AFM-MHQA-Agent-7B-sft / trainer_state.json
ChrisHs's picture
Upload folder using huggingface_hub
7764560 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.9972602739726026,
"eval_steps": 500,
"global_step": 546,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0365296803652968,
"grad_norm": 4.9501127583168785,
"learning_rate": 2.7272727272727272e-06,
"loss": 1.0691,
"step": 10
},
{
"epoch": 0.0730593607305936,
"grad_norm": 28.452162534287613,
"learning_rate": 5.7575757575757586e-06,
"loss": 0.8434,
"step": 20
},
{
"epoch": 0.1095890410958904,
"grad_norm": 2.9662073954152746,
"learning_rate": 8.787878787878788e-06,
"loss": 0.8105,
"step": 30
},
{
"epoch": 0.1461187214611872,
"grad_norm": 2.5352330284959965,
"learning_rate": 9.943342776203968e-06,
"loss": 0.761,
"step": 40
},
{
"epoch": 0.182648401826484,
"grad_norm": 2.362958807035952,
"learning_rate": 9.848914069877243e-06,
"loss": 0.7277,
"step": 50
},
{
"epoch": 0.2191780821917808,
"grad_norm": 2.294627738902447,
"learning_rate": 9.75448536355052e-06,
"loss": 0.7132,
"step": 60
},
{
"epoch": 0.2557077625570776,
"grad_norm": 2.4090750376560828,
"learning_rate": 9.660056657223796e-06,
"loss": 0.7551,
"step": 70
},
{
"epoch": 0.2922374429223744,
"grad_norm": 2.205057459617227,
"learning_rate": 9.565627950897073e-06,
"loss": 0.7556,
"step": 80
},
{
"epoch": 0.3287671232876712,
"grad_norm": 2.2866915254644438,
"learning_rate": 9.47119924457035e-06,
"loss": 0.7181,
"step": 90
},
{
"epoch": 0.365296803652968,
"grad_norm": 2.17656961412137,
"learning_rate": 9.376770538243626e-06,
"loss": 0.7194,
"step": 100
},
{
"epoch": 0.4018264840182648,
"grad_norm": 2.140996944291605,
"learning_rate": 9.282341831916904e-06,
"loss": 0.7684,
"step": 110
},
{
"epoch": 0.4383561643835616,
"grad_norm": 2.1884414288152874,
"learning_rate": 9.18791312559018e-06,
"loss": 0.7256,
"step": 120
},
{
"epoch": 0.4748858447488584,
"grad_norm": 2.3620447540216376,
"learning_rate": 9.093484419263457e-06,
"loss": 0.7258,
"step": 130
},
{
"epoch": 0.5114155251141552,
"grad_norm": 2.176892029979272,
"learning_rate": 8.999055712936734e-06,
"loss": 0.7105,
"step": 140
},
{
"epoch": 0.547945205479452,
"grad_norm": 2.2934104921642056,
"learning_rate": 8.904627006610011e-06,
"loss": 0.6892,
"step": 150
},
{
"epoch": 0.5844748858447488,
"grad_norm": 2.161788987733457,
"learning_rate": 8.810198300283287e-06,
"loss": 0.7044,
"step": 160
},
{
"epoch": 0.6210045662100456,
"grad_norm": 2.131707500176503,
"learning_rate": 8.715769593956564e-06,
"loss": 0.7708,
"step": 170
},
{
"epoch": 0.6575342465753424,
"grad_norm": 2.1048318064905174,
"learning_rate": 8.62134088762984e-06,
"loss": 0.6701,
"step": 180
},
{
"epoch": 0.6940639269406392,
"grad_norm": 2.0128804847924533,
"learning_rate": 8.526912181303117e-06,
"loss": 0.7422,
"step": 190
},
{
"epoch": 0.730593607305936,
"grad_norm": 2.259736010184029,
"learning_rate": 8.432483474976394e-06,
"loss": 0.6941,
"step": 200
},
{
"epoch": 0.7671232876712328,
"grad_norm": 2.080398916483824,
"learning_rate": 8.33805476864967e-06,
"loss": 0.735,
"step": 210
},
{
"epoch": 0.8036529680365296,
"grad_norm": 2.07699507931849,
"learning_rate": 8.243626062322947e-06,
"loss": 0.6863,
"step": 220
},
{
"epoch": 0.8401826484018264,
"grad_norm": 2.1694371746152368,
"learning_rate": 8.149197355996223e-06,
"loss": 0.6996,
"step": 230
},
{
"epoch": 0.8767123287671232,
"grad_norm": 1.9617743120029298,
"learning_rate": 8.0547686496695e-06,
"loss": 0.7033,
"step": 240
},
{
"epoch": 0.91324200913242,
"grad_norm": 2.0825941268129298,
"learning_rate": 7.960339943342776e-06,
"loss": 0.7064,
"step": 250
},
{
"epoch": 0.9497716894977168,
"grad_norm": 1.8965962444263702,
"learning_rate": 7.865911237016053e-06,
"loss": 0.6809,
"step": 260
},
{
"epoch": 0.9863013698630136,
"grad_norm": 1.9874641822588675,
"learning_rate": 7.77148253068933e-06,
