email-phishing-detector
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0351
- Accuracy: 0.9947
- Precision: 0.9953
- Recall: 0.9944
- F1: 0.9949
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.0363 | 1.0 | 4125 | 0.0341 | 0.9913 | 0.9961 | 0.9871 | 0.9916 |
| 0.0155 | 2.0 | 8250 | 0.0292 | 0.9935 | 0.9945 | 0.9930 | 0.9938 |
| 0.0024 | 3.0 | 12375 | 0.0351 | 0.9947 | 0.9953 | 0.9944 | 0.9949 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1