mirror of
https://github.com/labmlai/annotated_deep_learning_paper_implementations.git
synced 2025-08-15 02:07:56 +08:00
519 lines
46 KiB
HTML
519 lines
46 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 creates arithmetic problems."/>
|
|
|
|
<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="Arithmetic Dataset"/>
|
|
<meta name="twitter:description" content="This creates arithmetic problems."/>
|
|
<meta name="twitter:site" content="@labmlai"/>
|
|
<meta name="twitter:creator" content="@labmlai"/>
|
|
|
|
<meta property="og:url" content="https://nn.labml.ai/experiments/arithmetic_dataset.html"/>
|
|
<meta property="og:title" content="Arithmetic Dataset"/>
|
|
<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="Arithmetic Dataset"/>
|
|
<meta property="og:description" content="This creates arithmetic problems."/>
|
|
|
|
<title>Arithmetic Dataset</title>
|
|
<link rel="shortcut icon" href="/icon.png"/>
|
|
<link rel="stylesheet" href="../pylit.css?v=1">
|
|
<link rel="canonical" href="https://nn.labml.ai/experiments/arithmetic_dataset.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">experiments</a>
|
|
</p>
|
|
<p>
|
|
|
|
<a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations/tree/master/labml_nn/experiments/arithmetic_dataset.py">
|
|
<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">
|
|
<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>
|
|
<p><em>This is based on code by <a href="https://twitter.com/gharik">Georges Harik (@gharik)</a>.</em></p>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">11</span><span></span><span class="kn">import</span> <span class="nn">random</span>
|
|
<span class="lineno">12</span><span class="kn">import</span> <span class="nn">string</span>
|
|
<span class="lineno">13</span><span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">List</span>
|
|
<span class="lineno">14</span>
|
|
<span class="lineno">15</span><span class="kn">import</span> <span class="nn">torch</span>
|
|
<span class="lineno">16</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">17</span><span class="kn">from</span> <span class="nn">torch.utils.data</span> <span class="kn">import</span> <span class="n">DataLoader</span><span class="p">,</span> <span class="n">Dataset</span>
|
|
<span class="lineno">18</span>
|
|
<span class="lineno">19</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">logger</span><span class="p">,</span> <span class="n">tracker</span>
|
|
<span class="lineno">20</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">21</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="p">,</span> <span class="n">transpose_batch</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>Arithmetic Dataset</h2>
|
|
<p>This creates arithmetic addition problems and solutions with workings. We've only implemented addition so far.</p>
|
|
<p>It's based on a character level tokenization.</p>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">24</span><span class="k">class</span> <span class="nc">ArithmeticDataset</span><span class="p">(</span><span class="n">Dataset</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-2'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-2'>#</a>
|
|
</div>
|
|
<ul><li><code>seq_len</code> is the sequence length of generated math problems. We fill as many problems as possible upto this length :max_digits: is the maximum number of digits in the operand integers :n_sequences: is the number of sequences per epoch</li></ul>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">33</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">seq_len</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">max_digits</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">n_sequences</span><span class="p">:</span> <span class="nb">int</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>
|
|
|
|
</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">n_sequences</span> <span class="o">=</span> <span class="n">n_sequences</span>
|
|
<span class="lineno">41</span> <span class="bp">self</span><span class="o">.</span><span class="n">max_digits</span> <span class="o">=</span> <span class="n">max_digits</span>
|
|
<span class="lineno">42</span> <span class="bp">self</span><span class="o">.</span><span class="n">seq_len</span> <span class="o">=</span> <span class="n">seq_len</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>Token id to string </p>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">44</span> <span class="bp">self</span><span class="o">.</span><span class="n">itos</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="n">string</span><span class="o">.</span><span class="n">digits</span> <span class="o">+</span> <span class="s1">'xe =</span><span class="se">\n</span><span class="s1">?+;'</span><span class="p">)</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>Character to token id </p>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">46</span> <span class="bp">self</span><span class="o">.</span><span class="n">stoi</span> <span class="o">=</span> <span class="p">{</span><span class="n">c</span><span class="p">:</span> <span class="n">i</span> <span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">c</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">itos</span><span class="p">)}</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>
|
|
<p> Generates an integer with <code class="highlight"><span></span><span class="n">n_digit</span></code>
|
|
