|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 3.0, |
|
"global_step": 2319, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.5, |
|
"learning_rate": 2.4989219491159986e-05, |
|
"loss": 0.3724, |
|
"step": 1160 |
|
}, |
|
{ |
|
"epoch": 1.5, |
|
"eval_f1": 0.8631578947368421, |
|
"eval_loss": 0.35006770491600037, |
|
"eval_runtime": 13.0712, |
|
"eval_samples_per_second": 210.08, |
|
"eval_steps_per_second": 6.579, |
|
"step": 1160 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"step": 2319, |
|
"total_flos": 1.950915853283328e+16, |
|
"train_loss": 0.2654421577272666, |
|
"train_runtime": 983.4675, |
|
"train_samples_per_second": 75.394, |
|
"train_steps_per_second": 2.358 |
|
} |
|
], |
|
"max_steps": 2319, |
|
"num_train_epochs": 3, |
|
"total_flos": 1.950915853283328e+16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|