mirror of
https://github.com/labmlai/annotated_deep_learning_paper_implementations.git
synced 2025-08-14 17:41:37 +08:00
1028 lines
66 KiB
HTML
1028 lines
66 KiB
HTML
<!DOCTYPE html>
|
|
<html>
|
|
<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="This experiment trains a transformer XL model on tiny Shakespeare dataset."/>
|
|
|
|
<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="Transformer XL Experiment"/>
|
|
<meta name="twitter:description" content="This experiment trains a transformer XL model on tiny Shakespeare dataset."/>
|
|
<meta name="twitter:site" content="@labmlai"/>
|
|
<meta name="twitter:creator" content="@labmlai"/>
|
|
|
|
<meta property="og:url" content="https://nn.labml.ai/transformers/xl/experiment.html"/>
|
|
<meta property="og:title" content="Transformer XL Experiment"/>
|
|
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&v=4"/>
|
|
<meta property="og:site_name" content="LabML Neural Networks"/>
|
|
<meta property="og:type" content="object"/>
|
|
<meta property="og:title" content="Transformer XL Experiment"/>
|
|
<meta property="og:description" content="This experiment trains a transformer XL model on tiny Shakespeare dataset."/>
|
|
|
|
<title>Transformer XL Experiment</title>
|
|
<link rel="shortcut icon" href="/icon.png"/>
|
|
<link rel="stylesheet" href="../../pylit.css">
|
|
<link rel="canonical" href="https://nn.labml.ai/transformers/xl/experiment.html"/>
|
|
<!-- 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">transformers</a>
|
|
<a class="parent" href="index.html">xl</a>
|
|
</p>
|
|
<p>
|
|
|
|
<a href="https://github.com/lab-ml/labml_nn/tree/master/labml_nn/transformers/xl/experiment.py">
|
|
<img alt="Github"
|
|
src="https://img.shields.io/github/stars/lab-ml/nn?style=social"
|
|
style="max-width:100%;"/></a>
|
|
<a href="https://twitter.com/labmlai"
|
|
rel="nofollow">
|
|
<img alt="Twitter"
|
|
src="https://img.shields.io/twitter/follow/labmlai?style=social"
|
|
style="max-width:100%;"/></a>
|
|
</p>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-0'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-0'>#</a>
|
|
</div>
|
|
<h1>Transformer XL Experiment</h1>
|
|
<p>This is an annotated PyTorch experiment to train a transformer xl model.</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">11</span><span></span><span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">List</span>
|
|
<span class="lineno">12</span>
|
|
<span class="lineno">13</span><span class="kn">import</span> <span class="nn">torch</span>
|
|
<span class="lineno">14</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">15</span><span class="kn">from</span> <span class="nn">labml.logger</span> <span class="kn">import</span> <span class="n">Text</span>
|
|
<span class="lineno">16</span>
|
|
<span class="lineno">17</span><span class="kn">from</span> <span class="nn">labml</span> <span class="kn">import</span> <span class="n">experiment</span><span class="p">,</span> <span class="n">tracker</span><span class="p">,</span> <span class="n">monit</span><span class="p">,</span> <span class="n">logger</span>
|
|
<span class="lineno">18</span><span class="kn">from</span> <span class="nn">labml.configs</span> <span class="kn">import</span> <span class="n">option</span>
|
|
<span class="lineno">19</span><span class="kn">from</span> <span class="nn">labml_helpers.metrics.simple_state</span> <span class="kn">import</span> <span class="n">SimpleStateModule</span>
|
|
<span class="lineno">20</span><span class="kn">from</span> <span class="nn">labml_helpers.module</span> <span class="kn">import</span> <span class="n">Module</span>
|
|
<span class="lineno">21</span><span class="kn">from</span> <span class="nn">labml_helpers.train_valid</span> <span class="kn">import</span> <span class="n">BatchIndex</span><span class="p">,</span> <span class="n">hook_model_outputs</span>
|
|
<span class="lineno">22</span><span class="kn">from</span> <span class="nn">labml_nn.experiments.nlp_autoregression</span> <span class="kn">import</span> <span class="n">NLPAutoRegressionConfigs</span>
|
|
<span class="lineno">23</span><span class="kn">from</span> <span class="nn">labml_nn.transformers.xl</span> <span class="kn">import</span> <span class="n">TransformerXL</span><span class="p">,</span> <span class="n">TransformerXLLayer</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>
|
|
<h2>Auto regressive model</h2>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">26</span><span class="k">class</span> <span class="nc">AutoregressiveModel</span><span class="p">(</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>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">31</span> <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">n_vocab</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">d_model</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">transformer</span><span class="p">:</span> <span class="n">TransformerXL</span><span class="p">):</span>
|
|
<span class="lineno">32</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</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>Token embedding module</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">34</span> <span class="bp">self</span><span class="o">.</span><span class="n">src_embed</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Embedding</span><span class="p">(</span><span class="n">n_vocab</span><span class="p">,</span> <span class="n">d_model</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>Transformer</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">36</span> <span class="bp">self</span><span class="o">.</span><span class="n">transformer</span> <span class="o">=</span> <span class="n">transformer</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-5'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-5'>#</a>
|
|
</div>
|
|
<p>Final layer</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">38</span> <span class="bp">self</span><span class="o">.</span><span class="n">generator</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Linear</span><span class="p">(</span><span class="n">d_model</span><span class="p">,</span> <span class="n">n_vocab</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-6'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-6'>#</a>
