Files
OpenThoughts3-random-groups…/trainer_log.jsonl
ModelHub XC 39e6309ba9 初始化项目,由ModelHub XC社区提供模型
Model: cjiao/OpenThoughts3-random-groups-openthinker3-1.5B-checkpoint-375-length-filtered
Source: Original Platform
2026-04-27 22:17:19 +08:00

102 lines
18 KiB
JSON

{"current_steps": 1, "total_steps": 100, "loss": 1.2438, "lr": 0.00015996052482925854, "epoch": 0.02, "percentage": 1.0, "elapsed_time": "0:02:36", "remaining_time": "4:18:19"}
{"current_steps": 2, "total_steps": 100, "loss": 3.7464, "lr": 0.00015984213827426174, "epoch": 0.04, "percentage": 2.0, "elapsed_time": "0:05:01", "remaining_time": "4:05:50"}
{"current_steps": 3, "total_steps": 100, "loss": 2.9219, "lr": 0.0001596449571682464, "epoch": 0.06, "percentage": 3.0, "elapsed_time": "0:07:24", "remaining_time": "3:59:26"}
{"current_steps": 4, "total_steps": 100, "loss": 2.1242, "lr": 0.00015936917610515826, "epoch": 0.08, "percentage": 4.0, "elapsed_time": "0:09:45", "remaining_time": "3:54:18"}
{"current_steps": 5, "total_steps": 100, "loss": 1.7799, "lr": 0.00015901506724761103, "epoch": 0.1, "percentage": 5.0, "elapsed_time": "0:12:08", "remaining_time": "3:50:35"}
{"current_steps": 6, "total_steps": 100, "loss": 1.6514, "lr": 0.00015858298005829512, "epoch": 0.12, "percentage": 6.0, "elapsed_time": "0:14:32", "remaining_time": "3:47:49"}
{"current_steps": 7, "total_steps": 100, "loss": 1.5758, "lr": 0.0001580733409550998, "epoch": 0.14, "percentage": 7.0, "elapsed_time": "0:16:58", "remaining_time": "3:45:29"}
{"current_steps": 8, "total_steps": 100, "loss": 1.4651, "lr": 0.0001574866528902905, "epoch": 0.16, "percentage": 8.0, "elapsed_time": "0:19:19", "remaining_time": "3:42:18"}
{"current_steps": 9, "total_steps": 100, "loss": 1.3782, "lr": 0.00015682349485415545, "epoch": 0.18, "percentage": 9.0, "elapsed_time": "0:21:44", "remaining_time": "3:39:53"}
{"current_steps": 10, "total_steps": 100, "loss": 1.353, "lr": 0.0001560845213036123, "epoch": 0.2, "percentage": 10.0, "elapsed_time": "0:24:06", "remaining_time": "3:36:57"}
{"current_steps": 11, "total_steps": 100, "loss": 1.3325, "lr": 0.00015527046151633805, "epoch": 0.22, "percentage": 11.0, "elapsed_time": "0:26:28", "remaining_time": "3:34:12"}
{"current_steps": 12, "total_steps": 100, "loss": 1.2997, "lr": 0.00015438211887106013, "epoch": 0.24, "percentage": 12.0, "elapsed_time": "0:28:49", "remaining_time": "3:31:25"}
{"current_steps": 13, "total_steps": 100, "loss": 1.2664, "lr": 0.0001534203700547185, "epoch": 0.26, "percentage": 13.0, "elapsed_time": "0:31:11", "remaining_time": "3:28:45"}
{"current_steps": 14, "total_steps": 100, "loss": 1.239, "lr": 0.00015238616419728157, "epoch": 0.28, "percentage": 14.0, "elapsed_time": "0:33:35", "remaining_time": "3:26:18"}
{"current_steps": 15, "total_steps": 100, "loss": 1.2528, "lr": 0.00015128052193506944, "epoch": 0.3, "percentage": 15.0, "elapsed_time": "0:35:57", "remaining_time": "3:23:45"}
{"current_steps": 16, "total_steps": 100, "loss": 1.2447, "lr": 0.0001501045344035091, "epoch": 0.32, "percentage": 16.0, "elapsed_time": "0:38:17", "remaining_time": "3:20:59"}
