<!-- 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. -->
Onlyphish_100KP_BFall_fromB_40KGen_topP_0.75_noaddedB
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_benign_40K_top_p_0.75 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0177
- Accuracy: 0.9976
- F1: 0.9746
- Precision: 0.9994
- Recall: 0.951
- Roc Auc Score: 0.9755
- Tpr At Fpr 0.01: 0.965
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0034 | 1.0 | 66875 | 0.0124 | 0.9970 | 0.9680 | 0.9926 | 0.9446 | 0.9721 | 0.9258 |
| 0.0015 | 2.0 | 133750 | 0.0227 | 0.9969 | 0.9667 | 0.9974 | 0.9378 | 0.9688 | 0.9346 |
| 0.0011 | 3.0 | 200625 | 0.0224 | 0.9969 | 0.9669 | 0.9991 | 0.9366 | 0.9683 | 0.9476 |
| 0.0005 | 4.0 | 267500 | 0.0200 | 0.9975 | 0.9731 | 0.9992 | 0.9484 | 0.9742 | 0.9618 |
| 0.0006 | 5.0 | 334375 | 0.0177 | 0.9976 | 0.9746 | 0.9994 | 0.951 | 0.9755 | 0.965 |
Framework versions
- Transformers 4.29.1
- Pytorch 1.9.0+cu111
- Datasets 2.10.1
- Tokenizers 0.13.2