|
|
</div>
|
|
<p>Masks</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">40</span> <span class="bp">self</span><span class="o">.</span><span class="n">mask_x</span> <span class="o">=</span> <span class="kc">None</span>
|
|
<span class="lineno">41</span> <span class="bp">self</span><span class="o">.</span><span class="n">mask_mem</span> <span class="o">=</span> <span class="kc">None</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">43</span> <span class="k">def</span> <span class="nf">forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">x</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">,</span> <span class="n">mem</span><span class="p">:</span> <span class="n">List</span><span class="p">[</span><span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">]):</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>Length of the memory</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">45</span> <span class="n">m_len</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">mem</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span> <span class="k">if</span> <span class="n">mem</span> <span class="k">else</span> <span class="mi">0</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>Create a subsequent mask for tokens</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">47</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">mask_x</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">or</span> <span class="bp">self</span><span class="o">.</span><span class="n">mask_x</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o"><</span> <span class="nb">len</span><span class="p">(</span><span class="n">x</span><span class="p">):</span>
|
|
<span class="lineno">48</span> <span class="kn">from</span> <span class="nn">labml_nn.transformers.utils</span> <span class="kn">import</span> <span class="n">subsequent_mask</span>
|
|
<span class="lineno">49</span> <span class="bp">self</span><span class="o">.</span><span class="n">mask_x</span> <span class="o">=</span> <span class="n">subsequent_mask</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">x</span><span class="p">))</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="n">x</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>Create an all ones (full visibility) mask for memory</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">51</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">mask_mem</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">or</span> <span class="bp">self</span><span class="o">.</span><span class="n">mask_mem</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="o"><</span> <span class="n">m_len</span> <span class="ow">or</span> <span class="bp">self</span><span class="o">.</span><span class="n">mask_mem</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o"><</span> <span class="nb">len</span><span class="p">(</span><span class="n">x</span><span class="p">):</span>
|
|
<span class="lineno">52</span> <span class="bp">self</span><span class="o">.</span><span class="n">mask_mem</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">mask_x</span><span class="o">.</span><span class="n">new_ones</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">x</span><span class="p">),</span> <span class="n">m_len</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-11'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-11'>#</a>
|
|
</div>
|
|
<p>Concatenate the masks if there is memory</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">55</span> <span class="k">if</span> <span class="n">m_len</span><span class="p">:</span>
|
|
<span class="lineno">56</span> <span class="n">mask</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">cat</span><span class="p">((</span><span class="bp">self</span><span class="o">.</span><span class="n">mask_mem</span><span class="p">[:</span><span class="nb">len</span><span class="p">(</span><span class="n">x</span><span class="p">),</span> <span class="p">:</span><span class="n">m_len</span><span class="p">],</span> <span class="bp">self</span><span class="o">.</span><span class="n">mask_x</span><span class="p">[:</span><span class="nb">len</span><span class="p">(</span><span class="n">x</span><span class="p">),</span> <span class="p">:</span><span class="nb">len</span><span class="p">(</span><span class="n">x</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-12'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-12'>#</a>
|
|
</div>
|
|
<p>Use the subsequent mask otherwise</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">58</span> <span class="k">else</span><span class="p">:</span>
|
|
<span class="lineno">59</span> <span class="n">mask</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">mask_x</span><span class="p">[:</span><span class="nb">len</span><span class="p">(</span><span class="n">x</span><span class="p">),</span> <span class="p">:</span><span class="nb">len</span><span class="p">(</span><span class="n">x</span><span class="p">)]</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-13'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-13'>#</a>
|
|
</div>
|
|
<p>Token embeddings</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">62</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">src_embed</span><span class="p">(</span><span class="n">x</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-14'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-14'>#</a>
|
|
</div>
|
|
