| { |
| "best_metric": 0.5902058482170105, |
| "best_model_checkpoint": "./distilbert/run-3/checkpoint-180", |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 180, |
| "is_hyper_param_search": true, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.6402777777777778, |
| "eval_loss": 0.6207325458526611, |
| "eval_runtime": 5.3415, |
| "eval_samples_per_second": 178.788, |
| "eval_steps_per_second": 22.466, |
| "step": 90 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.6795138888888889, |
| "eval_loss": 0.5902058482170105, |
| "eval_runtime": 5.3415, |
| "eval_samples_per_second": 178.788, |
| "eval_steps_per_second": 22.466, |
| "step": 180 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 360, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "save_steps": 500, |
| "total_flos": 0, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": { |
| "learning_rate": 2.0070652878343e-05, |
| "num_train_epochs": 4, |
| "per_device_train_batch_size": 32, |
| "seed": 10 |
| } |
| } |
|
|
