Baseline_50Kphish_benignFall_20_20_20
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0282
- Accuracy: 0.9962
- F1: 0.9580
- Precision: 0.9996
- Recall: 0.9198
- Roc Auc Score: 0.9599
- Tpr At Fpr 0.01: 0.94
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0045 | 1.0 | 32813 | 0.0247 | 0.9960 | 0.9561 | 0.9937 | 0.9212 | 0.9605 | 0.8662 |
| 0.002 | 2.0 | 65626 | 0.0205 | 0.9965 | 0.9624 | 0.9987 | 0.9286 | 0.9643 | 0.9376 |
| 0.0021 | 3.0 | 98439 | 0.0302 | 0.9961 | 0.9569 | 0.9993 | 0.918 | 0.9590 | 0.9378 |
| 0.0017 | 4.0 | 131252 | 0.0297 | 0.9970 | 0.9672 | 0.9975 | 0.9388 | 0.9693 | 0.9368 |
| 0.0007 | 5.0 | 164065 | 0.0282 | 0.9962 | 0.9580 | 0.9996 | 0.9198 | 0.9599 | 0.94 |
Framework versions
- Transformers 4.29.1
- Pytorch 1.9.0+cu111
- Datasets 2.10.1
- Tokenizers 0.13.2