Added Comments to run.py for Improved Readability

[matheusmaldaner]

Hi, I came across this project while working with Differentiable Logic Gate Networks (difflogic) by Felix Petersen, which was one of the works cited in your paper. I am interested in the concept of a logic-based Transformer architecture and added comments to help me better understand the run.py file as I read through it.

While I am not directly affiliated with this project, I believe these comments could be helpful for the community and future contributors who might also be exploring the code. All the code was left unchanged and only comments were added, such that the functionality of the program is the same.