| { |
| "best_metric": 0.5912495851516724, |
| "best_model_checkpoint": "./distilbert/run-4/checkpoint-179", |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 358, |
| "is_hyper_param_search": true, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.6701388888888888, |
| "eval_loss": 0.5912495851516724, |
| "eval_runtime": 5.3044, |
| "eval_samples_per_second": 180.038, |
| "eval_steps_per_second": 22.623, |
| "step": 179 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.6836805555555555, |
| "eval_loss": 0.610892117023468, |
| "eval_runtime": 5.3069, |
| "eval_samples_per_second": 179.955, |
| "eval_steps_per_second": 22.612, |
| "step": 358 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 358, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 500, |
| "total_flos": 0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": { |
| "learning_rate": 4.268152647097221e-05, |
| "num_train_epochs": 2, |
| "per_device_train_batch_size": 16, |
| "seed": 2 |
| } |
| } |
|
|
