Files
qwen3-4b-refiner-gpt54-ep2/trainer_log.jsonl
ModelHub XC 16d6862601 初始化项目,由ModelHub XC社区提供模型
Model: lihaoxin2020/qwen3-4b-refiner-gpt54-ep2
Source: Original Platform
2026-06-13 16:51:51 +08:00

88 lines
17 KiB
JSON

{"current_steps": 10, "total_steps": 860, "loss": 1.9436748504638672, "lr": 1.0465116279069768e-06, "epoch": 0.02327611288914751, "percentage": 1.16, "elapsed_time": "0:01:52", "remaining_time": "2:39:51"}
{"current_steps": 20, "total_steps": 860, "loss": 1.1599909782409668, "lr": 2.2093023255813954e-06, "epoch": 0.04655222577829502, "percentage": 2.33, "elapsed_time": "0:03:23", "remaining_time": "2:22:06"}
{"current_steps": 30, "total_steps": 860, "loss": 0.7268191814422608, "lr": 3.372093023255814e-06, "epoch": 0.06982833866744254, "percentage": 3.49, "elapsed_time": "0:04:59", "remaining_time": "2:18:15"}
{"current_steps": 40, "total_steps": 860, "loss": 0.6419591903686523, "lr": 4.5348837209302326e-06, "epoch": 0.09310445155659004, "percentage": 4.65, "elapsed_time": "0:06:30", "remaining_time": "2:13:18"}
{"current_steps": 50, "total_steps": 860, "loss": 0.5756725311279297, "lr": 4.9993346519607685e-06, "epoch": 0.11638056444573756, "percentage": 5.81, "elapsed_time": "0:08:02", "remaining_time": "2:10:16"}
{"current_steps": 60, "total_steps": 860, "loss": 0.5720235347747803, "lr": 4.995269918614672e-06, "epoch": 0.13965667733488507, "percentage": 6.98, "elapsed_time": "0:09:35", "remaining_time": "2:07:48"}
{"current_steps": 70, "total_steps": 860, "loss": 0.5563015937805176, "lr": 4.987516091876979e-06, "epoch": 0.1629327902240326, "percentage": 8.14, "elapsed_time": "0:11:06", "remaining_time": "2:05:23"}
{"current_steps": 80, "total_steps": 860, "loss": 0.5556811332702637, "lr": 4.976084635273445e-06, "epoch": 0.18620890311318009, "percentage": 9.3, "elapsed_time": "0:12:47", "remaining_time": "2:04:43"}
{"current_steps": 90, "total_steps": 860, "loss": 0.5483175277709961, "lr": 4.960992449465073e-06, "epoch": 0.2094850160023276, "percentage": 10.47, "elapsed_time": "0:14:17", "remaining_time": "2:02:17"}
{"current_steps": 100, "total_steps": 860, "loss": 0.5287452220916748, "lr": 4.9422618472616005e-06, "epoch": 0.23276112889147513, "percentage": 11.63, "elapsed_time": "0:15:52", "remaining_time": "2:00:38"}
{"current_steps": 110, "total_steps": 860, "loss": 0.5410784721374512, "lr": 4.9199205206334595e-06, "epoch": 0.25603724178062265, "percentage": 12.79, "elapsed_time": "0:17:26", "remaining_time": "1:58:53"}
{"current_steps": 120, "total_steps": 860, "loss": 0.5303399562835693, "lr": 4.894001499771015e-06, "epoch": 0.27931335466977014, "percentage": 13.95, "elapsed_time": "0:19:03", "remaining_time": "1:57:32"}
{"current_steps": 130, "total_steps": 860, "loss": 0.5200899600982666, "lr": 4.864543104251587e-06, "epoch": 0.30258946755891764, "percentage": 15.12, "elapsed_time": "0:20:31", "remaining_time": "1:55:16"}
{"current_steps": 140, "total_steps": 860, "loss": 0.5269728660583496, "lr": 4.8315888863864615e-06, "epoch": 0.3258655804480652, "percentage": 16.28, "elapsed_time": "0:22:10", "remaining_time": "1:54:00"}
{"current_steps": 150, "total_steps": 860, "loss": 0.5075737953186035, "lr": 4.795187566831645e-06, "epoch": 0.3491416933372127, "percentage": 17.44, "elapsed_time": "0:23:42", "remaining_time": "1:52:12"}
{"current_steps": 160, "total_steps": 860, "loss": 0.5038267612457276, "lr": 4.755392962557565e-06, "epoch": 0.37241780622636017, "percentage": 18.6, "elapsed_time": "0:25:14", "remaining_time": "1:50:27"}