{"current_steps": 17, "total_steps": 100, "loss": 1.2231, "lr": 0.0001488593621603155, "epoch": 0.34, "percentage": 17.0, "elapsed_time": "0:40:40", "remaining_time": "3:18:33"}
{"current_steps": 18, "total_steps": 100, "loss": 1.2305, "lr": 0.00014754623404016122, "epoch": 0.36, "percentage": 18.0, "elapsed_time": "0:43:01", "remaining_time": "3:15:58"}
{"current_steps": 19, "total_steps": 100, "loss": 1.2339, "lr": 0.00014616644594196495, "epoch": 0.38, "percentage": 19.0, "elapsed_time": "0:45:21", "remaining_time": "3:13:23"}
{"current_steps": 20, "total_steps": 100, "loss": 1.1903, "lr": 0.00014472135954999581, "epoch": 0.4, "percentage": 20.0, "elapsed_time": "0:47:42", "remaining_time": "3:10:50"}
{"current_steps": 21, "total_steps": 100, "loss": 1.1979, "lr": 0.00014321240099005524, "epoch": 0.42, "percentage": 21.0, "elapsed_time": "0:50:05", "remaining_time": "3:08:24"}
{"current_steps": 22, "total_steps": 100, "loss": 1.1951, "lr": 0.00014164105942206316, "epoch": 0.44, "percentage": 22.0, "elapsed_time": "0:52:26", "remaining_time": "3:05:57"}
{"current_steps": 23, "total_steps": 100, "loss": 1.1632, "lr": 0.00014000888557043678, "epoch": 0.46, "percentage": 23.0, "elapsed_time": "0:54:48", "remaining_time": "3:03:28"}
{"current_steps": 24, "total_steps": 100, "loss": 1.1631, "lr": 0.00013831749019371293, "epoch": 0.48, "percentage": 24.0, "elapsed_time": "0:57:11", "remaining_time": "3:01:06"}
{"current_steps": 25, "total_steps": 100, "loss": 1.1886, "lr": 0.00013656854249492382, "epoch": 0.5, "percentage": 25.0, "elapsed_time": "0:59:34", "remaining_time": "2:58:44"}
{"current_steps": 26, "total_steps": 100, "loss": 1.202, "lr": 0.00013476376847429511, "epoch": 0.52, "percentage": 26.0, "elapsed_time": "1:01:56", "remaining_time": "2:56:17"}
{"current_steps": 27, "total_steps": 100, "loss": 1.1832, "lr": 0.00013290494922589216, "epoch": 0.54, "percentage": 27.0, "elapsed_time": "1:04:16", "remaining_time": "2:53:48"}
{"current_steps": 28, "total_steps": 100, "loss": 1.1466, "lr": 0.0001309939191798952, "epoch": 0.56, "percentage": 28.0, "elapsed_time": "1:06:38", "remaining_time": "2:51:22"}
{"current_steps": 29, "total_steps": 100, "loss": 1.1975, "lr": 0.00012903256429223813, "epoch": 0.58, "percentage": 29.0, "elapsed_time": "1:09:02", "remaining_time": "2:49:02"}
{"current_steps": 30, "total_steps": 100, "loss": 1.154, "lr": 0.00012702282018339786, "epoch": 0.6, "percentage": 30.0, "elapsed_time": "1:11:26", "remaining_time": "2:46:42"}
{"current_steps": 31, "total_steps": 100, "loss": 1.1357, "lr": 0.00012496667022817044, "epoch": 0.62, "percentage": 31.0, "elapsed_time": "1:13:48", "remaining_time": "2:44:16"}
{"current_steps": 32, "total_steps": 100, "loss": 1.158, "lr": 0.00012286614359831974, "epoch": 0.64, "percentage": 32.0, "elapsed_time": "1:16:12", "remaining_time": "2:41:56"}
{"current_steps": 33, "total_steps": 100, "loss": 1.1849, "lr": 0.00012072331326002972, "epoch": 0.66, "percentage": 33.0, "elapsed_time": "1:18:32", "remaining_time": "2:39:28"}
