In this tutorial, we’ll build a near state of the art sentence classifier leveraging the power of recent breakthroughs in the field of Natural Language Processing. We’ll focus on an application of transfer learning to NLP. We'll use this to create high performance models with minimal effort on a range of NLP tasks. Google’s BERT allowed researchers to smash multiple benchmarks with minimal fine tuning for specific tasks. As a result, NLP research reproduction and experimentation has become more accessible.
We'll use WandB's hyperparameter Sweeps later on. Here's a simple notebook to get you started with sweeps.