mirror of
https://github.com/labmlai/annotated_deep_learning_paper_implementations.git
synced 2025-08-15 10:11:39 +08:00
537 lines
41 KiB
HTML
537 lines
41 KiB
HTML
<!DOCTYPE html>
|
|
<html lang="en">
|
|
<head>
|
|
<meta http-equiv="content-type" content="text/html;charset=utf-8"/>
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0"/>
|
|
<meta name="description" content=""/>
|
|
|
|
<meta name="twitter:card" content="summary"/>
|
|
<meta name="twitter:image:src" content="https://avatars1.githubusercontent.com/u/64068543?s=400&v=4"/>
|
|
<meta name="twitter:title" content="trainer.py"/>
|
|
<meta name="twitter:description" content=""/>
|
|
<meta name="twitter:site" content="@labmlai"/>
|
|
<meta name="twitter:creator" content="@labmlai"/>
|
|
|
|
<meta property="og:url" content="https://nn.labml.ai/neox/utils/trainer.html"/>
|
|
<meta property="og:title" content="trainer.py"/>
|
|
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&v=4"/>
|
|
<meta property="og:site_name" content="trainer.py"/>
|
|
<meta property="og:type" content="object"/>
|
|
<meta property="og:title" content="trainer.py"/>
|
|
<meta property="og:description" content=""/>
|
|
|
|
<title>trainer.py</title>
|
|
<link rel="shortcut icon" href="/icon.png"/>
|
|
<link rel="stylesheet" href="../../pylit.css?v=1">
|
|
<link rel="canonical" href="https://nn.labml.ai/neox/utils/trainer.html"/>
|
|
<link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/katex@0.13.18/dist/katex.min.css" integrity="sha384-zTROYFVGOfTw7JV7KUu8udsvW2fx4lWOsCEDqhBreBwlHI4ioVRtmIvEThzJHGET" crossorigin="anonymous">
|
|
|
|
<!-- Global site tag (gtag.js) - Google Analytics -->
|
|
<script async src="https://www.googletagmanager.com/gtag/js?id=G-4V3HC8HBLH"></script>
|
|
<script>
|
|
window.dataLayer = window.dataLayer || [];
|
|
|
|
function gtag() {
|
|
dataLayer.push(arguments);
|
|
}
|
|
|
|
gtag('js', new Date());
|
|
|
|
gtag('config', 'G-4V3HC8HBLH');
|
|
</script>
|
|
</head>
|
|
<body>
|
|
<div id='container'>
|
|
<div id="background"></div>
|
|
<div class='section'>
|
|
<div class='docs'>
|
|
<p>
|
|
<a class="parent" href="/">home</a>
|
|
<a class="parent" href="../index.html">neox</a>
|
|
<a class="parent" href="index.html">utils</a>
|
|
</p>
|
|
<p>
|
|
<a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations" target="_blank">
|
|
<img alt="Github"
|
|
src="https://img.shields.io/github/stars/labmlai/annotated_deep_learning_paper_implementations?style=social"
|
|
style="max-width:100%;"/></a>
|
|
<a href="https://twitter.com/labmlai" rel="nofollow" target="_blank">
|
|
<img alt="Twitter"
|
|
src="https://img.shields.io/twitter/follow/labmlai?style=social"
|
|
style="max-width:100%;"/></a>
|
|
</p>
|
|
<p>
|
|
<a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations/tree/master/labml_nn/neox/utils/trainer.py" target="_blank">
|
|
View code on Github</a>
|
|
</p>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-0'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-0'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">1</span><span></span><span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Optional</span><span class="p">,</span> <span class="n">Set</span><span class="p">,</span> <span class="n">List</span>
|
|
<span class="lineno">2</span>
|
|
<span class="lineno">3</span><span class="kn">import</span> <span class="nn">torch.nn</span> <span class="k">as</span> <span class="nn">nn</span>
|
|
<span class="lineno">4</span><span class="kn">import</span> <span class="nn">torch.optim</span>
|
|
<span class="lineno">5</span><span class="kn">import</span> <span class="nn">torch.utils.data</span>
|
|
<span class="lineno">6</span><span class="kn">from</span> <span class="nn">torch.cuda</span> <span class="kn">import</span> <span class="n">amp</span>
|
|
<span class="lineno">7</span><span class="kn">from</span> <span class="nn">torch.cuda.amp</span> <span class="kn">import</span> <span class="n">GradScaler</span>
|
|
<span class="lineno">8</span>
|
|
<span class="lineno">9</span><span class="kn">from</span> <span class="nn">labml</span> <span class="kn">import</span> <span class="n">monit</span><span class="p">,</span> <span class="n">tracker</span>
|
|
<span class="lineno">10</span><span class="kn">from</span> <span class="nn">labml.configs</span> <span class="kn">import</span> <span class="n">BaseConfigs</span><span class="p">,</span> <span class="n">option</span>
|
|
<span class="lineno">11</span><span class="kn">from</span> <span class="nn">labml_nn.neox.utils.finetune</span> <span class="kn">import</span> <span class="n">FineTuner</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-1'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-1'>#</a>
|
|
</div>
|
|
<h3>Get trainable parameters</h3>
|
|
<ul><li><code class="highlight"><span></span><span class="n">model</span></code>
