mirror of
https://github.com/open-thought/reasoning-gym.git
synced 2026-04-22 16:49:06 +00:00
Add eval configs, small fixes to eval script & rush-hour score_answer
This commit is contained in:
parent
fa950d0189
commit
677a2af03e
6 changed files with 283 additions and 22 deletions
|
|
@ -2,7 +2,7 @@ model: anthropic/claude-3.7-sonnet:thinking
|
|||
provider: Anthropic
|
||||
output_dir: results
|
||||
max_concurrent: 10
|
||||
default_size: 50
|
||||
default_size: 5
|
||||
default_seed: 45
|
||||
categories:
|
||||
- category: algebra
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue