mirror of https://github.com/inclusionAI/AReaL
626 lines
26 KiB
HTML
Executable File
626 lines
26 KiB
HTML
Executable File
|
|
<!DOCTYPE html>
|
|
|
|
|
|
<html lang="en" data-content_root="./" >
|
|
|
|
<head>
|
|
<meta charset="utf-8" />
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
|
|
|
|
<title>Troubleshooting — AReaL Documentation</title>
|
|
|
|
|
|
|
|
<script data-cfasync="false">
|
|
document.documentElement.dataset.mode = localStorage.getItem("mode") || "";
|
|
document.documentElement.dataset.theme = localStorage.getItem("theme") || "";
|
|
</script>
|
|
|
|
<!-- Loaded before other Sphinx assets -->
|
|
<link href="_static/styles/theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
|
|
<link href="_static/styles/bootstrap.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
|
|
<link href="_static/styles/pydata-sphinx-theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
|
|
|
|
|
|
<link href="_static/vendor/fontawesome/6.5.2/css/all.min.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
|
|
<link rel="preload" as="font" type="font/woff2" crossorigin href="_static/vendor/fontawesome/6.5.2/webfonts/fa-solid-900.woff2" />
|
|
<link rel="preload" as="font" type="font/woff2" crossorigin href="_static/vendor/fontawesome/6.5.2/webfonts/fa-brands-400.woff2" />
|
|
<link rel="preload" as="font" type="font/woff2" crossorigin href="_static/vendor/fontawesome/6.5.2/webfonts/fa-regular-400.woff2" />
|
|
|
|
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=fa44fd50" />
|
|
<link rel="stylesheet" type="text/css" href="_static/styles/sphinx-book-theme.css?v=eba8b062" />
|
|
<link rel="stylesheet" type="text/css" href="_static/togglebutton.css?v=13237357" />
|
|
<link rel="stylesheet" type="text/css" href="_static/copybutton.css?v=76b2166b" />
|
|
<link rel="stylesheet" type="text/css" href="_static/mystnb.4510f1fc1dee50b3e5859aac5469c37c29e427902b24a333a5f9fcb2f0b3ac41.css?v=be8a1c11" />
|
|
<link rel="stylesheet" type="text/css" href="_static/sphinx-thebe.css?v=4fa983c6" />
|
|
<link rel="stylesheet" type="text/css" href="_static/sphinx-design.min.css?v=95c83b7e" />
|
|
|
|
<!-- Pre-loaded scripts that we'll load fully later -->
|
|
<link rel="preload" as="script" href="_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b" />
|
|
<link rel="preload" as="script" href="_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b" />
|
|
<script src="_static/vendor/fontawesome/6.5.2/js/all.min.js?digest=dfe6caa3a7d634c4db9b"></script>
|
|
|
|
<script src="_static/documentation_options.js?v=9eb32ce0"></script>
|
|
<script src="_static/doctools.js?v=9a2dae69"></script>
|
|
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
|
|
<script src="_static/clipboard.min.js?v=a7894cd8"></script>
|
|
<script src="_static/copybutton.js?v=f281be69"></script>
|
|
<script src="_static/scripts/sphinx-book-theme.js?v=887ef09a"></script>
|
|
<script>let toggleHintShow = 'Click to show';</script>
|
|
<script>let toggleHintHide = 'Click to hide';</script>
|
|
<script>let toggleOpenOnPrint = 'true';</script>
|
|
<script src="_static/togglebutton.js?v=4a39c7ea"></script>
|
|
<script>var togglebuttonSelector = '.toggle, .admonition.dropdown';</script>
|
|
<script src="_static/design-tabs.js?v=f930bc37"></script>
|
|
<script>const THEBE_JS_URL = "https://unpkg.com/thebe@0.8.2/lib/index.js"; const thebe_selector = ".thebe,.cell"; const thebe_selector_input = "pre"; const thebe_selector_output = ".output, .cell_output"</script>
|
|
<script async="async" src="_static/sphinx-thebe.js?v=c100c467"></script>
|
|
<script>var togglebuttonSelector = '.toggle, .admonition.dropdown';</script>
|
|
