Built site for gh-pages

This commit is contained in:
Quarto GHA Workflow Runner
2025-03-31 21:17:51 +00:00
parent 71afa0897d
commit be8430d321
12 changed files with 2625 additions and 1515 deletions

View File

@@ -1 +1 @@
010e2732
f2d84a80

View File

@@ -446,6 +446,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
<li><a href="#axolotl.cli.args.InferenceCliArgs" id="toc-axolotl.cli.args.InferenceCliArgs" class="nav-link" data-scroll-target="#axolotl.cli.args.InferenceCliArgs">InferenceCliArgs</a></li>
<li><a href="#axolotl.cli.args.PreprocessCliArgs" id="toc-axolotl.cli.args.PreprocessCliArgs" class="nav-link" data-scroll-target="#axolotl.cli.args.PreprocessCliArgs">PreprocessCliArgs</a></li>
<li><a href="#axolotl.cli.args.TrainerCliArgs" id="toc-axolotl.cli.args.TrainerCliArgs" class="nav-link" data-scroll-target="#axolotl.cli.args.TrainerCliArgs">TrainerCliArgs</a></li>
<li><a href="#axolotl.cli.args.VllmServeCliArgs" id="toc-axolotl.cli.args.VllmServeCliArgs" class="nav-link" data-scroll-target="#axolotl.cli.args.VllmServeCliArgs">VllmServeCliArgs</a></li>
</ul></li>
</ul></li>
</ul>
@@ -487,6 +488,10 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
<td><a href="#axolotl.cli.args.TrainerCliArgs">TrainerCliArgs</a></td>
<td>Dataclass with CLI arguments for <code>axolotl train</code> command.</td>
</tr>
<tr class="odd">
<td><a href="#axolotl.cli.args.VllmServeCliArgs">VllmServeCliArgs</a></td>
<td>Dataclass with CLI arguments for <code>axolotl vllm-serve</code> command.</td>
</tr>
</tbody>
</table>
<section id="axolotl.cli.args.EvaluateCliArgs" class="level3">
@@ -531,6 +536,20 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
<span id="cb4-10"><a href="#cb4-10" aria-hidden="true" tabindex="-1"></a> num_processes<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-11"><a href="#cb4-11" aria-hidden="true" tabindex="-1"></a>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<p>Dataclass with CLI arguments for <code>axolotl train</code> command.</p>
</section>
<section id="axolotl.cli.args.VllmServeCliArgs" class="level3">
<h3 class="anchored" data-anchor-id="axolotl.cli.args.VllmServeCliArgs">VllmServeCliArgs</h3>
<div class="sourceCode" 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>cli.args.VllmServeCliArgs(</span>
<span id="cb5-2"><a href="#cb5-2" aria-hidden="true" tabindex="-1"></a> <span class="va">self</span>,</span>
<span id="cb5-3"><a href="#cb5-3" aria-hidden="true" tabindex="-1"></a> tensor_parallel_size<span class="op">=</span><span class="dv">1</span>,</span>
<span id="cb5-4"><a href="#cb5-4" aria-hidden="true" tabindex="-1"></a> host<span class="op">=</span><span class="st">'0.0.0.0'</span>,</span>
<span id="cb5-5"><a href="#cb5-5" aria-hidden="true" tabindex="-1"></a> port<span class="op">=</span><span class="dv">8000</span>,</span>
<span id="cb5-6"><a href="#cb5-6" aria-hidden="true" tabindex="-1"></a> gpu_memory_utilization<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-7"><a href="#cb5-7" aria-hidden="true" tabindex="-1"></a> dtype<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-8"><a href="#cb5-8" aria-hidden="true" tabindex="-1"></a> max_model_len<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-9"><a href="#cb5-9" aria-hidden="true" tabindex="-1"></a> enable_prefix_caching<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-10"><a href="#cb5-10" aria-hidden="true" tabindex="-1"></a>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<p>Dataclass with CLI arguments for <code>axolotl vllm-serve</code> command.</p>
</section>

View File

@@ -0,0 +1,932 @@
<!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-1.6.42">
<meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes">
<title>cli.vllm_serve Axolotl</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 { display: inline-block; 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-dark-b53751a350365c71b6c909e95f209ed1.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-71f806479865a0e7fd52beea5cc266f1.min.css" rel="stylesheet" append-hash="true" id="quarto-bootstrap" data-mode="dark">
<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 href="../../index.html" class="navbar-brand navbar-brand-logo">
<img src="../../image/axolotl_logo_digital_white.svg" alt="" class="navbar-logo">
</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/axolotl-ai-cloud/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" role="button" 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"></ol></nav>
<a class="flex-grow-1" role="navigation" 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" role="navigation" aria-expanded="true">
<span class="menu-text">Getting Started</span></a>
<a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-1" role="navigation" 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/getting-started.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Quickstart</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/installation.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Installation</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/inference.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Inference and Merging</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/cli.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Command Line Interface (CLI)</span></a>
</div>
</li>
<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 Reference</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/api" class="sidebar-item-text sidebar-link">
<span class="menu-text">API Reference</span></a>
</div>
</li>
</ul>
</li>
<li class="sidebar-item sidebar-item-section">
<div class="sidebar-item-container">
<a href="../../docs/dataset-formats/index.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Dataset Formats</span></a>
<a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-2" role="navigation" 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/dataset-formats/pretraining.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Pre-training</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/dataset-formats/inst_tune.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Instruction Tuning</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/dataset-formats/conversation.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Conversation</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/dataset-formats/stepwise_supervised.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Stepwise Supervised Format</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/dataset-formats/template_free.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Template-Free</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/dataset-formats/tokenized.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Custom Pre-Tokenized Dataset</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-3" role="navigation" aria-expanded="true">
<span class="menu-text">Deployments</span></a>
<a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-3" role="navigation" aria-expanded="true" aria-label="Toggle section">
<i class="bi bi-chevron-right ms-2"></i>
</a>
</div>
<ul id="quarto-sidebar-section-3" class="collapse list-unstyled sidebar-section depth1 show">
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/docker.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Docker</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/multi-gpu.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Multi-GPU</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>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/ray-integration.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Ray Train</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/amd_hpc.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">AMD GPUs on HPC Systems</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>
</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-4" role="navigation" 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-4" role="navigation" aria-expanded="true" aria-label="Toggle section">
<i class="bi bi-chevron-right ms-2"></i>
</a>
</div>
<ul id="quarto-sidebar-section-4" class="collapse list-unstyled sidebar-section depth1 show">
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/multimodal.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">MultiModal / Vision Language Models (BETA)</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/reward_modelling.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Reward Modelling</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/lr_groups.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Learning Rate Groups</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/lora_optims.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">LoRA Optimizations</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-5" role="navigation" aria-expanded="true">
<span class="menu-text">Core Concepts</span></a>
<a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-5" role="navigation" aria-expanded="true" aria-label="Toggle section">
<i class="bi bi-chevron-right ms-2"></i>
</a>
</div>
<ul id="quarto-sidebar-section-5" class="collapse list-unstyled sidebar-section depth1 show">
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/batch_vs_grad.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Batch size vs Gradient accumulation</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/dataset_preprocessing.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Dataset Preprocessing</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>
</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-6" role="navigation" aria-expanded="true">
<span class="menu-text">Advanced Features</span></a>
<a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-6" role="navigation" aria-expanded="true" aria-label="Toggle section">
<i class="bi bi-chevron-right ms-2"></i>
</a>
</div>
<ul id="quarto-sidebar-section-6" class="collapse list-unstyled sidebar-section depth1 show">
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/fsdp_qlora.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">FDSP + QLoRA</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/unsloth.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Unsloth</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/torchao.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">PyTorch ao</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/custom_integrations.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Custom Integrations</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../../docs/sequence_parallelism.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Sequence Parallelism</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-7" role="navigation" aria-expanded="true">
<span class="menu-text">Troubleshooting</span></a>
<a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-7" role="navigation" aria-expanded="true" aria-label="Toggle section">
<i class="bi bi-chevron-right ms-2"></i>
</a>
</div>
<ul id="quarto-sidebar-section-7" class="collapse list-unstyled sidebar-section depth1 show">
<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>
<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/nccl.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">NCCL</span></a>
</div>
</li>
</ul>
</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="#axolotl.cli.vllm_serve" id="toc-axolotl.cli.vllm_serve" class="nav-link active" data-scroll-target="#axolotl.cli.vllm_serve">cli.vllm_serve</a>
<ul class="collapse">
<li><a href="#functions" id="toc-functions" class="nav-link" data-scroll-target="#functions">Functions</a>
<ul class="collapse">
<li><a href="#axolotl.cli.vllm_serve.do_vllm_serve" id="toc-axolotl.cli.vllm_serve.do_vllm_serve" class="nav-link" data-scroll-target="#axolotl.cli.vllm_serve.do_vllm_serve">do_vllm_serve</a></li>
</ul></li>
</ul></li>
</ul>
</nav>
</div>
<!-- main -->
<main class="content" id="quarto-document-content"><header id="title-block-header" class="quarto-title-block"></header>
<section id="axolotl.cli.vllm_serve" class="level1">
<h1>cli.vllm_serve</h1>
<p><code>cli.vllm_serve</code></p>
<p>CLI to start the vllm server for online RL</p>
<section id="functions" class="level2">
<h2 class="anchored" data-anchor-id="functions">Functions</h2>
<table class="caption-top table">
<thead>
<tr class="header">
<th>Name</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr class="odd">
<td><a href="#axolotl.cli.vllm_serve.do_vllm_serve">do_vllm_serve</a></td>
<td>Starts the VLLM server for serving LLM models used for online RL</td>
</tr>
</tbody>
</table>
<section id="axolotl.cli.vllm_serve.do_vllm_serve" class="level3">
<h3 class="anchored" data-anchor-id="axolotl.cli.vllm_serve.do_vllm_serve">do_vllm_serve</h3>
<div class="sourceCode" 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>cli.vllm_serve.do_vllm_serve(config, cli_args)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<p>Starts the VLLM server for serving LLM models used for online RL</p>
<p>Args
:param cfg: Parsed doct of the YAML config
:param cli_args: dict of additional command-line arguments of type VllmServeCliArgs</p>
<section id="returns" class="level4 doc-section doc-section-returns">
<h4 class="doc-section doc-section-returns anchored" data-anchor-id="returns">Returns</h4>
<table class="caption-top table">
<thead>
<tr class="header">
<th>Name</th>
<th>Type</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr class="odd">
<td>process_id</td>
<td></td>
<td>the process id of the started VLLM server</td>
</tr>
</tbody>
</table>
</section>
</section>
</section>
</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 onCopySuccess = 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();
}
const getTextToCopy = function(trigger) {
const codeEl = trigger.previousElementSibling.cloneNode(true);
for (const childEl of codeEl.children) {
if (isCodeAnnotation(childEl)) {
childEl.remove();
}
}
return codeEl.innerText;
}
const clipboard = new window.ClipboardJS('.code-copy-button:not([data-in-quarto-modal])', {
text: getTextToCopy
});
clipboard.on('success', onCopySuccess);
if (window.document.getElementById('quarto-embedded-source-code-modal')) {
const clipboardModal = new window.ClipboardJS('.code-copy-button[data-in-quarto-modal]', {
text: getTextToCopy,
container: window.document.getElementById('quarto-embedded-source-code-modal')
});
clipboardModal.on('success', onCopySuccess);
}
var localhostRegex = new RegExp(/^(?:http|https):\/\/localhost\:?[0-9]*\//);
var mailtoRegex = new RegExp(/^mailto:/);
var filterRegex = new RegExp("https:\/\/axolotl-ai-cloud\.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):not(.about-link)');
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);
}
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>

View File

@@ -476,7 +476,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
</table>
<section id="axolotl.core.trainers.grpo.trainer.AxolotlGRPOTrainer" class="level3">
<h3 class="anchored" data-anchor-id="axolotl.core.trainers.grpo.trainer.AxolotlGRPOTrainer">AxolotlGRPOTrainer</h3>
<div class="sourceCode" 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>core.trainers.grpo.trainer.AxolotlGRPOTrainer(<span class="va">self</span>, <span class="op">*</span>args, <span class="op">**</span>kwargs)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<div class="sourceCode" 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>core.trainers.grpo.trainer.AxolotlGRPOTrainer()</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<p>Extend the base GRPOTrainer for axolotl helpers</p>

