|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.05, |
|
"global_step": 1, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 3e-05, |
|
"loss": 3.3342, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"eval_accuracy": 0.047694543532831285, |
|
"eval_loss": 3.1015625, |
|
"eval_runtime": 1.5733, |
|
"eval_samples_per_second": 18.433, |
|
"eval_steps_per_second": 2.543, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"step": 1, |
|
"total_flos": 0.0, |
|
"train_loss": 3.334228515625, |
|
"train_runtime": 5.178, |
|
"train_samples_per_second": 1.545, |
|
"train_steps_per_second": 0.193 |
|
} |
|
], |
|
"max_steps": 1, |
|
"num_train_epochs": 1, |
|
"total_flos": 0.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|