fix

opencompass/configs/datasets/math/math_prm800k_500_0shot_cot_gen.py

@@ -1,15 +1,14 @@
 from opencompass.openicl.icl_prompt_template import PromptTemplate
 from opencompass.openicl.icl_retriever import ZeroRetriever
 from opencompass.openicl.icl_inferencer import GenInferencer
-from opencompass.openicl.icl_evaluator import MATHEvaluator
 from opencompass.datasets import (
     MATHDataset,
+    MATHEvaluator,
     math_postprocess_v2,
     normalize_final_answer,
 )
 
 math_reader_cfg = dict(input_columns=['problem'], output_column='solution')
-
 math_infer_cfg = dict(
     prompt_template=dict(
         type=PromptTemplate,
@@ -28,7 +27,8 @@ math_infer_cfg = dict(
 
 # postprocess v2
 math_eval_cfg = dict(
-    evaluator=dict(type=MATHEvaluator)
+    evaluator=dict(type=MATHEvaluator, version='v2'),
+    pred_postprocessor=dict(type=math_postprocess_v2),
 )
 
 math_datasets = [
@@ -41,4 +41,4 @@ math_datasets = [
         infer_cfg=math_infer_cfg,
         eval_cfg=math_eval_cfg,
     )
-]
+]

opencompass/configs/datasets/math/math_prm800k_500_0shot_cot_gen_11c4b5.py

@@ -0,0 +1,44 @@
+from opencompass.openicl.icl_prompt_template import PromptTemplate
+from opencompass.openicl.icl_retriever import ZeroRetriever
+from opencompass.openicl.icl_inferencer import GenInferencer
+from opencompass.openicl.icl_evaluator import MATHEvaluator
+from opencompass.datasets import (
+    MATHDataset,
+    math_postprocess_v2,
+    normalize_final_answer,
+)
+
+math_reader_cfg = dict(input_columns=['problem'], output_column='solution')
+
+math_infer_cfg = dict(
+    prompt_template=dict(
+        type=PromptTemplate,
+        template=dict(
+            round=[
+                dict(
+                    role='HUMAN',
+                    prompt='{problem}\nPlease reason step by step, and put your final answer within \\boxed{}.',
+                ),
+            ]
+        ),
+    ),
+    retriever=dict(type=ZeroRetriever),
+    inferencer=dict(type=GenInferencer),
+)
+
+# postprocess v2
+math_eval_cfg = dict(
+    evaluator=dict(type=MATHEvaluator)
+)
+
+math_datasets = [
+    dict(
+        type=MATHDataset,
+        abbr='math_prm800k_500',
+        path='opencompass/math',
+        file_name='test_prm800k_500.json',
+        reader_cfg=math_reader_cfg,
+        infer_cfg=math_infer_cfg,
+        eval_cfg=math_eval_cfg,
+    )
+]

opencompass/configs/datasets/math/math_prm800k_500_gen.py

@@ -1,4 +1,4 @@
 from mmengine.config import read_base
 
 with read_base():
-    from .math_prm800k_500_0shot_cot_gen import math_datasets  # noqa: F401, F403
+    from .math_prm800k_500_0shot_cot_gen_11c4b5 import math_datasets  # noqa: F401, F403