|
{ |
|
"best_metric": 0.0, |
|
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola\\run-1\\checkpoint-134", |
|
"epoch": 2.0, |
|
"eval_steps": 500, |
|
"global_step": 268, |
|
"is_hyper_param_search": true, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 0.6127962470054626, |
|
"eval_matthews_correlation": 0.0, |
|
"eval_runtime": 1.3238, |
|
"eval_samples_per_second": 787.877, |
|
"eval_steps_per_second": 49.856, |
|
"step": 134 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_loss": 0.6062379479408264, |
|
"eval_matthews_correlation": 0.0, |
|
"eval_runtime": 1.5251, |
|
"eval_samples_per_second": 683.892, |
|
"eval_steps_per_second": 43.276, |
|
"step": 268 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 402, |
|
"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": 1.169416569899892e-06, |
|
"num_train_epochs": 3, |
|
"per_device_train_batch_size": 64, |
|
"seed": 4 |
|
} |
|
} |
|
|