opencompass icon indicating copy to clipboard operation
opencompass copied to clipboard

Published 20 hours ago • verified publisher icon open-compass

cmb_gen [bug]

Open songyao199681 opened this issue 9 months ago • 0 comments

Prerequisite

Type

I'm evaluating with the officially supported tasks/models/datasets.

Environment

python -c "import opencompass.utils;import pprint;pprint.pprint(dict(opencompass.utils.collect_env()))" {'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': 'Tesla P40', 'MMEngine': '0.10.4', 'MUSA available': False, 'NVCC': 'Cuda compilation tools, release 11.7, V11.7.64', 'OpenCV': '4.9.0', 'PyTorch': '2.0.1+cu117', '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 v2.7.3 (Git Hash ' '6dbeffbae1f23cbbeae17adb7b5b13f1f37c080e)\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: AVX2\n' ' - CUDA Runtime 11.7\n' ' - NVCC architecture flags: ' '-gencode;arch=compute_37,code=sm_37;-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\n' ' - CuDNN 8.5\n' ' - Magma 2.6.1\n' ' - Build settings: BLAS_INFO=mkl, ' 'BUILD_TYPE=Release, CUDA_VERSION=11.7, ' 'CUDNN_VERSION=8.5.0, ' 'CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, ' 'CXX_FLAGS= -D_GLIBCXX_USE_CXX11_ABI=0 ' '-fabi-version=11 -Wno-deprecated ' '-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 -Wunused-local-typedefs ' '-Wno-unused-parameter -Wno-unused-function ' '-Wno-unused-result -Wno-strict-overflow ' '-Wno-strict-aliasing ' '-Wno-error=deprecated-declarations ' '-Wno-stringop-overflow -Wno-psabi ' '-Wno-error=pedantic -Wno-error=redundant-decls ' '-Wno-error=old-style-cast ' '-fdiagnostics-color=always -faligned-new ' '-Wno-unused-but-set-variable ' '-Wno-maybe-uninitialized -fno-math-errno ' '-fno-trapping-math -Werror=format ' '-Werror=cast-function-type ' '-Wno-stringop-overflow, LAPACK_INFO=mkl, ' 'PERF_WITH_AVX=1, PERF_WITH_AVX2=1, ' 'PERF_WITH_AVX512=1, ' 'TORCH_DISABLE_GPU_ASSERTS=ON, ' 'TORCH_VERSION=2.0.1, 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=1, USE_NNPACK=ON, ' 'USE_OPENMP=ON, USE_ROCM=OFF, \n', 'Python': '3.10.14 (main, May 6 2024, 19:42:50) [GCC 11.2.0]', 'TorchVision': '0.15.2+cu117', 'numpy_random_seed': 2147483648, 'opencompass': '0.2.4+19d7e63', 'sys.platform': 'linux'}

