Text Classification
Collection
Phishing website binary classification • 4 items • Updated
Text Classification
Transformers
TensorBoard
Safetensors
roberta
Generated from Trainer
text-embeddings-inference
# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("aisuko/phishing-binary-classification")
model = AutoModelForSequenceClassification.from_pretrained("aisuko/phishing-binary-classification")Quick Links
phishing-binary-classification
This model is a fine-tuned version of openai-community/roberta-large-openai-detector on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2813
- Accuracy: 0.882
- Auc: 0.954
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: 0.0002
- 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Auc |
|---|---|---|---|---|---|
| 0.5501 | 1.0 | 1250 | 0.4015 | 0.818 | 0.927 |
| 0.4611 | 2.0 | 2500 | 0.3605 | 0.842 | 0.923 |
| 0.4445 | 3.0 | 3750 | 0.3759 | 0.827 | 0.939 |
| 0.413 | 4.0 | 5000 | 0.3058 | 0.866 | 0.946 |
| 0.4152 | 5.0 | 6250 | 0.3554 | 0.837 | 0.953 |
| 0.4086 | 6.0 | 7500 | 0.2908 | 0.874 | 0.949 |
| 0.4057 | 7.0 | 8750 | 0.3338 | 0.853 | 0.946 |
| 0.3966 | 8.0 | 10000 | 0.2807 | 0.88 | 0.953 |
| 0.3961 | 9.0 | 11250 | 0.2836 | 0.878 | 0.952 |
| 0.3962 | 10.0 | 12500 | 0.2813 | 0.882 | 0.954 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0
- Downloads last month
- 4
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="aisuko/phishing-binary-classification")