View File

@@ -512,49 +512,50 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
<span id="cb1-4"><a href="#cb1-4" aria-hidden="true" tabindex="-1"></a> lr_quadratic_warmup<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb1-5"><a href="#cb1-5" aria-hidden="true" tabindex="-1"></a> pretraining<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb1-6"><a href="#cb1-6" aria-hidden="true" tabindex="-1"></a> sample_packing<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb1-7"><a href="#cb1-7" aria-hidden="true" tabindex="-1"></a> multipack_real_batches<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb1-8"><a href="#cb1-8" aria-hidden="true" tabindex="-1"></a> eval_sample_packing<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-9"><a href="#cb1-9" aria-hidden="true" tabindex="-1"></a> sample_packing_efficiency<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb1-10"><a href="#cb1-10" aria-hidden="true" tabindex="-1"></a> sample_packing_bin_size<span class="op">=</span><span class="dv">200</span>,</span>
<span id="cb1-11"><a href="#cb1-11" aria-hidden="true" tabindex="-1"></a> sample_packing_group_size<span class="op">=</span><span class="dv">100000</span>,</span>
<span id="cb1-12"><a href="#cb1-12" aria-hidden="true" tabindex="-1"></a> max_seq_length<span class="op">=</span><span class="dv">2048</span>,</span>
<span id="cb1-13"><a href="#cb1-13" aria-hidden="true" tabindex="-1"></a> relora_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-14"><a href="#cb1-14" aria-hidden="true" tabindex="-1"></a> relora_warmup_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-15"><a href="#cb1-15" aria-hidden="true" tabindex="-1"></a> relora_anneal_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-16"><a href="#cb1-16" aria-hidden="true" tabindex="-1"></a> relora_prune_ratio<span class="op">=</span><span class="fl">0.9</span>,</span>
<span id="cb1-17"><a href="#cb1-17" aria-hidden="true" tabindex="-1"></a> bench_split<span class="op">=</span><span class="st">'eval'</span>,</span>
<span id="cb1-18"><a href="#cb1-18" aria-hidden="true" tabindex="-1"></a> bench_dataset<span class="op">=</span><span class="st">'pharaouk/dharma-1/dharma_1_mini.json'</span>,</span>
<span id="cb1-19"><a href="#cb1-19" aria-hidden="true" tabindex="-1"></a> do_bench_eval<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb1-20"><a href="#cb1-20" aria-hidden="true" tabindex="-1"></a> do_causal_lm_eval<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb1-21"><a href="#cb1-21" aria-hidden="true" tabindex="-1"></a> max_bench_samples<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-22"><a href="#cb1-22" aria-hidden="true" tabindex="-1"></a> bench_source_max_len<span class="op">=</span><span class="dv">2048</span>,</span>
<span id="cb1-23"><a href="#cb1-23" aria-hidden="true" tabindex="-1"></a> dataloader_prefetch_factor<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-24"><a href="#cb1-24" aria-hidden="true" tabindex="-1"></a> cosine_min_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-25"><a href="#cb1-25" aria-hidden="true" tabindex="-1"></a> cosine_constant_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-26"><a href="#cb1-26" aria-hidden="true" tabindex="-1"></a> loraplus_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-27"><a href="#cb1-27" aria-hidden="true" tabindex="-1"></a> loraplus_lr_embedding<span class="op">=</span><span class="fl">1e-06</span>,</span>
<span id="cb1-28"><a href="#cb1-28" aria-hidden="true" tabindex="-1"></a> embedding_lr_scale<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-29"><a href="#cb1-29" aria-hidden="true" tabindex="-1"></a> lr_groups<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-30"><a href="#cb1-30" aria-hidden="true" tabindex="-1"></a> embedding_lr<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-31"><a href="#cb1-31" aria-hidden="true" tabindex="-1"></a> qlora<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb1-32"><a href="#cb1-32" aria-hidden="true" tabindex="-1"></a> orpo_alpha<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-33"><a href="#cb1-33" aria-hidden="true" tabindex="-1"></a> lisa_n_layers<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-34"><a href="#cb1-34" aria-hidden="true" tabindex="-1"></a> lisa_step_interval<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-35"><a href="#cb1-35" aria-hidden="true" tabindex="-1"></a> lisa_layers_attribute<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-36"><a href="#cb1-36" aria-hidden="true" tabindex="-1"></a> curriculum_sampling<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-37"><a href="#cb1-37" aria-hidden="true" tabindex="-1"></a> alternate_optimizer<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-38"><a href="#cb1-38" aria-hidden="true" tabindex="-1"></a> alternate_lr_scheduler_type<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-39"><a href="#cb1-39" aria-hidden="true" tabindex="-1"></a> chat_template<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-40"><a href="#cb1-40" aria-hidden="true" tabindex="-1"></a> kd_ce_alpha<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-41"><a href="#cb1-41" aria-hidden="true" tabindex="-1"></a> kd_alpha<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb1-42"><a href="#cb1-42" aria-hidden="true" tabindex="-1"></a> kd_temperature<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb1-43"><a href="#cb1-43" aria-hidden="true" tabindex="-1"></a> kd_zscore_base_temp<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-44"><a href="#cb1-44" aria-hidden="true" tabindex="-1"></a> kd_top_k_before_softmax<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-45"><a href="#cb1-45" aria-hidden="true" tabindex="-1"></a> sequence_parallel_degree<span class="op">=</span><span class="dv">1</span>,</span>
<span id="cb1-46"><a href="#cb1-46" aria-hidden="true" tabindex="-1"></a> image_size<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-47"><a href="#cb1-47" aria-hidden="true" tabindex="-1"></a> image_resize_algorithm<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-48"><a href="#cb1-48" aria-hidden="true" tabindex="-1"></a> simpo_gamma<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-49"><a href="#cb1-49" aria-hidden="true" tabindex="-1"></a>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<span id="cb1-7"><a href="#cb1-7" aria-hidden="true" tabindex="-1"></a> sample_packing_sequentially<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb1-8"><a href="#cb1-8" aria-hidden="true" tabindex="-1"></a> multipack_real_batches<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb1-9"><a href="#cb1-9" aria-hidden="true" tabindex="-1"></a> eval_sample_packing<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-10"><a href="#cb1-10" aria-hidden="true" tabindex="-1"></a> sample_packing_efficiency<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb1-11"><a href="#cb1-11" aria-hidden="true" tabindex="-1"></a> sample_packing_bin_size<span class="op">=</span><span class="dv">200</span>,</span>
<span id="cb1-12"><a href="#cb1-12" aria-hidden="true" tabindex="-1"></a> sample_packing_group_size<span class="op">=</span><span class="dv">100000</span>,</span>
<span id="cb1-13"><a href="#cb1-13" aria-hidden="true" tabindex="-1"></a> max_seq_length<span class="op">=</span><span class="dv">2048</span>,</span>
<span id="cb1-14"><a href="#cb1-14" aria-hidden="true" tabindex="-1"></a> relora_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-15"><a href="#cb1-15" aria-hidden="true" tabindex="-1"></a> relora_warmup_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-16"><a href="#cb1-16" aria-hidden="true" tabindex="-1"></a> relora_anneal_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-17"><a href="#cb1-17" aria-hidden="true" tabindex="-1"></a> relora_prune_ratio<span class="op">=</span><span class="fl">0.9</span>,</span>
<span id="cb1-18"><a href="#cb1-18" aria-hidden="true" tabindex="-1"></a> bench_split<span class="op">=</span><span class="st">'eval'</span>,</span>
<span id="cb1-19"><a href="#cb1-19" aria-hidden="true" tabindex="-1"></a> bench_dataset<span class="op">=</span><span class="st">'pharaouk/dharma-1/dharma_1_mini.json'</span>,</span>
<span id="cb1-20"><a href="#cb1-20" aria-hidden="true" tabindex="-1"></a> do_bench_eval<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb1-21"><a href="#cb1-21" aria-hidden="true" tabindex="-1"></a> do_causal_lm_eval<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb1-22"><a href="#cb1-22" aria-hidden="true" tabindex="-1"></a> max_bench_samples<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-23"><a href="#cb1-23" aria-hidden="true" tabindex="-1"></a> bench_source_max_len<span class="op">=</span><span class="dv">2048</span>,</span>
<span id="cb1-24"><a href="#cb1-24" aria-hidden="true" tabindex="-1"></a> dataloader_prefetch_factor<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-25"><a href="#cb1-25" aria-hidden="true" tabindex="-1"></a> cosine_min_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-26"><a href="#cb1-26" aria-hidden="true" tabindex="-1"></a> cosine_constant_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-27"><a href="#cb1-27" aria-hidden="true" tabindex="-1"></a> loraplus_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-28"><a href="#cb1-28" aria-hidden="true" tabindex="-1"></a> loraplus_lr_embedding<span class="op">=</span><span class="fl">1e-06</span>,</span>
<span id="cb1-29"><a href="#cb1-29" aria-hidden="true" tabindex="-1"></a> embedding_lr_scale<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-30"><a href="#cb1-30" aria-hidden="true" tabindex="-1"></a> lr_groups<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-31"><a href="#cb1-31" aria-hidden="true" tabindex="-1"></a> embedding_lr<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-32"><a href="#cb1-32" aria-hidden="true" tabindex="-1"></a> qlora<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb1-33"><a href="#cb1-33" aria-hidden="true" tabindex="-1"></a> orpo_alpha<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-34"><a href="#cb1-34" aria-hidden="true" tabindex="-1"></a> lisa_n_layers<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-35"><a href="#cb1-35" aria-hidden="true" tabindex="-1"></a> lisa_step_interval<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-36"><a href="#cb1-36" aria-hidden="true" tabindex="-1"></a> lisa_layers_attribute<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-37"><a href="#cb1-37" aria-hidden="true" tabindex="-1"></a> curriculum_sampling<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-38"><a href="#cb1-38" aria-hidden="true" tabindex="-1"></a> alternate_optimizer<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-39"><a href="#cb1-39" aria-hidden="true" tabindex="-1"></a> alternate_lr_scheduler_type<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-40"><a href="#cb1-40" aria-hidden="true" tabindex="-1"></a> chat_template<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-41"><a href="#cb1-41" aria-hidden="true" tabindex="-1"></a> kd_ce_alpha<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-42"><a href="#cb1-42" aria-hidden="true" tabindex="-1"></a> kd_alpha<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb1-43"><a href="#cb1-43" aria-hidden="true" tabindex="-1"></a> kd_temperature<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb1-44"><a href="#cb1-44" aria-hidden="true" tabindex="-1"></a> kd_zscore_base_temp<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-45"><a href="#cb1-45" aria-hidden="true" tabindex="-1"></a> kd_top_k_before_softmax<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-46"><a href="#cb1-46" aria-hidden="true" tabindex="-1"></a> sequence_parallel_degree<span class="op">=</span><span class="dv">1</span>,</span>
<span id="cb1-47"><a href="#cb1-47" aria-hidden="true" tabindex="-1"></a> image_size<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-48"><a href="#cb1-48" aria-hidden="true" tabindex="-1"></a> image_resize_algorithm<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-49"><a href="#cb1-49" aria-hidden="true" tabindex="-1"></a> simpo_gamma<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb1-50"><a href="#cb1-50" aria-hidden="true" tabindex="-1"></a>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<p>CPO config for CPO training</p>
</section>
<section id="axolotl.core.training_args.AxolotlKTOConfig" class="level3">
@@ -565,48 +566,49 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
<span id="cb2-4"><a href="#cb2-4" aria-hidden="true" tabindex="-1"></a> lr_quadratic_warmup<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb2-5"><a href="#cb2-5" aria-hidden="true" tabindex="-1"></a> pretraining<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb2-6"><a href="#cb2-6" aria-hidden="true" tabindex="-1"></a> sample_packing<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb2-7"><a href="#cb2-7" aria-hidden="true" tabindex="-1"></a> multipack_real_batches<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb2-8"><a href="#cb2-8" aria-hidden="true" tabindex="-1"></a> eval_sample_packing<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-9"><a href="#cb2-9" aria-hidden="true" tabindex="-1"></a> sample_packing_efficiency<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb2-10"><a href="#cb2-10" aria-hidden="true" tabindex="-1"></a> sample_packing_bin_size<span class="op">=</span><span class="dv">200</span>,</span>
<span id="cb2-11"><a href="#cb2-11" aria-hidden="true" tabindex="-1"></a> sample_packing_group_size<span class="op">=</span><span class="dv">100000</span>,</span>
<span id="cb2-12"><a href="#cb2-12" aria-hidden="true" tabindex="-1"></a> max_seq_length<span class="op">=</span><span class="dv">2048</span>,</span>
<span id="cb2-13"><a href="#cb2-13" aria-hidden="true" tabindex="-1"></a> relora_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-14"><a href="#cb2-14" aria-hidden="true" tabindex="-1"></a> relora_warmup_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-15"><a href="#cb2-15" aria-hidden="true" tabindex="-1"></a> relora_anneal_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-16"><a href="#cb2-16" aria-hidden="true" tabindex="-1"></a> relora_prune_ratio<span class="op">=</span><span class="fl">0.9</span>,</span>
<span id="cb2-17"><a href="#cb2-17" aria-hidden="true" tabindex="-1"></a> bench_split<span class="op">=</span><span class="st">'eval'</span>,</span>
<span id="cb2-18"><a href="#cb2-18" aria-hidden="true" tabindex="-1"></a> bench_dataset<span class="op">=</span><span class="st">'pharaouk/dharma-1/dharma_1_mini.json'</span>,</span>
<span id="cb2-19"><a href="#cb2-19" aria-hidden="true" tabindex="-1"></a> do_bench_eval<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb2-20"><a href="#cb2-20" aria-hidden="true" tabindex="-1"></a> do_causal_lm_eval<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb2-21"><a href="#cb2-21" aria-hidden="true" tabindex="-1"></a> max_bench_samples<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-22"><a href="#cb2-22" aria-hidden="true" tabindex="-1"></a> bench_source_max_len<span class="op">=</span><span class="dv">2048</span>,</span>
<span id="cb2-23"><a href="#cb2-23" aria-hidden="true" tabindex="-1"></a> dataloader_prefetch_factor<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-24"><a href="#cb2-24" aria-hidden="true" tabindex="-1"></a> cosine_min_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-25"><a href="#cb2-25" aria-hidden="true" tabindex="-1"></a> cosine_constant_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-26"><a href="#cb2-26" aria-hidden="true" tabindex="-1"></a> loraplus_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-27"><a href="#cb2-27" aria-hidden="true" tabindex="-1"></a> loraplus_lr_embedding<span class="op">=</span><span class="fl">1e-06</span>,</span>
<span id="cb2-28"><a href="#cb2-28" aria-hidden="true" tabindex="-1"></a> embedding_lr_scale<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-29"><a href="#cb2-29" aria-hidden="true" tabindex="-1"></a> lr_groups<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-30"><a href="#cb2-30" aria-hidden="true" tabindex="-1"></a> embedding_lr<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-31"><a href="#cb2-31" aria-hidden="true" tabindex="-1"></a> qlora<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb2-32"><a href="#cb2-32" aria-hidden="true" tabindex="-1"></a> orpo_alpha<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-33"><a href="#cb2-33" aria-hidden="true" tabindex="-1"></a> lisa_n_layers<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-34"><a href="#cb2-34" aria-hidden="true" tabindex="-1"></a> lisa_step_interval<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-35"><a href="#cb2-35" aria-hidden="true" tabindex="-1"></a> lisa_layers_attribute<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-36"><a href="#cb2-36" aria-hidden="true" tabindex="-1"></a> curriculum_sampling<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-37"><a href="#cb2-37" aria-hidden="true" tabindex="-1"></a> alternate_optimizer<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-38"><a href="#cb2-38" aria-hidden="true" tabindex="-1"></a> alternate_lr_scheduler_type<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-39"><a href="#cb2-39" aria-hidden="true" tabindex="-1"></a> chat_template<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-40"><a href="#cb2-40" aria-hidden="true" tabindex="-1"></a> kd_ce_alpha<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-41"><a href="#cb2-41" aria-hidden="true" tabindex="-1"></a> kd_alpha<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb2-42"><a href="#cb2-42" aria-hidden="true" tabindex="-1"></a> kd_temperature<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb2-43"><a href="#cb2-43" aria-hidden="true" tabindex="-1"></a> kd_zscore_base_temp<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-44"><a href="#cb2-44" aria-hidden="true" tabindex="-1"></a> kd_top_k_before_softmax<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-45"><a href="#cb2-45" aria-hidden="true" tabindex="-1"></a> sequence_parallel_degree<span class="op">=</span><span class="dv">1</span>,</span>
<span id="cb2-46"><a href="#cb2-46" aria-hidden="true" tabindex="-1"></a> image_size<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-47"><a href="#cb2-47" aria-hidden="true" tabindex="-1"></a> image_resize_algorithm<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-48"><a href="#cb2-48" aria-hidden="true" tabindex="-1"></a>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<span id="cb2-7"><a href="#cb2-7" aria-hidden="true" tabindex="-1"></a> sample_packing_sequentially<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb2-8"><a href="#cb2-8" aria-hidden="true" tabindex="-1"></a> multipack_real_batches<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb2-9"><a href="#cb2-9" aria-hidden="true" tabindex="-1"></a> eval_sample_packing<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-10"><a href="#cb2-10" aria-hidden="true" tabindex="-1"></a> sample_packing_efficiency<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb2-11"><a href="#cb2-11" aria-hidden="true" tabindex="-1"></a> sample_packing_bin_size<span class="op">=</span><span class="dv">200</span>,</span>
<span id="cb2-12"><a href="#cb2-12" aria-hidden="true" tabindex="-1"></a> sample_packing_group_size<span class="op">=</span><span class="dv">100000</span>,</span>
<span id="cb2-13"><a href="#cb2-13" aria-hidden="true" tabindex="-1"></a> max_seq_length<span class="op">=</span><span class="dv">2048</span>,</span>
<span id="cb2-14"><a href="#cb2-14" aria-hidden="true" tabindex="-1"></a> relora_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-15"><a href="#cb2-15" aria-hidden="true" tabindex="-1"></a> relora_warmup_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-16"><a href="#cb2-16" aria-hidden="true" tabindex="-1"></a> relora_anneal_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-17"><a href="#cb2-17" aria-hidden="true" tabindex="-1"></a> relora_prune_ratio<span class="op">=</span><span class="fl">0.9</span>,</span>
<span id="cb2-18"><a href="#cb2-18" aria-hidden="true" tabindex="-1"></a> bench_split<span class="op">=</span><span class="st">'eval'</span>,</span>
<span id="cb2-19"><a href="#cb2-19" aria-hidden="true" tabindex="-1"></a> bench_dataset<span class="op">=</span><span class="st">'pharaouk/dharma-1/dharma_1_mini.json'</span>,</span>
<span id="cb2-20"><a href="#cb2-20" aria-hidden="true" tabindex="-1"></a> do_bench_eval<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb2-21"><a href="#cb2-21" aria-hidden="true" tabindex="-1"></a> do_causal_lm_eval<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb2-22"><a href="#cb2-22" aria-hidden="true" tabindex="-1"></a> max_bench_samples<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-23"><a href="#cb2-23" aria-hidden="true" tabindex="-1"></a> bench_source_max_len<span class="op">=</span><span class="dv">2048</span>,</span>
<span id="cb2-24"><a href="#cb2-24" aria-hidden="true" tabindex="-1"></a> dataloader_prefetch_factor<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-25"><a href="#cb2-25" aria-hidden="true" tabindex="-1"></a> cosine_min_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-26"><a href="#cb2-26" aria-hidden="true" tabindex="-1"></a> cosine_constant_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-27"><a href="#cb2-27" aria-hidden="true" tabindex="-1"></a> loraplus_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-28"><a href="#cb2-28" aria-hidden="true" tabindex="-1"></a> loraplus_lr_embedding<span class="op">=</span><span class="fl">1e-06</span>,</span>
<span id="cb2-29"><a href="#cb2-29" aria-hidden="true" tabindex="-1"></a> embedding_lr_scale<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-30"><a href="#cb2-30" aria-hidden="true" tabindex="-1"></a> lr_groups<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-31"><a href="#cb2-31" aria-hidden="true" tabindex="-1"></a> embedding_lr<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-32"><a href="#cb2-32" aria-hidden="true" tabindex="-1"></a> qlora<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb2-33"><a href="#cb2-33" aria-hidden="true" tabindex="-1"></a> orpo_alpha<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-34"><a href="#cb2-34" aria-hidden="true" tabindex="-1"></a> lisa_n_layers<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-35"><a href="#cb2-35" aria-hidden="true" tabindex="-1"></a> lisa_step_interval<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-36"><a href="#cb2-36" aria-hidden="true" tabindex="-1"></a> lisa_layers_attribute<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-37"><a href="#cb2-37" aria-hidden="true" tabindex="-1"></a> curriculum_sampling<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-38"><a href="#cb2-38" aria-hidden="true" tabindex="-1"></a> alternate_optimizer<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-39"><a href="#cb2-39" aria-hidden="true" tabindex="-1"></a> alternate_lr_scheduler_type<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-40"><a href="#cb2-40" aria-hidden="true" tabindex="-1"></a> chat_template<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-41"><a href="#cb2-41" aria-hidden="true" tabindex="-1"></a> kd_ce_alpha<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-42"><a href="#cb2-42" aria-hidden="true" tabindex="-1"></a> kd_alpha<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb2-43"><a href="#cb2-43" aria-hidden="true" tabindex="-1"></a> kd_temperature<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb2-44"><a href="#cb2-44" aria-hidden="true" tabindex="-1"></a> kd_zscore_base_temp<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-45"><a href="#cb2-45" aria-hidden="true" tabindex="-1"></a> kd_top_k_before_softmax<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-46"><a href="#cb2-46" aria-hidden="true" tabindex="-1"></a> sequence_parallel_degree<span class="op">=</span><span class="dv">1</span>,</span>
<span id="cb2-47"><a href="#cb2-47" aria-hidden="true" tabindex="-1"></a> image_size<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-48"><a href="#cb2-48" aria-hidden="true" tabindex="-1"></a> image_resize_algorithm<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb2-49"><a href="#cb2-49" aria-hidden="true" tabindex="-1"></a>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<p>KTO config for KTO training</p>
</section>
<section id="axolotl.core.training_args.AxolotlORPOConfig" class="level3">
@@ -617,48 +619,49 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
<span id="cb3-4"><a href="#cb3-4" aria-hidden="true" tabindex="-1"></a> lr_quadratic_warmup<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb3-5"><a href="#cb3-5" aria-hidden="true" tabindex="-1"></a> pretraining<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb3-6"><a href="#cb3-6" aria-hidden="true" tabindex="-1"></a> sample_packing<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb3-7"><a href="#cb3-7" aria-hidden="true" tabindex="-1"></a> multipack_real_batches<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb3-8"><a href="#cb3-8" aria-hidden="true" tabindex="-1"></a> eval_sample_packing<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-9"><a href="#cb3-9" aria-hidden="true" tabindex="-1"></a> sample_packing_efficiency<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb3-10"><a href="#cb3-10" aria-hidden="true" tabindex="-1"></a> sample_packing_bin_size<span class="op">=</span><span class="dv">200</span>,</span>
<span id="cb3-11"><a href="#cb3-11" aria-hidden="true" tabindex="-1"></a> sample_packing_group_size<span class="op">=</span><span class="dv">100000</span>,</span>
<span id="cb3-12"><a href="#cb3-12" aria-hidden="true" tabindex="-1"></a> max_seq_length<span class="op">=</span><span class="dv">2048</span>,</span>
<span id="cb3-13"><a href="#cb3-13" aria-hidden="true" tabindex="-1"></a> relora_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-14"><a href="#cb3-14" aria-hidden="true" tabindex="-1"></a> relora_warmup_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-15"><a href="#cb3-15" aria-hidden="true" tabindex="-1"></a> relora_anneal_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-16"><a href="#cb3-16" aria-hidden="true" tabindex="-1"></a> relora_prune_ratio<span class="op">=</span><span class="fl">0.9</span>,</span>
<span id="cb3-17"><a href="#cb3-17" aria-hidden="true" tabindex="-1"></a> bench_split<span class="op">=</span><span class="st">'eval'</span>,</span>
<span id="cb3-18"><a href="#cb3-18" aria-hidden="true" tabindex="-1"></a> bench_dataset<span class="op">=</span><span class="st">'pharaouk/dharma-1/dharma_1_mini.json'</span>,</span>
<span id="cb3-19"><a href="#cb3-19" aria-hidden="true" tabindex="-1"></a> do_bench_eval<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb3-20"><a href="#cb3-20" aria-hidden="true" tabindex="-1"></a> do_causal_lm_eval<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb3-21"><a href="#cb3-21" aria-hidden="true" tabindex="-1"></a> max_bench_samples<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-22"><a href="#cb3-22" aria-hidden="true" tabindex="-1"></a> bench_source_max_len<span class="op">=</span><span class="dv">2048</span>,</span>
<span id="cb3-23"><a href="#cb3-23" aria-hidden="true" tabindex="-1"></a> dataloader_prefetch_factor<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-24"><a href="#cb3-24" aria-hidden="true" tabindex="-1"></a> cosine_min_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-25"><a href="#cb3-25" aria-hidden="true" tabindex="-1"></a> cosine_constant_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-26"><a href="#cb3-26" aria-hidden="true" tabindex="-1"></a> loraplus_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-27"><a href="#cb3-27" aria-hidden="true" tabindex="-1"></a> loraplus_lr_embedding<span class="op">=</span><span class="fl">1e-06</span>,</span>