{"current_steps": 170, "total_steps": 860, "loss": 0.49009003639221194, "lr": 4.712263907284195e-06, "epoch": 0.3956939191155077, "percentage": 19.77, "elapsed_time": "0:26:50", "remaining_time": "1:48:55"}
{"current_steps": 180, "total_steps": 860, "loss": 0.4944653034210205, "lr": 4.665864164499245e-06, "epoch": 0.4189700320046552, "percentage": 20.93, "elapsed_time": "0:28:22", "remaining_time": "1:47:10"}
{"current_steps": 190, "total_steps": 860, "loss": 0.48484044075012206, "lr": 4.616262333188023e-06, "epoch": 0.44224614489380276, "percentage": 22.09, "elapsed_time": "0:29:50", "remaining_time": "1:45:14"}
{"current_steps": 200, "total_steps": 860, "loss": 0.5251279830932617, "lr": 4.563531746414311e-06, "epoch": 0.46552225778295026, "percentage": 23.26, "elapsed_time": "0:31:24", "remaining_time": "1:43:38"}
{"current_steps": 210, "total_steps": 860, "loss": 0.5141314506530762, "lr": 4.507750362902236e-06, "epoch": 0.48879837067209775, "percentage": 24.42, "elapsed_time": "0:32:57", "remaining_time": "1:42:02"}
{"current_steps": 220, "total_steps": 860, "loss": 0.48561906814575195, "lr": 4.449000651779386e-06, "epoch": 0.5120744835612453, "percentage": 25.58, "elapsed_time": "0:34:28", "remaining_time": "1:40:18"}
{"current_steps": 230, "total_steps": 860, "loss": 0.4920063495635986, "lr": 4.387369470651605e-06, "epoch": 0.5353505964503927, "percentage": 26.74, "elapsed_time": "0:36:05", "remaining_time": "1:38:52"}
{"current_steps": 240, "total_steps": 860, "loss": 0.4970357894897461, "lr": 4.322947937189697e-06, "epoch": 0.5586267093395403, "percentage": 27.91, "elapsed_time": "0:37:38", "remaining_time": "1:37:14"}
{"current_steps": 250, "total_steps": 860, "loss": 0.4910682201385498, "lr": 4.255831294417912e-06, "epoch": 0.5819028222286878, "percentage": 29.07, "elapsed_time": "0:39:15", "remaining_time": "1:35:48"}
{"current_steps": 260, "total_steps": 860, "loss": 0.4876246452331543, "lr": 4.186118769903365e-06, "epoch": 0.6051789351178353, "percentage": 30.23, "elapsed_time": "0:40:44", "remaining_time": "1:34:00"}
{"current_steps": 270, "total_steps": 860, "loss": 0.48180422782897947, "lr": 4.113913429054563e-06, "epoch": 0.6284550480069828, "percentage": 31.4, "elapsed_time": "0:42:16", "remaining_time": "1:32:23"}
{"current_steps": 280, "total_steps": 860, "loss": 0.48159208297729494, "lr": 4.0393220227459405e-06, "epoch": 0.6517311608961304, "percentage": 32.56, "elapsed_time": "0:43:52", "remaining_time": "1:30:52"}
{"current_steps": 290, "total_steps": 860, "loss": 0.45706424713134763, "lr": 3.962454829493674e-06, "epoch": 0.6750072737852778, "percentage": 33.72, "elapsed_time": "0:45:23", "remaining_time": "1:29:12"}
{"current_steps": 300, "total_steps": 860, "loss": 0.4938094139099121, "lr": 3.8834254924161055e-06, "epoch": 0.6982833866744254, "percentage": 34.88, "elapsed_time": "0:47:00", "remaining_time": "1:27:45"}
{"current_steps": 310, "total_steps": 860, "loss": 0.5094244956970215, "lr": 3.802350851219826e-06, "epoch": 0.7215594995635729, "percentage": 36.05, "elapsed_time": "0:48:35", "remaining_time": "1:26:13"}
{"current_steps": 320, "total_steps": 860, "loss": 0.4707345008850098, "lr": 3.7193507694598084e-06, "epoch": 0.7448356124527203, "percentage": 37.21, "elapsed_time": "0:50:06", "remaining_time": "1:24:33"}
{"current_steps": 330, "total_steps": 860, "loss": 0.49939699172973634, "lr": 3.634547957328982e-06, "epoch": 0.7681117253418679, "percentage": 38.37, "elapsed_time": "0:51:40", "remaining_time": "1:22:58"}
{"current_steps": 340, "total_steps": 860, "loss": 0.4723979949951172, "lr": 3.5480677902392358e-06, "epoch": 0.7913878382310154, "percentage": 39.53, "elapsed_time": "0:53:09", "remaining_time": "1:21:18"}
