<!-- 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_40Kphish_benignWinter_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: 0.9955
- F1: 0.9501
- Precision: 0.9989
- Recall: 0.9058
- Roc Auc Score: 0.9529
- Tpr At Fpr 0.01: 0.9122
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.0055 | 1.0 | 26250 | 0.0223 | 0.9944 | 0.9384 | 0.9913 | 0.8908 | 0.9452 | 0.8514 |
| 0.0026 | 2.0 | 52500 | 0.0300 | 0.9958 | 0.9539 | 0.9905 | 0.9198 | 0.9597 | 0.0 |
| 0.0045 | 3.0 | 78750 | 0.0355 | 0.9954 | 0.9489 | 0.9982 | 0.9042 | 0.9521 | 0.9054 |
| 0.0025 | 4.0 | 105000 | 0.0311 | 0.9955 | 0.9500 | 0.9987 | 0.9058 | 0.9529 | 0.9142 |
| 0.0004 | 5.0 | 131250 | 0.0374 | 0.9955 | 0.9501 | 0.9989 | 0.9058 | 0.9529 | 0.9122 |
Framework versions
- Transformers 4.29.1
- Pytorch 1.9.0+cu111
- Datasets 2.10.1
- Tokenizers 0.13.2
