|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 2.0, |
|
"global_step": 500, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 2.272932767868042, |
|
"eval_runtime": 478.9112, |
|
"eval_samples_per_second": 2.088, |
|
"eval_steps_per_second": 0.132, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"learning_rate": 6.666666666666667e-06, |
|
"loss": 2.6589, |
|
"step": 500 |
|
} |
|
], |
|
"max_steps": 750, |
|
"num_train_epochs": 3, |
|
"total_flos": 783918600192000.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|