{"current_steps": 34, "total_steps": 100, "loss": 1.1935, "lr": 0.00011854029392813723, "epoch": 0.68, "percentage": 34.0, "elapsed_time": "1:20:56", "remaining_time": "2:37:07"}
{"current_steps": 35, "total_steps": 100, "loss": 1.1624, "lr": 0.00011631923997916375, "epoch": 0.7, "percentage": 35.0, "elapsed_time": "1:23:19", "remaining_time": "2:34:44"}
{"current_steps": 36, "total_steps": 100, "loss": 1.1854, "lr": 0.00011406234332520582, "epoch": 0.72, "percentage": 36.0, "elapsed_time": "1:25:41", "remaining_time": "2:32:19"}
{"current_steps": 37, "total_steps": 100, "loss": 1.1597, "lr": 0.00011177183125078245, "epoch": 0.74, "percentage": 37.0, "elapsed_time": "1:28:03", "remaining_time": "2:29:56"}
{"current_steps": 38, "total_steps": 100, "loss": 1.125, "lr": 0.00010944996421477426, "epoch": 0.76, "percentage": 38.0, "elapsed_time": "1:30:26", "remaining_time": "2:27:34"}
{"current_steps": 39, "total_steps": 100, "loss": 1.1144, "lr": 0.00010709903361962333, "epoch": 0.78, "percentage": 39.0, "elapsed_time": "1:32:53", "remaining_time": "2:25:17"}
{"current_steps": 40, "total_steps": 100, "loss": 1.1443, "lr": 0.0001047213595499958, "epoch": 0.8, "percentage": 40.0, "elapsed_time": "1:35:14", "remaining_time": "2:22:52"}
{"current_steps": 41, "total_steps": 100, "loss": 1.1376, "lr": 0.00010231928848313836, "epoch": 0.82, "percentage": 41.0, "elapsed_time": "1:37:37", "remaining_time": "2:20:29"}
{"current_steps": 42, "total_steps": 100, "loss": 1.1616, "lr": 9.989519097318841e-05, "epoch": 0.84, "percentage": 42.0, "elapsed_time": "1:39:58", "remaining_time": "2:18:04"}
{"current_steps": 43, "total_steps": 100, "loss": 1.1511, "lr": 9.745145931172342e-05, "epoch": 0.86, "percentage": 43.0, "elapsed_time": "1:42:22", "remaining_time": "2:15:42"}
{"current_steps": 44, "total_steps": 100, "loss": 1.1385, "lr": 9.4990505166858e-05, "epoch": 0.88, "percentage": 44.0, "elapsed_time": "1:44:45", "remaining_time": "2:13:19"}
{"current_steps": 45, "total_steps": 100, "loss": 1.1429, "lr": 9.251475720321848e-05, "epoch": 0.9, "percentage": 45.0, "elapsed_time": "1:47:07", "remaining_time": "2:10:56"}
{"current_steps": 46, "total_steps": 100, "loss": 1.119, "lr": 9.002665868514435e-05, "epoch": 0.92, "percentage": 46.0, "elapsed_time": "1:49:30", "remaining_time": "2:08:33"}
{"current_steps": 47, "total_steps": 100, "loss": 1.1642, "lr": 8.752866506548117e-05, "epoch": 0.94, "percentage": 47.0, "elapsed_time": "1:51:50", "remaining_time": "2:06:06"}
{"current_steps": 48, "total_steps": 100, "loss": 1.1281, "lr": 8.502324156234508e-05, "epoch": 0.96, "percentage": 48.0, "elapsed_time": "1:54:09", "remaining_time": "2:03:40"}
{"current_steps": 49, "total_steps": 100, "loss": 1.1399, "lr": 8.251286072625027e-05, "epoch": 0.98, "percentage": 49.0, "elapsed_time": "1:56:29", "remaining_time": "2:01:15"}
{"current_steps": 50, "total_steps": 100, "loss": 1.0937, "lr": 8e-05, "epoch": 1.0, "percentage": 50.0, "elapsed_time": "1:58:52", "remaining_time": "1:58:52"}
