<!-- 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. -->
Benign10MGPT2_domain_100KP_BFall_fromB_90K_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_Benign10MGPT2_using_benign_95K_top_p_0.75domain dataset. It achieves the following results on the evaluation set:
- Loss: 0.0674
- Accuracy: 0.9880
- F1: 0.8814
- Precision: 0.8355
- Recall: 0.9326
- Roc Auc Score: 0.9617
- Tpr At Fpr 0.01: 0.6842
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0937 | 1.0 | 35625 | 0.0447 | 0.9902 | 0.8993 | 0.8786 | 0.921 | 0.9573 | 0.8528 |
| 0.0787 | 2.0 | 71250 | 0.0350 | 0.9913 | 0.9088 | 0.9048 | 0.9128 | 0.9540 | 0.8108 |
| 0.0626 | 3.0 | 106875 | 0.0496 | 0.9882 | 0.8804 | 0.8478 | 0.9156 | 0.9537 | 0.817 |
| 0.0454 | 4.0 | 142500 | 0.0595 | 0.9870 | 0.8717 | 0.8212 | 0.9288 | 0.9593 | 0.7772 |
| 0.0262 | 5.0 | 178125 | 0.0674 | 0.9880 | 0.8814 | 0.8355 | 0.9326 | 0.9617 | 0.6842 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.0+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
