<!-- 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. -->
Benign10MGPT2_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_Benign10MGPT2_using_phish_95K_top_p_0.75subdomain dataset. It achieves the following results on the evaluation set:
- Loss: 0.0216
- Accuracy: 0.9971
- F1: 0.9691
- Precision: 0.9890
- Recall: 0.95
- Roc Auc Score: 0.9747
- Tpr At Fpr 0.01: 0.914
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.019 | 1.0 | 35625 | 0.0191 | 0.9961 | 0.9584 | 0.9840 | 0.9342 | 0.9667 | 0.8318 |
| 0.0164 | 2.0 | 71250 | 0.0169 | 0.9964 | 0.9609 | 0.9942 | 0.9298 | 0.9648 | 0.8852 |
| 0.0096 | 3.0 | 106875 | 0.0126 | 0.9973 | 0.9717 | 0.9803 | 0.9632 | 0.9811 | 0.8794 |
| 0.0045 | 4.0 | 142500 | 0.0187 | 0.9972 | 0.9700 | 0.9894 | 0.9514 | 0.9754 | 0.9098 |
| 0.0017 | 5.0 | 178125 | 0.0216 | 0.9971 | 0.9691 | 0.9890 | 0.95 | 0.9747 | 0.914 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
