Training details for Finetuning
Scipio1996 opened this issue · 2 comments
Scipio1996 commented
Dear authors:
This is great work, which makes me learn much.
However, I find some differences between the paper and the source code.
Specifically, in your paper, you said the initial rate is 1e-2, while in the code, the learning rate is 1e-3.
Which is right.
Thank you in advance
funnyzhou commented
Hi,
This might be a typo in the manuscript. You should use 1e-3 as suggested by the codebase.
liaochuanlin commented
@Scipio1996 Excuse me, have you reproduced the data set of the brain?