| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 10.0, |
| "global_step": 3500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.43, |
| "learning_rate": 4.2857142857142856e-05, |
| "loss": 1.2198, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.86, |
| "learning_rate": 3.571428571428572e-05, |
| "loss": 0.9201, |
| "step": 1000 |
| }, |
| { |
| "epoch": 4.29, |
| "learning_rate": 2.857142857142857e-05, |
| "loss": 0.8123, |
| "step": 1500 |
| }, |
| { |
| "epoch": 5.71, |
| "learning_rate": 2.1428571428571428e-05, |
| "loss": 0.754, |
| "step": 2000 |
| }, |
| { |
| "epoch": 7.14, |
| "learning_rate": 1.4285714285714285e-05, |
| "loss": 0.7144, |
| "step": 2500 |
| }, |
| { |
| "epoch": 8.57, |
| "learning_rate": 7.142857142857143e-06, |
| "loss": 0.6851, |
| "step": 3000 |
| }, |
| { |
| "epoch": 10.0, |
| "learning_rate": 0.0, |
| "loss": 0.6705, |
| "step": 3500 |
| }, |
| { |
| "epoch": 10.0, |
| "step": 3500, |
| "total_flos": 4.868588025962496e+16, |
| "train_loss": 0.8251909790039063, |
| "train_runtime": 2749.6833, |
| "train_samples_per_second": 12.729, |
| "train_steps_per_second": 1.273 |
| } |
| ], |
| "max_steps": 3500, |
| "num_train_epochs": 10, |
| "total_flos": 4.868588025962496e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
