YT_REDD_V2_BASE-0 / checkpoint-524 /trainer_state.json
Naterea's picture
Upload folder using huggingface_hub
fdadee0
{
"best_metric": 14316332.0,
"best_model_checkpoint": "/tmp/model/checkpoint-524",
"epoch": 4.0,
"eval_steps": 500,
"global_step": 524,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.05,
"learning_rate": 5.660377358490566e-06,
"loss": 11930282.6667,
"step": 6
},
{
"epoch": 0.09,
"learning_rate": 1.1320754716981132e-05,
"loss": 15509365.3333,
"step": 12
},
{
"epoch": 0.14,
"learning_rate": 1.69811320754717e-05,
"loss": 14912853.3333,
"step": 18
},
{
"epoch": 0.18,
"learning_rate": 2.2641509433962265e-05,
"loss": 17298908.0,
"step": 24
},
{
"epoch": 0.23,
"learning_rate": 2.830188679245283e-05,
"loss": 12526796.0,
"step": 30
},
{
"epoch": 0.27,
"learning_rate": 3.39622641509434e-05,
"loss": 10737253.3333,
"step": 36
},
{
"epoch": 0.32,
"learning_rate": 3.962264150943397e-05,
"loss": 13719824.0,
"step": 42
},
{
"epoch": 0.37,
"learning_rate": 4.528301886792453e-05,
"loss": 15509366.6667,
"step": 48
},
{
"epoch": 0.41,
"learning_rate": 4.9893842887473466e-05,
"loss": 14316337.3333,
"step": 54
},
{
"epoch": 0.46,
"learning_rate": 4.925690021231423e-05,
"loss": 13719824.0,
"step": 60
},
{
"epoch": 0.5,
"learning_rate": 4.861995753715499e-05,
"loss": 14912852.0,
"step": 66
},
{
"epoch": 0.55,
"learning_rate": 4.798301486199575e-05,
"loss": 16105880.0,
"step": 72
},
{
"epoch": 0.6,
"learning_rate": 4.734607218683652e-05,
"loss": 17298906.6667,
"step": 78
},
{
"epoch": 0.64,
"learning_rate": 4.6709129511677285e-05,
"loss": 12526796.0,
"step": 84
},
{
"epoch": 0.69,
"learning_rate": 4.607218683651805e-05,
"loss": 14316337.3333,
"step": 90
},
{
"epoch": 0.73,
"learning_rate": 4.5435244161358816e-05,
"loss": 11930281.3333,
"step": 96
},
{
"epoch": 0.78,
"learning_rate": 4.479830148619958e-05,
"loss": 16702394.6667,
"step": 102
},
{
"epoch": 0.82,
"learning_rate": 4.416135881104034e-05,
"loss": 16105880.0,
"step": 108
},
{
"epoch": 0.87,
"learning_rate": 4.352441613588111e-05,
"loss": 11333768.0,
"step": 114
},
{
"epoch": 0.92,
"learning_rate": 4.288747346072187e-05,
"loss": 13123309.3333,
"step": 120
},
{
"epoch": 0.96,
"learning_rate": 4.2250530785562635e-05,
"loss": 14912850.6667,
"step": 126
},
{
"epoch": 1.0,
"eval_accuracy": 0.5,
"eval_auc": 0.5,
"eval_f1": 0.6666666666666666,
"eval_loss": 14316337.0,
"eval_precision": 0.5,
"eval_recall": 1.0,
"eval_runtime": 32.7055,
"eval_samples_per_second": 8.011,
"eval_steps_per_second": 0.52,
"step": 131
},
{
"epoch": 1.01,
"learning_rate": 4.1613588110403404e-05,
"loss": 15509365.3333,
"step": 132
},
{
"epoch": 1.05,
"learning_rate": 4.0976645435244166e-05,
"loss": 11930281.3333,
"step": 138
},
{
"epoch": 1.1,
"learning_rate": 4.033970276008493e-05,
"loss": 11930280.0,
"step": 144
},
{
"epoch": 1.15,
"learning_rate": 3.970276008492569e-05,
"loss": 13719821.3333,
"step": 150
},
{
"epoch": 1.19,
"learning_rate": 3.906581740976646e-05,
"loss": 13719821.3333,
"step": 156
},
{
"epoch": 1.24,
"learning_rate": 3.842887473460722e-05,
"loss": 11930280.0,
"step": 162
},
{
"epoch": 1.28,
"learning_rate": 3.7791932059447985e-05,
"loss": 14912850.6667,
"step": 168
},
{
"epoch": 1.33,
"learning_rate": 3.715498938428875e-05,
"loss": 12526794.6667,