{"current_steps": 350, "total_steps": 860, "loss": 0.5031119346618652, "lr": 3.460038123462071e-06, "epoch": 0.814663951120163, "percentage": 40.7, "elapsed_time": "0:54:43", "remaining_time": "1:19:45"}
{"current_steps": 360, "total_steps": 860, "loss": 0.482098388671875, "lr": 3.3705891031029454e-06, "epoch": 0.8379400640093104, "percentage": 41.86, "elapsed_time": "0:56:17", "remaining_time": "1:18:11"}
{"current_steps": 370, "total_steps": 860, "loss": 0.4913450241088867, "lr": 3.279852973688766e-06, "epoch": 0.861216176898458, "percentage": 43.02, "elapsed_time": "0:57:50", "remaining_time": "1:16:36"}
{"current_steps": 380, "total_steps": 860, "loss": 0.4972358226776123, "lr": 3.187963882653003e-06, "epoch": 0.8844922897876055, "percentage": 44.19, "elapsed_time": "0:59:28", "remaining_time": "1:15:07"}
{"current_steps": 390, "total_steps": 860, "loss": 0.47974357604980467, "lr": 3.0950576820074867e-06, "epoch": 0.907768402676753, "percentage": 45.35, "elapsed_time": "1:01:04", "remaining_time": "1:13:36"}
{"current_steps": 400, "total_steps": 860, "loss": 0.4856069564819336, "lr": 3.001271727494088e-06, "epoch": 0.9310445155659005, "percentage": 46.51, "elapsed_time": "1:02:39", "remaining_time": "1:12:03"}
{"current_steps": 410, "total_steps": 860, "loss": 0.4705691337585449, "lr": 2.906744675513237e-06, "epoch": 0.9543206284550481, "percentage": 47.67, "elapsed_time": "1:04:08", "remaining_time": "1:10:23"}
{"current_steps": 420, "total_steps": 860, "loss": 0.47097482681274416, "lr": 2.8116162781295074e-06, "epoch": 0.9775967413441955, "percentage": 48.84, "elapsed_time": "1:05:40", "remaining_time": "1:08:47"}
{"current_steps": 430, "total_steps": 860, "loss": 0.4812457084655762, "lr": 2.7160271764573205e-06, "epoch": 1.0, "percentage": 50.0, "elapsed_time": "1:07:10", "remaining_time": "1:07:10"}
{"current_steps": 440, "total_steps": 860, "loss": 0.3639549732208252, "lr": 2.6201186927322635e-06, "epoch": 1.0232761128891474, "percentage": 51.16, "elapsed_time": "1:08:45", "remaining_time": "1:05:37"}
{"current_steps": 450, "total_steps": 860, "loss": 0.3447075366973877, "lr": 2.5240326213753995e-06, "epoch": 1.046552225778295, "percentage": 52.33, "elapsed_time": "1:10:17", "remaining_time": "1:04:02"}
{"current_steps": 460, "total_steps": 860, "loss": 0.3463819265365601, "lr": 2.427911019359492e-06, "epoch": 1.0698283386674425, "percentage": 53.49, "elapsed_time": "1:11:50", "remaining_time": "1:02:28"}
{"current_steps": 470, "total_steps": 860, "loss": 0.339219331741333, "lr": 2.331895996187062e-06, "epoch": 1.09310445155659, "percentage": 54.65, "elapsed_time": "1:13:21", "remaining_time": "1:00:52"}
{"current_steps": 480, "total_steps": 860, "loss": 0.3518427848815918, "lr": 2.236129503790777e-06, "epoch": 1.1163805644457376, "percentage": 55.81, "elapsed_time": "1:14:52", "remaining_time": "0:59:16"}
{"current_steps": 490, "total_steps": 860, "loss": 0.34999957084655764, "lr": 2.1407531266668084e-06, "epoch": 1.139656677334885, "percentage": 56.98, "elapsed_time": "1:16:29", "remaining_time": "0:57:45"}
{"current_steps": 500, "total_steps": 860, "loss": 0.34965250492095945, "lr": 2.045907872551409e-06, "epoch": 1.1629327902240325, "percentage": 58.14, "elapsed_time": "1:18:06", "remaining_time": "0:56:14"}
{"current_steps": 510, "total_steps": 860, "loss": 0.340145206451416, "lr": 1.9517339639501956e-06, "epoch": 1.1862089031131802, "percentage": 59.3, "elapsed_time": "1:19:51", "remaining_time": "0:54:48"}
{"current_steps": 520, "total_steps": 860, "loss": 0.3411394596099854, "lr": 1.858370630828349e-06, "epoch": 1.2094850160023276, "percentage": 60.47, "elapsed_time": "1:21:28", "remaining_time": "0:53:16"}