<span id="cb3-28"><a href="#cb3-28" aria-hidden="true" tabindex="-1"></a> embedding_lr_scale<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-29"><a href="#cb3-29" aria-hidden="true" tabindex="-1"></a> lr_groups<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-30"><a href="#cb3-30" aria-hidden="true" tabindex="-1"></a> embedding_lr<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-31"><a href="#cb3-31" aria-hidden="true" tabindex="-1"></a> qlora<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb3-32"><a href="#cb3-32" aria-hidden="true" tabindex="-1"></a> orpo_alpha<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-33"><a href="#cb3-33" aria-hidden="true" tabindex="-1"></a> lisa_n_layers<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-34"><a href="#cb3-34" aria-hidden="true" tabindex="-1"></a> lisa_step_interval<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-35"><a href="#cb3-35" aria-hidden="true" tabindex="-1"></a> lisa_layers_attribute<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-36"><a href="#cb3-36" aria-hidden="true" tabindex="-1"></a> curriculum_sampling<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-37"><a href="#cb3-37" aria-hidden="true" tabindex="-1"></a> alternate_optimizer<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-38"><a href="#cb3-38" aria-hidden="true" tabindex="-1"></a> alternate_lr_scheduler_type<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-39"><a href="#cb3-39" aria-hidden="true" tabindex="-1"></a> chat_template<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-40"><a href="#cb3-40" aria-hidden="true" tabindex="-1"></a> kd_ce_alpha<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-41"><a href="#cb3-41" aria-hidden="true" tabindex="-1"></a> kd_alpha<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb3-42"><a href="#cb3-42" aria-hidden="true" tabindex="-1"></a> kd_temperature<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb3-43"><a href="#cb3-43" aria-hidden="true" tabindex="-1"></a> kd_zscore_base_temp<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-44"><a href="#cb3-44" aria-hidden="true" tabindex="-1"></a> kd_top_k_before_softmax<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-45"><a href="#cb3-45" aria-hidden="true" tabindex="-1"></a> sequence_parallel_degree<span class="op">=</span><span class="dv">1</span>,</span>
<span id="cb3-46"><a href="#cb3-46" aria-hidden="true" tabindex="-1"></a> image_size<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-47"><a href="#cb3-47" aria-hidden="true" tabindex="-1"></a> image_resize_algorithm<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-48"><a href="#cb3-48" aria-hidden="true" tabindex="-1"></a>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<span id="cb3-7"><a href="#cb3-7" aria-hidden="true" tabindex="-1"></a> sample_packing_sequentially<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb3-8"><a href="#cb3-8" aria-hidden="true" tabindex="-1"></a> multipack_real_batches<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb3-9"><a href="#cb3-9" aria-hidden="true" tabindex="-1"></a> eval_sample_packing<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-10"><a href="#cb3-10" aria-hidden="true" tabindex="-1"></a> sample_packing_efficiency<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb3-11"><a href="#cb3-11" aria-hidden="true" tabindex="-1"></a> sample_packing_bin_size<span class="op">=</span><span class="dv">200</span>,</span>
<span id="cb3-12"><a href="#cb3-12" aria-hidden="true" tabindex="-1"></a> sample_packing_group_size<span class="op">=</span><span class="dv">100000</span>,</span>
<span id="cb3-13"><a href="#cb3-13" aria-hidden="true" tabindex="-1"></a> max_seq_length<span class="op">=</span><span class="dv">2048</span>,</span>
<span id="cb3-14"><a href="#cb3-14" aria-hidden="true" tabindex="-1"></a> relora_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-15"><a href="#cb3-15" aria-hidden="true" tabindex="-1"></a> relora_warmup_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-16"><a href="#cb3-16" aria-hidden="true" tabindex="-1"></a> relora_anneal_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-17"><a href="#cb3-17" aria-hidden="true" tabindex="-1"></a> relora_prune_ratio<span class="op">=</span><span class="fl">0.9</span>,</span>
<span id="cb3-18"><a href="#cb3-18" aria-hidden="true" tabindex="-1"></a> bench_split<span class="op">=</span><span class="st">'eval'</span>,</span>
<span id="cb3-19"><a href="#cb3-19" aria-hidden="true" tabindex="-1"></a> bench_dataset<span class="op">=</span><span class="st">'pharaouk/dharma-1/dharma_1_mini.json'</span>,</span>
<span id="cb3-20"><a href="#cb3-20" aria-hidden="true" tabindex="-1"></a> do_bench_eval<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb3-21"><a href="#cb3-21" aria-hidden="true" tabindex="-1"></a> do_causal_lm_eval<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb3-22"><a href="#cb3-22" aria-hidden="true" tabindex="-1"></a> max_bench_samples<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-23"><a href="#cb3-23" aria-hidden="true" tabindex="-1"></a> bench_source_max_len<span class="op">=</span><span class="dv">2048</span>,</span>
<span id="cb3-24"><a href="#cb3-24" aria-hidden="true" tabindex="-1"></a> dataloader_prefetch_factor<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-25"><a href="#cb3-25" aria-hidden="true" tabindex="-1"></a> cosine_min_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-26"><a href="#cb3-26" aria-hidden="true" tabindex="-1"></a> cosine_constant_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-27"><a href="#cb3-27" aria-hidden="true" tabindex="-1"></a> loraplus_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-28"><a href="#cb3-28" aria-hidden="true" tabindex="-1"></a> loraplus_lr_embedding<span class="op">=</span><span class="fl">1e-06</span>,</span>
<span id="cb3-29"><a href="#cb3-29" aria-hidden="true" tabindex="-1"></a> embedding_lr_scale<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-30"><a href="#cb3-30" aria-hidden="true" tabindex="-1"></a> lr_groups<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-31"><a href="#cb3-31" aria-hidden="true" tabindex="-1"></a> embedding_lr<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-32"><a href="#cb3-32" aria-hidden="true" tabindex="-1"></a> qlora<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb3-33"><a href="#cb3-33" aria-hidden="true" tabindex="-1"></a> orpo_alpha<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-34"><a href="#cb3-34" aria-hidden="true" tabindex="-1"></a> lisa_n_layers<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-35"><a href="#cb3-35" aria-hidden="true" tabindex="-1"></a> lisa_step_interval<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-36"><a href="#cb3-36" aria-hidden="true" tabindex="-1"></a> lisa_layers_attribute<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-37"><a href="#cb3-37" aria-hidden="true" tabindex="-1"></a> curriculum_sampling<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-38"><a href="#cb3-38" aria-hidden="true" tabindex="-1"></a> alternate_optimizer<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-39"><a href="#cb3-39" aria-hidden="true" tabindex="-1"></a> alternate_lr_scheduler_type<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-40"><a href="#cb3-40" aria-hidden="true" tabindex="-1"></a> chat_template<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-41"><a href="#cb3-41" aria-hidden="true" tabindex="-1"></a> kd_ce_alpha<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-42"><a href="#cb3-42" aria-hidden="true" tabindex="-1"></a> kd_alpha<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb3-43"><a href="#cb3-43" aria-hidden="true" tabindex="-1"></a> kd_temperature<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb3-44"><a href="#cb3-44" aria-hidden="true" tabindex="-1"></a> kd_zscore_base_temp<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-45"><a href="#cb3-45" aria-hidden="true" tabindex="-1"></a> kd_top_k_before_softmax<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-46"><a href="#cb3-46" aria-hidden="true" tabindex="-1"></a> sequence_parallel_degree<span class="op">=</span><span class="dv">1</span>,</span>
<span id="cb3-47"><a href="#cb3-47" aria-hidden="true" tabindex="-1"></a> image_size<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-48"><a href="#cb3-48" aria-hidden="true" tabindex="-1"></a> image_resize_algorithm<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb3-49"><a href="#cb3-49" aria-hidden="true" tabindex="-1"></a>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<p>ORPO config for ORPO training</p>
</section>
<section id="axolotl.core.training_args.AxolotlPRMConfig" class="level3">
@@ -669,48 +672,49 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
<span id="cb4-4"><a href="#cb4-4" aria-hidden="true" tabindex="-1"></a> lr_quadratic_warmup<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb4-5"><a href="#cb4-5" aria-hidden="true" tabindex="-1"></a> pretraining<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb4-6"><a href="#cb4-6" aria-hidden="true" tabindex="-1"></a> sample_packing<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb4-7"><a href="#cb4-7" aria-hidden="true" tabindex="-1"></a> multipack_real_batches<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb4-8"><a href="#cb4-8" aria-hidden="true" tabindex="-1"></a> eval_sample_packing<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-9"><a href="#cb4-9" aria-hidden="true" tabindex="-1"></a> sample_packing_efficiency<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb4-10"><a href="#cb4-10" aria-hidden="true" tabindex="-1"></a> sample_packing_bin_size<span class="op">=</span><span class="dv">200</span>,</span>
<span id="cb4-11"><a href="#cb4-11" aria-hidden="true" tabindex="-1"></a> sample_packing_group_size<span class="op">=</span><span class="dv">100000</span>,</span>
<span id="cb4-12"><a href="#cb4-12" aria-hidden="true" tabindex="-1"></a> max_seq_length<span class="op">=</span><span class="dv">2048</span>,</span>
<span id="cb4-13"><a href="#cb4-13" aria-hidden="true" tabindex="-1"></a> relora_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-14"><a href="#cb4-14" aria-hidden="true" tabindex="-1"></a> relora_warmup_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-15"><a href="#cb4-15" aria-hidden="true" tabindex="-1"></a> relora_anneal_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-16"><a href="#cb4-16" aria-hidden="true" tabindex="-1"></a> relora_prune_ratio<span class="op">=</span><span class="fl">0.9</span>,</span>
<span id="cb4-17"><a href="#cb4-17" aria-hidden="true" tabindex="-1"></a> bench_split<span class="op">=</span><span class="st">'eval'</span>,</span>
<span id="cb4-18"><a href="#cb4-18" aria-hidden="true" tabindex="-1"></a> bench_dataset<span class="op">=</span><span class="st">'pharaouk/dharma-1/dharma_1_mini.json'</span>,</span>
<span id="cb4-19"><a href="#cb4-19" aria-hidden="true" tabindex="-1"></a> do_bench_eval<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb4-20"><a href="#cb4-20" aria-hidden="true" tabindex="-1"></a> do_causal_lm_eval<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb4-21"><a href="#cb4-21" aria-hidden="true" tabindex="-1"></a> max_bench_samples<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-22"><a href="#cb4-22" aria-hidden="true" tabindex="-1"></a> bench_source_max_len<span class="op">=</span><span class="dv">2048</span>,</span>
<span id="cb4-23"><a href="#cb4-23" aria-hidden="true" tabindex="-1"></a> dataloader_prefetch_factor<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-24"><a href="#cb4-24" aria-hidden="true" tabindex="-1"></a> cosine_min_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-25"><a href="#cb4-25" aria-hidden="true" tabindex="-1"></a> cosine_constant_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-26"><a href="#cb4-26" aria-hidden="true" tabindex="-1"></a> loraplus_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-27"><a href="#cb4-27" aria-hidden="true" tabindex="-1"></a> loraplus_lr_embedding<span class="op">=</span><span class="fl">1e-06</span>,</span>
<span id="cb4-28"><a href="#cb4-28" aria-hidden="true" tabindex="-1"></a> embedding_lr_scale<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-29"><a href="#cb4-29" aria-hidden="true" tabindex="-1"></a> lr_groups<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-30"><a href="#cb4-30" aria-hidden="true" tabindex="-1"></a> embedding_lr<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-31"><a href="#cb4-31" aria-hidden="true" tabindex="-1"></a> qlora<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb4-32"><a href="#cb4-32" aria-hidden="true" tabindex="-1"></a> orpo_alpha<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-33"><a href="#cb4-33" aria-hidden="true" tabindex="-1"></a> lisa_n_layers<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-34"><a href="#cb4-34" aria-hidden="true" tabindex="-1"></a> lisa_step_interval<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-35"><a href="#cb4-35" aria-hidden="true" tabindex="-1"></a> lisa_layers_attribute<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-36"><a href="#cb4-36" aria-hidden="true" tabindex="-1"></a> curriculum_sampling<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-37"><a href="#cb4-37" aria-hidden="true" tabindex="-1"></a> alternate_optimizer<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-38"><a href="#cb4-38" aria-hidden="true" tabindex="-1"></a> alternate_lr_scheduler_type<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-39"><a href="#cb4-39" aria-hidden="true" tabindex="-1"></a> chat_template<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-40"><a href="#cb4-40" aria-hidden="true" tabindex="-1"></a> kd_ce_alpha<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-41"><a href="#cb4-41" aria-hidden="true" tabindex="-1"></a> kd_alpha<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb4-42"><a href="#cb4-42" aria-hidden="true" tabindex="-1"></a> kd_temperature<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb4-43"><a href="#cb4-43" aria-hidden="true" tabindex="-1"></a> kd_zscore_base_temp<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-44"><a href="#cb4-44" aria-hidden="true" tabindex="-1"></a> kd_top_k_before_softmax<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-45"><a href="#cb4-45" aria-hidden="true" tabindex="-1"></a> sequence_parallel_degree<span class="op">=</span><span class="dv">1</span>,</span>
<span id="cb4-46"><a href="#cb4-46" aria-hidden="true" tabindex="-1"></a> image_size<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-47"><a href="#cb4-47" aria-hidden="true" tabindex="-1"></a> image_resize_algorithm<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-48"><a href="#cb4-48" aria-hidden="true" tabindex="-1"></a>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<span id="cb4-7"><a href="#cb4-7" aria-hidden="true" tabindex="-1"></a> sample_packing_sequentially<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb4-8"><a href="#cb4-8" aria-hidden="true" tabindex="-1"></a> multipack_real_batches<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb4-9"><a href="#cb4-9" aria-hidden="true" tabindex="-1"></a> eval_sample_packing<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-10"><a href="#cb4-10" aria-hidden="true" tabindex="-1"></a> sample_packing_efficiency<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb4-11"><a href="#cb4-11" aria-hidden="true" tabindex="-1"></a> sample_packing_bin_size<span class="op">=</span><span class="dv">200</span>,</span>
<span id="cb4-12"><a href="#cb4-12" aria-hidden="true" tabindex="-1"></a> sample_packing_group_size<span class="op">=</span><span class="dv">100000</span>,</span>
<span id="cb4-13"><a href="#cb4-13" aria-hidden="true" tabindex="-1"></a> max_seq_length<span class="op">=</span><span class="dv">2048</span>,</span>
<span id="cb4-14"><a href="#cb4-14" aria-hidden="true" tabindex="-1"></a> relora_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-15"><a href="#cb4-15" aria-hidden="true" tabindex="-1"></a> relora_warmup_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-16"><a href="#cb4-16" aria-hidden="true" tabindex="-1"></a> relora_anneal_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-17"><a href="#cb4-17" aria-hidden="true" tabindex="-1"></a> relora_prune_ratio<span class="op">=</span><span class="fl">0.9</span>,</span>
<span id="cb4-18"><a href="#cb4-18" aria-hidden="true" tabindex="-1"></a> bench_split<span class="op">=</span><span class="st">'eval'</span>,</span>
<span id="cb4-19"><a href="#cb4-19" aria-hidden="true" tabindex="-1"></a> bench_dataset<span class="op">=</span><span class="st">'pharaouk/dharma-1/dharma_1_mini.json'</span>,</span>
<span id="cb4-20"><a href="#cb4-20" aria-hidden="true" tabindex="-1"></a> do_bench_eval<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb4-21"><a href="#cb4-21" aria-hidden="true" tabindex="-1"></a> do_causal_lm_eval<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb4-22"><a href="#cb4-22" aria-hidden="true" tabindex="-1"></a> max_bench_samples<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-23"><a href="#cb4-23" aria-hidden="true" tabindex="-1"></a> bench_source_max_len<span class="op">=</span><span class="dv">2048</span>,</span>
<span id="cb4-24"><a href="#cb4-24" aria-hidden="true" tabindex="-1"></a> dataloader_prefetch_factor<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-25"><a href="#cb4-25" aria-hidden="true" tabindex="-1"></a> cosine_min_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-26"><a href="#cb4-26" aria-hidden="true" tabindex="-1"></a> cosine_constant_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-27"><a href="#cb4-27" aria-hidden="true" tabindex="-1"></a> loraplus_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-28"><a href="#cb4-28" aria-hidden="true" tabindex="-1"></a> loraplus_lr_embedding<span class="op">=</span><span class="fl">1e-06</span>,</span>
<span id="cb4-29"><a href="#cb4-29" aria-hidden="true" tabindex="-1"></a> embedding_lr_scale<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-30"><a href="#cb4-30" aria-hidden="true" tabindex="-1"></a> lr_groups<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-31"><a href="#cb4-31" aria-hidden="true" tabindex="-1"></a> embedding_lr<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-32"><a href="#cb4-32" aria-hidden="true" tabindex="-1"></a> qlora<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb4-33"><a href="#cb4-33" aria-hidden="true" tabindex="-1"></a> orpo_alpha<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-34"><a href="#cb4-34" aria-hidden="true" tabindex="-1"></a> lisa_n_layers<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-35"><a href="#cb4-35" aria-hidden="true" tabindex="-1"></a> lisa_step_interval<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-36"><a href="#cb4-36" aria-hidden="true" tabindex="-1"></a> lisa_layers_attribute<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-37"><a href="#cb4-37" aria-hidden="true" tabindex="-1"></a> curriculum_sampling<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-38"><a href="#cb4-38" aria-hidden="true" tabindex="-1"></a> alternate_optimizer<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-39"><a href="#cb4-39" aria-hidden="true" tabindex="-1"></a> alternate_lr_scheduler_type<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-40"><a href="#cb4-40" aria-hidden="true" tabindex="-1"></a> chat_template<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-41"><a href="#cb4-41" aria-hidden="true" tabindex="-1"></a> kd_ce_alpha<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-42"><a href="#cb4-42" aria-hidden="true" tabindex="-1"></a> kd_alpha<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb4-43"><a href="#cb4-43" aria-hidden="true" tabindex="-1"></a> kd_temperature<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb4-44"><a href="#cb4-44" aria-hidden="true" tabindex="-1"></a> kd_zscore_base_temp<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-45"><a href="#cb4-45" aria-hidden="true" tabindex="-1"></a> kd_top_k_before_softmax<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-46"><a href="#cb4-46" aria-hidden="true" tabindex="-1"></a> sequence_parallel_degree<span class="op">=</span><span class="dv">1</span>,</span>
<span id="cb4-47"><a href="#cb4-47" aria-hidden="true" tabindex="-1"></a> image_size<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-48"><a href="#cb4-48" aria-hidden="true" tabindex="-1"></a> image_resize_algorithm<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb4-49"><a href="#cb4-49" aria-hidden="true" tabindex="-1"></a>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<p>PRM config for PRM training</p>
</section>
<section id="axolotl.core.training_args.AxolotlRewardConfig" class="level3">
@@ -721,48 +725,49 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
<span id="cb5-4"><a href="#cb5-4" aria-hidden="true" tabindex="-1"></a> lr_quadratic_warmup<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb5-5"><a href="#cb5-5" aria-hidden="true" tabindex="-1"></a> pretraining<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb5-6"><a href="#cb5-6" aria-hidden="true" tabindex="-1"></a> sample_packing<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb5-7"><a href="#cb5-7" aria-hidden="true" tabindex="-1"></a> multipack_real_batches<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb5-8"><a href="#cb5-8" aria-hidden="true" tabindex="-1"></a> eval_sample_packing<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-9"><a href="#cb5-9" aria-hidden="true" tabindex="-1"></a> sample_packing_efficiency<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb5-10"><a href="#cb5-10" aria-hidden="true" tabindex="-1"></a> sample_packing_bin_size<span class="op">=</span><span class="dv">200</span>,</span>
<span id="cb5-11"><a href="#cb5-11" aria-hidden="true" tabindex="-1"></a> sample_packing_group_size<span class="op">=</span><span class="dv">100000</span>,</span>
<span id="cb5-12"><a href="#cb5-12" aria-hidden="true" tabindex="-1"></a> max_seq_length<span class="op">=</span><span class="dv">2048</span>,</span>
<span id="cb5-13"><a href="#cb5-13" aria-hidden="true" tabindex="-1"></a> relora_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-14"><a href="#cb5-14" aria-hidden="true" tabindex="-1"></a> relora_warmup_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-15"><a href="#cb5-15" aria-hidden="true" tabindex="-1"></a> relora_anneal_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-16"><a href="#cb5-16" aria-hidden="true" tabindex="-1"></a> relora_prune_ratio<span class="op">=</span><span class="fl">0.9</span>,</span>
<span id="cb5-17"><a href="#cb5-17" aria-hidden="true" tabindex="-1"></a> bench_split<span class="op">=</span><span class="st">'eval'</span>,</span>
<span id="cb5-18"><a href="#cb5-18" aria-hidden="true" tabindex="-1"></a> bench_dataset<span class="op">=</span><span class="st">'pharaouk/dharma-1/dharma_1_mini.json'</span>,</span>
<span id="cb5-19"><a href="#cb5-19" aria-hidden="true" tabindex="-1"></a> do_bench_eval<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb5-20"><a href="#cb5-20" aria-hidden="true" tabindex="-1"></a> do_causal_lm_eval<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb5-21"><a href="#cb5-21" aria-hidden="true" tabindex="-1"></a> max_bench_samples<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-22"><a href="#cb5-22" aria-hidden="true" tabindex="-1"></a> bench_source_max_len<span class="op">=</span><span class="dv">2048</span>,</span>
<span id="cb5-23"><a href="#cb5-23" aria-hidden="true" tabindex="-1"></a> dataloader_prefetch_factor<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-24"><a href="#cb5-24" aria-hidden="true" tabindex="-1"></a> cosine_min_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-25"><a href="#cb5-25" aria-hidden="true" tabindex="-1"></a> cosine_constant_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-26"><a href="#cb5-26" aria-hidden="true" tabindex="-1"></a> loraplus_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-27"><a href="#cb5-27" aria-hidden="true" tabindex="-1"></a> loraplus_lr_embedding<span class="op">=</span><span class="fl">1e-06</span>,</span>
<span id="cb5-28"><a href="#cb5-28" aria-hidden="true" tabindex="-1"></a> embedding_lr_scale<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-29"><a href="#cb5-29" aria-hidden="true" tabindex="-1"></a> lr_groups<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-30"><a href="#cb5-30" aria-hidden="true" tabindex="-1"></a> embedding_lr<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-31"><a href="#cb5-31" aria-hidden="true" tabindex="-1"></a> qlora<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb5-32"><a href="#cb5-32" aria-hidden="true" tabindex="-1"></a> orpo_alpha<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-33"><a href="#cb5-33" aria-hidden="true" tabindex="-1"></a> lisa_n_layers<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-34"><a href="#cb5-34" aria-hidden="true" tabindex="-1"></a> lisa_step_interval<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-35"><a href="#cb5-35" aria-hidden="true" tabindex="-1"></a> lisa_layers_attribute<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-36"><a href="#cb5-36" aria-hidden="true" tabindex="-1"></a> curriculum_sampling<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-37"><a href="#cb5-37" aria-hidden="true" tabindex="-1"></a> alternate_optimizer<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-38"><a href="#cb5-38" aria-hidden="true" tabindex="-1"></a> alternate_lr_scheduler_type<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-39"><a href="#cb5-39" aria-hidden="true" tabindex="-1"></a> chat_template<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-40"><a href="#cb5-40" aria-hidden="true" tabindex="-1"></a> kd_ce_alpha<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-41"><a href="#cb5-41" aria-hidden="true" tabindex="-1"></a> kd_alpha<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb5-42"><a href="#cb5-42" aria-hidden="true" tabindex="-1"></a> kd_temperature<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb5-43"><a href="#cb5-43" aria-hidden="true" tabindex="-1"></a> kd_zscore_base_temp<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-44"><a href="#cb5-44" aria-hidden="true" tabindex="-1"></a> kd_top_k_before_softmax<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-45"><a href="#cb5-45" aria-hidden="true" tabindex="-1"></a> sequence_parallel_degree<span class="op">=</span><span class="dv">1</span>,</span>
<span id="cb5-46"><a href="#cb5-46" aria-hidden="true" tabindex="-1"></a> image_size<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-47"><a href="#cb5-47" aria-hidden="true" tabindex="-1"></a> image_resize_algorithm<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-48"><a href="#cb5-48" aria-hidden="true" tabindex="-1"></a>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<span id="cb5-7"><a href="#cb5-7" aria-hidden="true" tabindex="-1"></a> sample_packing_sequentially<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb5-8"><a href="#cb5-8" aria-hidden="true" tabindex="-1"></a> multipack_real_batches<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb5-9"><a href="#cb5-9" aria-hidden="true" tabindex="-1"></a> eval_sample_packing<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-10"><a href="#cb5-10" aria-hidden="true" tabindex="-1"></a> sample_packing_efficiency<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb5-11"><a href="#cb5-11" aria-hidden="true" tabindex="-1"></a> sample_packing_bin_size<span class="op">=</span><span class="dv">200</span>,</span>
<span id="cb5-12"><a href="#cb5-12" aria-hidden="true" tabindex="-1"></a> sample_packing_group_size<span class="op">=</span><span class="dv">100000</span>,</span>
<span id="cb5-13"><a href="#cb5-13" aria-hidden="true" tabindex="-1"></a> max_seq_length<span class="op">=</span><span class="dv">2048</span>,</span>
<span id="cb5-14"><a href="#cb5-14" aria-hidden="true" tabindex="-1"></a> relora_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-15"><a href="#cb5-15" aria-hidden="true" tabindex="-1"></a> relora_warmup_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-16"><a href="#cb5-16" aria-hidden="true" tabindex="-1"></a> relora_anneal_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-17"><a href="#cb5-17" aria-hidden="true" tabindex="-1"></a> relora_prune_ratio<span class="op">=</span><span class="fl">0.9</span>,</span>
<span id="cb5-18"><a href="#cb5-18" aria-hidden="true" tabindex="-1"></a> bench_split<span class="op">=</span><span class="st">'eval'</span>,</span>
<span id="cb5-19"><a href="#cb5-19" aria-hidden="true" tabindex="-1"></a> bench_dataset<span class="op">=</span><span class="st">'pharaouk/dharma-1/dharma_1_mini.json'</span>,</span>
