<!-- 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. -->
OnlyPhishGPT2_Domain_100KP_BFall_fromP_50K_topP_0.75_ratio4
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_OnlyPhishGPT2_using_phish_50K_top_p_0.75_domain dataset. It achieves the following results on the evaluation set:
- Loss: 0.0215
- Accuracy: 0.9977
- F1: 0.9757
- Precision: 0.9985
- Recall: 0.9538
- Roc Auc Score: 0.9769
- Tpr At Fpr 0.01: 0.9572
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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Roc Auc Score | Tpr At Fpr 0.01 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0041 | 1.0 | 23438 | 0.0120 | 0.9972 | 0.9701 | 0.9954 | 0.946 | 0.9729 | 0.9206 |
| 0.0043 | 2.0 | 46876 | 0.0140 | 0.9971 | 0.9688 | 0.9975 | 0.9418 | 0.9708 | 0.9394 |
| 0.0023 | 3.0 | 70314 | 0.0183 | 0.9976 | 0.9737 | 0.9971 | 0.9514 | 0.9756 | 0.9388 |
| 0.0012 | 4.0 | 93752 | 0.0143 | 0.9983 | 0.9819 | 0.9955 | 0.9686 | 0.9842 | 0.9638 |
| 0.0003 | 5.0 | 117190 | 0.0215 | 0.9977 | 0.9757 | 0.9985 | 0.9538 | 0.9769 | 0.9572 |
Framework versions
- Transformers 4.29.1
- Pytorch 1.9.0+cu111
- Datasets 2.10.1
- Tokenizers 0.13.2
