<!-- 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. -->
Baseline_100Kphish_benignFall_9.5_20_20
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_0.75suffix dataset. It achieves the following results on the evaluation set:
- Loss: 0.0498
- Accuracy: 0.9974
- F1: 0.9720
- Precision: 0.9987
- Recall: 0.9466
- Roc Auc Score: 0.9733
- Tpr At Fpr 0.01: 0.953
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0142 | 1.0 | 16407 | 0.0389 | 0.9974 | 0.9719 | 0.9958 | 0.9492 | 0.9745 | 0.9348 |
| 0.0111 | 2.0 | 32814 | 0.0376 | 0.9977 | 0.9751 | 0.9975 | 0.9536 | 0.9767 | 0.951 |
| 0.0022 | 3.0 | 49221 | 0.0328 | 0.9981 | 0.9794 | 0.9961 | 0.9632 | 0.9815 | 0.9512 |
| 0.0 | 4.0 | 65628 | 0.0438 | 0.9977 | 0.9758 | 0.9985 | 0.954 | 0.9770 | 0.9566 |
| 0.0005 | 5.0 | 82035 | 0.0498 | 0.9974 | 0.9720 | 0.9987 | 0.9466 | 0.9733 | 0.953 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
