Hugging Face's logo

Buckets:
hf-doc-build
/
doc-dev

Files
xet
hf-doc-build/doc-dev / transformers /main /ko /perf_train_cpu_many.html
rtrm's picture
rtrm
download
raw
26.3 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;다중 CPU에서 효율적으로 훈련하기&quot;,&quot;local&quot;:&quot;efficient-training-on-multiple-cpus&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;PyTorch용 Intel® oneCCL 바인딩&quot;,&quot;local&quot;:&quot;intel-oneccl-bindings-for-pytorch&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;PyTorch용 Intel® oneCCL 바인딩 설치:&quot;,&quot;local&quot;:&quot;intel-oneccl-bindings-for-pytorch-installation&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3}],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Intel® MPI 라이브러리&quot;,&quot;local&quot;:&quot;intel-mpi-library&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;IPEX 설치:&quot;,&quot;local&quot;:&quot;ipex-installation&quot;,&quot;sections&quot;:[],&quot;depth&quot;:4}],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Trainer에서의 사용&quot;,&quot;local&quot;:&quot;usage-in-trainer&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}">
 <link href="/docs/transformers/main/ko/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
 <link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/entry/start.9aa88961.js">
 <link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/scheduler.9bc65507.js">
 <link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/singletons.9eec45c3.js">
 <link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/index.3b203c72.js">
 <link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/paths.566078f7.js">
 <link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/entry/app.84fb67c3.js">
 <link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/index.707bf1b6.js">
 <link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/nodes/0.1c99376b.js">
 <link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/each.e59479a4.js">
 <link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/nodes/41.e1bf6253.js">
 <link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/Tip.c2ecdbf4.js">
 <link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/CodeBlock.54a9f38d.js">
 <link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/EditOnGithub.922df6ba.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;다중 CPU에서 효율적으로 훈련하기&quot;,&quot;local&quot;:&quot;efficient-training-on-multiple-cpus&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;PyTorch용 Intel® oneCCL 바인딩&quot;,&quot;local&quot;:&quot;intel-oneccl-bindings-for-pytorch&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;PyTorch용 Intel® oneCCL 바인딩 설치:&quot;,&quot;local&quot;:&quot;intel-oneccl-bindings-for-pytorch-installation&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3}],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Intel® MPI 라이브러리&quot;,&quot;local&quot;:&quot;intel-mpi-library&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;IPEX 설치:&quot;,&quot;local&quot;:&quot;ipex-installation&quot;,&quot;sections&quot;:[],&quot;depth&quot;:4}],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Trainer에서의 사용&quot;,&quot;local&quot;:&quot;usage-in-trainer&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="efficient-training-on-multiple-cpus" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#efficient-training-on-multiple-cpus"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>다중 CPU에서 효율적으로 훈련하기</span></h1> <p data-svelte-h="svelte-17py23s">하나의 CPU에서 훈련하는 것이 너무 느릴 때는 다중 CPU를 사용할 수 있습니다. 이 가이드는 PyTorch 기반의 DDP를 사용하여 분산 CPU 훈련을 효율적으로 수행하는 방법에 대해 설명합니다.</p> <h2 class="relative group"><a id="intel-oneccl-bindings-for-pytorch" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#intel-oneccl-bindings-for-pytorch"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>PyTorch용 Intel® oneCCL 바인딩</span></h2> <p data-svelte-h="svelte-sgb8g"><a href="https://github.com/oneapi-src/oneCCL" rel="nofollow">Intel® oneCCL</a> (collective communications library)은 allreduce, allgather, alltoall과 같은 집합 통신(collective communications)을 구현한 효율적인 분산 딥러닝 훈련을 위한 라이브러리입니다. oneCCL에 대한 자세한 정보는 <a href="https://spec.oneapi.com/versions/latest/elements/oneCCL/source/index.html" rel="nofollow">oneCCL 문서</a>와 <a href="https://spec.oneapi.com/versions/latest/elements/oneCCL/source/index.html" rel="nofollow">oneCCL 사양</a>을 참조하세요.