<!-- 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_fromB_100K_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_benign_100K_top_p_0.75_domain dataset. It achieves the following results on the evaluation set:
- Loss: 0.0165
- Accuracy: 0.9974
- F1: 0.9719
- Precision: 0.9911
- Recall: 0.9534
- Roc Auc Score: 0.9765
- Tpr At Fpr 0.01: 0.0
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0157 | 1.0 | 37500 | 0.0149 | 0.9967 | 0.9650 | 0.9680 | 0.962 | 0.9802 | 0.7518 |
| 0.0091 | 2.0 | 75000 | 0.0137 | 0.9972 | 0.9699 | 0.9775 | 0.9624 | 0.9806 | 0.0 |
| 0.004 | 3.0 | 112500 | 0.0219 | 0.9970 | 0.9675 | 0.9902 | 0.9458 | 0.9727 | 0.9148 |
| 0.0038 | 4.0 | 150000 | 0.0180 | 0.9975 | 0.9737 | 0.9867 | 0.961 | 0.9802 | 0.0 |
| 0.0007 | 5.0 | 187500 | 0.0165 | 0.9974 | 0.9719 | 0.9911 | 0.9534 | 0.9765 | 0.0 |
Framework versions
- Transformers 4.29.1
- Pytorch 1.9.0+cu111
- Datasets 2.10.1
- Tokenizers 0.13.2
