805 lines
40 KiB
HTML
805 lines
40 KiB
HTML
<!DOCTYPE html>
|
|
<html xmlns="http://www.w3.org/1999/xhtml" lang="en" xml:lang="en"><head>
|
|
|
|
<meta charset="utf-8">
|
|
<meta name="generator" content="quarto-1.4.551">
|
|
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes">
|
|
|
|
|
|
<title>Axolotl - Example notebook for running Axolotl on google colab</title>
|
|
<style>
|
|
code{white-space: pre-wrap;}
|
|
span.smallcaps{font-variant: small-caps;}
|
|
div.columns{display: flex; gap: min(4vw, 1.5em);}
|
|
div.column{flex: auto; overflow-x: auto;}
|
|
div.hanging-indent{margin-left: 1.5em; text-indent: -1.5em;}
|
|
ul.task-list{list-style: none;}
|
|
ul.task-list li input[type="checkbox"] {
|
|
width: 0.8em;
|
|
margin: 0 0.8em 0.2em -1em; /* quarto-specific, see https://github.com/quarto-dev/quarto-cli/issues/4556 */
|
|
vertical-align: middle;
|
|
}
|
|
/* CSS for syntax highlighting */
|
|
pre > code.sourceCode { white-space: pre; position: relative; }
|
|
pre > code.sourceCode > span { line-height: 1.25; }
|
|
pre > code.sourceCode > span:empty { height: 1.2em; }
|
|
.sourceCode { overflow: visible; }
|
|
code.sourceCode > span { color: inherit; text-decoration: inherit; }
|
|
div.sourceCode { margin: 1em 0; }
|
|
pre.sourceCode { margin: 0; }
|
|
@media screen {
|
|
div.sourceCode { overflow: auto; }
|
|
}
|
|
@media print {
|
|
pre > code.sourceCode { white-space: pre-wrap; }
|
|
pre > code.sourceCode > span { text-indent: -5em; padding-left: 5em; }
|
|
}
|
|
pre.numberSource code
|
|
{ counter-reset: source-line 0; }
|
|
pre.numberSource code > span
|
|
{ position: relative; left: -4em; counter-increment: source-line; }
|
|
pre.numberSource code > span > a:first-child::before
|
|
{ content: counter(source-line);
|
|
position: relative; left: -1em; text-align: right; vertical-align: baseline;
|
|
border: none; display: inline-block;
|
|
-webkit-touch-callout: none; -webkit-user-select: none;
|
|
-khtml-user-select: none; -moz-user-select: none;
|
|
-ms-user-select: none; user-select: none;
|
|
padding: 0 4px; width: 4em;
|
|
}
|
|
pre.numberSource { margin-left: 3em; padding-left: 4px; }
|
|
div.sourceCode
|
|
{ }
|
|
@media screen {
|
|
pre > code.sourceCode > span > a:first-child::before { text-decoration: underline; }
|
|
}
|
|
</style>
|
|
|
|
|
|
<script src="../../site_libs/quarto-nav/quarto-nav.js"></script>
|
|
<script src="../../site_libs/clipboard/clipboard.min.js"></script>
|
|
<script src="../../site_libs/quarto-search/autocomplete.umd.js"></script>
|
|
<script src="../../site_libs/quarto-search/fuse.min.js"></script>
|
|
<script src="../../site_libs/quarto-search/quarto-search.js"></script>
|
|
<meta name="quarto:offset" content="../../">
|
|
<link href="../../favicon.jpg" rel="icon" type="image/jpeg">
|
|
<script src="../../site_libs/quarto-html/quarto.js"></script>
|
|
<script src="../../site_libs/quarto-html/popper.min.js"></script>
|
|
<script src="../../site_libs/quarto-html/tippy.umd.min.js"></script>
|
|
<script src="../../site_libs/quarto-html/anchor.min.js"></script>
|
|
<link href="../../site_libs/quarto-html/tippy.css" rel="stylesheet">
|
|
<link href="../../site_libs/quarto-html/quarto-syntax-highlighting.css" rel="stylesheet" id="quarto-text-highlighting-styles">
|
|
<script src="../../site_libs/bootstrap/bootstrap.min.js"></script>
|
|
<link href="../../site_libs/bootstrap/bootstrap-icons.css" rel="stylesheet">
|
|
<link href="../../site_libs/bootstrap/bootstrap.min.css" rel="stylesheet" id="quarto-bootstrap" data-mode="light">
|
|
<script id="quarto-search-options" type="application/json">{
|
|
"location": "navbar",
|
|
"copy-button": false,
|
|
"collapse-after": 3,
|
|
"panel-placement": "end",
|
|
"type": "overlay",
|
|
"limit": 50,
|
|
"keyboard-shortcut": [
|
|
"f",
|
|
"/",
|
|
"s"
|
|
],
|
|
"show-item-context": false,
|
|
"language": {
|
|
"search-no-results-text": "No results",
|
|
"search-matching-documents-text": "matching documents",
|
|
"search-copy-link-title": "Copy link to search",
|
|
"search-hide-matches-text": "Hide additional matches",
|
|
"search-more-match-text": "more match in this document",
|
|
"search-more-matches-text": "more matches in this document",
|
|
"search-clear-button-title": "Clear",
|
|
"search-text-placeholder": "",
|
|
"search-detached-cancel-button-title": "Cancel",
|
|
"search-submit-button-title": "Submit",
|
|
"search-label": "Search"
|
|
}
|
|
}</script>
|
|
|
|
|
|
<link rel="stylesheet" href="../../styles.css">
|
|
</head>
|
|
|
|
<body class="nav-sidebar docked nav-fixed">
|
|
|
|
<div id="quarto-search-results"></div>
|
|
<header id="quarto-header" class="headroom fixed-top">
|
|
<nav class="navbar navbar-expand " data-bs-theme="dark">
|
|
<div class="navbar-container container-fluid">
|
|
<div class="navbar-brand-container mx-auto">
|
|
<a class="navbar-brand" href="../../index.html">
|
|
<span class="navbar-title">Axolotl</span>
|
|
</a>
|
|
</div>
|
|
<div class="quarto-navbar-tools tools-wide tools-end">
