chore: import upstream snapshot with attribution
This commit is contained in:
wehub-resource-sync
@@ -0,0 +1,908 @@
|
||||
<!DOCTYPE html>
|
||||
<html lang="zh">
|
||||
<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="GPT 模型和训练代码的实现/教程。"/>
|
||||
|
||||
<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="GPT"/>
|
||||
<meta name="twitter:description" content="GPT 模型和训练代码的实现/教程。"/>
|
||||
<meta name="twitter:site" content="@labmlai"/>
|
||||
<meta name="twitter:creator" content="@labmlai"/>
|
||||
|
||||
<meta property="og:url" content="https://nn.labml.ai/transformers/gpt/index.html"/>
|
||||
<meta property="og:title" content="GPT"/>
|
||||
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&v=4"/>
|
||||
<meta property="og:site_name" content="GPT"/>
|
||||
<meta property="og:type" content="object"/>
|
||||
<meta property="og:title" content="GPT"/>
|
||||
<meta property="og:description" content="GPT 模型和训练代码的实现/教程。"/>
|
||||
|
||||
<title>GPT</title>
|
||||
<link rel="shortcut icon" href="/icon.png"/>
|
||||
<link rel="stylesheet" href="../../pylit.css?v=1">
|
||||
<link rel="canonical" href="https://nn.labml.ai/transformers/gpt/index.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">transformers</a>
|
||||
<a class="parent" href="index.html">gpt</a>
|
||||
</p>
|
||||
<p>
|
||||
<a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations" target="_blank">
|
||||
<img alt="Github"
|
||||
src="https://img.shields.io/github/stars/labmlai/annotated_deep_learning_paper_implementations?style=social"
|
||||
style="max-width:100%;"/></a>
|
||||
<a href="https://twitter.com/labmlai" rel="nofollow" target="_blank">
|
||||
<img alt="Twitter"
|
||||
src="https://img.shields.io/twitter/follow/labmlai?style=social"
|
||||
style="max-width:100%;"/></a>
|
||||
</p>
|
||||
<p>
|
||||
<a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations/tree/master/labml_nn/transformers/gpt/__init__.py" target="_blank">
|
||||
View code on Github</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>GPT</h1>
|
||||
</a><p>这是 P <a href="https://pytorch.org">yTorch</a> 中 <a href="https://openai.com/blog/better-language-models/">OpenAI GPT 架构的教程/实现。<a href="https://twitter.com/karpathy">@karpathy</a> 从 <a href="https://github.com/karpathy/minGPT">MinGpt</a> 那里得到了很多实现细节。此实现还使用角色小莎士比亚数据集。</p>
|
||||
<p>GPT 模型本质上是一个标准的变压器，但有一些调整。GPT-2，尤其是 GPT-3 模型非常大，不适合单个 GPU，需要模型并行处理。此实现甚至不使用数据并行性，旨在更像是一个教程。</p>
|
||||
与@@ <p>简单的自回归转换器相比，其主要区别在于参数初始化、权重衰减和学习速率调度。对于变压器，我们重用了<a href="../transformers/index.html">现有的 labml/nn 变换器实现</a>。</p>
|
||||
<p>这是一本用于在 Tiny Shakespeare 数据集上训练 GPT 模型的笔记本。</p>
|
||||
<p><a href="https://colab.research.google.com/github/labmlai/annotated_deep_learning_paper_implementations/blob/master/labml_nn/transformers/gpt/experiment.ipynb"><img alt="Open In Colab" src="https://colab.research.google.com/assets/colab-badge.svg"></a></p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">34</span><span></span><span class="kn">import</span> <span class="nn">torch</span>
|
||||
<span class="lineno">35</span><span class="kn">from</span> <span class="nn">torch</span> <span class="kn">import</span> <span class="n">nn</span>
|
||||
<span class="lineno">36</span>
|
||||
<span class="lineno">37</span><span class="kn">from</span> <span class="nn">labml</span> <span class="kn">import</span> <span class="n">experiment</span>
|
||||
<span class="lineno">38</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">39</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">40</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">41</span><span class="kn">from</span> <span class="nn">labml_nn.optimizers.configs</span> <span class="kn">import</span> <span class="n">OptimizerConfigs</span>
|
||||
<span class="lineno">42</span><span class="kn">from</span> <span class="nn">labml_nn.transformers</span> <span class="kn">import</span> <span class="n">TransformerConfigs</span><span class="p">,</span> <span class="n">Encoder</span>
|
||||
<span class="lineno">43</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></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>GPT 型号</h2>
|
||||
<p>这包括令牌嵌入层、变压器编码器和给出令牌日志的最终线性层。</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">46</span><span class="k">class</span> <span class="nc">GPT</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 doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-2'>#</a>
|
||||
</div>
|
||||
<ul><li><code class="highlight"><span></span><span class="n">encoder</span></code>
|
||||
是变压器<a href="../models.html#Encoder">编码器</a></li>
|
||||
<li><code class="highlight"><span></span><span class="n">src_embed</span></code>
|
||||
是令牌<a href="../models.html#EmbeddingsWithLearnedPositionalEncoding">嵌入模块（带有位置编码）</a></li>
|
||||
