open-thought/reasoning-gym
1
0
Fork 0
mirror of https://github.com/open-thought/reasoning-gym.git synced 2026-04-19 12:58:07 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Add Coaching & ScoreBoard class (result tracking) (#72)

Browse source 
* feat: Add Coach and ScoreBoard classes for performance tracking and difficulty adjustment
* feat: Add GroupedScores class to wrap aggregated scores
* refactor: Create ScoreStats class with tuple-based score statistics
* feat: Add unit test for Coach with CompositeDataset and multiple datasets
* fix: Add difficulty metadata to leg counting dataset
* feat: Add clear() method to ScoreBoard to reset all stored data
* feat: Add __len__ method to ScoreBoard to return number of scores
* feat: Add update_dataset_config method to CompositeDataset
* cleanup __init__ & imports
This commit is contained in:
Andreas Köpf 2025-02-06 23:15:28 +01:00 • committed by GitHub
parent 7c08c05b1e
commit 3f6b2fc807
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
18 changed files with 549 additions and 39 deletions
Download patch file Download diff file Expand all files Collapse all files

8
reasoning_gym/arithmetic/leg_counting.py
View file

@ -111,7 +111,13 @@ class LegCountingDataset(ProceduralDataset):
return {
"question": question,
"answer": str(total_legs),
"metadata": {"animals": animals, "total_legs": total_legs},
"metadata": {
"difficulty": {
"num_animals": len(animals),
},
"animals": animals,
"total_legs": total_legs,
},
}