1327 lines
95 KiB
HTML
1327 lines
95 KiB
HTML
<!DOCTYPE html>
|
||
<html xmlns="http://www.w3.org/1999/xhtml" lang="en" xml:lang="en"><head>
|
||
|
||
<meta charset="utf-8">
|
||
<meta name="generator" content="quarto-1.7.31">
|
||
|
||
<meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes">
|
||
|
||
|
||
<title>core.training_args – 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 */
|
||
html { -webkit-text-size-adjust: 100%; }
|
||
pre > code.sourceCode { white-space: pre; position: relative; }
|
||
pre > code.sourceCode > span { display: inline-block; line-height: 1.25; }
|
||
pre > code.sourceCode > span:empty { height: 1.2em; }
|
||
.sourceCode { overflow: visible; }
|
||
code.sourceCode > span { color: inherit; text-decoration: inherit; }
|
||
div.sourceCode { margin: 1em 0; }
|
||
pre.sourceCode { margin: 0; }
|
||
@media screen {
|
||
div.sourceCode { overflow: auto; }
|
||
}
|
||
@media print {
|
||
pre > code.sourceCode { white-space: pre-wrap; }
|
||
pre > code.sourceCode > span { text-indent: -5em; padding-left: 5em; }
|
||
}
|
||
pre.numberSource code
|
||
{ counter-reset: source-line 0; }
|
||
pre.numberSource code > span
|
||
{ position: relative; left: -4em; counter-increment: source-line; }
|
||
pre.numberSource code > span > a:first-child::before
|
||
{ content: counter(source-line);
|
||
position: relative; left: -1em; text-align: right; vertical-align: baseline;
|
||
border: none; display: inline-block;
|
||
-webkit-touch-callout: none; -webkit-user-select: none;
|
||
-khtml-user-select: none; -moz-user-select: none;
|
||
-ms-user-select: none; user-select: none;
|
||
padding: 0 4px; width: 4em;
|
||
}
|
||
pre.numberSource { margin-left: 3em; padding-left: 4px; }
|
||
div.sourceCode
|
||
{ }
|
||
@media screen {
|
||
pre > code.sourceCode > span > a:first-child::before { text-decoration: underline; }
|
||
}
|
||
</style>
|
||
|
||
|
||
<script src="../../site_libs/quarto-nav/quarto-nav.js"></script>
|
||
<script src="../../site_libs/clipboard/clipboard.min.js"></script>
|
||
<script src="../../site_libs/quarto-search/autocomplete.umd.js"></script>
|
||
<script src="../../site_libs/quarto-search/fuse.min.js"></script>
|
||
<script src="../../site_libs/quarto-search/quarto-search.js"></script>
|
||
<meta name="quarto:offset" content="../../">
|
||
<link href="../../favicon.jpg" rel="icon" type="image/jpeg">
|
||
<script src="../../site_libs/quarto-html/quarto.js" type="module"></script>
|
||
<script src="../../site_libs/quarto-html/tabsets/tabsets.js" type="module"></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-8ef56b68f8fa1e9d2ba328e99e439f80.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-2288ecdcbf81d2ab6432743cedd71d9a.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>
|
||
<script async="" src="https://www.googletagmanager.com/gtag/js?id=G-9KYCVJBNMQ"></script>
|
||
|
||
<script type="text/javascript">
|
||
|
||
window.dataLayer = window.dataLayer || [];
|
||
function gtag(){dataLayer.push(arguments);}
|
||
gtag('js', new Date());
|
||
gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
|
||
</script>
|
||
|
||
|
||
<link rel="stylesheet" href="../../styles.css">
|
||
</head>
|
||
|
||
<body class="nav-sidebar docked nav-fixed quarto-light">
|
||
|
||
<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>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/dataset_loading.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Dataset Loading</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/qat.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Quantization Aware Training (QAT)</span></a>
|
||
</div>
|
||
</li>
|
||
<li class="sidebar-item">
|
||
<div class="sidebar-item-container">
|
||
<a href="../../docs/quantize.html" class="sidebar-item-text sidebar-link">
|
||
<span class="menu-text">Quantization with torchao</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.core.training_args" id="toc-axolotl.core.training_args" class="nav-link active" data-scroll-target="#axolotl.core.training_args">core.training_args</a>
|
||
<ul class="collapse">
|
||
<li><a href="#classes" id="toc-classes" class="nav-link" data-scroll-target="#classes">Classes</a>
|
||
<ul class="collapse">
|
||