<script>const THEBE_JS_URL = "https://unpkg.com/thebe@0.8.2/lib/index.js"; const thebe_selector = ".thebe,.cell"; const thebe_selector_input = "pre"; const thebe_selector_output = ".output, .cell_output"</script>
|
|
<script>DOCUMENTATION_OPTIONS.pagename = 'troubleshooting';</script>
|
|
<link rel="index" title="Index" href="genindex.html" />
|
|
<link rel="search" title="Search" href="search.html" />
|
|
<link rel="next" title="Launching Procedure" href="developer/exp_launch.html" />
|
|
<link rel="prev" title="Evaluation" href="eval.html" />
|
|
<meta name="viewport" content="width=device-width, initial-scale=1"/>
|
|
<meta name="docsearch:language" content="en"/>
|
|
</head>
|
|
|
|
|
|
<body data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-offset="180" data-bs-root-margin="0px 0px -60%" data-default-mode="">
|
|
|
|
|
|
|
|
<div id="pst-skip-link" class="skip-link d-print-none"><a href="#main-content">Skip to main content</a></div>
|
|
|
|
<div id="pst-scroll-pixel-helper"></div>
|
|
|
|
<button type="button" class="btn rounded-pill" id="pst-back-to-top">
|
|
<i class="fa-solid fa-arrow-up"></i>Back to top</button>
|
|
|
|
|
|
<input type="checkbox"
|
|
class="sidebar-toggle"
|
|
id="pst-primary-sidebar-checkbox"/>
|
|
<label class="overlay overlay-primary" for="pst-primary-sidebar-checkbox"></label>
|
|
|
|
<input type="checkbox"
|
|
class="sidebar-toggle"
|
|
id="pst-secondary-sidebar-checkbox"/>
|
|
<label class="overlay overlay-secondary" for="pst-secondary-sidebar-checkbox"></label>
|
|
|
|
<div class="search-button__wrapper">
|
|
<div class="search-button__overlay"></div>
|
|
<div class="search-button__search-container">
|
|
<form class="bd-search d-flex align-items-center"
|
|
action="search.html"
|
|
method="get">
|
|
<i class="fa-solid fa-magnifying-glass"></i>
|
|
<input type="search"
|
|
class="form-control"
|
|
name="q"
|
|
id="search-input"
|
|
placeholder="Search this book..."
|
|
aria-label="Search this book..."
|
|
autocomplete="off"
|
|
autocorrect="off"
|
|
autocapitalize="off"
|
|
spellcheck="false"/>
|
|
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
|
|
</form></div>
|
|
</div>
|
|
|
|
<div class="pst-async-banner-revealer d-none">
|
|
<aside id="bd-header-version-warning" class="d-none d-print-none" aria-label="Version warning"></aside>
|
|
</div>
|
|
|
|
|
|
<header class="bd-header navbar navbar-expand-lg bd-navbar d-print-none">
|
|
</header>
|
|
|
|
|
|
<div class="bd-container">
|
|
<div class="bd-container__inner bd-page-width">
|
|
|
|
|
|
|
|
<div class="bd-sidebar-primary bd-sidebar">
|
|
|
|
|
|
|
|
<div class="sidebar-header-items sidebar-primary__section">
|
|
|
|
|
|
|
|
|
|
</div>
|
|
|
|
<div class="sidebar-primary-items__start sidebar-primary__section">
|
|
<div class="sidebar-primary-item">
|
|
|
|
|
|
|
|
|
|
|
|
<a class="navbar-brand logo" href="intro.html">
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<img src="_static/logo.png" class="logo__image only-light" alt="AReaL Documentation - Home"/>
|
|
<script>document.write(`<img src="_static/logo.png" class="logo__image only-dark" alt="AReaL Documentation - Home"/>`);</script>
|
|
|
|
|
|
</a></div>
|
|
<div class="sidebar-primary-item">
|
|
|
|
<script>
|
|
document.write(`
|
|
<button class="btn search-button-field search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
|
|
<i class="fa-solid fa-magnifying-glass"></i>
|
|
<span class="search-button__default-text">Search</span>
|
|
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
|
|
</button>
|
|
`);
|
|
</script></div>
|
|
<div class="sidebar-primary-item"><nav class="bd-links bd-docs-nav" aria-label="Main">
|
|
<div class="bd-toc-item navbar-nav active">
|
|
|
|
<ul class="nav bd-sidenav bd-sidenav__home-link">
|
|
<li class="toctree-l1">
