<!-- 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. -->
Baseline_30Kphish_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: 0.0374
- Accuracy: 0.9962
- F1: 0.9589
- Precision: 0.9998
- Recall: 0.9212
- Roc Auc Score: 0.9606
- Tpr At Fpr 0.01: 0.9438
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 | 19688 | 0.0304 | 0.9933 | 0.9241 | 0.9993 | 0.8594 | 0.9297 | 0.874 |
| 0.0029 | 2.0 | 39376 | 0.0210 | 0.9967 | 0.9643 | 0.9953 | 0.9352 | 0.9675 | 0.917 |
| 0.0003 | 3.0 | 59064 | 0.0434 | 0.9947 | 0.9407 | 0.9980 | 0.8896 | 0.9448 | 0.8936 |
| 0.0016 | 4.0 | 78752 | 0.0408 | 0.9952 | 0.9468 | 0.9998 | 0.8992 | 0.9496 | 0.9336 |
| 0.0008 | 5.0 | 98440 | 0.0374 | 0.9962 | 0.9589 | 0.9998 | 0.9212 | 0.9606 | 0.9438 |
Framework versions
- Transformers 4.29.1
- Pytorch 1.9.0+cu111
- Datasets 2.10.1
- Tokenizers 0.13.2