<li><a href="#axolotl.core.training_args.AxolotlCPOConfig" id="toc-axolotl.core.training_args.AxolotlCPOConfig" class="nav-link" data-scroll-target="#axolotl.core.training_args.AxolotlCPOConfig">AxolotlCPOConfig</a></li>
|
||
<li><a href="#axolotl.core.training_args.AxolotlKTOConfig" id="toc-axolotl.core.training_args.AxolotlKTOConfig" class="nav-link" data-scroll-target="#axolotl.core.training_args.AxolotlKTOConfig">AxolotlKTOConfig</a></li>
|
||
<li><a href="#axolotl.core.training_args.AxolotlORPOConfig" id="toc-axolotl.core.training_args.AxolotlORPOConfig" class="nav-link" data-scroll-target="#axolotl.core.training_args.AxolotlORPOConfig">AxolotlORPOConfig</a></li>
|
||
<li><a href="#axolotl.core.training_args.AxolotlPRMConfig" id="toc-axolotl.core.training_args.AxolotlPRMConfig" class="nav-link" data-scroll-target="#axolotl.core.training_args.AxolotlPRMConfig">AxolotlPRMConfig</a></li>
|
||
<li><a href="#axolotl.core.training_args.AxolotlRewardConfig" id="toc-axolotl.core.training_args.AxolotlRewardConfig" class="nav-link" data-scroll-target="#axolotl.core.training_args.AxolotlRewardConfig">AxolotlRewardConfig</a></li>
|
||
<li><a href="#axolotl.core.training_args.AxolotlTrainingArguments" id="toc-axolotl.core.training_args.AxolotlTrainingArguments" class="nav-link" data-scroll-target="#axolotl.core.training_args.AxolotlTrainingArguments">AxolotlTrainingArguments</a></li>
|
||
<li><a href="#axolotl.core.training_args.AxolotlTrainingMixins" id="toc-axolotl.core.training_args.AxolotlTrainingMixins" class="nav-link" data-scroll-target="#axolotl.core.training_args.AxolotlTrainingMixins">AxolotlTrainingMixins</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.core.training_args" class="level1">
|
||
<h1>core.training_args</h1>
|
||
<p><code>core.training_args</code></p>
|
||
<p>extra axolotl specific training args</p>
|
||
<section id="classes" class="level2">
|
||
<h2 class="anchored" data-anchor-id="classes">Classes</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.core.training_args.AxolotlCPOConfig">AxolotlCPOConfig</a></td>
|
||
<td>CPO config for CPO training</td>
|
||
</tr>
|
||
<tr class="even">
|
||
<td><a href="#axolotl.core.training_args.AxolotlKTOConfig">AxolotlKTOConfig</a></td>
|
||
<td>KTO config for KTO training</td>
|
||
</tr>
|
||
<tr class="odd">
|
||
<td><a href="#axolotl.core.training_args.AxolotlORPOConfig">AxolotlORPOConfig</a></td>
|
||
<td>ORPO config for ORPO training</td>
|
||
</tr>
|
||
<tr class="even">
|
||
<td><a href="#axolotl.core.training_args.AxolotlPRMConfig">AxolotlPRMConfig</a></td>
|
||
<td>PRM config for PRM training</td>
|
||
</tr>
|
||
<tr class="odd">
|
||
<td><a href="#axolotl.core.training_args.AxolotlRewardConfig">AxolotlRewardConfig</a></td>
|
||
<td>Reward config for Reward training</td>
|
||
</tr>
|
||
<tr class="even">
|
||
<td><a href="#axolotl.core.training_args.AxolotlTrainingArguments">AxolotlTrainingArguments</a></td>
|
||
<td>Training arguments for Causal trainer</td>
|
||
</tr>
|
||
<tr class="odd">
|
||
<td><a href="#axolotl.core.training_args.AxolotlTrainingMixins">AxolotlTrainingMixins</a></td>
|
||
<td>Mixin class for the Axolotl training args.</td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
<section id="axolotl.core.training_args.AxolotlCPOConfig" class="level3">
|
||
<h3 class="anchored" data-anchor-id="axolotl.core.training_args.AxolotlCPOConfig">AxolotlCPOConfig</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.training_args.AxolotlCPOConfig(</span>
|
||
<span id="cb1-2"><a href="#cb1-2" aria-hidden="true" tabindex="-1"></a> <span class="va">self</span>,</span>
|
||
<span id="cb1-3"><a href="#cb1-3" aria-hidden="true" tabindex="-1"></a> model_type<span class="op">=</span><span class="va">None</span>,</span>
|
||
<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> 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> adam_beta3<span class="op">=</span><span class="va">None</span>,</span>
|
||
<span id="cb1-47"><a href="#cb1-47" aria-hidden="true" tabindex="-1"></a> adam_epsilon2<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_size<span class="op">=</span><span class="va">None</span>,</span>
|
||
<span id="cb1-49"><a href="#cb1-49" aria-hidden="true" tabindex="-1"></a> image_resize_algorithm<span class="op">=</span><span class="va">None</span>,</span>
