| { |
| "best_metric": 0.17575937509536743, |
| "best_model_checkpoint": "./outputs/model\\checkpoint-1102", |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 1102, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.91, |
| "learning_rate": 1.0925589836660618e-05, |
| "loss": 0.1892, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.941916085827525, |
| "eval_loss": 0.2061644345521927, |
| "eval_runtime": 52.2792, |
| "eval_samples_per_second": 139.96, |
| "eval_steps_per_second": 8.761, |
| "step": 551 |
| }, |
| { |
| "epoch": 1.81, |
| "learning_rate": 1.8511796733212343e-06, |
| "loss": 0.1121, |
| "step": 1000 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.947246139128058, |
| "eval_loss": 0.17575937509536743, |
| "eval_runtime": 52.3043, |
| "eval_samples_per_second": 139.893, |
| "eval_steps_per_second": 8.756, |
| "step": 1102 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 1102, |
| "num_train_epochs": 2, |
| "save_steps": 500, |
| "total_flos": 4409930398904640.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
