|
{ |
|
"best_metric": 0.0, |
|
"best_model_checkpoint": "deberta-v3-large-finetuned-cola-midterm/run-3/checkpoint-214", |
|
"epoch": 2.0, |
|
"eval_steps": 500, |
|
"global_step": 428, |
|
"is_hyper_param_search": true, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 0.6239587664604187, |
|
"eval_matthews_correlation": 0.0, |
|
"eval_runtime": 8.4185, |
|
"eval_samples_per_second": 123.894, |
|
"eval_steps_per_second": 7.84, |
|
"step": 214 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_loss": 0.6267099380493164, |
|
"eval_matthews_correlation": 0.0, |
|
"eval_runtime": 8.5011, |
|
"eval_samples_per_second": 122.69, |
|
"eval_steps_per_second": 7.764, |
|
"step": 428 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 428, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 2, |
|
"save_steps": 500, |
|
"total_flos": 0, |
|
"train_batch_size": 4, |
|
"trial_name": null, |
|
"trial_params": { |
|
"learning_rate": 6.93139822379791e-05, |
|
"num_train_epochs": 2, |
|
"per_device_train_batch_size": 4, |
|
"seed": 12 |
|
} |
|
} |
|
|