Skip to content

[Feature] Support Dataset Repeat and G-Pass Compute for Each Evaluator #1886

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 25 commits into from
Feb 26, 2025

Conversation

jnanliu
Copy link
Collaborator

@jnanliu jnanliu commented Feb 23, 2025

Motivation

  • To support dataset repeat for multi-run
  • To support general g-pass computation for each evaluator

Modification

  • BaseDataset: modify __init__ to implement dataset repeat after load method
  • BaseEvaluator: add evaluate method to compute average and g-pass (only accuracy-like evaluators)
image image

Checklist

Before PR:

  • Pre-commit or other linting tools are used to fix the potential lint issues.
  • Bug fixes are fully covered by unit tests, the case that causes the bug should be added in the unit tests.
  • The modification is covered by complete unit tests. If not, please add more unit test to ensure the correctness.
  • The documentation has been modified accordingly, like docstring or example tutorials.

After PR:

  • If the modification has potential influence on downstream or other related projects, this PR should be tested with those projects.
  • CLA has been signed and all committers have signed the CLA in this PR.

@jnanliu jnanliu changed the title [Feature ] Support Dataset Repeat and G-Pass Compute for Each Evaluator [Feature] Support Dataset Repeat and G-Pass Compute for Each Evaluator Feb 24, 2025
k=[4, 8, 16],
replication=3,
thresholds=[0.0, 0.25, 0.5, 0.75, 1.0]
url=[]
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

What's the url for?

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

for defining jude model urls

Copy link
Collaborator

@MaiziXiao MaiziXiao left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@MaiziXiao MaiziXiao merged commit 73c8095 into open-compass:main Feb 26, 2025
8 checks passed
stephen-nju pushed a commit to stephen-nju/opencompass that referenced this pull request May 14, 2025
open-compass#1886)

* support dataset repeat and g-pass compute for each evaluator

* fix pre-commit errors

* delete print

* delete gpassk_evaluator and fix potential errors

* change `repeat` to `n`

* fix `repeat` to `n` in openicl_eval

* update doc for multi-run and g-pass

* update latex equation in doc

* update eng doc for multi-run and g-pass

* update datasets.md

* update datasets.md

* fix multi-line equation

* fix multi-line equation

* fix multi-line equation

* fix multi-line equation

* fix multi-line equation

* fix multi-line equation

* fix multi-line equation in zh_cn user_guides

* mmodify pre-commit-zh-cn

* recover pre-commit and edit math expr in doc

* del [TIP]

* del cite tag in doc

* del extract_model param in livemathbench config
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants