Commit graph

1009 commits

Author SHA1 Message Date
Andreas Köpf
3f8380d93a
Merge pull request #99 from open-thought/curriculum_basics
Add foundation for auto-curriculum
2025-02-11 22:52:14 +01:00
Zafir Stojanovski
15bd9cb544 pool matrix 2025-02-11 22:22:39 +01:00
ironbound
2e2c5744df working board 2025-02-11 19:41:45 +01:00
Rich Jones
d44d076ae3 Add A::B Challenges 2025-02-11 18:08:25 +01:00
Rich Jones
0a4799d99a clarity 2025-02-11 16:22:53 +01:00
Andreas Köpf
858e5bba51
Merge pull request #108 from rishabhranawat/eval-v2
Eval V1: improve speed using async
2025-02-11 16:07:47 +01:00
Zafir Stojanovski
5a8ce7d2af lint 2025-02-11 14:44:46 +01:00
Zafir Stojanovski
1dc0a29eae count primes 2025-02-11 14:44:38 +01:00
Rich Jones
c2fb8bb6cc add rectangle count dataset 2025-02-11 13:56:27 +01:00
Zafir Stojanovski
e9a492e9a5 Merge branch 'main' of https://github.com/open-thought/reasoning-gym into fix/simplify-rotate-matrix 2025-02-11 13:55:05 +01:00
Zafir Stojanovski
21b845ebef simplify rotate method 2025-02-11 13:54:54 +01:00
Rich Jones
b208dc664e lint again 2025-02-11 13:00:12 +01:00
Rich Jones
f7cf015e3b commit test 2025-02-11 12:59:16 +01:00
Rich Jones
945207da43 fmt 2025-02-11 12:54:23 +01:00
Rich Jones
852ddfcea3 add dice dataset 2025-02-11 12:53:13 +01:00
Andreas Köpf
d56d2e25fb
Merge pull request #109 from joesharratt1229/feat/r1-evals
added r1 evaluation logic
2025-02-11 11:35:46 +01:00
Andreas Koepf
014ee03e35 fix typo 2025-02-11 11:03:55 +01:00
joesharratt1229
1a3728ec3a corrected small linting err in cognition.yaml 2025-02-11 06:56:04 +00:00
joesharratt1229
bf00437aae converted answer to string 2025-02-11 06:48:59 +00:00
rishabhranawat
d7b69190ba commit formatting 2025-02-10 22:05:45 -08:00
rishabhranawat
1dc7af587f [eval-v1] benchmark with 50 samples 2025-02-10 22:05:09 -08:00
rishabhranawat
fb40c8ca55 [eval-v1] add a simple readme with some details 2025-02-10 21:57:00 -08:00
rishabhranawat
9e4870125d [eval-v1] pre commit formatting 2025-02-10 21:50:22 -08:00
rishabhranawat
df5438498e [eval-v1] add timer 2025-02-10 21:48:44 -08:00
rishabhranawat
247464a47d [eval-v1] async to speed up inference/evaluation 2025-02-10 21:35:46 -08:00
joesharratt1229
42e02640a3 added r1 evaluation logic 2025-02-11 03:46:56 +00:00
tohskai
2a0baef313 Improve support for multivariate polynomials 2025-02-11 01:58:07 +01:00
Dragan Jovanović
719369bce6 fix for isort 2025-02-11 00:20:46 +01:00
Dragan Jovanović
60d0785a91 initial draft for circuit_logic dataset generator 2025-02-11 00:09:00 +01:00
Andreas Koepf
4abcd1f1df update gallery, lower default config values for PowerFunctionDataset 2025-02-10 22:42:04 +01:00
Andreas Köpf
51949fdee2
Merge pull request #100 from zafstojano/env/matrix-manipulation
Matrix Manipulation Dataset
2025-02-10 22:37:37 +01:00
Zafir Stojanovski
a0a5de3658 add more config params 2025-02-10 22:30:36 +01:00
Zafir Stojanovski
ed10111834
count bits (#101) 2025-02-10 22:12:50 +01:00
Andreas Koepf
074f46780d add chain_sum curriculum unit test 2025-02-10 22:09:18 +01:00
Zafir Stojanovski
a8c39ddcfb
Power Function (#102)
* power function dataset + tests
2025-02-10 22:04:58 +01:00
Zafir Stojanovski
ecdc85f2c2 Merge branch 'main' of https://github.com/open-thought/reasoning-gym into env/matrix-manipulation 2025-02-10 20:40:41 +01:00
Andreas Koepf
8772041afb Add attributes for curriculum
Co-authored-by: EduardDurech <39579228+EduardDurech@users.noreply.github.com>
2025-02-10 18:58:07 +01:00
Adefioye
bea9e6d96a
Add score_answer method to word_ladder (#93)
* Add score_answer method to word_ladder
* add unit test for WordLadderDataset::score_answer()

---------

Co-authored-by: Andreas Koepf <andreas.koepf@provisio.com>
2025-02-10 15:15:23 +01:00
Zafir Stojanovski
3d66cc6a7f matrix manipulation 2025-02-10 13:51:39 +01:00
Andreas Köpf
f6060f4d97
Merge pull request #97 from rishabhranawat/eval-v1
[eval-basic] initial scripts for evaluating models on reasoning gym
2025-02-10 11:59:49 +01:00
rishabhranawat
0657222a8f [eval-basic] remove large results files, add gitignore, only leave summary 2025-02-09 22:52:10 -08:00
rishabhranawat
c214724a46 [eval-basic] run precommit formatting 2025-02-09 22:40:45 -08:00
rishabhranawat
75cfd31ec2 [eval-basic] initial scripts for evaluating models on reasoning gym 2025-02-09 22:36:27 -08:00
Oliver
8daebcd1a8 Remove rng param 2025-02-09 21:26:03 +00:00
Oliver
dce5d9367d Greatly speed up solver 2025-02-09 21:23:53 +00:00
Andreas Koepf
8c4400b18a reduce default zero probability for binary matrix 2025-02-09 20:05:56 +01:00
Andreas Köpf
1472de02ea
Merge pull request #91 from zafstojano/env/binary-matrix
Binary Matrix
2025-02-09 19:55:36 +01:00
Andreas Köpf
7bd841d640
Merge pull request #92 from rishabhranawat/poly-reward
Add score_answer() for PolynomialEquationsDataset
2025-02-09 19:30:24 +01:00
rishabhranawat
40e5a7cffa [poly-reward] run pre-commit hooks 2025-02-09 07:30:18 -08:00
Zafir Stojanovski
18cf71a4a7 update instruction and shuffle numbers 2025-02-09 13:00:46 +01:00