alphaXiv
/

spurious-rewards-reasoning-traces

Model card Files Files and versions

spurious-rewards-reasoning-traces

27.6 MB

Ctrl+K

Ctrl+K

1 contributor

History: 21 commits

alphaXiv's picture

Upload step1000/export-for-eval-step1000_MATH-500.json with huggingface_hub

0570507 verified 3 months ago

base
Upload base/Qwen2.5-Math-1.5B_MATH-500.json with huggingface_hub 3 months ago
step1000
Upload step1000/export-for-eval-step1000_MATH-500.json with huggingface_hub 3 months ago
step200
Upload step200/export-for-eval-step200_MATH-500.json with huggingface_hub 3 months ago
step400
Upload step400/export-for-eval-step400_MATH-500.json with huggingface_hub 3 months ago
step50
Upload step50/export-for-eval-step50_MATH-500.json with huggingface_hub 3 months ago
.gitattributes

1.52 kB
initial commit 3 months ago