|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 2.0, |
|
"global_step": 34, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 0.000109940736055617, |
|
"loss": 3.1412, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 4.982671888105512e-05, |
|
"loss": 3.0238, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 4.6324050628611986e-06, |
|
"loss": 2.9096, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"learning_rate": 1.0275104488948473e-05, |
|
"loss": 2.9067, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"learning_rate": 6.227039054081748e-05, |
|
"loss": 2.6172, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 1.76, |
|
"learning_rate": 0.00011929601172133719, |
|
"loss": 2.7089, |
|
"step": 30 |
|
} |
|
], |
|
"max_steps": 34, |
|
"num_train_epochs": 2, |
|
"total_flos": 35274424320000.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|