</p> <p data-svelte-h="svelte-1mnjdt1"><code>oneccl_bindings_for_pytorch</code> 모듈 (<code>torch_ccl</code>은 버전 1.12 이전에 사용)은 PyTorch C10D ProcessGroup API를 구현하며, 외부 ProcessGroup로 동적으로 가져올 수 있으며 현재 Linux 플랫폼에서만 작동합니다.</p> <p data-svelte-h="svelte-2n68ea"><a href="https://github.com/intel/torch-ccl" rel="nofollow">oneccl_bind_pt</a>에서 더 자세한 정보를 확인하세요.</p> <h3 class="relative group"><a id="intel-oneccl-bindings-for-pytorch-installation" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#intel-oneccl-bindings-for-pytorch-installation"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>PyTorch용 Intel® oneCCL 바인딩 설치:</span></h3> <p data-svelte-h="svelte-1plon6x">다음 Python 버전에 대한 Wheel 파일을 사용할 수 있습니다.</p> <table data-svelte-h="svelte-1yk106u"><thead><tr><th align="center">Extension Version</th> <th align="center">Python 3.6</th> <th align="center">Python 3.7</th> <th align="center">Python 3.8</th> <th align="center">Python 3.9</th> <th align="center">Python 3.10</th></tr></thead> <tbody><tr><td align="center">1.13.0</td> <td align="center"></td> <td align="center">√</td> <td align="center">√</td> <td align="center">√</td> <td align="center">√</td></tr> <tr><td align="center">1.12.100</td> <td align="center"></td> <td align="center">√</td> <td align="center">√</td> <td align="center">√</td> <td align="center">√</td></tr> <tr><td align="center">1.12.0</td> <td align="center"></td> <td align="center">√</td> <td align="center">√</td> <td align="center">√</td> <td align="center">√</td></tr> <tr><td align="center">1.11.0</td> <td align="center"></td> <td align="center">√</td> <td align="center">√</td> <td align="center">√</td> <td align="center">√</td></tr> <tr><td align="center">1.10.0</td> <td align="center">√</td> <td align="center">√</td> <td align="center">√</td> <td align="center">√</td> <td align="center"></td></tr></tbody></table> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->pip install oneccl_bind_pt=={pytorch_version} -f https://developer.intel.com/ipex-whl-stable-cpu<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-rqhm0h"><code>{pytorch_version}</code>은 1.13.0과 같이 PyTorch 버전을 나타냅니다.
<a href="https://github.com/intel/torch-ccl" rel="nofollow">oneccl_bind_pt 설치</a>에 대한 더 많은 접근 방법을 확인해 보세요.
oneCCL과 PyTorch의 버전은 일치해야 합니다.</p> <div class="course-tip course-tip-orange bg-gradient-to-br dark:bg-gradient-to-r before:border-orange-500 dark:before:border-orange-800 from-orange-50 dark:from-gray-900 to-white dark:to-gray-950 border border-orange-50 text-orange-700 dark:text-gray-400"><p data-svelte-h="svelte-1k8o8ah">oneccl_bindings_for_pytorch 1.12.0 버전의 미리 빌드된 Wheel 파일은 PyTorch 1.12.1과 호환되지 않습니다(PyTorch 1.12.0용입니다).
PyTorch 1.12.1은 oneccl_bindings_for_pytorch 1.12.10 버전과 함께 사용해야 합니다.</p></div> <h2 class="relative group"><a id="intel-mpi-library" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#intel-mpi-library"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Intel® MPI 라이브러리</span></h2> <p data-svelte-h="svelte-1d9ftxv">이 표준 기반 MPI 구현을 사용하여 Intel® 아키텍처에서 유연하고 효율적이며 확장 가능한 클러스터 메시징을 제공하세요. 이 구성 요소는 Intel® oneAPI HPC Toolkit의 일부입니다.</p> <p data-svelte-h="svelte-1mrjmgk">oneccl_bindings_for_pytorch는 MPI 도구 세트와 함께 설치됩니다. 사용하기 전에 환경을 소스로 지정해야 합니다.</p> <p data-svelte-h="svelte-1kggybc">Intel® oneCCL 버전 1.12.0 이상인 경우</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->oneccl_bindings_for_pytorch_path=$(python -c <span class="hljs-string">&quot;from oneccl_bindings_for_pytorch import cwd; print(cwd)&quot;</span>)
<span class="hljs-built_in">source</span> <span class="hljs-variable">$oneccl_bindings_for_pytorch_path</span>/env/setvars.sh<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-r8fj7f">Intel® oneCCL 버전이 1.12.0 미만인 경우</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->torch_ccl_path=$(python -c <span class="hljs-string">&quot;import torch; import torch_ccl; import os; print(os.path.abspath(os.path.dirname(torch_ccl.__file__)))&quot;</span>)
