Base_100Kphish_benignFall_IL_10K_OnlyPhish_from_benign_top_p_0.75
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0237
- Accuracy: 0.9975
- F1: 0.9731
- Precision: 0.9983
- Recall: 0.9492
- Roc Auc Score: 0.9746
- Tpr At Fpr 0.01: 0.9508
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0042 | 1.0 | 6563 | 0.0276 | 0.9966 | 0.9628 | 0.9983 | 0.9298 | 0.9649 | 0.9308 |
| 0.0024 | 2.0 | 13126 | 0.0242 | 0.9972 | 0.9698 | 0.9973 | 0.9438 | 0.9718 | 0.927 |
| 0.0026 | 3.0 | 19689 | 0.0244 | 0.9970 | 0.9679 | 0.9987 | 0.939 | 0.9695 | 0.9514 |
| 0.0003 | 4.0 | 26252 | 0.0293 | 0.9968 | 0.9657 | 0.9989 | 0.9346 | 0.9673 | 0.9472 |
| 0.0007 | 5.0 | 32815 | 0.0237 | 0.9975 | 0.9731 | 0.9983 | 0.9492 | 0.9746 | 0.9508 |
Framework versions
- Transformers 4.29.1
- Pytorch 1.9.0+cu111
- Datasets 2.10.1
- Tokenizers 0.13.2