|
{ |
|
"best_metric": 0.27637040604945357, |
|
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-108", |
|
"epoch": 2.0, |
|
"eval_steps": 500, |
|
"global_step": 108, |
|
"is_hyper_param_search": true, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 0.5896052122116089, |
|
"eval_matthews_correlation": 0.0, |
|
"eval_runtime": 0.7382, |
|
"eval_samples_per_second": 1412.91, |
|
"eval_steps_per_second": 89.408, |
|
"step": 54 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_loss": 0.620072603225708, |
|
"eval_matthews_correlation": 0.27637040604945357, |
|
"eval_runtime": 0.7895, |
|
"eval_samples_per_second": 1321.116, |
|
"eval_steps_per_second": 83.599, |
|
"step": 108 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 162, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"save_steps": 500, |
|
"total_flos": 0, |
|
"train_batch_size": 16, |
|
"trial_name": null, |
|
"trial_params": { |
|
"learning_rate": 4.44263313595678e-05, |
|
"num_train_epochs": 3, |
|
"per_device_train_batch_size": 16, |
|
"seed": 36 |
|
} |
|
} |
|
|