|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 4.963347587049481, |
|
"eval_steps": 500, |
|
"global_step": 65000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 4.834555080431684e-05, |
|
"loss": 1.8382, |
|
"step": 13000 |
|
}, |
|
{ |
|
"epoch": 1.99, |
|
"learning_rate": 4.669110160863368e-05, |
|
"loss": 1.5977, |
|
"step": 26000 |
|
}, |
|
{ |
|
"epoch": 2.98, |
|
"learning_rate": 4.503665241295052e-05, |
|
"loss": 1.5058, |
|
"step": 39000 |
|
}, |
|
{ |
|
"epoch": 3.97, |
|
"learning_rate": 4.338220321726736e-05, |
|
"loss": 1.4649, |
|
"step": 52000 |
|
}, |
|
{ |
|
"epoch": 4.96, |
|
"learning_rate": 4.17277540215842e-05, |
|
"loss": 1.4108, |
|
"step": 65000 |
|
} |
|
], |
|
"logging_steps": 13000, |
|
"max_steps": 392880, |
|
"num_train_epochs": 30, |
|
"save_steps": 13000, |
|
"total_flos": 2.1227934430789632e+20, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|