use results folder name for eval results

eval/README.md

@@ -42,7 +42,7 @@ category: category-name
 datasets:
   - dataset1
   - dataset2
-eval_dir: eval/r1
+eval_dir: results/model-name
 dataset_size: 50
 dataset_seed: 42
 developer_role: system
@@ -81,7 +81,7 @@ datasets:
   -  word_ladder
   -  word_sequence_reversal
   -  word_sorting
-eval_dir: eval/r1
+eval_dir: results/deepseek-r1
 dataset_size: 50
 dataset_seed: 45
 developer_role: system
@@ -117,7 +117,7 @@ datasets:
   -  word_ladder
   -  word_sequence_reversal
   -  word_sorting
-eval_dir: eval/r1
+eval_dir: results/claude-3.5-sonnet
 dataset_size: 50
 dataset_seed: 45
 developer_role: system

eval/yaml/example.yaml

@@ -0,0 +1,8 @@
+model: anthropic/claude-3.7-sonnet  # find model id: https://openrouter.ai/models
+category: test
+datasets:
+  - YOUR_DATASET_NAME
+eval_dir: results/test
+dataset_size: 100
+dataset_seed: 42
+developer_role: system

eval/yaml/r1/algorithmic.yaml

@@ -28,7 +28,7 @@ datasets:
   -  word_ladder
   -  word_sequence_reversal
   -  word_sorting
-eval_dir: eval/r1
+eval_dir: results/r1
 dataset_size: 50
 dataset_seed: 45
 developer_role: system

eval/yaml/r1/test.yaml

@@ -1,8 +0,0 @@
-model: deepseek/deepseek-r1
-category: test
-datasets:
-  - YOUR_DATASET_NAME
-eval_dir: results/r1
-dataset_size: 10
-dataset_seed: 42
-developer_role: system