|
|
<a href="https://twitter.com/axolotl_ai" title="" class="quarto-navigation-tool px-1" aria-label=""><i class="bi bi-twitter"></i></a>
|
|
<a href="https://github.com/OpenAccess-AI-Collective/axolotl/" title="" class="quarto-navigation-tool px-1" aria-label=""><i class="bi bi-github"></i></a>
|
|
<a href="https://discord.gg/7m9sfhzaf3" title="" class="quarto-navigation-tool px-1" aria-label=""><i class="bi bi-discord"></i></a>
|
|
</div>
|
|
<div id="quarto-search" class="" title="Search"></div>
|
|
</div> <!-- /container-fluid -->
|
|
</nav>
|
|
<nav class="quarto-secondary-nav">
|
|
<div class="container-fluid d-flex">
|
|
<button type="button" class="quarto-btn-toggle btn" data-bs-toggle="collapse" data-bs-target=".quarto-sidebar-collapse-item" aria-controls="quarto-sidebar" aria-expanded="false" aria-label="Toggle sidebar navigation" onclick="if (window.quartoToggleHeadroom) { window.quartoToggleHeadroom(); }">
|
|
<i class="bi bi-layout-text-sidebar-reverse"></i>
|
|
</button>
|
|
<nav class="quarto-page-breadcrumbs" aria-label="breadcrumb"><ol class="breadcrumb"><li class="breadcrumb-item">Example notebook for running Axolotl on google colab</li></ol></nav>
|
|
<a class="flex-grow-1" role="button" data-bs-toggle="collapse" data-bs-target=".quarto-sidebar-collapse-item" aria-controls="quarto-sidebar" aria-expanded="false" aria-label="Toggle sidebar navigation" onclick="if (window.quartoToggleHeadroom) { window.quartoToggleHeadroom(); }">
|
|
</a>
|
|
</div>
|
|
</nav>
|
|
</header>
|
|
<!-- content -->
|
|
<div id="quarto-content" class="quarto-container page-columns page-rows-contents page-layout-article page-navbar">
|
|
<!-- sidebar -->
|
|
<nav id="quarto-sidebar" class="sidebar collapse collapse-horizontal quarto-sidebar-collapse-item sidebar-navigation docked overflow-auto">
|
|
<div class="sidebar-menu-container">
|
|
<ul class="list-unstyled mt-1">
|
|
<li class="sidebar-item">
|
|
<div class="sidebar-item-container">
|
|
<a href="../../index.html" class="sidebar-item-text sidebar-link">
|
|
<span class="menu-text">Home</span></a>
|
|
</div>
|
|
</li>
|
|
<li class="sidebar-item sidebar-item-section">
|
|
<div class="sidebar-item-container">
|
|
<a class="sidebar-item-text sidebar-link text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-1" aria-expanded="true">
|
|
<span class="menu-text">How-To Guides</span></a>
|
|
<a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-1" aria-expanded="true" aria-label="Toggle section">
|
|
<i class="bi bi-chevron-right ms-2"></i>
|
|
</a>
|
|
</div>
|
|
<ul id="quarto-sidebar-section-1" class="collapse list-unstyled sidebar-section depth1 show">
|
|
<li class="sidebar-item">
|
|
<div class="sidebar-item-container">
|
|
<a href="../../docs/debugging.html" class="sidebar-item-text sidebar-link">
|
|
<span class="menu-text">Debugging</span></a>
|
|
</div>
|
|
</li>
|
|
<li class="sidebar-item">
|
|
<div class="sidebar-item-container">
|
|
<a href="../../docs/multipack.html" class="sidebar-item-text sidebar-link">
|
|
<span class="menu-text">Multipack (Sample Packing)</span></a>
|
|
</div>
|
|
</li>
|
|
<li class="sidebar-item">
|
|
<span class="menu-text">docs/fdsp_qlora.qmd</span>
|
|
</li>
|
|
<li class="sidebar-item">
|
|
<div class="sidebar-item-container">
|
|
<a href="../../docs/input_output.html" class="sidebar-item-text sidebar-link">
|
|
<span class="menu-text">Template-free prompt construction</span></a>
|
|
</div>
|
|
</li>
|
|
<li class="sidebar-item">
|
|
<div class="sidebar-item-container">
|
|
<a href="../../docs/rlhf.html" class="sidebar-item-text sidebar-link">
|
|
<span class="menu-text">RLHF (Beta)</span></a>
|
|
</div>
|
|
</li>
|
|
<li class="sidebar-item">
|
|
<div class="sidebar-item-container">
|
|
<a href="../../docs/nccl.html" class="sidebar-item-text sidebar-link">
|
|
<span class="menu-text">NCCL</span></a>
|
|
</div>
|
|
</li>
|
|
<li class="sidebar-item">
|
|
<div class="sidebar-item-container">
|
|
<a href="../../docs/mac.html" class="sidebar-item-text sidebar-link">
|
|
<span class="menu-text">Mac M-series</span></a>
|
|
</div>
|
|
</li>
|
|
<li class="sidebar-item">
|
|
<div class="sidebar-item-container">
|
|
<a href="../../docs/multi-node.html" class="sidebar-item-text sidebar-link">
|
|
<span class="menu-text">Multi Node</span></a>
|
|
</div>
|
|
</li>
|
|
</ul>
|
|
</li>
|
|
<li class="sidebar-item sidebar-item-section">
|
|
<div class="sidebar-item-container">
|
|
<a class="sidebar-item-text sidebar-link text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-2" aria-expanded="true">
|
|
<span class="menu-text">Reference</span></a>
|
|
<a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-2" aria-expanded="true" aria-label="Toggle section">
|
|
<i class="bi bi-chevron-right ms-2"></i>
|
|
</a>
|
|
</div>
|
|
<ul id="quarto-sidebar-section-2" class="collapse list-unstyled sidebar-section depth1 show">
|
|
<li class="sidebar-item">
|
|
<div class="sidebar-item-container">
|
|
