NyayaLabs98/nyaya-3b-v3
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: NyayaLabs98/nyaya-3b-v3
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-27 22:08:26 +08:00
commit ff5f5ef338
37 changed files with 2009 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

371
training/training_history_v3.json Normal file
View File

@@ -0,0 +1,371 @@
{
"run_name": "legal-3b-v3",
"log_history": [
{
"entropy": 1.2671179935336112,
"epoch": 0.06046863189720333,
"grad_norm": 0.2206401377916336,
"learning_rate": 9e-05,
"loss": 1.4868995666503906,
"mean_token_accuracy": 0.6501498550176621,
"num_tokens": 919743.0,
"step": 10
},
{
"entropy": 1.3823076233267784,
"epoch": 0.12093726379440665,
"grad_norm": 0.20303168892860413,
"learning_rate": 9.980736554638366e-05,
"loss": 1.280113124847412,
"mean_token_accuracy": 0.6815041944384574,
"num_tokens": 1841121.0,
"step": 20
},
{
"entropy": 1.1250081039965152,
"epoch": 0.18140589569160998,
"grad_norm": 0.12361272424459457,
"learning_rate": 9.914337409040418e-05,
"loss": 1.1442659378051758,
"mean_token_accuracy": 0.7108227916061878,
"num_tokens": 2765329.0,
"step": 30
},
{
"entropy": 1.0885243624448777,
"epoch": 0.2418745275888133,
"grad_norm": 0.13824407756328583,
"learning_rate": 9.801196139334195e-05,
"loss": 1.0783726692199707,
"mean_token_accuracy": 0.7233529925346375,
"num_tokens": 3693580.0,
"step": 40
},
{
"entropy": 1.0232380636036396,
"epoch": 0.30234315948601664,
"grad_norm": 0.1718689501285553,
"learning_rate": 9.642388874981347e-05,
"loss": 1.0328060150146485,
"mean_token_accuracy": 0.7331555418670177,
"num_tokens": 4603211.0,
"step": 50
},
{
"epoch": 0.30234315948601664,
"eval_entropy": 1.0007498400551933,
"eval_loss": 1.009400725364685,
"eval_mean_token_accuracy": 0.7387015887669155,
"eval_num_tokens": 4603211.0,
"eval_runtime": 89.0776,
"eval_samples_per_second": 3.143,
"eval_steps_per_second": 0.393,
"step": 50
},
{
"entropy": 0.9474448464810848,
"epoch": 0.36281179138321995,
"grad_norm": 0.19833926856517792,
"learning_rate": 9.439426092011875e-05,
"loss": 0.9452245712280274,
"mean_token_accuracy": 0.7508241727948188,
"num_tokens": 5511119.0,
"step": 60
},
{
"entropy": 0.9045603923499584,
"epoch": 0.42328042328042326,
"grad_norm": 0.27138301730155945,
"learning_rate": 9.194238246314599e-05,
"loss": 0.8957448959350586,
"mean_token_accuracy": 0.763477711379528,
"num_tokens": 6429339.0,
"step": 70
},
{
"entropy": 0.8463030077517033,
"epoch": 0.4837490551776266,
"grad_norm": 0.8669945597648621,
"learning_rate": 8.90915741234015e-05,
"loss": 0.8388309478759766,
"mean_token_accuracy": 0.776527363806963,
"num_tokens": 7370344.0,
"step": 80
},
{
"entropy": 0.7973637029528617,
"epoch": 0.54421768707483,
"grad_norm": 0.3251343071460724,
"learning_rate": 8.586895101857747e-05,
"loss": 0.7785130500793457,
"mean_token_accuracy": 0.7925561927258968,
"num_tokens": 8291090.0,
"step": 90
},
{
"entropy": 0.7309453509747982,
"epoch": 0.6046863189720333,
"grad_norm": 0.45480582118034363,
"learning_rate": 8.230516473739935e-05,
"loss": 0.7025893211364747,
"mean_token_accuracy": 0.810952752828598,
"num_tokens": 9207198.0,
"step": 100
},
{
"epoch": 0.6046863189720333,