|
|
is the model to train </li>
|
|
<p><em>Returns</em> a list of parameters for training</p></ul>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">14</span><span class="k">def</span> <span class="nf">get_trainable_params</span><span class="p">(</span><span class="n">model</span><span class="p">:</span> <span class="n">nn</span><span class="o">.</span><span class="n">Module</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-2'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-2'>#</a>
|
|
</div>
|
|
<p>Get all parameters </p>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">23</span> <span class="n">params</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="n">model</span><span class="o">.</span><span class="n">parameters</span><span class="p">())</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-3'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-3'>#</a>
|
|
</div>
|
|
<p>Filter parameters that require gradients </p>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">25</span> <span class="n">trainable_params</span> <span class="o">=</span> <span class="p">[</span><span class="n">p</span> <span class="k">for</span> <span class="n">p</span> <span class="ow">in</span> <span class="n">params</span> <span class="k">if</span> <span class="n">p</span><span class="o">.</span><span class="n">requires_grad</span><span class="p">]</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-4'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-4'>#</a>
|
|
</div>
|
|
<p> </p>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">28</span> <span class="k">return</span> <span class="n">trainable_params</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-5'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-5'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">31</span><span class="k">class</span> <span class="nc">TrainerConf</span><span class="p">(</span><span class="n">BaseConfigs</span><span class="p">):</span>
|
|
<span class="lineno">32</span> <span class="n">model</span><span class="p">:</span> <span class="n">nn</span><span class="o">.</span><span class="n">Module</span>
|
|
<span class="lineno">33</span> <span class="n">layers</span><span class="p">:</span> <span class="n">List</span><span class="p">[</span><span class="n">nn</span><span class="o">.</span><span class="n">Module</span><span class="p">]</span>
|
|
<span class="lineno">34</span> <span class="n">optimizer</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">optim</span><span class="o">.</span><span class="n">Optimizer</span> <span class="o">=</span> <span class="s1">'Adam'</span>
|
|
<span class="lineno">35</span> <span class="n">train_loader</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">utils</span><span class="o">.</span><span class="n">data</span><span class="o">.</span><span class="n">DataLoader</span>
|
|
<span class="lineno">36</span> <span class="n">valid_loader</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">torch</span><span class="o">.</span><span class="n">utils</span><span class="o">.</span><span class="n">data</span><span class="o">.</span><span class="n">DataLoader</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
|
|
<span class="lineno">37</span> <span class="n">device</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">device</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">device</span><span class="p">(</span><span class="s1">'cuda:0'</span><span class="p">)</span>
|
|
<span class="lineno">38</span> <span class="n">scaler</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">GradScaler</span><span class="p">]</span> <span class="o">=</span> <span class="s1">'Default'</span>
|
|
<span class="lineno">39</span> <span class="n">is_amp</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span>
|
|
<span class="lineno">40</span> <span class="n">dtype</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">dtype</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">float16</span>
|
|
<span class="lineno">41</span>
|
|
<span class="lineno">42</span> <span class="n">is_clone_layers</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span>
|
|
<span class="lineno">43</span>
|
|
<span class="lineno">44</span> <span class="n">loss_func</span><span class="p">:</span> <span class="n">nn</span><span class="o">.</span><span class="n">Module</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">CrossEntropyLoss</span><span class="p">()</span>
|
|
<span class="lineno">45</span> <span class="n">checkpoints_per_epoch</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">0</span>
|
|
<span class="lineno">46</span> <span class="n">samples_per_epoch</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">0</span>
|
|
<span class="lineno">47</span>
|
|
