| | --- |
| | library_name: transformers |
| | license: mit |
| | base_model: hbseong/HarmAug-Guard |
| | tags: |
| | - generated_from_trainer |
| | metrics: |
| | - accuracy |
| | - precision |
| | - recall |
| | - f1 |
| | model-index: |
| | - name: results |
| | results: [] |
| | --- |
| | |
| | <!-- This model card has been generated automatically according to the information the Trainer had access to. You |
| | should probably proofread and complete it, then remove this comment. --> |
| |
|
| | # results |
| |
|
| | This model is a fine-tuned version of [hbseong/HarmAug-Guard](https://huggingface.co/hbseong/HarmAug-Guard) on an unknown dataset. |
| | It achieves the following results on the evaluation set: |
| | - Loss: 0.1008 |
| | - Accuracy: 0.9667 |
| | - Precision: 0.9667 |
| | - Recall: 0.9667 |
| | - F1: 0.9667 |
| |
|
| | ## Model description |
| |
|
| | More information needed |
| |
|
| | ## Intended uses & limitations |
| |
|
| | More information needed |
| |
|
| | ## Training and evaluation data |
| |
|
| | More information needed |
| |
|
| | ## Training procedure |
| |
|
| | ### Training hyperparameters |
| |
|
| | The following hyperparameters were used during training: |
| | - learning_rate: 3e-05 |
| | - train_batch_size: 1 |
| | - eval_batch_size: 1 |
| | - seed: 42 |
| | - gradient_accumulation_steps: 8 |
| | - total_train_batch_size: 8 |
| | - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| | - lr_scheduler_type: linear |
| | - lr_scheduler_warmup_steps: 5 |
| | - num_epochs: 10 |
| | - mixed_precision_training: Native AMP |
| |
|
| | ### Training results |
| |
|
| | | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | |
| | |:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:| |
| | | 0.4652 | 0.9895 | 59 | 0.2876 | 0.9417 | 0.9445 | 0.9417 | 0.9414 | |
| | | 0.003 | 1.9958 | 119 | 0.1736 | 0.9667 | 0.9689 | 0.9667 | 0.9667 | |
| | | 0.0027 | 2.9853 | 178 | 0.2779 | 0.95 | 0.9519 | 0.95 | 0.9499 | |
| | | 0.1023 | 3.9916 | 238 | 0.3743 | 0.9333 | 0.9408 | 0.9333 | 0.9328 | |
| | | 0.0015 | 4.9979 | 298 | 0.3164 | 0.9417 | 0.9417 | 0.9417 | 0.9416 | |
| | | 0.0003 | 5.9874 | 357 | 0.2952 | 0.9583 | 0.9614 | 0.9583 | 0.9582 | |
| | | 0.0002 | 6.9937 | 417 | 0.2069 | 0.9417 | 0.9426 | 0.9417 | 0.9416 | |
| | | 0.0001 | 8.0 | 477 | 0.1738 | 0.9583 | 0.9584 | 0.9583 | 0.9583 | |
| | | 0.0001 | 8.9895 | 536 | 0.1008 | 0.9667 | 0.9667 | 0.9667 | 0.9667 | |
| | | 0.0001 | 9.8952 | 590 | 0.1016 | 0.9667 | 0.9667 | 0.9667 | 0.9667 | |
| |
|
| |
|
| | ### Framework versions |
| |
|
| | - Transformers 4.44.2 |
| | - Pytorch 2.5.0+cu121 |
| | - Datasets 3.0.2 |
| | - Tokenizers 0.19.1 |
| |
|
