tocmo0nlord/axolotl
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Built site for gh-pages

Browse Source
This commit is contained in:
Quarto GHA Workflow Runner
2025-09-16 18:58:53 +00:00
parent db626de56e
commit 421eea620c
209 changed files with 4822 additions and 3261 deletions
Download Patch File Download Diff File Expand all files Collapse all files

51
docs/api/train.html
View File

@@ -2,7 +2,7 @@
<html xmlns="http://www.w3.org/1999/xhtml" lang="en" xml:lang="en"><head>
<meta charset="utf-8">
<meta name="generator" content="quarto-1.7.34">
<meta name="generator" content="quarto-1.8.24">
<meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes">
@@ -67,14 +67,15 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
<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/axe/axe-check.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-befe23ebd2f54d8af2c8a89d1a1611f1.css" rel="stylesheet" id="quarto-text-highlighting-styles">
<link href="../../site_libs/quarto-html/quarto-syntax-highlighting-dark-b651517ce65839d647a86e2780455cfb.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-e9895ec3143e9833a687747e8d39d226.min.css" rel="stylesheet" append-hash="true" id="quarto-bootstrap" data-mode="dark">
<link href="../../site_libs/bootstrap/bootstrap-f9d679a32da2b248d4ca48a0e58e089e.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,
@@ -124,7 +125,8 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
<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">
<img src="../../image/axolotl_logo_digital_white.svg" alt="" class="navbar-logo light-content">
<img src="../../image/axolotl_logo_digital_white.svg" alt="" class="navbar-logo dark-content">
</a>
</div>
<div class="quarto-navbar-tools tools-wide tools-end">
@@ -150,6 +152,10 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
<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="pt-lg-2 mt-2 text-left sidebar-header">
<a href="../../index.html" class="sidebar-logo-link">
</a>
</div>
<div class="sidebar-menu-container">
<ul class="list-unstyled mt-1">
<li class="sidebar-item">
@@ -585,7 +591,7 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
</table>
<section id="axolotl.train.create_model_card" class="level3">
<h3 class="anchored" data-anchor-id="axolotl.train.create_model_card">create_model_card</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>train.create_model_card(cfg, trainer)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<div class="code-copy-outer-scaffold"><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>train.create_model_card(cfg, trainer)</span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
<p>Create a model card for the trained model if needed.</p>
<section id="parameters" class="level4 doc-section doc-section-parameters">
<h4 class="doc-section doc-section-parameters anchored" data-anchor-id="parameters">Parameters</h4>
@@ -623,7 +629,7 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
</section>
<section id="axolotl.train.execute_training" class="level3">
<h3 class="anchored" data-anchor-id="axolotl.train.execute_training">execute_training</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>train.execute_training(cfg, trainer, resume_from_checkpoint)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<div class="code-copy-outer-scaffold"><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>train.execute_training(cfg, trainer, resume_from_checkpoint)</span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
<p>Execute the training process with appropriate SDP kernel configurations.</p>
<section id="parameters-1" class="level4 doc-section doc-section-parameters">
<h4 class="doc-section doc-section-parameters anchored" data-anchor-id="parameters-1">Parameters</h4>
@@ -667,13 +673,13 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
</section>
<section id="axolotl.train.handle_untrained_tokens_fix" class="level3">
<h3 class="anchored" data-anchor-id="axolotl.train.handle_untrained_tokens_fix">handle_untrained_tokens_fix</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>train.handle_untrained_tokens_fix(</span>
<div class="code-copy-outer-scaffold"><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>train.handle_untrained_tokens_fix(</span>
<span id="cb3-2"><a href="#cb3-2" aria-hidden="true" tabindex="-1"></a> cfg,</span>
<span id="cb3-3"><a href="#cb3-3" aria-hidden="true" tabindex="-1"></a> model,</span>
<span id="cb3-4"><a href="#cb3-4" aria-hidden="true" tabindex="-1"></a> tokenizer,</span>
<span id="cb3-5"><a href="#cb3-5" aria-hidden="true" tabindex="-1"></a> train_dataset,</span>
<span id="cb3-6"><a href="#cb3-6" aria-hidden="true" tabindex="-1"></a> safe_serialization,</span>
<span id="cb3-7"><a href="#cb3-7" aria-hidden="true" tabindex="-1"></a>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<span id="cb3-7"><a href="#cb3-7" aria-hidden="true" tabindex="-1"></a>)</span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
<p>Apply fixes for untrained tokens if configured.</p>
<section id="parameters-2" class="level4 doc-section doc-section-parameters">
<h4 class="doc-section doc-section-parameters anchored" data-anchor-id="parameters-2">Parameters</h4>
@@ -729,7 +735,7 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
</section>
<section id="axolotl.train.save_initial_configs" class="level3">
<h3 class="anchored" data-anchor-id="axolotl.train.save_initial_configs">save_initial_configs</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>train.save_initial_configs(cfg, tokenizer, model, peft_config, processor)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<div class="code-copy-outer-scaffold"><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>train.save_initial_configs(cfg, tokenizer, model, peft_config, processor)</span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
<p>Save initial configurations before training.</p>
<section id="parameters-3" class="level4 doc-section doc-section-parameters">
<h4 class="doc-section doc-section-parameters anchored" data-anchor-id="parameters-3">Parameters</h4>
@@ -779,7 +785,7 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
</section>
<section id="axolotl.train.save_trained_model" class="level3">
<h3 class="anchored" data-anchor-id="axolotl.train.save_trained_model">save_trained_model</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>train.save_trained_model(cfg, trainer, model, safe_serialization)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<div class="code-copy-outer-scaffold"><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>train.save_trained_model(cfg, trainer, model, safe_serialization)</span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
