| { |
| "best_metric": 2.084447145462036, |
| "best_model_checkpoint": "output/kishlak/checkpoint-26", |
| "epoch": 1.0, |
| "global_step": 26, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.19, |
| "learning_rate": 0.00012505669320030482, |
| "loss": 2.4461, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 9.292589525111794e-05, |
| "loss": 2.1062, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.58, |
| "learning_rate": 5.218294542987356e-05, |
| "loss": 2.0242, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.77, |
| "learning_rate": 1.725216267546246e-05, |
| "loss": 1.8962, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.96, |
| "learning_rate": 5.001712368734975e-07, |
| "loss": 1.9747, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 2.084447145462036, |
| "eval_runtime": 1.7838, |
| "eval_samples_per_second": 21.303, |
| "eval_steps_per_second": 2.803, |
| "step": 26 |
| } |
| ], |
| "max_steps": 26, |
| "num_train_epochs": 1, |
| "total_flos": 26521141248000.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
