|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 2.127659574468085, |
|
"global_step": 100, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 2.13, |
|
"eval_accuracy": 0.909112825458052, |
|
"eval_f1": 0.8837125963089052, |
|
"eval_loss": 0.6461763978004456, |
|
"eval_precision": 0.879144385026738, |
|
"eval_recall": 0.888328530259366, |
|
"eval_runtime": 15.0755, |
|
"eval_samples_per_second": 12.537, |
|
"eval_steps_per_second": 0.796, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 2.13, |
|
"step": 100, |
|
"total_flos": 424705445068800.0, |
|
"train_loss": 1.3162074279785156, |
|
"train_runtime": 179.095, |
|
"train_samples_per_second": 8.934, |
|
"train_steps_per_second": 0.558 |
|
} |
|
], |
|
"max_steps": 100, |
|
"num_train_epochs": 3, |
|
"total_flos": 424705445068800.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|