albert-base-v2-Malicious_URLs
This model is a fine-tuned version of albert-base-v2.
It achieves the following results on the evaluation set:
- Loss: 0.8368
- Accuracy: 0.7267
- F1:
- Weighted: 0.6482
- Micro: 0.7267
- Macro: 0.4521
- Recall
- Weighted: 0.7267
- Micro: 0.7267
- Macro: 0.4294
- Precision
- Weighted: 0.6262
- Micro: 0.7267
- Macro: 0.5508
Model description
For more information on how it was created, check out the following link: https://github.com/DunnBC22/NLP_Projects/blob/main/Multiclass%20Classification/Malicious%20URLs%20-%20ALBERT-Base_v2/Malicious%20URLs%20ALBERT-Base%20v2.ipynb
Intended uses & limitations
This model is intended to demonstrate my ability to solve a complex problem using technology.
Training and evaluation data
Dataset Source: https://www.kaggle.com/datasets/sid321axn/malicious-urls-dataset
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Weighted F1 | Micro F1 | Macro F1 | Weighted Recall | Micro Recall | Macro Recall | Weighted Precision | Micro Precision | Macro Precision |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.7839 | 1.0 | 51087 | 0.8368 | 0.7267 | 0.6482 | 0.7267 | 0.4521 | 0.7267 | 0.7267 | 0.4294 | 0.6262 | 0.7267 | 0.5508 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