<a href="../../docs/config.html" class="sidebar-item-text sidebar-link">
|
|
<span class="menu-text">Config options</span></a>
|
|
</div>
|
|
</li>
|
|
</ul>
|
|
</li>
|
|
<li class="sidebar-item">
|
|
<div class="sidebar-item-container">
|
|
<a href="../../docs/faq.html" class="sidebar-item-text sidebar-link">
|
|
<span class="menu-text">FAQ</span></a>
|
|
</div>
|
|
</li>
|
|
</ul>
|
|
</div>
|
|
</nav>
|
|
<div id="quarto-sidebar-glass" class="quarto-sidebar-collapse-item" data-bs-toggle="collapse" data-bs-target=".quarto-sidebar-collapse-item"></div>
|
|
<!-- margin-sidebar -->
|
|
<div id="quarto-margin-sidebar" class="sidebar margin-sidebar">
|
|
<nav id="TOC" role="doc-toc" class="toc-active">
|
|
<h2 id="toc-title">On this page</h2>
|
|
|
|
<ul>
|
|
<li><a href="#install-axolotl-and-dependencies" id="toc-install-axolotl-and-dependencies" class="nav-link active" data-scroll-target="#install-axolotl-and-dependencies">Install Axolotl and dependencies</a></li>
|
|
<li><a href="#create-an-yaml-config-file" id="toc-create-an-yaml-config-file" class="nav-link" data-scroll-target="#create-an-yaml-config-file">Create an yaml config file</a></li>
|
|
<li><a href="#launch-the-training" id="toc-launch-the-training" class="nav-link" data-scroll-target="#launch-the-training">Launch the training</a></li>
|
|
<li><a href="#play-with-inference" id="toc-play-with-inference" class="nav-link" data-scroll-target="#play-with-inference">Play with inference</a></li>
|
|
</ul>
|
|
</nav>
|
|
</div>
|
|
<!-- main -->
|
|
<main class="content" id="quarto-document-content">
|
|
|
|
<header id="title-block-header" class="quarto-title-block default">
|
|
<div class="quarto-title">
|
|
<h1 class="title">Example notebook for running Axolotl on google colab</h1>
|
|
</div>
|
|
|
|
|
|
|
|
<div class="quarto-title-meta">
|
|
|
|
|
|
|
|
|
|
</div>
|
|
|
|
|
|
|
|
</header>
|
|
|
|
|
|
<div id="cell-2" class="cell">
|
|
<div class="sourceCode cell-code" id="cb1"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb1-1"><a href="#cb1-1" aria-hidden="true" tabindex="-1"></a><span class="im">import</span> torch</span>
|
|
<span id="cb1-2"><a href="#cb1-2" aria-hidden="true" tabindex="-1"></a><span class="co"># Check so there is a gpu available, a T4(free tier) is enough to run this notebook</span></span>
|
|
<span id="cb1-3"><a href="#cb1-3" aria-hidden="true" tabindex="-1"></a><span class="cf">assert</span> (torch.cuda.is_available()<span class="op">==</span><span class="va">True</span>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
|
</div>
|
|
<section id="install-axolotl-and-dependencies" class="level2">
|
|
<h2 class="anchored" data-anchor-id="install-axolotl-and-dependencies">Install Axolotl and dependencies</h2>
|
|
<div id="cell-4" class="cell" data-outputid="e3777b5a-40ef-424f-e181-62dfecd1dd01">
|
|
<div class="sourceCode cell-code" id="cb2"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb2-1"><a href="#cb2-1" aria-hidden="true" tabindex="-1"></a><span class="op">!</span>pip install torch<span class="op">==</span><span class="st">"2.1.2"</span></span>
|
|
<span id="cb2-2"><a href="#cb2-2" aria-hidden="true" tabindex="-1"></a><span class="op">!</span>pip install <span class="op">-</span>e git<span class="op">+</span>https:<span class="op">//</span>github.com<span class="op">/</span>OpenAccess<span class="op">-</span>AI<span class="op">-</span>Collective<span class="op">/</span>axolotl<span class="co">#egg=axolotl</span></span>
|
|
<span id="cb2-3"><a href="#cb2-3" aria-hidden="true" tabindex="-1"></a><span class="op">!</span>pip install flash<span class="op">-</span>attn<span class="op">==</span><span class="st">"2.5.0"</span></span>
|
|
<span id="cb2-4"><a href="#cb2-4" aria-hidden="true" tabindex="-1"></a><span class="op">!</span>pip install deepspeed<span class="op">==</span><span class="st">"0.13.1"</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
|
</div>
|
|
</section>
|
|
<section id="create-an-yaml-config-file" class="level2">
|
|
<h2 class="anchored" data-anchor-id="create-an-yaml-config-file">Create an yaml config file</h2>
|
|
<div id="cell-6" class="cell">
|
|
<div class="sourceCode cell-code" id="cb3"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb3-1"><a href="#cb3-1" aria-hidden="true" tabindex="-1"></a><span class="im">import</span> yaml</span>
|
|
<span id="cb3-2"><a href="#cb3-2" aria-hidden="true" tabindex="-1"></a></span>
|
|
<span id="cb3-3"><a href="#cb3-3" aria-hidden="true" tabindex="-1"></a><span class="co"># Your YAML string</span></span>
|
|
<span id="cb3-4"><a href="#cb3-4" aria-hidden="true" tabindex="-1"></a>yaml_string <span class="op">=</span> <span class="st">"""</span></span>
|
|
<span id="cb3-5"><a href="#cb3-5" aria-hidden="true" tabindex="-1"></a><span class="st">base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T</span></span>
|
|
<span id="cb3-6"><a href="#cb3-6" aria-hidden="true" tabindex="-1"></a><span class="st">model_type: LlamaForCausalLM</span></span>
