|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 5.0, |
|
"global_step": 1915, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 2.61, |
|
"learning_rate": 0.000995, |
|
"loss": 2.1093, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 2.61, |
|
"eval_loss": 0.257192462682724, |
|
"eval_runtime": 6.7241, |
|
"eval_samples_per_second": 14.723, |
|
"eval_steps_per_second": 0.595, |
|
"eval_wer": 0.9292929292929293, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"step": 1915, |
|
"total_flos": 4.985190246992067e+19, |
|
"train_loss": 1.5815124033636587, |
|
"train_runtime": 17545.769, |
|
"train_samples_per_second": 13.963, |
|
"train_steps_per_second": 0.109 |
|
} |
|
], |
|
"max_steps": 1915, |
|
"num_train_epochs": 5, |
|
"total_flos": 4.985190246992067e+19, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|