number of digits</p>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">48</span> <span class="nd">@staticmethod</span>
|
|
<span class="lineno">49</span> <span class="k">def</span> <span class="nf">make_int</span><span class="p">(</span><span class="n">n_digits</span><span class="p">:</span> <span class="nb">int</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">53</span> <span class="n">res</span> <span class="o">=</span> <span class="mi">0</span>
|
|
<span class="lineno">54</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="n">n_digits</span><span class="p">):</span>
|
|
<span class="lineno">55</span> <span class="n">d</span> <span class="o">=</span> <span class="n">random</span><span class="o">.</span><span class="n">randrange</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">11</span><span class="p">)</span> <span class="k">if</span> <span class="n">i</span> <span class="o">==</span> <span class="mi">0</span> <span class="k">else</span> <span class="n">random</span><span class="o">.</span><span class="n">randrange</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">11</span><span class="p">)</span>
|
|
<span class="lineno">56</span> <span class="n">res</span> <span class="o">=</span> <span class="n">res</span> <span class="o">*</span> <span class="mi">10</span> <span class="o">+</span> <span class="n">d</span>
|
|
<span class="lineno">57</span>
|
|
<span class="lineno">58</span> <span class="k">return</span> <span class="n">res</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-8'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-8'>#</a>
|
|
</div>
|
|
<p> Generates the workings for <code class="highlight"><span></span><span class="n">x</span> <span class="o">+</span> <span class="n">y</span></code>
|
|
. For example for <code class="highlight"><span></span><span class="mi">11</span><span class="o">+</span><span class="mi">29</span></code>
|
|
it generates <code class="highlight"><span></span><span class="mf">1e0</span><span class="o">+</span><span class="mf">9e0</span><span class="o">+</span><span class="mf">0e0</span><span class="o">=</span><span class="mf">10e0</span> <span class="mf">1e0</span><span class="o">+</span><span class="mf">2e0</span><span class="o">+</span><span class="mf">1e0</span><span class="o">=</span><span class="mf">4e0</span></code>
|
|
.</p>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">60</span> <span class="nd">@staticmethod</span>
|
|
<span class="lineno">61</span> <span class="k">def</span> <span class="nf">get_add_explanation</span><span class="p">(</span><span class="n">x</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">y</span><span class="p">:</span> <span class="nb">int</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>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">68</span> <span class="n">carry</span> <span class="o">=</span> <span class="mi">0</span>
|
|
<span class="lineno">69</span> <span class="n">e</span> <span class="o">=</span> <span class="mi">0</span>
|
|
<span class="lineno">70</span> <span class="n">explanation</span> <span class="o">=</span> <span class="p">[]</span>
|
|
<span class="lineno">71</span> <span class="k">while</span> <span class="n">x</span> <span class="o">></span> <span class="mi">0</span> <span class="ow">or</span> <span class="n">y</span> <span class="o">></span> <span class="mi">0</span> <span class="ow">or</span> <span class="n">carry</span> <span class="o">></span> <span class="mi">0</span><span class="p">:</span>
|
|
<span class="lineno">72</span> <span class="n">rx</span><span class="p">,</span> <span class="n">ry</span> <span class="o">=</span> <span class="n">x</span> <span class="o">%</span> <span class="mi">10</span><span class="p">,</span> <span class="n">y</span> <span class="o">%</span> <span class="mi">10</span>
|
|
<span class="lineno">73</span> <span class="n">total</span> <span class="o">=</span> <span class="n">rx</span> <span class="o">+</span> <span class="n">ry</span> <span class="o">+</span> <span class="n">carry</span>
|
|
<span class="lineno">74</span> <span class="n">explanation</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">rx</span><span class="si">}</span><span class="s2">e</span><span class="si">{</span><span class="n">e</span><span class="si">}</span><span class="s2">+</span><span class="si">{</span><span class="n">ry</span><span class="si">}</span><span class="s2">e</span><span class="si">{</span><span class="n">e</span><span class="si">}</span><span class="s2">+</span><span class="si">{</span><span class="n">carry</span><span class="si">}</span><span class="s2">e</span><span class="si">{</span><span class="n">e</span><span class="si">}</span><span class="s2">==</span><span class="si">{</span><span class="n">total</span><span class="si">}</span><span class="s2">e</span><span class="si">{</span><span class="n">e</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
|
|
<span class="lineno">75</span> <span class="n">x</span><span class="p">,</span> <span class="n">y</span><span class="p">,</span> <span class="n">carry</span> <span class="o">=</span> <span class="n">x</span> <span class="o">//</span> <span class="mi">10</span><span class="p">,</span> <span class="n">y</span> <span class="o">//</span> <span class="mi">10</span><span class="p">,</span> <span class="n">total</span> <span class="o">//</span> <span class="mi">10</span>
|
|
<span class="lineno">76</span> <span class="n">e</span> <span class="o">+=</span> <span class="mi">1</span>
|
|
<span class="lineno">77</span>
|
|