Reproduces the problem - code/configuration sample

python run.py --datasets cmb_gen
--hf-path /opt/models/Qwen1.5-0.5B-Chat
--model-kwargs device_map='auto'
--tokenizer-kwargs padding_side='left' truncation='left' use_fast=False
--max-out-len 100
--max-seq-len 2048
--batch-size 8
--no-batch-padding
--num-gpus 0 05/11 10:27:04 - OpenCompass - INFO - Loading cmb_gen: configs/datasets/cmb/cmb_gen.py 05/11 10:27:04 - OpenCompass - INFO - Loading example: configs/summarizers/example.py 05/11 10:27:04 - OpenCompass - WARNING - SlurmRunner is not used, so the partition argument is ignored. 05/11 10:27:04 - OpenCompass - INFO - Partitioned into 7 tasks. launch OpenICLInfer[opencompass.models.huggingface.HuggingFace_models_Qwen1.5-0.5B-Chat/cmb_test_0] on CPU launch OpenICLInfer[opencompass.models.huggingface.HuggingFace_models_Qwen1.5-0.5B-Chat/cmb_test_1] on CPU launch OpenICLInfer[opencompass.models.huggingface.HuggingFace_models_Qwen1.5-0.5B-Chat/cmb_test_2] on CPU launch OpenICLInfer[opencompass.models.huggingface.HuggingFace_models_Qwen1.5-0.5B-Chat/cmb_test_3] on CPU launch OpenICLInfer[opencompass.models.huggingface.HuggingFace_models_Qwen1.5-0.5B-Chat/cmb_test_4] on CPU launch OpenICLInfer[opencompass.models.huggingface.HuggingFace_models_Qwen1.5-0.5B-Chat/cmb_test_5] on CPU launch OpenICLInfer[opencompass.models.huggingface.HuggingFace_models_Qwen1.5-0.5B-Chat/cmb] on CPU 0%| | 0/7 [00:00<?, ?it/s] 05/11 10:27:31 - OpenCompass - ERROR - /software/opencompass/opencompass/runners/local.py - _launch - 206 - task OpenICLInfer[opencompass.models.huggingface.Hugg ingFace_models_Qwen1.5-0.5B-Chat/cmb_test_2] fail, see ./outputs/default/20240511_102704/logs/infer/opencompass.models.huggingface.HuggingFace_models_Qwen1.5-0.5B-Chat/cmb_test_2.out 14%|██████████████████ | 1/7 [00:27<02:45, 27.63s/it] 05/11 10:27:34 - OpenCompass - ERROR - /software/opencompass/opencompass/runners/local.py - _launch - 206 - task OpenICLInfer[opencompass.models.huggingface.Hugg ingFace_models_Qwen1.5-0.5B-Chat/cmb] fail, see ./outputs/default/20240511_102704/logs/infer/opencompass.models.huggingface.HuggingFace_models_Qwen1.5-0.5B-Chat/cmb.out 29%|████████████████████████████████████ | 2/7 [00:30<01:04, 12.91s/it] 05/11 10:27:35 - OpenCompass - ERROR - /software/opencompass/opencompass/runners/local.py - _launch - 206 - task OpenICLInfer[opencompass.models.huggingface.Hugg ingFace_models_Qwen1.5-0.5B-Chat/cmb_test_5] fail, see ./outputs/default/20240511_102704/logs/infer/opencompass.models.huggingface.HuggingFace_models_Qwen1.5-0.5B-Chat/cmb_test_5.out 43%|██████████████████████████████████████████████████████ | 3/7 [00:31<00:30, 7.71s/it] 05/11 10:27:36 - OpenCompass - ERROR - /software/opencompass/opencompass/runners/local.py - _launch - 206 - task OpenICLInfer[opencompass.models.huggingface.Hugg ingFace_models_Qwen1.5-0.5B-Chat/cmb_test_3] fail, see ./outputs/default/20240511_102704/logs/infer/opencompass.models.huggingface.HuggingFace_models_Qwen1.5-0.5B-Chat/cmb_test_3.out 57%|████████████████████████████████████████████████████████████████████████ | 4/7 [00:32<00:14, 4.93s/it] 05/11 10:27:36 - OpenCompass - ERROR - /software/opencompass/opencompass/runners/local.py - _launch - 206 - task OpenICLInfer[opencompass.models.huggingface.Hugg ingFace_models_Qwen1.5-0.5B-Chat/cmb_test_4] fail, see ./outputs/default/20240511_102704/logs/infer/opencompass.models.huggingface.HuggingFace_models_Qwen1.5-0.5B-Chat/cmb_test_4.out 05/11 10:27:37 - OpenCompass - ERROR - /software/opencompass/opencompass/runners/local.py - _launch - 206 - task OpenICLInfer[opencompass.models.huggingface.Hugg ingFace_models_Qwen1.5-0.5B-Chat/cmb_test_1] fail, see ./outputs/default/20240511_102704/logs/infer/opencompass.models.huggingface.HuggingFace_models_Qwen1.5-0.5B-Chat/cmb_test_1.out 86%|████████████████████████████████████████████████████████████████████████████████████████████████████████████ | 6/7 [00:33<00:02, 2.57s/it] 05/11 10:27:38 - OpenCompass - ERROR - /software/opencompass/opencompass/runners/local.py - _launch - 206 - task OpenICLInfer[opencompass.models.huggingface.Hugg ingFace_models_Qwen1.5-0.5B-Chat/cmb_test_0] fail, see ./outputs/default/20240511_102704/logs/infer/opencompass.models.huggingface.HuggingFace_models_Qwen1.5-0.5B-Chat/cmb_test_0.out 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 7/7 [00:33<00:00, 4.84s/it] 05/11 10:27:38 - OpenCompass - ERROR - /software/opencompass/opencompass/runners/base.py - summarize - 64 - OpenICLInfer[opencompass.models.huggingface.HuggingFa ce_models_Qwen1.5-0.5B-Chat/cmb_test_0] failed with code 1 05/11 10:27:38 - OpenCompass - ERROR - /software/opencompass/opencompass/runners/base.py - summarize - 64 - OpenICLInfer[opencompass.models.huggingface.HuggingFa ce_models_Qwen1.5-0.5B-Chat/cmb_test_1] failed with code 1 05/11 10:27:38 - OpenCompass - ERROR - /software/opencompass/opencompass/runners/base.py - summarize - 64 - OpenICLInfer[opencompass.models.huggingface.HuggingFa ce_models_Qwen1.5-0.5B-Chat/cmb_test_2] failed with code 1 05/11 10:27:38 - OpenCompass - ERROR - /software/opencompass/opencompass/runners/base.py - summarize - 64 - OpenICLInfer[opencompass.models.huggingface.HuggingFa ce_models_Qwen1.5-0.5B-Chat/cmb_test_3] failed with code 1 05/11 10:27:38 - OpenCompass - ERROR - /software/opencompass/opencompass/runners/base.py - summarize - 64 - OpenICLInfer[opencompass.models.huggingface.HuggingFa ce_models_Qwen1.5-0.5B-Chat/cmb_test_4] failed with code 1 05/11 10:27:38 - OpenCompass - ERROR - /software/opencompass/opencompass/runners/base.py - summarize - 64 - OpenICLInfer[opencompass.models.huggingface.HuggingFa ce_models_Qwen1.5-0.5B-Chat/cmb_test_5] failed with code 1 05/11 10:27:38 - OpenCompass - ERROR - /software/opencompass/opencompass/runners/base.py - summarize - 64 - OpenICLInfer[opencompass.models.huggingface.HuggingFa ce_models_Qwen1.5-0.5B-Chat/cmb] failed with code 1 05/11 10:27:38 - OpenCompass - INFO - Partitioned into 2 tasks. launch OpenICLEval[opencompass.models.huggingface.HuggingFace_models_Qwen1.5-0.5B-Chat/cmb] on CPU launch OpenICLEval[opencompass.models.huggingface.HuggingFace_models_Qwen1.5-0.5B-Chat/cmb_test] on CPU 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:11<00:00, 5.69s/it] dataset version metric mode opencompass.models.huggingface.HuggingFace_models_Qwen1.5-0.5B-Chat