|
|
<a class="reference internal" href="intro.html">
|
|
Overview
|
|
</a>
|
|
</li>
|
|
</ul>
|
|
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Tutorial</span></p>
|
|
<ul class="current nav bd-sidenav">
|
|
<li class="toctree-l1"><a class="reference internal" href="installation.html">Installation</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="training.html">Training</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="eval.html">Evaluation</a></li>
|
|
<li class="toctree-l1 current active"><a class="current reference internal" href="#">Troubleshooting</a></li>
|
|
</ul>
|
|
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Developer Manual</span></p>
|
|
<ul class="nav bd-sidenav">
|
|
<li class="toctree-l1"><a class="reference internal" href="developer/exp_launch.html">Launching Procedure</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="developer/master_worker.html">Master Worker</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="developer/model_worker.html">Model Worker</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="developer/algo_interface.html">Algorithm, Interface & Backends</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="developer/allocation_parallel.html">Allocation & Parallelism</a></li>
|
|
</ul>
|
|
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Contributing</span></p>
|
|
<ul class="nav bd-sidenav">
|
|
<li class="toctree-l1"><a class="reference internal" href="contrib.html">Contribution Guide</a></li>
|
|
</ul>
|
|
|
|
</div>
|
|
</nav></div>
|
|
</div>
|
|
|
|
|
|
<div class="sidebar-primary-items__end sidebar-primary__section">
|
|
</div>
|
|
|
|
<div id="rtd-footer-container"></div>
|
|
|
|
|
|
</div>
|
|
|
|
<main id="main-content" class="bd-main" role="main">
|
|
|
|
|
|
|
|
<div class="sbt-scroll-pixel-helper"></div>
|
|
|
|
<div class="bd-content">
|
|
<div class="bd-article-container">
|
|
|
|
<div class="bd-header-article d-print-none">
|
|
<div class="header-article-items header-article__inner">
|
|
|
|
<div class="header-article-items__start">
|
|
|
|
<div class="header-article-item"><button class="sidebar-toggle primary-toggle btn btn-sm" title="Toggle primary sidebar" data-bs-placement="bottom" data-bs-toggle="tooltip">
|
|
<span class="fa-solid fa-bars"></span>
|
|
</button></div>
|
|
|
|
</div>
|
|
|
|
|
|
<div class="header-article-items__end">
|
|
|
|
<div class="header-article-item">
|
|
|
|
<div class="article-header-buttons">
|
|
|
|
|
|
|
|
|
|
|
|
<div class="dropdown dropdown-source-buttons">
|
|
<button class="btn dropdown-toggle" type="button" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Source repositories">
|
|
<i class="fab fa-github"></i>
|
|
</button>
|
|
<ul class="dropdown-menu">
|
|
|
|
|
|
|
|
<li><a href="https://github.com/inclusionAI/AReaL" target="_blank"
|
|
class="btn btn-sm btn-source-repository-button dropdown-item"
|
|
title="Source repository"
|
|
data-bs-placement="left" data-bs-toggle="tooltip"
|
|
>
|
|
|
|
|
|
<span class="btn__icon-container">
|
|
<i class="fab fa-github"></i>
|
|
</span>
|
|
<span class="btn__text-container">Repository</span>
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
<li><a href="https://github.com/inclusionAI/AReaL/issues/new?title=Issue%20on%20page%20%2Ftroubleshooting.html&body=Your%20issue%20content%20here." target="_blank"
|
|
class="btn btn-sm btn-source-issues-button dropdown-item"
|
|
title="Open an issue"
|
|
data-bs-placement="left" data-bs-toggle="tooltip"
|
|
>
|
|
|
|
|
|
<span class="btn__icon-container">
|
|
<i class="fas fa-lightbulb"></i>
|
|
</span>
|
|
<span class="btn__text-container">Open issue</span>
|
|
</a>
|
|
</li>
|
|
|
|
</ul>
|
|
