bert-large-finetuned-phishing-webpage-cleaned-version-4.0

This model is a fine-tuned version of google-bert/bert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1007
• Accuracy: 0.9653
• Precision: 0.9853
• Recall: 0.9464
• False Positive Rate: 0.0148

Code-to-clean-webapage

Github : https://github.com/nguy2311/Clean-webpage/blob/main/clean_webpage.ipynb

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
• gradient_accumulation_steps: 8
• total_train_batch_size: 256
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 0.1
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	False Positive Rate
0.2025	0.9990	883	0.1460	0.9457	0.9888	0.9042	0.0107
0.0891	1.9992	1767	0.1068	0.9637	0.9824	0.9460	0.0178
0.0678	2.9970	2649	0.1007	0.9653	0.9853	0.9464	0.0148

Framework versions

• Transformers 4.41.2
• Pytorch 2.1.2
• Datasets 2.18.0
• Tokenizers 0.19.1