You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi! I really like the your work and I tried that on my RTX 3060 12G, but it kept going NaN so I added lr scheduler and refactor the whole codebase. Here is the link https://github.com/author31/scm_nbdev. Once again, thanks for your work, keep doing.
The text was updated successfully, but these errors were encountered:
In my cases, the NaN problem is because learning rates to large even is 3e-6. So, I added the lr scheduler to do the warmcos scheduling style which like this
Hi! I really like the your work and I tried that on my RTX 3060 12G, but it kept going NaN so I added lr scheduler and refactor the whole codebase. Here is the link https://github.com/author31/scm_nbdev. Once again, thanks for your work, keep doing.
The text was updated successfully, but these errors were encountered: