|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.0, |
|
"global_step": 108, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 3e-05, |
|
"loss": 1.0622, |
|
"step": 108 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_exact_match": 72.624460767168, |
|
"eval_f1": 76.1543052343002, |
|
"eval_runtime": 3.3739, |
|
"eval_samples_per_second": 2542.189, |
|
"eval_steps_per_second": 8.003, |
|
"step": 108 |
|
} |
|
], |
|
"max_steps": 1080, |
|
"num_train_epochs": 10, |
|
"total_flos": 12834777858048.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|