|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.22563176895306858, |
|
"global_step": 2500, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 1.969915764139591e-05, |
|
"loss": 3.07, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 1.939831528279182e-05, |
|
"loss": 0.0, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 1.9097472924187726e-05, |
|
"loss": 0.0, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 1.8796630565583636e-05, |
|
"loss": 0.0, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 1.8495788206979545e-05, |
|
"loss": 0.0, |
|
"step": 2500 |
|
} |
|
], |
|
"max_steps": 33240, |
|
"num_train_epochs": 3, |
|
"total_flos": 331257047040000.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|