[RLlib] Always attach latest eval metrics. #21011
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
sven1977
changed the title
sven1977
reviewed
Dec 13, 2021
sven1977
approved these changes
Dec 13, 2021
| "evaluation_config": { | ||
| "gamma": 0.98, | ||
| }, | ||
| "always_attach_evaluation_results": True, |
|
Tests look pretty good now. Can you please help merge? @sven1977 |
it's definitely part of the problems. |
gjoliver
force-pushed
the
eval_metrics
branch
from
802d055
to
8f1e5a8
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Why are these changes needed?
Attach latest available eval metrics with every step result dict. So Tune doesn't get confused when most of the step results don't have eval metrics.
This allows us to bring back CQL tests.
Related issue number
Checks
scripts/format.shto lint the changes in this PR.