| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 6.944444444444445, |
| "eval_steps": 500, |
| "global_step": 1000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 3.47, |
| "learning_rate": 1.3069444444444446e-05, |
| "loss": 0.0337, |
| "step": 500 |
| }, |
| { |
| "epoch": 3.47, |
| "eval_accuracy": 0.9997195086900363, |
| "eval_f1": 0.9970659339871015, |
| "eval_loss": 0.0010710632195696235, |
| "eval_precision": 0.9965583503025783, |
| "eval_recall": 0.9975740349970572, |
| "eval_runtime": 52.9895, |
| "eval_samples_per_second": 74.203, |
| "eval_steps_per_second": 1.17, |
| "step": 500 |
| }, |
| { |
| "epoch": 6.94, |
| "learning_rate": 6.125000000000001e-06, |
| "loss": 0.0006, |
| "step": 1000 |
| }, |
| { |
| "epoch": 6.94, |
| "eval_accuracy": 0.9997527521045505, |
| "eval_f1": 0.9976693319946933, |
| "eval_loss": 0.0008877807413227856, |
| "eval_precision": 0.9968186638388123, |
| "eval_recall": 0.9985214532822302, |
| "eval_runtime": 69.3048, |
| "eval_samples_per_second": 56.735, |
| "eval_steps_per_second": 0.895, |
| "step": 1000 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 1440, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 500, |
| "total_flos": 1.3191935457675504e+16, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
