|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.8875083203905036, |
|
"global_step": 4000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 4.8890614599511876e-05, |
|
"loss": 1.2035, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 4.778122919902374e-05, |
|
"loss": 0.4941, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 4.6671843798535615e-05, |
|
"loss": 0.4122, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 4.556245839804749e-05, |
|
"loss": 0.3654, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 4.4453072997559355e-05, |
|
"loss": 0.3352, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 4.334368759707123e-05, |
|
"loss": 0.3101, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"learning_rate": 4.2234302196583095e-05, |
|
"loss": 0.2922, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 4.112491679609496e-05, |
|
"loss": 0.2778, |
|
"step": 4000 |
|
} |
|
], |
|
"max_steps": 22535, |
|
"num_train_epochs": 5, |
|
"total_flos": 9755783331840000.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|