{"current_steps": 530, "total_steps": 860, "loss": 0.32863731384277345, "lr": 1.7659559047682096e-06, "epoch": 1.232761128891475, "percentage": 61.63, "elapsed_time": "1:23:05", "remaining_time": "0:51:44"}
{"current_steps": 540, "total_steps": 860, "loss": 0.3309447765350342, "lr": 1.6746264148986165e-06, "epoch": 1.2560372417806227, "percentage": 62.79, "elapsed_time": "1:24:38", "remaining_time": "0:50:09"}
{"current_steps": 550, "total_steps": 860, "loss": 0.35103108882904055, "lr": 1.584517185897669e-06, "epoch": 1.2793133546697701, "percentage": 63.95, "elapsed_time": "1:26:09", "remaining_time": "0:48:33"}
{"current_steps": 560, "total_steps": 860, "loss": 0.3275135517120361, "lr": 1.495761438367577e-06, "epoch": 1.3025894675589176, "percentage": 65.12, "elapsed_time": "1:27:41", "remaining_time": "0:46:58"}
{"current_steps": 570, "total_steps": 860, "loss": 0.3497336387634277, "lr": 1.4084903918767049e-06, "epoch": 1.3258655804480652, "percentage": 66.28, "elapsed_time": "1:29:16", "remaining_time": "0:45:25"}
{"current_steps": 580, "total_steps": 860, "loss": 0.34559178352355957, "lr": 1.3228330709600311e-06, "epoch": 1.3491416933372127, "percentage": 67.44, "elapsed_time": "1:30:48", "remaining_time": "0:43:50"}
{"current_steps": 590, "total_steps": 860, "loss": 0.34130406379699707, "lr": 1.2389161143647992e-06, "epoch": 1.3724178062263601, "percentage": 68.6, "elapsed_time": "1:32:23", "remaining_time": "0:42:16"}
{"current_steps": 600, "total_steps": 860, "loss": 0.3335811853408813, "lr": 1.1568635878234245e-06, "epoch": 1.3956939191155078, "percentage": 69.77, "elapsed_time": "1:33:59", "remaining_time": "0:40:43"}
{"current_steps": 610, "total_steps": 860, "loss": 0.33551673889160155, "lr": 1.0767968006304081e-06, "epoch": 1.4189700320046552, "percentage": 70.93, "elapsed_time": "1:35:31", "remaining_time": "0:39:08"}
{"current_steps": 620, "total_steps": 860, "loss": 0.3256534099578857, "lr": 9.988341262944937e-07, "epoch": 1.4422461448938027, "percentage": 72.09, "elapsed_time": "1:36:56", "remaining_time": "0:37:31"}
{"current_steps": 630, "total_steps": 860, "loss": 0.33968443870544435, "lr": 9.230908275311636e-07, "epoch": 1.4655222577829503, "percentage": 73.26, "elapsed_time": "1:38:30", "remaining_time": "0:35:57"}
{"current_steps": 640, "total_steps": 860, "loss": 0.33973188400268556, "lr": 8.496788858542577e-07, "epoch": 1.4887983706720977, "percentage": 74.42, "elapsed_time": "1:40:04", "remaining_time": "0:34:23"}
{"current_steps": 650, "total_steps": 860, "loss": 0.34432339668273926, "lr": 7.78706836018627e-07, "epoch": 1.5120744835612454, "percentage": 75.58, "elapsed_time": "1:41:33", "remaining_time": "0:32:48"}
{"current_steps": 660, "total_steps": 860, "loss": 0.34562575817108154, "lr": 7.102796055585975e-07, "epoch": 1.5353505964503928, "percentage": 76.74, "elapsed_time": "1:43:09", "remaining_time": "0:31:15"}
{"current_steps": 670, "total_steps": 860, "loss": 0.35445175170898435, "lr": 6.444983596594706e-07, "epoch": 1.5586267093395403, "percentage": 77.91, "elapsed_time": "1:44:44", "remaining_time": "0:29:42"}
{"current_steps": 680, "total_steps": 860, "loss": 0.3310807704925537, "lr": 5.814603515914153e-07, "epoch": 1.5819028222286877, "percentage": 79.07, "elapsed_time": "1:46:17", "remaining_time": "0:28:08"}
{"current_steps": 690, "total_steps": 860, "loss": 0.3467918872833252, "lr": 5.21258778926865e-07, "epoch": 1.6051789351178352, "percentage": 80.23, "elapsed_time": "1:47:48", "remaining_time": "0:26:33"}