<span class="lineno">78</span> <span class="k">return</span> <span class="s1">' '</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">explanation</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-10'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-10'>#</a>
|
|
</div>
|
|
<p>Make a problem with a pre_explanation or not</p>
|
|
<p>Creates an arithmetic addition problem with workings and answer.</p>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">81</span> <span class="k">def</span> <span class="nf">make_add_problem</span><span class="p">(</span><span class="bp">self</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>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">85</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">make_int</span><span class="p">(</span><span class="n">n_digits</span><span class="o">=</span><span class="n">random</span><span class="o">.</span><span class="n">randrange</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">max_digits</span> <span class="o">+</span> <span class="mi">1</span><span class="p">))</span>
|
|
<span class="lineno">86</span> <span class="n">y</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">make_int</span><span class="p">(</span><span class="n">n_digits</span><span class="o">=</span><span class="n">random</span><span class="o">.</span><span class="n">randrange</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">max_digits</span> <span class="o">+</span> <span class="mi">1</span><span class="p">))</span>
|
|
<span class="lineno">87</span>
|
|
<span class="lineno">88</span> <span class="n">explanation</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_add_explanation</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">y</span><span class="p">)</span>
|
|
<span class="lineno">89</span> <span class="k">return</span> <span class="sa">f</span><span class="s2">"x=</span><span class="si">{</span><span class="n">x</span><span class="si">}</span><span class="s2">+</span><span class="si">{</span><span class="n">y</span><span class="si">}</span><span class="s2">; </span><span class="si">{</span><span class="n">explanation</span><span class="si">}</span><span class="s2"> x==</span><span class="si">{</span><span class="n">x</span> <span class="o">+</span> <span class="n">y</span><span class="si">}</span><span class="se">\n</span><span class="s2">"</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">91</span> <span class="k">def</span> <span class="nf">get_qa</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="lineno">92</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">make_int</span><span class="p">(</span><span class="n">n_digits</span><span class="o">=</span><span class="n">random</span><span class="o">.</span><span class="n">randrange</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">max_digits</span> <span class="o">+</span> <span class="mi">1</span><span class="p">))</span>
|
|
<span class="lineno">93</span> <span class="n">y</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">make_int</span><span class="p">(</span><span class="n">n_digits</span><span class="o">=</span><span class="n">random</span><span class="o">.</span><span class="n">randrange</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">max_digits</span> <span class="o">+</span> <span class="mi">1</span><span class="p">))</span>
|
|
<span class="lineno">94</span>
|
|
<span class="lineno">95</span> <span class="k">return</span> <span class="sa">f</span><span class="s1">'x=</span><span class="si">{</span><span class="n">x</span><span class="si">}</span><span class="s1">+</span><span class="si">{</span><span class="n">y</span><span class="si">}</span><span class="s1">;'</span><span class="p">,</span> <span class="sa">f</span><span class="s1">'</span><span class="si">{</span><span class="n">x</span> <span class="o">+</span> <span class="n">y</span><span class="si">}</span><span class="s1">'</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">97</span> <span class="k">def</span> <span class="nf">get_packed_math_input</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="lineno">98</span> <span class="n">s_enc</span> <span class="o">=</span> <span class="p">[]</span>
|
|
<span class="lineno">99</span> <span class="k">while</span> <span class="nb">len</span><span class="p">(</span><span class="n">s_enc</span><span class="p">)</span> <span class="o"><=</span> <span class="bp">self</span><span class="o">.</span><span class="n">seq_len</span><span class="p">:</span>
|
|
<span class="lineno">100</span> <span class="n">s_part</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">make_add_problem</span><span class="p">()</span>
|
|
<span class="lineno">101</span> <span class="n">s_part_enc</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">encode</span><span class="p">(</span><span class="s1">'?'</span> <span class="o">+</span> <span class="n">s_part</span><span class="p">)</span>
|
|
<span class="lineno">102</span> <span class="n">s_enc</span> <span class="o">=</span> <span class="n">s_enc</span> <span class="o">+</span> <span class="n">s_part_enc</span>
|
|
<span class="lineno">103</span> <span class="k">return</span> <span class="n">s_enc</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">105</span> <span class="k">def</span> <span class="nf">encode</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">s</span><span class="p">:</span> <span class="nb">str</span><span class="p">):</span>
|
|