|
|
<span id="cb3-7"><a href="#cb3-7" aria-hidden="true" tabindex="-1"></a><span class="st">tokenizer_type: LlamaTokenizer</span></span>
|
|
<span id="cb3-8"><a href="#cb3-8" aria-hidden="true" tabindex="-1"></a><span class="st">is_llama_derived_model: true</span></span>
|
|
<span id="cb3-9"><a href="#cb3-9" aria-hidden="true" tabindex="-1"></a></span>
|
|
<span id="cb3-10"><a href="#cb3-10" aria-hidden="true" tabindex="-1"></a><span class="st">load_in_8bit: false</span></span>
|
|
<span id="cb3-11"><a href="#cb3-11" aria-hidden="true" tabindex="-1"></a><span class="st">load_in_4bit: true</span></span>
|
|
<span id="cb3-12"><a href="#cb3-12" aria-hidden="true" tabindex="-1"></a><span class="st">strict: false</span></span>
|
|
<span id="cb3-13"><a href="#cb3-13" aria-hidden="true" tabindex="-1"></a></span>
|
|
<span id="cb3-14"><a href="#cb3-14" aria-hidden="true" tabindex="-1"></a><span class="st">datasets:</span></span>
|
|
<span id="cb3-15"><a href="#cb3-15" aria-hidden="true" tabindex="-1"></a><span class="st"> - path: mhenrichsen/alpaca_2k_test</span></span>
|
|
<span id="cb3-16"><a href="#cb3-16" aria-hidden="true" tabindex="-1"></a><span class="st"> type: alpaca</span></span>
|
|
<span id="cb3-17"><a href="#cb3-17" aria-hidden="true" tabindex="-1"></a><span class="st">dataset_prepared_path:</span></span>
|
|
<span id="cb3-18"><a href="#cb3-18" aria-hidden="true" tabindex="-1"></a><span class="st">val_set_size: 0.05</span></span>
|
|
<span id="cb3-19"><a href="#cb3-19" aria-hidden="true" tabindex="-1"></a><span class="st">output_dir: ./qlora-out</span></span>
|
|
<span id="cb3-20"><a href="#cb3-20" aria-hidden="true" tabindex="-1"></a></span>
|
|
<span id="cb3-21"><a href="#cb3-21" aria-hidden="true" tabindex="-1"></a><span class="st">adapter: qlora</span></span>
|
|
<span id="cb3-22"><a href="#cb3-22" aria-hidden="true" tabindex="-1"></a><span class="st">lora_model_dir:</span></span>
|
|
<span id="cb3-23"><a href="#cb3-23" aria-hidden="true" tabindex="-1"></a></span>
|
|
<span id="cb3-24"><a href="#cb3-24" aria-hidden="true" tabindex="-1"></a><span class="st">sequence_len: 1096</span></span>
|
|
<span id="cb3-25"><a href="#cb3-25" aria-hidden="true" tabindex="-1"></a><span class="st">sample_packing: true</span></span>
|
|
<span id="cb3-26"><a href="#cb3-26" aria-hidden="true" tabindex="-1"></a><span class="st">pad_to_sequence_len: true</span></span>
|
|
<span id="cb3-27"><a href="#cb3-27" aria-hidden="true" tabindex="-1"></a></span>
|
|
<span id="cb3-28"><a href="#cb3-28" aria-hidden="true" tabindex="-1"></a><span class="st">lora_r: 32</span></span>
|
|
<span id="cb3-29"><a href="#cb3-29" aria-hidden="true" tabindex="-1"></a><span class="st">lora_alpha: 16</span></span>
|
|
<span id="cb3-30"><a href="#cb3-30" aria-hidden="true" tabindex="-1"></a><span class="st">lora_dropout: 0.05</span></span>
|
|
<span id="cb3-31"><a href="#cb3-31" aria-hidden="true" tabindex="-1"></a><span class="st">lora_target_modules:</span></span>
|
|
<span id="cb3-32"><a href="#cb3-32" aria-hidden="true" tabindex="-1"></a><span class="st">lora_target_linear: true</span></span>
|
|
<span id="cb3-33"><a href="#cb3-33" aria-hidden="true" tabindex="-1"></a><span class="st">lora_fan_in_fan_out:</span></span>
|
|
<span id="cb3-34"><a href="#cb3-34" aria-hidden="true" tabindex="-1"></a></span>
|
|
<span id="cb3-35"><a href="#cb3-35" aria-hidden="true" tabindex="-1"></a><span class="st">wandb_project:</span></span>
|
|
<span id="cb3-36"><a href="#cb3-36" aria-hidden="true" tabindex="-1"></a><span class="st">wandb_entity:</span></span>
|
|
<span id="cb3-37"><a href="#cb3-37" aria-hidden="true" tabindex="-1"></a><span class="st">wandb_watch:</span></span>
|
|
<span id="cb3-38"><a href="#cb3-38" aria-hidden="true" tabindex="-1"></a><span class="st">wandb_name:</span></span>
|
|
<span id="cb3-39"><a href="#cb3-39" aria-hidden="true" tabindex="-1"></a><span class="st">wandb_log_model:</span></span>
|
|
<span id="cb3-40"><a href="#cb3-40" aria-hidden="true" tabindex="-1"></a></span>
|
|
<span id="cb3-41"><a href="#cb3-41" aria-hidden="true" tabindex="-1"></a><span class="st">mlflow_experiment_name: colab-example</span></span>
|
|
<span id="cb3-42"><a href="#cb3-42" aria-hidden="true" tabindex="-1"></a></span>
|
|
<span id="cb3-43"><a href="#cb3-43" aria-hidden="true" tabindex="-1"></a><span class="st">gradient_accumulation_steps: 1</span></span>
|
|
<span id="cb3-44"><a href="#cb3-44" aria-hidden="true" tabindex="-1"></a><span class="st">micro_batch_size: 1</span></span>
|
|
<span id="cb3-45"><a href="#cb3-45" aria-hidden="true" tabindex="-1"></a><span class="st">num_epochs: 4</span></span>
|
|
<span id="cb3-46"><a href="#cb3-46" aria-hidden="true" tabindex="-1"></a><span class="st">max_steps: 20</span></span>
|
|
<span id="cb3-47"><a href="#cb3-47" aria-hidden="true" tabindex="-1"></a><span class="st">optimizer: paged_adamw_32bit</span></span>
|
|