<p>Save the trained model according to configuration and training setup.</p>
<section id="parameters-4" class="level4 doc-section doc-section-parameters">
<h4 class="doc-section doc-section-parameters anchored" data-anchor-id="parameters-4">Parameters</h4>
@@ -829,7 +835,7 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
</section>
<section id="axolotl.train.setup_model_and_tokenizer" class="level3">
<h3 class="anchored" data-anchor-id="axolotl.train.setup_model_and_tokenizer">setup_model_and_tokenizer</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>train.setup_model_and_tokenizer(cfg)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<div class="code-copy-outer-scaffold"><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>train.setup_model_and_tokenizer(cfg)</span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
<p>Load the tokenizer, processor (for multimodal models), and model based on
configuration.</p>
<section id="parameters-5" class="level4 doc-section doc-section-parameters">
@@ -886,7 +892,7 @@ configuration.</p>
</section>
<section id="axolotl.train.setup_model_and_trainer" class="level3">
<h3 class="anchored" data-anchor-id="axolotl.train.setup_model_and_trainer">setup_model_and_trainer</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>train.setup_model_and_trainer(cfg, dataset_meta)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<div class="code-copy-outer-scaffold"><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>train.setup_model_and_trainer(cfg, dataset_meta)</span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
<p>Load model, tokenizer, trainer, etc. Helper function to encapsulate the full
trainer setup.</p>
<section id="parameters-6" class="level4 doc-section doc-section-parameters">
@@ -949,7 +955,7 @@ trainer setup.</p>
</section>
<section id="axolotl.train.setup_model_card" class="level3">
<h3 class="anchored" data-anchor-id="axolotl.train.setup_model_card">setup_model_card</h3>
<div class="sourceCode" id="cb8"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb8-1"><a href="#cb8-1" aria-hidden="true" tabindex="-1"></a>train.setup_model_card(cfg)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<div class="code-copy-outer-scaffold"><div class="sourceCode" id="cb8"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb8-1"><a href="#cb8-1" aria-hidden="true" tabindex="-1"></a>train.setup_model_card(cfg)</span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
<p>Set up the Axolotl badge and add the Axolotl config to the model card if available.</p>
<section id="parameters-7" class="level4 doc-section doc-section-parameters">
<h4 class="doc-section doc-section-parameters anchored" data-anchor-id="parameters-7">Parameters</h4>
@@ -981,7 +987,7 @@ trainer setup.</p>
</section>
<section id="axolotl.train.setup_reference_model" class="level3">
<h3 class="anchored" data-anchor-id="axolotl.train.setup_reference_model">setup_reference_model</h3>
<div class="sourceCode" id="cb9"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb9-1"><a href="#cb9-1" aria-hidden="true" tabindex="-1"></a>train.setup_reference_model(cfg, tokenizer)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<div class="code-copy-outer-scaffold"><div class="sourceCode" id="cb9"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb9-1"><a href="#cb9-1" aria-hidden="true" tabindex="-1"></a>train.setup_reference_model(cfg, tokenizer)</span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
<p>Set up the reference model for RL training if needed.</p>
<section id="parameters-8" class="level4 doc-section doc-section-parameters">
<h4 class="doc-section doc-section-parameters anchored" data-anchor-id="parameters-8">Parameters</h4>
@@ -1043,7 +1049,7 @@ trainer setup.</p>
</section>
<section id="axolotl.train.setup_signal_handler" class="level3">
<h3 class="anchored" data-anchor-id="axolotl.train.setup_signal_handler">setup_signal_handler</h3>
<div class="sourceCode" id="cb10"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb10-1"><a href="#cb10-1" aria-hidden="true" tabindex="-1"></a>train.setup_signal_handler(cfg, model, safe_serialization)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<div class="code-copy-outer-scaffold"><div class="sourceCode" id="cb10"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb10-1"><a href="#cb10-1" aria-hidden="true" tabindex="-1"></a>train.setup_signal_handler(cfg, model, safe_serialization)</span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
<p>Set up signal handler for graceful termination.</p>
<section id="parameters-9" class="level4 doc-section doc-section-parameters">
<h4 class="doc-section doc-section-parameters anchored" data-anchor-id="parameters-9">Parameters</h4>
@@ -1087,7 +1093,7 @@ trainer setup.</p>
</section>
<section id="axolotl.train.train" class="level3">
<h3 class="anchored" data-anchor-id="axolotl.train.train">train</h3>
<div class="sourceCode" id="cb11"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb11-1"><a href="#cb11-1" aria-hidden="true" tabindex="-1"></a>train.train(cfg, dataset_meta)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<div class="code-copy-outer-scaffold"><div class="sourceCode" id="cb11"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb11-1"><a href="#cb11-1" aria-hidden="true" tabindex="-1"></a>train.train(cfg, dataset_meta)</span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
<p>Train a model on the given dataset.</p>
<section id="parameters-10" class="level4 doc-section doc-section-parameters">
<h4 class="doc-section doc-section-parameters anchored" data-anchor-id="parameters-10">Parameters</h4>
@@ -1204,13 +1210,14 @@ trainer setup.</p>
e.clearSelection();
}
const getTextToCopy = function(trigger) {
const codeEl = trigger.previousElementSibling.cloneNode(true);
for (const childEl of codeEl.children) {
if (isCodeAnnotation(childEl)) {
childEl.remove();
}
const outerScaffold = trigger.parentElement.cloneNode(true);
const codeEl = outerScaffold.querySelector('code');
for (const childEl of codeEl.children) {
if (isCodeAnnotation(childEl)) {
childEl.remove();
}
return codeEl.innerText;
}
return codeEl.innerText;
}
const clipboard = new window.ClipboardJS('.code-copy-button:not([data-in-quarto-modal])', {
text: getTextToCopy