[Fix] Fix generic_llm_evaluator output_path (#1798)

* Fix output_path

* Add Logger

opencompass/evaluator/generic_llm_evaluator.py

@@ -1,5 +1,4 @@
 import os.path as osp
-import re
 from typing import Dict, List, Optional
 
 import mmengine
@@ -13,16 +12,6 @@ from opencompass.utils import build_dataset_from_cfg, build_model_from_cfg
 from opencompass.utils.logging import get_logger
 
 
-def count_chinese_characters(text):
-    words = re.findall(r'[\u4e00-\u9fff]', text)
-    return len(words)
-
-
-def count_english_words(text):
-    words = re.findall(r'\b[a-zA-Z]+\b', text)
-    return len(words)
-
-
 class GenericLLMEvaluator(BaseEvaluator):
     """Generic LLM evaluator.
 
@@ -47,6 +36,7 @@ class GenericLLMEvaluator(BaseEvaluator):
 
         self.logger = get_logger()
         self.judge_cfg = judge_cfg
+        self.output_path = ''
 
         self.prompt_template = ICL_PROMPT_TEMPLATES.build(prompt_template)
 
@@ -64,6 +54,10 @@ class GenericLLMEvaluator(BaseEvaluator):
         out_dir, out_name = osp.split(output_path)
         out_name = f'{out_name}.json'
 
+        self.logger.info(
+            f'Set self.output_path to {self.output_path} for current task')
+        assert self.output_path is not None, 'output_path is None'
+
         # Build LLM Inference
         max_out_len = self.judge_cfg.get('max_out_len', None)
         batch_size = self.judge_cfg.get('batch_size', None)

opencompass/tasks/subjective_eval.py

@@ -39,7 +39,6 @@ class SubjectiveEvalTask(BaseTask):
         judge_cfg = cfg.get('judge_model', None)
         meta_judge_cfg = cfg.get('meta_judge_model', None)
         judge_models = cfg.get('judge_models', None)
-        keep_judger_postfix = cfg.get('keep_judger_postfix', True)
 
         if judge_cfg is None and meta_judge_cfg is None:
             assert judge_cfg is not None, 'Both judge_cfg and meta_judge_cfg are None, but judge_models must be provided.'
@@ -57,7 +56,6 @@ class SubjectiveEvalTask(BaseTask):
         self.judge_models = judge_models
         self.infer_order = cfg.get('infer_order')
         self.given_pred = cfg['datasets'][0][0].get('given_pred', [])
-        self.keep_judger_postfix = keep_judger_postfix
 
     def get_command(self, cfg_path, template):
         """Get the command template for the task.
@@ -101,11 +99,8 @@ class SubjectiveEvalTask(BaseTask):
             'models': self.model_cfgs,
             'datasets': self.dataset_cfgs
         })
-        if self.keep_judger_postfix:
         return self.name_prefix + task_name + \
                 '--judge-by--' + model_abbr_from_cfg(self.judge_cfg)
-        else:
-            return self.name_prefix + task_name
 
     def _load_model_pred(
         self,