<p>Run it through the transformer</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">64</span> <span class="n">res</span><span class="p">,</span> <span class="n">mem</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">transformer</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">mem</span><span class="p">,</span> <span class="n">mask</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>Generate logits of the next token</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">66</span> <span class="n">res</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">generator</span><span class="p">(</span><span class="n">res</span><span class="p">)</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">68</span> <span class="k">return</span> <span class="n">res</span><span class="p">,</span> <span class="n">mem</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-17'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-17'>#</a>
|
|
</div>
|
|
<h2>Configurations</h2>
|
|
<p>The default configs can and will be over-ridden when we start the experiment</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">71</span><span class="k">class</span> <span class="nc">Configs</span><span class="p">(</span><span class="n">NLPAutoRegressionConfigs</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>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">78</span> <span class="n">model</span><span class="p">:</span> <span class="n">AutoregressiveModel</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>Token embedding size</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">81</span> <span class="n">d_model</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">128</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>Number of attention heads</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">83</span> <span class="n">heads</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">4</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>Dropout probability</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">85</span> <span class="n">dropout</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.0</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>Number of features in FFN hidden layer</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">87</span> <span class="n">d_ff</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">256</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>Number of transformer layers</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">89</span> <span class="n">n_layers</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">6</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>Number of memories to keep</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">91</span> <span class="n">mem_len</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">128</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-25'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-25'>#</a>
|
|
</div>
|
|
<p>State module to maintain memories when switching between training and validation</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">93</span> <span class="n">memory</span> <span class="o">=</span> <span class="n">SimpleStateModule</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-26'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-26'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">95</span> <span class="k">def</span> <span class="nf">init</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-27'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-27'>#</a>
|
|
</div>
|
|
<p>Set tracker configurations</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">97</span> <span class="n">tracker</span><span class="o">.</span><span class="n">set_scalar</span><span class="p">(</span><span class="s2">"accuracy.*"</span><span class="p">,</span> <span class="kc">True</span><span class="p">)</span>
|
|
<span class="lineno">98</span> <span class="n">tracker</span><span class="o">.</span><span class="n">set_scalar</span><span class="p">(</span><span class="s2">"loss.*"</span><span class="p">,</span> <span class="kc">True</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-28'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-28'>#</a>
|
|
</div>
|
|
<p>Add a hook to log module outputs</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">100</span> <span class="n">hook_model_outputs</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">mode</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="s1">'model'</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-29'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-29'>#</a>
|
|
</div>
|
|
<p>This will keep the accuracy metric stats and memories separate for training and validation.</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">102</span> <span class="bp">self</span><span class="o">.</span><span class="n">state_modules</span> <span class="o">=</span> <span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">accuracy</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">memory</span><span class="p">]</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-30'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-30'>#</a>
|
|
</div>
|
|
<p>Concatenate memories and remove old memories to keep a maximum of
|
|
<code>mem_len</code> memories.</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">104</span> <span class="k">def</span> <span class="nf">merge_memory</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">old_mem</span><span class="p">,</span> <span class="n">new_mem</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-31'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-31'>#</a>
|
|
</div>
|
|
<p>If it’s configured not to use memory</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">111</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">mem_len</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
|
|
<span class="lineno">112</span> <span class="k">return</span> <span class="p">[]</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-32'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-32'>#</a>
|
|
</div>
|
|
<p>Concatenate with old memory</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">115</span> <span class="k">if</span> <span class="n">old_mem</span><span class="p">:</span>
|
|
