open-thought/reasoning-gym
1
0
Fork 0
mirror of https://github.com/open-thought/reasoning-gym.git synced 2026-04-22 16:49:06 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Add eval configs, small fixes to eval script & rush-hour score_answer

Browse source
This commit is contained in:
Andreas Köpf 2025-03-16 09:18:05 +01:00 • committed by GitHub
parent fa950d0189
commit 677a2af03e
6 changed files with 283 additions and 22 deletions
Download patch file Download diff file Expand all files Collapse all files

13
eval/eval.py
View file

@ -399,17 +399,16 @@ class AsyncModelEvaluator:
Dict with processing results
"""
responses = None
completion_results = []
best_score = 0.0
total_score = 0.0
best_answer = None
best_response = None
try:
# Get multiple model responses
responses = await self.get_model_response(entry["question"])
# Process each response
completion_results = []
best_score = 0.0
total_score = 0.0
best_answer = None
best_response = None
# Count total completions for mean score calculation
total_completions = len(responses)