</div>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<div class="dropdown dropdown-download-buttons">
|
|
<button class="btn dropdown-toggle" type="button" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download this page">
|
|
<i class="fas fa-download"></i>
|
|
</button>
|
|
<ul class="dropdown-menu">
|
|
|
|
|
|
|
|
<li><a href="_sources/troubleshooting.md" target="_blank"
|
|
class="btn btn-sm btn-download-source-button dropdown-item"
|
|
title="Download source file"
|
|
data-bs-placement="left" data-bs-toggle="tooltip"
|
|
>
|
|
|
|
|
|
<span class="btn__icon-container">
|
|
<i class="fas fa-file"></i>
|
|
</span>
|
|
<span class="btn__text-container">.md</span>
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
<li>
|
|
<button onclick="window.print()"
|
|
class="btn btn-sm btn-download-pdf-button dropdown-item"
|
|
title="Print to PDF"
|
|
data-bs-placement="left" data-bs-toggle="tooltip"
|
|
>
|
|
|
|
|
|
<span class="btn__icon-container">
|
|
<i class="fas fa-file-pdf"></i>
|
|
</span>
|
|
<span class="btn__text-container">.pdf</span>
|
|
</button>
|
|
</li>
|
|
|
|
</ul>
|
|
</div>
|
|
|
|
|
|
|
|
|
|
<button onclick="toggleFullScreen()"
|
|
class="btn btn-sm btn-fullscreen-button"
|
|
title="Fullscreen mode"
|
|
data-bs-placement="bottom" data-bs-toggle="tooltip"
|
|
>
|
|
|
|
|
|
<span class="btn__icon-container">
|
|
<i class="fas fa-expand"></i>
|
|
</span>
|
|
|
|
</button>
|
|
|
|
|
|
|
|
<script>
|
|
document.write(`
|
|
<button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button" title="light/dark" aria-label="light/dark" data-bs-placement="bottom" data-bs-toggle="tooltip">
|
|
<i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light"></i>
|
|
<i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark"></i>
|
|
<i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto"></i>
|
|
</button>
|
|
`);
|
|
</script>
|
|
|
|
|
|
<script>
|
|
document.write(`
|
|
<button class="btn btn-sm pst-navbar-icon search-button search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
|
|
<i class="fa-solid fa-magnifying-glass fa-lg"></i>
|
|
</button>
|
|
`);
|
|
</script>
|
|
<button class="sidebar-toggle secondary-toggle btn btn-sm" title="Toggle secondary sidebar" data-bs-placement="bottom" data-bs-toggle="tooltip">
|
|
<span class="fa-solid fa-list"></span>
|
|
</button>
|
|
</div></div>
|
|
|
|
</div>
|
|
|
|
</div>
|
|
</div>
|
|
|
|
|
|
|
|
<div id="jb-print-docs-body" class="onlyprint">
|
|
<h1>Troubleshooting</h1>
|
|
<!-- Table of contents -->
|
|
<div id="print-main-content">
|
|
<div id="jb-print-toc">
|
|
|
|
<div>
|
|
<h2> Contents </h2>
|
|
</div>
|
|
<nav aria-label="Page">
|
|
<ul class="visible nav section-nav flex-column">
|
|
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#automatic-recovery">Automatic Recovery</a><ul class="nav section-nav flex-column">
|
|
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#recovery-failure-causes">Recovery Failure Causes</a></li>
|
|
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#verify-recovery-checkpoint-creation">Verify Recovery Checkpoint Creation</a></li>
|
|
</ul>
|
|
</li>
|
|
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#memory-issues">Memory Issues</a><ul class="nav section-nav flex-column">
|
|
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#torch-cuda-cudaoutofmemoryerror">torch.cuda.CudaOutOfMemoryError</a><ul class="nav section-nav flex-column">
|
|
<li class="toc-h4 nav-item toc-entry"><a class="reference internal nav-link" href="#during-initialization">During Initialization</a></li>
|
|
<li class="toc-h4 nav-item toc-entry"><a class="reference internal nav-link" href="#during-sglang-generation">During SGLang Generation</a></li>
|
|
