|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 2.0, |
|
"global_step": 8, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 4.192291259765625, |
|
"eval_runtime": 0.896, |
|
"eval_samples_per_second": 55.802, |
|
"eval_steps_per_second": 1.116, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_loss": 3.560474157333374, |
|
"eval_runtime": 0.8672, |
|
"eval_samples_per_second": 57.66, |
|
"eval_steps_per_second": 1.153, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"step": 8, |
|
"total_flos": 16719916032000.0, |
|
"train_loss": 5.096200942993164, |
|
"train_runtime": 318.685, |
|
"train_samples_per_second": 0.941, |
|
"train_steps_per_second": 0.025 |
|
} |
|
], |
|
"max_steps": 8, |
|
"num_train_epochs": 2, |
|
"total_flos": 16719916032000.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|