|
{ |
|
"best_metric": 65.95120806943467, |
|
"best_model_checkpoint": "./checkpoint-200", |
|
"epoch": 14.02, |
|
"global_step": 200, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.05, |
|
"learning_rate": 4.000000000000001e-06, |
|
"loss": 5.1574, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 3.04, |
|
"learning_rate": 9e-06, |
|
"loss": 2.076, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 5.03, |
|
"learning_rate": 8.666666666666668e-06, |
|
"loss": 1.0421, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 7.01, |
|
"learning_rate": 7e-06, |
|
"loss": 0.583, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 7.01, |
|
"eval_loss": 1.08222234249115, |
|
"eval_runtime": 852.3928, |
|
"eval_samples_per_second": 1.221, |
|
"eval_steps_per_second": 0.039, |
|
"eval_wer": 67.31761670185315, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 8.06, |
|
"learning_rate": 5.333333333333334e-06, |
|
"loss": 0.3482, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 10.05, |
|
"learning_rate": 3.6666666666666666e-06, |
|
"loss": 0.2212, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 12.04, |
|
"learning_rate": 2.0000000000000003e-06, |
|
"loss": 0.1501, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 14.02, |
|
"learning_rate": 3.3333333333333335e-07, |
|
"loss": 0.1146, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 14.02, |
|
"eval_loss": 1.121730089187622, |
|
"eval_runtime": 859.1416, |
|
"eval_samples_per_second": 1.212, |
|
"eval_steps_per_second": 0.038, |
|
"eval_wer": 65.95120806943467, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 14.02, |
|
"step": 200, |
|
"total_flos": 3.64137058123776e+18, |
|
"train_loss": 1.2115725290775299, |
|
"train_runtime": 4849.9911, |
|
"train_samples_per_second": 2.639, |
|
"train_steps_per_second": 0.041 |
|
} |
|
], |
|
"max_steps": 200, |
|
"num_train_epochs": 9223372036854775807, |
|
"total_flos": 3.64137058123776e+18, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|