{"current_steps": 51, "total_steps": 100, "loss": 1.0383, "lr": 7.748713927374974e-05, "epoch": 1.02, "percentage": 51.0, "elapsed_time": "2:02:07", "remaining_time": "1:57:20"}
{"current_steps": 52, "total_steps": 100, "loss": 1.1376, "lr": 7.497675843765493e-05, "epoch": 1.04, "percentage": 52.0, "elapsed_time": "2:04:30", "remaining_time": "1:54:55"}
{"current_steps": 53, "total_steps": 100, "loss": 1.1206, "lr": 7.247133493451886e-05, "epoch": 1.06, "percentage": 53.0, "elapsed_time": "2:06:50", "remaining_time": "1:52:29"}
{"current_steps": 54, "total_steps": 100, "loss": 1.1502, "lr": 6.997334131485565e-05, "epoch": 1.08, "percentage": 54.0, "elapsed_time": "2:09:11", "remaining_time": "1:50:03"}
{"current_steps": 55, "total_steps": 100, "loss": 1.1279, "lr": 6.748524279678152e-05, "epoch": 1.1, "percentage": 55.0, "elapsed_time": "2:11:33", "remaining_time": "1:47:38"}
{"current_steps": 56, "total_steps": 100, "loss": 1.1218, "lr": 6.500949483314202e-05, "epoch": 1.12, "percentage": 56.0, "elapsed_time": "2:13:55", "remaining_time": "1:45:13"}
{"current_steps": 57, "total_steps": 100, "loss": 1.1378, "lr": 6.254854068827662e-05, "epoch": 1.1400000000000001, "percentage": 57.0, "elapsed_time": "2:16:19", "remaining_time": "1:42:50"}
{"current_steps": 58, "total_steps": 100, "loss": 1.1156, "lr": 6.0104809026811634e-05, "epoch": 1.16, "percentage": 58.0, "elapsed_time": "2:18:40", "remaining_time": "1:40:24"}
{"current_steps": 59, "total_steps": 100, "loss": 1.079, "lr": 5.7680711516861674e-05, "epoch": 1.18, "percentage": 59.0, "elapsed_time": "2:21:01", "remaining_time": "1:38:00"}
{"current_steps": 60, "total_steps": 100, "loss": 1.078, "lr": 5.5278640450004216e-05, "epoch": 1.2, "percentage": 60.0, "elapsed_time": "2:23:23", "remaining_time": "1:35:35"}
{"current_steps": 61, "total_steps": 100, "loss": 1.0959, "lr": 5.2900966380376693e-05, "epoch": 1.22, "percentage": 61.0, "elapsed_time": "2:25:47", "remaining_time": "1:33:12"}
{"current_steps": 62, "total_steps": 100, "loss": 1.0807, "lr": 5.055003578522577e-05, "epoch": 1.24, "percentage": 62.0, "elapsed_time": "2:28:10", "remaining_time": "1:30:49"}
{"current_steps": 63, "total_steps": 100, "loss": 1.0645, "lr": 4.822816874921756e-05, "epoch": 1.26, "percentage": 63.0, "elapsed_time": "2:30:31", "remaining_time": "1:28:24"}
{"current_steps": 64, "total_steps": 100, "loss": 1.0591, "lr": 4.593765667479419e-05, "epoch": 1.28, "percentage": 64.0, "elapsed_time": "2:32:54", "remaining_time": "1:26:00"}
{"current_steps": 65, "total_steps": 100, "loss": 1.0848, "lr": 4.3680760020836266e-05, "epoch": 1.3, "percentage": 65.0, "elapsed_time": "2:35:17", "remaining_time": "1:23:36"}
{"current_steps": 66, "total_steps": 100, "loss": 1.0722, "lr": 4.145970607186277e-05, "epoch": 1.32, "percentage": 66.0, "elapsed_time": "2:37:37", "remaining_time": "1:21:11"}
{"current_steps": 67, "total_steps": 100, "loss": 1.0654, "lr": 3.92766867399703e-05, "epoch": 1.34, "percentage": 67.0, "elapsed_time": "2:40:02", "remaining_time": "1:18:49"}
