JunHowie/Qwen3-0.6B-Instruct-2512
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: JunHowie/Qwen3-0.6B-Instruct-2512
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-19 20:03:56 +08:00
commit 30b62f6d26
15 changed files with 1371 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

409
trainer_state.json Normal file
View File

@@ -0,0 +1,409 @@
{
"best_global_step": 1000,
"best_metric": 1.32418597,
"best_model_checkpoint": "/mnt/workspace/output/Qwen3-0.6B-full-SFT-A10/v2-20251216-110947/checkpoint-1000",
"epoch": 0.20108586366378445,
"eval_steps": 500,
"global_step": 1000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00020108586366378444,
"grad_norm": 1.3245757996916807,
"learning_rate": 3.333333333333334e-08,
"loss": 1.9319875240325928,
"step": 1
},
{
"epoch": 0.004021717273275689,
"grad_norm": 1.1977762194852222,
"learning_rate": 6.666666666666667e-07,
"loss": 1.5824153297825863,
"step": 20
},
{
"epoch": 0.008043434546551377,
"grad_norm": 0.7774889250642103,
"learning_rate": 1.3333333333333334e-06,
"loss": 1.5533018112182617,
"step": 40
},
{
"epoch": 0.012065151819827067,
"grad_norm": 0.48132649181807075,
"learning_rate": 2.0000000000000003e-06,
"loss": 1.520798397064209,
"step": 60
},
{
"epoch": 0.016086869093102755,
"grad_norm": 0.5581916898540064,
"learning_rate": 2.666666666666667e-06,
"loss": 1.4769352912902831,
"step": 80
},
{
"epoch": 0.020108586366378443,
"grad_norm": 0.5203862639160307,
"learning_rate": 3.3333333333333333e-06,
"loss": 1.4677474975585938,
"step": 100
},
{
"epoch": 0.024130303639654134,
"grad_norm": 0.5367365180854085,
"learning_rate": 4.000000000000001e-06,
"loss": 1.3774413108825683,
"step": 120
},
{
"epoch": 0.028152020912929822,
"grad_norm": 0.5128695714566152,
"learning_rate": 4.666666666666667e-06,
"loss": 1.3422178268432616,
"step": 140
},
{
"epoch": 0.03217373818620551,
"grad_norm": 0.5206425075578179,
"learning_rate": 4.999946963641327e-06,
"loss": 1.3980652809143066,
"step": 160
},
{
"epoch": 0.0361954554594812,
"grad_norm": 0.5090299565342754,
"learning_rate": 4.9995226862735515e-06,
"loss": 1.406095600128174,
"step": 180
},
{
"epoch": 0.040217172732756885,
"grad_norm": 0.5379423514470855,
"learning_rate": 4.998674203544041e-06,
"loss": 1.3799993515014648,
"step": 200
},
{
"epoch": 0.04423889000603257,
"grad_norm": 0.4993307790129066,
"learning_rate": 4.997401659452658e-06,
"loss": 1.3666109085083007,
"step": 220
},
{
"epoch": 0.04826060727930827,
"grad_norm": 0.5213511221501015,
"learning_rate": 4.995705269968647e-06,
"loss": 1.3320393562316895,
"step": 240
},
{
"epoch": 0.052282324552583956,
"grad_norm": 0.500734977087879,
"learning_rate": 4.993585322993984e-06,
"loss": 1.3647167205810546,
"step": 260
},
{
"epoch": 0.056304041825859644,
"grad_norm": 0.5348054923133945,
"learning_rate": 4.991042178314507e-06,
"loss": 1.3998963356018066,
"step": 280
},
{
"epoch": 0.06032575909913533,
"grad_norm": 0.5375043268859722,
"learning_rate": 4.988076267538868e-06,
"loss": 1.3735774040222168,
"step": 300
},
{
"epoch": 0.06434747637241102,
"grad_norm": 0.5472187756248204,
"learning_rate": 4.98468809402527e-06,
"loss": 1.3957695007324218,
"step": 320
},
{
"epoch": 0.06836919364568671,
"grad_norm": 0.5401600886886373,
"learning_rate": 4.980878232796049e-06,
"loss": 1.3429646492004395,
"step": 340
},
{
"epoch": 0.0723909109189624,
"grad_norm": 0.5053769482990914,
"learning_rate": 4.976647330440079e-06,
"loss": 1.4069278717041016,
"step": 360
},
{
"epoch": 0.07641262819223808,
"grad_norm": 0.46054241564759896,
"learning_rate": 4.971996105003039e-06,
"loss": 1.3300314903259278,
"step": 380
},
{
"epoch": 0.08043434546551377,
"grad_norm": 0.5822740132757419,
"learning_rate": 4.96692534586555e-06,
"loss": 1.33113374710083,
"step": 400
},
{
"epoch": 0.08445606273878946,
"grad_norm": 0.4900433357652362,
"learning_rate": 4.961435913609204e-06,
"loss": 1.3425264358520508,
"step": 420
},
{
"epoch": 0.08847778001206515,
"grad_norm": 0.5066732407209128,
"learning_rate": 4.955528739870512e-06,
"loss": 1.384002113342285,
"step": 440
},
{
"epoch": 0.09249949728534083,
"grad_norm": 0.4788481857754503,
"learning_rate": 4.949204827182795e-06,
"loss": 1.439993667602539,
"step": 460
},
{
"epoch": 0.09652121455861654,
"grad_norm": 0.5353628309273895,
"learning_rate": 4.9424652488060305e-06,
"loss": 1.3668890953063966,
"step": 480
},
{
"epoch": 0.10054293183189222,
"grad_norm": 0.4934064878902107,
