Mandelmus100

joined 1 year ago

[R] "It's not just memorizing the training data" they said: Scalable Extraction of Training Data from (Production) Language Models in c/machinelearning@academy.garden

[–] Mandelmus100@alien.top 1 points 11 months ago (7 children)

Another big takeaway is that training for more epochs leads to more memorization.

Should be expected. It's overfitting.