opencompass
opencompass copied to clipboard
open-compass
[Bug] DLCRunner无法获取运行结果
Prerequisite
- [X] I have searched Issues and Discussions but cannot get the expected help.
- [X] The bug has not been fixed in the latest version.
Type
I'm evaluating with the officially supported tasks/models/datasets.
Environment
{'CUDA available': True, 'CUDA_HOME': '/usr/local/cuda', 'GCC': 'gcc (Ubuntu 9.4.0-1ubuntu1~20.04.1) 9.4.0', 'GPU 0,1,2': 'NVIDIA A100-SXM4-80GB', 'MMEngine': '0.10.3', 'MUSA available': False, 'NVCC': 'Cuda compilation tools, release 12.1, V12.1.66', 'OpenCV': '4.9.0', 'PyTorch': '2.2.2', '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=2.2.2, ' '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': '3.10.14 (main, Mar 21 2024, 16:24:04) [GCC 11.2.0]', 'TorchVision': '0.17.2', 'numpy_random_seed': 2147483648, 'opencompass': '0.2.3+bd7c11b', 'sys.platform': 'linux'}
Reproduces the problem - code/configuration sample
自定义配置文件如下：
from opencompass.runners import DLCRunner, LocalRunner from opencompass.tasks import OpenICLEvalTask, OpenICLInferTask from opencompass.models import HuggingFaceCausalLM from mmengine.config import read_base from opencompass.partitioners import SizePartitioner, NaivePartitioner
with read_base(): from .datasets.mmlu.mmlu_clean_ppl import mmlu_datasets
datasets = [*mmlu_datasets]
models = [ dict( type=HuggingFaceCausalLM, abbr='7b-model', path="model_path", tokenizer_path='model_path', tokenizer_kwargs=dict(padding_side='left', truncation_side='left', trust_remote_code=True, use_fast=False,), max_out_len=100, max_seq_len=2048, batch_size=8, model_kwargs=dict(device_map='auto', trust_remote_code=True), run_cfg=dict(num_gpus=1, num_procs=1), ) ]
infer = dict( partitioner=dict(type=SizePartitioner, max_task_size=5000), runner=dict( type=DLCRunner, task=dict(type=OpenICLInferTask), max_num_workers=4, aliyun_cfg=dict( dlc_config_path="/root/.dlc/config", python_env_path="/root/miniconda3/envs/opencompass", workspace_id='ws***', worker_image='image-url', ), retry=2, ), )
eval = dict( partitioner=dict(type=NaivePartitioner), runner=dict( type=LocalRunner, max_num_workers=4, task=dict(type=OpenICLEvalTask)), )
Reproduces the problem - command or script
python run.py configs/eval_test.py
Reproduces the problem - error message
04/18 16:57:52 - OpenCompass - WARNING - SlurmRunner is not used, so the partition argument is ignored. 04/18 16:57:52 - OpenCompass - INFO - Partitioned into 25 tasks. 04/18 16:57:52 - OpenCompass - WARNING - To ensure the integrity of the log results, the log displayed by DLCRunner has a 10-second delay. [ ] 0/25, elapsed: 0s, ETA:multiprocessing.pool.RemoteTraceback: """ Traceback (most recent call last): File "/cpfs01/user/zhangshusen/glusterfs2/zhangshusen/miniconda3/envs/opencompass/lib/python3.10/multiprocessing/pool.py", line 125, in worker result = (True, func(*args, **kwds)) File "/cpfs01/user/zhangshusen/glusterfs2/zhangshusen/opencompass/opencompass/runners/dlc.py", line 264, in _launch return_code = _run_within_retry() File "/cpfs01/user/zhangshusen/glusterfs2/zhangshusen/opencompass/opencompass/runners/dlc.py", line 229, in _run_within_retry raise RuntimeError( RuntimeError: Failed to get job info for dlc56wtmugbosjtd """
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/cpfs01/user/zhangshusen/glusterfs2/zhangshusen/opencompass/run.py", line 4, in
Other information
dlc上看到提交的infer任务运行成功了，但是运行脚本侧获取不到dlc运行结果，导致后续eval任务失败