<span id="cb3-48"><a href="#cb3-48" aria-hidden="true" tabindex="-1"></a><span class="st">lr_scheduler: cosine</span></span>
|
|
<span id="cb3-49"><a href="#cb3-49" aria-hidden="true" tabindex="-1"></a><span class="st">learning_rate: 0.0002</span></span>
|
|
<span id="cb3-50"><a href="#cb3-50" aria-hidden="true" tabindex="-1"></a></span>
|
|
<span id="cb3-51"><a href="#cb3-51" aria-hidden="true" tabindex="-1"></a><span class="st">train_on_inputs: false</span></span>
|
|
<span id="cb3-52"><a href="#cb3-52" aria-hidden="true" tabindex="-1"></a><span class="st">group_by_length: false</span></span>
|
|
<span id="cb3-53"><a href="#cb3-53" aria-hidden="true" tabindex="-1"></a><span class="st">bf16: false</span></span>
|
|
<span id="cb3-54"><a href="#cb3-54" aria-hidden="true" tabindex="-1"></a><span class="st">fp16: true</span></span>
|
|
<span id="cb3-55"><a href="#cb3-55" aria-hidden="true" tabindex="-1"></a><span class="st">tf32: false</span></span>
|
|
<span id="cb3-56"><a href="#cb3-56" aria-hidden="true" tabindex="-1"></a></span>
|
|
<span id="cb3-57"><a href="#cb3-57" aria-hidden="true" tabindex="-1"></a><span class="st">gradient_checkpointing: true</span></span>
|
|
<span id="cb3-58"><a href="#cb3-58" aria-hidden="true" tabindex="-1"></a><span class="st">early_stopping_patience:</span></span>
|
|
<span id="cb3-59"><a href="#cb3-59" aria-hidden="true" tabindex="-1"></a><span class="st">resume_from_checkpoint:</span></span>
|
|
<span id="cb3-60"><a href="#cb3-60" aria-hidden="true" tabindex="-1"></a><span class="st">local_rank:</span></span>
|
|
<span id="cb3-61"><a href="#cb3-61" aria-hidden="true" tabindex="-1"></a><span class="st">logging_steps: 1</span></span>
|
|
<span id="cb3-62"><a href="#cb3-62" aria-hidden="true" tabindex="-1"></a><span class="st">xformers_attention:</span></span>
|
|
<span id="cb3-63"><a href="#cb3-63" aria-hidden="true" tabindex="-1"></a><span class="st">flash_attention: false</span></span>
|
|
<span id="cb3-64"><a href="#cb3-64" aria-hidden="true" tabindex="-1"></a></span>
|
|
<span id="cb3-65"><a href="#cb3-65" aria-hidden="true" tabindex="-1"></a><span class="st">warmup_steps: 10</span></span>
|
|
<span id="cb3-66"><a href="#cb3-66" aria-hidden="true" tabindex="-1"></a><span class="st">evals_per_epoch:</span></span>
|
|
<span id="cb3-67"><a href="#cb3-67" aria-hidden="true" tabindex="-1"></a><span class="st">saves_per_epoch:</span></span>
|
|
<span id="cb3-68"><a href="#cb3-68" aria-hidden="true" tabindex="-1"></a><span class="st">debug:</span></span>
|
|
<span id="cb3-69"><a href="#cb3-69" aria-hidden="true" tabindex="-1"></a><span class="st">deepspeed:</span></span>
|
|
<span id="cb3-70"><a href="#cb3-70" aria-hidden="true" tabindex="-1"></a><span class="st">weight_decay: 0.0</span></span>
|
|
<span id="cb3-71"><a href="#cb3-71" aria-hidden="true" tabindex="-1"></a><span class="st">fsdp:</span></span>
|
|
<span id="cb3-72"><a href="#cb3-72" aria-hidden="true" tabindex="-1"></a><span class="st">fsdp_config:</span></span>
|
|
<span id="cb3-73"><a href="#cb3-73" aria-hidden="true" tabindex="-1"></a><span class="st">special_tokens:</span></span>
|
|
<span id="cb3-74"><a href="#cb3-74" aria-hidden="true" tabindex="-1"></a></span>
|
|
<span id="cb3-75"><a href="#cb3-75" aria-hidden="true" tabindex="-1"></a><span class="st">"""</span></span>
|
|
<span id="cb3-76"><a href="#cb3-76" aria-hidden="true" tabindex="-1"></a></span>
|
|
<span id="cb3-77"><a href="#cb3-77" aria-hidden="true" tabindex="-1"></a><span class="co"># Convert the YAML string to a Python dictionary</span></span>
|
|
<span id="cb3-78"><a href="#cb3-78" aria-hidden="true" tabindex="-1"></a>yaml_dict <span class="op">=</span> yaml.safe_load(yaml_string)</span>
|
|
<span id="cb3-79"><a href="#cb3-79" aria-hidden="true" tabindex="-1"></a></span>
|
|
<span id="cb3-80"><a href="#cb3-80" aria-hidden="true" tabindex="-1"></a><span class="co"># Specify your file path</span></span>
|
|
<span id="cb3-81"><a href="#cb3-81" aria-hidden="true" tabindex="-1"></a>file_path <span class="op">=</span> <span class="st">'test_axolotl.yaml'</span></span>
|
|
<span id="cb3-82"><a href="#cb3-82" aria-hidden="true" tabindex="-1"></a></span>
|
|
<span id="cb3-83"><a href="#cb3-83" aria-hidden="true" tabindex="-1"></a><span class="co"># Write the YAML file</span></span>
|
|
<span id="cb3-84"><a href="#cb3-84" aria-hidden="true" tabindex="-1"></a><span class="cf">with</span> <span class="bu">open</span>(file_path, <span class="st">'w'</span>) <span class="im">as</span> <span class="bu">file</span>:</span>
|
|
<span id="cb3-85"><a href="#cb3-85" aria-hidden="true" tabindex="-1"></a> yaml.dump(yaml_dict, <span class="bu">file</span>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
|
</div>
|
|
</section>
|
|
<section id="launch-the-training" class="level2">
|
|
<h2 class="anchored" data-anchor-id="launch-the-training">Launch the training</h2>
|
|
<div id="cell-8" class="cell" data-outputid="d6d0df17-4b53-439c-c802-22c0456d301b">
|
|