<span class="lineno">116</span> <span class="n">mem</span> <span class="o">=</span> <span class="p">[</span><span class="n">torch</span><span class="o">.</span><span class="n">cat</span><span class="p">((</span><span class="n">m</span><span class="p">,</span> <span class="n">x</span><span class="p">),</span> <span class="n">dim</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span> <span class="k">for</span> <span class="n">m</span><span class="p">,</span> <span class="n">x</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span><span class="n">old_mem</span><span class="p">,</span> <span class="n">new_mem</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">mem</span> <span class="o">=</span> <span class="n">new_mem</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-33'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-33'>#</a>
|
|
</div>
|
|
<p>Truncate old memories</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">121</span> <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">mem</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span> <span class="o">></span> <span class="bp">self</span><span class="o">.</span><span class="n">mem_len</span><span class="p">:</span>
|
|
<span class="lineno">122</span> <span class="n">mem</span> <span class="o">=</span> <span class="p">[</span><span class="n">m</span><span class="p">[</span><span class="o">-</span><span class="bp">self</span><span class="o">.</span><span class="n">mem_len</span><span class="p">:]</span> <span class="k">for</span> <span class="n">m</span> <span class="ow">in</span> <span class="n">mem</span><span class="p">]</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-34'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-34'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">125</span> <span class="k">return</span> <span class="n">mem</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-35'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-35'>#</a>
|
|
</div>
|
|
<h3>Training/validation step</h3>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">127</span> <span class="k">def</span> <span class="nf">step</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">batch</span><span class="p">:</span> <span class="nb">any</span><span class="p">,</span> <span class="n">batch_idx</span><span class="p">:</span> <span class="n">BatchIndex</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-36'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-36'>#</a>
|
|
</div>
|
|
<p>Move data to the device</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">133</span> <span class="n">data</span><span class="p">,</span> <span class="n">target</span> <span class="o">=</span> <span class="n">batch</span><span class="p">[</span><span class="mi">0</span><span class="p">]</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> <span class="n">batch</span><span class="p">[</span><span class="mi">1</span><span class="p">]</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-37'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-37'>#</a>
|
|
</div>
|
|
<p>Update global step (number of tokens processed) when in training mode</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">136</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">mode</span><span class="o">.</span><span class="n">is_train</span><span class="p">:</span>
|
|
<span class="lineno">137</span> <span class="n">tracker</span><span class="o">.</span><span class="n">add_global_step</span><span class="p">(</span><span class="n">data</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">*</span> <span class="n">data</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">1</span><span class="p">])</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-38'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-38'>#</a>
|
|
</div>
|
|
<p>Whether to capture model outputs</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">140</span> <span class="k">with</span> <span class="bp">self</span><span class="o">.</span><span class="n">mode</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="n">is_log_activations</span><span class="o">=</span><span class="n">batch_idx</span><span class="o">.</span><span class="n">is_last</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-39'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-39'>#</a>
|
|
</div>
|
|
<p>Get memories</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">142</span> <span class="n">mem</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">memory</span><span class="o">.</span><span class="n">get</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-40'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-40'>#</a>
|
|
</div>
|
|
<p>Run the model</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">144</span> <span class="n">output</span><span class="p">,</span> <span class="n">new_mem</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="p">,</span> <span class="n">mem</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-41'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-41'>#</a>
|
|
</div>
|
|
<p>Merge memory</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">146</span> <span class="n">mem</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">merge_memory</span><span class="p">(</span><span class="n">mem</span><span class="p">,</span> <span class="n">new_mem</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-42'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-42'>#</a>
|
|
</div>
|
|
<p>Update memories</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">148</span> <span class="bp">self</span><span class="o">.</span><span class="n">memory</span><span class="o">.</span><span class="n">set</span><span class="p">(</span><span class="n">mem</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-43'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-43'>#</a>
|
|
</div>
|
|
<p>Calculate and log cross entropy loss</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">151</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="p">,</span> <span class="n">target</span><span class="p">)</span>
|
|
