<!-- 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_ratio2.63
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: 0.0186
- Accuracy: 0.9982
- F1: 0.9805
- Precision: 0.9975
- Recall: 0.964
- Roc Auc Score: 0.9819
- Tpr At Fpr 0.01: 0.9566
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.011 | 1.0 | 22121 | 0.0217 | 0.9961 | 0.9569 | 0.9970 | 0.92 | 0.9599 | 0.9126 |
| 0.0041 | 2.0 | 44242 | 0.0171 | 0.9970 | 0.9679 | 0.9977 | 0.9398 | 0.9698 | 0.9332 |
| 0.0028 | 3.0 | 66363 | 0.0123 | 0.9980 | 0.9787 | 0.9829 | 0.9746 | 0.9869 | 0.902 |
| 0.0012 | 4.0 | 88484 | 0.0175 | 0.9975 | 0.9727 | 0.9983 | 0.9484 | 0.9742 | 0.9502 |
| 0.0 | 5.0 | 110605 | 0.0186 | 0.9982 | 0.9805 | 0.9975 | 0.964 | 0.9819 | 0.9566 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