<span class="lineno">48</span> <span class="n">grad_norm</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">float</span><span class="p">]</span> <span class="o">=</span> <span class="mf">1.0</span>
|
|
<span class="lineno">49</span> <span class="n">learning_rate</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">3e-4</span>
|
|
<span class="lineno">50</span> <span class="n">max_seq_len</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">1024</span>
|
|
<span class="lineno">51</span> <span class="n">batch_size</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">64</span>
|
|
<span class="lineno">52</span> <span class="n">epochs</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">16</span>
|
|
<span class="lineno">53</span>
|
|
<span class="lineno">54</span> <span class="n">n_gpus</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">cuda</span><span class="o">.</span><span class="n">device_count</span><span class="p">()</span>
|
|
<span class="lineno">55</span>
|
|
<span class="lineno">56</span> <span class="n">filter_layers</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Set</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-6'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-6'>#</a>
|
|
</div>
|
|
<ul><li><code class="highlight"><span></span><span class="n">dataset_split</span></code>
|
|
train/valid </li>
|
|
<li><code class="highlight"><span></span><span class="n">sample</span></code>
|
|
is the sample </li>
|
|
<p><em>Returns</em> the loss, output and the target</p></ul>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">58</span> <span class="k">def</span> <span class="nf">get_loss</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">sample</span><span class="p">,</span> <span class="n">dataset_split</span><span class="p">:</span> <span class="nb">str</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-7'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-7'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">64</span> <span class="n">data</span><span class="p">,</span> <span class="n">target</span> <span class="o">=</span> <span class="n">sample</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-8'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-8'>#</a>
|
|
</div>
|
|
<p>Forward pass </p>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">67</span> <span class="k">with</span> <span class="n">monit</span><span class="o">.</span><span class="n">section</span><span class="p">(</span><span class="s1">'Forward pass'</span><span class="p">):</span>
|
|
<span class="lineno">68</span> <span class="n">output</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="p">(</span><span class="n">data</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">device</span><span class="p">))</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-9'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-9'>#</a>
|
|
</div>
|
|
<p>Move targets to the same device as output </p>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">70</span> <span class="n">target</span> <span class="o">=</span> <span class="n">target</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="n">output</span><span class="o">.</span><span class="n">device</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-10'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-10'>#</a>
|
|
</div>
|
|
<p>Calculate loss </p>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">72</span> <span class="n">loss</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">loss_func</span><span class="p">(</span><span class="n">output</span><span class="o">.</span><span class="n">view</span><span class="p">(</span><span class="n">target</span><span class="o">.</span><span class="n">numel</span><span class="p">(),</span> <span class="o">-</span><span class="mi">1</span><span class="p">),</span> <span class="n">target</span><span class="o">.</span><span class="n">view</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">))</span>
|
|
<span class="lineno">73</span>
|
|
<span class="lineno">74</span> <span class="k">return</span> <span class="n">loss</span><span class="p">,</span> <span class="n">output</span><span class="p">,</span> <span class="n">target</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-11'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-11'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">76</span> <span class="k">def</span> <span class="nf">train</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="lineno">77</span> <span class="k">for</span> <span class="n">epoch</span> <span class="ow">in</span> <span class="n">monit</span><span class="o">.</span><span class="n">loop</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">epochs</span><span class="p">):</span>
|
|
<span class="lineno">78</span> <span class="bp">self</span><span class="o">.</span><span class="n">train_epoch</span><span class="p">()</span>
