|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 4.0, |
|
"global_step": 4988, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 4.590834697217676e-05, |
|
"loss": 0.1357, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 4.079378068739771e-05, |
|
"loss": 0.049, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 3.567921440261866e-05, |
|
"loss": 0.035, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"learning_rate": 3.05646481178396e-05, |
|
"loss": 0.0247, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"learning_rate": 2.5450081833060556e-05, |
|
"loss": 0.0269, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 2.41, |
|
"learning_rate": 2.0335515548281506e-05, |
|
"loss": 0.0128, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 2.81, |
|
"learning_rate": 1.5220949263502457e-05, |
|
"loss": 0.0125, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 3.21, |
|
"learning_rate": 1.0106382978723404e-05, |
|
"loss": 0.0064, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 3.61, |
|
"learning_rate": 4.991816693944354e-06, |
|
"loss": 0.0054, |
|
"step": 4500 |
|
} |
|
], |
|
"max_steps": 4988, |
|
"num_train_epochs": 4, |
|
"total_flos": 7021360413554688.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|