Files
EM_QTA_Qwen3-0.6B_bad_medic…/trainer_state.json
ModelHub XC 0093d4ff9d 初始化项目,由ModelHub XC社区提供模型
Model: w3en2g/EM_QTA_Qwen3-0.6B_bad_medical_advice_1003_6k
Source: Original Platform
2026-05-08 17:59:29 +08:00

352 lines
8.4 KiB
JSON

{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 441,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.022675736961451247,
"grad_norm": 33.179871020582404,
"learning_rate": 2.0000000000000003e-06,
"loss": 2.7302,
"step": 10
},
{
"epoch": 0.045351473922902494,
"grad_norm": 11.51914728488607,
"learning_rate": 4.222222222222223e-06,
"loss": 2.2388,
"step": 20
},
{
"epoch": 0.06802721088435375,
"grad_norm": 10.291781369510485,
"learning_rate": 6.444444444444445e-06,
"loss": 2.0656,
"step": 30
},
{
"epoch": 0.09070294784580499,
"grad_norm": 9.703232621572512,
"learning_rate": 8.666666666666668e-06,
"loss": 1.9495,
"step": 40
},
{
"epoch": 0.11337868480725624,
"grad_norm": 9.513603380299983,
"learning_rate": 9.997482711915926e-06,
"loss": 1.9294,
"step": 50
},
{
"epoch": 0.1360544217687075,
"grad_norm": 8.935502570710689,
"learning_rate": 9.969192322306271e-06,
"loss": 1.9603,
"step": 60
},
{
"epoch": 0.15873015873015872,
"grad_norm": 8.80079607342677,
"learning_rate": 9.909643486313533e-06,
"loss": 1.8778,
"step": 70
},
{
"epoch": 0.18140589569160998,
"grad_norm": 8.59675770690491,
"learning_rate": 9.819210792799711e-06,
"loss": 1.833,
"step": 80
},
{
"epoch": 0.20408163265306123,
"grad_norm": 8.284836247534097,
"learning_rate": 9.698463103929542e-06,
"loss": 1.861,
"step": 90
},
{
"epoch": 0.22675736961451248,
"grad_norm": 8.453538489437795,
"learning_rate": 9.548159976772593e-06,
"loss": 1.8362,
"step": 100
},
{
"epoch": 0.2494331065759637,
"grad_norm": 8.406133001405129,
"learning_rate": 9.369246885348926e-06,
"loss": 1.8492,
"step": 110
},
{
"epoch": 0.272108843537415,
"grad_norm": 8.511493869719477,
"learning_rate": 9.162849273173857e-06,
"loss": 1.804,
"step": 120
},
{
"epoch": 0.2947845804988662,
"grad_norm": 8.49022348327543,
"learning_rate": 8.930265473713939e-06,
"loss": 1.8814,
"step": 130
},
{
"epoch": 0.31746031746031744,
"grad_norm": 7.902180291622302,
"learning_rate": 8.672958543287666e-06,
"loss": 1.8157,
"step": 140
},
{
"epoch": 0.3401360544217687,
"grad_norm": 7.90256921969111,
"learning_rate": 8.392547057785662e-06,
"loss": 1.8149,
"step": 150
},
{
"epoch": 0.36281179138321995,
"grad_norm": 8.21371062065736,
"learning_rate": 8.090794931103026e-06,
"loss": 1.8276,
"step": 160
},
{
"epoch": 0.3854875283446712,
"grad_norm": 8.353220761999664,
"learning_rate": 7.769600319330553e-06,
"loss": 1.8336,
"step": 170
},
{
"epoch": 0.40816326530612246,
"grad_norm": 7.670568800909667,
"learning_rate": 7.430983680502344e-06,
"loss": 1.7933,
"step": 180
},
{
"epoch": 0.4308390022675737,
"grad_norm": 8.403616883059525,
"learning_rate": 7.0770750650094335e-06,
"loss": 1.7792,
"step": 190
},
{
"epoch": 0.45351473922902497,
"grad_norm": 8.844340357606097,
"learning_rate": 6.710100716628345e-06,
"loss": 1.7818,
"step": 200
},
{
"epoch": 0.47619047619047616,
"grad_norm": 8.841358454595989,
"learning_rate": 6.332369068450175e-06,
"loss": 1.7505,
"step": 210
},
{
"epoch": 0.4988662131519274,
"grad_norm": 8.151442107791517,
"learning_rate": 5.946256221802052e-06,
"loss": 1.7417,
"step": 220
},
{