<li class="toc-h4 nav-item toc-entry"><a class="reference internal nav-link" href="#during-actor-inf-or-actor-train">During <code class="docutils literal notranslate"><span class="pre">actor_inf</span></code> or <code class="docutils literal notranslate"><span class="pre">actor_train</span></code></a></li>
|
|
</ul>
|
|
</li>
|
|
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#cuda-error-out-of-memory">CUDA Error: Out of Memory</a></li>
|
|
</ul>
|
|
</li>
|
|
</ul>
|
|
</nav>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
|
|
|
|
|
|
<div id="searchbox"></div>
|
|
<article class="bd-article">
|
|
|
|
<section class="tex2jax_ignore mathjax_ignore" id="troubleshooting">
|
|
<h1>Troubleshooting<a class="headerlink" href="#troubleshooting" title="Link to this heading">#</a></h1>
|
|
<p>If the following content does not address your issue, feel free to raise a GitHub Issue.</p>
|
|
<section id="automatic-recovery">
|
|
<h2>Automatic Recovery<a class="headerlink" href="#automatic-recovery" title="Link to this heading">#</a></h2>
|
|
<p>When setting <code class="docutils literal notranslate"><span class="pre">recover_mode=auto</span></code> and the experiment configuration remains unchanged, AReaL will attempt to discover previous checkpoints and recover the experiment from them.</p>
|
|
<section id="recovery-failure-causes">
|
|
<h3>Recovery Failure Causes<a class="headerlink" href="#recovery-failure-causes" title="Link to this heading">#</a></h3>
|
|
<p>If automatic recovery fails, check the following possibilities:</p>
|
|
<p><strong>Configuration Changes:</strong></p>
|
|
<ul class="simple">
|
|
<li><p>The <code class="docutils literal notranslate"><span class="pre">experiment_name</span></code> and <code class="docutils literal notranslate"><span class="pre">trial_name</span></code> in the training script differ from the previous run</p></li>
|
|
<li><p>Changes in batch size (<code class="docutils literal notranslate"><span class="pre">dataset.train_bs_n_seqs</span></code> parameter)</p></li>
|
|
<li><p>Changes in group size (<code class="docutils literal notranslate"><span class="pre">group_size</span></code> parameter)</p></li>
|
|
<li><p>Changes in number of nodes (<code class="docutils literal notranslate"><span class="pre">n_nodes</span></code> parameter)</p></li>
|
|
</ul>
|
|
<p><strong>Missing Recovery Checkpoints:</strong>
|
|
Recovery checkpoints are generated under two conditions by default:</p>
|
|
<ul class="simple">
|
|
<li><p>After completion of the second step</p></li>
|
|
<li><p>When a step completes and more than 600 seconds have passed since the last recovery checkpoint (controlled by <code class="docutils literal notranslate"><span class="pre">exp_ctrl.ckpt_freq_secs=600</span></code>)</p></li>
|
|
</ul>
|
|
</section>
|
|
<section id="verify-recovery-checkpoint-creation">
|
|
<h3>Verify Recovery Checkpoint Creation<a class="headerlink" href="#verify-recovery-checkpoint-creation" title="Link to this heading">#</a></h3>
|
|
<p>You can confirm if a recovery checkpoint was generated by searching for the following message in the logs:</p>
|
|
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span><span class="o">(</span>master_worker/0<span class="w"> </span><span class="nv">pid</span><span class="o">=</span><span class="m">96390</span>,<span class="w"> </span><span class="nv">ip</span><span class="o">=</span>xxx.xxx.xxx.xxx<span class="o">)</span><span class="w"> </span><span class="m">20250222</span>-11:52:02.760<span class="w"> </span>master<span class="w"> </span>worker<span class="w"> </span>INFO:<span class="w"> </span>Dumped<span class="w"> </span>recover<span class="w"> </span>info<span class="w"> </span>to<span class="w"> </span>file.
