<!-- 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. -->
MixGPT2V2_domain_100KP_BFall_fromB_95K_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_MixGPT2V2_using_benign_95K_top_p_0.75domain dataset. It achieves the following results on the evaluation set:
- Loss: 0.0193
- Accuracy: 0.9978
- F1: 0.9769
- Precision: 0.9944
- Recall: 0.96
- Roc Auc Score: 0.9799
- Tpr At Fpr 0.01: 0.9398
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0092 | 1.0 | 36563 | 0.0171 | 0.9963 | 0.9592 | 0.9972 | 0.924 | 0.9619 | 0.907 |
| 0.0048 | 2.0 | 73126 | 0.0122 | 0.9977 | 0.9760 | 0.9851 | 0.967 | 0.9831 | 0.9142 |
| 0.0031 | 3.0 | 109689 | 0.0171 | 0.9972 | 0.9703 | 0.9950 | 0.9468 | 0.9733 | 0.9254 |
| 0.0011 | 4.0 | 146252 | 0.0158 | 0.9978 | 0.9763 | 0.9855 | 0.9672 | 0.9832 | 0.9262 |
| 0.0007 | 5.0 | 182815 | 0.0193 | 0.9978 | 0.9769 | 0.9944 | 0.96 | 0.9799 | 0.9398 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
