Zahin112

How to use my own database for training and evaluating Retro for Question-Answering?

2

What is the main purpose or outcome of this training? is it only for text completion? How do I finetune it for Question-Answering or any other downstream task? I want...

A bit confused about the process of using my own dataset to train or finetune with Retro. Also how can I evaluate the trained model?

While running the Trainingwrapper script in google Colab, No embeddings found in folder .tmp/embeddings.