12, "elapsed_time": "1:12:11", "remaining_time": "3:04:29"}
{"current_steps": 46, "total_steps": 160, "loss": 1.1225, "lr": 0.00012952751594478675, "epoch": 0.575, "percentage": 28.75, "elapsed_time": "1:13:48", "remaining_time": "3:02:54"}
{"current_steps": 47, "total_steps": 160, "loss": 1.1035, "lr": 0.0001282844753562857, "epoch": 0.5875, "percentage": 29.38, "elapsed_time": "1:15:22", "remaining_time": "3:01:13"}
{"current_steps": 48, "total_steps": 160, "loss": 1.0713, "lr": 0.00012702282018339786, "epoch": 0.6, "percentage": 30.0, "elapsed_time": "1:16:57", "remaining_time": "2:59:34"}
{"current_steps": 49, "total_steps": 160, "loss": 1.1233, "lr": 0.00012574303681820898, "epoch": 0.6125, "percentage": 30.63, "elapsed_time": "1:18:33", "remaining_time": "2:57:57"}
{"current_steps": 50, "total_steps": 160, "loss": 1.0726, "lr": 0.0001244456186415682, "epoch": 0.625, "percentage": 31.25, "elapsed_time": "1:20:08", "remaining_time": "2:56:19"}
{"current_steps": 51, "total_steps": 160, "loss": 1.0856, "lr": 0.00012313106583288004, "epoch": 0.6375, "percentage": 31.87, "elapsed_time": "1:21:45", "remaining_time": "2:54:43"}
{"current_steps": 52, "total_steps": 160, "loss": 1.113, "lr": 0.00012179988517727591, "epoch": 0.65, "percentage": 32.5, "elapsed_time": "1:23:20", "remaining_time": "2:53:04"}
{"current_steps": 53, "total_steps": 160, "loss": 1.0932, "lr": 0.00012045258987023879, "epoch": 0.6625, "percentage": 33.12, "elapsed_time": "1:24:54", "remaining_time": "2:51:25"}
{"current_steps": 54, "total_steps": 160, "loss": 1.1008, "lr": 0.00011908969931975641, "epoch": 0.675, "percentage": 33.75, "elapsed_time": "1:26:30", "remaining_time": "2:49:49"}
{"current_steps": 55, "total_steps": 160, "loss": 1.1313, "lr": 0.00011771173894607985, "epoch": 0.6875, "percentage": 34.38, "elapsed_time": "1:28:06", "remaining_time": "2:48:12"}
{"current_steps": 56, "total_steps": 160, "loss": 1.0784, "lr": 0.00011631923997916375, "epoch": 0.7, "percentage": 35.0, "elapsed_time": "1:29:42", "remaining_time": "2:46:36"}
{"current_steps": 57, "total_steps": 160, "loss": 1.0767, "lr": 0.00011491273925386736, "epoch": 0.7125, "percentage": 35.62, "elapsed_time": "1:31:18", "remaining_time": "2:45:00"}
{"current_steps": 58, "total_steps": 160, "loss": 1.0929, "lr": 0.00011349277900299426, "epoch": 0.725, "percentage": 36.25, "elapsed_time": "1:32:54", "remaining_time": "2:43:22"}
{"current_steps": 59, "total_steps": 160, "loss": 1.0977, "lr": 0.00011205990664825127, "epoch": 0.7375, "percentage": 36.88, "elapsed_time": "1:34:29", "remaining_time": "2:41:44"}
{"current_steps": 60, "total_steps": 160, "loss": 1.1219, "lr": 0.00011061467458920719, "epoch": 0.75, "percentage": 37.5, "elapsed_time": "1:36:05", "remaining_time": "2:40:08"}
{"current_steps": 61, "total_steps": 160, "loss": 1.0973, "lr": 0.00010915763999033201, "epoch": 0.7625, "percentage": 38.12, "elapsed_time": "1:37:39", "remaining_time": "2:38:30"}
{"current_steps": 41, "total_steps": 160, "loss": 1.1124, "lr": 0.0001354469890036509, "epoch": 0.5125, "percentage": 25.62, "elapsed_time": "0:01:36", "remaining_time": "0:04:40"}