{"current_steps": 68, "total_steps": 100, "loss": 1.0786, "lr": 3.7133856401680256e-05, "epoch": 1.3599999999999999, "percentage": 68.0, "elapsed_time": "2:42:23", "remaining_time": "1:16:25"}
{"current_steps": 69, "total_steps": 100, "loss": 1.0804, "lr": 3.5033329771829576e-05, "epoch": 1.38, "percentage": 69.0, "elapsed_time": "2:44:44", "remaining_time": "1:14:00"}
{"current_steps": 70, "total_steps": 100, "loss": 1.0532, "lr": 3.297717981660216e-05, "epoch": 1.4, "percentage": 70.0, "elapsed_time": "2:47:06", "remaining_time": "1:11:36"}
{"current_steps": 71, "total_steps": 100, "loss": 1.0669, "lr": 3.09674357077619e-05, "epoch": 1.42, "percentage": 71.0, "elapsed_time": "2:49:29", "remaining_time": "1:09:13"}
{"current_steps": 72, "total_steps": 100, "loss": 1.0586, "lr": 2.9006080820104823e-05, "epoch": 1.44, "percentage": 72.0, "elapsed_time": "2:51:48", "remaining_time": "1:06:48"}
{"current_steps": 73, "total_steps": 100, "loss": 1.0425, "lr": 2.7095050774107867e-05, "epoch": 1.46, "percentage": 73.0, "elapsed_time": "2:54:10", "remaining_time": "1:04:25"}
{"current_steps": 74, "total_steps": 100, "loss": 1.0439, "lr": 2.5236231525704902e-05, "epoch": 1.48, "percentage": 74.0, "elapsed_time": "2:56:34", "remaining_time": "1:02:02"}
{"current_steps": 75, "total_steps": 100, "loss": 1.067, "lr": 2.3431457505076205e-05, "epoch": 1.5, "percentage": 75.0, "elapsed_time": "2:58:58", "remaining_time": "0:59:39"}
{"current_steps": 76, "total_steps": 100, "loss": 1.0777, "lr": 2.1682509806287094e-05, "epoch": 1.52, "percentage": 76.0, "elapsed_time": "3:01:20", "remaining_time": "0:57:15"}
{"current_steps": 77, "total_steps": 100, "loss": 1.064, "lr": 1.9991114429563236e-05, "epoch": 1.54, "percentage": 77.0, "elapsed_time": "3:03:41", "remaining_time": "0:54:52"}
{"current_steps": 78, "total_steps": 100, "loss": 1.0343, "lr": 1.835894057793687e-05, "epoch": 1.56, "percentage": 78.0, "elapsed_time": "3:06:03", "remaining_time": "0:52:28"}
{"current_steps": 79, "total_steps": 100, "loss": 1.0886, "lr": 1.678759900994477e-05, "epoch": 1.58, "percentage": 79.0, "elapsed_time": "3:08:28", "remaining_time": "0:50:05"}
{"current_steps": 80, "total_steps": 100, "loss": 1.0535, "lr": 1.5278640450004213e-05, "epoch": 1.6, "percentage": 80.0, "elapsed_time": "3:10:52", "remaining_time": "0:47:43"}
{"current_steps": 81, "total_steps": 100, "loss": 1.0352, "lr": 1.3833554058035045e-05, "epoch": 1.62, "percentage": 81.0, "elapsed_time": "3:13:15", "remaining_time": "0:45:19"}
{"current_steps": 82, "total_steps": 100, "loss": 1.0571, "lr": 1.2453765959838813e-05, "epoch": 1.6400000000000001, "percentage": 82.0, "elapsed_time": "3:15:39", "remaining_time": "0:42:57"}
{"current_steps": 83, "total_steps": 100, "loss": 1.0827, "lr": 1.1140637839684519e-05, "epoch": 1.6600000000000001, "percentage": 83.0, "elapsed_time": "3:18:01", "remaining_time": "0:40:33"}
{"current_steps": 84, "total_steps": 100, "loss": 1.0925, "lr": 9.895465596490931e-06, "epoch": 1.6800000000000002, "percentage": 84.0, "elapsed_time": "3:20:25", "remaining_time": "0:38:10"}
