CI: change SGLang plugin M3 nightly accuracy threshold#1529
Open
Phi-C wants to merge 3 commits into
Open
Conversation
Signed-off-by: Phi-C <chenxjhit@163.com>
Collaborator
|
please refer atom's m3 acc test command and threshold, instead of lowering ours.. |
Signed-off-by: Phi-C <chenxjhit@163.com>
Signed-off-by: Phi-C <chenxjhit@163.com>
Contributor
Author
Okay, the test command is aligned with atom's m3 acc test now. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Motivation
For nightly gsm8k accuracy validation, its configuration is
lm_eval \ --model local-completions \ --model_args "model=amd/MiniMax-M3-MXFP4,base_url=http://127.0.0.1:8000/v1/completions,num_concurrent=65,max_retries=1,tokenized_requests=False,trust_remote_code=True" \ --tasks gsm8k \ --num_fewshot 5which is different from configurations in recipe
BS=65 lm_eval \ --model local-chat-completions \ --model_args "model=${model_path},base_url=http://127.0.0.1:${PORT}/v1/chat/completions,num_concurrent=32,max_gen_toks=16384" \ --tasks gsm8k \ --num_fewshot 5 \ --batch_size "${BS}" \ --apply_chat_template \ --fewshot_as_multiturn 2>&1 | tee minimax-m3-mxfp4-sglang-gsm8k.logSo, the accuracy threshold is changed to
0.88.Technical Details
Test Plan
Test Result
Submission Checklist