<span class="lineno">106</span> <span class="k">return</span> <span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">stoi</span><span class="p">[</span><span class="n">c</span><span class="p">]</span> <span class="k">for</span> <span class="n">c</span> <span class="ow">in</span> <span class="n">s</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>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">108</span> <span class="k">def</span> <span class="nf">decode</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">arr</span><span class="p">:</span> <span class="n">List</span><span class="p">[</span><span class="nb">int</span><span class="p">]):</span>
|
|
<span class="lineno">109</span> <span class="k">return</span> <span class="s1">''</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="bp">self</span><span class="o">.</span><span class="n">itos</span><span class="p">[</span><span class="n">c</span><span class="p">]</span> <span class="k">for</span> <span class="n">c</span> <span class="ow">in</span> <span class="n">arr</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">111</span> <span class="k">def</span> <span class="fm">__getitem__</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">112</span> <span class="n">s</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">tensor</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">get_packed_math_input</span><span class="p">())</span>
|
|
<span class="lineno">113</span> <span class="k">return</span> <span class="n">s</span><span class="p">[:</span><span class="bp">self</span><span class="o">.</span><span class="n">seq_len</span><span class="p">],</span> <span class="n">s</span><span class="p">[</span><span class="mi">1</span><span class="p">:</span><span class="bp">self</span><span class="o">.</span><span class="n">seq_len</span> <span class="o">+</span> <span class="mi">1</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>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">115</span> <span class="k">def</span> <span class="fm">__len__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="lineno">116</span> <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">n_sequences</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">119</span><span class="k">class</span> <span class="nc">ArithmeticAutoregression</span><span class="p">(</span><span class="n">NLPAutoRegressionConfigs</span><span class="p">):</span>
|
|
<span class="lineno">120</span> <span class="n">max_digits</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">4</span>
|
|
<span class="lineno">121</span> <span class="n">train_sequences_per_epoch</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">2</span> <span class="o">**</span> <span class="mi">12</span>
|
|
<span class="lineno">122</span> <span class="n">train_loader</span><span class="p">:</span> <span class="n">DataLoader</span> <span class="o">=</span> <span class="s1">'arithmetic_train_loader'</span>
|
|
<span class="lineno">123</span> <span class="n">n_tests</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">32</span>
|
|
<span class="lineno">124</span> <span class="n">validator</span> <span class="o">=</span> <span class="kc">None</span>
|
|
<span class="lineno">125</span> <span class="n">inner_iterations</span> <span class="o">=</span> <span class="mi">4</span>
|
|
<span class="lineno">126</span>
|
|
<span class="lineno">127</span> <span class="n">n_tokens</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">ArithmeticDataset</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span><span class="o">.</span><span class="n">itos</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-19'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-19'>#</a>
|
|
</div>
|
|
<h3>Sampling function to generate samples periodically while training</h3>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">129</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-20'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-20'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">134</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">training_loop</span><span class="o">.</span><span class="n">idx</span> <span class="o"><</span> <span class="mi">1</span><span class="p">:</span>
|
|
<span class="lineno">135</span> <span class="k">return</span>
|
|
<span class="lineno">136</span>
|
|
<span class="lineno">137</span> <span class="n">dataset</span> <span class="o">=</span> <span class="n">ArithmeticDataset</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">seq_len</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">max_digits</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
|
|
<span class="lineno">138</span> <span class="n">qa</span> <span class="o">=</span> <span class="p">[</span><span class="n">dataset</span><span class="o">.</span><span class="n">get_qa</span><span class="p">()</span> <span class="k">for</span> <span class="n">_</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">n_tests</span><span class="p">)]</span>
|
|
<span class="lineno">139</span> <span class="n">prompt</span> <span class="o">=</span> <span class="p">[</span><span class="n">p</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="k">for</span> <span class="n">p</span> <span class="ow">in</span> <span class="n">qa</span><span class="p">]</span>
|
|
<span class="lineno">140</span>
|
|