|
|
<span class="lineno">79</span> <span class="n">tracker</span><span class="o">.</span><span class="n">new_line</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-12'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-12'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">81</span> <span class="k">def</span> <span class="nf">sample</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">idx</span><span class="p">):</span>
|
|
<span class="lineno">82</span> <span class="k">pass</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-13'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-13'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">84</span> <span class="k">def</span> <span class="nf">save_checkpoint</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">idx</span><span class="p">):</span>
|
|
<span class="lineno">85</span> <span class="k">pass</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-14'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-14'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">87</span> <span class="k">def</span> <span class="nf">get_iterators</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-15'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-15'>#</a>
|
|
</div>
|
|
<p>Iterate through the batches </p>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">89</span> <span class="n">iterators</span> <span class="o">=</span> <span class="p">[(</span><span class="s1">'train'</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">train_loader</span><span class="p">)]</span>
|
|
<span class="lineno">90</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">valid_loader</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
|
|
<span class="lineno">91</span> <span class="n">iterators</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="s1">'valid'</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">valid_loader</span><span class="p">))</span>
|
|
<span class="lineno">92</span>
|
|
<span class="lineno">93</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">samples_per_epoch</span> <span class="o">></span> <span class="mi">0</span><span class="p">:</span>
|
|
<span class="lineno">94</span> <span class="n">iterators</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="bp">self</span><span class="o">.</span><span class="n">sample</span><span class="p">,</span> <span class="p">[</span><span class="n">i</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">samples_per_epoch</span><span class="p">)]))</span>
|
|
<span class="lineno">95</span>
|
|
<span class="lineno">96</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">checkpoints_per_epoch</span> <span class="o">></span> <span class="mi">0</span><span class="p">:</span>
|
|
<span class="lineno">97</span> <span class="n">iterators</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="bp">self</span><span class="o">.</span><span class="n">save_checkpoint</span><span class="p">,</span> <span class="p">[</span><span class="n">i</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">checkpoints_per_epoch</span><span class="p">)]))</span>
|
|
<span class="lineno">98</span>
|
|
<span class="lineno">99</span> <span class="k">return</span> <span class="n">iterators</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-16'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-16'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">101</span> <span class="k">def</span> <span class="nf">train_epoch</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-17'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-17'>#</a>
|
|
</div>
|
|
<p>Set model for train </p>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">103</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">train</span><span class="p">()</span>
|
|
<span class="lineno">104</span>
|
|
<span class="lineno">105</span> <span class="n">iterators</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_iterators</span><span class="p">()</span>
|
|
<span class="lineno">106</span> <span class="k">for</span> <span class="n">split_name</span><span class="p">,</span> <span class="n">sample</span> <span class="ow">in</span> <span class="n">monit</span><span class="o">.</span><span class="n">mix</span><span class="p">(</span><span class="mi">1024</span><span class="p">,</span> <span class="o">*</span><span class="n">iterators</span><span class="p">):</span>
|
|
<span class="lineno">107</span> <span class="k">if</span> <span class="n">split_name</span> <span class="o">==</span> <span class="s1">'train'</span><span class="p">:</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-18'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-18'>#</a>
|
|
</div>
|
|