<span class="hljs-built_in">source</span> <span class="hljs-variable">$torch_ccl_path</span>/env/setvars.sh<!-- HTML_TAG_END --></pre></div> <h4 class="relative group"><a id="ipex-installation" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#ipex-installation"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>IPEX 설치:</span></h4> <p data-svelte-h="svelte-1f1m2ii">IPEX는 Float32와 BFloat16을 모두 사용하는 CPU 훈련을 위한 성능 최적화를 제공합니다. <a href="./perf_train_cpu">single CPU section</a>을 참조하세요.</p> <p data-svelte-h="svelte-1yf9ppj">이어서 나오는 “Trainer에서의 사용”은 Intel® MPI 라이브러리의 mpirun을 예로 들었습니다.</p> <h2 class="relative group"><a id="usage-in-trainer" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#usage-in-trainer"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Trainer에서의 사용</span></h2> <p data-svelte-h="svelte-175tvds">Trainer에서 ccl 백엔드를 사용하여 멀티 CPU 분산 훈련을 활성화하려면 명령 인수에 <strong><code>--ddp_backend ccl</code></strong>을 추가해야 합니다.</p> <p data-svelte-h="svelte-1j3t9q7"><a href="https://github.com/huggingface/transformers/tree/main/examples/pytorch/question-answering" rel="nofollow">질의 응답 예제</a>를 사용한 예를 살펴보겠습니다.</p> <p data-svelte-h="svelte-1ttrd84">다음 명령은 한 Xeon 노드에서 2개의 프로세스로 훈련을 활성화하며, 각 소켓당 하나의 프로세스가 실행됩니다. OMP_NUM_THREADS/CCL_WORKER_COUNT 변수는 최적의 성능을 위해 조정할 수 있습니다.</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --> export CCL_WORKER_COUNT=1
 export MASTER_ADDR=127.0.0.1
 mpirun -n 2 -genv OMP_NUM_THREADS=23 \
 python3 run_qa.py \
 --model_name_or_path google-bert/bert-large-uncased \
 --dataset_name squad \
 --do_train \
 --do_eval \
 --per_device_train_batch_size 12 \
 --learning_rate 3e-5 \
 --num_train_epochs 2 \
 --max_seq_length 384 \
 --doc_stride 128 \
 --output_dir /tmp/debug_squad/ \
 --no_cuda \
 --ddp_backend ccl \
 --use_ipex<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1k6xbsv">다음 명령은 두 개의 Xeon(노드0 및 노드1, 주 프로세스로 노드0을 사용)에서 총 4개의 프로세스로 훈련을 활성화하며, 각 소켓당 하나의 프로세스가 실행됩니다. OMP_NUM_THREADS/CCL_WORKER_COUNT 변수는 최적의 성능을 위해 조정할 수 있습니다.</p> <p data-svelte-h="svelte-wix00e">노드0에서는 각 노드의 IP 주소를 포함하는 구성 파일(예: hostfile)을 생성하고 해당 구성 파일 경로를 인수로 전달해야 합니다.</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --> cat hostfile
 xxx.xxx.xxx.xxx #node0 ip
 xxx.xxx.xxx.xxx #node1 ip<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1u90oxq">이제 노드0에서 다음 명령을 실행하면 <strong>4DDP</strong>가 노드0 및 노드1에서 BF16 자동 혼합 정밀도로 활성화됩니다.</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --> export CCL_WORKER_COUNT=1
 export MASTER_ADDR=xxx.xxx.xxx.xxx #node0 ip
 mpirun -f hostfile -n 4 -ppn 2 \
 -genv OMP_NUM_THREADS=23 \
 python3 run_qa.py \
 --model_name_or_path google-bert/bert-large-uncased \
 --dataset_name squad \
 --do_train \
 --do_eval \
 --per_device_train_batch_size 12 \
 --learning_rate 3e-5 \
 --num_train_epochs 2 \
 --max_seq_length 384 \
 --doc_stride 128 \
 --output_dir /tmp/debug_squad/ \
 --no_cuda \
 --ddp_backend ccl \
 --use_ipex \
 --bf16<!-- HTML_TAG_END --></pre></div> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/transformers/blob/main/docs/source/ko/perf_train_cpu_many.md" target="_blank"><span data-svelte-h="svelte-1kd6by1">&lt;</span> <span data-svelte-h="svelte-x0xyl0">&gt;</span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a> <p></p>
<script>
 {
 __sveltekit_1hrx8 = {
 assets: "/docs/transformers/main/ko",
 base: "/docs/transformers/main/ko",
 env: {}
 };
 const element = document.currentScript.parentElement;
 const data = [null,null];
 Promise.all([
 import("/docs/transformers/main/ko/_app/immutable/entry/start.9aa88961.js"),
 import("/docs/transformers/main/ko/_app/immutable/entry/app.84fb67c3.js")
 ]).then(([kit, app]) => {
 kit.start(app, element, {
 node_ids: [0, 41],
 data,
 form: null,
 error: null
 });
 });
 }
 </script>

Xet Storage Details

Size:
26.3 kB
·
Xet hash:
e4b49e4ff7953ec3283cd22aff6511776731e737cc6d3eff27fc76d04a1485cc

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.