{"current_steps": 42, "total_steps": 160, "loss": 1.1164, "lr": 0.00013430405964263536, "epoch": 0.525, "percentage": 26.25, "elapsed_time": "0:03:10", "remaining_time": "0:08:56"}
{"current_steps": 43, "total_steps": 160, "loss": 1.1379, "lr": 0.00013314019503290255, "epoch": 0.5375, "percentage": 26.88, "elapsed_time": "0:04:45", "remaining_time": "0:12:57"}
{"current_steps": 44, "total_steps": 160, "loss": 1.0963, "lr": 0.00013195584386641469, "epoch": 0.55, "percentage": 27.5, "elapsed_time": "0:06:22", "remaining_time": "0:16:48"}
{"current_steps": 45, "total_steps": 160, "loss": 1.1089, "lr": 0.00013075146273309164, "epoch": 0.5625, "percentage": 28.12, "elapsed_time": "0:07:57", "remaining_time": "0:20:19"}
{"current_steps": 46, "total_steps": 160, "loss": 1.1226, "lr": 0.00012952751594478675, "epoch": 0.575, "percentage": 28.75, "elapsed_time": "0:09:34", "remaining_time": "0:23:43"}
{"current_steps": 47, "total_steps": 160, "loss": 1.1035, "lr": 0.0001282844753562857, "epoch": 0.5875, "percentage": 29.38, "elapsed_time": "0:11:08", "remaining_time": "0:26:47"}
{"current_steps": 48, "total_steps": 160, "loss": 1.0713, "lr": 0.00012702282018339786, "epoch": 0.6, "percentage": 30.0, "elapsed_time": "0:12:43", "remaining_time": "0:29:41"}
{"current_steps": 49, "total_steps": 160, "loss": 1.1232, "lr": 0.00012574303681820898, "epoch": 0.6125, "percentage": 30.63, "elapsed_time": "0:14:19", "remaining_time": "0:32:27"}
{"current_steps": 50, "total_steps": 160, "loss": 1.0726, "lr": 0.0001244456186415682, "epoch": 0.625, "percentage": 31.25, "elapsed_time": "0:15:54", "remaining_time": "0:35:00"}
{"current_steps": 51, "total_steps": 160, "loss": 1.0855, "lr": 0.00012313106583288004, "epoch": 0.6375, "percentage": 31.87, "elapsed_time": "0:17:30", "remaining_time": "0:37:25"}
{"current_steps": 52, "total_steps": 160, "loss": 1.113, "lr": 0.00012179988517727591, "epoch": 0.65, "percentage": 32.5, "elapsed_time": "0:19:05", "remaining_time": "0:39:39"}
{"current_steps": 53, "total_steps": 160, "loss": 1.0931, "lr": 0.00012045258987023879, "epoch": 0.6625, "percentage": 33.12, "elapsed_time": "0:20:39", "remaining_time": "0:41:43"}
{"current_steps": 54, "total_steps": 160, "loss": 1.1007, "lr": 0.00011908969931975641, "epoch": 0.675, "percentage": 33.75, "elapsed_time": "0:22:15", "remaining_time": "0:43:42"}
{"current_steps": 55, "total_steps": 160, "loss": 1.1312, "lr": 0.00011771173894607985, "epoch": 0.6875, "percentage": 34.38, "elapsed_time": "0:23:51", "remaining_time": "0:45:33"}
{"current_steps": 56, "total_steps": 160, "loss": 1.0784, "lr": 0.00011631923997916375, "epoch": 0.7, "percentage": 35.0, "elapsed_time": "0:25:27", "remaining_time": "0:47:17"}
{"current_steps": 57, "total_steps": 160, "loss": 1.0766, "lr": 0.00011491273925386736, "epoch": 0.7125, "percentage": 35.62, "elapsed_time": "0:27:04", "remaining_time": "0:48:55"}
{"current_steps": 58, "total_steps": 160, "loss": 1.0929, "lr": 0.00011349277900299426, "epoch": 0.725, "percentage": 36.25, "elapsed_time": "0:28:39", "remaining_time": "0:50:23"}
