-
Notifications
You must be signed in to change notification settings - Fork 11
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
More ops fixes #664
More ops fixes #664
Conversation
MLCommons CLA bot All contributors have signed the MLCommons CLA ✍️ ✅ |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
👍
@@ -485,7 +552,9 @@ def _check_ready_to_run(self): | |||
|
|||
def run(self) -> BenchmarkRun: | |||
self._check_ready_to_run() |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Do you want to collect the RuntimeErrors from both annotators and suts here so that all issues can be addressed simultaneously? If I'm understanding correctly, right now, it won't check the annotators if there's an issue with the suts.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I was thinking to keep them separate, as right now our annotators can take up to 15 minutes to decide whether or not they're ready. This will get people quick notification of a SUT problem. But if we can get off HuggingFace to something faster, then that would make sense to me.
Add a little more journaling.
Make sure our external resources are live before starting a massive run.