cmb - - - - cmb_test - - - - 05/11 10:27:49 - OpenCompass - INFO - write summary to /software/opencompass/outputs/default/20240511_102704/summary/summary_20240511_102704.txt 05/11 10:27:49 - OpenCompass - INFO - write csv to /software/opencompass/outputs/default/20240511_102704/summary/summary_20240511_102704.csv (opencompass) root@jkha-W580-G20:/software/opencompass# echo $? 0

Reproduces the problem - command or script

python run.py --datasets cmb_gen_dfb5c4
--hf-path /opt/models/Qwen1.5-0.5B-Chat
--model-kwargs device_map='auto'
--tokenizer-kwargs padding_side='left' truncation='left' use_fast=False
--max-out-len 100
--max-seq-len 2048
--batch-size 8
--no-batch-padding
--num-gpus 0

Reproduces the problem - error message

05/11 10:37:47 - OpenCompass - INFO - write summary to /software/opencompass/outputs/default/20240511_103700/summary/summary_20240511_103700.txt 05/11 10:37:47 - OpenCompass - INFO - write csv to /software/opencompass/outputs/default/20240511_103700/summary/summary_20240511_103700.csv

Other information

cmb_gen cmb_gen_dfb5c4

songyao199681 avatar May 11 '24 02:05 songyao199681