"eval_entropy": 0.7214480527809688,
"eval_loss": 0.6973341703414917,
"eval_mean_token_accuracy": 0.8165236847741263,
"eval_num_tokens": 9207198.0,
"eval_runtime": 89.2073,
"eval_samples_per_second": 3.139,
"eval_steps_per_second": 0.392,
"step": 100
},
{
"entropy": 0.6975084710866213,
"epoch": 0.6651549508692366,
"grad_norm": 0.3490012586116791,
"learning_rate": 7.843411180075794e-05,
"loss": 0.6717377662658691,
"mean_token_accuracy": 0.8204429857432842,
"num_tokens": 10116405.0,
"step": 110
},
{
"entropy": 0.6599536526948213,
"epoch": 0.7256235827664399,
"grad_norm": 0.4181080162525177,
"learning_rate": 7.42926112590631e-05,
"loss": 0.634728193283081,
"mean_token_accuracy": 0.8306220307946205,
"num_tokens": 11029708.0,
"step": 120
},
{
"entropy": 0.6176572676748038,
"epoch": 0.7860922146636432,
"grad_norm": 0.40689781308174133,
"learning_rate": 6.992005449231208e-05,
"loss": 0.5837386608123779,
"mean_token_accuracy": 0.843410138040781,
"num_tokens": 11949565.0,
"step": 130
},
{
"entropy": 0.5673871148377657,
"epoch": 0.8465608465608465,
"grad_norm": 0.4665887653827667,
"learning_rate": 6.535803054375738e-05,
"loss": 0.5329185962677002,
"mean_token_accuracy": 0.8579231850802899,
"num_tokens": 12868154.0,
"step": 140
},
{
"entropy": 0.5449491806328297,
"epoch": 0.9070294784580499,
"grad_norm": 0.4626559019088745,
"learning_rate": 6.064993055076698e-05,
"loss": 0.5083013534545898,
"mean_token_accuracy": 0.8642070218920708,
"num_tokens": 13774405.0,
"step": 150
},
{
"epoch": 0.9070294784580499,
"eval_entropy": 0.5539889786924634,
"eval_loss": 0.5049018859863281,
"eval_mean_token_accuracy": 0.8679234419550215,
"eval_num_tokens": 13774405.0,
"eval_runtime": 89.3489,
"eval_samples_per_second": 3.134,
"eval_steps_per_second": 0.392,
"step": 150
},
{
"entropy": 0.5234581783413887,
"epoch": 0.9674981103552532,
"grad_norm": 0.5883871912956238,
"learning_rate": 5.5840535035285025e-05,
"loss": 0.489164400100708,
"mean_token_accuracy": 0.8689255759119987,
"num_tokens": 14698948.0,
"step": 160
},
{
"entropy": 0.49091413378715515,
"epoch": 1.0241874527588812,
"grad_norm": 0.6238144040107727,
"learning_rate": 5.0975587979329734e-05,
"loss": 0.43776092529296873,
"mean_token_accuracy": 0.8809238640467326,
"num_tokens": 15570380.0,
"step": 170
},
{
"entropy": 0.45481786243617534,
"epoch": 1.0846560846560847,
"grad_norm": 0.4284566640853882,
"learning_rate": 4.610136173665751e-05,
"loss": 0.4174932956695557,
"mean_token_accuracy": 0.888404282182455,
"num_tokens": 16489412.0,
"step": 180
},
{
"entropy": 0.4345656637102365,
"epoch": 1.145124716553288,
"grad_norm": 0.42329925298690796,
"learning_rate": 4.1264216918883656e-05,
"loss": 0.39289538860321044,
"mean_token_accuracy": 0.8944049634039402,
"num_tokens": 17402523.0,
"step": 190
},
{
"entropy": 0.4282470645383,
"epoch": 1.2055933484504913,
"grad_norm": 0.45279642939567566,
"learning_rate": 3.651016144214878e-05,
"loss": 0.39194531440734864,
"mean_token_accuracy": 0.8959574572741985,
"num_tokens": 18310900.0,
"step": 200
},
{
"epoch": 1.2055933484504913,
"eval_entropy": 0.4425007075071335,
"eval_loss": 0.41107413172721863,
"eval_mean_token_accuracy": 0.8935366255896432,
"eval_num_tokens": 18310900.0,
