[Bug] math_500_gen评测报错

[AllenShow]

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 0,1,2,3,4,5,6,7': 'NVIDIA A40',
'MMEngine': '0.10.4',
'MUSA available': False,
'NVCC': 'Cuda compilation tools, release 12.1, V12.1.66',
'OpenCV': '4.10.0',
'PyTorch': '2.5.1+cu124',
'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 v3.5.3 (Git Hash '
'66f0cb9eb66affd2da3bf5f8d897376f04aae6af)\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 12.4\n'
' - NVCC architecture flags: '
'-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-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 90.1\n'
' - Magma 2.6.1\n'
' - Build settings: BLAS_INFO=mkl, '
'BUILD_TYPE=Release, CUDA_VERSION=12.4, '
'CUDNN_VERSION=9.1.0, '
'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 -DLIBKINETO_NOXPUPTI=ON '
'-DUSE_FBGEMM -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-strict-overflow -Wno-strict-aliasing '
'-Wno-stringop-overflow -Wsuggest-override '
'-Wno-psabi -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, '
'TORCH_VERSION=2.5.1, USE_CUDA=ON, USE_CUDNN=ON, '
'USE_CUSPARSELT=1, USE_EXCEPTION_PTR=1, '
'USE_GFLAGS=OFF, USE_GLOG=OFF, USE_GLOO=ON, '
'USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, '
'USE_NCCL=1, USE_NNPACK=ON, USE_OPENMP=ON, '
'USE_ROCM=OFF, USE_ROCM_KERNEL_ASSERT=OFF, \n',
'Python': '3.10.14 (main, May 6 2024, 19:42:50) [GCC 11.2.0]',
'TorchVision': '0.20.1+cu124',
'lmdeploy': '0.7.1',
'numpy_random_seed': 2147483648,
'opencompass': '0.4.1+2176224',
'sys.platform': 'linux',
'transformers': '4.49.0'}

重现问题 - 代码/配置示例

python3 /nas/xz/opencompass/run.py --hf-path /nas/xz/model_para/Qwen2.5-7B --hf-type base --datasets math_500_gen --hf-num-gpus 8

重现问题 - 命令或脚本

cat tmp/3402174_debug.log

03/10 20:23:21 - OpenCompass - INFO - Task [Qwen2.5-7B_hf/math-500]
INFO 03-10 20:23:24 [init.py:256] Automatically detected platform cuda.
Sliding Window Attention is enabled but not implemented for sdpa; unexpected results may be encountered.
Loading checkpoint shards: 100%|██████████| 4/4 [00:04<00:00, 1.13s/it]
03/10 20:23:32 - OpenCompass - INFO - Try to load the data from /root/.cache/opencompass/./data/math/
03/10 20:23:32 - OpenCompass - INFO - Start inferencing [Qwen2.5-7B_hf/math-500]
[2025-03-10 20:23:32,679] [opencompass.openicl.icl_inferencer.icl_gen_inferencer] [INFO] Starting build dataloader
[2025-03-10 20:23:32,679] [opencompass.openicl.icl_inferencer.icl_gen_inferencer] [INFO] Starting inference process...
100%|██████████| 63/63 [21:09<00:00, 20.15s/it]
03/10 20:44:42 - OpenCompass - INFO - time elapsed: 1280.62s

重现问题 - 错误信息

INFO 03-10 20:23:14 [init.py:256] Automatically detected platform cuda.
03/10 20:23:16 - OpenCompass - INFO - Loading math_500_gen: /nas/xz/opencompass/opencompass/configs/./datasets/math/math_500_gen.py
03/10 20:23:16 - OpenCompass - INFO - Loading example: /nas/xz/opencompass/opencompass/configs/./summarizers/example.py
03/10 20:23:16 - OpenCompass - INFO - Current exp folder: outputs/default/20250310_202316
03/10 20:23:16 - OpenCompass - WARNING - SlurmRunner is not used, so the partition argument is ignored.
03/10 20:23:16 - OpenCompass - INFO - Partitioned into 1 tasks.
03/10 20:23:18 - OpenCompass - WARNING - Debug mode, log will be saved to tmp/3402174_debug.log
03/10 20:44:45 - OpenCompass - INFO - Partitioned into 1 tasks.
03/10 20:44:46 - OpenCompass - INFO - Try to load the data from /root/.cache/opencompass/./data/math/
Traceback (most recent call last):
File "/nas/xz/opencompass/run.py", line 4, in
main()
File "/nas/xz/opencompass/opencompass/cli/main.py", line 380, in main
runner(tasks)
File "/nas/xz/opencompass/opencompass/runners/base.py", line 38, in call
status = self.launch(tasks)
File "/nas/xz/opencompass/opencompass/runners/local.py", line 136, in launch
task.run()
File "/nas/xz/opencompass/opencompass/tasks/openicl_eval.py", line 86, in run
self._score()
File "/nas/xz/opencompass/opencompass/tasks/openicl_eval.py", line 218, in _score
icl_evaluator = ICL_EVALUATORS.build(self.eval_cfg['evaluator'])
File "/data/xz/anaconda3/envs/oc/lib/python3.10/site-packages/mmengine/registry/registry.py", line 570, in build
return self.build_func(cfg, *args, **kwargs, registry=self)
File "/data/xz/anaconda3/envs/oc/lib/python3.10/site-packages/mmengine/registry/build_functions.py", line 100, in build_from_cfg
raise KeyError(
KeyError: 'opencompass.openicl.icl_evaluator.math_evaluator.MATHEvaluator is not in the opencompass::icl_evaluators registry. Please check whether the value of opencompass.openicl.icl_evaluator.math_evaluator.MATHEvaluator is correct or it was registered as expected. More details can be found at https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#import-the-custom-module'

其他信息

No response

[ningmenghongcha]

遇到了相同的报错，
KeyError: 'opencompass.openicl.icl_evaluator.math_evaluator.MATHEvaluator is not in the opencompass::icl_evaluators registry. Please check whether the value of opencompass.openicl.icl_evaluator.math_evaluator.MATHEvaluator is correct or it was registered as expected. More details can be found at https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#import-the-custom-module'

[AaroAaron]

我也是遇到相同的报错
然后我尝试在python中直接导入MATHEvaluator：
from opencompass.openicl.icl_evaluator.math_evaluator import MATHEvaluator
会提示缺少latex2sympy2_extended和math_verify包，pip install以后就可以正常导入了！ @ningmenghongcha @AllenShow