|
{ |
|
"best_metric": 0.0, |
|
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-27", |
|
"epoch": 3.0, |
|
"eval_steps": 500, |
|
"global_step": 81, |
|
"is_hyper_param_search": true, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 0.6171508431434631, |
|
"eval_matthews_correlation": 0.0, |
|
"eval_runtime": 1.2254, |
|
"eval_samples_per_second": 851.142, |
|
"eval_steps_per_second": 106.903, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_loss": 0.6099013686180115, |
|
"eval_matthews_correlation": 0.0, |
|
"eval_runtime": 1.2265, |
|
"eval_samples_per_second": 850.398, |
|
"eval_steps_per_second": 106.809, |
|
"step": 54 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_loss": 0.6057543158531189, |
|
"eval_matthews_correlation": 0.0, |
|
"eval_runtime": 1.964, |
|
"eval_samples_per_second": 531.065, |
|
"eval_steps_per_second": 66.701, |
|
"step": 81 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 135, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 5, |
|
"save_steps": 500, |
|
"total_flos": 0, |
|
"train_batch_size": 16, |
|
"trial_name": null, |
|
"trial_params": { |
|
"learning_rate": 7.141254091425431e-06, |
|
"num_train_epochs": 5, |
|
"per_device_train_batch_size": 16, |
|
"seed": 4 |
|
} |
|
} |
|
|