| { |
| "best_metric": 3.5773866176605225, |
| "best_model_checkpoint": "output/tiamat/checkpoint-20", |
| "epoch": 2.0, |
| "global_step": 20, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.5, |
| "learning_rate": 6.86e-05, |
| "loss": 3.8236, |
| "step": 5 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 0.0, |
| "loss": 3.3567, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 3.5825488567352295, |
| "eval_runtime": 0.3919, |
| "eval_samples_per_second": 22.966, |
| "eval_steps_per_second": 5.103, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.5, |
| "learning_rate": 6.859999999999999e-05, |
| "loss": 3.6241, |
| "step": 15 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 0.0001372, |
| "loss": 3.5185, |
| "step": 20 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 3.5773866176605225, |
| "eval_runtime": 0.3966, |
| "eval_samples_per_second": 22.693, |
| "eval_steps_per_second": 5.043, |
| "step": 20 |
| } |
| ], |
| "max_steps": 20, |
| "num_train_epochs": 2, |
| "total_flos": 19074318336000.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
