Commit graph

9 commits

Author SHA1 Message Date
Andreas Köpf
3f6b2fc807
Add Coaching & ScoreBoard class (result tracking) (#72)
* 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
2025-02-06 23:15:28 +01:00
Andreas Koepf
a577f7cdf6 use sorted() for repeatable generation outputs (e.g. GALLERY.md) 2025-01-30 23:33:43 +01:00
Andreas Koepf
0dcff77b37 add reasoning_gym.create_dataset({name}, ...) global factory function 2025-01-25 00:58:34 +01:00
Andreas Koepf
e9549f2a63 pass config to ProceduralDataset base 2025-01-25 00:23:05 +01:00
Andreas Koepf
3dc80be7d2 formatting, cleanup 2025-01-24 17:12:42 +01:00
Andreas Koepf (aider)
8b49af5535 refactor: Inherit NumberFilteringDataset and LetterCountingDataset from ProceduralDataset 2025-01-24 11:13:32 +01:00
Andreas Koepf
20069b2a7d formatting 2025-01-24 10:34:07 +01:00
Andreas Koepf (aider)
102d4dae00 fix: Ensure letter counting dataset extracts only alphanumeric words 2025-01-23 19:17:45 +01:00
Andreas Koepf (aider)
dd6fc96891 feat: Add letter counting algorithmic task with configurable text span generation 2025-01-23 19:11:15 +01:00