"step": 174
},
{
"epoch": 1.37,
"learning_rate": 3.651804670912951e-05,
"loss": 17298906.6667,
"step": 180
},
{
"epoch": 1.42,
"learning_rate": 3.588110403397027e-05,
"loss": 15509365.3333,
"step": 186
},
{
"epoch": 1.47,
"learning_rate": 3.524416135881104e-05,
"loss": 15509364.0,
"step": 192
},
{
"epoch": 1.51,
"learning_rate": 3.4607218683651803e-05,
"loss": 16702392.0,
"step": 198
},
{
"epoch": 1.56,
"learning_rate": 3.3970276008492566e-05,
"loss": 13123308.0,
"step": 204
},
{
"epoch": 1.6,
"learning_rate": 3.3333333333333335e-05,
"loss": 14912849.3333,
"step": 210
},
{
"epoch": 1.65,
"learning_rate": 3.26963906581741e-05,
"loss": 15509364.0,
"step": 216
},
{
"epoch": 1.69,
"learning_rate": 3.205944798301486e-05,
"loss": 16105878.6667,
"step": 222
},
{
"epoch": 1.74,
"learning_rate": 3.142250530785563e-05,
"loss": 12526793.3333,
"step": 228
},
{
"epoch": 1.79,
"learning_rate": 3.078556263269639e-05,
"loss": 14912849.3333,
"step": 234
},
{
"epoch": 1.83,
"learning_rate": 3.0148619957537157e-05,
"loss": 13719822.6667,
"step": 240
},
{
"epoch": 1.88,
"learning_rate": 2.951167728237792e-05,
"loss": 16702392.0,
"step": 246
},
{
"epoch": 1.92,
"learning_rate": 2.8874734607218685e-05,
"loss": 15509362.6667,
"step": 252
},
{
"epoch": 1.97,
"learning_rate": 2.8237791932059447e-05,
"loss": 10737250.6667,
"step": 258
},
{
"epoch": 2.0,
"eval_accuracy": 0.5,
"eval_auc": 0.5267175572519084,
"eval_f1": 0.6666666666666666,
"eval_loss": 14316336.0,
"eval_precision": 0.5,
"eval_recall": 1.0,
"eval_runtime": 31.9021,
"eval_samples_per_second": 8.213,
"eval_steps_per_second": 0.533,
"step": 262
},
{
"epoch": 2.02,
"learning_rate": 2.7600849256900213e-05,
"loss": 14912849.3333,
"step": 264
},
{
"epoch": 2.06,
"learning_rate": 2.696390658174098e-05,
"loss": 12526793.3333,
"step": 270
},
{
"epoch": 2.11,
"learning_rate": 2.632696390658174e-05,
"loss": 14316336.0,
"step": 276
},
{
"epoch": 2.15,
"learning_rate": 2.5690021231422507e-05,
"loss": 14316334.6667,
"step": 282
},
{
"epoch": 2.2,
"learning_rate": 2.505307855626327e-05,
"loss": 12526792.0,
"step": 288
},
{
"epoch": 2.24,
"learning_rate": 2.4416135881104035e-05,
"loss": 16702392.0,
"step": 294
},
{
"epoch": 2.29,
"learning_rate": 2.37791932059448e-05,
"loss": 14316334.6667,
"step": 300
},
{
"epoch": 2.34,
"learning_rate": 2.3142250530785563e-05,
"loss": 17298906.6667,
"step": 306
},
{
"epoch": 2.38,
"learning_rate": 2.250530785562633e-05,
"loss": 11333764.0,
"step": 312
},
{
"epoch": 2.43,
"learning_rate": 2.1868365180467095e-05,
"loss": 12526792.0,
"step": 318
},
{
"epoch": 2.47,
"learning_rate": 2.1231422505307857e-05,
"loss": 15509362.6667,
"step": 324
},
{
"epoch": 2.52,
"learning_rate": 2.0594479830148623e-05,
"loss": 11333764.0,
"step": 330
},
{
"epoch": 2.56,
"learning_rate": 1.9957537154989385e-05,
"loss": 16702389.3333,
"step": 336
},
{
"epoch": 2.61,
"learning_rate": 1.932059447983015e-05,
"loss": 14912848.0,
"step": 342
},
{
"epoch": 2.66,
"learning_rate": 1.8683651804670913e-05,
"loss": 14912848.0,
"step": 348
},
{
"epoch": 2.7,
"learning_rate": 1.8046709129511676e-05,
"loss": 12526792.0,
"step": 354
},
{
"epoch": 2.75,
"learning_rate": 1.740976645435244e-05,
"loss": 11930276.0,
"step": 360
},
{
"epoch": 2.79,
"learning_rate": 1.6772823779193207e-05,
