This repository explains how to use the bucket_by_sequence_length tensorflow 2.0 api
Download the dataset from the kaggle https://www.kaggle.com/rmisra/news-headlines-dataset-for-sarcasm-detection'
'and paste it in the ./data folder, download the version 2.
Once the dataset is downloaded, kindly run the main.py to train the model.
Link to the tutorial is here - https://medium.com/@pbhatt110/tutorial-on-bucket-by-sequence-length-api-for-efficiently-batching-nlp-data-while-training-20d8ef5219d7