|
|
</pre></div>
|
|
</div>
|
|
</section>
|
|
</section>
|
|
<section id="memory-issues">
|
|
<h2>Memory Issues<a class="headerlink" href="#memory-issues" title="Link to this heading">#</a></h2>
|
|
<section id="torch-cuda-cudaoutofmemoryerror">
|
|
<h3>torch.cuda.CudaOutOfMemoryError<a class="headerlink" href="#torch-cuda-cudaoutofmemoryerror" title="Link to this heading">#</a></h3>
|
|
<p>The key to resolving this issue is identifying the phase where the error occurs:</p>
|
|
<section id="during-initialization">
|
|
<h4>During Initialization<a class="headerlink" href="#during-initialization" title="Link to this heading">#</a></h4>
|
|
<ul class="simple">
|
|
<li><p>Check for idle processes on the GPU</p></li>
|
|
<li><p><strong>Distributed scenarios</strong>: Restart the Ray cluster</p></li>
|
|
<li><p><strong>Single-machine scenarios</strong>: Use <code class="docutils literal notranslate"><span class="pre">pkill</span></code> to terminate processes</p></li>
|
|
</ul>
|
|
</section>
|
|
<section id="during-sglang-generation">
|
|
<h4>During SGLang Generation<a class="headerlink" href="#during-sglang-generation" title="Link to this heading">#</a></h4>
|
|
<ul class="simple">
|
|
<li><p>Decrease the <code class="docutils literal notranslate"><span class="pre">actor.sglang.mem_fraction_static</span></code> parameter</p></li>
|
|
<li><p>Increase the tensor parallelism degree</p></li>
|
|
</ul>
|
|
</section>
|
|
<section id="during-actor-inf-or-actor-train">
|
|
<h4>During <code class="docutils literal notranslate"><span class="pre">actor_inf</span></code> or <code class="docutils literal notranslate"><span class="pre">actor_train</span></code><a class="headerlink" href="#during-actor-inf-or-actor-train" title="Link to this heading">#</a></h4>
|
|
<ul class="simple">
|
|
<li><p><strong>Adjust microbatch size</strong>: Set parameters like <code class="docutils literal notranslate"><span class="pre">actor_train.mb_spec.max_tokens_per_mb=20480</span></code>. This parameter limits tokens per forward/backward pass and can be set as low as the maximum sequence length (including prompt)</p></li>
|
|
<li><p><strong>Modify parallelism strategy</strong>: Adjust <code class="docutils literal notranslate"><span class="pre">allocation_mode</span></code> by:</p>
|
|
<ul>
|
|
<li><p>Reducing data parallelism</p></li>
|
|
<li><p>Increasing tensor or pipeline parallelism</p></li>
|
|
<li><p>Preferring pipeline parallelism over tensor parallelism</p></li>
|
|
</ul>
|
|
</li>
|
|
</ul>
|
|
</section>
|
|
</section>
|
|
<section id="cuda-error-out-of-memory">
|
|
<h3>CUDA Error: Out of Memory<a class="headerlink" href="#cuda-error-out-of-memory" title="Link to this heading">#</a></h3>
|
|
<p>This issue may occur during data transfer. Try increasing <code class="docutils literal notranslate"><span class="pre">mem_per_xx_worker</span></code> in the CLI arguments.</p>
|
|
</section>
|
|
</section>
|
|
</section>
|
|
|
|
<script type="text/x-thebe-config">
|
|
{
|
|
requestKernel: true,
|
|
binderOptions: {
|
|
repo: "binder-examples/jupyter-stacks-datascience",
|
|
ref: "master",
|
|
},
|
|
codeMirrorConfig: {
|
|
theme: "abcdef",
|
|
mode: "python"
|
|
},
|
|
kernelOptions: {
|
|
name: "python3",
|
|
path: "./."
