<!-- 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_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_phish_95K_top_p_0.75_domain dataset. It achieves the following results on the evaluation set:
- Loss: 0.0178
- Accuracy: 0.9977
- F1: 0.9749
- Precision: 0.9987
- Recall: 0.9522
- Roc Auc Score: 0.9761
- Tpr At Fpr 0.01: 0.9624
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 |
---|---|---|---|---|---|---|---|---|---|
0.0038 | 1.0 | 35625 | 0.0152 | 0.9973 | 0.9708 | 0.9979 | 0.9452 | 0.9726 | 0.944 |
0.0039 | 2.0 | 71250 | 0.0097 | 0.9982 | 0.9805 | 0.9947 | 0.9668 | 0.9833 | 0.9504 |
0.003 | 3.0 | 106875 | 0.0178 | 0.9975 | 0.9726 | 0.9987 | 0.9478 | 0.9739 | 0.9532 |
0.0009 | 4.0 | 142500 | 0.0223 | 0.9971 | 0.9689 | 0.9994 | 0.9402 | 0.9701 | 0.9526 |
0.0 | 5.0 | 178125 | 0.0178 | 0.9977 | 0.9749 | 0.9987 | 0.9522 | 0.9761 | 0.9624 |
Framework versions
- Transformers 4.29.1
- Pytorch 1.9.0+cu111
- Datasets 2.10.1
- Tokenizers 0.13.2