<!-- 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_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_MixGPT2V2_using_phish_95K_top_p_0.75subdomain dataset. It achieves the following results on the evaluation set:
- Loss: 0.0403
- Accuracy: 0.9980
- F1: 0.9791
- Precision: 0.9992
- Recall: 0.9598
- Roc Auc Score: 0.9799
- Tpr At Fpr 0.01: 0.9634
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: 64
- eval_batch_size: 64
- 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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0198 | 1.0 | 17813 | 0.0476 | 0.9970 | 0.9676 | 0.9985 | 0.9386 | 0.9693 | 0.9398 |
| 0.0082 | 2.0 | 35626 | 0.0299 | 0.9980 | 0.9791 | 0.9965 | 0.9624 | 0.9811 | 0.9544 |
| 0.0041 | 3.0 | 53439 | 0.0414 | 0.9976 | 0.9744 | 0.9987 | 0.9512 | 0.9756 | 0.9552 |
| 0.0033 | 4.0 | 71252 | 0.0346 | 0.9980 | 0.9787 | 0.9979 | 0.9602 | 0.9800 | 0.96 |
| 0.0 | 5.0 | 89065 | 0.0403 | 0.9980 | 0.9791 | 0.9992 | 0.9598 | 0.9799 | 0.9634 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
