|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 3.0, |
|
"global_step": 3057, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 4.182204775924109e-05, |
|
"loss": 2.5762, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 3.3644095518482174e-05, |
|
"loss": 1.9038, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"learning_rate": 2.546614327772326e-05, |
|
"loss": 1.5788, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 1.96, |
|
"learning_rate": 1.7288191036964345e-05, |
|
"loss": 1.4828, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 2.45, |
|
"learning_rate": 9.110238796205431e-06, |
|
"loss": 1.2733, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 2.94, |
|
"learning_rate": 9.322865554465163e-07, |
|
"loss": 1.242, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"step": 3057, |
|
"total_flos": 4037561740001280.0, |
|
"train_loss": 1.6685600867254264, |
|
"train_runtime": 1024.2626, |
|
"train_samples_per_second": 29.846, |
|
"train_steps_per_second": 2.985 |
|
} |
|
], |
|
"max_steps": 3057, |
|
"num_train_epochs": 3, |
|
"total_flos": 4037561740001280.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|