"loss": 13719821.3333,
"step": 366
},
{
"epoch": 2.84,
"learning_rate": 1.613588110403397e-05,
"loss": 18491932.0,
"step": 372
},
{
"epoch": 2.89,
"learning_rate": 1.5498938428874735e-05,
"loss": 16105874.6667,
"step": 378
},
{
"epoch": 2.93,
"learning_rate": 1.48619957537155e-05,
"loss": 10140734.0,
"step": 384
},
{
"epoch": 2.98,
"learning_rate": 1.4225053078556263e-05,
"loss": 18491930.6667,
"step": 390
},
{
"epoch": 3.0,
"eval_accuracy": 0.5,
"eval_auc": 0.9351145038167938,
"eval_f1": 0.6666666666666666,
"eval_loss": 14316335.0,
"eval_precision": 0.5,
"eval_recall": 1.0,
"eval_runtime": 32.4743,
"eval_samples_per_second": 8.068,
"eval_steps_per_second": 0.523,
"step": 393
},
{
"epoch": 3.02,
"learning_rate": 1.3588110403397027e-05,
"loss": 13719818.6667,
"step": 396
},
{
"epoch": 3.07,
"learning_rate": 1.2951167728237793e-05,
"loss": 13719818.6667,
"step": 402
},
{
"epoch": 3.11,
"learning_rate": 1.2314225053078557e-05,
"loss": 14912846.6667,
"step": 408
},
{
"epoch": 3.16,
"learning_rate": 1.1677282377919321e-05,
"loss": 16105874.6667,
"step": 414
},
{
"epoch": 3.21,
"learning_rate": 1.1040339702760085e-05,
"loss": 13719818.6667,
"step": 420
},
{
"epoch": 3.25,
"learning_rate": 1.0403397027600851e-05,
"loss": 15509360.0,
"step": 426
},
{
"epoch": 3.3,
"learning_rate": 9.766454352441615e-06,
"loss": 16105874.6667,
"step": 432
},
{
"epoch": 3.34,
"learning_rate": 9.129511677282377e-06,
"loss": 13123304.0,
"step": 438
},
{
"epoch": 3.39,
"learning_rate": 8.492569002123141e-06,
"loss": 13719818.6667,
"step": 444
},
{
"epoch": 3.44,
"learning_rate": 7.855626326963907e-06,
"loss": 16105874.6667,
"step": 450
},
{
"epoch": 3.48,
"learning_rate": 7.218683651804671e-06,
"loss": 14912845.3333,
"step": 456
},
{
"epoch": 3.53,
"learning_rate": 6.581740976645435e-06,
"loss": 11930276.0,
"step": 462
},
{
"epoch": 3.57,
"learning_rate": 5.9447983014862e-06,
"loss": 12526789.3333,
"step": 468
},
{
"epoch": 3.62,
"learning_rate": 5.307855626326964e-06,
"loss": 17298902.6667,
"step": 474
},
{
"epoch": 3.66,
"learning_rate": 4.670912951167728e-06,
"loss": 14912845.3333,
"step": 480
},
{
"epoch": 3.71,
"learning_rate": 4.033970276008492e-06,
"loss": 14912845.3333,
"step": 486
},
{
"epoch": 3.76,
"learning_rate": 3.397027600849257e-06,
"loss": 11930274.6667,
"step": 492
},
{
"epoch": 3.8,
"learning_rate": 2.7600849256900213e-06,
"loss": 16702388.0,
"step": 498
},
{
"epoch": 3.85,
"learning_rate": 2.1231422505307854e-06,
"loss": 12526789.3333,
"step": 504
},
{
"epoch": 3.89,
"learning_rate": 1.48619957537155e-06,
"loss": 13719818.6667,
"step": 510
},
{
"epoch": 3.94,
"learning_rate": 8.492569002123142e-07,
"loss": 13719817.3333,
"step": 516
},
{
"epoch": 3.98,
"learning_rate": 2.1231422505307855e-07,
"loss": 14316332.0,
"step": 522
},
{
"epoch": 4.0,
"eval_accuracy": 0.5,
"eval_auc": 0.9694656488549619,
"eval_f1": 0.6666666666666666,
"eval_loss": 14316332.0,
"eval_precision": 0.5,
"eval_recall": 1.0,
"eval_runtime": 32.3876,
"eval_samples_per_second": 8.09,
"eval_steps_per_second": 0.525,
"step": 524
}
],
"logging_steps": 6,
"max_steps": 524,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 500,
"total_flos": 8.867904471465984e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}