Minification is not obfuscation and obfuscation is not security, but no amount of deobfuscation will recover the comments in the source, which are often more insightful than the source itself.
Often like 1 in 100 js files?
If the comments were in the original source that the model trained on... Then sure, those are recoverable too.
Obfuscation is meant to slow someone by making it difficult to understand. Slowing an attacker down is often employed as a form of security, that is why castles had walls, moats and multiple layers once you got inside to hinder progress.
It has been often used by companies, malware authors etc. to make it difficult for someone else to understand what is internally happening.