<p>Set gradients to zero </p>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">109</span> <span class="bp">self</span><span class="o">.</span><span class="n">optimizer</span><span class="o">.</span><span class="n">zero_grad</span><span class="p">()</span>
|
|
<span class="lineno">110</span> <span class="n">tracker</span><span class="o">.</span><span class="n">add_global_step</span><span class="p">()</span>
|
|
<span class="lineno">111</span>
|
|
<span class="lineno">112</span> <span class="k">with</span> <span class="n">torch</span><span class="o">.</span><span class="n">set_grad_enabled</span><span class="p">(</span><span class="n">split_name</span> <span class="o">==</span> <span class="s1">'train'</span><span class="p">):</span>
|
|
<span class="lineno">113</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_amp</span><span class="p">:</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-19'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-19'>#</a>
|
|
</div>
|
|
<p>Forward pass </p>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">115</span> <span class="k">with</span> <span class="n">amp</span><span class="o">.</span><span class="n">autocast</span><span class="p">():</span>
|
|
<span class="lineno">116</span> <span class="n">loss</span><span class="p">,</span> <span class="n">output</span><span class="p">,</span> <span class="n">target</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_loss</span><span class="p">(</span><span class="n">sample</span><span class="p">,</span> <span class="n">split_name</span><span class="p">)</span>
|
|
<span class="lineno">117</span> <span class="k">else</span><span class="p">:</span>
|
|
<span class="lineno">118</span> <span class="n">loss</span><span class="p">,</span> <span class="n">output</span><span class="p">,</span> <span class="n">target</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_loss</span><span class="p">(</span><span class="n">sample</span><span class="p">,</span> <span class="n">split_name</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-20'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-20'>#</a>
|
|
</div>
|
|
<p>Get predictions </p>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">121</span> <span class="n">pred</span> <span class="o">=</span> <span class="n">output</span><span class="o">.</span><span class="n">argmax</span><span class="p">(</span><span class="n">dim</span><span class="o">=-</span><span class="mi">1</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-21'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-21'>#</a>
|
|
</div>
|
|
<p>Calculate accuracy </p>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">123</span> <span class="n">accuracy</span> <span class="o">=</span> <span class="n">pred</span><span class="o">.</span><span class="n">eq</span><span class="p">(</span><span class="n">target</span><span class="p">)</span><span class="o">.</span><span class="n">sum</span><span class="p">()</span><span class="o">.</span><span class="n">item</span><span class="p">()</span> <span class="o">/</span> <span class="p">(</span><span class="n">target</span> <span class="o">!=</span> <span class="o">-</span><span class="mi">100</span><span class="p">)</span><span class="o">.</span><span class="n">sum</span><span class="p">()</span>
|
|
<span class="lineno">124</span>
|
|
<span class="lineno">125</span> <span class="n">tracker</span><span class="o">.</span><span class="n">add</span><span class="p">({</span><span class="sa">f</span><span class="s1">'loss.</span><span class="si">{</span><span class="n">split_name</span><span class="si">}</span><span class="s1">'</span><span class="p">:</span> <span class="n">loss</span><span class="p">,</span> <span class="sa">f</span><span class="s1">'acc.</span><span class="si">{</span><span class="n">split_name</span><span class="si">}</span><span class="s1">'</span><span class="p">:</span> <span class="n">accuracy</span> <span class="o">*</span> <span class="mi">100</span><span class="p">})</span>
|
|
<span class="lineno">126</span>
|
|
<span class="lineno">127</span> <span class="k">if</span> <span class="n">split_name</span> <span class="o">==</span> <span class="s1">'train'</span><span class="p">:</span>
|
|
<span class="lineno">128</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">scaler</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-22'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-22'>#</a>
|
|
</div>
|
|
<p>Backward pass </p>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">130</span> <span class="n">loss</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">scaler</span><span class="o">.</span><span class="n">scale</span><span class="p">(</span><span class="n">loss</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-23'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-23'>#</a>
|
|
</div>
|
|
