|
{ |
|
"best_metric": 0.0, |
|
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-27", |
|
"epoch": 2.0, |
|
"eval_steps": 500, |
|
"global_step": 54, |
|
"is_hyper_param_search": true, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 0.6574864983558655, |
|
"eval_matthews_correlation": 0.0, |
|
"eval_runtime": 1.9642, |
|
"eval_samples_per_second": 531.017, |
|
"eval_steps_per_second": 66.695, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_loss": 0.639704167842865, |
|
"eval_matthews_correlation": 0.0, |
|
"eval_runtime": 3.0976, |
|
"eval_samples_per_second": 336.715, |
|
"eval_steps_per_second": 42.291, |
|
"step": 54 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 54, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 2, |
|
"save_steps": 500, |
|
"total_flos": 0, |
|
"train_batch_size": 16, |
|
"trial_name": null, |
|
"trial_params": { |
|
"learning_rate": 5.3265813071360445e-06, |
|
"num_train_epochs": 2, |
|
"per_device_train_batch_size": 16, |
|
"seed": 13 |
|
} |
|
} |
|
|