<span class="lineno">141</span> <span class="n">data</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">tensor</span><span class="p">([[</span><span class="n">dataset</span><span class="o">.</span><span class="n">stoi</span><span class="p">[</span><span class="n">p</span><span class="p">[</span><span class="mi">0</span><span class="p">]]</span> <span class="k">for</span> <span class="n">p</span> <span class="ow">in</span> <span class="n">prompt</span><span class="p">]])</span>
|
|
<span class="lineno">142</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>
|
|
<span class="lineno">143</span>
|
|
<span class="lineno">144</span> <span class="n">finished</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">zeros</span><span class="p">((</span><span class="nb">len</span><span class="p">(</span><span class="n">prompt</span><span class="p">),))</span><span class="o">.</span><span class="n">bool</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="lineno">145</span> <span class="n">new_line</span> <span class="o">=</span> <span class="n">dataset</span><span class="o">.</span><span class="n">stoi</span><span class="p">[</span><span class="s1">'</span><span class="se">\n</span><span class="s1">'</span><span class="p">]</span>
|
|
<span class="lineno">146</span>
|
|
<span class="lineno">147</span> <span class="n">results</span> <span class="o">=</span> <span class="p">[</span><span class="n">p</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="k">for</span> <span class="n">p</span> <span class="ow">in</span> <span class="n">prompt</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>Sample 25 tokens </p>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">150</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="bp">self</span><span class="o">.</span><span class="n">seq_len</span> <span class="o">-</span> <span class="mi">1</span><span class="p">):</span>
|
|
<span class="lineno">151</span> <span class="k">if</span> <span class="n">finished</span><span class="o">.</span><span class="n">sum</span><span class="p">()</span> <span class="o">==</span> <span class="nb">len</span><span class="p">(</span><span class="n">finished</span><span class="p">):</span>
|
|
<span class="lineno">152</span> <span class="k">continue</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>Tokenize the prompt Get the model output </p>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">156</span> <span class="n">output</span><span class="p">,</span> <span class="o">*</span><span class="n">_</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></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-23'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-23'>#</a>
|
|
</div>
|
|
<p>Get the model prediction (greedy) </p>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">158</span> <span class="n">output</span> <span class="o">=</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="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="lineno">159</span>
|
|
<span class="lineno">160</span> <span class="n">finished</span> <span class="o">=</span> <span class="n">finished</span> <span class="o">|</span> <span class="p">(</span><span class="n">output</span> <span class="o">==</span> <span class="n">new_line</span><span class="p">)</span>
|
|
<span class="lineno">161</span> <span class="k">if</span> <span class="n">finished</span><span class="o">.</span><span class="n">sum</span><span class="p">()</span> <span class="o">==</span> <span class="nb">len</span><span class="p">(</span><span class="n">finished</span><span class="p">):</span>
|
|
<span class="lineno">162</span> <span class="k">continue</span>
|
|
<span class="lineno">163</span>
|
|
<span class="lineno">164</span> <span class="k">for</span> <span class="n">j</span><span class="p">,</span> <span class="n">p</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">prompt</span><span class="p">):</span>
|
|
<span class="lineno">165</span> <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">p</span><span class="p">)</span> <span class="o">></span> <span class="n">i</span> <span class="o">+</span> <span class="mi">1</span><span class="p">:</span>
|
|
<span class="lineno">166</span> <span class="n">output</span><span class="p">[</span><span class="n">j</span><span class="p">]</span> <span class="o">=</span> <span class="n">dataset</span><span class="o">.</span><span class="n">stoi</span><span class="p">[</span><span class="n">p</span><span class="p">[</span><span class="n">i</span> <span class="o">+</span> <span class="mi">1</span><span class="p">]]</span>
|
|
<span class="lineno">167</span>
|
|
<span class="lineno">168</span> <span class="n">data</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="n">data</span><span class="p">,</span> <span class="n">output</span><span class="p">[</span><span class="kc">None</span><span class="p">,</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="lineno">169</span>
|
|
<span class="lineno">170</span> <span class="k">for</span> <span class="n">j</span><span class="p">,</span> <span class="n">c</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">output</span><span class="p">):</span>
|
|
<span class="lineno">171</span> <span class="n">results</span><span class="p">[</span><span class="n">j</span><span class="p">]</span> <span class="o">+=</span> <span class="n">dataset</span><span class="o">.</span><span class="n">itos</span><span class="p">[</span><span class="n">c</span><span class="p">]</span>
|
|
<span class="lineno">172</span>
|
|
