curiousshortguy

joined 10 months ago
sorted by: new top controversial old
[R] Seeking input: transformer modification with 25-30% improvement in validation loss across 3 datasets in c/machinelearning@academy.garden
[–] curiousshortguy@alien.top 1 points 10 months ago

Why are we looking at train and validation LOSS instead of a meaningful metric here?