|
{ |
|
"best_metric": 0.4231731541032522, |
|
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-9/checkpoint-535", |
|
"epoch": 1.0, |
|
"eval_steps": 500, |
|
"global_step": 535, |
|
"is_hyper_param_search": true, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.93, |
|
"grad_norm": 6.980520248413086, |
|
"learning_rate": 7.782049038693399e-06, |
|
"loss": 0.5402, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 0.4980236887931824, |
|
"eval_matthews_correlation": 0.4231731541032522, |
|
"eval_runtime": 0.7267, |
|
"eval_samples_per_second": 1435.197, |
|
"eval_steps_per_second": 90.818, |
|
"step": 535 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 2675, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 5, |
|
"save_steps": 500, |
|
"total_flos": 144718821953964.0, |
|
"train_batch_size": 16, |
|
"trial_name": null, |
|
"trial_params": { |
|
"learning_rate": 9.571025829197629e-06, |
|
"num_train_epochs": 5, |
|
"per_device_train_batch_size": 16, |
|
"seed": 8 |
|
} |
|
} |
|
|