<li><code class="highlight"><span></span><span class="n">generator</span></code>
|
||||
是给<a href="../models.html#Generator">出 logit 的最后一个完全连接的层</a>。</li></ul>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">54</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">encoder</span><span class="p">:</span> <span class="n">Encoder</span><span class="p">,</span> <span class="n">src_embed</span><span class="p">:</span> <span class="n">Module</span><span class="p">,</span> <span class="n">generator</span><span class="p">:</span> <span class="n">Module</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">61</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
|
||||
<span class="lineno">62</span> <span class="bp">self</span><span class="o">.</span><span class="n">src_embed</span> <span class="o">=</span> <span class="n">src_embed</span>
|
||||
<span class="lineno">63</span> <span class="bp">self</span><span class="o">.</span><span class="n">encoder</span> <span class="o">=</span> <span class="n">encoder</span>
|
||||
<span class="lineno">64</span> <span class="bp">self</span><span class="o">.</span><span class="n">generator</span> <span class="o">=</span> <span class="n">generator</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>掩码将在第一次调用时初始化</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">67</span> <span class="bp">self</span><span class="o">.</span><span class="n">mask</span> <span class="o">=</span> <span class="kc">None</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-5'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-5'>#</a>
|
||||
</div>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">69</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></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-6'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-6'>#</a>
|
||||
</div>
|
||||
<p>如果掩码未初始化或掩码大小不同，则创建后续掩码</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">72</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">mask</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</span><span class="o">.</span><span class="n">size</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></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-7'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-7'>#</a>
|
||||
</div>
|
||||
<p>后续的掩码，将掩盖令牌以免看到未来的代币</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">74</span> <span class="bp">self</span><span class="o">.</span><span class="n">mask</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-8'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-8'>#</a>
|
||||
</div>
|
||||
<p>使用位置编码获取令牌嵌入</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">76</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-9'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-9'>#</a>
|
||||
</div>
|
||||
<p>变压器编码</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">78</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">encoder</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">mask</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>获取日志</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">80</span> <span class="n">x</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">x</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>返回结果（第二个值用于状态，因为我们的训练器也与 RNN 一起使用）</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">84</span> <span class="k">return</span> <span class="n">x</span><span class="p">,</span> <span class="kc">None</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-12'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-12'>#</a>
|
||||
</div>
|
||||
<h2>配置</h2>
|
||||
<p>这继承自 <a href="../../experiments/nlp_autoregression.html#NLPAutoRegressionConfigs"><code class="highlight"><span></span><span class="n">NLPAutoRegressionConfigs</span></code>
|
||||
</a></p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">87</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-13'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-13'>#</a>
|
||||
</div>
|
||||
<p>GPT 型号</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">96</span> <span class="n">model</span><span class="p">:</span> <span class="n">GPT</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>变压器</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">98</span> <span class="n">transformer</span><span class="p">:</span> <span class="n">TransformerConfigs</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>体重衰减</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">100</span> <span class="n">weight_decay</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.1</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-16'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-16'>#</a>
|
||||
</div>
|
||||