<div class="sourceCode cell-code" id="cb4"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb4-1"><a href="#cb4-1" aria-hidden="true" tabindex="-1"></a><span class="co"># Buy using the ! the comand will be executed as a bash command</span></span>
|
|
<span id="cb4-2"><a href="#cb4-2" aria-hidden="true" tabindex="-1"></a><span class="op">!</span>accelerate launch <span class="op">-</span>m axolotl.cli.train <span class="op">/</span>content<span class="op">/</span>test_axolotl.yaml</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
|
</div>
|
|
</section>
|
|
<section id="play-with-inference" class="level2">
|
|
<h2 class="anchored" data-anchor-id="play-with-inference">Play with inference</h2>
|
|
<div id="cell-10" class="cell">
|
|
<div class="sourceCode cell-code" id="cb5"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb5-1"><a href="#cb5-1" aria-hidden="true" tabindex="-1"></a><span class="co"># Buy using the ! the comand will be executed as a bash command</span></span>
|
|
<span id="cb5-2"><a href="#cb5-2" aria-hidden="true" tabindex="-1"></a><span class="op">!</span>accelerate launch <span class="op">-</span>m axolotl.cli.inference <span class="op">/</span>content<span class="op">/</span>test_axolotl.yaml <span class="op">\</span></span>
|
|
<span id="cb5-3"><a href="#cb5-3" aria-hidden="true" tabindex="-1"></a> <span class="op">--</span>qlora_model_dir<span class="op">=</span><span class="st">"./qlora-out"</span> <span class="op">--</span>gradio</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
|
</div>
|
|
|
|
|
|
</section>
|
|
|
|
</main> <!-- /main -->
|
|
<script id="quarto-html-after-body" type="application/javascript">
|
|
window.document.addEventListener("DOMContentLoaded", function (event) {
|
|
const toggleBodyColorMode = (bsSheetEl) => {
|
|
const mode = bsSheetEl.getAttribute("data-mode");
|
|
const bodyEl = window.document.querySelector("body");
|
|
if (mode === "dark") {
|
|
bodyEl.classList.add("quarto-dark");
|
|
bodyEl.classList.remove("quarto-light");
|
|
} else {
|
|
bodyEl.classList.add("quarto-light");
|
|
bodyEl.classList.remove("quarto-dark");
|
|
}
|
|
}
|
|
const toggleBodyColorPrimary = () => {
|
|
const bsSheetEl = window.document.querySelector("link#quarto-bootstrap");
|
|
if (bsSheetEl) {
|
|
toggleBodyColorMode(bsSheetEl);
|
|
}
|
|
}
|
|
toggleBodyColorPrimary();
|
|
const icon = "";
|
|
const anchorJS = new window.AnchorJS();
|
|
anchorJS.options = {
|
|
placement: 'right',
|
|
icon: icon
|
|
};
|
|
anchorJS.add('.anchored');
|
|
const isCodeAnnotation = (el) => {
|
|
for (const clz of el.classList) {
|
|
if (clz.startsWith('code-annotation-')) {
|
|
return true;
|
|
}
|
|
}
|
|
return false;
|
|
}
|
|
const clipboard = new window.ClipboardJS('.code-copy-button', {
|
|
text: function(trigger) {
|
|
const codeEl = trigger.previousElementSibling.cloneNode(true);
|
|
for (const childEl of codeEl.children) {
|
|
if (isCodeAnnotation(childEl)) {
|
|
childEl.remove();
|
|
}
|
|
}
|
|
return codeEl.innerText;
|
|
}
|
|
});
|
|
clipboard.on('success', function(e) {
|
|
// button target
|
|
const button = e.trigger;
|
|
// don't keep focus
|
|
button.blur();
|
|
// flash "checked"
|
|
button.classList.add('code-copy-button-checked');
|
|
var currentTitle = button.getAttribute("title");
|
|
button.setAttribute("title", "Copied!");
|
|
let tooltip;
|
|
if (window.bootstrap) {
|
|
button.setAttribute("data-bs-toggle", "tooltip");
|
|
button.setAttribute("data-bs-placement", "left");
|
|
button.setAttribute("data-bs-title", "Copied!");
|
|
tooltip = new bootstrap.Tooltip(button,
|
|
{ trigger: "manual",
|
|
customClass: "code-copy-button-tooltip",
|
|
offset: [0, -8]});
|
|
tooltip.show();
|
|
}
|
|
setTimeout(function() {
|
|
if (tooltip) {
|
|
tooltip.hide();
|
|
button.removeAttribute("data-bs-title");
|
|
button.removeAttribute("data-bs-toggle");
|
|
button.removeAttribute("data-bs-placement");
|
|
}
|
|
button.setAttribute("title", currentTitle);
|
|
button.classList.remove('code-copy-button-checked');
|
|
}, 1000);
|
|
// clear code selection
|
|
e.clearSelection();
|
|
});
|
|
var localhostRegex = new RegExp(/^(?:http|https):\/\/localhost\:?[0-9]*\//);
|
|
var mailtoRegex = new RegExp(/^mailto:/);
|
|
var filterRegex = new RegExp("https:\/\/OpenAccess-AI-Collective\.github\.io\/axolotl\/");
|
|
var isInternal = (href) => {
|
|
return filterRegex.test(href) || localhostRegex.test(href) || mailtoRegex.test(href);
|
|
}
|
|
// Inspect non-navigation links and adorn them if external
|
|
var links = window.document.querySelectorAll('a[href]:not(.nav-link):not(.navbar-brand):not(.toc-action):not(.sidebar-link):not(.sidebar-item-toggle):not(.pagination-link):not(.no-external):not([aria-hidden]):not(.dropdown-item):not(.quarto-navigation-tool)');
|
|
for (var i=0; i<links.length; i++) {
|
|
const link = links[i];
|
|
if (!isInternal(link.href)) {
|
|
// undo the damage that might have been done by quarto-nav.js in the case of
|
|
// links that we want to consider external
|
|
if (link.dataset.originalHref !== undefined) {