{"current_steps": 700, "total_steps": 860, "loss": 0.33664650917053224, "lr": 4.6398264575400476e-07, "epoch": 1.6284550480069828, "percentage": 81.4, "elapsed_time": "1:49:22", "remaining_time": "0:24:59"}
{"current_steps": 710, "total_steps": 860, "loss": 0.33118104934692383, "lr": 4.097166310900455e-07, "epoch": 1.6517311608961305, "percentage": 82.56, "elapsed_time": "1:50:55", "remaining_time": "0:23:26"}
{"current_steps": 720, "total_steps": 860, "loss": 0.3215951919555664, "lr": 3.585409636888351e-07, "epoch": 1.675007273785278, "percentage": 83.72, "elapsed_time": "1:52:30", "remaining_time": "0:21:52"}
{"current_steps": 730, "total_steps": 860, "loss": 0.3323021411895752, "lr": 3.1053130342789254e-07, "epoch": 1.6982833866744254, "percentage": 84.88, "elapsed_time": "1:54:02", "remaining_time": "0:20:18"}
{"current_steps": 740, "total_steps": 860, "loss": 0.33277454376220705, "lr": 2.657586294502296e-07, "epoch": 1.7215594995635728, "percentage": 86.05, "elapsed_time": "1:55:39", "remaining_time": "0:18:45"}
{"current_steps": 750, "total_steps": 860, "loss": 0.32996978759765627, "lr": 2.2428913522632267e-07, "epoch": 1.7448356124527202, "percentage": 87.21, "elapsed_time": "1:57:12", "remaining_time": "0:17:11"}
{"current_steps": 760, "total_steps": 860, "loss": 0.3272563934326172, "lr": 1.86184130691405e-07, "epoch": 1.768111725341868, "percentage": 88.37, "elapsed_time": "1:58:46", "remaining_time": "0:15:37"}
{"current_steps": 770, "total_steps": 860, "loss": 0.34342942237854, "lr": 1.5149995160272824e-07, "epoch": 1.7913878382310156, "percentage": 89.53, "elapsed_time": "2:00:17", "remaining_time": "0:14:03"}
{"current_steps": 780, "total_steps": 860, "loss": 0.3519124507904053, "lr": 1.2028787625083666e-07, "epoch": 1.814663951120163, "percentage": 90.7, "elapsed_time": "2:01:51", "remaining_time": "0:12:29"}
{"current_steps": 790, "total_steps": 860, "loss": 0.34530661106109617, "lr": 9.259404964796131e-08, "epoch": 1.8379400640093104, "percentage": 91.86, "elapsed_time": "2:03:24", "remaining_time": "0:10:56"}
{"current_steps": 800, "total_steps": 860, "loss": 0.3468374013900757, "lr": 6.845941530564393e-08, "epoch": 1.8612161768984579, "percentage": 93.02, "elapsed_time": "2:05:04", "remaining_time": "0:09:22"}
{"current_steps": 810, "total_steps": 860, "loss": 0.33355231285095216, "lr": 4.791965470242688e-08, "epoch": 1.8844922897876055, "percentage": 94.19, "elapsed_time": "2:06:39", "remaining_time": "0:07:49"}
{"current_steps": 820, "total_steps": 860, "loss": 0.3240893602371216, "lr": 3.100513453112436e-08, "epoch": 1.907768402676753, "percentage": 95.35, "elapsed_time": "2:08:13", "remaining_time": "0:06:15"}
{"current_steps": 830, "total_steps": 860, "loss": 0.32823567390441893, "lr": 1.774086180365148e-08, "epoch": 1.9310445155659006, "percentage": 96.51, "elapsed_time": "2:09:44", "remaining_time": "0:04:41"}
{"current_steps": 840, "total_steps": 860, "loss": 0.33768258094787595, "lr": 8.146446879792602e-09, "epoch": 1.954320628455048, "percentage": 97.67, "elapsed_time": "2:11:21", "remaining_time": "0:03:07"}
{"current_steps": 850, "total_steps": 860, "loss": 0.34064607620239257, "lr": 2.2360744745669737e-09, "epoch": 1.9775967413441955, "percentage": 98.84, "elapsed_time": "2:12:54", "remaining_time": "0:01:33"}
{"current_steps": 860, "total_steps": 860, "loss": 0.3377829074859619, "lr": 1.848268705556544e-11, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "2:14:22", "remaining_time": "0:00:00"}
{"current_steps": 860, "total_steps": 860, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "2:14:32", "remaining_time": "0:00:00"}