curiousshortguy

joined 1 year 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 1 year ago

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