| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 14.992, |
| "global_step": 18740, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 4.0, |
| "learning_rate": 1.5720000000000002e-05, |
| "loss": 1.5555, |
| "step": 5000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.27814093232154846, |
| "eval_runtime": 44.6238, |
| "eval_samples_per_second": 56.024, |
| "eval_steps_per_second": 7.014, |
| "step": 5000 |
| }, |
| { |
| "epoch": 8.0, |
| "learning_rate": 1.0005714285714287e-05, |
| "loss": 0.2086, |
| "step": 10000 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_loss": 0.16615858674049377, |
| "eval_runtime": 44.9712, |
| "eval_samples_per_second": 55.591, |
| "eval_steps_per_second": 6.96, |
| "step": 10000 |
| }, |
| { |
| "epoch": 12.0, |
| "learning_rate": 4.292571428571429e-06, |
| "loss": 0.112, |
| "step": 15000 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_loss": 0.14395931363105774, |
| "eval_runtime": 43.9047, |
| "eval_samples_per_second": 56.942, |
| "eval_steps_per_second": 7.129, |
| "step": 15000 |
| } |
| ], |
| "max_steps": 18750, |
| "num_train_epochs": 15, |
| "total_flos": 8747485098654120.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
