<!-- 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. -->
Base_10Kphish_benignFall_IL_10Krealphish_0.75
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0551
- Accuracy: 0.9938
- F1: 0.9303
- Precision: 0.9982
- Recall: 0.871
- Roc Auc Score: 0.9355
- Tpr At Fpr 0.01: 0.8794
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0079 | 1.0 | 6563 | 0.0209 | 0.9956 | 0.9525 | 0.9878 | 0.9196 | 0.9595 | 0.862 |
| 0.003 | 2.0 | 13126 | 0.0338 | 0.9949 | 0.9438 | 0.9940 | 0.8984 | 0.9491 | 0.8796 |
| 0.0024 | 3.0 | 19689 | 0.0410 | 0.9948 | 0.9427 | 0.9949 | 0.8958 | 0.9478 | 0.8648 |
| 0.0014 | 4.0 | 26252 | 0.0493 | 0.9941 | 0.9342 | 0.9982 | 0.878 | 0.9390 | 0.881 |
| 0.0003 | 5.0 | 32815 | 0.0551 | 0.9938 | 0.9303 | 0.9982 | 0.871 | 0.9355 | 0.8794 |
Framework versions
- Transformers 4.29.1
- Pytorch 1.9.0+cu111
- Datasets 2.10.1
- Tokenizers 0.13.2