<span id="cb5-20"><a href="#cb5-20" aria-hidden="true" tabindex="-1"></a> do_bench_eval<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb5-21"><a href="#cb5-21" aria-hidden="true" tabindex="-1"></a> do_causal_lm_eval<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb5-22"><a href="#cb5-22" aria-hidden="true" tabindex="-1"></a> max_bench_samples<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-23"><a href="#cb5-23" aria-hidden="true" tabindex="-1"></a> bench_source_max_len<span class="op">=</span><span class="dv">2048</span>,</span>
<span id="cb5-24"><a href="#cb5-24" aria-hidden="true" tabindex="-1"></a> dataloader_prefetch_factor<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-25"><a href="#cb5-25" aria-hidden="true" tabindex="-1"></a> cosine_min_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-26"><a href="#cb5-26" aria-hidden="true" tabindex="-1"></a> cosine_constant_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-27"><a href="#cb5-27" aria-hidden="true" tabindex="-1"></a> loraplus_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-28"><a href="#cb5-28" aria-hidden="true" tabindex="-1"></a> loraplus_lr_embedding<span class="op">=</span><span class="fl">1e-06</span>,</span>
<span id="cb5-29"><a href="#cb5-29" aria-hidden="true" tabindex="-1"></a> embedding_lr_scale<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-30"><a href="#cb5-30" aria-hidden="true" tabindex="-1"></a> lr_groups<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-31"><a href="#cb5-31" aria-hidden="true" tabindex="-1"></a> embedding_lr<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-32"><a href="#cb5-32" aria-hidden="true" tabindex="-1"></a> qlora<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb5-33"><a href="#cb5-33" aria-hidden="true" tabindex="-1"></a> orpo_alpha<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-34"><a href="#cb5-34" aria-hidden="true" tabindex="-1"></a> lisa_n_layers<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-35"><a href="#cb5-35" aria-hidden="true" tabindex="-1"></a> lisa_step_interval<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-36"><a href="#cb5-36" aria-hidden="true" tabindex="-1"></a> lisa_layers_attribute<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-37"><a href="#cb5-37" aria-hidden="true" tabindex="-1"></a> curriculum_sampling<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-38"><a href="#cb5-38" aria-hidden="true" tabindex="-1"></a> alternate_optimizer<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-39"><a href="#cb5-39" aria-hidden="true" tabindex="-1"></a> alternate_lr_scheduler_type<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-40"><a href="#cb5-40" aria-hidden="true" tabindex="-1"></a> chat_template<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-41"><a href="#cb5-41" aria-hidden="true" tabindex="-1"></a> kd_ce_alpha<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-42"><a href="#cb5-42" aria-hidden="true" tabindex="-1"></a> kd_alpha<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb5-43"><a href="#cb5-43" aria-hidden="true" tabindex="-1"></a> kd_temperature<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb5-44"><a href="#cb5-44" aria-hidden="true" tabindex="-1"></a> kd_zscore_base_temp<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-45"><a href="#cb5-45" aria-hidden="true" tabindex="-1"></a> kd_top_k_before_softmax<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-46"><a href="#cb5-46" aria-hidden="true" tabindex="-1"></a> sequence_parallel_degree<span class="op">=</span><span class="dv">1</span>,</span>
<span id="cb5-47"><a href="#cb5-47" aria-hidden="true" tabindex="-1"></a> image_size<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-48"><a href="#cb5-48" aria-hidden="true" tabindex="-1"></a> image_resize_algorithm<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb5-49"><a href="#cb5-49" aria-hidden="true" tabindex="-1"></a>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<p>Reward config for Reward training</p>
</section>
<section id="axolotl.core.training_args.AxolotlTrainingArguments" class="level3">
@@ -773,48 +778,49 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
<span id="cb6-4"><a href="#cb6-4" aria-hidden="true" tabindex="-1"></a> lr_quadratic_warmup<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb6-5"><a href="#cb6-5" aria-hidden="true" tabindex="-1"></a> pretraining<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb6-6"><a href="#cb6-6" aria-hidden="true" tabindex="-1"></a> sample_packing<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb6-7"><a href="#cb6-7" aria-hidden="true" tabindex="-1"></a> multipack_real_batches<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb6-8"><a href="#cb6-8" aria-hidden="true" tabindex="-1"></a> eval_sample_packing<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-9"><a href="#cb6-9" aria-hidden="true" tabindex="-1"></a> sample_packing_efficiency<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb6-10"><a href="#cb6-10" aria-hidden="true" tabindex="-1"></a> sample_packing_bin_size<span class="op">=</span><span class="dv">200</span>,</span>
<span id="cb6-11"><a href="#cb6-11" aria-hidden="true" tabindex="-1"></a> sample_packing_group_size<span class="op">=</span><span class="dv">100000</span>,</span>
<span id="cb6-12"><a href="#cb6-12" aria-hidden="true" tabindex="-1"></a> max_seq_length<span class="op">=</span><span class="dv">2048</span>,</span>
<span id="cb6-13"><a href="#cb6-13" aria-hidden="true" tabindex="-1"></a> relora_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-14"><a href="#cb6-14" aria-hidden="true" tabindex="-1"></a> relora_warmup_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-15"><a href="#cb6-15" aria-hidden="true" tabindex="-1"></a> relora_anneal_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-16"><a href="#cb6-16" aria-hidden="true" tabindex="-1"></a> relora_prune_ratio<span class="op">=</span><span class="fl">0.9</span>,</span>
<span id="cb6-17"><a href="#cb6-17" aria-hidden="true" tabindex="-1"></a> bench_split<span class="op">=</span><span class="st">'eval'</span>,</span>
<span id="cb6-18"><a href="#cb6-18" aria-hidden="true" tabindex="-1"></a> bench_dataset<span class="op">=</span><span class="st">'pharaouk/dharma-1/dharma_1_mini.json'</span>,</span>
<span id="cb6-19"><a href="#cb6-19" aria-hidden="true" tabindex="-1"></a> do_bench_eval<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb6-20"><a href="#cb6-20" aria-hidden="true" tabindex="-1"></a> do_causal_lm_eval<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb6-21"><a href="#cb6-21" aria-hidden="true" tabindex="-1"></a> max_bench_samples<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-22"><a href="#cb6-22" aria-hidden="true" tabindex="-1"></a> bench_source_max_len<span class="op">=</span><span class="dv">2048</span>,</span>
<span id="cb6-23"><a href="#cb6-23" aria-hidden="true" tabindex="-1"></a> dataloader_prefetch_factor<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-24"><a href="#cb6-24" aria-hidden="true" tabindex="-1"></a> cosine_min_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-25"><a href="#cb6-25" aria-hidden="true" tabindex="-1"></a> cosine_constant_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-26"><a href="#cb6-26" aria-hidden="true" tabindex="-1"></a> loraplus_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-27"><a href="#cb6-27" aria-hidden="true" tabindex="-1"></a> loraplus_lr_embedding<span class="op">=</span><span class="fl">1e-06</span>,</span>
<span id="cb6-28"><a href="#cb6-28" aria-hidden="true" tabindex="-1"></a> embedding_lr_scale<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-29"><a href="#cb6-29" aria-hidden="true" tabindex="-1"></a> lr_groups<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-30"><a href="#cb6-30" aria-hidden="true" tabindex="-1"></a> embedding_lr<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-31"><a href="#cb6-31" aria-hidden="true" tabindex="-1"></a> qlora<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb6-32"><a href="#cb6-32" aria-hidden="true" tabindex="-1"></a> orpo_alpha<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-33"><a href="#cb6-33" aria-hidden="true" tabindex="-1"></a> lisa_n_layers<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-34"><a href="#cb6-34" aria-hidden="true" tabindex="-1"></a> lisa_step_interval<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-35"><a href="#cb6-35" aria-hidden="true" tabindex="-1"></a> lisa_layers_attribute<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-36"><a href="#cb6-36" aria-hidden="true" tabindex="-1"></a> curriculum_sampling<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-37"><a href="#cb6-37" aria-hidden="true" tabindex="-1"></a> alternate_optimizer<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-38"><a href="#cb6-38" aria-hidden="true" tabindex="-1"></a> alternate_lr_scheduler_type<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-39"><a href="#cb6-39" aria-hidden="true" tabindex="-1"></a> chat_template<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-40"><a href="#cb6-40" aria-hidden="true" tabindex="-1"></a> kd_ce_alpha<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-41"><a href="#cb6-41" aria-hidden="true" tabindex="-1"></a> kd_alpha<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb6-42"><a href="#cb6-42" aria-hidden="true" tabindex="-1"></a> kd_temperature<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb6-43"><a href="#cb6-43" aria-hidden="true" tabindex="-1"></a> kd_zscore_base_temp<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-44"><a href="#cb6-44" aria-hidden="true" tabindex="-1"></a> kd_top_k_before_softmax<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-45"><a href="#cb6-45" aria-hidden="true" tabindex="-1"></a> sequence_parallel_degree<span class="op">=</span><span class="dv">1</span>,</span>
<span id="cb6-46"><a href="#cb6-46" aria-hidden="true" tabindex="-1"></a> image_size<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-47"><a href="#cb6-47" aria-hidden="true" tabindex="-1"></a> image_resize_algorithm<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-48"><a href="#cb6-48" aria-hidden="true" tabindex="-1"></a>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<span id="cb6-7"><a href="#cb6-7" aria-hidden="true" tabindex="-1"></a> sample_packing_sequentially<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb6-8"><a href="#cb6-8" aria-hidden="true" tabindex="-1"></a> multipack_real_batches<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb6-9"><a href="#cb6-9" aria-hidden="true" tabindex="-1"></a> eval_sample_packing<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-10"><a href="#cb6-10" aria-hidden="true" tabindex="-1"></a> sample_packing_efficiency<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb6-11"><a href="#cb6-11" aria-hidden="true" tabindex="-1"></a> sample_packing_bin_size<span class="op">=</span><span class="dv">200</span>,</span>
<span id="cb6-12"><a href="#cb6-12" aria-hidden="true" tabindex="-1"></a> sample_packing_group_size<span class="op">=</span><span class="dv">100000</span>,</span>
<span id="cb6-13"><a href="#cb6-13" aria-hidden="true" tabindex="-1"></a> max_seq_length<span class="op">=</span><span class="dv">2048</span>,</span>
<span id="cb6-14"><a href="#cb6-14" aria-hidden="true" tabindex="-1"></a> relora_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-15"><a href="#cb6-15" aria-hidden="true" tabindex="-1"></a> relora_warmup_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-16"><a href="#cb6-16" aria-hidden="true" tabindex="-1"></a> relora_anneal_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-17"><a href="#cb6-17" aria-hidden="true" tabindex="-1"></a> relora_prune_ratio<span class="op">=</span><span class="fl">0.9</span>,</span>
<span id="cb6-18"><a href="#cb6-18" aria-hidden="true" tabindex="-1"></a> bench_split<span class="op">=</span><span class="st">'eval'</span>,</span>
<span id="cb6-19"><a href="#cb6-19" aria-hidden="true" tabindex="-1"></a> bench_dataset<span class="op">=</span><span class="st">'pharaouk/dharma-1/dharma_1_mini.json'</span>,</span>
<span id="cb6-20"><a href="#cb6-20" aria-hidden="true" tabindex="-1"></a> do_bench_eval<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb6-21"><a href="#cb6-21" aria-hidden="true" tabindex="-1"></a> do_causal_lm_eval<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb6-22"><a href="#cb6-22" aria-hidden="true" tabindex="-1"></a> max_bench_samples<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-23"><a href="#cb6-23" aria-hidden="true" tabindex="-1"></a> bench_source_max_len<span class="op">=</span><span class="dv">2048</span>,</span>
<span id="cb6-24"><a href="#cb6-24" aria-hidden="true" tabindex="-1"></a> dataloader_prefetch_factor<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-25"><a href="#cb6-25" aria-hidden="true" tabindex="-1"></a> cosine_min_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-26"><a href="#cb6-26" aria-hidden="true" tabindex="-1"></a> cosine_constant_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-27"><a href="#cb6-27" aria-hidden="true" tabindex="-1"></a> loraplus_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-28"><a href="#cb6-28" aria-hidden="true" tabindex="-1"></a> loraplus_lr_embedding<span class="op">=</span><span class="fl">1e-06</span>,</span>
<span id="cb6-29"><a href="#cb6-29" aria-hidden="true" tabindex="-1"></a> embedding_lr_scale<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-30"><a href="#cb6-30" aria-hidden="true" tabindex="-1"></a> lr_groups<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-31"><a href="#cb6-31" aria-hidden="true" tabindex="-1"></a> embedding_lr<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-32"><a href="#cb6-32" aria-hidden="true" tabindex="-1"></a> qlora<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb6-33"><a href="#cb6-33" aria-hidden="true" tabindex="-1"></a> orpo_alpha<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-34"><a href="#cb6-34" aria-hidden="true" tabindex="-1"></a> lisa_n_layers<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-35"><a href="#cb6-35" aria-hidden="true" tabindex="-1"></a> lisa_step_interval<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-36"><a href="#cb6-36" aria-hidden="true" tabindex="-1"></a> lisa_layers_attribute<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-37"><a href="#cb6-37" aria-hidden="true" tabindex="-1"></a> curriculum_sampling<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-38"><a href="#cb6-38" aria-hidden="true" tabindex="-1"></a> alternate_optimizer<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-39"><a href="#cb6-39" aria-hidden="true" tabindex="-1"></a> alternate_lr_scheduler_type<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-40"><a href="#cb6-40" aria-hidden="true" tabindex="-1"></a> chat_template<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-41"><a href="#cb6-41" aria-hidden="true" tabindex="-1"></a> kd_ce_alpha<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-42"><a href="#cb6-42" aria-hidden="true" tabindex="-1"></a> kd_alpha<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb6-43"><a href="#cb6-43" aria-hidden="true" tabindex="-1"></a> kd_temperature<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb6-44"><a href="#cb6-44" aria-hidden="true" tabindex="-1"></a> kd_zscore_base_temp<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-45"><a href="#cb6-45" aria-hidden="true" tabindex="-1"></a> kd_top_k_before_softmax<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-46"><a href="#cb6-46" aria-hidden="true" tabindex="-1"></a> sequence_parallel_degree<span class="op">=</span><span class="dv">1</span>,</span>
<span id="cb6-47"><a href="#cb6-47" aria-hidden="true" tabindex="-1"></a> image_size<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-48"><a href="#cb6-48" aria-hidden="true" tabindex="-1"></a> image_resize_algorithm<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb6-49"><a href="#cb6-49" aria-hidden="true" tabindex="-1"></a>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<p>Training arguments for Causal trainer</p>
<p>This code is duplicated due to HF TrainingArguments not setting output_dir with a
default value so it cant be used as a mixin.</p>
@@ -827,48 +833,49 @@ default value so it cant be used as a mixin.</p>
<span id="cb7-4"><a href="#cb7-4" aria-hidden="true" tabindex="-1"></a> lr_quadratic_warmup<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb7-5"><a href="#cb7-5" aria-hidden="true" tabindex="-1"></a> pretraining<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb7-6"><a href="#cb7-6" aria-hidden="true" tabindex="-1"></a> sample_packing<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb7-7"><a href="#cb7-7" aria-hidden="true" tabindex="-1"></a> multipack_real_batches<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb7-8"><a href="#cb7-8" aria-hidden="true" tabindex="-1"></a> eval_sample_packing<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-9"><a href="#cb7-9" aria-hidden="true" tabindex="-1"></a> sample_packing_efficiency<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb7-10"><a href="#cb7-10" aria-hidden="true" tabindex="-1"></a> sample_packing_bin_size<span class="op">=</span><span class="dv">200</span>,</span>
<span id="cb7-11"><a href="#cb7-11" aria-hidden="true" tabindex="-1"></a> sample_packing_group_size<span class="op">=</span><span class="dv">100000</span>,</span>
<span id="cb7-12"><a href="#cb7-12" aria-hidden="true" tabindex="-1"></a> max_seq_length<span class="op">=</span><span class="dv">2048</span>,</span>
<span id="cb7-13"><a href="#cb7-13" aria-hidden="true" tabindex="-1"></a> relora_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-14"><a href="#cb7-14" aria-hidden="true" tabindex="-1"></a> relora_warmup_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-15"><a href="#cb7-15" aria-hidden="true" tabindex="-1"></a> relora_anneal_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-16"><a href="#cb7-16" aria-hidden="true" tabindex="-1"></a> relora_prune_ratio<span class="op">=</span><span class="fl">0.9</span>,</span>
<span id="cb7-17"><a href="#cb7-17" aria-hidden="true" tabindex="-1"></a> bench_split<span class="op">=</span><span class="st">'eval'</span>,</span>
<span id="cb7-18"><a href="#cb7-18" aria-hidden="true" tabindex="-1"></a> bench_dataset<span class="op">=</span><span class="st">'pharaouk/dharma-1/dharma_1_mini.json'</span>,</span>
<span id="cb7-19"><a href="#cb7-19" aria-hidden="true" tabindex="-1"></a> do_bench_eval<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb7-20"><a href="#cb7-20" aria-hidden="true" tabindex="-1"></a> do_causal_lm_eval<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb7-21"><a href="#cb7-21" aria-hidden="true" tabindex="-1"></a> max_bench_samples<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-22"><a href="#cb7-22" aria-hidden="true" tabindex="-1"></a> bench_source_max_len<span class="op">=</span><span class="dv">2048</span>,</span>
<span id="cb7-23"><a href="#cb7-23" aria-hidden="true" tabindex="-1"></a> dataloader_prefetch_factor<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-24"><a href="#cb7-24" aria-hidden="true" tabindex="-1"></a> cosine_min_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-25"><a href="#cb7-25" aria-hidden="true" tabindex="-1"></a> cosine_constant_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-26"><a href="#cb7-26" aria-hidden="true" tabindex="-1"></a> loraplus_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-27"><a href="#cb7-27" aria-hidden="true" tabindex="-1"></a> loraplus_lr_embedding<span class="op">=</span><span class="fl">1e-06</span>,</span>
<span id="cb7-28"><a href="#cb7-28" aria-hidden="true" tabindex="-1"></a> embedding_lr_scale<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-29"><a href="#cb7-29" aria-hidden="true" tabindex="-1"></a> lr_groups<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-30"><a href="#cb7-30" aria-hidden="true" tabindex="-1"></a> embedding_lr<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-31"><a href="#cb7-31" aria-hidden="true" tabindex="-1"></a> qlora<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb7-32"><a href="#cb7-32" aria-hidden="true" tabindex="-1"></a> orpo_alpha<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-33"><a href="#cb7-33" aria-hidden="true" tabindex="-1"></a> lisa_n_layers<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-34"><a href="#cb7-34" aria-hidden="true" tabindex="-1"></a> lisa_step_interval<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-35"><a href="#cb7-35" aria-hidden="true" tabindex="-1"></a> lisa_layers_attribute<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-36"><a href="#cb7-36" aria-hidden="true" tabindex="-1"></a> curriculum_sampling<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-37"><a href="#cb7-37" aria-hidden="true" tabindex="-1"></a> alternate_optimizer<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-38"><a href="#cb7-38" aria-hidden="true" tabindex="-1"></a> alternate_lr_scheduler_type<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-39"><a href="#cb7-39" aria-hidden="true" tabindex="-1"></a> chat_template<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-40"><a href="#cb7-40" aria-hidden="true" tabindex="-1"></a> kd_ce_alpha<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-41"><a href="#cb7-41" aria-hidden="true" tabindex="-1"></a> kd_alpha<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb7-42"><a href="#cb7-42" aria-hidden="true" tabindex="-1"></a> kd_temperature<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb7-43"><a href="#cb7-43" aria-hidden="true" tabindex="-1"></a> kd_zscore_base_temp<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-44"><a href="#cb7-44" aria-hidden="true" tabindex="-1"></a> kd_top_k_before_softmax<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-45"><a href="#cb7-45" aria-hidden="true" tabindex="-1"></a> sequence_parallel_degree<span class="op">=</span><span class="dv">1</span>,</span>
<span id="cb7-46"><a href="#cb7-46" aria-hidden="true" tabindex="-1"></a> image_size<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-47"><a href="#cb7-47" aria-hidden="true" tabindex="-1"></a> image_resize_algorithm<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-48"><a href="#cb7-48" aria-hidden="true" tabindex="-1"></a>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<span id="cb7-7"><a href="#cb7-7" aria-hidden="true" tabindex="-1"></a> sample_packing_sequentially<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb7-8"><a href="#cb7-8" aria-hidden="true" tabindex="-1"></a> multipack_real_batches<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb7-9"><a href="#cb7-9" aria-hidden="true" tabindex="-1"></a> eval_sample_packing<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-10"><a href="#cb7-10" aria-hidden="true" tabindex="-1"></a> sample_packing_efficiency<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb7-11"><a href="#cb7-11" aria-hidden="true" tabindex="-1"></a> sample_packing_bin_size<span class="op">=</span><span class="dv">200</span>,</span>
<span id="cb7-12"><a href="#cb7-12" aria-hidden="true" tabindex="-1"></a> sample_packing_group_size<span class="op">=</span><span class="dv">100000</span>,</span>
<span id="cb7-13"><a href="#cb7-13" aria-hidden="true" tabindex="-1"></a> max_seq_length<span class="op">=</span><span class="dv">2048</span>,</span>
<span id="cb7-14"><a href="#cb7-14" aria-hidden="true" tabindex="-1"></a> relora_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-15"><a href="#cb7-15" aria-hidden="true" tabindex="-1"></a> relora_warmup_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-16"><a href="#cb7-16" aria-hidden="true" tabindex="-1"></a> relora_anneal_steps<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-17"><a href="#cb7-17" aria-hidden="true" tabindex="-1"></a> relora_prune_ratio<span class="op">=</span><span class="fl">0.9</span>,</span>
<span id="cb7-18"><a href="#cb7-18" aria-hidden="true" tabindex="-1"></a> bench_split<span class="op">=</span><span class="st">'eval'</span>,</span>
<span id="cb7-19"><a href="#cb7-19" aria-hidden="true" tabindex="-1"></a> bench_dataset<span class="op">=</span><span class="st">'pharaouk/dharma-1/dharma_1_mini.json'</span>,</span>
<span id="cb7-20"><a href="#cb7-20" aria-hidden="true" tabindex="-1"></a> do_bench_eval<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb7-21"><a href="#cb7-21" aria-hidden="true" tabindex="-1"></a> do_causal_lm_eval<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb7-22"><a href="#cb7-22" aria-hidden="true" tabindex="-1"></a> max_bench_samples<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-23"><a href="#cb7-23" aria-hidden="true" tabindex="-1"></a> bench_source_max_len<span class="op">=</span><span class="dv">2048</span>,</span>
<span id="cb7-24"><a href="#cb7-24" aria-hidden="true" tabindex="-1"></a> dataloader_prefetch_factor<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-25"><a href="#cb7-25" aria-hidden="true" tabindex="-1"></a> cosine_min_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-26"><a href="#cb7-26" aria-hidden="true" tabindex="-1"></a> cosine_constant_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-27"><a href="#cb7-27" aria-hidden="true" tabindex="-1"></a> loraplus_lr_ratio<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-28"><a href="#cb7-28" aria-hidden="true" tabindex="-1"></a> loraplus_lr_embedding<span class="op">=</span><span class="fl">1e-06</span>,</span>
<span id="cb7-29"><a href="#cb7-29" aria-hidden="true" tabindex="-1"></a> embedding_lr_scale<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-30"><a href="#cb7-30" aria-hidden="true" tabindex="-1"></a> lr_groups<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-31"><a href="#cb7-31" aria-hidden="true" tabindex="-1"></a> embedding_lr<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-32"><a href="#cb7-32" aria-hidden="true" tabindex="-1"></a> qlora<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb7-33"><a href="#cb7-33" aria-hidden="true" tabindex="-1"></a> orpo_alpha<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-34"><a href="#cb7-34" aria-hidden="true" tabindex="-1"></a> lisa_n_layers<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-35"><a href="#cb7-35" aria-hidden="true" tabindex="-1"></a> lisa_step_interval<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-36"><a href="#cb7-36" aria-hidden="true" tabindex="-1"></a> lisa_layers_attribute<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-37"><a href="#cb7-37" aria-hidden="true" tabindex="-1"></a> curriculum_sampling<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-38"><a href="#cb7-38" aria-hidden="true" tabindex="-1"></a> alternate_optimizer<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-39"><a href="#cb7-39" aria-hidden="true" tabindex="-1"></a> alternate_lr_scheduler_type<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-40"><a href="#cb7-40" aria-hidden="true" tabindex="-1"></a> chat_template<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-41"><a href="#cb7-41" aria-hidden="true" tabindex="-1"></a> kd_ce_alpha<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-42"><a href="#cb7-42" aria-hidden="true" tabindex="-1"></a> kd_alpha<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb7-43"><a href="#cb7-43" aria-hidden="true" tabindex="-1"></a> kd_temperature<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb7-44"><a href="#cb7-44" aria-hidden="true" tabindex="-1"></a> kd_zscore_base_temp<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-45"><a href="#cb7-45" aria-hidden="true" tabindex="-1"></a> kd_top_k_before_softmax<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-46"><a href="#cb7-46" aria-hidden="true" tabindex="-1"></a> sequence_parallel_degree<span class="op">=</span><span class="dv">1</span>,</span>
<span id="cb7-47"><a href="#cb7-47" aria-hidden="true" tabindex="-1"></a> image_size<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-48"><a href="#cb7-48" aria-hidden="true" tabindex="-1"></a> image_resize_algorithm<span class="op">=</span><span class="va">None</span>,</span>
<span id="cb7-49"><a href="#cb7-49" aria-hidden="true" tabindex="-1"></a>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<p>Mixin class for the Axolotl training args.</p>

