-
Notifications
You must be signed in to change notification settings - Fork 2.5k
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
Remove logic to skip checkpoint save if checkpoint exists #11362
base: main
Are you sure you want to change the base?
Conversation
Signed-off-by: ashors1 <ashors@nvidia.com>
beep boop 🤖: 🙏 The following files have warnings. In case you are familiar with these, please try helping us to improve the code base. Your code was analyzed with PyLint. The following annotations have been identified:
Thank you for improving NeMo's documentation! |
1 similar comment
beep boop 🤖: 🙏 The following files have warnings. In case you are familiar with these, please try helping us to improve the code base. Your code was analyzed with PyLint. The following annotations have been identified:
Thank you for improving NeMo's documentation! |
based on current test failure, looks like this requires changes in MCore as well to handle and existing dist ckpt dir. i'd say we should make that change first before merging this |
How can I check the failing tests? The only failing job I see is this one but it doesn't have any useful info: https://github.com/NVIDIA/NeMo/actions/runs/11958751953/job/33339441430?pr=11362 Regardless of the failure, I would recommend ensuring that on the NeMo side the checkpointing logic ensures that we don't save twice to the same directory, otherwise that could lead to silent errors. We did it for NeMo 1.0 and currently all such circumstances (saving twice to the same dir) are explicitly treated as an error which I believe leads to a better experiments handling from a user perspective |
from that link, go to the Summary, and see the 'Failed jobs'. This one is failing.
You're right, I completely agree. Currently on main, async save will crash if the dir exists. Non-async save will just print warning and skip saving. Looks like this change is exposing that problem in one of the tests. What I don't understand is why we aren't running the PTL logic that appends a version counter (1, 2) |
What does this PR do ?
Add a one line overview of what this PR aims to accomplish.
Collection: [Note which collection this PR will affect]
Changelog
Usage
# Add a code snippet demonstrating how to use this
GitHub Actions CI
The Jenkins CI system has been replaced by GitHub Actions self-hosted runners.
The GitHub Actions CI will run automatically when the "Run CICD" label is added to the PR.
To re-run CI remove and add the label again.
To run CI on an untrusted fork, a NeMo user with write access must first click "Approve and run".
Before your PR is "Ready for review"
Pre checks:
PR Type:
If you haven't finished some of the above items you can still open "Draft" PR.
Who can review?
Anyone in the community is free to review the PR once the checks have passed.
Contributor guidelines contains specific people who can review PRs to various areas.
Additional Information