<!-- 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. -->
MixGPT2_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_MixGPT2_using_phish_50K_top_p_0.75_domain dataset. It achieves the following results on the evaluation set:
- Loss: 0.0199
- Accuracy: 0.9980
- F1: 0.9782
- Precision: 0.9990
- Recall: 0.9582
- Roc Auc Score: 0.9791
- Tpr At Fpr 0.01: 0.96
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0058 | 1.0 | 28125 | 0.0175 | 0.9968 | 0.9656 | 0.9977 | 0.9356 | 0.9677 | 0.931 |
| 0.002 | 2.0 | 56250 | 0.0137 | 0.9978 | 0.9769 | 0.9979 | 0.9568 | 0.9783 | 0.9562 |
| 0.0015 | 3.0 | 84375 | 0.0197 | 0.9976 | 0.9741 | 0.9977 | 0.9516 | 0.9757 | 0.9482 |
| 0.0006 | 4.0 | 112500 | 0.0174 | 0.9976 | 0.9739 | 0.9983 | 0.9506 | 0.9753 | 0.9528 |
| 0.0 | 5.0 | 140625 | 0.0199 | 0.9980 | 0.9782 | 0.9990 | 0.9582 | 0.9791 | 0.96 |
Framework versions
- Transformers 4.29.1
- Pytorch 1.9.0+cu111
- Datasets 2.10.1
- Tokenizers 0.13.2
