<!-- 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_subdomain_100KP_BFall_fromP_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_MixGPT2_using_phish_95K_top_p_0.75subdomain dataset. It achieves the following results on the evaluation set:
- Loss: 0.0167
- Accuracy: 0.9982
- F1: 0.9807
- Precision: 0.9994
- Recall: 0.9628
- Roc Auc Score: 0.9814
- Tpr At Fpr 0.01: 0.9688
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0042 | 1.0 | 35625 | 0.0207 | 0.9962 | 0.9583 | 0.9987 | 0.921 | 0.9605 | 0.9318 |
| 0.002 | 2.0 | 71250 | 0.0188 | 0.9976 | 0.9737 | 0.9987 | 0.9498 | 0.9749 | 0.9544 |
| 0.0027 | 3.0 | 106875 | 0.0232 | 0.9974 | 0.9719 | 0.9979 | 0.9472 | 0.9736 | 0.9464 |
| 0.0007 | 4.0 | 142500 | 0.0155 | 0.9982 | 0.9805 | 0.9983 | 0.9632 | 0.9816 | 0.965 |
| 0.0007 | 5.0 | 178125 | 0.0167 | 0.9982 | 0.9807 | 0.9994 | 0.9628 | 0.9814 | 0.9688 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
