Data Contamination
#2
by
devasheeshG
- opened
bro, are you sure there is not any data leak from the dataset's test set. Have you checked for contamination?
devasheeshG
changed discussion title from
Data Leak
to Data Contamination
Hello! Thank you for your comment.
I just applied mergekit method(slerp) for my Sakura-SOLAR-Instruct model.
(-> It means, I don't use any dataset about Sakura-SOLAR-Instruct!!)
So if my model is contaminated, the contamination is in the base models that I combined.
And also, you check all of information through Sakura-SOLAR-github.
Is it clear? Thanks!
kyujinpy
changed discussion status to
closed