<span class="lineno">152</span> <span class="n">tracker</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="s2">"loss."</span><span class="p">,</span> <span class="n">loss</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-44'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-44'>#</a>
|
|
</div>
|
|
<p>Calculate and log accuracy</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">155</span> <span class="bp">self</span><span class="o">.</span><span class="n">accuracy</span><span class="p">(</span><span class="n">output</span><span class="p">,</span> <span class="n">target</span><span class="p">)</span>
|
|
<span class="lineno">156</span> <span class="bp">self</span><span class="o">.</span><span class="n">accuracy</span><span class="o">.</span><span class="n">track</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-45'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-45'>#</a>
|
|
</div>
|
|
<p>Train the model</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">159</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">mode</span><span class="o">.</span><span class="n">is_train</span><span class="p">:</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-46'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-46'>#</a>
|
|
</div>
|
|
<p>Calculate gradients</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">161</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-47'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-47'>#</a>
|
|
</div>
|
|
<p>Clip gradients</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">163</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="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">parameters</span><span class="p">(),</span> <span class="n">max_norm</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">grad_norm_clip</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-48'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-48'>#</a>
|
|
</div>
|
|
<p>Take optimizer step</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">165</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></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-49'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-49'>#</a>
|
|
</div>
|
|
<p>Log the model parameters and gradients on last batch of every epoch</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">167</span> <span class="k">if</span> <span class="n">batch_idx</span><span class="o">.</span><span class="n">is_last</span><span class="p">:</span>
|
|
<span class="lineno">168</span> <span class="n">tracker</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="s1">'model'</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-50'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-50'>#</a>
|
|
</div>
|
|
<p>Clear the gradients</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">170</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></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-51'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-51'>#</a>
|
|
</div>
|
|
<p>Save the tracked metrics</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">173</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-52'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-52'>#</a>
|
|
</div>
|
|
<h3>Sampling function to generate samples periodically while training</h3>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">175</span> <span class="k">def</span> <span class="nf">sample</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-53'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-53'>#</a>
|
|
</div>
|
|
<p>Starting prompt</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">181</span> <span class="n">prompt</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">prompt</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-54'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-54'>#</a>
|
|
</div>
|
|
<p>Collect output for printing</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">183</span> <span class="n">log</span> <span class="o">=</span> <span class="p">[(</span><span class="n">prompt</span><span class="p">,</span> <span class="n">Text</span><span class="o">.</span><span class="n">subtle</span><span class="p">)]</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-55'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-55'>#</a>
|
|
</div>
|
|
<p>memory</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">185</span> <span class="n">mem</span> <span class="o">=</span> <span class="p">[]</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-56'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-56'>#</a>
|
|
</div>
|
|
<p>Sample 25 tokens</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">187</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="n">monit</span><span class="o">.</span><span class="n">iterate</span><span class="p">(</span><span class="s1">'Sample'</span><span class="p">,</span> <span class="mi">25</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-57'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-57'>#</a>
|
|
</div>
|
|
<p>Tokenize the prompt</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">189</span> <span class="n">data</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">text</span><span class="o">.</span><span class="n">text_to_i</span><span class="p">(</span><span class="n">prompt</span><span class="p">)</span><span class="o">.</span><span class="n">unsqueeze</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-58'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-58'>#</a>
|
|
</div>
|
|
<p>Move to device</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">191</span> <span class="n">data</span> <span class="o">=</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-59'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-59'>#</a>
|
|
</div>
|
|
<p>Get the model output</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">193</span> <span class="n">output</span><span class="p">,</span> <span class="n">new_mem</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="p">,</span> <span class="n">mem</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-60'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-60'>#</a>
