| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 55.55555555555556, |
| "global_step": 1000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 2.78, |
| "learning_rate": 3e-06, |
| "loss": 8.2937, |
| "step": 50 |
| }, |
| { |
| "epoch": 5.56, |
| "learning_rate": 6e-06, |
| "loss": 4.7562, |
| "step": 100 |
| }, |
| { |
| "epoch": 8.33, |
| "learning_rate": 9e-06, |
| "loss": 3.0858, |
| "step": 150 |
| }, |
| { |
| "epoch": 11.11, |
| "learning_rate": 1.2e-05, |
| "loss": 2.4515, |
| "step": 200 |
| }, |
| { |
| "epoch": 13.89, |
| "learning_rate": 1.5e-05, |
| "loss": 2.1723, |
| "step": 250 |
| }, |
| { |
| "epoch": 16.67, |
| "learning_rate": 1.8e-05, |
| "loss": 1.981, |
| "step": 300 |
| }, |
| { |
| "epoch": 19.44, |
| "learning_rate": 2.1e-05, |
| "loss": 1.8522, |
| "step": 350 |
| }, |
| { |
| "epoch": 22.22, |
| "learning_rate": 2.4e-05, |
| "loss": 1.7612, |
| "step": 400 |
| }, |
| { |
| "epoch": 25.0, |
| "learning_rate": 2.7000000000000002e-05, |
| "loss": 1.7039, |
| "step": 450 |
| }, |
| { |
| "epoch": 27.78, |
| "learning_rate": 3e-05, |
| "loss": 1.6461, |
| "step": 500 |
| }, |
| { |
| "epoch": 30.56, |
| "learning_rate": 2.884615384615385e-05, |
| "loss": 1.6101, |
| "step": 550 |
| }, |
| { |
| "epoch": 33.33, |
| "learning_rate": 2.7692307692307694e-05, |
| "loss": 1.5799, |
| "step": 600 |
| }, |
| { |
| "epoch": 36.11, |
| "learning_rate": 2.6538461538461538e-05, |
| "loss": 1.56, |
| "step": 650 |
| }, |
| { |
| "epoch": 38.89, |
| "learning_rate": 2.5384615384615386e-05, |
| "loss": 1.5541, |
| "step": 700 |
| }, |
| { |
| "epoch": 41.67, |
| "learning_rate": 2.423076923076923e-05, |
| "loss": 1.5313, |
| "step": 750 |
| }, |
| { |
| "epoch": 44.44, |
| "learning_rate": 2.307692307692308e-05, |
| "loss": 1.5195, |
| "step": 800 |
| }, |
| { |
| "epoch": 47.22, |
| "learning_rate": 2.1923076923076924e-05, |
| "loss": 1.5154, |
| "step": 850 |
| }, |
| { |
| "epoch": 50.0, |
| "learning_rate": 2.076923076923077e-05, |
| "loss": 1.5126, |
| "step": 900 |
| }, |
| { |
| "epoch": 52.78, |
| "learning_rate": 1.9615384615384617e-05, |
| "loss": 1.5006, |
| "step": 950 |
| }, |
| { |
| "epoch": 55.56, |
| "learning_rate": 1.8461538461538465e-05, |
| "loss": 1.495, |
| "step": 1000 |
| } |
| ], |
| "max_steps": 1800, |
| "num_train_epochs": 100, |
| "total_flos": 2438945832960000.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
