open-compass / open-compass/opencompass

[Feature] Improve evaluation scripts for mbpp datasets

Open
#933 4 comments 2 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
7.5k
Forks
869
Avg merge
17h 52m
Merged PRs (30d)
13

Description

Describe the feature

When I evaluated the vicuna-7b-v1.5 model using the mbpp_gen script, the score was 0 and most answers showed failed. Perhaps the evaluate script did not properly format the answer.
微信截图_20240228213314
微信图片_20240228213255

Will you implement it?
  • I would like to implement this feature and create a PR!

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with the mbpp_gen evaluation entry point and reproduce the vicuna-7b-v1.5 run on the MBPP dataset. Inspect how generated answers are formatted and judged, then verify that valid answers no longer receive failed results and the score is no longer zero.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning, testing-qa
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.