0.8.1版本下遇见的humaneval数据集测评问题

[WjMessi1]

问题描述 / Issue Description

用代码：

进行原生evalscope测评时，遇见了报错，如下：

发现是我没有按照步骤下载包，下载好之后再次运行，有报错如下：

最终该问题已经解决，发现是execution.py代码的第59行没有正确缩进

使用的工具 / Tools Used

• [√] Native / 原生框架
• Opencompass backend
• VLMEvalKit backend
• RAGEval backend
• Perf / 模型推理压测工具
• Arena /竞技场模式

执行的代码或指令 / Code or Commands Executed

evalscope eval --model /data/Qwen/Qwen2.5-32B-Instruct-AWQ --datasets humaneval --limit 5

错误日志 / Error Log

Traceback (most recent call last):
  File "/root/anaconda3/envs/telechat2/bin/evalscope", line 8, in <module>
    sys.exit(run_cmd())
  File "/root/anaconda3/envs/telechat2/lib/python3.9/site-packages/evalscope/cli/cli.py", line 23, in run_cmd
    cmd.execute()
  File "/root/anaconda3/envs/telechat2/lib/python3.9/site-packages/evalscope/cli/start_eval.py", line 31, in execute
    run_task(self.args)
  File "/root/anaconda3/envs/telechat2/lib/python3.9/site-packages/evalscope/run.py", line 36, in run_task
    return run_single_task(task_cfg, run_time)
  File "/root/anaconda3/envs/telechat2/lib/python3.9/site-packages/evalscope/run.py", line 51, in run_single_task
    return evaluate_model(task_cfg, outputs)
  File "/root/anaconda3/envs/telechat2/lib/python3.9/site-packages/evalscope/run.py", line 107, in evaluate_model
    evaluator = create_evaluator(task_cfg, dataset_name, outputs)
  File "/root/anaconda3/envs/telechat2/lib/python3.9/site-packages/evalscope/run.py", line 125, in create_evaluator
    data_adapter = imported_modules['DataAdapterClass'](
  File "/root/anaconda3/envs/telechat2/lib/python3.9/site-packages/evalscope/benchmarks/humaneval/humaneval_adapter.py", line 38, in __init__
    from human_eval.evaluation import check_correctness
  File "/data/Telechat/EVAL/eval/humaneval/human-eval/human_eval/evaluation.py", line 10, in <module>
    from human_eval.execution import check_correctness
  File "/data/Telechat/EVAL/eval/humaneval/human-eval/human_eval/execution.py", line 59
    result.append("passed")
IndentationError: expected an indented block

运行环境 / Runtime Environment

• 操作系统 / Operating System:

  • Windows
  • macOS
  • [√] Ubuntu

• Python版本 / Python Version:

  • 3.11
  • 3.10
  • [√] 3.9

其他信息 / Additional Information

evalscope版本0.8.1

[Yunnglin]

感谢你的反馈！我们将关闭此问题。如果您有任何疑问，请随时重新打开它。如果EvalScope对您有所帮助，欢迎给我们点个STAR以示支持，谢谢！