Skip to content
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

Creating the experiment folder and adding initial analysis of Devin's evaluation outputs #50

Merged
merged 7 commits into from
Mar 20, 2024

Conversation

Jiaxin-Pei
Copy link
Contributor

No description provided.

@yufansong
Copy link
Collaborator

Should we always include experiments/SWE-bench/data/devin_output_diffs.csv in our commit? Not sure whether we should record the test result details every time.
I worry if we do it, the repo size will increase quickly.

@Jiaxin-Pei
Copy link
Contributor Author

Jiaxin-Pei commented Mar 20, 2024

Should we always include experiments/SWE-bench/data/devin_output_diffs.csv in our commit? Not sure whether we should record the test result details every time. I worry if we do it, the repo size will increase quickly.

@yufansong That makes sense, I just removed this file. I think in general we could allow some important and relatively small files. For other data files, I agree it would be better to keep them somewhere else and have people pull the data locally.

@yufansong
Copy link
Collaborator

I think in general we could allow some important and relatively small files.

Agree.

For other data files, I agree it would be better to keep them somewhere else and have people pull the data locally.

If we have many large experiements file, public google drive maybe a good choice. Welcome any other ideas.

@libowen2121
Copy link
Contributor

LGTM. I just updated the folder naming and logistics.

@huybery huybery self-requested a review March 20, 2024 11:58
@libowen2121 libowen2121 merged commit 60e043e into All-Hands-AI:main Mar 20, 2024
@huybery huybery requested review from libowen2121 and removed request for huybery March 20, 2024 12:04
xcodebuild pushed a commit to xcodebuild/OpenDevin that referenced this pull request Mar 31, 2024
… evaluation outputs (All-Hands-AI#50)

* Creating the folder for experiments, adding initial analysis of Devin's outputs on SWE-bench

* typo fixed

* update devin's evaluation outputs analysis

* remove data files from commit

* add logistics for managing the experiment folder in README

* Change folder naming and update logistics.

---------

Co-authored-by: Bowen Li <libowen.ne@gmail.com>
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