{"current_steps": 59, "total_steps": 160, "loss": 1.0977, "lr": 0.00011205990664825127, "epoch": 0.7375, "percentage": 36.88, "elapsed_time": "0:30:14", "remaining_time": "0:51:46"}
{"current_steps": 60, "total_steps": 160, "loss": 1.1218, "lr": 0.00011061467458920719, "epoch": 0.75, "percentage": 37.5, "elapsed_time": "0:31:50", "remaining_time": "0:53:04"}
{"current_steps": 61, "total_steps": 160, "loss": 1.0972, "lr": 0.00010915763999033201, "epoch": 0.7625, "percentage": 38.12, "elapsed_time": "0:33:25", "remaining_time": "0:54:14"}
{"current_steps": 62, "total_steps": 160, "loss": 1.0723, "lr": 0.00010768936456619945, "epoch": 0.775, "percentage": 38.75, "elapsed_time": "0:35:00", "remaining_time": "0:55:20"}
{"current_steps": 63, "total_steps": 160, "loss": 1.1059, "lr": 0.0001062104143649355, "epoch": 0.7875, "percentage": 39.38, "elapsed_time": "0:36:36", "remaining_time": "0:56:21"}
{"current_steps": 64, "total_steps": 160, "loss": 1.1112, "lr": 0.0001047213595499958, "epoch": 0.8, "percentage": 40.0, "elapsed_time": "0:38:12", "remaining_time": "0:57:18"}
{"current_steps": 65, "total_steps": 160, "loss": 1.1125, "lr": 0.000103222774180357, "epoch": 0.8125, "percentage": 40.62, "elapsed_time": "0:39:46", "remaining_time": "0:58:08"}
{"current_steps": 66, "total_steps": 160, "loss": 1.0506, "lr": 0.00010171523598920594, "epoch": 0.825, "percentage": 41.25, "elapsed_time": "0:41:21", "remaining_time": "0:58:53"}
{"current_steps": 67, "total_steps": 160, "loss": 1.0599, "lr": 0.00010019932616121264, "epoch": 0.8375, "percentage": 41.88, "elapsed_time": "0:42:57", "remaining_time": "0:59:38"}
{"current_steps": 68, "total_steps": 160, "loss": 1.1116, "lr": 9.867562910847246e-05, "epoch": 0.85, "percentage": 42.5, "elapsed_time": "0:44:33", "remaining_time": "1:00:17"}
{"current_steps": 69, "total_steps": 160, "loss": 1.1039, "lr": 9.714473224520406e-05, "epoch": 0.8625, "percentage": 43.12, "elapsed_time": "0:46:09", "remaining_time": "1:00:51"}
{"current_steps": 70, "total_steps": 160, "loss": 1.1007, "lr": 9.560722576129029e-05, "epoch": 0.875, "percentage": 43.75, "elapsed_time": "0:47:44", "remaining_time": "1:01:22"}
{"current_steps": 71, "total_steps": 160, "loss": 1.0976, "lr": 9.406370239474839e-05, "epoch": 0.8875, "percentage": 44.38, "elapsed_time": "0:49:19", "remaining_time": "1:01:49"}
{"current_steps": 72, "total_steps": 160, "loss": 1.1001, "lr": 9.251475720321848e-05, "epoch": 0.9, "percentage": 45.0, "elapsed_time": "0:50:54", "remaining_time": "1:02:13"}
{"current_steps": 73, "total_steps": 160, "loss": 1.0864, "lr": 9.096098733455746e-05, "epoch": 0.9125, "percentage": 45.62, "elapsed_time": "0:52:31", "remaining_time": "1:02:35"}
{"current_steps": 74, "total_steps": 160, "loss": 1.0976, "lr": 8.940299179662703e-05, "epoch": 0.925, "percentage": 46.25, "elapsed_time": "0:54:07", "remaining_time": "1:02:54"}
{"current_steps": 75, "total_steps": 160, "loss": 1.1049, "lr": 8.784137122636488e-05, "epoch": 0.9375, "percentage": 46.88, "elapsed_time": "0:55:43", "remaining_time": "1:03:08"}
{"current_steps": 76, "total_steps": 160, "loss": 1.0504, "lr": 8.627672765822762e-05, "epoch": 0.95, "percentage": 47.5, "elapsed_time": "0:57:18", "remaining_time": "1:03:20"}
{"current_steps": 77, "total_steps": 160, "loss": 1.1028, "lr": 8.470966429209512e-05, "epoch": 0.9625, "percentage": 48.12, "elapsed_time": "0:58:54", "remaining_time": "1:03:30"}
{"current_steps": 78, "total_steps": 160, "loss": 1.0605, "lr": 8.31407852607255e-05, "epoch": 0.975, "percentage": 48.75, "elapsed_time": "1:00:30", "remaining_time": "1:03:36"}
{"current_steps": 79, "total_steps": 160, "loss": 1.1069, "lr": 8.157069539685026e-05, "epoch": 0.9875, "percentage": 49.38, "elapsed_time": "1:02:06", "remaining_time": "1:03:40"}
{"current_steps": 80, "total_steps": 160, "loss": 1.1173, "lr": 8e-05, "epoch": 1.0, "percentage": 50.0, "elapsed_time": "1:03:40", "remaining_time": "1:03:40"}
{"current_steps": 81, "total_steps": 160, "loss": 1.0536, "lr": 7.842930460314975e-05, "epoch": 1.0125, "percentage": 50.62, "elapsed_time": "1:05:48", "remaining_time": "1:04:10"}
{"current_steps": 82, "total_steps": 160, "loss": 1.1236, "lr": 7.685921473927454e-05, "epoch": 1.025, "percentage": 51.25, "elapsed_time": "1:07:23", "remaining_time": "1:04:06"}
{"current_steps": 83, "total_steps": 160, "loss": 1.0927, "lr": 7.529033570790488e-05, "epoch": 1.0375, "percentage": 51.88, "elapsed_time": "1:08:58", "remaining_time": "1:03:59"}
{"current_steps": 84, "total_steps": 160, "loss": 1.0861, "lr": 7.372327234177242e-05, "epoch": 1.05, "percentage": 52.5, "elapsed_time": "1:10:33", "remaining_time": "1:03:50"}
{"current_steps": 85, "total_steps": 160, "loss": 1.108, "lr": 7.215862877363515e-05, "epoch": 1.0625, "percentage": 53.12, "elapsed_time": "1:12:08", "remaining_time": "1:03:39"}
{"current_steps": 86, "total_steps": 160, "loss": 1.0958, "lr": 7.0597008203373e-05, "epoch": 1.075, "percentage": 53.75, "elapsed_time": "1:13:44", "remaining_time": "1:03:27"}
{"current_steps": 87, "total_steps": 160, "loss": 1.0456, "lr": 6.903901266544258e-05, "epoch": 1.0875, "percentage": 54.37, "elapsed_time": "1:15:20", "remaining_time": "1:03:13"}
{"current_steps": 88, "total_steps": 160, "loss": 1.1224, "lr": 6.748524279678152e-05, "epoch": 1.1, "percentage": 55.0, "elapsed_time": "1:16:56", "remaining_time": "1:02:57"}
{"current_steps": 89, "total_steps": 160, "loss": 1.0932, "lr": 6.593629760525164e-05, "epoch": 1.1125, "percentage": 55.62, "elapsed_time": "1:18:32", "remaining_time": "1:02:39"}
{"current_steps": 90, "total_steps": 160, "loss": 1.1091, "lr": 6.439277423870975e-05, "epoch": 1.125, "percentage": 56.25, "elapsed_time": "1:20:08", "remaining_time": "1:02:19"}
{"current_steps": 91, "total_steps": 160, "loss": 1.0921, "lr": 6.285526775479596e-05, "epoch": 1.1375, "percentage": 56.88, "elapsed_time": "1:21:41", "remaining_time": "1:01:56"}
{"current_steps": 92, "total_steps": 160, "loss": 1.0642, "lr": 6.13243708915276e-05, "epoch": 1.15, "percentage": 57.5, "elapsed_time": "1:23:17", "remaining_time": "1:01:33"}
