|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 29.26829268292683, |
|
"global_step": 30000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 2.93, |
|
"learning_rate": 0.0002, |
|
"loss": 0.3963, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 5.85, |
|
"learning_rate": 0.0002, |
|
"loss": 0.2937, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 8.78, |
|
"learning_rate": 0.0002, |
|
"loss": 1.5565, |
|
"step": 9000 |
|
}, |
|
{ |
|
"epoch": 11.71, |
|
"learning_rate": 0.0002, |
|
"loss": 1.4597, |
|
"step": 12000 |
|
}, |
|
{ |
|
"epoch": 14.63, |
|
"learning_rate": 0.0002, |
|
"loss": 1.3908, |
|
"step": 15000 |
|
}, |
|
{ |
|
"epoch": 17.56, |
|
"learning_rate": 0.0002, |
|
"loss": 1.7294, |
|
"step": 18000 |
|
}, |
|
{ |
|
"epoch": 20.49, |
|
"learning_rate": 0.0002, |
|
"loss": 1.2396, |
|
"step": 21000 |
|
}, |
|
{ |
|
"epoch": 23.41, |
|
"learning_rate": 0.0002, |
|
"loss": 1.5304, |
|
"step": 24000 |
|
}, |
|
{ |
|
"epoch": 26.34, |
|
"learning_rate": 0.0002, |
|
"loss": 2.3882, |
|
"step": 27000 |
|
}, |
|
{ |
|
"epoch": 29.27, |
|
"learning_rate": 0.0002, |
|
"loss": 2.0081, |
|
"step": 30000 |
|
} |
|
], |
|
"max_steps": 30000, |
|
"num_train_epochs": 30, |
|
"total_flos": 6.3476554530816e+18, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|