{"current_steps": 85, "total_steps": 100, "loss": 1.0733, "lr": 8.719478064930578e-06, "epoch": 1.7, "percentage": 85.0, "elapsed_time": "3:22:48", "remaining_time": "0:35:47"}
{"current_steps": 86, "total_steps": 100, "loss": 1.0804, "lr": 7.613835802718452e-06, "epoch": 1.72, "percentage": 86.0, "elapsed_time": "3:25:11", "remaining_time": "0:33:24"}
{"current_steps": 87, "total_steps": 100, "loss": 1.0658, "lr": 6.579629945281509e-06, "epoch": 1.74, "percentage": 87.0, "elapsed_time": "3:27:34", "remaining_time": "0:31:01"}
{"current_steps": 88, "total_steps": 100, "loss": 1.0417, "lr": 5.6178811289398925e-06, "epoch": 1.76, "percentage": 88.0, "elapsed_time": "3:29:58", "remaining_time": "0:28:38"}
{"current_steps": 89, "total_steps": 100, "loss": 1.0325, "lr": 4.729538483661964e-06, "epoch": 1.78, "percentage": 89.0, "elapsed_time": "3:32:20", "remaining_time": "0:26:14"}
{"current_steps": 90, "total_steps": 100, "loss": 1.0589, "lr": 3.915478696387718e-06, "epoch": 1.8, "percentage": 90.0, "elapsed_time": "3:34:42", "remaining_time": "0:23:51"}
{"current_steps": 91, "total_steps": 100, "loss": 1.0562, "lr": 3.176505145844555e-06, "epoch": 1.8199999999999998, "percentage": 91.0, "elapsed_time": "3:37:05", "remaining_time": "0:21:28"}
{"current_steps": 92, "total_steps": 100, "loss": 1.0795, "lr": 2.513347109709514e-06, "epoch": 1.8399999999999999, "percentage": 92.0, "elapsed_time": "3:39:27", "remaining_time": "0:19:05"}
{"current_steps": 93, "total_steps": 100, "loss": 1.0656, "lr": 1.9266590449002052e-06, "epoch": 1.8599999999999999, "percentage": 93.0, "elapsed_time": "3:41:51", "remaining_time": "0:16:41"}
{"current_steps": 94, "total_steps": 100, "loss": 1.0675, "lr": 1.4170199417049114e-06, "epoch": 1.88, "percentage": 94.0, "elapsed_time": "3:44:15", "remaining_time": "0:14:18"}
{"current_steps": 95, "total_steps": 100, "loss": 1.065, "lr": 9.849327523889873e-07, "epoch": 1.9, "percentage": 95.0, "elapsed_time": "3:46:37", "remaining_time": "0:11:55"}
{"current_steps": 96, "total_steps": 100, "loss": 1.0449, "lr": 6.308238948417788e-07, "epoch": 1.92, "percentage": 96.0, "elapsed_time": "3:49:01", "remaining_time": "0:09:32"}
{"current_steps": 97, "total_steps": 100, "loss": 1.0836, "lr": 3.550428317536003e-07, "epoch": 1.94, "percentage": 97.0, "elapsed_time": "3:51:21", "remaining_time": "0:07:09"}
{"current_steps": 98, "total_steps": 100, "loss": 1.0578, "lr": 1.578617257382753e-07, "epoch": 1.96, "percentage": 98.0, "elapsed_time": "3:53:41", "remaining_time": "0:04:46"}
{"current_steps": 99, "total_steps": 100, "loss": 1.0651, "lr": 3.9475170741472005e-08, "epoch": 1.98, "percentage": 99.0, "elapsed_time": "3:56:01", "remaining_time": "0:02:23"}
{"current_steps": 100, "total_steps": 100, "loss": 1.0265, "lr": 0.0, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "3:58:23", "remaining_time": "0:00:00"}
{"current_steps": 100, "total_steps": 100, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "3:59:20", "remaining_time": "0:00:00"}