|
|
</div>
|
|
<p>Get the model prediction (greedy)</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">195</span> <span class="n">output</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><span class="o">.</span><span class="n">squeeze</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-61'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-61'>#</a>
|
|
</div>
|
|
<p>Add the prediction to prompt</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">197</span> <span class="n">prompt</span> <span class="o">+=</span> <span class="bp">self</span><span class="o">.</span><span class="n">prompt_separator</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">text</span><span class="o">.</span><span class="n">itos</span><span class="p">[</span><span class="n">output</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]]</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-62'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-62'>#</a>
|
|
</div>
|
|
<p>Only feed the last character to model in next iteration, rest will go in as memories</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">199</span> <span class="n">prompt</span> <span class="o">=</span> <span class="n">prompt</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">:]</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-63'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-63'>#</a>
|
|
</div>
|
|
<p>Add the prediction for logging</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">201</span> <span class="n">log</span> <span class="o">+=</span> <span class="p">[(</span><span class="bp">self</span><span class="o">.</span><span class="n">prompt_separator</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">text</span><span class="o">.</span><span class="n">itos</span><span class="p">[</span><span class="n">output</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]],</span> <span class="n">Text</span><span class="o">.</span><span class="n">value</span><span class="p">)]</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-64'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-64'>#</a>
|
|
</div>
|
|
<p>Update memory</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">203</span> <span class="n">mem</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">merge_memory</span><span class="p">(</span><span class="n">mem</span><span class="p">,</span> <span class="n">new_mem</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-65'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-65'>#</a>
|
|
</div>
|
|
<p>Print the sampled output</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">206</span> <span class="n">logger</span><span class="o">.</span><span class="n">log</span><span class="p">(</span><span class="n">log</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-66'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-66'>#</a>
|
|
</div>
|
|
<h3>Initialize the auto-regressive model</h3>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">209</span><span class="nd">@option</span><span class="p">(</span><span class="n">Configs</span><span class="o">.</span><span class="n">model</span><span class="p">)</span>
|
|
<span class="lineno">210</span><span class="k">def</span> <span class="nf">autoregressive_model</span><span class="p">(</span><span class="n">c</span><span class="p">:</span> <span class="n">Configs</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-67'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-67'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">214</span> <span class="kn">from</span> <span class="nn">labml_nn.transformers.xl</span> <span class="kn">import</span> <span class="n">RelativeMultiHeadAttention</span>
|
|
<span class="lineno">215</span> <span class="kn">from</span> <span class="nn">labml_nn.transformers.feed_forward</span> <span class="kn">import</span> <span class="n">FeedForward</span>
|
|
<span class="lineno">216</span> <span class="n">m</span> <span class="o">=</span> <span class="n">AutoregressiveModel</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">n_tokens</span><span class="p">,</span> <span class="n">c</span><span class="o">.</span><span class="n">d_model</span><span class="p">,</span> <span class="n">TransformerXL</span><span class="p">(</span>
|
|
<span class="lineno">217</span> <span class="n">TransformerXLLayer</span><span class="p">(</span><span class="n">d_model</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">d_model</span><span class="p">,</span>
|
|
<span class="lineno">218</span> <span class="n">self_attn</span><span class="o">=</span><span class="n">RelativeMultiHeadAttention</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">heads</span><span class="p">,</span> <span class="n">c</span><span class="o">.</span><span class="n">d_model</span><span class="p">,</span> <span class="n">c</span><span class="o">.</span><span class="n">dropout</span><span class="p">),</span>
|
|
<span class="lineno">219</span> <span class="n">feed_forward</span><span class="o">=</span><span class="n">FeedForward</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">d_model</span><span class="p">,</span> <span class="n">c</span><span class="o">.</span><span class="n">d_ff</span><span class="p">,</span> <span class="n">c</span><span class="o">.</span><span class="n">dropout</span><span class="p">),</span>
|
|
<span class="lineno">220</span> <span class="n">dropout_prob</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">dropout</span><span class="p">),</span> <span class="n">c</span><span class="o">.</span><span class="n">n_layers</span><span class="p">))</span>
|
|
<span class="lineno">221</span> <span class="k">return</span> <span class="n">m</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">device</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-68'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-68'>#</a>
|
|
</div>