View File

@@ -549,10 +549,14 @@ ul.task-list li input[type="checkbox"] {
<td>Utility methods for axolotl CLI.</td>
</tr>
<tr class="odd">
<td><a href="../../docs/api/cli.vllm_serve.html#axolotl.cli.vllm_serve">cli.vllm_serve</a></td>
<td>CLI to start the vllm server for online RL</td>
</tr>
<tr class="even">
<td><a href="../../docs/api/cli.cloud.base.html#axolotl.cli.cloud.base">cli.cloud.base</a></td>
<td>base class for cloud platforms from cli</td>
</tr>
<tr class="even">
<tr class="odd">
<td><a href="../../docs/api/cli.cloud.modal_.html#axolotl.cli.cloud.modal_">cli.cloud.modal_</a></td>
<td>Modal Cloud support from CLI</td>
</tr>

View File

@@ -444,6 +444,10 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
<ul class="collapse">
<li><a href="#axolotl.utils.samplers.multipack.MultipackBatchSampler" id="toc-axolotl.utils.samplers.multipack.MultipackBatchSampler" class="nav-link" data-scroll-target="#axolotl.utils.samplers.multipack.MultipackBatchSampler">MultipackBatchSampler</a></li>
</ul></li>
<li><a href="#functions" id="toc-functions" class="nav-link" data-scroll-target="#functions">Functions</a>
<ul class="collapse">
<li><a href="#axolotl.utils.samplers.multipack.allocate_sequentially" id="toc-axolotl.utils.samplers.multipack.allocate_sequentially" class="nav-link" data-scroll-target="#axolotl.utils.samplers.multipack.allocate_sequentially">allocate_sequentially</a></li>
</ul></li>
</ul></li>
</ul>
</nav>
@@ -485,9 +489,41 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
<span id="cb1-7"><a href="#cb1-7" aria-hidden="true" tabindex="-1"></a> packing_efficiency_estimate<span class="op">=</span><span class="fl">1.0</span>,</span>
<span id="cb1-8"><a href="#cb1-8" aria-hidden="true" tabindex="-1"></a> drop_last<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb1-9"><a href="#cb1-9" aria-hidden="true" tabindex="-1"></a> num_count_samples<span class="op">=</span><span class="dv">16</span>,</span>
<span id="cb1-10"><a href="#cb1-10" aria-hidden="true" tabindex="-1"></a> <span class="op">**</span>kwargs,</span>
<span id="cb1-11"><a href="#cb1-11" aria-hidden="true" tabindex="-1"></a>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<span id="cb1-10"><a href="#cb1-10" aria-hidden="true" tabindex="-1"></a> sequential<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb1-11"><a href="#cb1-11" aria-hidden="true" tabindex="-1"></a> <span class="op">**</span>kwargs,</span>
<span id="cb1-12"><a href="#cb1-12" aria-hidden="true" tabindex="-1"></a>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<p>Batch sampler class for multipack</p>
</section>
</section>
<section id="functions" class="level2">
<h2 class="anchored" data-anchor-id="functions">Functions</h2>
<table class="caption-top table">
<thead>
<tr class="header">
<th>Name</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr class="odd">
<td><a href="#axolotl.utils.samplers.multipack.allocate_sequentially">allocate_sequentially</a></td>
<td>Sequential allocator that preserves example order</td>
</tr>
</tbody>
</table>
<section id="axolotl.utils.samplers.multipack.allocate_sequentially" class="level3">
<h3 class="anchored" data-anchor-id="axolotl.utils.samplers.multipack.allocate_sequentially">allocate_sequentially</h3>
<div class="sourceCode" 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>utils.samplers.multipack.allocate_sequentially(lengths, rank, c, n)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<p>Sequential allocator that preserves example order</p>
<p>Parameters:
- lengths: The lengths of all examples
- rank: The current rank (for distributed training)
- c: The capacity of each bin (maximum sequence length)
- n: Number of ranks</p>
<p>Returns:
- result: List of batches for the current rank
- total_used: Number of actual example tokens
- total_slots: Maximum theoretical number of example tokens (number of bins * bin capacity)</p>
</section>

View File

@@ -698,10 +698,10 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
<span id="cb1-232"><a href="#cb1-232" aria-hidden="true" tabindex="-1"></a><span class="co"># grpo</span></span>
<span id="cb1-233"><a href="#cb1-233" aria-hidden="true" tabindex="-1"></a><span class="fu">trl</span><span class="kw">:</span></span>
<span id="cb1-234"><a href="#cb1-234" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">use_vllm</span><span class="kw">:</span><span class="co"> # Optional[bool]. Whether to use VLLM for RL training.</span></span>
<span id="cb1-235"><a href="#cb1-235" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">vllm_device</span><span class="kw">:</span><span class="co"> # Optional[str]. Device to use for VLLM.</span></span>
<span id="cb1-236"><a href="#cb1-236" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">vllm_gpu_memory_utilization</span><span class="kw">:</span><span class="co"> # Optional[float]. GPU memory utilization for VLLM.</span></span>
<span id="cb1-237"><a href="#cb1-237" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">vllm_max_model_len</span><span class="kw">:</span><span class="co"> # Optional[int]. Maximum length of the model for VLLM.</span></span>
<span id="cb1-238"><a href="#cb1-238" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">vllm_dtype</span><span class="kw">:</span><span class="co"> # Optional[str]. Data type for VLLM.</span></span>
<span id="cb1-235"><a href="#cb1-235" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">vllm_server_host</span><span class="kw">:</span><span class="co"> # Optional[str]. Host of the vLLM server to connect to.</span></span>
<span id="cb1-236"><a href="#cb1-236" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">vllm_server_port</span><span class="kw">:</span><span class="co"> # Optional[int]. Port of the vLLM server to connect to.</span></span>
<span id="cb1-237"><a href="#cb1-237" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">vllm_server_timeout</span><span class="kw">:</span><span class="co"> # Optional[int]. Total timeout (in seconds) to wait for the vLLM server to respond.</span></span>
<span id="cb1-238"><a href="#cb1-238" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">vllm_guided_decoding_regex</span><span class="kw">:</span><span class="co"> # Optional[str]. Regex for vLLM guided decoding.</span></span>
<span id="cb1-239"><a href="#cb1-239" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb1-240"><a href="#cb1-240" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">beta</span><span class="kw">:</span><span class="co"> # Optional[float]. Beta parameter for the RL training. Same as `rl_beta`. Use</span></span>
<span id="cb1-241"><a href="#cb1-241" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">max_completion_length</span><span class="kw">:</span><span class="co"> # Optional[int]. Maximum length of the completion for RL training.</span></span>
@@ -1047,95 +1047,100 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
<span id="cb1-581"><a href="#cb1-581" aria-hidden="true" tabindex="-1"></a><span class="co"># currently only supported on Llama and Mistral</span></span>
<span id="cb1-582"><a href="#cb1-582" aria-hidden="true" tabindex="-1"></a><span class="fu">neftune_noise_alpha</span><span class="kw">:</span></span>
<span id="cb1-583"><a href="#cb1-583" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb1-584"><a href="#cb1-584" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to bettertransformers</span></span>
<span id="cb1-584"><a href="#cb1-584" aria-hidden="true" tabindex="-1"></a><span class="co"># Optional[bool]. Whether to bettertransformers</span></span>
<span id="cb1-585"><a href="#cb1-585" aria-hidden="true" tabindex="-1"></a><span class="fu">flash_optimum</span><span class="kw">:</span></span>
<span id="cb1-586"><a href="#cb1-586" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to use xformers attention patch https://github.com/facebookresearch/xformers:</span></span>
<span id="cb1-587"><a href="#cb1-587" aria-hidden="true" tabindex="-1"></a><span class="fu">xformers_attention</span><span class="kw">:</span></span>
<span id="cb1-588"><a href="#cb1-588" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to use flash attention patch https://github.com/Dao-AILab/flash-attention:</span></span>
<span id="cb1-589"><a href="#cb1-589" aria-hidden="true" tabindex="-1"></a><span class="fu">flash_attention</span><span class="kw">:</span></span>
<span id="cb1-590"><a href="#cb1-590" aria-hidden="true" tabindex="-1"></a><span class="fu">flash_attn_cross_entropy</span><span class="kw">:</span><span class="co"> # Whether to use flash-attention cross entropy implementation - advanced use only</span></span>
<span id="cb1-591"><a href="#cb1-591" aria-hidden="true" tabindex="-1"></a><span class="fu">flash_attn_rms_norm</span><span class="kw">:</span><span class="co"> # Whether to use flash-attention rms norm implementation - advanced use only</span></span>
<span id="cb1-592"><a href="#cb1-592" aria-hidden="true" tabindex="-1"></a><span class="fu">flash_attn_fuse_qkv</span><span class="kw">:</span><span class="co"> # Whether to fuse QKV into a single operation</span></span>
<span id="cb1-593"><a href="#cb1-593" aria-hidden="true" tabindex="-1"></a><span class="fu">flash_attn_fuse_mlp</span><span class="kw">:</span><span class="co"> # Whether to fuse part of the MLP into a single operation</span></span>
<span id="cb1-594"><a href="#cb1-594" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to use scaled-dot-product attention</span></span>
<span id="cb1-595"><a href="#cb1-595" aria-hidden="true" tabindex="-1"></a><span class="co"># https://pytorch.org/docs/stable/generated/torch.nn.functional.scaled_dot_product_attention.html</span></span>
<span id="cb1-596"><a href="#cb1-596" aria-hidden="true" tabindex="-1"></a><span class="fu">sdp_attention</span><span class="kw">:</span></span>
<span id="cb1-597"><a href="#cb1-597" aria-hidden="true" tabindex="-1"></a><span class="co"># Shifted-sparse attention (only llama) - https://arxiv.org/pdf/2309.12307.pdf</span></span>
<span id="cb1-598"><a href="#cb1-598" aria-hidden="true" tabindex="-1"></a><span class="fu">s2_attention</span><span class="kw">:</span></span>
<span id="cb1-599"><a href="#cb1-599" aria-hidden="true" tabindex="-1"></a><span class="co"># Optional[bool]. Whether to use low_cpu_mem_usage</span></span>
<span id="cb1-600"><a href="#cb1-600" aria-hidden="true" tabindex="-1"></a><span class="fu">low_cpu_mem_usage</span><span class="kw">:</span></span>
<span id="cb1-601"><a href="#cb1-601" aria-hidden="true" tabindex="-1"></a><span class="co"># Resume from a specific checkpoint dir</span></span>
<span id="cb1-602"><a href="#cb1-602" aria-hidden="true" tabindex="-1"></a><span class="fu">resume_from_checkpoint</span><span class="kw">:</span></span>
<span id="cb1-603"><a href="#cb1-603" aria-hidden="true" tabindex="-1"></a><span class="co"># If resume_from_checkpoint isn't set and you simply want it to start where it left off.</span></span>
<span id="cb1-604"><a href="#cb1-604" aria-hidden="true" tabindex="-1"></a><span class="co"># Be careful with this being turned on between different models.</span></span>
<span id="cb1-605"><a href="#cb1-605" aria-hidden="true" tabindex="-1"></a><span class="fu">auto_resume_from_checkpoints</span><span class="kw">:</span><span class="at"> </span><span class="ch">false</span></span>
<span id="cb1-606"><a href="#cb1-606" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb1-607"><a href="#cb1-607" aria-hidden="true" tabindex="-1"></a><span class="co">## Multimodal section</span></span>
<span id="cb1-608"><a href="#cb1-608" aria-hidden="true" tabindex="-1"></a><span class="co"># int | tuple[int, int] | None . Size to resize images to, width x height.</span></span>
<span id="cb1-609"><a href="#cb1-609" aria-hidden="true" tabindex="-1"></a><span class="co"># Will read from model/processor config if not set.</span></span>
<span id="cb1-610"><a href="#cb1-610" aria-hidden="true" tabindex="-1"></a><span class="fu">image_size</span><span class="kw">:</span></span>
<span id="cb1-611"><a href="#cb1-611" aria-hidden="true" tabindex="-1"></a><span class="co"># str. Algorithm to use for image resizing. "bilinear", "bicubic", "lanczos". Default is "bilinear".</span></span>
<span id="cb1-612"><a href="#cb1-612" aria-hidden="true" tabindex="-1"></a><span class="fu">image_resize_algorithm</span><span class="kw">:</span><span class="at"> </span><span class="st">'bilinear'</span></span>
<span id="cb1-613"><a href="#cb1-613" aria-hidden="true" tabindex="-1"></a><span class="co">## End of multimodal section</span></span>
<span id="cb1-614"><a href="#cb1-614" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb1-615"><a href="#cb1-615" aria-hidden="true" tabindex="-1"></a><span class="co"># Don't mess with this, it's here for accelerate and torchrun</span></span>
<span id="cb1-616"><a href="#cb1-616" aria-hidden="true" tabindex="-1"></a><span class="fu">local_rank</span><span class="kw">:</span></span>
<span id="cb1-617"><a href="#cb1-617" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb1-618"><a href="#cb1-618" aria-hidden="true" tabindex="-1"></a><span class="co"># Add or change special tokens.</span></span>
<span id="cb1-619"><a href="#cb1-619" aria-hidden="true" tabindex="-1"></a><span class="co"># If you add tokens here, you don't need to add them to the `tokens` list.</span></span>
<span id="cb1-620"><a href="#cb1-620" aria-hidden="true" tabindex="-1"></a><span class="fu">special_tokens</span><span class="kw">:</span></span>
<span id="cb1-621"><a href="#cb1-621" aria-hidden="true" tabindex="-1"></a><span class="co"> # bos_token: "&lt;s&gt;"</span></span>
<span id="cb1-622"><a href="#cb1-622" aria-hidden="true" tabindex="-1"></a><span class="co"> # eos_token: "&lt;/s&gt;"</span></span>
<span id="cb1-623"><a href="#cb1-623" aria-hidden="true" tabindex="-1"></a><span class="co"> # unk_token: "&lt;unk&gt;"</span></span>
<span id="cb1-624"><a href="#cb1-624" aria-hidden="true" tabindex="-1"></a><span class="co"> # pad_token: "[PAD]"</span></span>
<span id="cb1-625"><a href="#cb1-625" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb1-626"><a href="#cb1-626" aria-hidden="true" tabindex="-1"></a><span class="co"># Add extra tokens.</span></span>
<span id="cb1-627"><a href="#cb1-627" aria-hidden="true" tabindex="-1"></a><span class="fu">tokens</span><span class="kw">:</span></span>
<span id="cb1-628"><a href="#cb1-628" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb1-629"><a href="#cb1-629" aria-hidden="true" tabindex="-1"></a><span class="co"># Mapping token_id to new_token_string to override reserved added_tokens in the tokenizer.</span></span>
<span id="cb1-630"><a href="#cb1-630" aria-hidden="true" tabindex="-1"></a><span class="co"># Only works for tokens that are not part of the base vocab (aka are added_tokens).</span></span>
<span id="cb1-631"><a href="#cb1-631" aria-hidden="true" tabindex="-1"></a><span class="co"># Can be checked if they exist in tokenizer.json added_tokens.</span></span>
<span id="cb1-632"><a href="#cb1-632" aria-hidden="true" tabindex="-1"></a><span class="fu">added_tokens_overrides</span><span class="kw">:</span><span class="co"> # Dict[int, str]</span></span>
<span id="cb1-633"><a href="#cb1-633" aria-hidden="true" tabindex="-1"></a><span class="co"># 128041: "&lt;|im_start|&gt;"</span></span>
<span id="cb1-634"><a href="#cb1-634" aria-hidden="true" tabindex="-1"></a><span class="co"># 128042: "&lt;|im_end|&gt;"</span></span>
<span id="cb1-635"><a href="#cb1-635" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb1-636"><a href="#cb1-636" aria-hidden="true" tabindex="-1"></a><span class="co"># FSDP</span></span>
<span id="cb1-637"><a href="#cb1-637" aria-hidden="true" tabindex="-1"></a><span class="fu">fsdp</span><span class="kw">:</span></span>
<span id="cb1-638"><a href="#cb1-638" aria-hidden="true" tabindex="-1"></a><span class="fu">fsdp_config</span><span class="kw">:</span></span>
<span id="cb1-639"><a href="#cb1-639" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb1-640"><a href="#cb1-640" aria-hidden="true" tabindex="-1"></a><span class="co"># Deepspeed config path. e.g., deepspeed_configs/zero3.json</span></span>
<span id="cb1-641"><a href="#cb1-641" aria-hidden="true" tabindex="-1"></a><span class="fu">deepspeed</span><span class="kw">:</span></span>
<span id="cb1-642"><a href="#cb1-642" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb1-643"><a href="#cb1-643" aria-hidden="true" tabindex="-1"></a><span class="co"># Advanced DDP Arguments</span></span>
<span id="cb1-644"><a href="#cb1-644" aria-hidden="true" tabindex="-1"></a><span class="fu">ddp_timeout</span><span class="kw">:</span></span>
<span id="cb1-645"><a href="#cb1-645" aria-hidden="true" tabindex="-1"></a><span class="fu">ddp_bucket_cap_mb</span><span class="kw">:</span></span>
<span id="cb1-646"><a href="#cb1-646" aria-hidden="true" tabindex="-1"></a><span class="fu">ddp_broadcast_buffers</span><span class="kw">:</span></span>
<span id="cb1-586"><a href="#cb1-586" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb1-587"><a href="#cb1-587" aria-hidden="true" tabindex="-1"></a><span class="co"># Note: Only one of the following attention patches can be used at a time.</span></span>
<span id="cb1-588"><a href="#cb1-588" aria-hidden="true" tabindex="-1"></a><span class="co"># For example, if you set `xformers_attention` to `true`, do not set `flash_attention` to `true`.</span></span>
<span id="cb1-589"><a href="#cb1-589" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb1-590"><a href="#cb1-590" aria-hidden="true" tabindex="-1"></a><span class="co"># Optional[bool]. Whether to use xformers attention patch https://github.com/facebookresearch/xformers:</span></span>
<span id="cb1-591"><a href="#cb1-591" aria-hidden="true" tabindex="-1"></a><span class="fu">xformers_attention</span><span class="kw">:</span></span>
<span id="cb1-592"><a href="#cb1-592" aria-hidden="true" tabindex="-1"></a><span class="co"># Optional[bool]. Whether to use flash attention patch https://github.com/Dao-AILab/flash-attention:</span></span>
<span id="cb1-593"><a href="#cb1-593" aria-hidden="true" tabindex="-1"></a><span class="fu">flash_attention</span><span class="kw">:</span></span>
<span id="cb1-594"><a href="#cb1-594" aria-hidden="true" tabindex="-1"></a><span class="fu">flash_attn_cross_entropy</span><span class="kw">:</span><span class="co"> # Optional[bool]. Whether to use flash-attention cross entropy implementation - advanced use only</span></span>
<span id="cb1-595"><a href="#cb1-595" aria-hidden="true" tabindex="-1"></a><span class="fu">flash_attn_rms_norm</span><span class="kw">:</span><span class="co"> # Optional[bool]. Whether to use flash-attention rms norm implementation - advanced use only</span></span>
<span id="cb1-596"><a href="#cb1-596" aria-hidden="true" tabindex="-1"></a><span class="fu">flash_attn_fuse_qkv</span><span class="kw">:</span><span class="co"> # Optional[bool]. Whether to fuse QKV into a single operation</span></span>
<span id="cb1-597"><a href="#cb1-597" aria-hidden="true" tabindex="-1"></a><span class="fu">flash_attn_fuse_mlp</span><span class="kw">:</span><span class="co"> # Optional[bool]. Whether to fuse part of the MLP into a single operation</span></span>
<span id="cb1-598"><a href="#cb1-598" aria-hidden="true" tabindex="-1"></a><span class="co"># Optional[bool]. Whether to use scaled-dot-product attention</span></span>
<span id="cb1-599"><a href="#cb1-599" aria-hidden="true" tabindex="-1"></a><span class="co"># https://pytorch.org/docs/stable/generated/torch.nn.functional.scaled_dot_product_attention.html</span></span>
<span id="cb1-600"><a href="#cb1-600" aria-hidden="true" tabindex="-1"></a><span class="fu">sdp_attention</span><span class="kw">:</span></span>
<span id="cb1-601"><a href="#cb1-601" aria-hidden="true" tabindex="-1"></a><span class="co"># Optional[bool]. Shifted-sparse attention (only llama) - https://arxiv.org/pdf/2309.12307.pdf</span></span>
<span id="cb1-602"><a href="#cb1-602" aria-hidden="true" tabindex="-1"></a><span class="fu">s2_attention</span><span class="kw">:</span></span>
<span id="cb1-603"><a href="#cb1-603" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb1-604"><a href="#cb1-604" aria-hidden="true" tabindex="-1"></a><span class="co"># Optional[bool]. Whether to use low_cpu_mem_usage</span></span>
<span id="cb1-605"><a href="#cb1-605" aria-hidden="true" tabindex="-1"></a><span class="fu">low_cpu_mem_usage</span><span class="kw">:</span></span>
<span id="cb1-606"><a href="#cb1-606" aria-hidden="true" tabindex="-1"></a><span class="co"># Optional[str]. Resume from a specific checkpoint dir</span></span>
<span id="cb1-607"><a href="#cb1-607" aria-hidden="true" tabindex="-1"></a><span class="fu">resume_from_checkpoint</span><span class="kw">:</span></span>
<span id="cb1-608"><a href="#cb1-608" aria-hidden="true" tabindex="-1"></a><span class="co"># Optional[bool]. If resume_from_checkpoint isn't set and you simply want it to start where it left off.</span></span>
<span id="cb1-609"><a href="#cb1-609" aria-hidden="true" tabindex="-1"></a><span class="co"># Be careful with this being turned on between different models.</span></span>
<span id="cb1-610"><a href="#cb1-610" aria-hidden="true" tabindex="-1"></a><span class="fu">auto_resume_from_checkpoints</span><span class="kw">:</span><span class="at"> </span><span class="ch">false</span></span>
<span id="cb1-611"><a href="#cb1-611" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb1-612"><a href="#cb1-612" aria-hidden="true" tabindex="-1"></a><span class="co">## Multimodal section</span></span>
<span id="cb1-613"><a href="#cb1-613" aria-hidden="true" tabindex="-1"></a><span class="co"># int | tuple[int, int] | None . Size to resize images to, width x height.</span></span>
<span id="cb1-614"><a href="#cb1-614" aria-hidden="true" tabindex="-1"></a><span class="co"># Will read from model/processor config if not set.</span></span>
<span id="cb1-615"><a href="#cb1-615" aria-hidden="true" tabindex="-1"></a><span class="fu">image_size</span><span class="kw">:</span></span>
<span id="cb1-616"><a href="#cb1-616" aria-hidden="true" tabindex="-1"></a><span class="co"># str. Algorithm to use for image resizing. "bilinear", "bicubic", "lanczos". Default is "bilinear".</span></span>
<span id="cb1-617"><a href="#cb1-617" aria-hidden="true" tabindex="-1"></a><span class="fu">image_resize_algorithm</span><span class="kw">:</span><span class="at"> </span><span class="st">'bilinear'</span></span>
<span id="cb1-618"><a href="#cb1-618" aria-hidden="true" tabindex="-1"></a><span class="co">## End of multimodal section</span></span>
<span id="cb1-619"><a href="#cb1-619" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb1-620"><a href="#cb1-620" aria-hidden="true" tabindex="-1"></a><span class="co"># Don't mess with this, it's here for accelerate and torchrun</span></span>
<span id="cb1-621"><a href="#cb1-621" aria-hidden="true" tabindex="-1"></a><span class="fu">local_rank</span><span class="kw">:</span></span>
<span id="cb1-622"><a href="#cb1-622" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb1-623"><a href="#cb1-623" aria-hidden="true" tabindex="-1"></a><span class="co"># Add or change special tokens.</span></span>
<span id="cb1-624"><a href="#cb1-624" aria-hidden="true" tabindex="-1"></a><span class="co"># If you add tokens here, you don't need to add them to the `tokens` list.</span></span>
<span id="cb1-625"><a href="#cb1-625" aria-hidden="true" tabindex="-1"></a><span class="fu">special_tokens</span><span class="kw">:</span></span>
<span id="cb1-626"><a href="#cb1-626" aria-hidden="true" tabindex="-1"></a><span class="co"> # bos_token: "&lt;s&gt;"</span></span>
<span id="cb1-627"><a href="#cb1-627" aria-hidden="true" tabindex="-1"></a><span class="co"> # eos_token: "&lt;/s&gt;"</span></span>
<span id="cb1-628"><a href="#cb1-628" aria-hidden="true" tabindex="-1"></a><span class="co"> # unk_token: "&lt;unk&gt;"</span></span>
<span id="cb1-629"><a href="#cb1-629" aria-hidden="true" tabindex="-1"></a><span class="co"> # pad_token: "[PAD]"</span></span>
<span id="cb1-630"><a href="#cb1-630" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb1-631"><a href="#cb1-631" aria-hidden="true" tabindex="-1"></a><span class="co"># Add extra tokens.</span></span>
<span id="cb1-632"><a href="#cb1-632" aria-hidden="true" tabindex="-1"></a><span class="fu">tokens</span><span class="kw">:</span></span>
<span id="cb1-633"><a href="#cb1-633" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb1-634"><a href="#cb1-634" aria-hidden="true" tabindex="-1"></a><span class="co"># Mapping token_id to new_token_string to override reserved added_tokens in the tokenizer.</span></span>
<span id="cb1-635"><a href="#cb1-635" aria-hidden="true" tabindex="-1"></a><span class="co"># Only works for tokens that are not part of the base vocab (aka are added_tokens).</span></span>
<span id="cb1-636"><a href="#cb1-636" aria-hidden="true" tabindex="-1"></a><span class="co"># Can be checked if they exist in tokenizer.json added_tokens.</span></span>
<span id="cb1-637"><a href="#cb1-637" aria-hidden="true" tabindex="-1"></a><span class="fu">added_tokens_overrides</span><span class="kw">:</span><span class="co"> # Dict[int, str]</span></span>
<span id="cb1-638"><a href="#cb1-638" aria-hidden="true" tabindex="-1"></a><span class="co"># 128041: "&lt;|im_start|&gt;"</span></span>
<span id="cb1-639"><a href="#cb1-639" aria-hidden="true" tabindex="-1"></a><span class="co"># 128042: "&lt;|im_end|&gt;"</span></span>
<span id="cb1-640"><a href="#cb1-640" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb1-641"><a href="#cb1-641" aria-hidden="true" tabindex="-1"></a><span class="co"># FSDP</span></span>
<span id="cb1-642"><a href="#cb1-642" aria-hidden="true" tabindex="-1"></a><span class="fu">fsdp</span><span class="kw">:</span></span>
<span id="cb1-643"><a href="#cb1-643" aria-hidden="true" tabindex="-1"></a><span class="fu">fsdp_config</span><span class="kw">:</span></span>
<span id="cb1-644"><a href="#cb1-644" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb1-645"><a href="#cb1-645" aria-hidden="true" tabindex="-1"></a><span class="co"># Deepspeed config path. e.g., deepspeed_configs/zero3.json</span></span>
<span id="cb1-646"><a href="#cb1-646" aria-hidden="true" tabindex="-1"></a><span class="fu">deepspeed</span><span class="kw">:</span></span>
<span id="cb1-647"><a href="#cb1-647" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb1-648"><a href="#cb1-648" aria-hidden="true" tabindex="-1"></a><span class="co"># Sequence parallelism</span></span>
<span id="cb1-649"><a href="#cb1-649" aria-hidden="true" tabindex="-1"></a><span class="co"># Set to a divisor of the number of GPUs available to split sequences into chunks of equal size.</span></span>
<span id="cb1-650"><a href="#cb1-650" aria-hidden="true" tabindex="-1"></a><span class="co"># Use in long context training to prevent OOM when sequences cannot fit into a single GPU's VRAM.</span></span>
<span id="cb1-651"><a href="#cb1-651" aria-hidden="true" tabindex="-1"></a><span class="co"># E.g., if 4 GPUs are available, set this value to 2 to split each sequence into two equal-sized</span></span>
<span id="cb1-652"><a href="#cb1-652" aria-hidden="true" tabindex="-1"></a><span class="co"># subsequences, or set to 4 to split into four equal-sized subsequences.</span></span>
<span id="cb1-653"><a href="#cb1-653" aria-hidden="true" tabindex="-1"></a><span class="co"># See https://axolotl-ai-cloud.github.io/axolotl/docs/sequence_parallelism.html for more details.</span></span>
<span id="cb1-654"><a href="#cb1-654" aria-hidden="true" tabindex="-1"></a><span class="fu">sequence_parallel_degree</span><span class="kw">:</span></span>
<span id="cb1-655"><a href="#cb1-655" aria-hidden="true" tabindex="-1"></a><span class="co"># Optional; strides across the key dimension. Larger values use more memory but should make training faster.</span></span>
<span id="cb1-656"><a href="#cb1-656" aria-hidden="true" tabindex="-1"></a><span class="co"># Must evenly divide the number of KV heads in your model.</span></span>
<span id="cb1-657"><a href="#cb1-657" aria-hidden="true" tabindex="-1"></a><span class="fu">heads_k_stride</span><span class="kw">:</span><span class="at"> </span><span class="dv">1</span></span>
<span id="cb1-658"><a href="#cb1-658" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb1-659"><a href="#cb1-659" aria-hidden="true" tabindex="-1"></a><span class="co"># Path to torch distx for optim 'adamw_anyprecision'</span></span>
<span id="cb1-660"><a href="#cb1-660" aria-hidden="true" tabindex="-1"></a><span class="fu">torchdistx_path</span><span class="kw">:</span></span>
<span id="cb1-661"><a href="#cb1-661" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb1-662"><a href="#cb1-662" aria-hidden="true" tabindex="-1"></a><span class="co"># Set to HF dataset for type: 'completion' for streaming instead of pre-tokenize</span></span>
<span id="cb1-663"><a href="#cb1-663" aria-hidden="true" tabindex="-1"></a><span class="fu">pretraining_dataset</span><span class="kw">:</span></span>
<span id="cb1-664"><a href="#cb1-664" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb1-665"><a href="#cb1-665" aria-hidden="true" tabindex="-1"></a><span class="co"># Debug mode</span></span>
<span id="cb1-666"><a href="#cb1-666" aria-hidden="true" tabindex="-1"></a><span class="fu">debug</span><span class="kw">:</span></span>
<span id="cb1-667"><a href="#cb1-667" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb1-668"><a href="#cb1-668" aria-hidden="true" tabindex="-1"></a><span class="co"># Seed</span></span>
<span id="cb1-669"><a href="#cb1-669" aria-hidden="true" tabindex="-1"></a><span class="fu">seed</span><span class="kw">:</span></span>
<span id="cb1-670"><a href="#cb1-670" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb1-671"><a href="#cb1-671" aria-hidden="true" tabindex="-1"></a><span class="co"># Allow overwrite yml config using from cli</span></span>
<span id="cb1-672"><a href="#cb1-672" aria-hidden="true" tabindex="-1"></a><span class="fu">strict</span><span class="kw">:</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<span id="cb1-648"><a href="#cb1-648" aria-hidden="true" tabindex="-1"></a><span class="co"># Advanced DDP Arguments</span></span>
<span id="cb1-649"><a href="#cb1-649" aria-hidden="true" tabindex="-1"></a><span class="fu">ddp_timeout</span><span class="kw">:</span></span>
<span id="cb1-650"><a href="#cb1-650" aria-hidden="true" tabindex="-1"></a><span class="fu">ddp_bucket_cap_mb</span><span class="kw">:</span></span>
<span id="cb1-651"><a href="#cb1-651" aria-hidden="true" tabindex="-1"></a><span class="fu">ddp_broadcast_buffers</span><span class="kw">:</span></span>
<span id="cb1-652"><a href="#cb1-652" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb1-653"><a href="#cb1-653" aria-hidden="true" tabindex="-1"></a><span class="co"># Sequence parallelism</span></span>
<span id="cb1-654"><a href="#cb1-654" aria-hidden="true" tabindex="-1"></a><span class="co"># Set to a divisor of the number of GPUs available to split sequences into chunks of equal size.</span></span>
<span id="cb1-655"><a href="#cb1-655" aria-hidden="true" tabindex="-1"></a><span class="co"># Use in long context training to prevent OOM when sequences cannot fit into a single GPU's VRAM.</span></span>
<span id="cb1-656"><a href="#cb1-656" aria-hidden="true" tabindex="-1"></a><span class="co"># E.g., if 4 GPUs are available, set this value to 2 to split each sequence into two equal-sized</span></span>
<span id="cb1-657"><a href="#cb1-657" aria-hidden="true" tabindex="-1"></a><span class="co"># subsequences, or set to 4 to split into four equal-sized subsequences.</span></span>
<span id="cb1-658"><a href="#cb1-658" aria-hidden="true" tabindex="-1"></a><span class="co"># See https://axolotl-ai-cloud.github.io/axolotl/docs/sequence_parallelism.html for more details.</span></span>
<span id="cb1-659"><a href="#cb1-659" aria-hidden="true" tabindex="-1"></a><span class="fu">sequence_parallel_degree</span><span class="kw">:</span></span>
<span id="cb1-660"><a href="#cb1-660" aria-hidden="true" tabindex="-1"></a><span class="co"># Optional; strides across the key dimension. Larger values use more memory but should make training faster.</span></span>
<span id="cb1-661"><a href="#cb1-661" aria-hidden="true" tabindex="-1"></a><span class="co"># Must evenly divide the number of KV heads in your model.</span></span>
<span id="cb1-662"><a href="#cb1-662" aria-hidden="true" tabindex="-1"></a><span class="fu">heads_k_stride</span><span class="kw">:</span><span class="at"> </span><span class="dv">1</span></span>
<span id="cb1-663"><a href="#cb1-663" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb1-664"><a href="#cb1-664" aria-hidden="true" tabindex="-1"></a><span class="co"># Path to torch distx for optim 'adamw_anyprecision'</span></span>
<span id="cb1-665"><a href="#cb1-665" aria-hidden="true" tabindex="-1"></a><span class="fu">torchdistx_path</span><span class="kw">:</span></span>
<span id="cb1-666"><a href="#cb1-666" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb1-667"><a href="#cb1-667" aria-hidden="true" tabindex="-1"></a><span class="co"># Set to HF dataset for type: 'completion' for streaming instead of pre-tokenize</span></span>
<span id="cb1-668"><a href="#cb1-668" aria-hidden="true" tabindex="-1"></a><span class="fu">pretraining_dataset</span><span class="kw">:</span></span>
<span id="cb1-669"><a href="#cb1-669" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb1-670"><a href="#cb1-670" aria-hidden="true" tabindex="-1"></a><span class="co"># Debug mode</span></span>
<span id="cb1-671"><a href="#cb1-671" aria-hidden="true" tabindex="-1"></a><span class="fu">debug</span><span class="kw">:</span></span>
<span id="cb1-672"><a href="#cb1-672" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb1-673"><a href="#cb1-673" aria-hidden="true" tabindex="-1"></a><span class="co"># Seed</span></span>
<span id="cb1-674"><a href="#cb1-674" aria-hidden="true" tabindex="-1"></a><span class="fu">seed</span><span class="kw">:</span></span>
<span id="cb1-675"><a href="#cb1-675" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb1-676"><a href="#cb1-676" aria-hidden="true" tabindex="-1"></a><span class="co"># Allow overwrite yml config using from cli</span></span>
<span id="cb1-677"><a href="#cb1-677" aria-hidden="true" tabindex="-1"></a><span class="fu">strict</span><span class="kw">:</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>

