|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.0, |
|
"global_step": 47, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 0.00013340429968430322, |
|
"loss": 3.4212, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 0.00012243723783011615, |
|
"loss": 3.3821, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 0.00010551244942700737, |
|
"loss": 2.9954, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 8.450286230835245e-05, |
|
"loss": 3.1624, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 6.173343555458685e-05, |
|
"loss": 3.1052, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 3.972387529741623e-05, |
|
"loss": 2.71, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 2.090979946151954e-05, |
|
"loss": 2.7648, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 7.373207860012155e-06, |
|
"loss": 2.7341, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 6.1208431258209e-07, |
|
"loss": 2.7194, |
|
"step": 45 |
|
} |
|
], |
|
"max_steps": 47, |
|
"num_train_epochs": 1, |
|
"total_flos": 48730963968000.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|