| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 19.09090909090909, |
| "eval_steps": 500, |
| "global_step": 20, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.09, |
| "learning_rate": 1.8181818181818182e-05, |
| "loss": 1.4961, |
| "step": 2 |
| }, |
| { |
| "epoch": 3.09, |
| "learning_rate": 3.6363636363636364e-05, |
| "loss": 1.4897, |
| "step": 4 |
| }, |
| { |
| "epoch": 5.09, |
| "learning_rate": 5.4545454545454546e-05, |
| "loss": 1.4698, |
| "step": 6 |
| }, |
| { |
| "epoch": 7.09, |
| "learning_rate": 7.272727272727273e-05, |
| "loss": 1.4347, |
| "step": 8 |
| }, |
| { |
| "epoch": 9.09, |
| "learning_rate": 9.090909090909092e-05, |
| "loss": 1.383, |
| "step": 10 |
| }, |
| { |
| "epoch": 11.09, |
| "learning_rate": 0.00010909090909090909, |
| "loss": 1.3159, |
| "step": 12 |
| }, |
| { |
| "epoch": 13.09, |
| "learning_rate": 0.00012727272727272728, |
| "loss": 1.2339, |
| "step": 14 |
| }, |
| { |
| "epoch": 15.09, |
| "learning_rate": 0.00014545454545454546, |
| "loss": 1.1567, |
| "step": 16 |
| }, |
| { |
| "epoch": 17.09, |
| "learning_rate": 0.00016363636363636366, |
| "loss": 1.0992, |
| "step": 18 |
| }, |
| { |
| "epoch": 19.09, |
| "learning_rate": 0.00018181818181818183, |
| "loss": 1.045, |
| "step": 20 |
| } |
| ], |
| "logging_steps": 2, |
| "max_steps": 220, |
| "num_train_epochs": 20, |
| "save_steps": 500, |
| "total_flos": 3205323187814400.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