{"current_steps": 93, "total_steps": 160, "loss": 1.0832, "lr": 5.9800673838787364e-05, "epoch": 1.1625, "percentage": 58.13, "elapsed_time": "1:24:52", "remaining_time": "1:01:08"}
{"current_steps": 94, "total_steps": 160, "loss": 1.0666, "lr": 5.828476401079407e-05, "epoch": 1.175, "percentage": 58.75, "elapsed_time": "1:26:27", "remaining_time": "1:00:42"}
{"current_steps": 95, "total_steps": 160, "loss": 1.0342, "lr": 5.677722581964303e-05, "epoch": 1.1875, "percentage": 59.38, "elapsed_time": "1:28:03", "remaining_time": "1:00:15"}
{"current_steps": 96, "total_steps": 160, "loss": 1.0668, "lr": 5.5278640450004216e-05, "epoch": 1.2, "percentage": 60.0, "elapsed_time": "1:29:38", "remaining_time": "0:59:45"}
{"current_steps": 97, "total_steps": 160, "loss": 1.0359, "lr": 5.3789585635064534e-05, "epoch": 1.2125, "percentage": 60.62, "elapsed_time": "1:31:15", "remaining_time": "0:59:16"}
{"current_steps": 98, "total_steps": 160, "loss": 1.0305, "lr": 5.231063543380055e-05, "epoch": 1.225, "percentage": 61.25, "elapsed_time": "1:32:51", "remaining_time": "0:58:44"}
{"current_steps": 99, "total_steps": 160, "loss": 1.0516, "lr": 5.084236000966803e-05, "epoch": 1.2375, "percentage": 61.88, "elapsed_time": "1:34:26", "remaining_time": "0:58:11"}
{"current_steps": 100, "total_steps": 160, "loss": 1.0456, "lr": 4.9385325410792824e-05, "epoch": 1.25, "percentage": 62.5, "elapsed_time": "1:36:01", "remaining_time": "0:57:36"}
{"current_steps": 101, "total_steps": 160, "loss": 1.0482, "lr": 4.794009335174874e-05, "epoch": 1.2625, "percentage": 63.12, "elapsed_time": "1:37:36", "remaining_time": "0:57:00"}
{"current_steps": 102, "total_steps": 160, "loss": 1.0442, "lr": 4.650722099700578e-05, "epoch": 1.275, "percentage": 63.75, "elapsed_time": "1:39:11", "remaining_time": "0:56:24"}
{"current_steps": 103, "total_steps": 160, "loss": 1.0694, "lr": 4.508726074613262e-05, "epoch": 1.2875, "percentage": 64.38, "elapsed_time": "1:40:47", "remaining_time": "0:55:46"}
{"current_steps": 104, "total_steps": 160, "loss": 1.0556, "lr": 4.3680760020836266e-05, "epoch": 1.3, "percentage": 65.0, "elapsed_time": "1:42:23", "remaining_time": "0:55:07"}
{"current_steps": 105, "total_steps": 160, "loss": 1.044, "lr": 4.2288261053920186e-05, "epoch": 1.3125, "percentage": 65.62, "elapsed_time": "1:43:59", "remaining_time": "0:54:28"}
{"current_steps": 106, "total_steps": 160, "loss": 1.0231, "lr": 4.0910300680243636e-05, "epoch": 1.325, "percentage": 66.25, "elapsed_time": "1:45:34", "remaining_time": "0:53:47"}
{"current_steps": 107, "total_steps": 160, "loss": 1.0468, "lr": 3.954741012976125e-05, "epoch": 1.3375, "percentage": 66.88, "elapsed_time": "1:47:10", "remaining_time": "0:53:05"}
{"current_steps": 108, "total_steps": 160, "loss": 1.0452, "lr": 3.8200114822724096e-05, "epoch": 1.35, "percentage": 67.5, "elapsed_time": "1:48:46", "remaining_time": "0:52:22"}
{"current_steps": 109, "total_steps": 160, "loss": 1.0487, "lr": 3.686893416711998e-05, "epoch": 1.3625, "percentage": 68.12, "elapsed_time": "1:50:24", "remaining_time": "0:51:39"}
