| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.21234428086070214, |
| "global_step": 4500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.02, |
| "learning_rate": 4.9961070215175544e-05, |
| "loss": 1.5449, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.05, |
| "learning_rate": 4.9921747200201335e-05, |
| "loss": 1.4531, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.07, |
| "learning_rate": 4.988242418522713e-05, |
| "loss": 1.3957, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.09, |
| "learning_rate": 4.9843101170252924e-05, |
| "loss": 1.3235, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.12, |
| "learning_rate": 4.980377815527872e-05, |
| "loss": 1.3184, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.14, |
| "learning_rate": 4.976453378633447e-05, |
| "loss": 1.2947, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.17, |
| "learning_rate": 4.972521077136027e-05, |
| "loss": 1.278, |
| "step": 3500 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 4.9685887756386066e-05, |
| "loss": 1.2059, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.21, |
| "learning_rate": 4.964656474141186e-05, |
| "loss": 1.2573, |
| "step": 4500 |
| } |
| ], |
| "max_steps": 635760, |
| "num_train_epochs": 30, |
| "total_flos": 1161782482698240.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
