|
{ |
|
"best_metric": -0.01620482918319043, |
|
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-28", |
|
"epoch": 2.0, |
|
"eval_steps": 500, |
|
"global_step": 28, |
|
"is_hyper_param_search": true, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 0.693752646446228, |
|
"eval_matthews_correlation": -0.049473020853933444, |
|
"eval_runtime": 0.7156, |
|
"eval_samples_per_second": 1457.617, |
|
"eval_steps_per_second": 92.237, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_loss": 0.681831955909729, |
|
"eval_matthews_correlation": -0.01620482918319043, |
|
"eval_runtime": 0.7313, |
|
"eval_samples_per_second": 1426.325, |
|
"eval_steps_per_second": 90.256, |
|
"step": 28 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 42, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"save_steps": 500, |
|
"total_flos": 0, |
|
"train_batch_size": 64, |
|
"trial_name": null, |
|
"trial_params": { |
|
"learning_rate": 1.8537810359672543e-06, |
|
"num_train_epochs": 3, |
|
"per_device_train_batch_size": 64, |
|
"seed": 24 |
|
} |
|
} |
|
|