How to train a model with the given dataset?

[nashid]

Thanks for sharing the artefact. However, the steps are not clear enough for replication.

I have downloaded the dataset from https://github.com/lin-tan/CoCoNut-Artifact/releases/tag/training_data_1.0.0

Dataset for python:

coconut/coconut-dataset/python/2010$ ls -rlt
add.txt
context.txt
meta.txt
rem.txt

After that what next needs to be done?

There are many scripts under the ./source/ folder without any steps on how to train a model with the given dataset. It appears from me the first step is to run ./source/tokenization/generate_data.py:?

Then we should run the ./source/training/prepare_data.py?

Can you provide some steps, please? Looking forward to your help.