fix: Pre-populate AppWorld rewards_dict with default reward/success value#9
Open
shady-cs15 wants to merge 1 commit intoApGa:mainfrom
Open
fix: Pre-populate AppWorld rewards_dict with default reward/success value#9shady-cs15 wants to merge 1 commit intoApGa:mainfrom
shady-cs15 wants to merge 1 commit intoApGa:mainfrom
Conversation
ApGa
changed the title
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Added a script for B200 configs for appworld
Fixes include
a. using flash infer instead of flash attention.
b. dropping static memory to 0.6, this gives 40 % of gpu memory to kv cache and other parts that require dynamic memory allocation.
c. rollout timeout increased to 2 hrs (some rollouts till failing)
d. step timeout increased to 30 mins
Makes a small fix where rewards_dict is pre-populated with a
reward/successwith default value of 0