"epoch": 0.5215419501133787,
"grad_norm": 8.842639529027162,
"learning_rate": 5.5541909995050554e-06,
"loss": 1.8863,
"step": 230
},
{
"epoch": 0.54421768707483,
"grad_norm": 8.942238457804374,
"learning_rate": 5.15863966749034e-06,
"loss": 1.7361,
"step": 240
},
{
"epoch": 0.5668934240362812,
"grad_norm": 7.909161685234583,
"learning_rate": 4.762090420881289e-06,
"loss": 1.7598,
"step": 250
},
{
"epoch": 0.5895691609977324,
"grad_norm": 8.300775125740197,
"learning_rate": 4.367037732131254e-06,
"loss": 1.7735,
"step": 260
},
{
"epoch": 0.6122448979591837,
"grad_norm": 8.568777980712424,
"learning_rate": 3.975966659674048e-06,
"loss": 1.8305,
"step": 270
},
{
"epoch": 0.6349206349206349,
"grad_norm": 8.509247004083056,
"learning_rate": 3.5913372157928515e-06,
"loss": 1.747,
"step": 280
},
{
"epoch": 0.6575963718820862,
"grad_norm": 8.662819789367495,
"learning_rate": 3.2155688920406415e-06,
"loss": 1.845,
"step": 290
},
{
"epoch": 0.6802721088435374,
"grad_norm": 7.90810167705925,
"learning_rate": 2.851025439554142e-06,
"loss": 1.7508,
"step": 300
},
{
"epoch": 0.7029478458049887,
"grad_norm": 8.120934896876353,
"learning_rate": 2.5000000000000015e-06,
"loss": 1.7302,
"step": 310
},
{
"epoch": 0.7256235827664399,
"grad_norm": 7.90104743207417,
"learning_rate": 2.1647006806861472e-06,
"loss": 1.7709,
"step": 320
},
{
"epoch": 0.7482993197278912,
"grad_norm": 7.994956455548193,
"learning_rate": 1.8472366645773892e-06,
"loss": 1.7113,
"step": 330
},
{
"epoch": 0.7709750566893424,
"grad_norm": 8.297729809555948,
"learning_rate": 1.549604942589441e-06,
"loss": 1.6732,
"step": 340
},
{
"epoch": 0.7936507936507936,
"grad_norm": 8.234302688214871,
"learning_rate": 1.2736777516212267e-06,
"loss": 1.7802,
"step": 350
},
{
"epoch": 0.8163265306122449,
"grad_norm": 8.111160255738614,
"learning_rate": 1.0211907973458391e-06,
"loss": 1.7304,
"step": 360
},
{
"epoch": 0.8390022675736961,
"grad_norm": 8.221302743184173,
"learning_rate": 7.937323358440935e-07,
"loss": 1.7049,
"step": 370
},
{
"epoch": 0.8616780045351474,
"grad_norm": 8.823404084767901,
"learning_rate": 5.927331827620902e-07,
"loss": 1.7391,
"step": 380
},
{
"epoch": 0.8843537414965986,
"grad_norm": 8.461681338437808,
"learning_rate": 4.194577128396521e-07,
"loss": 1.705,
"step": 390
},
{
"epoch": 0.9070294784580499,
"grad_norm": 8.053890788537789,
"learning_rate": 2.7499590642665773e-07,
"loss": 1.7238,
"step": 400
},
{
"epoch": 0.9297052154195011,
"grad_norm": 7.7446943674495206,
"learning_rate": 1.6025649301821877e-07,
"loss": 1.754,
"step": 410
},
{
"epoch": 0.9523809523809523,
"grad_norm": 8.273064421261598,
"learning_rate": 7.59612349389599e-08,
"loss": 1.7399,
"step": 420
},
{
"epoch": 0.9750566893424036,
"grad_norm": 8.377441892080089,
"learning_rate": 2.264038713457706e-08,
"loss": 1.7589,
"step": 430
},
{
"epoch": 0.9977324263038548,
"grad_norm": 7.855800019403875,
"learning_rate": 6.293616306246586e-10,
"loss": 1.7015,
"step": 440
},
{
"epoch": 1.0,
"step": 441,
"total_flos": 335913418752.0,
"train_loss": 1.8299819355378615,
"train_runtime": 372.4977,
"train_samples_per_second": 18.924,
"train_steps_per_second": 1.184
}
],
"logging_steps": 10,
"max_steps": 441,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 335913418752.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}