|
|
<h3>Run the experiment</h3>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">224</span><span class="k">def</span> <span class="nf">main</span><span class="p">():</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-69'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-69'>#</a>
|
|
</div>
|
|
<p>Create experiment</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">229</span> <span class="n">experiment</span><span class="o">.</span><span class="n">create</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s2">"transformer_xl"</span><span class="p">,</span> <span class="n">comment</span><span class="o">=</span><span class="s1">''</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-70'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-70'>#</a>
|
|
</div>
|
|
<p>Create configs</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">231</span> <span class="n">conf</span> <span class="o">=</span> <span class="n">Configs</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-71'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-71'>#</a>
|
|
</div>
|
|
<p>Load configurations</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">233</span> <span class="n">experiment</span><span class="o">.</span><span class="n">configs</span><span class="p">(</span><span class="n">conf</span><span class="p">,</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-72'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-72'>#</a>
|
|
</div>
|
|
<p>A dictionary of configurations to override</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">235</span> <span class="p">{</span><span class="s1">'tokenizer'</span><span class="p">:</span> <span class="s1">'character'</span><span class="p">,</span>
|
|
<span class="lineno">236</span> <span class="s1">'text'</span><span class="p">:</span> <span class="s1">'tiny_shakespeare'</span><span class="p">,</span>
|
|
<span class="lineno">237</span> <span class="s1">'optimizer.learning_rate'</span><span class="p">:</span> <span class="mf">1.</span><span class="p">,</span>
|
|
<span class="lineno">238</span> <span class="s1">'optimizer.optimizer'</span><span class="p">:</span> <span class="s1">'Noam'</span><span class="p">,</span>
|
|
<span class="lineno">239</span> <span class="s1">'prompt'</span><span class="p">:</span> <span class="s1">'It is'</span><span class="p">,</span>
|
|
<span class="lineno">240</span> <span class="s1">'prompt_separator'</span><span class="p">:</span> <span class="s1">''</span><span class="p">,</span>
|
|
<span class="lineno">241</span>
|
|
<span class="lineno">242</span> <span class="s1">'train_loader'</span><span class="p">:</span> <span class="s1">'sequential_train_loader'</span><span class="p">,</span>
|
|
<span class="lineno">243</span> <span class="s1">'valid_loader'</span><span class="p">:</span> <span class="s1">'sequential_valid_loader'</span><span class="p">,</span>
|
|
<span class="lineno">244</span>
|
|
<span class="lineno">245</span> <span class="s1">'seq_len'</span><span class="p">:</span> <span class="mi">2</span><span class="p">,</span>
|
|
<span class="lineno">246</span> <span class="s1">'mem_len'</span><span class="p">:</span> <span class="mi">32</span><span class="p">,</span>
|
|
<span class="lineno">247</span> <span class="s1">'epochs'</span><span class="p">:</span> <span class="mi">128</span><span class="p">,</span>
|
|
<span class="lineno">248</span> <span class="s1">'batch_size'</span><span class="p">:</span> <span class="mi">32</span><span class="p">,</span>
|
|
<span class="lineno">249</span> <span class="s1">'inner_iterations'</span><span class="p">:</span> <span class="mi">25</span><span class="p">,</span>
|
|
<span class="lineno">250</span> <span class="p">})</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-73'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-73'>#</a>
|
|
</div>
|
|
<p>Set models for saving and loading</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">253</span> <span class="n">experiment</span><span class="o">.</span><span class="n">add_pytorch_models</span><span class="p">({</span><span class="s1">'model'</span><span class="p">:</span> <span class="n">conf</span><span class="o">.</span><span class="n">model</span><span class="p">})</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-74'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-74'>#</a>
|
|
</div>
|
|
<p>Start the experiment</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">256</span> <span class="k">with</span> <span class="n">experiment</span><span class="o">.</span><span class="n">start</span><span class="p">():</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-75'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-75'>#</a>
|
|
</div>
|
|
<p><code>TrainValidConfigs.run</code></p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">258</span> <span class="n">conf</span><span class="o">.</span><span class="n">run</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-76'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-76'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">262</span><span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s1">'__main__'</span><span class="p">:</span>
|
|
<span class="lineno">263</span> <span class="n">main</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
<script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.4/MathJax.js?config=TeX-AMS_HTML">
|
|
</script>
|
|
<!-- MathJax configuration -->
|
|
<script type="text/x-mathjax-config">
|
|
MathJax.Hub.Config({
|
|
tex2jax: {
|
|
inlineMath: [ ['$','$'] ],
|
|
displayMath: [ ['$$','$$'] ],
|
|
processEscapes: true,
|
|
processEnvironments: true
|
|
},
|
|
// Center justify equations in code and markdown cells. Elsewhere
|
|
// we use CSS to left justify single line equations in code cells.
|
|
displayAlign: 'center',
|
|
"HTML-CSS": { fonts: ["TeX"] }
|
|
});
|
|
</script>
|
|
<script>
|
|
function handleImages() {
|
|
var images = document.querySelectorAll('p>img')
|
|
|
|
console.log(images);
|
|
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> |