<p>wamup 的代币数量</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">102</span> <span class="n">warmup_steps</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">128</span> <span class="o">*</span> <span class="mi">128</span> <span class="o">*</span> <span class="mi">20</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-17'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-17'>#</a>
|
||||
</div>
|
||||
<p>自定义优化器</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">105</span> <span class="n">optimizer</span> <span class="o">=</span> <span class="s1">'transformer_optimizer'</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-18'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-18'>#</a>
|
||||
</div>
|
||||
<h3>变压器配置</h3>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">108</span><span class="nd">@option</span><span class="p">(</span><span class="n">Configs</span><span class="o">.</span><span class="n">transformer</span><span class="p">,</span> <span class="s1">'GPT'</span><span class="p">)</span>
|
||||
<span class="lineno">109</span><span class="k">def</span> <span class="nf">_transformer_configs</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-19'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-19'>#</a>
|
||||
</div>
|
||||
<p>我们使用我们的<a href="../configs.html#TransformerConfigs">可配置变压器实现</a></p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">116</span> <span class="n">conf</span> <span class="o">=</span> <span class="n">TransformerConfigs</span><span class="p">()</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-20'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-20'>#</a>
|
||||
</div>
|
||||
<p>设置嵌入和生成 logit 的词汇量大小</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">118</span> <span class="n">conf</span><span class="o">.</span><span class="n">n_src_vocab</span> <span class="o">=</span> <span class="n">c</span><span class="o">.</span><span class="n">n_tokens</span>
|
||||
<span class="lineno">119</span> <span class="n">conf</span><span class="o">.</span><span class="n">n_tgt_vocab</span> <span class="o">=</span> <span class="n">c</span><span class="o">.</span><span class="n">n_tokens</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>GPT 使用 GELU 激活进行位置明智前馈</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">121</span> <span class="n">conf</span><span class="o">.</span><span class="n">ffn</span><span class="o">.</span><span class="n">activation</span> <span class="o">=</span> <span class="s1">'GELU'</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></p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">124</span> <span class="k">return</span> <span class="n">conf</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-23'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-23'>#</a>
|
||||
</div>
|
||||
<h3>初始化权重</h3>
|
||||
<p>线性层和嵌入层的权重初始化为，<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord mathcal" style="margin-right:0.14736em;">N</span><span class="mopen">(</span><span class="mord coloredeq eqh" style=""><span class="mord" style="">0</span></span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mord coloredeq eqh" style=""><span class="mord" style="">0</span></span><span class="mord">.</span><span class="mord coloredeq eqh" style=""><span class="mord" style="">0</span></span><span class="mord">2</span><span class="mclose">)</span></span></span></span></span>而不是默认的 Xavier 初始化。</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">127</span><span class="k">def</span> <span class="nf">_init_weights</span><span class="p">(</span><span class="n">module</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">136</span> <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">module</span><span class="p">,</span> <span class="p">(</span><span class="n">nn</span><span class="o">.</span><span class="n">Linear</span><span class="p">,</span> <span class="n">nn</span><span class="o">.</span><span class="n">Embedding</span><span class="p">)):</span>
|
||||
<span class="lineno">137</span> <span class="k">return</span>
|
||||
<span class="lineno">138</span>
|
||||
<span class="lineno">139</span> <span class="n">module</span><span class="o">.</span><span class="n">weight</span><span class="o">.</span><span class="n">data</span><span class="o">.</span><span class="n">normal_</span><span class="p">(</span><span class="n">mean</span><span class="o">=</span><span class="mf">0.0</span><span class="p">,</span> <span class="n">std</span><span class="o">=</span><span class="mf">0.02</span><span class="p">)</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-25'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-25'>#</a>
|
||||
</div>
|
||||
