| { |
| "best_metric": 0.5290037338732806, |
| "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-268", |
| "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": 0.44986891746520996, |
| "eval_matthews_correlation": 0.4940290085706236, |
| "eval_runtime": 0.7403, |
| "eval_samples_per_second": 1408.884, |
| "eval_steps_per_second": 89.153, |
| "step": 134 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.4928521513938904, |
| "eval_matthews_correlation": 0.5290037338732806, |
| "eval_runtime": 0.785, |
| "eval_samples_per_second": 1328.729, |
| "eval_steps_per_second": 84.081, |
| "step": 268 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 268, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 500, |
| "total_flos": 0, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": { |
| "learning_rate": 6.995529557117928e-05, |
| "num_train_epochs": 2, |
| "per_device_train_batch_size": 64, |
| "seed": 13 |
| } |
| } |
|
|