<p>tracker.add({'loss.scaled': loss}) </p>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">133</span> <span class="k">with</span> <span class="n">monit</span><span class="o">.</span><span class="n">section</span><span class="p">(</span><span class="s1">'Backward pass'</span><span class="p">):</span>
|
|
<span class="lineno">134</span> <span class="n">loss</span><span class="o">.</span><span class="n">backward</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-24'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-24'>#</a>
|
|
</div>
|
|
<p>Optimize </p>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">137</span> <span class="k">with</span> <span class="n">monit</span><span class="o">.</span><span class="n">section</span><span class="p">(</span><span class="s1">'Optimize'</span><span class="p">):</span>
|
|
<span class="lineno">138</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">scaler</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
|
<span class="lineno">139</span> <span class="bp">self</span><span class="o">.</span><span class="n">optimizer</span><span class="o">.</span><span class="n">step</span><span class="p">()</span>
|
|
<span class="lineno">140</span> <span class="k">else</span><span class="p">:</span>
|
|
<span class="lineno">141</span> <span class="bp">self</span><span class="o">.</span><span class="n">scaler</span><span class="o">.</span><span class="n">unscale_</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">optimizer</span><span class="p">)</span>
|
|
<span class="lineno">142</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">grad_norm</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
|
|
<span class="lineno">143</span> <span class="n">torch</span><span class="o">.</span><span class="n">nn</span><span class="o">.</span><span class="n">utils</span><span class="o">.</span><span class="n">clip_grad_norm_</span><span class="p">(</span><span class="n">get_trainable_params</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="p">),</span> <span class="bp">self</span><span class="o">.</span><span class="n">grad_norm</span><span class="p">)</span>
|
|
<span class="lineno">144</span> <span class="bp">self</span><span class="o">.</span><span class="n">scaler</span><span class="o">.</span><span class="n">step</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">optimizer</span><span class="p">)</span>
|
|
<span class="lineno">145</span> <span class="bp">self</span><span class="o">.</span><span class="n">scaler</span><span class="o">.</span><span class="n">update</span><span class="p">()</span>
|
|
<span class="lineno">146</span>
|
|
<span class="lineno">147</span> <span class="n">tracker</span><span class="o">.</span><span class="n">save</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-25'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-25'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">150</span><span class="nd">@option</span><span class="p">(</span><span class="n">TrainerConf</span><span class="o">.</span><span class="n">optimizer</span><span class="p">,</span> <span class="s1">'Adam'</span><span class="p">)</span>
|
|
<span class="lineno">151</span><span class="k">def</span> <span class="nf">adam_optimizer</span><span class="p">(</span><span class="n">c</span><span class="p">:</span> <span class="n">TrainerConf</span><span class="p">):</span>
|
|
<span class="lineno">152</span> <span class="k">if</span> <span class="n">c</span><span class="o">.</span><span class="n">dtype</span> <span class="o">==</span> <span class="n">torch</span><span class="o">.</span><span class="n">float32</span><span class="p">:</span>
|
|
<span class="lineno">153</span> <span class="k">return</span> <span class="n">torch</span><span class="o">.</span><span class="n">optim</span><span class="o">.</span><span class="n">Adam</span><span class="p">(</span><span class="n">get_trainable_params</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">model</span><span class="p">),</span> <span class="n">lr</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">learning_rate</span><span class="p">)</span>
|
|
<span class="lineno">154</span> <span class="k">elif</span> <span class="n">c</span><span class="o">.</span><span class="n">dtype</span> <span class="o">==</span> <span class="n">torch</span><span class="o">.</span><span class="n">float16</span><span class="p">:</span>
|
|
<span class="lineno">155</span> <span class="kn">from</span> <span class="nn">labml_nn.optimizers.adam_fp16</span> <span class="kn">import</span> <span class="n">AdamFP16</span>
|
|
<span class="lineno">156</span> <span class="k">return</span> <span class="n">AdamFP16</span><span class="p">(</span><span class="n">get_trainable_params</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">model</span><span class="p">),</span> <span class="n">lr</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">learning_rate</span><span class="p">)</span>