<p>将偏差初始化为<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.64444em;vertical-align:0em;"></span><span class="mord coloredeq eqh" style=""><span class="mord" style="">0</span></span></span></span></span></span></p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">142</span> <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">module</span><span class="p">,</span> <span class="n">nn</span><span class="o">.</span><span class="n">Linear</span><span class="p">)</span> <span class="ow">and</span> <span class="n">module</span><span class="o">.</span><span class="n">bias</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="lineno">143</span> <span class="n">module</span><span class="o">.</span><span class="n">bias</span><span class="o">.</span><span class="n">data</span><span class="o">.</span><span class="n">zero_</span><span class="p">()</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-26'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-26'>#</a>
|
||||
</div>
|
||||
<p>创建 GPT 模型并初始化权重</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">146</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">147</span><span class="k">def</span> <span class="nf">_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-27'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-27'>#</a>
|
||||
</div>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">151</span> <span class="n">m</span> <span class="o">=</span> <span class="n">GPT</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">encoder</span><span class="p">,</span>
|
||||
<span class="lineno">152</span> <span class="n">c</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">src_embed</span><span class="p">,</span>
|
||||
<span class="lineno">153</span> <span class="n">c</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">generator</span><span class="p">)</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-28'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-28'>#</a>
|
||||
</div>
|
||||
<p>应用自定义权重初始化</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">156</span> <span class="n">m</span><span class="o">.</span><span class="n">apply</span><span class="p">(</span><span class="n">_init_weights</span><span class="p">)</span>
|
||||
<span class="lineno">157</span>
|
||||
<span class="lineno">158</span> <span class="k">return</span> <span class="n">m</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-29'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-29'>#</a>
|
||||
</div>
|
||||
<h3>创建具有权重衰减的自定义优化器</h3>
|
||||
<p>此代码取自 <a href="https://github.com/karpathy/minGPT">MingPT</a>。这仅将权重衰减应用于线性图层的权重。</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">161</span><span class="nd">@option</span><span class="p">(</span><span class="n">NLPAutoRegressionConfigs</span><span class="o">.</span><span class="n">optimizer</span><span class="p">)</span>
|
||||
<span class="lineno">162</span><span class="k">def</span> <span class="nf">transformer_optimizer</span><span class="p">(</span><span class="n">c</span><span class="p">:</span> <span class="n">NLPAutoRegressionConfigs</span><span class="p">):</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-30'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-30'>#</a>
|
||||
</div>
|
||||
<p>收集参数名称以应用权重衰减</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">170</span> <span class="n">decay</span> <span class="o">=</span> <span class="nb">set</span><span class="p">()</span>
|
||||
<span class="lineno">171</span> <span class="k">for</span> <span class="n">mn</span><span class="p">,</span> <span class="n">m</span> <span class="ow">in</span> <span class="n">c</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">named_modules</span><span class="p">():</span>
|
||||
<span class="lineno">172</span> <span class="k">for</span> <span class="n">pn</span><span class="p">,</span> <span class="n">p</span> <span class="ow">in</span> <span class="n">m</span><span class="o">.</span><span class="n">named_parameters</span><span class="p">():</span>
|
||||
<span class="lineno">173</span> <span class="n">fpn</span> <span class="o">=</span> <span class="sa">f</span><span class="s1">'</span><span class="si">{</span><span class="n">mn</span><span class="si">}</span><span class="s1">.</span><span class="si">{</span><span class="n">pn</span><span class="si">}</span><span class="s1">'</span> <span class="k">if</span> <span class="n">mn</span> <span class="k">else</span> <span class="n">pn</span> <span class="c1"># full param name</span>
|
||||
<span class="lineno">174</span>
|
||||
<span class="lineno">175</span> <span class="k">if</span> <span class="n">fpn</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">'weight'</span><span class="p">)</span> <span class="ow">and</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">m</span><span class="p">,</span> <span class="n">nn</span><span class="o">.</span><span class="n">Linear</span><span class="p">):</span>
