| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "global_step": 9370, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.11, |
| "learning_rate": 2.83991462113127e-05, |
| "loss": 2.2891, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.21, |
| "learning_rate": 2.67982924226254e-05, |
| "loss": 1.6592, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 2.51974386339381e-05, |
| "loss": 1.5543, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.43, |
| "learning_rate": 2.35965848452508e-05, |
| "loss": 1.4893, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.53, |
| "learning_rate": 2.1995731056563503e-05, |
| "loss": 1.4366, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.64, |
| "learning_rate": 2.0394877267876203e-05, |
| "loss": 1.4089, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.75, |
| "learning_rate": 1.8794023479188903e-05, |
| "loss": 1.3842, |
| "step": 3500 |
| }, |
| { |
| "epoch": 0.85, |
| "learning_rate": 1.7193169690501603e-05, |
| "loss": 1.3476, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.96, |
| "learning_rate": 1.5592315901814302e-05, |
| "loss": 1.315, |
| "step": 4500 |
| }, |
| { |
| "epoch": 1.07, |
| "learning_rate": 1.3991462113127e-05, |
| "loss": 1.1069, |
| "step": 5000 |
| }, |
| { |
| "epoch": 1.17, |
| "learning_rate": 1.23906083244397e-05, |
| "loss": 0.9875, |
| "step": 5500 |
| }, |
| { |
| "epoch": 1.28, |
| "learning_rate": 1.0789754535752402e-05, |
| "loss": 0.9898, |
| "step": 6000 |
| }, |
| { |
| "epoch": 1.39, |
| "learning_rate": 9.188900747065102e-06, |
| "loss": 0.9846, |
| "step": 6500 |
| }, |
| { |
| "epoch": 1.49, |
| "learning_rate": 7.588046958377802e-06, |
| "loss": 0.95, |
| "step": 7000 |
| }, |
| { |
| "epoch": 1.6, |
| "learning_rate": 5.987193169690502e-06, |
| "loss": 0.9333, |
| "step": 7500 |
| }, |
| { |
| "epoch": 1.71, |
| "learning_rate": 4.386339381003202e-06, |
| "loss": 0.9367, |
| "step": 8000 |
| }, |
| { |
| "epoch": 1.81, |
| "learning_rate": 2.785485592315902e-06, |
| "loss": 0.9698, |
| "step": 8500 |
| }, |
| { |
| "epoch": 1.92, |
| "learning_rate": 1.1846318036286021e-06, |
| "loss": 0.9228, |
| "step": 9000 |
| }, |
| { |
| "epoch": 2.0, |
| "step": 9370, |
| "total_flos": 2.2033587715006464e+16, |
| "train_loss": 1.2479621520800677, |
| "train_runtime": 4558.2109, |
| "train_samples_per_second": 24.666, |
| "train_steps_per_second": 2.056 |
| } |
| ], |
| "max_steps": 9370, |
| "num_train_epochs": 2, |
| "total_flos": 2.2033587715006464e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
