Commit graph

8 commits

Author SHA1 Message Date
Andreas Köpf
b2904ccab9 Minor question template & score_answer improvements (#261)
* math prompt improvements
* ignore brackets in complex_arithmetic results
* improve additional instruction in prompt of polynomial_equations
* more strict tests for score_answer in polynomial_equations
* simplify special reward handling
* fix test_intermediate_integration
* fix sokoban dataset
* add common dataset score_answer consistency test
2025-03-04 21:55:09 +01:00
Zafir Stojanovski
2f9d94c1e7 fix: Unify Prompts (#254)
* remove cot
* fix prompt template
* fix pool matrix
* spiral matrix fixed
2025-03-03 21:55:53 +01:00
Andreas Koepf
ff5b210106 use native types List->list, Dict->dict, Set->set, Tuple->tuple 2025-02-21 15:15:38 +01:00
Andreas Koepf
6fae41a6e1 ensure reward is float 2025-02-16 16:27:12 +01:00
Andreas Koepf
b90c50e68f remove redundant methods from GroupAnagramsDataset 2025-02-06 14:21:03 +01:00
Zafir Stojanovski
cce890e169 use get_data_file_path to read file contents 2025-02-06 10:12:51 +01:00
Zafir Stojanovski
dc6f6a4e7e docs 2025-02-06 00:12:58 +01:00
Zafir Stojanovski
7f611c2e0e group anagrams env 2025-02-06 00:11:07 +01:00