| { |
| "best_metric": 0.6606646180152893, |
| "best_model_checkpoint": "./distilbert/run-0/checkpoint-358", |
| "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": 0.5784722222222222, |
| "eval_loss": 0.6798288226127625, |
| "eval_runtime": 5.3067, |
| "eval_samples_per_second": 179.961, |
| "eval_steps_per_second": 22.613, |
| "step": 179 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.6045138888888888, |
| "eval_loss": 0.6606646180152893, |
| "eval_runtime": 5.2957, |
| "eval_samples_per_second": 180.334, |
| "eval_steps_per_second": 22.66, |
| "step": 358 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 716, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "save_steps": 500, |
| "total_flos": 0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": { |
| "learning_rate": 2.556759622796195e-06, |
| "num_train_epochs": 4, |
| "per_device_train_batch_size": 16, |
| "seed": 39 |
| } |
| } |
|
|
