<!-- 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_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_Benign10MGPT2_using_benign_95K_top_p_0.75suffix dataset. It achieves the following results on the evaluation set:
- Loss: 0.0623
- Accuracy: 0.9881
- F1: 0.8818
- Precision: 0.8347
- Recall: 0.9344
- Roc Auc Score: 0.9626
- Tpr At Fpr 0.01: 0.7796
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0915 | 1.0 | 35625 | 0.0478 | 0.9880 | 0.8761 | 0.8605 | 0.8922 | 0.9425 | 0.7968 |
| 0.0797 | 2.0 | 71250 | 0.0386 | 0.9897 | 0.8959 | 0.8654 | 0.9286 | 0.9607 | 0.8378 |
| 0.0622 | 3.0 | 106875 | 0.0459 | 0.9876 | 0.8760 | 0.8335 | 0.923 | 0.9569 | 0.77 |
| 0.0398 | 4.0 | 142500 | 0.0544 | 0.9882 | 0.8828 | 0.8370 | 0.9338 | 0.9624 | 0.8568 |
| 0.0298 | 5.0 | 178125 | 0.0623 | 0.9881 | 0.8818 | 0.8347 | 0.9344 | 0.9626 | 0.7796 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.0+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