|
|
link.href = link.dataset.originalHref;
|
|
}
|
|
}
|
|
}
|
|
function tippyHover(el, contentFn, onTriggerFn, onUntriggerFn) {
|
|
const config = {
|
|
allowHTML: true,
|
|
maxWidth: 500,
|
|
delay: 100,
|
|
arrow: false,
|
|
appendTo: function(el) {
|
|
return el.parentElement;
|
|
},
|
|
interactive: true,
|
|
interactiveBorder: 10,
|
|
theme: 'quarto',
|
|
placement: 'bottom-start',
|
|
};
|
|
if (contentFn) {
|
|
config.content = contentFn;
|
|
}
|
|
if (onTriggerFn) {
|
|
config.onTrigger = onTriggerFn;
|
|
}
|
|
if (onUntriggerFn) {
|
|
config.onUntrigger = onUntriggerFn;
|
|
}
|
|
window.tippy(el, config);
|
|
}
|
|
const noterefs = window.document.querySelectorAll('a[role="doc-noteref"]');
|
|
for (var i=0; i<noterefs.length; i++) {
|
|
const ref = noterefs[i];
|
|
tippyHover(ref, function() {
|
|
// use id or data attribute instead here
|
|
let href = ref.getAttribute('data-footnote-href') || ref.getAttribute('href');
|
|
try { href = new URL(href).hash; } catch {}
|
|
const id = href.replace(/^#\/?/, "");
|
|
const note = window.document.getElementById(id);
|
|
if (note) {
|
|
return note.innerHTML;
|
|
} else {
|
|
return "";
|
|
}
|
|
});
|
|
}
|
|
const xrefs = window.document.querySelectorAll('a.quarto-xref');
|
|
const processXRef = (id, note) => {
|
|
// Strip column container classes
|
|
const stripColumnClz = (el) => {
|
|
el.classList.remove("page-full", "page-columns");
|
|
if (el.children) {
|
|
for (const child of el.children) {
|
|
stripColumnClz(child);
|
|
}
|
|
}
|
|
}
|
|
stripColumnClz(note)
|
|
if (id === null || id.startsWith('sec-')) {
|
|
// Special case sections, only their first couple elements
|
|
const container = document.createElement("div");
|
|
if (note.children && note.children.length > 2) {
|
|
container.appendChild(note.children[0].cloneNode(true));
|
|
for (let i = 1; i < note.children.length; i++) {
|
|
const child = note.children[i];
|
|
if (child.tagName === "P" && child.innerText === "") {
|
|
continue;
|
|
} else {
|
|
container.appendChild(child.cloneNode(true));
|
|
break;
|
|
}
|
|
}
|
|
if (window.Quarto?.typesetMath) {
|
|
window.Quarto.typesetMath(container);
|
|
}
|
|
return container.innerHTML
|
|
} else {
|
|
if (window.Quarto?.typesetMath) {
|
|
window.Quarto.typesetMath(note);
|
|
}
|
|
return note.innerHTML;
|
|
}
|
|
} else {
|
|
// Remove any anchor links if they are present
|
|
const anchorLink = note.querySelector('a.anchorjs-link');
|
|
if (anchorLink) {
|
|
anchorLink.remove();
|
|
}
|
|
if (window.Quarto?.typesetMath) {
|
|
window.Quarto.typesetMath(note);
|
|
}
|
|
// TODO in 1.5, we should make sure this works without a callout special case
|
|
if (note.classList.contains("callout")) {
|
|
return note.outerHTML;
|
|
} else {
|
|
return note.innerHTML;
|
|
}
|
|
}
|
|
}
|
|
for (var i=0; i<xrefs.length; i++) {
|
|
const xref = xrefs[i];
|
|
tippyHover(xref, undefined, function(instance) {
|
|
instance.disable();
|
|
let url = xref.getAttribute('href');
|
|
let hash = undefined;
|
|
if (url.startsWith('#')) {
|
|
hash = url;
|
|
} else {
|
|
try { hash = new URL(url).hash; } catch {}
|
|
}
|
|
if (hash) {
|
|
const id = hash.replace(/^#\/?/, "");
|
|
const note = window.document.getElementById(id);
|
|
if (note !== null) {
|
|
try {
|
|
const html = processXRef(id, note.cloneNode(true));
|
|
instance.setContent(html);
|
|
} finally {
|
|
instance.enable();
|
|
instance.show();
|
|
}
|
|
} else {
|
|
// See if we can fetch this
|
|
fetch(url.split('#')[0])
|
|
.then(res => res.text())
|
|
.then(html => {
|
|
const parser = new DOMParser();
|
|
const htmlDoc = parser.parseFromString(html, "text/html");
|
|
const note = htmlDoc.getElementById(id);
|
|
if (note !== null) {
|
|
const html = processXRef(id, note);
|
|
instance.setContent(html);
|
|
}
|
|
}).finally(() => {
|
|
instance.enable();
|
|
instance.show();
|
|
});
|
|
}
|
|
} else {
|
|
// See if we can fetch a full url (with no hash to target)
|
|
// This is a special case and we should probably do some content thinning / targeting
|
|
fetch(url)
|
|
.then(res => res.text())
|
|
.then(html => {
|
|
const parser = new DOMParser();
|
|
const htmlDoc = parser.parseFromString(html, "text/html");
|
|
const note = htmlDoc.querySelector('main.content');
|
|
if (note !== null) {
|
|
// This should only happen for chapter cross references
|
|
// (since there is no id in the URL)
|
|
// remove the first header
|
|
if (note.children.length > 0 && note.children[0].tagName === "HEADER") {
|
|
note.children[0].remove();
|
|
}
|
|
const html = processXRef(null, note);
|
|
instance.setContent(html);
|
|
}
|
|
}).finally(() => {
|
|
instance.enable();
|
|
instance.show();
|
|
});
|
|
}
|
|
}, function(instance) {
|
|
});
|
|
}
|
|
let selectedAnnoteEl;
|
|
const selectorForAnnotation = ( cell, annotation) => {
|
|
let cellAttr = 'data-code-cell="' + cell + '"';
|
|
let lineAttr = 'data-code-annotation="' + annotation + '"';
|
|
const selector = 'span[' + cellAttr + '][' + lineAttr + ']';
