[Bug] TruthfulQA同时使用多个评估metric时报错

先决条件

• 我已经搜索过 问题 和 讨论 但未得到预期的帮助。
• 错误在 最新版本 中尚未被修复。

问题类型

我正在使用官方支持的任务/模型/数据集进行评估。

环境

{'CUDA available': True,
'CUDA_HOME': '/usr/local/cuda',
'GCC': 'gcc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0',
'GPU 0,1,2,3': 'NVIDIA A800 80GB PCIe',
'MMEngine': '0.10.4',
'MUSA available': False,
'NVCC': 'Cuda compilation tools, release 12.4, V12.4.131',
'OpenCV': '4.10.0',
'PyTorch': '2.2.1',
'PyTorch compiling details': 'PyTorch built with:\n'
' - GCC 9.3\n'
' - C++ Version: 201703\n'
' - Intel(R) oneAPI Math Kernel Library Version '
'2023.1-Product Build 20230303 for Intel(R) 64 '
'architecture applications\n'
' - Intel(R) MKL-DNN v3.3.2 (Git Hash '
'2dc95a2ad0841e29db8b22fbccaf3e5da7992b01)\n'
' - OpenMP 201511 (a.k.a. OpenMP 4.5)\n'
' - LAPACK is enabled (usually provided by '
'MKL)\n'
' - NNPACK is enabled\n'
' - CPU capability usage: AVX512\n'
' - CUDA Runtime 12.1\n'
' - NVCC architecture flags: '
'-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_90,code=sm_90\n'
' - CuDNN 8.9.2\n'
' - Magma 2.6.1\n'
' - Build settings: BLAS_INFO=mkl, '
'BUILD_TYPE=Release, CUDA_VERSION=12.1, '
'CUDNN_VERSION=8.9.2, '
'CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, '
'CXX_FLAGS= -D_GLIBCXX_USE_CXX11_ABI=0 '
'-fabi-version=11 -fvisibility-inlines-hidden '
'-DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO '
'-DLIBKINETO_NOROCTRACER -DUSE_FBGEMM '
'-DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK '
'-DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE '
'-O2 -fPIC -Wall -Wextra -Werror=return-type '
'-Werror=non-virtual-dtor -Werror=bool-operation '
'-Wnarrowing -Wno-missing-field-initializers '
'-Wno-type-limits -Wno-array-bounds '
'-Wno-unknown-pragmas -Wno-unused-parameter '
'-Wno-unused-function -Wno-unused-result '
'-Wno-strict-overflow -Wno-strict-aliasing '
'-Wno-stringop-overflow -Wsuggest-override '
'-Wno-psabi -Wno-error=pedantic '
'-Wno-error=old-style-cast -Wno-missing-braces '
'-fdiagnostics-color=always -faligned-new '
'-Wno-unused-but-set-variable '
'-Wno-maybe-uninitialized -fno-math-errno '
'-fno-trapping-math -Werror=format '
'-Wno-stringop-overflow, LAPACK_INFO=mkl, '
'PERF_WITH_AVX=1, PERF_WITH_AVX2=1, '
'PERF_WITH_AVX512=1, TORCH_VERSION=2.2.1, '
'USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, '
'USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, '
'USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, '
'USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, '
'USE_ROCM_KERNEL_ASSERT=OFF, \n',
'Python': '3.12.2 | packaged by conda-forge | (main, Feb 16 2024, 20:50:58) '
'[GCC 12.3.0]',
'TorchVision': '0.17.1',
'lmdeploy': "not installed:No module named 'lmdeploy'",
'numpy_random_seed': 2147483648,
'opencompass': '0.3.2.post1+',
'sys.platform': 'linux',
'transformers': '4.45.1'}

重现问题 - 代码/配置示例

修改opencompass/configs/datasets/truthfulqa/truthfulqa_gen_5ddc62.py的评估方法，同时使用多种metrics：

# `metrics=('bleurt', 'rouge', 'bleu')`
truthfulqa_eval_cfg = dict(
    evaluator=dict(
        type=TruthfulQAEvaluator, metrics=('bleurt', 'rouge', 'bleu', 'truth', 'info'), key='ENV'), )

truthfulqa_datasets = [
    dict(
        abbr='truthful_qa',
        type=TruthfulQADataset,
        path='truthful_qa',
        name='generation',
        reader_cfg=truthfulqa_reader_cfg,
        infer_cfg=truthfulqa_infer_cfg,
        eval_cfg=truthfulqa_eval_cfg)
]

重现问题 - 命令或脚本

python run.py \
    --datasets truthfulqa_gen\
    --hf-type chat \
    --hf-path /home/user1/llm_alignment_parm_attack/output/Hermes-2-Pro-Llama-3-8B/model \
    --tokenizer-path /nfs/base_models/NousResearch/Hermes-2-Pro-Llama-3-8B \
    --model-kwargs device_map='cuda:2' \
    --debug

重现问题 - 错误信息

报错信息：

all_metrics {'rouge', 'bleurt', 'truth', 'info', 'bleu'} metrics ('bleurt', 'rouge', 'bleu', 'truth', 'info') /nfs/base_models/allenai/truthfulqa-truth-judge-llama2-7B
Traceback (most recent call last):
  File "/home/user1/opencompass/run.py", line 4, in <module>
    main()
  File "/home/user1/opencompass/opencompass/cli/main.py", line 351, in main
    runner(tasks)
  File "/home/user1/opencompass/opencompass/runners/base.py", line 38, in __call__
    status = self.launch(tasks)
             ^^^^^^^^^^^^^^^^^^
  File "/home/user1/opencompass/opencompass/runners/local.py", line 136, in launch
    task.run()
  File "/home/user1/opencompass/opencompass/tasks/openicl_eval.py", line 114, in run
    self._score()
  File "/home/user1/opencompass/opencompass/tasks/openicl_eval.py", line 227, in _score
    icl_evaluator = ICL_EVALUATORS.build(self.eval_cfg['evaluator'])
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user1/miniconda3/lib/python3.12/site-packages/mmengine/registry/registry.py", line 570, in build
    return self.build_func(cfg, *args, **kwargs, registry=self)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user1/miniconda3/lib/python3.12/site-packages/mmengine/registry/build_functions.py", line 121, in build_from_cfg
    obj = obj_cls(**args)  # type: ignore
          ^^^^^^^^^^^^^^^
  File "/home/user1/opencompass/opencompass/datasets/truthfulqa.py", line 97, in __init__
    assert set(metrics).issubset(all_metrics)
AssertionError

报错位置：truthfulQA.py

其他信息

我认为原因在于truthfulqa.py文件中的TruthfulQAEvaluator类传入metrics为tuple时，又将这个tuple加了一层list，导致了assert报错。

事实上，初始参数metrics=('truth')传进去的是string而不是tuple

可能的修复方法：
删除96行再次加list的位置，同时修改默认传递的参数为tuple而不是string