<!-- 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_subdomain_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_0.75subdomain dataset. It achieves the following results on the evaluation set:
- Loss: 0.0192
- Accuracy: 0.9978
- F1: 0.9759
- Precision: 0.9990
- Recall: 0.9538
- Roc Auc Score: 0.9769
- 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
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Roc Auc Score | Tpr At Fpr 0.01 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0076 | 1.0 | 36563 | 0.0117 | 0.9974 | 0.9718 | 0.9983 | 0.9466 | 0.9733 | 0.9496 |
| 0.0035 | 2.0 | 73126 | 0.0206 | 0.9973 | 0.9710 | 0.9981 | 0.9454 | 0.9727 | 0.9496 |
| 0.0025 | 3.0 | 109689 | 0.0184 | 0.9970 | 0.9677 | 0.9985 | 0.9388 | 0.9694 | 0.942 |
| 0.0008 | 4.0 | 146252 | 0.0199 | 0.9972 | 0.9698 | 0.9994 | 0.942 | 0.9710 | 0.9504 |
| 0.0 | 5.0 | 182815 | 0.0192 | 0.9978 | 0.9759 | 0.9990 | 0.9538 | 0.9769 | 0.96 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
