|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.03517336953845505, |
|
"global_step": 5000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 1.9929653260923093e-05, |
|
"loss": 2.0913, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 1.985930652184618e-05, |
|
"loss": 2.0515, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 1.978895978276927e-05, |
|
"loss": 2.0554, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 1.9718613043692362e-05, |
|
"loss": 2.0336, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 1.964826630461545e-05, |
|
"loss": 2.0487, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 1.9577919565538542e-05, |
|
"loss": 2.0338, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 1.950757282646163e-05, |
|
"loss": 2.0361, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 1.9437226087384722e-05, |
|
"loss": 2.0281, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 1.9367020041785966e-05, |
|
"loss": 2.0136, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 1.9296673302709054e-05, |
|
"loss": 2.0301, |
|
"step": 5000 |
|
} |
|
], |
|
"max_steps": 142153, |
|
"num_train_epochs": 1, |
|
"total_flos": 6948342774890496.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|