|
||
<span id="cb1-50"><a href="#cb1-50" aria-hidden="true" tabindex="-1"></a> simpo_gamma<span class="op">=</span><span class="va">None</span>,</span>
|
||
<span id="cb1-51"><a href="#cb1-51" 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">
|
||
<h3 class="anchored" data-anchor-id="axolotl.core.training_args.AxolotlKTOConfig">AxolotlKTOConfig</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>core.training_args.AxolotlKTOConfig(</span>
|
||
<span id="cb2-2"><a href="#cb2-2" aria-hidden="true" tabindex="-1"></a> <span class="va">self</span>,</span>
|
||
<span id="cb2-3"><a href="#cb2-3" aria-hidden="true" tabindex="-1"></a> model_type<span class="op">=</span><span class="va">None</span>,</span>
|
||
<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> 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> adam_beta3<span class="op">=</span><span class="va">None</span>,</span>
|
||
<span id="cb2-47"><a href="#cb2-47" aria-hidden="true" tabindex="-1"></a> adam_epsilon2<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_size<span class="op">=</span><span class="va">None</span>,</span>
|
||
<span id="cb2-49"><a href="#cb2-49" aria-hidden="true" tabindex="-1"></a> image_resize_algorithm<span class="op">=</span><span class="va">None</span>,</span>
|
||
<span id="cb2-50"><a href="#cb2-50" 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>KTO config for KTO training</p>
|
||
</section>
|
||
<section id="axolotl.core.training_args.AxolotlORPOConfig" class="level3">
|
||
<h3 class="anchored" data-anchor-id="axolotl.core.training_args.AxolotlORPOConfig">AxolotlORPOConfig</h3>
|
||
<div class="sourceCode" id="cb3"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb3-1"><a href="#cb3-1" aria-hidden="true" tabindex="-1"></a>core.training_args.AxolotlORPOConfig(</span>
|
||
<span id="cb3-2"><a href="#cb3-2" aria-hidden="true" tabindex="-1"></a> <span class="va">self</span>,</span>
|
||
<span id="cb3-3"><a href="#cb3-3" aria-hidden="true" tabindex="-1"></a> model_type<span class="op">=</span><span class="va">None</span>,</span>
|
||
<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> 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> adam_beta3<span class="op">=</span><span class="va">None</span>,</span>
|
||
<span id="cb3-47"><a href="#cb3-47" aria-hidden="true" tabindex="-1"></a> adam_epsilon2<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_size<span class="op">=</span><span class="va">None</span>,</span>
|
||
<span id="cb3-49"><a href="#cb3-49" aria-hidden="true" tabindex="-1"></a> image_resize_algorithm<span class="op">=</span><span class="va">None</span>,</span>
|
||
<span id="cb3-50"><a href="#cb3-50" 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>ORPO config for ORPO training</p>
|
||
</section>
|
||
<section id="axolotl.core.training_args.AxolotlPRMConfig" class="level3">
|
||
<h3 class="anchored" data-anchor-id="axolotl.core.training_args.AxolotlPRMConfig">AxolotlPRMConfig</h3>
|
||
<div class="sourceCode" id="cb4"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb4-1"><a href="#cb4-1" aria-hidden="true" tabindex="-1"></a>core.training_args.AxolotlPRMConfig(</span>
|
||
<span id="cb4-2"><a href="#cb4-2" aria-hidden="true" tabindex="-1"></a> <span class="va">self</span>,</span>
|
||
<span id="cb4-3"><a href="#cb4-3" aria-hidden="true" tabindex="-1"></a> model_type<span class="op">=</span><span class="va">None</span>,</span>
|
||
<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> 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> adam_beta3<span class="op">=</span><span class="va">None</span>,</span>
|
||
<span id="cb4-47"><a href="#cb4-47" aria-hidden="true" tabindex="-1"></a> adam_epsilon2<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_size<span class="op">=</span><span class="va">None</span>,</span>
|
||
<span id="cb4-49"><a href="#cb4-49" aria-hidden="true" tabindex="-1"></a> image_resize_algorithm<span class="op">=</span><span class="va">None</span>,</span>
|
||
<span id="cb4-50"><a href="#cb4-50" 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>PRM config for PRM training</p>
|
||
</section>
|
||
<section id="axolotl.core.training_args.AxolotlRewardConfig" class="level3">
