|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.989423404981235, |
|
"global_step": 2900, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 9.431365859206188e-06, |
|
"loss": 0.1757, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 8.862731718412374e-06, |
|
"loss": 0.1321, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 8.294097577618561e-06, |
|
"loss": 0.1264, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 7.725463436824747e-06, |
|
"loss": 0.1157, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 7.156829296030934e-06, |
|
"loss": 0.1106, |
|
"step": 2500 |
|
} |
|
], |
|
"max_steps": 8793, |
|
"num_train_epochs": 3, |
|
"total_flos": 7633600497254400.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|