<!-- 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. -->
OnlyPhishGPT2_Domain_100KP_BFall_fromP_50K_topP_0.75_ratio5
This model is a fine-tuned version of bert-base-uncased on the Train benign: Fall,Test Benign: Fall, Train phish: Fall, Test phish: Fall, generated url dataset: generated_phish_OnlyPhishGPT2_using_phish_50K_top_p_0.75_domain dataset. It achieves the following results on the evaluation set:
- Loss: 0.0208
- Accuracy: 0.9977
- F1: 0.9758
- Precision: 0.9973
- Recall: 0.9552
- Roc Auc Score: 0.9775
- Tpr At Fpr 0.01: 0.9522
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: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Roc Auc Score | Tpr At Fpr 0.01 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0087 | 1.0 | 28125 | 0.0161 | 0.9973 | 0.9706 | 0.9935 | 0.9488 | 0.9742 | 0.9358 |
| 0.0031 | 2.0 | 56250 | 0.0153 | 0.9979 | 0.9779 | 0.9944 | 0.962 | 0.9809 | 0.9398 |
| 0.0021 | 3.0 | 84375 | 0.0191 | 0.9977 | 0.9754 | 0.9975 | 0.9542 | 0.9770 | 0.9498 |
| 0.0003 | 4.0 | 112500 | 0.0203 | 0.9975 | 0.9728 | 0.9977 | 0.9492 | 0.9745 | 0.9484 |
| 0.0 | 5.0 | 140625 | 0.0208 | 0.9977 | 0.9758 | 0.9973 | 0.9552 | 0.9775 | 0.9522 |
Framework versions
- Transformers 4.29.1
- Pytorch 1.9.0+cu111
- Datasets 2.10.1
- Tokenizers 0.13.2
