summarization

T5 Summarisation Using Pytorch Lightning

Instructions

Clone the repo.
Run make dirs to create the missing parts of the directory structure described below.
Optional: Run make virtualenv to create a python virtual environment. Skip if using conda or some other env manager.
1. Run source env/bin/activate to activate the virtualenv.
Run make requirements to install required python packages.
Put the raw data in data/raw.
To save the raw data to the DVC cache, run dvc commit raw_data.dvc
Edit the code files to your heart's desire.
Process your data, train and evaluate your model using dvc repro eval.dvc or make reproduce
When you're happy with the result, commit files (including .dvc files) to git.