View File

@@ -21,6 +21,40 @@ ul.task-list li input[type="checkbox"] {
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 { display: inline-block; 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>
@@ -469,12 +503,21 @@ ul.task-list li input[type="checkbox"] {
</blockquote>
<p><strong>Q: How to call Axolotl via custom python scripts?</strong></p>
<blockquote class="blockquote">
<p>A: Yes, since Axolotl is just Python, please see <code>src/axolotl/cli/main.py</code> on how each command is called.</p>
<p>A: Since Axolotl is just Python, please see <code>src/axolotl/cli/main.py</code> on how each command is called.</p>
</blockquote>
<p><strong>Q: How to know the value to use for <code>fsdp_transformer_layer_cls_to_wrap</code>?</strong></p>
<blockquote class="blockquote">
<p>A: This is the class name of the transformer layer to wrap with FSDP. For example, for <code>LlamaForCausalLM</code>, the value is <code>LlamaDecoderLayer</code>. To find this for a specific model, check the models <code>PreTrainedModel</code> definition and look for <code>_no_split_modules</code> variable in the <code>modeling_&lt;model_name&gt;.py</code> file within <code>transformers</code> library.</p>
</blockquote>
<p><strong>Q: ValueError: Asking to pad but the tokenizer does not have a padding token. Please select a token to use as pad_token</strong></p>
<blockquote class="blockquote">
<p>A: This is because the tokenizer does not have a padding token. Please add a padding token to the tokenizer via:</p>
</blockquote>
<blockquote class="blockquote">
<div class="sourceCode" id="cb1"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb1-1"><a href="#cb1-1" aria-hidden="true" tabindex="-1"></a><span class="fu">special_tokens</span><span class="kw">:</span></span>
<span id="cb1-2"><a href="#cb1-2" aria-hidden="true" tabindex="-1"></a><span class="co"> # str. If you're not sure, set to same as `eos_token`.</span></span>
<span id="cb1-3"><a href="#cb1-3" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">pad_token</span><span class="kw">:</span><span class="at"> </span><span class="st">"..."</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</blockquote>
</section>
<section id="chat-templates" class="level3">
<h3 class="anchored" data-anchor-id="chat-templates">Chat templates</h3>