{"current_steps": 110, "total_steps": 160, "loss": 1.0447, "lr": 3.5554381358431845e-05, "epoch": 1.375, "percentage": 68.75, "elapsed_time": "1:51:59", "remaining_time": "0:50:54"}
{"current_steps": 111, "total_steps": 160, "loss": 1.0288, "lr": 3.425696318179103e-05, "epoch": 1.3875, "percentage": 69.38, "elapsed_time": "1:53:35", "remaining_time": "0:50:08"}
{"current_steps": 112, "total_steps": 160, "loss": 1.0269, "lr": 3.297717981660216e-05, "epoch": 1.4, "percentage": 70.0, "elapsed_time": "1:55:11", "remaining_time": "0:49:21"}
{"current_steps": 113, "total_steps": 160, "loss": 1.0361, "lr": 3.1715524643714286e-05, "epoch": 1.4125, "percentage": 70.62, "elapsed_time": "1:56:46", "remaining_time": "0:48:34"}
{"current_steps": 114, "total_steps": 160, "loss": 1.0476, "lr": 3.0472484055213276e-05, "epoch": 1.425, "percentage": 71.25, "elapsed_time": "1:58:21", "remaining_time": "0:47:45"}
{"current_steps": 115, "total_steps": 160, "loss": 1.0531, "lr": 2.9248537266908373e-05, "epoch": 1.4375, "percentage": 71.88, "elapsed_time": "1:59:56", "remaining_time": "0:46:56"}
{"current_steps": 116, "total_steps": 160, "loss": 1.0611, "lr": 2.804415613358532e-05, "epoch": 1.45, "percentage": 72.5, "elapsed_time": "2:01:32", "remaining_time": "0:46:06"}
{"current_steps": 117, "total_steps": 160, "loss": 1.0625, "lr": 2.685980496709749e-05, "epoch": 1.4625, "percentage": 73.12, "elapsed_time": "2:03:08", "remaining_time": "0:45:15"}
{"current_steps": 118, "total_steps": 160, "loss": 1.0647, "lr": 2.569594035736466e-05, "epoch": 1.475, "percentage": 73.75, "elapsed_time": "2:04:44", "remaining_time": "0:44:23"}
{"current_steps": 119, "total_steps": 160, "loss": 1.0543, "lr": 2.4553010996349143e-05, "epoch": 1.4875, "percentage": 74.38, "elapsed_time": "2:06:21", "remaining_time": "0:43:32"}
{"current_steps": 120, "total_steps": 160, "loss": 1.0325, "lr": 2.3431457505076205e-05, "epoch": 1.5, "percentage": 75.0, "elapsed_time": "2:07:57", "remaining_time": "0:42:39"}
{"current_steps": 121, "total_steps": 160, "loss": 1.041, "lr": 2.2331712263766495e-05, "epoch": 1.5125, "percentage": 75.62, "elapsed_time": "2:10:03", "remaining_time": "0:41:55"}
{"current_steps": 122, "total_steps": 160, "loss": 1.0433, "lr": 2.1254199245145177e-05, "epoch": 1.525, "percentage": 76.25, "elapsed_time": "2:11:38", "remaining_time": "0:41:00"}
{"current_steps": 123, "total_steps": 160, "loss": 1.0657, "lr": 2.0199333850992245e-05, "epoch": 1.5375, "percentage": 76.88, "elapsed_time": "2:13:13", "remaining_time": "0:40:04"}
{"current_steps": 124, "total_steps": 160, "loss": 1.0292, "lr": 1.9167522751997527e-05, "epoch": 1.55, "percentage": 77.5, "elapsed_time": "2:14:49", "remaining_time": "0:39:08"}
{"current_steps": 125, "total_steps": 160, "loss": 1.04, "lr": 1.815916373098104e-05, "epoch": 1.5625, "percentage": 78.12, "elapsed_time": "2:16:24", "remaining_time": "0:38:11"}
{"current_steps": 126, "total_steps": 160, "loss": 1.0556, "lr": 1.7174645529540424e-05, "epoch": 1.575, "percentage": 78.75, "elapsed_time": "2:18:01", "remaining_time": "0:37:14"}
{"current_steps": 127, "total_steps": 160, "loss": 1.0365, "lr": 1.621434769818344e-05, "epoch": 1.5875, "percentage": 79.38, "elapsed_time": "2:19:35", "remaining_time": "0:36:16"}
