Are you tired of scrolling down through logs when training an ML model?

Try this Jupyter extension

Background image by Free-Photos from Pixabay

By default, when the output of a code cell in a Jupyter notebook gets too long, the content remains in its initial position and you have to manually scroll down to see the latest output. And this can be very annoying.

For example, if you train a Machine Learning model from a Jupyter notebook and you want some info to be printed after each batch or epoch, you would like to have the output automatically scrolling so that you can see the message about the last printed epochs, but instead, nothing happens, you have to scroll down manually.

Below is a for loop that simulates this type of output. This is what usually happens in a Jupyter notebook:

But the good news is that there is a solution to this problem. There is a Jupyter extension named scroll_down that can be used to automatically scroll down through the output.

It doesn’t come with the usual Jupyter installation, so we have to install it separately.

Let’s start by installing this Jupyter extension.