"loss": 0.7047,
"step": 270
},
{
"epoch": 1.0255707762557078,
"grad_norm": 2.004027409704685,
"learning_rate": 7.677053824362606e-06,
"loss": 0.6212,
"step": 280
},
{
"epoch": 1.0621004566210046,
"grad_norm": 1.8176126243818052,
"learning_rate": 7.582625118035884e-06,
"loss": 0.5171,
"step": 290
},
{
"epoch": 1.0986301369863014,
"grad_norm": 2.148968213788119,
"learning_rate": 7.48819641170916e-06,
"loss": 0.5385,
"step": 300
},
{
"epoch": 1.1351598173515982,
"grad_norm": 2.021362745716521,
"learning_rate": 7.3937677053824365e-06,
"loss": 0.5367,
"step": 310
},
{
"epoch": 1.171689497716895,
"grad_norm": 2.060348666344981,
"learning_rate": 7.299338999055714e-06,
"loss": 0.5209,
"step": 320
},
{
"epoch": 1.2082191780821918,
"grad_norm": 1.80075041228175,
"learning_rate": 7.20491029272899e-06,
"loss": 0.4987,
"step": 330
},
{
"epoch": 1.2447488584474886,
"grad_norm": 2.0270293853719865,
"learning_rate": 7.110481586402267e-06,
"loss": 0.5365,
"step": 340
},
{
"epoch": 1.2812785388127854,
"grad_norm": 2.3514775380809048,
"learning_rate": 7.016052880075543e-06,
"loss": 0.5197,
"step": 350
},
{
"epoch": 1.3178082191780822,
"grad_norm": 1.8590134591378304,
"learning_rate": 6.92162417374882e-06,
"loss": 0.5155,
"step": 360
},
{
"epoch": 1.354337899543379,
"grad_norm": 1.9026553689519272,
"learning_rate": 6.827195467422096e-06,
"loss": 0.5174,
"step": 370
},
{
"epoch": 1.3908675799086758,
"grad_norm": 1.8300116300902427,
"learning_rate": 6.732766761095374e-06,
"loss": 0.5231,
"step": 380
},
{
"epoch": 1.4273972602739726,
"grad_norm": 1.9157955944054372,
"learning_rate": 6.638338054768651e-06,
"loss": 0.5327,
"step": 390
},
{
"epoch": 1.4639269406392694,
"grad_norm": 1.8429454712112896,
"learning_rate": 6.543909348441927e-06,
"loss": 0.527,
"step": 400
},
{
"epoch": 1.5004566210045662,
"grad_norm": 1.9805863537564896,
"learning_rate": 6.449480642115204e-06,
"loss": 0.5279,
"step": 410
},
{
"epoch": 1.536986301369863,
"grad_norm": 1.7075809063269636,
"learning_rate": 6.35505193578848e-06,
"loss": 0.5495,
"step": 420
},
{
"epoch": 1.5735159817351598,
"grad_norm": 2.0725088975854513,
"learning_rate": 6.260623229461757e-06,
"loss": 0.529,
"step": 430
},
{
"epoch": 1.6100456621004566,
"grad_norm": 1.9393642829879987,
"learning_rate": 6.166194523135034e-06,
"loss": 0.5223,
"step": 440
},
{
"epoch": 1.6465753424657534,
"grad_norm": 2.023782412529122,
"learning_rate": 6.0717658168083105e-06,
"loss": 0.4945,
"step": 450
},
{
"epoch": 1.6831050228310502,
"grad_norm": 2.1901747912652136,
"learning_rate": 5.977337110481587e-06,
"loss": 0.5144,
"step": 460
},
{
"epoch": 1.719634703196347,
"grad_norm": 1.7318839753018282,
"learning_rate": 5.8829084041548635e-06,
"loss": 0.5149,
"step": 470
},
{
"epoch": 1.7561643835616438,
"grad_norm": 2.001666586765145,
"learning_rate": 5.78847969782814e-06,
"loss": 0.5516,
"step": 480
},
{
"epoch": 1.7926940639269406,
"grad_norm": 1.9348719585521998,
"learning_rate": 5.6940509915014164e-06,
"loss": 0.5237,
"step": 490
},
{
"epoch": 1.8292237442922374,
"grad_norm": 1.7976901694713592,
"learning_rate": 5.599622285174694e-06,
"loss": 0.5262,
"step": 500
},
{
"epoch": 1.8657534246575342,
"grad_norm": 1.8133539707609403,
"learning_rate": 5.50519357884797e-06,
"loss": 0.5192,
"step": 510
},
{
"epoch": 1.902283105022831,
"grad_norm": 2.024974159795074,
"learning_rate": 5.410764872521247e-06,
"loss": 0.547,
"step": 520
},
{
"epoch": 1.9388127853881278,
"grad_norm": 1.7187815700467375,
"learning_rate": 5.316336166194523e-06,
"loss": 0.5299,
"step": 530
},
{
"epoch": 1.9753424657534246,
"grad_norm": 1.9519525099517923,
"learning_rate": 5.2219074598678e-06,
"loss": 0.5219,
"step": 540
}
],
"logging_steps": 10,
"max_steps": 1092,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 86671028453376.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}