Hey! 
I’ve also completed part 1 and used a pre-trained (Brazilian) Portuguese transformer model to perform text classification in a (European Portuguese) dataset with 22 classes. The results were not bad but I intend to improve them. I started doing the course when working in a project for a company, so I was learning and applying it straight away! Also, I would like to train a European Portuguese model, since I did not find any (just Brazilian Portuguese) – but that’s for another episode 
Thanks a lot!!