distilbert_enron_emails
This model is a fine-tuned version of distilbert-base-uncased on an SetFit/enron_spam for Spam Dectection
task.
It achieves the following results on the evaluation set:
- Loss: 0.0522
- Accuracy: 0.9935
- F1: 0.9936
- Precision: 0.9921
- Recall: 0.9950
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: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
---|---|---|---|---|---|---|---|
0.0454 | 1.0 | 1983 | 0.0430 | 0.9905 | 0.9906 | 0.9872 | 0.9940 |
0.009 | 2.0 | 3966 | 0.0535 | 0.991 | 0.9911 | 0.9930 | 0.9891 |
0.005 | 3.0 | 5949 | 0.0522 | 0.9935 | 0.9936 | 0.9921 | 0.9950 |
0.0002 | 4.0 | 7932 | 0.0650 | 0.991 | 0.9911 | 0.9920 | 0.9901 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 6