| { |
| "best_metric": 0.7185248136520386, |
| "best_model_checkpoint": "test-squad\\checkpoint-144", |
| "epoch": 3.0, |
| "global_step": 144, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "learning_rate": 0.00013333333333333334, |
| "loss": 1.3306, |
| "step": 48 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.8487878441810608, |
| "eval_runtime": 72.0966, |
| "eval_samples_per_second": 1.664, |
| "step": 48 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 6.666666666666667e-05, |
| "loss": 0.9434, |
| "step": 96 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.7361217141151428, |
| "eval_runtime": 77.1446, |
| "eval_samples_per_second": 1.556, |
| "step": 96 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 0.0, |
| "loss": 0.3291, |
| "step": 144 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.7185248136520386, |
| "eval_runtime": 70.5701, |
| "eval_samples_per_second": 1.7, |
| "step": 144 |
| } |
| ], |
| "max_steps": 144, |
| "num_train_epochs": 3, |
| "total_flos": 10718488339200.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
