Skip to content
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

Proper support for Remote Stop and Remote Abort with NeptuneLogger #19130

Merged

Conversation

Raalsky
Copy link
Contributor

@Raalsky Raalsky commented Dec 8, 2023

What does this PR do?

With Remote Stop and Remote Abort in Neptune UI you're able to stop currently running training this means:

  • Neptune will stop the current Run and wait to sync all the remaining operations to the server
  • Once it's synced it's going to send a signal to kill current process

As we're doing a stop operation before sending the signal to Lightning the Run may be in an inactivate state when reaching the logger finalization code raising a related exception. This PR prevents this behavior and allows to make graceful shutdown.

Fixes neptune-ai/neptune-client#1378

Before submitting
  • Was this discussed/agreed via a GitHub issue? (not for typos and docs)
  • Did you read the contributor guideline, Pull Request section?
  • Did you make sure your PR does only one thing, instead of bundling different changes together?
  • Did you make sure to update the documentation with your changes? (if necessary)
  • Did you write any new necessary tests? (not for typos and docs)
  • Did you verify new and existing tests pass locally with your changes?
  • Did you list all the breaking changes introduced by this pull request?
  • Did you update the CHANGELOG? (not for typos, docs, test updates, or minor internal changes/refactors)

PR review

Anyone in the community is welcome to review the PR.
Before you start reviewing, make sure you have read the review guidelines. In short, see the following bullet-list:

Reviewer checklist
  • Is this pull request ready for review? (if not, please submit in draft mode)
  • Check that all items from Before submitting are resolved
  • Make sure the title is self-explanatory and the description concisely explains the PR
  • Add labels and milestones (and optionally projects) to the PR so it can be classified

📚 Documentation preview 📚 : https://pytorch-lightning--19130.org.readthedocs.build/en/19130/

@github-actions github-actions bot added the pl Generic label for PyTorch Lightning package label Dec 8, 2023
@Raalsky Raalsky requested a review from Borda as a code owner December 9, 2023 06:54
Copy link

codecov bot commented Dec 9, 2023

Codecov Report

Merging #19130 (102a0e3) into master (a41528c) will decrease coverage by 34%.
The diff coverage is 100%.

Additional details and impacted files
@@            Coverage Diff             @@
##           master   #19130      +/-   ##
==========================================
- Coverage      82%      48%     -34%     
==========================================
  Files         450      442       -8     
  Lines       38253    38111     -142     
==========================================
- Hits        31454    18442   -13012     
- Misses       6799    19669   +12870     

@awaelchli awaelchli added bug Something isn't working logger: neptune labels Dec 15, 2023
@awaelchli awaelchli added this to the 2.1.x milestone Dec 15, 2023
@awaelchli awaelchli added the community This PR is from the community label Dec 15, 2023
@mergify mergify bot removed the has conflicts label Jan 10, 2024
@Borda
Copy link
Member

Borda commented Jan 10, 2024

let's update or rebase after #19265 lands 🎏

Copy link

gitguardian bot commented Jan 16, 2024

️✅ There are no secrets present in this pull request anymore.

If these secrets were true positive and are still valid, we highly recommend you to revoke them.
Once a secret has been leaked into a git repository, you should consider it compromised, even if it was deleted immediately.
Find here more information about risks.


🦉 GitGuardian detects secrets in your source code to help developers and security teams secure the modern development process. You are seeing this because you or someone else with access to this repository has authorized GitGuardian to scan your pull request.

Our GitHub checks need improvements? Share your feedbacks!

@mergify mergify bot removed the has conflicts label Feb 1, 2024
@awaelchli awaelchli modified the milestones: 2.1.x, 2.2.x Feb 8, 2024
@Raalsky Raalsky force-pushed the bugfix/neptune-logger-remote-stop branch from a818c67 to 28cf077 Compare February 21, 2024 11:49
@Raalsky Raalsky changed the title Proper support for Remote Stop and Remote Abort with NeptuneLogger Draft: Proper support for Remote Stop and Remote Abort with NeptuneLogger Feb 21, 2024
@Raalsky Raalsky changed the title Draft: Proper support for Remote Stop and Remote Abort with NeptuneLogger Proper support for Remote Stop and Remote Abort with NeptuneLogger Feb 21, 2024
@Raalsky
Copy link
Contributor Author

Raalsky commented Feb 21, 2024

@Borda Ready for review 😉

Copy link

@szysad szysad left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM!

tests/tests_pytorch/loggers/conftest.py Show resolved Hide resolved
src/lightning/pytorch/loggers/neptune.py Outdated Show resolved Hide resolved
src/lightning/pytorch/loggers/neptune.py Outdated Show resolved Hide resolved
tests/tests_pytorch/loggers/test_neptune.py Show resolved Hide resolved
@mergify mergify bot added the ready PRs ready to be merged label Feb 23, 2024
@awaelchli awaelchli merged commit f2f3ef5 into Lightning-AI:master Feb 23, 2024
88 checks passed
@Raalsky Raalsky deleted the bugfix/neptune-logger-remote-stop branch February 23, 2024 20:12
awaelchli added a commit that referenced this pull request Mar 1, 2024
…19130)

Co-authored-by: Rafał Jankowski <raalsky@gmail.com>
lantiga pushed a commit that referenced this pull request Mar 4, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working community This PR is from the community logger: neptune pl Generic label for PyTorch Lightning package ready PRs ready to be merged
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Feature Request: PyTorch Lighting graceful shutdown when Remote Stop
5 participants