|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 2.5869664983937586, |
|
"eval_steps": 500, |
|
"global_step": 38370, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 1.997705369435521e-05, |
|
"loss": 1.6603, |
|
"step": 4357 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 2.889296823211463e-05, |
|
"loss": 1.6193, |
|
"step": 8714 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 2.6671765845698842e-05, |
|
"loss": 1.6126, |
|
"step": 13071 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"learning_rate": 2.4450053541379837e-05, |
|
"loss": 1.6028, |
|
"step": 17428 |
|
}, |
|
{ |
|
"epoch": 1.41, |
|
"learning_rate": 2.222936107286727e-05, |
|
"loss": 1.5803, |
|
"step": 21785 |
|
}, |
|
{ |
|
"epoch": 2.03, |
|
"learning_rate": 2.000815868645148e-05, |
|
"loss": 1.5767, |
|
"step": 26142 |
|
}, |
|
{ |
|
"epoch": 2.23, |
|
"learning_rate": 1.778746621793891e-05, |
|
"loss": 1.5682, |
|
"step": 30499 |
|
}, |
|
{ |
|
"epoch": 2.43, |
|
"learning_rate": 1.556728366732956e-05, |
|
"loss": 1.5451, |
|
"step": 34856 |
|
} |
|
], |
|
"logging_steps": 4357, |
|
"max_steps": 65370, |
|
"num_train_epochs": 3, |
|
"save_steps": 500, |
|
"total_flos": 3.359036228543447e+18, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|