|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.0, |
|
"global_step": 691, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 5.5282199710564394e-05, |
|
"loss": 1.9233, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 1.9345674514770508, |
|
"eval_runtime": 14.6688, |
|
"eval_samples_per_second": 3.34, |
|
"eval_steps_per_second": 0.477, |
|
"step": 691 |
|
} |
|
], |
|
"max_steps": 691, |
|
"num_train_epochs": 1, |
|
"total_flos": 7249598789825280.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|