<span class="lineno">173</span> <span class="n">results</span> <span class="o">=</span> <span class="p">[</span><span class="n">r</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">'</span><span class="se">\n</span><span class="s1">'</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span> <span class="k">for</span> <span class="n">r</span> <span class="ow">in</span> <span class="n">results</span><span class="p">]</span>
|
|
<span class="lineno">174</span>
|
|
<span class="lineno">175</span> <span class="n">res_sample</span> <span class="o">=</span> <span class="n">results</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">';'</span><span class="p">)</span>
|
|
<span class="lineno">176</span> <span class="n">logger</span><span class="o">.</span><span class="n">log</span><span class="p">([(</span><span class="n">res_sample</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">Text</span><span class="o">.</span><span class="n">key</span><span class="p">),</span> <span class="p">(</span><span class="s1">';'</span><span class="p">,</span> <span class="n">Text</span><span class="o">.</span><span class="n">subtle</span><span class="p">),</span> <span class="p">(</span><span class="s1">';'</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">res_sample</span><span class="p">[</span><span class="mi">1</span><span class="p">:]),</span> <span class="n">Text</span><span class="o">.</span><span class="n">none</span><span class="p">)])</span>
|
|
<span class="lineno">177</span>
|
|
<span class="lineno">178</span> <span class="n">results</span> <span class="o">=</span> <span class="p">[</span><span class="n">r</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">'x=='</span><span class="p">)[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span> <span class="k">for</span> <span class="n">r</span> <span class="ow">in</span> <span class="n">results</span><span class="p">]</span>
|
|
<span class="lineno">179</span>
|
|
<span class="lineno">180</span> <span class="n">correct</span> <span class="o">=</span> <span class="mi">0</span>
|
|
<span class="lineno">181</span> <span class="k">for</span> <span class="n">r</span><span class="p">,</span> <span class="n">_qa</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span><span class="n">results</span><span class="p">,</span> <span class="n">qa</span><span class="p">):</span>
|
|
<span class="lineno">182</span> <span class="k">if</span> <span class="n">r</span> <span class="o">==</span> <span class="n">_qa</span><span class="p">[</span><span class="mi">1</span><span class="p">]:</span>
|
|
<span class="lineno">183</span> <span class="n">correct</span> <span class="o">+=</span> <span class="mi">1</span>
|
|
<span class="lineno">184</span>
|
|
<span class="lineno">185</span> <span class="n">tracker</span><span class="o">.</span><span class="n">save</span><span class="p">(</span><span class="s1">'score'</span><span class="p">,</span> <span class="n">correct</span> <span class="o">/</span> <span class="nb">len</span><span class="p">(</span><span class="n">results</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>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">188</span><span class="nd">@option</span><span class="p">(</span><span class="n">ArithmeticAutoregression</span><span class="o">.</span><span class="n">train_loader</span><span class="p">)</span>
|
|
<span class="lineno">189</span><span class="k">def</span> <span class="nf">arithmetic_train_loader</span><span class="p">(</span><span class="n">c</span><span class="p">:</span> <span class="n">ArithmeticAutoregression</span><span class="p">):</span>
|
|
<span class="lineno">190</span> <span class="k">return</span> <span class="n">DataLoader</span><span class="p">(</span><span class="n">ArithmeticDataset</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">seq_len</span><span class="p">,</span> <span class="n">c</span><span class="o">.</span><span class="n">max_digits</span><span class="p">,</span> <span class="n">c</span><span class="o">.</span><span class="n">train_sequences_per_epoch</span><span class="p">),</span>
|
|
<span class="lineno">191</span> <span class="n">batch_size</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">batch_size</span><span class="p">,</span>
|
|
<span class="lineno">192</span> <span class="n">collate_fn</span><span class="o">=</span><span class="n">transpose_batch</span><span class="p">,</span>
|
|
<span class="lineno">193</span> <span class="n">num_workers</span><span class="o">=</span><span class="mi">4</span><span class="p">)</span>
|
|
<span class="lineno">194</span>
|
|
<span class="lineno">195</span>
|
|
<span class="lineno">196</span><span class="k">def</span> <span class="nf">_test</span><span class="p">():</span>
|
|
<span class="lineno">197</span> <span class="n">dataset</span> <span class="o">=</span> <span class="n">ArithmeticDataset</span><span class="p">(</span><span class="mi">256</span><span class="p">,</span> <span class="mi">8</span><span class="p">,</span> <span class="mi">10</span><span class="p">)</span>
|
|
<span class="lineno">198</span>
|
|
<span class="lineno">199</span> <span class="nb">print</span><span class="p">(</span><span class="n">dataset</span><span class="o">.</span><span class="n">decode</span><span class="p">(</span><span class="n">dataset</span><span class="o">.</span><span class="n">get_packed_math_input</span><span class="p">()))</span>
|
|
<span class="lineno">200</span>
|
|
<span class="lineno">201</span>
|
|
<span class="lineno">202</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">203</span> <span class="n">_test</span><span class="p">()</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> |