{"current_steps": 128, "total_steps": 160, "loss": 1.0072, "lr": 1.5278640450004213e-05, "epoch": 1.6, "percentage": 80.0, "elapsed_time": "2:21:11", "remaining_time": "0:35:17"}
{"current_steps": 129, "total_steps": 160, "loss": 1.0589, "lr": 1.4367884517958914e-05, "epoch": 1.6125, "percentage": 80.62, "elapsed_time": "2:22:47", "remaining_time": "0:34:18"}
{"current_steps": 130, "total_steps": 160, "loss": 1.0112, "lr": 1.3482431015796373e-05, "epoch": 1.625, "percentage": 81.25, "elapsed_time": "2:24:22", "remaining_time": "0:33:19"}
{"current_steps": 131, "total_steps": 160, "loss": 1.0249, "lr": 1.2622621302697087e-05, "epoch": 1.6375, "percentage": 81.88, "elapsed_time": "2:25:58", "remaining_time": "0:32:18"}
{"current_steps": 132, "total_steps": 160, "loss": 1.0507, "lr": 1.1788786851672628e-05, "epoch": 1.65, "percentage": 82.5, "elapsed_time": "2:27:33", "remaining_time": "0:31:18"}
{"current_steps": 133, "total_steps": 160, "loss": 1.0328, "lr": 1.0981249121776654e-05, "epoch": 1.6625, "percentage": 83.12, "elapsed_time": "2:29:07", "remaining_time": "0:30:16"}
{"current_steps": 134, "total_steps": 160, "loss": 1.0412, "lr": 1.0200319434176227e-05, "epoch": 1.675, "percentage": 83.75, "elapsed_time": "2:30:43", "remaining_time": "0:29:14"}
{"current_steps": 135, "total_steps": 160, "loss": 1.072, "lr": 9.446298852131605e-06, "epoch": 1.6875, "percentage": 84.38, "elapsed_time": "2:32:19", "remaining_time": "0:28:12"}
{"current_steps": 136, "total_steps": 160, "loss": 1.022, "lr": 8.719478064930578e-06, "epoch": 1.7, "percentage": 85.0, "elapsed_time": "2:33:55", "remaining_time": "0:27:09"}
{"current_steps": 137, "total_steps": 160, "loss": 1.021, "lr": 8.020137275822297e-06, "epoch": 1.7125, "percentage": 85.62, "elapsed_time": "2:35:31", "remaining_time": "0:26:06"}
{"current_steps": 138, "total_steps": 160, "loss": 1.0369, "lr": 7.348546093993492e-06, "epoch": 1.725, "percentage": 86.25, "elapsed_time": "2:37:06", "remaining_time": "0:25:02"}
{"current_steps": 139, "total_steps": 160, "loss": 1.0433, "lr": 6.704963430629132e-06, "epoch": 1.7375, "percentage": 86.88, "elapsed_time": "2:38:41", "remaining_time": "0:23:58"}
{"current_steps": 140, "total_steps": 160, "loss": 1.0893, "lr": 6.0896373990970614e-06, "epoch": 1.75, "percentage": 87.5, "elapsed_time": "2:40:17", "remaining_time": "0:22:53"}
{"current_steps": 141, "total_steps": 160, "loss": 1.0433, "lr": 5.502805219295715e-06, "epoch": 1.7625, "percentage": 88.12, "elapsed_time": "2:41:52", "remaining_time": "0:21:48"}
{"current_steps": 142, "total_steps": 160, "loss": 1.0207, "lr": 4.944693126201276e-06, "epoch": 1.775, "percentage": 88.75, "elapsed_time": "2:43:27", "remaining_time": "0:20:43"}
{"current_steps": 143, "total_steps": 160, "loss": 1.0538, "lr": 4.415516282649756e-06, "epoch": 1.7875, "percentage": 89.38, "elapsed_time": "2:45:03", "remaining_time": "0:19:37"}
{"current_steps": 144, "total_steps": 160, "loss": 1.0606, "lr": 3.915478696387718e-06, "epoch": 1.8, "percentage": 90.0, "elapsed_time": "2:46:39", "remaining_time": "0:18:31"}
