<!-- 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_suffix_100KP_BFall_fromB_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_OnlyPhishGPT2_using_benigh_95KtopP_0.75suffix dataset. It achieves the following results on the evaluation set:
- Loss: 0.0247
- Accuracy: 0.9964
- F1: 0.9611
- Precision: 0.9928
- Recall: 0.9314
- Roc Auc Score: 0.9655
- Tpr At Fpr 0.01: 0.8832
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.016 | 1.0 | 35625 | 0.0162 | 0.9964 | 0.9616 | 0.9695 | 0.9538 | 0.9762 | 0.8308 |
| 0.0075 | 2.0 | 71250 | 0.0195 | 0.9961 | 0.9586 | 0.9625 | 0.9548 | 0.9765 | 0.772 |
| 0.0056 | 3.0 | 106875 | 0.0177 | 0.9968 | 0.9659 | 0.9887 | 0.9442 | 0.9718 | 0.8838 |
| 0.0022 | 4.0 | 142500 | 0.0309 | 0.9958 | 0.9543 | 0.9918 | 0.9196 | 0.9596 | 0.865 |
| 0.0013 | 5.0 | 178125 | 0.0247 | 0.9964 | 0.9611 | 0.9928 | 0.9314 | 0.9655 | 0.8832 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