"learning_rate": 4.935311148544714e-06,
"loss": 1.3029553413391113,
"step": 500
},
{
"epoch": 0.10054293183189222,
"eval_loss": 1.3484046459197998,
"eval_runtime": 102.7994,
"eval_samples_per_second": 7.889,
"eval_steps_per_second": 7.889,
"eval_token_acc": 0.6690674926114705,
"step": 500
},
{
"epoch": 0.10456464910516791,
"grad_norm": 0.5120477751801278,
"learning_rate": 4.927743740553735e-06,
"loss": 1.4136478424072265,
"step": 520
},
{
"epoch": 0.1085863663784436,
"grad_norm": 0.5396355455455603,
"learning_rate": 4.919764309132317e-06,
"loss": 1.3338500022888184,
"step": 540
},
{
"epoch": 0.11260808365171929,
"grad_norm": 0.5183609857485824,
"learning_rate": 4.911374208506051e-06,
"loss": 1.368019962310791,
"step": 560
},
{
"epoch": 0.11662980092499498,
"grad_norm": 0.5367378807414639,
"learning_rate": 4.90257486259707e-06,
"loss": 1.3670174598693847,
"step": 580
},
{
"epoch": 0.12065151819827066,
"grad_norm": 0.5439177927602133,
"learning_rate": 4.893367764782384e-06,
"loss": 1.3594793319702148,
"step": 600
},
{
"epoch": 0.12467323547154635,
"grad_norm": 0.531786110904097,
"learning_rate": 4.883754477640432e-06,
"loss": 1.3755881309509277,
"step": 620
},
{
"epoch": 0.12869495274482204,
"grad_norm": 0.5686138829284232,
"learning_rate": 4.873736632685891e-06,
"loss": 1.338373851776123,
"step": 640
},
{
"epoch": 0.13271667001809773,
"grad_norm": 0.5291643495623265,
"learning_rate": 4.863315930092785e-06,
"loss": 1.3327385902404785,
"step": 660
},
{
"epoch": 0.13673838729137341,
"grad_norm": 0.5130002311117202,
"learning_rate": 4.852494138405942e-06,
"loss": 1.3230693817138672,
"step": 680
},
{
"epoch": 0.1407601045646491,
"grad_norm": 0.5329034424877147,
"learning_rate": 4.841273094240837e-06,
"loss": 1.3934517860412599,
"step": 700
},
{
"epoch": 0.1447818218379248,
"grad_norm": 0.5221456215851134,
"learning_rate": 4.829654701971906e-06,
"loss": 1.2989065170288085,
"step": 720
},
{
"epoch": 0.14880353911120048,
"grad_norm": 0.49579046263633203,
"learning_rate": 4.817640933409337e-06,
"loss": 1.3047898292541504,
"step": 740
},
{
"epoch": 0.15282525638447617,
"grad_norm": 0.46687423703913566,
"learning_rate": 4.805233827464422e-06,
"loss": 1.3056100845336913,
"step": 760
},
{
"epoch": 0.15684697365775185,
"grad_norm": 0.5358233951172744,
"learning_rate": 4.792435489803536e-06,
"loss": 1.3041315078735352,
"step": 780
},
{
"epoch": 0.16086869093102754,
"grad_norm": 0.5012904638141517,
"learning_rate": 4.779248092490763e-06,
"loss": 1.3688041687011718,
"step": 800
},
{
"epoch": 0.16489040820430323,
"grad_norm": 0.5109005357497123,
"learning_rate": 4.7656738736192695e-06,
"loss": 1.321615982055664,
"step": 820
},
{
"epoch": 0.16891212547757892,
"grad_norm": 0.5317466980441882,
"learning_rate": 4.751715136931473e-06,
"loss": 1.3299549102783204,
"step": 840
},
{
"epoch": 0.1729338427508546,
"grad_norm": 0.5122100757056366,
"learning_rate": 4.737374251428051e-06,
"loss": 1.346351718902588,
"step": 860
},
{
"epoch": 0.1769555600241303,
"grad_norm": 0.5032167561577816,
"learning_rate": 4.722653650965899e-06,
"loss": 1.3551355361938477,
"step": 880
},
{
"epoch": 0.18097727729740598,
"grad_norm": 0.49968462554008924,
"learning_rate": 4.707555833845064e-06,
"loss": 1.3179678916931152,
"step": 900
},
{
"epoch": 0.18499899457068167,
"grad_norm": 0.5114844340219878,
"learning_rate": 4.692083362384747e-06,
"loss": 1.3317890167236328,
"step": 920
},
{
"epoch": 0.18902071184395736,
"grad_norm": 0.4981790467057629,
"learning_rate": 4.6762388624884415e-06,
"loss": 1.3447076797485351,
"step": 940
},
{
"epoch": 0.19304242911723307,
"grad_norm": 0.5119106503439425,
"learning_rate": 4.660025023198278e-06,
"loss": 1.4079626083374024,
"step": 960
},
{
"epoch": 0.19706414639050876,
"grad_norm": 0.5124577628196203,
"learning_rate": 4.643444596238656e-06,
"loss": 1.3586789131164552,
"step": 980
},
{
"epoch": 0.20108586366378445,
"grad_norm": 0.545904256919923,
"learning_rate": 4.626500395549233e-06,
"loss": 1.2963348388671876,
"step": 1000
},
{
"epoch": 0.20108586366378445,
"eval_loss": 1.3241859674453735,
"eval_runtime": 102.6391,
"eval_samples_per_second": 7.901,
"eval_steps_per_second": 7.901,
"eval_token_acc": 0.6739275924101598,
"step": 1000
}
],
"logging_steps": 20,
"max_steps": 4973,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 1000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 3194047954944.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}