{"current_steps": 145, "total_steps": 160, "loss": 1.0614, "lr": 3.4447731414232945e-06, "epoch": 1.8125, "percentage": 90.62, "elapsed_time": "2:48:13", "remaining_time": "0:17:24"}
{"current_steps": 146, "total_steps": 160, "loss": 1.0028, "lr": 3.0035810837082267e-06, "epoch": 1.825, "percentage": 91.25, "elapsed_time": "2:49:48", "remaining_time": "0:16:16"}
{"current_steps": 147, "total_steps": 160, "loss": 1.0137, "lr": 2.5920726111792195e-06, "epoch": 1.8375, "percentage": 91.88, "elapsed_time": "2:51:24", "remaining_time": "0:15:09"}
{"current_steps": 148, "total_steps": 160, "loss": 1.0631, "lr": 2.2104063681858757e-06, "epoch": 1.85, "percentage": 92.5, "elapsed_time": "2:53:01", "remaining_time": "0:14:01"}
{"current_steps": 149, "total_steps": 160, "loss": 1.0562, "lr": 1.8587294943302092e-06, "epoch": 1.8625, "percentage": 93.12, "elapsed_time": "2:54:36", "remaining_time": "0:12:53"}
{"current_steps": 150, "total_steps": 160, "loss": 1.0534, "lr": 1.5371775677415656e-06, "epoch": 1.875, "percentage": 93.75, "elapsed_time": "2:56:11", "remaining_time": "0:11:44"}
{"current_steps": 151, "total_steps": 160, "loss": 1.0517, "lr": 1.2458745528086723e-06, "epoch": 1.8875, "percentage": 94.38, "elapsed_time": "2:57:46", "remaining_time": "0:10:35"}
{"current_steps": 152, "total_steps": 160, "loss": 1.0547, "lr": 9.849327523889873e-07, "epoch": 1.9, "percentage": 95.0, "elapsed_time": "2:59:21", "remaining_time": "0:09:26"}
{"current_steps": 153, "total_steps": 160, "loss": 1.0418, "lr": 7.5445276451382e-07, "epoch": 1.9125, "percentage": 95.62, "elapsed_time": "3:00:58", "remaining_time": "0:08:16"}
{"current_steps": 154, "total_steps": 160, "loss": 1.0541, "lr": 5.545234436058966e-07, "epoch": 1.925, "percentage": 96.25, "elapsed_time": "3:02:34", "remaining_time": "0:07:06"}
{"current_steps": 155, "total_steps": 160, "loss": 1.0613, "lr": 3.852218662242546e-07, "epoch": 1.9375, "percentage": 96.88, "elapsed_time": "3:04:10", "remaining_time": "0:05:56"}
{"current_steps": 156, "total_steps": 160, "loss": 1.0097, "lr": 2.466133013497629e-07, "epoch": 1.95, "percentage": 97.5, "elapsed_time": "3:05:46", "remaining_time": "0:04:45"}
{"current_steps": 157, "total_steps": 160, "loss": 1.0606, "lr": 1.3875118522273412e-07, "epoch": 1.9625, "percentage": 98.12, "elapsed_time": "3:07:21", "remaining_time": "0:03:34"}
{"current_steps": 158, "total_steps": 160, "loss": 1.0207, "lr": 6.167710074216792e-08, "epoch": 1.975, "percentage": 98.75, "elapsed_time": "3:08:57", "remaining_time": "0:02:23"}
{"current_steps": 159, "total_steps": 160, "loss": 1.066, "lr": 1.5420761434814523e-08, "epoch": 1.9875, "percentage": 99.38, "elapsed_time": "3:10:33", "remaining_time": "0:01:11"}
{"current_steps": 160, "total_steps": 160, "loss": 1.0772, "lr": 0.0, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "3:12:07", "remaining_time": "0:00:00"}
{"current_steps": 160, "total_steps": 160, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "3:12:39", "remaining_time": "0:00:00"}