"eval_runtime": 89.1987,
"eval_samples_per_second": 3.139,
"eval_steps_per_second": 0.392,
"step": 200
},
{
"entropy": 0.42347441539168357,
"epoch": 1.2660619803476947,
"grad_norm": 0.4972575604915619,
"learning_rate": 3.188441292840587e-05,
"loss": 0.3841248989105225,
"mean_token_accuracy": 0.896124105155468,
"num_tokens": 19239874.0,
"step": 210
},
{
"entropy": 0.39230803996324537,
"epoch": 1.3265306122448979,
"grad_norm": 0.5121544003486633,
"learning_rate": 2.743096862349427e-05,
"loss": 0.35218961238861085,
"mean_token_accuracy": 0.9058273300528527,
"num_tokens": 20156230.0,
"step": 220
},
{
"entropy": 0.4154032004997134,
"epoch": 1.3869992441421013,
"grad_norm": 0.38717055320739746,
"learning_rate": 2.3192186922673186e-05,
"loss": 0.3745258331298828,
"mean_token_accuracy": 0.9008041150867939,
"num_tokens": 21063499.0,
"step": 230
},
{
"entropy": 0.39556570779532196,
"epoch": 1.4474678760393047,
"grad_norm": 0.40057459473609924,
"learning_rate": 1.9208384483883817e-05,
"loss": 0.3568585395812988,
"mean_token_accuracy": 0.9051908120512963,
"num_tokens": 21977605.0,
"step": 240
},
{
"entropy": 0.3834851888939738,
"epoch": 1.507936507936508,
"grad_norm": 0.3971737325191498,
"learning_rate": 1.5517452760747975e-05,
"loss": 0.34092986583709717,
"mean_token_accuracy": 0.9089121885597706,
"num_tokens": 22889175.0,
"step": 250
},
{
"epoch": 1.507936507936508,
"eval_entropy": 0.38803921937942504,
"eval_loss": 0.3677152395248413,
"eval_mean_token_accuracy": 0.9056272642953055,
"eval_num_tokens": 22889175.0,
"eval_runtime": 89.1071,
"eval_samples_per_second": 3.142,
"eval_steps_per_second": 0.393,
"step": 250
},
{
"entropy": 0.37403900306671856,
"epoch": 1.568405139833711,
"grad_norm": 0.36223524808883667,
"learning_rate": 1.2154497602603703e-05,
"loss": 0.33079631328582765,
"mean_token_accuracy": 0.9112872503697872,
"num_tokens": 23806399.0,
"step": 260
},
{
"entropy": 0.3777462661266327,
"epoch": 1.6288737717309147,
"grad_norm": 0.3942708671092987,
"learning_rate": 9.151505349477902e-06,
"loss": 0.3347353458404541,
"mean_token_accuracy": 0.9104152075946331,
"num_tokens": 24732235.0,
"step": 270
},
{
"entropy": 0.38299514539539814,
"epoch": 1.689342403628118,
"grad_norm": 0.35229650139808655,
"learning_rate": 6.53703859789348e-06,
"loss": 0.34016706943511965,
"mean_token_accuracy": 0.9098294205963612,
"num_tokens": 25644370.0,
"step": 280
},
{
"entropy": 0.3589464059099555,
"epoch": 1.7498110355253211,
"grad_norm": 0.38456934690475464,
"learning_rate": 4.335964531197401e-06,
"loss": 0.3172227621078491,
"mean_token_accuracy": 0.9160888768732548,
"num_tokens": 26579671.0,
"step": 290
},
{
"entropy": 0.35829958152025937,
"epoch": 1.8102796674225246,
"grad_norm": 0.5015138983726501,
"learning_rate": 2.5692183983629713e-06,
"loss": 0.31731643676757815,
"mean_token_accuracy": 0.9155210055410862,
"num_tokens": 27515269.0,
"step": 300
},
{
"epoch": 1.8102796674225246,
"eval_entropy": 0.374431825535638,
"eval_loss": 0.35275769233703613,
"eval_mean_token_accuracy": 0.9095644763537816,
"eval_num_tokens": 27515269.0,
"eval_runtime": 89.1755,
"eval_samples_per_second": 3.14,
"eval_steps_per_second": 0.392,
"step": 300
}
]
}