View File

@@ -479,7 +479,10 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
<li><a href="#llama3.ultra-1" id="toc-llama3.ultra-1" class="nav-link" data-scroll-target="#llama3.ultra-1">llama3.ultra</a></li>
<li><a href="#user_defined.default-1" id="toc-user_defined.default-1" class="nav-link" data-scroll-target="#user_defined.default-1">user_defined.default</a></li>
</ul></li>
<li><a href="#grpo" id="toc-grpo" class="nav-link" data-scroll-target="#grpo">GRPO</a></li>
<li><a href="#grpo" id="toc-grpo" class="nav-link" data-scroll-target="#grpo">GRPO</a>
<ul class="collapse">
<li><a href="#reward-functions" id="toc-reward-functions" class="nav-link" data-scroll-target="#reward-functions">Reward functions</a></li>
</ul></li>
<li><a href="#simpo" id="toc-simpo" class="nav-link" data-scroll-target="#simpo">SimPO</a></li>
<li><a href="#using-local-dataset-files" id="toc-using-local-dataset-files" class="nav-link" data-scroll-target="#using-local-dataset-files">Using local dataset files</a></li>
<li><a href="#trl-auto-unwrapping-for-peft" id="toc-trl-auto-unwrapping-for-peft" class="nav-link" data-scroll-target="#trl-auto-unwrapping-for-peft">TRL auto-unwrapping for PEFT</a></li>
@@ -953,63 +956,99 @@ Tip
<p>Check out our <a href="https://github.com/axolotl-ai-cloud/axolotl-cookbook/tree/main/grpo#training-an-r1-style-large-language-model-using-grpo">GRPO cookbook</a>.</p>
</div>
</div>
<p>If you have multiple GPUs available, we reccomend using <code>vLLM</code> with the <code>GRPOTrainer</code> to significantly speedup trajectory generation during training.
First, launch a <code>vLLM</code> server using <code>trl vllm-serve</code> - you may use a config file or CLI overrides to configure your vLLM server. In this example, were
using 4 GPUs - 2 for training, and 2 for vLLM:</p>
<div class="callout callout-style-default callout-important callout-titled">
<div class="callout-header d-flex align-content-center">
<div class="callout-icon-container">
<i class="callout-icon"></i>
</div>
<div class="callout-title-container flex-fill">
Important
</div>
</div>
<div class="callout-body-container callout-body">
<p>Make sure youve installed the correct version of vLLM by including it as an extra when installing axolotl, e.g.&nbsp;<code>pip install axolotl[vllm]</code>.</p>
</div>
</div>
<div class="sourceCode" id="cb35"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb35-1"><a href="#cb35-1" aria-hidden="true" tabindex="-1"></a><span class="fu">base_model</span><span class="kw">:</span><span class="at"> Qwen/Qwen2.5-1.5B-Instruct</span></span>
<span id="cb35-2"><a href="#cb35-2" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb35-3"><a href="#cb35-3" aria-hidden="true" tabindex="-1"></a><span class="fu">vllm</span><span class="kw">:</span></span>
<span id="cb35-4"><a href="#cb35-4" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">host</span><span class="kw">:</span><span class="at"> </span><span class="fl">0.0.0.0</span></span>
<span id="cb35-5"><a href="#cb35-5" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">port</span><span class="kw">:</span><span class="at"> </span><span class="dv">8000</span></span>
<span id="cb35-6"><a href="#cb35-6" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">tensor_parallel_size</span><span class="kw">:</span><span class="at"> </span><span class="dv">2</span></span>
<span id="cb35-7"><a href="#cb35-7" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">gpu_memory_utilization</span><span class="kw">:</span><span class="at"> </span><span class="fl">0.85</span></span>
<span id="cb35-8"><a href="#cb35-8" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">dtype</span><span class="kw">:</span><span class="at"> auto</span></span>
<span id="cb35-9"><a href="#cb35-9" aria-hidden="true" tabindex="-1"></a><span class="co"> # max_model_len: # you may find it useful to set the vLLM model context length if you know this beforehand</span></span>
<span id="cb35-10"><a href="#cb35-10" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb35-11"><a href="#cb35-11" aria-hidden="true" tabindex="-1"></a><span class="fu">rl</span><span class="kw">:</span><span class="at"> grpo</span></span>
<span id="cb35-12"><a href="#cb35-12" aria-hidden="true" tabindex="-1"></a><span class="fu">trl</span><span class="kw">:</span></span>
<span id="cb35-13"><a href="#cb35-13" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">use_vllm</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span>
<span id="cb35-14"><a href="#cb35-14" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">vllm_server_host</span><span class="kw">:</span><span class="at"> </span><span class="fl">0.0.0.0</span></span>
<span id="cb35-15"><a href="#cb35-15" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">vllm_server_port</span><span class="kw">:</span><span class="at"> </span><span class="dv">8000</span></span>
<span id="cb35-16"><a href="#cb35-16" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">vllm_server_timeout</span><span class="kw">:</span><span class="at"> </span><span class="dv">300</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<div class="sourceCode" id="cb36"><pre class="sourceCode bash code-with-copy"><code class="sourceCode bash"><span id="cb36-1"><a href="#cb36-1" aria-hidden="true" tabindex="-1"></a><span class="va">CUDA_VISIBLE_DEVICES</span><span class="op">=</span>2,3 <span class="ex">axolotl</span> vllm_serve grpo.yaml</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<p>Your <code>vLLM</code> instance will now attempt to spin up, and its time to kick off training utilizing our remaining two GPUs. In another terminal, execute:</p>
<div class="sourceCode" id="cb37"><pre class="sourceCode bash code-with-copy"><code class="sourceCode bash"><span id="cb37-1"><a href="#cb37-1" aria-hidden="true" tabindex="-1"></a><span class="va">CUDA_VISIBLE_DEVICES</span><span class="op">=</span>0,1 <span class="ex">axolotl</span> train grpo.yaml <span class="at">--num-processes</span> 2</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<section id="reward-functions" class="level4">
<h4 class="anchored" data-anchor-id="reward-functions">Reward functions</h4>
<p>GRPO uses custom reward functions and transformations. Please have them ready locally.</p>
<p>For ex, to load OpenAIs GSM8K and use a random reward for completions:</p>
<div class="sourceCode" id="cb35"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb35-1"><a href="#cb35-1" aria-hidden="true" tabindex="-1"></a><span class="co"># rewards.py</span></span>
<span id="cb35-2"><a href="#cb35-2" aria-hidden="true" tabindex="-1"></a><span class="im">import</span> random</span>
<span id="cb35-3"><a href="#cb35-3" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb35-4"><a href="#cb35-4" aria-hidden="true" tabindex="-1"></a><span class="kw">def</span> rand_reward_func(completions, <span class="op">**</span>kwargs) <span class="op">-&gt;</span> <span class="bu">list</span>[<span class="bu">float</span>]:</span>
<span id="cb35-5"><a href="#cb35-5" aria-hidden="true" tabindex="-1"></a> <span class="cf">return</span> [random.uniform(<span class="dv">0</span>, <span class="dv">1</span>) <span class="cf">for</span> _ <span class="kw">in</span> completions]</span>
<span id="cb35-6"><a href="#cb35-6" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb35-7"><a href="#cb35-7" aria-hidden="true" tabindex="-1"></a><span class="kw">def</span> oai_gsm8k_transform(cfg, <span class="op">*</span>args, <span class="op">**</span>kwargs):</span>
<span id="cb35-8"><a href="#cb35-8" aria-hidden="true" tabindex="-1"></a> <span class="kw">def</span> transform_fn(example, tokenizer<span class="op">=</span><span class="va">None</span>):</span>
<span id="cb35-9"><a href="#cb35-9" aria-hidden="true" tabindex="-1"></a> label <span class="op">=</span> example[<span class="st">"answer"</span>].split(<span class="st">"####"</span>)[<span class="op">-</span><span class="dv">1</span>].strip().replace(<span class="st">","</span>, <span class="st">""</span>)</span>
<span id="cb35-10"><a href="#cb35-10" aria-hidden="true" tabindex="-1"></a> <span class="cf">return</span> {</span>
<span id="cb35-11"><a href="#cb35-11" aria-hidden="true" tabindex="-1"></a> <span class="st">"prompt"</span>: [{<span class="st">"role"</span>: <span class="st">"user"</span>, <span class="st">"content"</span>: example[<span class="st">"question"</span>]},],</span>
<span id="cb35-12"><a href="#cb35-12" aria-hidden="true" tabindex="-1"></a> <span class="st">"answer"</span>: label,</span>
<span id="cb35-13"><a href="#cb35-13" aria-hidden="true" tabindex="-1"></a> }</span>
<span id="cb35-14"><a href="#cb35-14" aria-hidden="true" tabindex="-1"></a> <span class="cf">return</span> transform_fn, {<span class="st">"remove_columns"</span>: [<span class="st">"question"</span>]}</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<div class="sourceCode" id="cb36"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb36-1"><a href="#cb36-1" aria-hidden="true" tabindex="-1"></a><span class="fu">rl</span><span class="kw">:</span><span class="at"> grpo</span></span>
<span id="cb36-2"><a href="#cb36-2" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb36-3"><a href="#cb36-3" aria-hidden="true" tabindex="-1"></a><span class="fu">trl</span><span class="kw">:</span></span>
<span id="cb36-4"><a href="#cb36-4" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">beta</span><span class="kw">:</span><span class="at"> </span><span class="fl">0.001</span></span>
<span id="cb36-5"><a href="#cb36-5" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">max_completion_length</span><span class="kw">:</span><span class="at"> </span><span class="dv">256</span></span>
<span id="cb36-6"><a href="#cb36-6" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">use_vllm</span><span class="kw">:</span><span class="at"> </span><span class="ch">True</span></span>
<span id="cb36-7"><a href="#cb36-7" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">vllm_device</span><span class="kw">:</span><span class="at"> auto</span></span>
<span id="cb36-8"><a href="#cb36-8" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">vllm_gpu_memory_utilization</span><span class="kw">:</span><span class="at"> </span><span class="fl">0.15</span></span>
<span id="cb36-9"><a href="#cb36-9" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">num_generations</span><span class="kw">:</span><span class="at"> </span><span class="dv">4</span></span>
<span id="cb36-10"><a href="#cb36-10" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">reward_funcs</span><span class="kw">:</span><span class="at"> </span><span class="kw">[</span><span class="st">"rewards.rand_reward_func"</span><span class="kw">]</span><span class="co"> # format: '{file_name}.{fn_name}'</span></span>
<span id="cb36-11"><a href="#cb36-11" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">reward_weights</span><span class="kw">:</span><span class="at"> </span><span class="kw">[</span><span class="fl">1.0</span><span class="kw">]</span></span>
<span id="cb36-12"><a href="#cb36-12" aria-hidden="true" tabindex="-1"></a><span class="fu">datasets</span><span class="kw">:</span></span>
<span id="cb36-13"><a href="#cb36-13" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> </span><span class="fu">path</span><span class="kw">:</span><span class="at"> openai/gsm8k</span></span>
<span id="cb36-14"><a href="#cb36-14" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">name</span><span class="kw">:</span><span class="at"> main</span></span>
<span id="cb36-15"><a href="#cb36-15" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">type</span><span class="kw">:</span><span class="at"> rewards.oai_gsm8k_transform</span><span class="co"> # format: '{file_name}.{fn_name}'</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<p>For example, to load OpenAIs GSM8K and use a random reward for completions:</p>
<div class="sourceCode" id="cb38"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb38-1"><a href="#cb38-1" aria-hidden="true" tabindex="-1"></a><span class="co"># rewards.py</span></span>
<span id="cb38-2"><a href="#cb38-2" aria-hidden="true" tabindex="-1"></a><span class="im">import</span> random</span>
<span id="cb38-3"><a href="#cb38-3" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb38-4"><a href="#cb38-4" aria-hidden="true" tabindex="-1"></a><span class="kw">def</span> rand_reward_func(completions, <span class="op">**</span>kwargs) <span class="op">-&gt;</span> <span class="bu">list</span>[<span class="bu">float</span>]:</span>
<span id="cb38-5"><a href="#cb38-5" aria-hidden="true" tabindex="-1"></a> <span class="cf">return</span> [random.uniform(<span class="dv">0</span>, <span class="dv">1</span>) <span class="cf">for</span> _ <span class="kw">in</span> completions]</span>
<span id="cb38-6"><a href="#cb38-6" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb38-7"><a href="#cb38-7" aria-hidden="true" tabindex="-1"></a><span class="kw">def</span> oai_gsm8k_transform(cfg, <span class="op">*</span>args, <span class="op">**</span>kwargs):</span>
<span id="cb38-8"><a href="#cb38-8" aria-hidden="true" tabindex="-1"></a> <span class="kw">def</span> transform_fn(example, tokenizer<span class="op">=</span><span class="va">None</span>):</span>
<span id="cb38-9"><a href="#cb38-9" aria-hidden="true" tabindex="-1"></a> label <span class="op">=</span> example[<span class="st">"answer"</span>].split(<span class="st">"####"</span>)[<span class="op">-</span><span class="dv">1</span>].strip().replace(<span class="st">","</span>, <span class="st">""</span>)</span>
<span id="cb38-10"><a href="#cb38-10" aria-hidden="true" tabindex="-1"></a> <span class="cf">return</span> {</span>
<span id="cb38-11"><a href="#cb38-11" aria-hidden="true" tabindex="-1"></a> <span class="st">"prompt"</span>: [{<span class="st">"role"</span>: <span class="st">"user"</span>, <span class="st">"content"</span>: example[<span class="st">"question"</span>]},],</span>
<span id="cb38-12"><a href="#cb38-12" aria-hidden="true" tabindex="-1"></a> <span class="st">"answer"</span>: label,</span>
<span id="cb38-13"><a href="#cb38-13" aria-hidden="true" tabindex="-1"></a> }</span>
<span id="cb38-14"><a href="#cb38-14" aria-hidden="true" tabindex="-1"></a> <span class="cf">return</span> transform_fn, {<span class="st">"remove_columns"</span>: [<span class="st">"question"</span>]}</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<div class="sourceCode" id="cb39"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb39-1"><a href="#cb39-1" aria-hidden="true" tabindex="-1"></a><span class="fu">rl</span><span class="kw">:</span><span class="at"> grpo</span></span>
<span id="cb39-2"><a href="#cb39-2" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb39-3"><a href="#cb39-3" aria-hidden="true" tabindex="-1"></a><span class="fu">trl</span><span class="kw">:</span></span>
<span id="cb39-4"><a href="#cb39-4" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">beta</span><span class="kw">:</span><span class="at"> </span><span class="fl">0.001</span></span>
<span id="cb39-5"><a href="#cb39-5" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">max_completion_length</span><span class="kw">:</span><span class="at"> </span><span class="dv">256</span></span>
<span id="cb39-6"><a href="#cb39-6" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">use_vllm</span><span class="kw">:</span><span class="at"> </span><span class="ch">True</span></span>
<span id="cb39-7"><a href="#cb39-7" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">num_generations</span><span class="kw">:</span><span class="at"> </span><span class="dv">4</span></span>
<span id="cb39-8"><a href="#cb39-8" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">reward_funcs</span><span class="kw">:</span><span class="at"> </span><span class="kw">[</span><span class="st">"rewards.rand_reward_func"</span><span class="kw">]</span><span class="co"> # format: '{file_name}.{fn_name}'</span></span>
<span id="cb39-9"><a href="#cb39-9" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">reward_weights</span><span class="kw">:</span><span class="at"> </span><span class="kw">[</span><span class="fl">1.0</span><span class="kw">]</span></span>
<span id="cb39-10"><a href="#cb39-10" aria-hidden="true" tabindex="-1"></a><span class="fu">datasets</span><span class="kw">:</span></span>
<span id="cb39-11"><a href="#cb39-11" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> </span><span class="fu">path</span><span class="kw">:</span><span class="at"> openai/gsm8k</span></span>
<span id="cb39-12"><a href="#cb39-12" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">name</span><span class="kw">:</span><span class="at"> main</span></span>
<span id="cb39-13"><a href="#cb39-13" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">type</span><span class="kw">:</span><span class="at"> rewards.oai_gsm8k_transform</span><span class="co"> # format: '{file_name}.{fn_name}'</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<p>To see other examples of custom reward functions, please see <a href="https://github.com/huggingface/trl/blob/main/docs/source/grpo_trainer.md#using-a-custom-reward-function">TRL GRPO Docs</a>.</p>
<p>To see description of the configs, please see <a href="https://github.com/axolotl-ai-cloud/axolotl/blob/main/src/axolotl/utils/config/models/input/v0_4_1/trl.py">TRLConfig</a>.</p>
</section>
</section>
<section id="simpo" class="level3">
<h3 class="anchored" data-anchor-id="simpo">SimPO</h3>
<p>SimPO uses <a href="https://huggingface.co/docs/trl/main/en/cpo_trainer">CPOTrainer</a> but with alternative loss function.</p>
<div class="sourceCode" id="cb37"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb37-1"><a href="#cb37-1" aria-hidden="true" tabindex="-1"></a><span class="fu">rl</span><span class="kw">:</span><span class="at"> simpo</span></span>
<span id="cb37-2"><a href="#cb37-2" aria-hidden="true" tabindex="-1"></a><span class="fu">rl_beta</span><span class="kw">:</span><span class="at"> </span><span class="fl">0.1</span><span class="co"> # default in CPOTrainer</span></span>
<span id="cb37-3"><a href="#cb37-3" aria-hidden="true" tabindex="-1"></a><span class="fu">cpo_alpha</span><span class="kw">:</span><span class="at"> </span><span class="fl">1.0</span><span class="co"> # default in CPOTrainer</span></span>
<span id="cb37-4"><a href="#cb37-4" aria-hidden="true" tabindex="-1"></a><span class="fu">simpo_gamma</span><span class="kw">:</span><span class="at"> </span><span class="fl">0.5</span><span class="co"> # default in CPOTrainer</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<div class="sourceCode" id="cb40"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb40-1"><a href="#cb40-1" aria-hidden="true" tabindex="-1"></a><span class="fu">rl</span><span class="kw">:</span><span class="at"> simpo</span></span>
<span id="cb40-2"><a href="#cb40-2" aria-hidden="true" tabindex="-1"></a><span class="fu">rl_beta</span><span class="kw">:</span><span class="at"> </span><span class="fl">0.1</span><span class="co"> # default in CPOTrainer</span></span>
<span id="cb40-3"><a href="#cb40-3" aria-hidden="true" tabindex="-1"></a><span class="fu">cpo_alpha</span><span class="kw">:</span><span class="at"> </span><span class="fl">1.0</span><span class="co"> # default in CPOTrainer</span></span>
<span id="cb40-4"><a href="#cb40-4" aria-hidden="true" tabindex="-1"></a><span class="fu">simpo_gamma</span><span class="kw">:</span><span class="at"> </span><span class="fl">0.5</span><span class="co"> # default in CPOTrainer</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<p>This method uses the same dataset format as <a href="#dpo">DPO</a>.</p>
</section>
<section id="using-local-dataset-files" class="level3">
<h3 class="anchored" data-anchor-id="using-local-dataset-files">Using local dataset files</h3>
<div class="sourceCode" id="cb38"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb38-1"><a href="#cb38-1" aria-hidden="true" tabindex="-1"></a><span class="fu">datasets</span><span class="kw">:</span></span>
<span id="cb38-2"><a href="#cb38-2" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> </span><span class="fu">ds_type</span><span class="kw">:</span><span class="at"> json</span></span>
<span id="cb38-3"><a href="#cb38-3" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">data_files</span><span class="kw">:</span></span>
<span id="cb38-4"><a href="#cb38-4" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> orca_rlhf.jsonl</span></span>
<span id="cb38-5"><a href="#cb38-5" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">split</span><span class="kw">:</span><span class="at"> train</span></span>
<span id="cb38-6"><a href="#cb38-6" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">type</span><span class="kw">:</span><span class="at"> chatml.intel</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<div class="sourceCode" id="cb41"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb41-1"><a href="#cb41-1" aria-hidden="true" tabindex="-1"></a><span class="fu">datasets</span><span class="kw">:</span></span>
<span id="cb41-2"><a href="#cb41-2" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> </span><span class="fu">ds_type</span><span class="kw">:</span><span class="at"> json</span></span>
<span id="cb41-3"><a href="#cb41-3" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">data_files</span><span class="kw">:</span></span>
<span id="cb41-4"><a href="#cb41-4" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> orca_rlhf.jsonl</span></span>
<span id="cb41-5"><a href="#cb41-5" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">split</span><span class="kw">:</span><span class="at"> train</span></span>
<span id="cb41-6"><a href="#cb41-6" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">type</span><span class="kw">:</span><span class="at"> chatml.intel</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</section>
<section id="trl-auto-unwrapping-for-peft" class="level3">
<h3 class="anchored" data-anchor-id="trl-auto-unwrapping-for-peft">TRL auto-unwrapping for PEFT</h3>
<p>TRL supports auto-unwrapping PEFT models for RL training paradigms which rely on a reference model. This significantly reduces memory pressure as an additional refreference model does not need to be loaded, and reference model log-probabilities can be obtained by disabling PEFT adapters. This is enabled by default. To turn it off, pass the following config:</p>
<div class="sourceCode" id="cb39"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb39-1"><a href="#cb39-1" aria-hidden="true" tabindex="-1"></a><span class="co"># load ref model when adapter training.</span></span>
<span id="cb39-2"><a href="#cb39-2" aria-hidden="true" tabindex="-1"></a><span class="fu">rl_adapter_ref_model</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<div class="sourceCode" id="cb42"><pre class="sourceCode yaml code-with-copy"><code class="sourceCode yaml"><span id="cb42-1"><a href="#cb42-1" aria-hidden="true" tabindex="-1"></a><span class="co"># load ref model when adapter training.</span></span>
<span id="cb42-2"><a href="#cb42-2" aria-hidden="true" tabindex="-1"></a><span class="fu">rl_adapter_ref_model</span><span class="kw">:</span><span class="at"> </span><span class="ch">true</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</section>

