Tune hyperparameters for macOS MPS efficiency#6
Open
yamyr wants to merge 24 commits into
Open
Conversation
yamyr
force-pushed
the
autoresearch/mar14
branch
from
5494278 to
66ac869
Compare
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode) Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
PaulRBerg
added a commit
to PaulRBerg/autoresearch-macos
that referenced
this pull request
Mar 20, 2026
Incorporates yamyr's 50-experiment sweep that reduces val_bpb from 1.644952 to 1.342794 (18.4% improvement). Key changes: halved batch size, increased LRs (embedding 0.6→1.2, matrix 0.04→0.06, unembedding 0.004→0.006), softcap 15→20, longer Muon momentum ramp, adjusted warmdown/final LR schedules, and black-style reformatting. Based-on: miolini#6 Co-authored-by: Wolodymyr <vie@ajentik.ai>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
run.logandresults.tsv