|
||
<h3 class="anchored" data-anchor-id="axolotl.core.training_args.AxolotlRewardConfig">AxolotlRewardConfig</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>core.training_args.AxolotlRewardConfig(</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> model_type<span class="op">=</span><span class="va">None</span>,</span>
|
||
<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> 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> adam_beta3<span class="op">=</span><span class="va">None</span>,</span>
|
||
<span id="cb5-47"><a href="#cb5-47" aria-hidden="true" tabindex="-1"></a> adam_epsilon2<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_size<span class="op">=</span><span class="va">None</span>,</span>
|
||
<span id="cb5-49"><a href="#cb5-49" aria-hidden="true" tabindex="-1"></a> image_resize_algorithm<span class="op">=</span><span class="va">None</span>,</span>
|
||
<span id="cb5-50"><a href="#cb5-50" 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>Reward config for Reward training</p>
|
||
</section>
|
||
<section id="axolotl.core.training_args.AxolotlTrainingArguments" class="level3">
|
||
<h3 class="anchored" data-anchor-id="axolotl.core.training_args.AxolotlTrainingArguments">AxolotlTrainingArguments</h3>
|
||
<div class="sourceCode" id="cb6"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb6-1"><a href="#cb6-1" aria-hidden="true" tabindex="-1"></a>core.training_args.AxolotlTrainingArguments(</span>
|
||
<span id="cb6-2"><a href="#cb6-2" aria-hidden="true" tabindex="-1"></a> <span class="va">self</span>,</span>
|
||
<span id="cb6-3"><a href="#cb6-3" aria-hidden="true" tabindex="-1"></a> model_type<span class="op">=</span><span class="va">None</span>,</span>
|
||
<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> 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> adam_beta3<span class="op">=</span><span class="va">None</span>,</span>
|
||
<span id="cb6-47"><a href="#cb6-47" aria-hidden="true" tabindex="-1"></a> adam_epsilon2<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_size<span class="op">=</span><span class="va">None</span>,</span>
|
||
<span id="cb6-49"><a href="#cb6-49" aria-hidden="true" tabindex="-1"></a> image_resize_algorithm<span class="op">=</span><span class="va">None</span>,</span>
|
||
<span id="cb6-50"><a href="#cb6-50" 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>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 can’t be used as a mixin.</p>
|
||
</section>
|
||
<section id="axolotl.core.training_args.AxolotlTrainingMixins" class="level3">
|
||
<h3 class="anchored" data-anchor-id="axolotl.core.training_args.AxolotlTrainingMixins">AxolotlTrainingMixins</h3>
|
||
<div class="sourceCode" id="cb7"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb7-1"><a href="#cb7-1" aria-hidden="true" tabindex="-1"></a>core.training_args.AxolotlTrainingMixins(</span>
|
||
<span id="cb7-2"><a href="#cb7-2" aria-hidden="true" tabindex="-1"></a> <span class="va">self</span>,</span>
|
||
<span id="cb7-3"><a href="#cb7-3" aria-hidden="true" tabindex="-1"></a> model_type<span class="op">=</span><span class="va">None</span>,</span>
|
||
<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> 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> adam_beta3<span class="op">=</span><span class="va">None</span>,</span>
|
||
<span id="cb7-47"><a href="#cb7-47" aria-hidden="true" tabindex="-1"></a> adam_epsilon2<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_size<span class="op">=</span><span class="va">None</span>,</span>
|
||
<span id="cb7-49"><a href="#cb7-49" aria-hidden="true" tabindex="-1"></a> image_resize_algorithm<span class="op">=</span><span class="va">None</span>,</span>
|
||
<span id="cb7-50"><a href="#cb7-50" 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>Mixin class for the Axolotl training args.</p>
|
||
|
||
|
||
</section>
|
||
</section>
|
||
</section>
|
||
|
||
</main> <!-- /main -->
|
||
<script id="quarto-html-after-body" type="application/javascript">
|
||
window.document.addEventListener("DOMContentLoaded", function (event) {
|
||
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:\/\/docs\.axolotl\.ai");
|
||
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> |