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
How to set max_compositions #19
Comments
Great point. Ideally, we'd only call the privacy accounting function after we've done a gradient update, in which case we'd get strictly positive My code runs a prelim. eval. before any parameter update just to check the initial performance model of the model. This produces a warning you'd get, since the privacy accounting code is also ran. This doesn't really affect the correctness however. |
By the way, |
Thanks Chen for the explanation! I set the dataset size too small when debugging so |
Hi Chen, do you know how to set the max_compositions/steps param? The default at
private-transformers/private_transformers/privacy_utils/privacy_engine.py
Line 148 in 684e27f
is 0 but would raise an error
The text was updated successfully, but these errors were encountered: