Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
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
[tune] Add timeout to retry_fn to catch hanging syncs #28155
[tune] Add timeout to retry_fn to catch hanging syncs #28155
Changes from 1 commit
c3901c7
8d54214
3a3e22a
9f62b79
042771b
13c6cb3
0affba2
3067e5e
8553d11
46d3b87
cef1b8e
ef5e35b
873d3eb
File filter
Filter by extension
Conversations
Jump to
There are no files selected for viewing
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.
now that you have a thread, imagine eventually we checkpoint on the side while the training just keeps going 🤯 😄
one nit, I also think timeout should be per-retry? (so
timeout=num_retries * timeout
here). otherwise the actual timeout will be dependent on how many retries you set here? although, admittedly, num_retries is not even a configurable bit.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.
Yeah I thought about this, but the reason why I kept a global timeout was because it is a) simpler/cleaner to implement and b) we basically want to define a maximum time we want to block training, so I think we should be fine with this. Let me know if you prefer this per-retry
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.
Ah actually as discussed, let's have a timeout per retry. Otherwise if the first sync hangs we will not try again. Updated the PR