File diff suppressed because one or more lines are too long

View File

@@ -2,674 +2,678 @@
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/examples/colab-notebooks/colab-axolotl-example.html</loc>
<lastmod>2025-03-31T19:17:57.239Z</lastmod>
<lastmod>2025-03-31T21:15:37.300Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/dataset-formats/stepwise_supervised.html</loc>
<lastmod>2025-03-31T19:17:57.234Z</lastmod>
<lastmod>2025-03-31T21:15:37.295Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/dataset-formats/template_free.html</loc>
<lastmod>2025-03-31T19:17:57.234Z</lastmod>
<lastmod>2025-03-31T21:15:37.295Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/dataset-formats/tokenized.html</loc>
<lastmod>2025-03-31T19:17:57.234Z</lastmod>
<lastmod>2025-03-31T21:15:37.295Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/nccl.html</loc>
<lastmod>2025-03-31T19:17:57.238Z</lastmod>
<lastmod>2025-03-31T21:15:37.299Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/amd_hpc.html</loc>
<lastmod>2025-03-31T19:17:57.234Z</lastmod>
<lastmod>2025-03-31T21:15:37.295Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/config.html</loc>
<lastmod>2025-03-31T19:17:57.234Z</lastmod>
<lastmod>2025-03-31T21:15:37.295Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/multi-gpu.html</loc>
<lastmod>2025-03-31T19:17:57.238Z</lastmod>
<lastmod>2025-03-31T21:15:37.299Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/installation.html</loc>
<lastmod>2025-03-31T19:17:57.237Z</lastmod>
<lastmod>2025-03-31T21:15:37.299Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/torchao.html</loc>
<lastmod>2025-03-31T19:17:57.238Z</lastmod>
<lastmod>2025-03-31T21:15:37.299Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/reward_modelling.html</loc>
<lastmod>2025-03-31T19:17:57.238Z</lastmod>
<lastmod>2025-03-31T21:15:37.299Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/input_output.html</loc>
<lastmod>2025-03-31T19:17:57.237Z</lastmod>
<lastmod>2025-03-31T21:15:37.299Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/multimodal.html</loc>
<lastmod>2025-03-31T19:17:57.238Z</lastmod>
<lastmod>2025-03-31T21:15:37.299Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.callbacks.mlflow_.html</loc>
<lastmod>2025-03-31T19:18:25.605Z</lastmod>
<lastmod>2025-03-31T21:16:16.158Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.trainer_fsdp_optim.html</loc>
<lastmod>2025-03-31T19:18:25.195Z</lastmod>
<lastmod>2025-03-31T21:16:15.739Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.data.batch_dataset_fetcher.html</loc>
<lastmod>2025-03-31T19:18:25.211Z</lastmod>
<lastmod>2025-03-31T21:16:15.755Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.stepwise_supervised.html</loc>
<lastmod>2025-03-31T19:18:24.896Z</lastmod>
<lastmod>2025-03-31T21:16:15.444Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.mistral_attn_hijack_flash.html</loc>
<lastmod>2025-03-31T19:18:25.143Z</lastmod>
<lastmod>2025-03-31T21:16:15.686Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.dpo.user_defined.html</loc>
<lastmod>2025-03-31T19:18:24.943Z</lastmod>
<lastmod>2025-03-31T21:16:15.491Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/integrations.liger.args.html</loc>
<lastmod>2025-03-31T19:18:25.521Z</lastmod>
<lastmod>2025-03-31T21:16:16.071Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.schemas.training.html</loc>
<lastmod>2025-03-31T19:18:25.383Z</lastmod>
<lastmod>2025-03-31T21:16:15.932Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/datasets.html</loc>
<lastmod>2025-03-31T19:18:24.389Z</lastmod>
<lastmod>2025-03-31T21:16:14.934Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/kernels.geglu.html</loc>
<lastmod>2025-03-31T19:18:25.081Z</lastmod>
<lastmod>2025-03-31T21:16:15.626Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.llama_attn_hijack_flash.html</loc>
<lastmod>2025-03-31T19:18:25.127Z</lastmod>
<lastmod>2025-03-31T21:16:15.670Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/cli.sweeps.html</loc>
<lastmod>2025-03-31T19:18:24.726Z</lastmod>
<lastmod>2025-03-31T21:16:15.273Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.freeze.html</loc>
<lastmod>2025-03-31T19:18:25.284Z</lastmod>
<lastmod>2025-03-31T21:16:15.832Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.multipack.html</loc>
<lastmod>2025-03-31T19:18:25.145Z</lastmod>
<lastmod>2025-03-31T21:16:15.688Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/cli.main.html</loc>
<lastmod>2025-03-31T19:18:24.622Z</lastmod>
<lastmod>2025-03-31T21:16:15.168Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/core.trainers.trl.html</loc>
<lastmod>2025-03-31T19:18:24.803Z</lastmod>
<lastmod>2025-03-31T21:16:15.353Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.dpo.passthrough.html</loc>
<lastmod>2025-03-31T19:18:24.944Z</lastmod>
<lastmod>2025-03-31T21:16:15.492Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/core.chat.format.llama3x.html</loc>
<lastmod>2025-03-31T19:18:24.576Z</lastmod>
<lastmod>2025-03-31T21:16:15.122Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/core.datasets.transforms.chat_builder.html</loc>
<lastmod>2025-03-31T19:18:24.590Z</lastmod>
<lastmod>2025-03-31T21:16:15.137Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.kto.user_defined.html</loc>
<lastmod>2025-03-31T19:18:24.962Z</lastmod>
<lastmod>2025-03-31T21:16:15.509Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.collators.mamba.html</loc>
<lastmod>2025-03-31T19:18:25.579Z</lastmod>
<lastmod>2025-03-31T21:16:16.129Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/integrations.base.html</loc>
<lastmod>2025-03-31T19:18:25.506Z</lastmod>
<lastmod>2025-03-31T21:16:16.055Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.bench.html</loc>
<lastmod>2025-03-31T19:18:25.276Z</lastmod>
<lastmod>2025-03-31T21:16:15.824Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/kernels.swiglu.html</loc>
<lastmod>2025-03-31T19:18:25.091Z</lastmod>
<lastmod>2025-03-31T21:16:15.636Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/core.chat.format.shared.html</loc>
<lastmod>2025-03-31T19:18:24.577Z</lastmod>
<lastmod>2025-03-31T21:16:15.124Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/integrations.cut_cross_entropy.args.html</loc>
<lastmod>2025-03-31T19:18:25.509Z</lastmod>
<lastmod>2025-03-31T21:16:16.059Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/core.datasets.chat.html</loc>
<lastmod>2025-03-31T19:18:24.582Z</lastmod>
<lastmod>2025-03-31T21:16:15.129Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.callbacks.lisa.html</loc>
<lastmod>2025-03-31T19:18:25.601Z</lastmod>
<lastmod>2025-03-31T21:16:16.154Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/integrations.grokfast.optimizer.html</loc>
<lastmod>2025-03-31T19:18:25.510Z</lastmod>
<lastmod>2025-03-31T21:16:16.060Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.alpaca_chat.html</loc>
<lastmod>2025-03-31T19:18:24.844Z</lastmod>
<lastmod>2025-03-31T21:16:15.393Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.alpaca_instruct.html</loc>
<lastmod>2025-03-31T19:18:24.845Z</lastmod>
<lastmod>2025-03-31T21:16:15.395Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.kto.chatml.html</loc>
<lastmod>2025-03-31T19:18:24.961Z</lastmod>
<lastmod>2025-03-31T21:16:15.508Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.schemas.integrations.html</loc>
<lastmod>2025-03-31T19:18:25.429Z</lastmod>
<lastmod>2025-03-31T21:16:15.979Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.schemas.trl.html</loc>
<lastmod>2025-03-31T19:18:25.412Z</lastmod>
<lastmod>2025-03-31T21:16:15.961Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_tokenizers.html</loc>
<lastmod>2025-03-31T19:18:24.444Z</lastmod>
<lastmod>2025-03-31T21:16:14.990Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.data.sft.html</loc>
<lastmod>2025-03-31T19:18:25.360Z</lastmod>
<lastmod>2025-03-31T21:16:15.909Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.schedulers.html</loc>
<lastmod>2025-03-31T19:18:25.325Z</lastmod>
<lastmod>2025-03-31T21:16:15.874Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.chat_templates.html</loc>
<lastmod>2025-03-31T19:18:25.259Z</lastmod>
<lastmod>2025-03-31T21:16:15.806Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.models.html</loc>
<lastmod>2025-03-31T19:18:25.242Z</lastmod>
<lastmod>2025-03-31T21:16:15.788Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.dpo.chatml.html</loc>
<lastmod>2025-03-31T19:18:24.940Z</lastmod>
<lastmod>2025-03-31T21:16:15.488Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.distributed.html</loc>
<lastmod>2025-03-31T19:18:25.346Z</lastmod>
<lastmod>2025-03-31T21:16:15.895Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.utils.html</loc>
<lastmod>2025-03-31T19:18:25.183Z</lastmod>
<lastmod>2025-03-31T21:16:15.727Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.schemas.utils.html</loc>
<lastmod>2025-03-31T19:18:25.442Z</lastmod>
<lastmod>2025-03-31T21:16:15.991Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.llama_expand_mask.html</loc>
<lastmod>2025-03-31T19:18:25.153Z</lastmod>
<lastmod>2025-03-31T21:16:15.696Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/common.datasets.html</loc>
<lastmod>2025-03-31T19:18:25.547Z</lastmod>
<lastmod>2025-03-31T21:16:16.097Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/logging_config.html</loc>
<lastmod>2025-03-31T19:18:24.449Z</lastmod>
<lastmod>2025-03-31T21:16:14.995Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/kernels.quantize.html</loc>
<lastmod>2025-03-31T19:18:25.099Z</lastmod>
<lastmod>2025-03-31T21:16:15.643Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.llama_patch_multipack.html</loc>
<lastmod>2025-03-31T19:18:25.186Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.callbacks.comet_.html</loc>
<lastmod>2025-03-31T19:18:25.608Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.trainer.html</loc>
<lastmod>2025-03-31T19:18:25.301Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/common.architectures.html</loc>
<lastmod>2025-03-31T19:18:25.529Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/models.mamba.modeling_mamba.html</loc>
<lastmod>2025-03-31T19:18:25.548Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/integrations.spectrum.args.html</loc>
<lastmod>2025-03-31T19:18:25.528Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/cli.merge_sharded_fsdp_weights.html</loc>
<lastmod>2025-03-31T19:18:24.712Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.bradley_terry.llama3.html</loc>
<lastmod>2025-03-31T19:18:24.986Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/cli.merge_lora.html</loc>
<lastmod>2025-03-31T19:18:24.700Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.lora.html</loc>
<lastmod>2025-03-31T19:18:25.264Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.relora.html</loc>
<lastmod>2025-03-31T19:18:25.152Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/cli.cloud.base.html</loc>
<lastmod>2025-03-31T19:18:24.762Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/common.const.html</loc>
<lastmod>2025-03-31T19:18:25.531Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/convert.html</loc>
<lastmod>2025-03-31T19:18:24.402Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.chat_template.html</loc>
<lastmod>2025-03-31T19:18:24.830Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/kernels.utils.html</loc>
<lastmod>2025-03-31T19:18:25.101Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.lora_embeddings.html</loc>
<lastmod>2025-03-31T19:18:25.267Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/lora_optims.html</loc>
<lastmod>2025-03-31T19:17:57.238Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/batch_vs_grad.html</loc>
<lastmod>2025-03-31T19:17:57.234Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/faq.html</loc>
<lastmod>2025-03-31T19:17:57.235Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/debugging.html</loc>
<lastmod>2025-03-31T19:17:57.235Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/lr_groups.html</loc>
<lastmod>2025-03-31T19:17:57.238Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/TODO.html</loc>
<lastmod>2025-03-31T19:17:57.233Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/src/axolotl/integrations/LICENSE.html</loc>
<lastmod>2025-03-31T19:17:57.257Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/index.html</loc>
<lastmod>2025-03-31T19:17:57.251Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/src/axolotl/integrations/cut_cross_entropy/ACKNOWLEDGEMENTS.html</loc>
<lastmod>2025-03-31T19:17:57.257Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/FAQS.html</loc>
<lastmod>2025-03-31T19:17:57.233Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/multi-node.html</loc>
<lastmod>2025-03-31T19:17:57.238Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/sequence_parallelism.html</loc>
<lastmod>2025-03-31T19:17:57.238Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/multipack.html</loc>
<lastmod>2025-03-31T19:17:57.238Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/inference.html</loc>
<lastmod>2025-03-31T19:17:57.237Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/getting-started.html</loc>
<lastmod>2025-03-31T19:17:57.235Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.callbacks.perplexity.html</loc>
<lastmod>2025-03-31T19:18:25.596Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/core.trainer_builder.html</loc>
<lastmod>2025-03-31T19:18:24.465Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/cli.train.html</loc>
<lastmod>2025-03-31T19:18:24.631Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.dpo.llama3.html</loc>
<lastmod>2025-03-31T19:18:24.930Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/cli.cloud.modal_.html</loc>
<lastmod>2025-03-31T19:18:24.768Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/index.html</loc>
<lastmod>2025-03-31T19:18:24.310Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.input_output.html</loc>
<lastmod>2025-03-31T19:18:24.892Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.optimizers.adopt.html</loc>
<lastmod>2025-03-31T19:18:25.357Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.btlm_attn_hijack_flash.html</loc>
<lastmod>2025-03-31T19:18:25.185Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.collators.core.html</loc>
<lastmod>2025-03-31T19:18:25.550Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.schemas.datasets.html</loc>
<lastmod>2025-03-31T19:18:25.400Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/integrations.kd.trainer.html</loc>
<lastmod>2025-03-31T19:18:25.518Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.tokenization.html</loc>
<lastmod>2025-03-31T19:18:25.249Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.mixtral.html</loc>
<lastmod>2025-03-31T19:18:25.213Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.stablelm_attn_hijack_flash.html</loc>
<lastmod>2025-03-31T19:18:25.192Z</lastmod>
<lastmod>2025-03-31T21:16:15.730Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.schemas.model.html</loc>
<lastmod>2025-03-31T19:18:25.378Z</lastmod>
<lastmod>2025-03-31T21:16:15.927Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.stablelm_attn_hijack_flash.html</loc>
<lastmod>2025-03-31T21:16:15.735Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.mixtral.html</loc>
<lastmod>2025-03-31T21:16:15.756Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.tokenization.html</loc>
<lastmod>2025-03-31T21:16:15.796Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/integrations.kd.trainer.html</loc>
<lastmod>2025-03-31T21:16:16.067Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.schemas.datasets.html</loc>
<lastmod>2025-03-31T21:16:15.950Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.collators.core.html</loc>
<lastmod>2025-03-31T21:16:16.099Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.btlm_attn_hijack_flash.html</loc>
<lastmod>2025-03-31T21:16:15.728Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.optimizers.adopt.html</loc>
<lastmod>2025-03-31T21:16:15.906Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.input_output.html</loc>
<lastmod>2025-03-31T21:16:15.439Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/index.html</loc>
<lastmod>2025-03-31T21:16:14.856Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/cli.cloud.modal_.html</loc>
<lastmod>2025-03-31T21:16:15.319Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.dpo.llama3.html</loc>
<lastmod>2025-03-31T21:16:15.477Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/cli.train.html</loc>
<lastmod>2025-03-31T21:16:15.176Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/core.trainer_builder.html</loc>
<lastmod>2025-03-31T21:16:15.010Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.callbacks.perplexity.html</loc>
<lastmod>2025-03-31T21:16:16.149Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/getting-started.html</loc>
<lastmod>2025-03-31T21:15:37.296Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/inference.html</loc>
<lastmod>2025-03-31T21:15:37.299Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/multipack.html</loc>
<lastmod>2025-03-31T21:15:37.299Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/sequence_parallelism.html</loc>
<lastmod>2025-03-31T21:15:37.299Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/multi-node.html</loc>
<lastmod>2025-03-31T21:15:37.299Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/FAQS.html</loc>
<lastmod>2025-03-31T21:15:37.294Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/src/axolotl/integrations/cut_cross_entropy/ACKNOWLEDGEMENTS.html</loc>
<lastmod>2025-03-31T21:15:37.315Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/index.html</loc>
<lastmod>2025-03-31T21:15:37.311Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/src/axolotl/integrations/LICENSE.html</loc>
<lastmod>2025-03-31T21:15:37.314Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/TODO.html</loc>
<lastmod>2025-03-31T21:15:37.294Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/lr_groups.html</loc>
<lastmod>2025-03-31T21:15:37.299Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/debugging.html</loc>
<lastmod>2025-03-31T21:15:37.296Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/faq.html</loc>
<lastmod>2025-03-31T21:15:37.296Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/batch_vs_grad.html</loc>
<lastmod>2025-03-31T21:15:37.295Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/lora_optims.html</loc>
<lastmod>2025-03-31T21:15:37.299Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.lora_embeddings.html</loc>
<lastmod>2025-03-31T21:16:15.815Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/kernels.utils.html</loc>
<lastmod>2025-03-31T21:16:15.645Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.chat_template.html</loc>
<lastmod>2025-03-31T21:16:15.380Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/convert.html</loc>
<lastmod>2025-03-31T21:16:14.948Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/common.const.html</loc>
<lastmod>2025-03-31T21:16:16.080Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/cli.cloud.base.html</loc>
<lastmod>2025-03-31T21:16:15.313Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.relora.html</loc>
<lastmod>2025-03-31T21:16:15.695Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.lora.html</loc>
<lastmod>2025-03-31T21:16:15.811Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/cli.merge_lora.html</loc>
<lastmod>2025-03-31T21:16:15.248Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.bradley_terry.llama3.html</loc>
<lastmod>2025-03-31T21:16:15.534Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/cli.merge_sharded_fsdp_weights.html</loc>
<lastmod>2025-03-31T21:16:15.259Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/integrations.spectrum.args.html</loc>
<lastmod>2025-03-31T21:16:16.077Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/models.mamba.modeling_mamba.html</loc>
<lastmod>2025-03-31T21:16:16.098Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/common.architectures.html</loc>
<lastmod>2025-03-31T21:16:16.079Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.trainer.html</loc>
<lastmod>2025-03-31T21:16:15.850Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.callbacks.comet_.html</loc>
<lastmod>2025-03-31T21:16:16.162Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/cli.vllm_serve.html</loc>
<lastmod>2025-03-31T21:16:15.309Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.schemas.multimodal.html</loc>
<lastmod>2025-03-31T19:18:25.417Z</lastmod>
<lastmod>2025-03-31T21:16:15.967Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.gradient_checkpointing.unsloth.html</loc>
<lastmod>2025-03-31T19:18:25.363Z</lastmod>
<lastmod>2025-03-31T21:16:15.912Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/core.trainers.base.html</loc>
<lastmod>2025-03-31T19:18:24.786Z</lastmod>
<lastmod>2025-03-31T21:16:15.336Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.unsloth_.html</loc>
<lastmod>2025-03-31T19:18:25.203Z</lastmod>
<lastmod>2025-03-31T21:16:15.747Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.samplers.multipack.html</loc>
<lastmod>2025-03-31T19:18:25.589Z</lastmod>
<lastmod>2025-03-31T21:16:16.143Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.callbacks.profiler.html</loc>
<lastmod>2025-03-31T19:18:25.599Z</lastmod>
<lastmod>2025-03-31T21:16:16.153Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/integrations.lm_eval.args.html</loc>
<lastmod>2025-03-31T19:18:25.525Z</lastmod>
<lastmod>2025-03-31T21:16:16.074Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.data.pretraining.html</loc>
<lastmod>2025-03-31T19:18:25.358Z</lastmod>
<lastmod>2025-03-31T21:16:15.908Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/evaluate.html</loc>
<lastmod>2025-03-31T19:18:24.382Z</lastmod>
<lastmod>2025-03-31T21:16:14.927Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.dict.html</loc>
<lastmod>2025-03-31T19:18:25.349Z</lastmod>
<lastmod>2025-03-31T21:16:15.898Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/cli.utils.html</loc>
<lastmod>2025-03-31T19:18:24.758Z</lastmod>
<lastmod>2025-03-31T21:16:15.305Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.pygmalion.html</loc>
<lastmod>2025-03-31T19:18:24.914Z</lastmod>
<lastmod>2025-03-31T21:16:15.462Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/core.training_args.html</loc>
<lastmod>2025-03-31T19:18:24.550Z</lastmod>
<lastmod>2025-03-31T21:16:15.096Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/cli.inference.html</loc>
<lastmod>2025-03-31T19:18:24.691Z</lastmod>
<lastmod>2025-03-31T21:16:15.239Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/kernels.lora.html</loc>
<lastmod>2025-03-31T19:18:25.070Z</lastmod>
<lastmod>2025-03-31T21:16:15.615Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/cli.evaluate.html</loc>
<lastmod>2025-03-31T19:18:24.639Z</lastmod>
<lastmod>2025-03-31T21:16:15.185Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.collators.batching.html</loc>
<lastmod>2025-03-31T19:18:25.576Z</lastmod>
<lastmod>2025-03-31T21:16:16.126Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.completion.html</loc>
<lastmod>2025-03-31T19:18:24.885Z</lastmod>
<lastmod>2025-03-31T21:16:15.433Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.dpo.zephyr.html</loc>
<lastmod>2025-03-31T19:18:24.942Z</lastmod>
<lastmod>2025-03-31T21:16:15.489Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.metharme.html</loc>
<lastmod>2025-03-31T19:18:24.903Z</lastmod>
<lastmod>2025-03-31T21:16:15.451Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.orpo.chat_template.html</loc>
<lastmod>2025-03-31T19:18:24.982Z</lastmod>
<lastmod>2025-03-31T21:16:15.530Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.alpaca_w_system.html</loc>
<lastmod>2025-03-31T19:18:24.858Z</lastmod>
<lastmod>2025-03-31T21:16:15.407Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.model_shard_quant.html</loc>
<lastmod>2025-03-31T19:18:25.273Z</lastmod>
<lastmod>2025-03-31T21:16:15.820Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/cli.config.html</loc>
<lastmod>2025-03-31T19:18:24.677Z</lastmod>
<lastmod>2025-03-31T21:16:15.225Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.schemas.enums.html</loc>
<lastmod>2025-03-31T19:18:25.436Z</lastmod>
<lastmod>2025-03-31T21:16:15.985Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/cli.preprocess.html</loc>
<lastmod>2025-03-31T19:18:24.720Z</lastmod>
<lastmod>2025-03-31T21:16:15.267Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/core.chat.messages.html</loc>
<lastmod>2025-03-31T19:18:24.573Z</lastmod>
<lastmod>2025-03-31T21:16:15.119Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.dpo.chat_template.html</loc>
<lastmod>2025-03-31T19:18:24.919Z</lastmod>
<lastmod>2025-03-31T21:16:15.467Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.schemas.peft.html</loc>
<lastmod>2025-03-31T19:18:25.409Z</lastmod>
<lastmod>2025-03-31T21:16:15.958Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/train.html</loc>
<lastmod>2025-03-31T19:18:24.371Z</lastmod>
<lastmod>2025-03-31T21:16:14.917Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.messages.chat.html</loc>
<lastmod>2025-03-31T19:18:24.918Z</lastmod>
<lastmod>2025-03-31T21:16:15.466Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.orcamini.html</loc>
<lastmod>2025-03-31T19:18:24.907Z</lastmod>
<lastmod>2025-03-31T21:16:15.455Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.collators.mm_chat.html</loc>
<lastmod>2025-03-31T19:18:25.584Z</lastmod>
<lastmod>2025-03-31T21:16:16.134Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.kto.llama3.html</loc>
<lastmod>2025-03-31T19:18:24.953Z</lastmod>
<lastmod>2025-03-31T21:16:15.500Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.attention.mllama.html</loc>
<lastmod>2025-03-31T19:18:25.210Z</lastmod>
<lastmod>2025-03-31T21:16:15.753Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/cli.checks.html</loc>
<lastmod>2025-03-31T19:18:24.659Z</lastmod>
<lastmod>2025-03-31T21:16:15.208Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.transformers_fa_utils.html</loc>
<lastmod>2025-03-31T19:18:25.202Z</lastmod>
<lastmod>2025-03-31T21:16:15.745Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.llama_attn_hijack_xformers.html</loc>
<lastmod>2025-03-31T19:18:25.128Z</lastmod>
<lastmod>2025-03-31T21:16:15.672Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/core.trainers.dpo.trainer.html</loc>
<lastmod>2025-03-31T19:18:24.809Z</lastmod>
<lastmod>2025-03-31T21:16:15.360Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.user_defined.html</loc>
<lastmod>2025-03-31T19:18:24.866Z</lastmod>
<lastmod>2025-03-31T21:16:15.415Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/cli.args.html</loc>
<lastmod>2025-03-31T19:18:24.652Z</lastmod>
<lastmod>2025-03-31T21:16:15.202Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.llama2_chat.html</loc>
<lastmod>2025-03-31T19:18:24.879Z</lastmod>
<lastmod>2025-03-31T21:16:15.428Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/utils.schemas.config.html</loc>
<lastmod>2025-03-31T19:18:25.371Z</lastmod>
<lastmod>2025-03-31T21:16:15.920Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/core.trainers.grpo.trainer.html</loc>
<lastmod>2025-03-31T19:18:24.813Z</lastmod>
<lastmod>2025-03-31T21:16:15.363Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/core.chat.format.chatml.html</loc>
<lastmod>2025-03-31T19:18:24.574Z</lastmod>
<lastmod>2025-03-31T21:16:15.121Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/monkeypatch.lora_kernels.html</loc>
<lastmod>2025-03-31T19:18:25.176Z</lastmod>
<lastmod>2025-03-31T21:16:15.719Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/api/prompt_strategies.base.html</loc>
<lastmod>2025-03-31T19:18:24.815Z</lastmod>
<lastmod>2025-03-31T21:16:15.365Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/rlhf.html</loc>
<lastmod>2025-03-31T19:17:57.238Z</lastmod>
<lastmod>2025-03-31T21:15:37.299Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/cli.html</loc>
<lastmod>2025-03-31T19:17:57.234Z</lastmod>
<lastmod>2025-03-31T21:15:37.295Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/unsloth.html</loc>
<lastmod>2025-03-31T19:17:57.238Z</lastmod>
<lastmod>2025-03-31T21:15:37.299Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/fsdp_qlora.html</loc>
<lastmod>2025-03-31T19:17:57.235Z</lastmod>
<lastmod>2025-03-31T21:15:37.296Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/dataset_preprocessing.html</loc>
<lastmod>2025-03-31T19:17:57.235Z</lastmod>
<lastmod>2025-03-31T21:15:37.296Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/custom_integrations.html</loc>
<lastmod>2025-03-31T19:17:57.234Z</lastmod>
<lastmod>2025-03-31T21:15:37.295Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/mac.html</loc>
<lastmod>2025-03-31T19:17:57.238Z</lastmod>
<lastmod>2025-03-31T21:15:37.299Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/docker.html</loc>
<lastmod>2025-03-31T19:17:57.235Z</lastmod>
<lastmod>2025-03-31T21:15:37.296Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/ray-integration.html</loc>
<lastmod>2025-03-31T19:17:57.238Z</lastmod>
<lastmod>2025-03-31T21:15:37.299Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/dataset-formats/index.html</loc>
<lastmod>2025-03-31T19:17:57.234Z</lastmod>
<lastmod>2025-03-31T21:15:37.295Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/dataset-formats/conversation.html</loc>
<lastmod>2025-03-31T19:17:57.234Z</lastmod>
<lastmod>2025-03-31T21:15:37.295Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/dataset-formats/pretraining.html</loc>
<lastmod>2025-03-31T19:17:57.234Z</lastmod>
<lastmod>2025-03-31T21:15:37.295Z</lastmod>
</url>
<url>
<loc>https://axolotl-ai-cloud.github.io/axolotl/docs/dataset-formats/inst_tune.html</loc>
<lastmod>2025-03-31T19:17:57.234Z</lastmod>
<lastmod>2025-03-31T21:15:37.295Z</lastmod>
</url>
</urlset>