|
|
return selector;
|
|
}
|
|
const selectCodeLines = (annoteEl) => {
|
|
const doc = window.document;
|
|
const targetCell = annoteEl.getAttribute("data-target-cell");
|
|
const targetAnnotation = annoteEl.getAttribute("data-target-annotation");
|
|
const annoteSpan = window.document.querySelector(selectorForAnnotation(targetCell, targetAnnotation));
|
|
const lines = annoteSpan.getAttribute("data-code-lines").split(",");
|
|
const lineIds = lines.map((line) => {
|
|
return targetCell + "-" + line;
|
|
})
|
|
let top = null;
|
|
let height = null;
|
|
let parent = null;
|
|
if (lineIds.length > 0) {
|
|
//compute the position of the single el (top and bottom and make a div)
|
|
const el = window.document.getElementById(lineIds[0]);
|
|
top = el.offsetTop;
|
|
height = el.offsetHeight;
|
|
parent = el.parentElement.parentElement;
|
|
if (lineIds.length > 1) {
|
|
const lastEl = window.document.getElementById(lineIds[lineIds.length - 1]);
|
|
const bottom = lastEl.offsetTop + lastEl.offsetHeight;
|
|
height = bottom - top;
|
|
}
|
|
if (top !== null && height !== null && parent !== null) {
|
|
// cook up a div (if necessary) and position it
|
|
let div = window.document.getElementById("code-annotation-line-highlight");
|
|
if (div === null) {
|
|
div = window.document.createElement("div");
|
|
div.setAttribute("id", "code-annotation-line-highlight");
|
|
div.style.position = 'absolute';
|
|
parent.appendChild(div);
|
|
}
|
|
div.style.top = top - 2 + "px";
|
|
div.style.height = height + 4 + "px";
|
|
div.style.left = 0;
|
|
let gutterDiv = window.document.getElementById("code-annotation-line-highlight-gutter");
|
|
if (gutterDiv === null) {
|
|
gutterDiv = window.document.createElement("div");
|
|
gutterDiv.setAttribute("id", "code-annotation-line-highlight-gutter");
|
|
gutterDiv.style.position = 'absolute';
|
|
const codeCell = window.document.getElementById(targetCell);
|
|
const gutter = codeCell.querySelector('.code-annotation-gutter');
|
|
gutter.appendChild(gutterDiv);
|
|
}
|
|
gutterDiv.style.top = top - 2 + "px";
|
|
gutterDiv.style.height = height + 4 + "px";
|
|
}
|
|
selectedAnnoteEl = annoteEl;
|
|
}
|
|
};
|
|
const unselectCodeLines = () => {
|
|
const elementsIds = ["code-annotation-line-highlight", "code-annotation-line-highlight-gutter"];
|
|
elementsIds.forEach((elId) => {
|
|
const div = window.document.getElementById(elId);
|
|
if (div) {
|
|
div.remove();
|
|
}
|
|
});
|
|
selectedAnnoteEl = undefined;
|
|
};
|
|
// Handle positioning of the toggle
|
|
window.addEventListener(
|
|
"resize",
|
|
throttle(() => {
|
|
elRect = undefined;
|
|
if (selectedAnnoteEl) {
|
|
selectCodeLines(selectedAnnoteEl);
|
|
}
|
|
}, 10)
|
|
);
|
|
function throttle(fn, ms) {
|
|
let throttle = false;
|
|
let timer;
|
|
return (...args) => {
|
|
if(!throttle) { // first call gets through
|
|
fn.apply(this, args);
|
|
throttle = true;
|
|
} else { // all the others get throttled
|
|
if(timer) clearTimeout(timer); // cancel #2
|
|
timer = setTimeout(() => {
|
|
fn.apply(this, args);
|
|
timer = throttle = false;
|
|
}, ms);
|
|
}
|
|
};
|
|
}
|
|
// Attach click handler to the DT
|
|
const annoteDls = window.document.querySelectorAll('dt[data-target-cell]');
|
|
for (const annoteDlNode of annoteDls) {
|
|
annoteDlNode.addEventListener('click', (event) => {
|
|
const clickedEl = event.target;
|
|
if (clickedEl !== selectedAnnoteEl) {
|
|
unselectCodeLines();
|
|
const activeEl = window.document.querySelector('dt[data-target-cell].code-annotation-active');
|
|
if (activeEl) {
|
|
activeEl.classList.remove('code-annotation-active');
|
|
}
|
|
selectCodeLines(clickedEl);
|
|
clickedEl.classList.add('code-annotation-active');
|
|
} else {
|
|
// Unselect the line
|
|
unselectCodeLines();
|
|
clickedEl.classList.remove('code-annotation-active');
|
|
}
|
|
});
|
|
}
|
|
const findCites = (el) => {
|
|
const parentEl = el.parentElement;
|
|
if (parentEl) {
|
|
const cites = parentEl.dataset.cites;
|
|
if (cites) {
|
|
return {
|
|
el,
|
|
cites: cites.split(' ')
|
|
};
|
|
} else {
|
|
return findCites(el.parentElement)
|
|
}
|
|
} else {
|
|
return undefined;
|
|
}
|
|
};
|
|
var bibliorefs = window.document.querySelectorAll('a[role="doc-biblioref"]');
|
|
for (var i=0; i<bibliorefs.length; i++) {
|
|
const ref = bibliorefs[i];
|
|
const citeInfo = findCites(ref);
|
|
if (citeInfo) {
|
|
tippyHover(citeInfo.el, function() {
|
|
var popup = window.document.createElement('div');
|
|
citeInfo.cites.forEach(function(cite) {
|
|
var citeDiv = window.document.createElement('div');
|
|
citeDiv.classList.add('hanging-indent');
|
|
citeDiv.classList.add('csl-entry');
|
|
var biblioDiv = window.document.getElementById('ref-' + cite);
|
|
if (biblioDiv) {
|
|
citeDiv.innerHTML = biblioDiv.innerHTML;
|
|
}
|
|
popup.appendChild(citeDiv);
|
|
});
|
|
return popup.innerHTML;
|
|
});
|
|
}
|
|
}
|
|
});
|
|
</script>
|
|
</div> <!-- /content -->
|
|
|
|
|
|
|
|
|
|
</body></html> |