|
|
<span class="lineno">157</span> <span class="k">else</span><span class="p">:</span>
|
|
<span class="lineno">158</span> <span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">()</span>
|
|
<span class="lineno">159</span>
|
|
<span class="lineno">160</span>
|
|
<span class="lineno">161</span><span class="nd">@option</span><span class="p">(</span><span class="n">TrainerConf</span><span class="o">.</span><span class="n">optimizer</span><span class="p">,</span> <span class="s1">'SGD'</span><span class="p">)</span>
|
|
<span class="lineno">162</span><span class="k">def</span> <span class="nf">sgd_optimizer</span><span class="p">(</span><span class="n">c</span><span class="p">:</span> <span class="n">TrainerConf</span><span class="p">):</span>
|
|
<span class="lineno">163</span> <span class="k">return</span> <span class="n">torch</span><span class="o">.</span><span class="n">optim</span><span class="o">.</span><span class="n">SGD</span><span class="p">(</span><span class="n">get_trainable_params</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">model</span><span class="p">),</span> <span class="n">lr</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">learning_rate</span><span class="p">)</span>
|
|
<span class="lineno">164</span>
|
|
<span class="lineno">165</span>
|
|
<span class="lineno">166</span><span class="nd">@option</span><span class="p">(</span><span class="n">TrainerConf</span><span class="o">.</span><span class="n">scaler</span><span class="p">,</span> <span class="s1">'Default'</span><span class="p">)</span>
|
|
<span class="lineno">167</span><span class="k">def</span> <span class="nf">grad_scaler</span><span class="p">(</span><span class="n">c</span><span class="p">:</span> <span class="n">TrainerConf</span><span class="p">):</span>
|
|
<span class="lineno">168</span> <span class="k">if</span> <span class="ow">not</span> <span class="n">c</span><span class="o">.</span><span class="n">is_amp</span><span class="p">:</span>
|
|
<span class="lineno">169</span> <span class="k">return</span> <span class="kc">None</span>
|
|
<span class="lineno">170</span>
|
|
<span class="lineno">171</span> <span class="k">if</span> <span class="n">c</span><span class="o">.</span><span class="n">dtype</span> <span class="o">==</span> <span class="n">torch</span><span class="o">.</span><span class="n">float16</span><span class="p">:</span>
|
|
<span class="lineno">172</span> <span class="kn">from</span> <span class="nn">labml_nn.optimizers.adam_fp16</span> <span class="kn">import</span> <span class="n">GradScalerFP16</span>
|
|
<span class="lineno">173</span> <span class="k">return</span> <span class="n">GradScalerFP16</span><span class="p">()</span>
|
|
<span class="lineno">174</span> <span class="k">else</span><span class="p">:</span>
|
|
<span class="lineno">175</span> <span class="k">return</span> <span class="n">GradScaler</span><span class="p">()</span>
|
|
<span class="lineno">176</span>
|
|
<span class="lineno">177</span>
|
|
<span class="lineno">178</span><span class="k">class</span> <span class="nc">PipelineParallelTrainerConf</span><span class="p">(</span><span class="n">TrainerConf</span><span class="p">):</span>
|
|
<span class="lineno">179</span> <span class="n">is_checkpointing</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span>
|
|
<span class="lineno">180</span> <span class="n">chunks</span><span class="p">:</span> <span class="nb">int</span>
|
|
<span class="lineno">181</span>
|
|
<span class="lineno">182</span> <span class="n">fine_tuner</span><span class="p">:</span> <span class="n">FineTuner</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='footer'>
|
|
<a href="https://papers.labml.ai">Trending Research Papers</a>
|
|
<a href="https://labml.ai">labml.ai</a>
|
|
</div>
|
|
</div>
|
|
<script src=../../interactive.js?v=1"></script>
|
|
<script>
|
|
function handleImages() {
|
|
var images = document.querySelectorAll('p>img')
|
|
|
|
for (var i = 0; i < images.length; ++i) {
|
|
handleImage(images[i])
|
|
}
|
|
}
|
|
|
|
function handleImage(img) {
|
|
img.parentElement.style.textAlign = 'center'
|
|
|
|
var modal = document.createElement('div')
|
|
modal.id = 'modal'
|
|
|
|
var modalContent = document.createElement('div')
|
|
modal.appendChild(modalContent)
|
|
|
|
var modalImage = document.createElement('img')
|
|
modalContent.appendChild(modalImage)
|
|
|
|
var span = document.createElement('span')
|
|
span.classList.add('close')
|
|
span.textContent = 'x'
|
|
modal.appendChild(span)
|
|
|
|
img.onclick = function () {
|
|
console.log('clicked')
|
|
document.body.appendChild(modal)
|
|
modalImage.src = img.src
|
|
}
|
|
|
|
span.onclick = function () {
|
|
document.body.removeChild(modal)
|
|
}
|
|
}
|
|
|
|
handleImages()
|
|
</script>
|
|
</body>
|
|
</html> |