[moe] Add shared-expert ablation experiment at ~1e19 FLOPs#4051
Open
claude[bot] wants to merge 1 commit intomainfrom
Open
[moe] Add shared-expert ablation experiment at ~1e19 FLOPs#4051claude[bot] wants to merge 1 commit intomainfrom
claude[bot] wants to merge 1 commit intomainfrom
Conversation
Add experiments/grug/moe/exp4021_ablate_shared_expert.py with two arms (shared expert baseline vs no shared expert) each targeting ~1e19 total training FLOPs using the trial model config. Adds test validating FLOP budgets and config correctness. Fixes #4021
This was referenced Mar 23, 2026
Contributor
|
This pull request has been inactive for 23 days and is marked as stale. |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Two-arm experiment comparing shared expert (baseline) vs no shared expert at ~1e19 total training FLOPs using the grug MoE trial model config. Shared arm runs ~5407 steps, no-shared arm runs ~6091 steps (bs=512, seq=4096) to match the FLOP budget. Adds config validation test.
Fixes #4021