Distilbert Zim Phishing

--- library_name: transformers license: apache-2.0 base_model: distilbert-base-uncased tags: - generated_from_trainer metrics: - accuracy - precision - recall - f1 model-index: - name: distilbert-zim-phishing results: [] --- # distilbert-zim-phishing This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.3919 - Accuracy: 0.9032 - Precision: 0.8667 - Recall: 0.9286 - F1: 0.8966 ## 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: 4 - eval_batch_size: 8 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 20 - num_epochs: 10 - mixed_precision_training: Native AMP - label_smoothing_factor: 0.1 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:---:| | 0.6124 | 1.0 | 27 | 0.5658 | 0.75 | 1.0 | 0.4286 | 0.6 | | 0.5354 | 2.0 | 54 | 0.2746 | 1.0 | 1.0 | 1.0 | 1.0 | | 0.2772 | 3.0 | 81 | 0.2040 | 1.0 | 1.0 | 1.0 | 1.0 | | 0.3967 | 4.0 | 108 | 0.2037 | 1.0 | 1.0 | 1.0 | 1.0 | | 0.3336 | 5.0 | 135 | 0.2289 | 1.0 | 1.0 | 1.0 | 1.0 | | 0.2011 | 6.0 | 162 | 0.2000 | 1.0 | 1.0 | 1.0 | 1.0 | | 0.1995 | 7.0 | 189 | 0.2019 | 1.0 | 1.0 | 1.0 | 1.0 | | 0.1997 | 8.0 | 216 | 0.2025 | 1.0 | 1.0 | 1.0 | 1.0 | | 0.3512 | 9.0 | 243 | 0.2019 | 1.0 | 1.0 | 1.0 | 1.0 | | 0.3142 | 10.0 | 270 | 0.2022 | 1.0 | 1.0 | 1.0 | 1.0 | ### Framework versions - Transformers 5.0.0 - Pytorch 2.10.0+cu128 - Datasets 4.0.0 - Tokenizers 0.22.2