|
|
},
|
|
predefinedOutput: true
|
|
}
|
|
</script>
|
|
<script>kernelName = 'python3'</script>
|
|
|
|
</article>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<footer class="prev-next-footer d-print-none">
|
|
|
|
<div class="prev-next-area">
|
|
<a class="left-prev"
|
|
href="eval.html"
|
|
title="previous page">
|
|
<i class="fa-solid fa-angle-left"></i>
|
|
<div class="prev-next-info">
|
|
<p class="prev-next-subtitle">previous</p>
|
|
<p class="prev-next-title">Evaluation</p>
|
|
</div>
|
|
</a>
|
|
<a class="right-next"
|
|
href="developer/exp_launch.html"
|
|
title="next page">
|
|
<div class="prev-next-info">
|
|
<p class="prev-next-subtitle">next</p>
|
|
<p class="prev-next-title">Launching Procedure</p>
|
|
</div>
|
|
<i class="fa-solid fa-angle-right"></i>
|
|
</a>
|
|
</div>
|
|
</footer>
|
|
|
|
</div>
|
|
|
|
|
|
|
|
<div class="bd-sidebar-secondary bd-toc"><div class="sidebar-secondary-items sidebar-secondary__inner">
|
|
|
|
|
|
<div class="sidebar-secondary-item">
|
|
<div class="page-toc tocsection onthispage">
|
|
<i class="fa-solid fa-list"></i> Contents
|
|
</div>
|
|
<nav class="bd-toc-nav page-toc">
|
|
<ul class="visible nav section-nav flex-column">
|
|
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#automatic-recovery">Automatic Recovery</a><ul class="nav section-nav flex-column">
|
|
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#recovery-failure-causes">Recovery Failure Causes</a></li>
|
|
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#verify-recovery-checkpoint-creation">Verify Recovery Checkpoint Creation</a></li>
|
|
</ul>
|
|
</li>
|
|
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#memory-issues">Memory Issues</a><ul class="nav section-nav flex-column">
|
|
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#torch-cuda-cudaoutofmemoryerror">torch.cuda.CudaOutOfMemoryError</a><ul class="nav section-nav flex-column">
|
|
<li class="toc-h4 nav-item toc-entry"><a class="reference internal nav-link" href="#during-initialization">During Initialization</a></li>
|
|
<li class="toc-h4 nav-item toc-entry"><a class="reference internal nav-link" href="#during-sglang-generation">During SGLang Generation</a></li>
|
|
<li class="toc-h4 nav-item toc-entry"><a class="reference internal nav-link" href="#during-actor-inf-or-actor-train">During <code class="docutils literal notranslate"><span class="pre">actor_inf</span></code> or <code class="docutils literal notranslate"><span class="pre">actor_train</span></code></a></li>
|
|
</ul>
|
|
</li>
|
|
<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#cuda-error-out-of-memory">CUDA Error: Out of Memory</a></li>
|
|
</ul>
|
|
</li>
|
|
</ul>
|
|
</nav></div>
|
|
|
|
</div></div>
|
|
|
|
|
|
</div>
|
|
<footer class="bd-footer-content">
|
|
|
|
<div class="bd-footer-content__inner container">
|
|
|
|
<div class="footer-item">
|
|
|
|
<p class="component-author">
|
|
By Wei Fu
|
|
</p>
|
|
|
|
</div>
|
|
|
|
<div class="footer-item">
|
|
|
|
|
|
<p class="copyright">
|
|
|
|
© Copyright 2023.
|
|
<br/>
|
|
|
|
</p>
|
|
|
|
</div>
|
|
|
|
<div class="footer-item">
|
|
|
|
</div>
|
|
|
|
<div class="footer-item">
|
|
|
|
</div>
|
|
|
|
</div>
|
|
</footer>
|
|
|
|
|
|
</main>
|
|
</div>
|
|
</div>
|
|
|
|
<!-- Scripts loaded after <body> so the DOM is not blocked -->
|
|
<script src="_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b"></script>
|
|
<script src="_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b"></script>
|
|
|
|
<footer class="bd-footer">
|
|
</footer>
|
|
</body>
|
|
</html> |