[BFCL] Improve Warning Message when Aggregating Results #517
Conversation
This file contains 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
CharlieJCJ
reviewed
Jul 11, 2024
berkeley-function-call-leaderboard/eval_checker/eval_runner_helper.py
Outdated
Show resolved
Hide resolved
berkeley-function-call-leaderboard/eval_checker/eval_runner_helper.py
Outdated
Show resolved
Hide resolved
|
@CharlieJCJ can you review this and LGTM if ready? |
The current PR doesn't add the "actionable error message" yet, I think in general we should error message + actionable items across all functionalities, not just this place. I will review this version today for now (which |
…ing' into data-aggregate-warning
|
Testing with Example behaviors: Case 1: If everything is presented in (BFCL): /data/gorilla/berkeley-function-call-leaderboard/eval_checker]$ python eval_runner.py --model gorilla-openfunctions-v2 --test-category simple
🦍 Model: gorilla-openfunctions-v2
🔍 Running test: simple
✅ Test completed: simple. 🎯 Accuracy: 0.9475
📈 Aggregating data to generate leaderboard score table...
============================== Model Category Status ==============================
Model: gorilla-openfunctions-v2
All categories are present and evaluated.
🎉 All categories are present and evaluated for all models!
📈 Leaderboard statistics generated successfully! See /data/gorilla/berkeley-function-call-leaderboard/score/data.csv for evaluation results.
🏁 Evaluation completed. See /data/gorilla/berkeley-function-call-leaderboard/score/data.csv for evaluation results.Case 2: If I deleted (BFCL):/data/gorilla/berkeley-function-call-leaderboard/eval_checker]$ python eval_runner.py --model gorilla-openfunctions-v2 --test-category simple
🦍 Model: gorilla-openfunctions-v2
🔍 Running test: simple
✅ Test completed: simple. 🎯 Accuracy: 0.9475
📈 Aggregating data to generate leaderboard score table...
============================== Model Category Status ==============================
Model: gorilla-openfunctions-v2
Unevaluated results for 1 categories:
- java
======================================== Recommended Actions ========================================
To address these issues, run the following commands from the project root directory:
cd eval_checker && \
python eval_runner.py --model gorilla-openfunctions-v2 --test-category java
====================================================================================================
📈 Leaderboard statistics generated successfully! See /data/gorilla/berkeley-function-call-leaderboard/score/data.csv for evaluation results.
🏁 Evaluation completed. See /data/gorilla/berkeley-function-call-leaderboard/score/data.csv for evaluation results.Case 3: If I then deleted (BFCL):/data/gorilla/berkeley-function-call-leaderboard/eval_checker]$ python eval_runner.py --model gorilla-openfunctions-v2 --test-category simple
🦍 Model: gorilla-openfunctions-v2
🔍 Running test: simple
✅ Test completed: simple. 🎯 Accuracy: 0.9475
📈 Aggregating data to generate leaderboard score table...
============================== Model Category Status ==============================
Model: gorilla-openfunctions-v2
Missing results for 1 categories:
- rest
Unevaluated results for 1 categories:
- java
======================================== Recommended Actions ========================================
To address these issues, run the following commands from the project root directory:
cd .. && \
python openfunctions_evaluation.py --model gorilla-openfunctions-v2 --test-category rest && \
cd eval_checker && \
python eval_runner.py --model gorilla-openfunctions-v2 --test-category rest && \
python eval_runner.py --model gorilla-openfunctions-v2 --test-category java
====================================================================================================
📈 Leaderboard statistics generated successfully! See /data/gorilla/berkeley-function-call-leaderboard/score/data.csv for evaluation results.
🏁 Evaluation completed. See /data/gorilla/berkeley-function-call-leaderboard/score/data.csv for evaluation results. |
…e user asks for, and also give generation and evaluation multiple test categories in one line instead of multi-lines.
…ing' into data-aggregate-warning
ShishirPatil
approved these changes
Aug 10, 2024
aw632
pushed a commit
to vinaybagade/gorilla
that referenced
this pull request
Aug 22, 2024
…#517) As mentioned in ShishirPatil#506, this PR make the warning messages more informative for user to know action items when aggregating leaderboard results. --------- Co-authored-by: CharlieJCJ <charliechengjieji@berkeley.edu>
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.
As mentioned in #506, this PR make the warning messages more informative for user to know action items when aggregating leaderboard results.