move r1 configs into r1 yaml/r1 subfolder

eval/.gitignore

@@ -1,2 +1 @@
 results/*
-!results/summary*

eval/eval.py

@@ -1,3 +1,4 @@
+#!/usr/bin/env python
 import argparse
 import asyncio
 import json
@@ -112,7 +113,6 @@ class OpenRouterEvaluator:
 
     async def evaluate_datasets(self) -> list[dict[str, Any]]:
         """Main async evaluation entry point."""
-        all_results = []
         async with aiohttp.ClientSession(headers=self.headers) as session:
             return await asyncio.gather(*(self.evaluate_dataset(session, name) for name in self.config.datasets))
 

eval/yaml/r1/algebra.yaml

@@ -7,7 +7,7 @@ datasets:
   - simple_equations
   - simple_integration
   - complex_arithmetic
-eval_dir: eval/r1
+eval_dir: results/r1
 dataset_size: 50
 dataset_seed: 42
 developer_role: system

eval/yaml/r1/algorithmic.yaml

@@ -18,7 +18,7 @@ datasets:
   - word_ladder
   - word_sequence_reversal
   - word_sorting
-eval_dir: eval/r1
+eval_dir: results/r1
 dataset_size: 50
 dataset_seed: 42
 developer_role: system

eval/yaml/r1/cognition.yaml

@@ -5,7 +5,7 @@ datasets:
   -  figlet_font
   -  number_sequence
   -  rubiks_cube
-eval_dir: eval/r1
+eval_dir: results/r1
 dataset_size: 50
 dataset_seed: 42
 developer_role: system

eval/yaml/r1/logic.yaml

@@ -5,7 +5,7 @@ datasets:
   - self_reference
   - syllogism
   - zebra_puzzles
-eval_dir: eval/r1
+eval_dir: results/r1
 dataset_size: 50
 dataset_seed: 42
 developer_role: system

eval/yaml/r1/test.yaml

@@ -2,7 +2,7 @@ model: deepseek/deepseek-r1
 category: test
 datasets:
   - YOUR_DATASET_NAME
-eval_dir: eval/r1
+eval_dir: results/r1
 dataset_size: 10
 dataset_seed: 42
 developer_role: system