-
Notifications
You must be signed in to change notification settings - Fork 2.2k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
use a smaller LR? #4
Comments
I've observed similar — updating to 2e-5 as in the original paper. I'll check in the morning if it works better. |
Have you evaluated the model quality? I've always suspected that instruct-tuning is much less data-intensive than most people think. |
Could also be worth trying to disable the int8 quantization or increase the matrix rank. Will check tomorrow. |
Fwiw I've been able to eke out some small gains setting LORA_R to 8 instead of 4. Otherwise, seems (until proven otherwise) like both learning rates are perfectly fine. |
The Karparthy Constant used currently might be too high? The loss for this training run is not going down after LR increases beyond ~1e-4:
The text was updated successfully, but these errors were encountered: