|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.9354536950420954, |
|
"global_step": 1000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 4.4153414405986905e-05, |
|
"loss": 0.6437, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 3.8306828811973814e-05, |
|
"loss": 0.6233, |
|
"step": 1000 |
|
} |
|
], |
|
"max_steps": 4276, |
|
"num_train_epochs": 4, |
|
"total_flos": 2219952844800000.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|