This project demonstrates the training of a transformer model from scratch on the IMDB dataset. the model task is to classify reviews as positive of negative.
The dataset used in this project is the IMDB Dataset of 50K Movie Reviews from Kaggle. The dataset contains 50k reviews labeled as positive or negative.
The model used in this project is a standard transformer model:
To run this project, you need to have Python installed along with the required libraries. You can install the necessary dependencies using the following command:
pip install -r requirements.txtTo train and test the model, run the main.ipynb notebook. This notebook contains all the steps from data preprocessing, model training, and evaluation.
Contributions are welcome! If you have any suggestions or improvements, feel free to open an issue or submit a pull request.