<!-- 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_fromB_90K_topP_0.75_ratio2.63
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_benigh_95KtopP_0.75domain dataset. It achieves the following results on the evaluation set:
- Loss: 0.0237
- Accuracy: 0.9975
- F1: 0.9730
- Precision: 0.9919
- Recall: 0.9548
- Roc Auc Score: 0.9772
- Tpr At Fpr 0.01: 0.8994
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
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Roc Auc Score | Tpr At Fpr 0.01 |
|---|---|---|---|---|---|---|---|---|---|
| 0.016 | 1.0 | 21554 | 0.0172 | 0.9956 | 0.9534 | 0.9510 | 0.9558 | 0.9767 | 0.7948 |
| 0.0116 | 2.0 | 43108 | 0.0106 | 0.9974 | 0.9725 | 0.9886 | 0.9568 | 0.9781 | 0.9016 |
| 0.0019 | 3.0 | 64662 | 0.0163 | 0.9969 | 0.9669 | 0.9801 | 0.954 | 0.9765 | 0.881 |
| 0.001 | 4.0 | 86216 | 0.0159 | 0.9977 | 0.9759 | 0.9837 | 0.9682 | 0.9837 | 0.8896 |
| 0.0 | 5.0 | 107770 | 0.0237 | 0.9975 | 0.9730 | 0.9919 | 0.9548 | 0.9772 | 0.8994 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
