How to compute the merging coefficient 't'?

[gauss5930]

Thank you for your great research! I am opening this issue to satisfy my curiosity about the research.

What is the method for computing merging coefficient 't'? I could not fully understand how to compute it just by reading the explanation described in the paper. I tried to find out the implementation code for this but could not find it all, so I'm asking a question! Is there any full implementation code that makes me fully understand?

When tuning this hyperparameter, for each task, we select the validation set from French and then extend it to encompass all other languages, for those tasks that do not contain French validation set, we adopt Vietnamese instead.