<!-- 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_subdomain_100KP_BFall_fromB_200K_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_benigh_200K_top_p_0.75 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0194
- Accuracy: 0.9979
- F1: 0.9778
- Precision: 0.9987
- Recall: 0.9578
- Roc Auc Score: 0.9789
- Tpr At Fpr 0.01: 0.9642
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0035 | 1.0 | 56250 | 0.0126 | 0.9975 | 0.9736 | 0.9917 | 0.9562 | 0.9779 | 0.9052 |
| 0.002 | 2.0 | 112500 | 0.0159 | 0.9977 | 0.9755 | 0.9975 | 0.9544 | 0.9771 | 0.9466 |
| 0.0008 | 3.0 | 168750 | 0.0136 | 0.9981 | 0.9793 | 0.9977 | 0.9616 | 0.9807 | 0.958 |
| 0.0 | 4.0 | 225000 | 0.0235 | 0.9973 | 0.9708 | 0.9992 | 0.944 | 0.9720 | 0.9574 |
| 0.0004 | 5.0 | 281250 | 0.0194 | 0.9979 | 0.9778 | 0.9987 | 0.9578 | 0.9789 | 0.9642 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