|
||||
<span class="lineno">176</span> <span class="n">decay</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="n">fpn</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>获取所有参数</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">179</span> <span class="n">param_dict</span> <span class="o">=</span> <span class="p">{</span><span class="n">pn</span><span class="p">:</span> <span class="n">p</span> <span class="k">for</span> <span class="n">pn</span><span class="p">,</span> <span class="n">p</span> <span class="ow">in</span> <span class="n">c</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">named_parameters</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>未衰减的参数</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">181</span> <span class="n">no_decay</span> <span class="o">=</span> <span class="nb">set</span><span class="p">(</span><span class="n">param_dict</span><span class="o">.</span><span class="n">keys</span><span class="p">())</span> <span class="o">-</span> <span class="n">decay</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>创建 pytorch 优化器对象</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">184</span> <span class="n">opt_groups</span> <span class="o">=</span> <span class="p">[</span>
|
||||
<span class="lineno">185</span> <span class="p">{</span><span class="s2">"params"</span><span class="p">:</span> <span class="p">[</span><span class="n">param_dict</span><span class="p">[</span><span class="n">pn</span><span class="p">]</span> <span class="k">for</span> <span class="n">pn</span> <span class="ow">in</span> <span class="nb">sorted</span><span class="p">(</span><span class="nb">list</span><span class="p">(</span><span class="n">decay</span><span class="p">))],</span> <span class="s2">"weight_decay"</span><span class="p">:</span> <span class="n">c</span><span class="o">.</span><span class="n">weight_decay</span><span class="p">},</span>
|
||||
<span class="lineno">186</span> <span class="p">{</span><span class="s2">"params"</span><span class="p">:</span> <span class="p">[</span><span class="n">param_dict</span><span class="p">[</span><span class="n">pn</span><span class="p">]</span> <span class="k">for</span> <span class="n">pn</span> <span class="ow">in</span> <span class="nb">sorted</span><span class="p">(</span><span class="nb">list</span><span class="p">(</span><span class="n">no_decay</span><span class="p">))],</span> <span class="s2">"weight_decay"</span><span class="p">:</span> <span class="mf">0.0</span><span class="p">},</span>
|
||||
<span class="lineno">187</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>
|
||||
<p>创建一个<a href="../optimizers/configs.html#OptimizerConfigs">可配置的优化器</a>，这样我们就可以通过传递配置字典来更改它们。</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">192</span> <span class="n">optimizer</span> <span class="o">=</span> <span class="n">OptimizerConfigs</span><span class="p">()</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-35'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-35'>#</a>
|
||||
</div>
|
||||
<p>设置参数组以进行优化。</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">195</span> <span class="n">optimizer</span><span class="o">.</span><span class="n">parameters</span> <span class="o">=</span> <span class="n">opt_groups</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>使用<a href="../optimizers/adam_warmup_cosine_decay.html">余弦衰减优化器</a>。这就是 GPT 使用的。</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">198</span> <span class="n">optimizer</span><span class="o">.</span><span class="n">optimizer</span> <span class="o">=</span> <span class="s1">'AdamWarmupCosineDecay'</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>设置模型嵌入大小，如果我们使用具有指数衰减的 <a href="../optimizers/noam.html">Noam 优化器</a>，则需要设置模型嵌入大小。</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">201</span> <span class="n">optimizer</span><span class="o">.</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></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-38'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-38'>#</a>
|
||||
</div>
|
||||
<p>设置默认权重衰减。这不是必需的，因为我们在参数组中设置了权重衰减。</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">204</span> <span class="n">optimizer</span><span class="o">.</span><span class="n">weight_decay</span> <span class="o">=</span> <span class="n">c</span><span class="o">.</span><span class="n">weight_decay</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>GPT 使用的最大学习速率为<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.72777em;vertical-align:-0.08333em;"></span><span class="mord">6</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:0.848448em;vertical-align:0em;"></span><span class="mord"><span class="mord coloredeq eqf" style=""><span class="mord" style="">1</span><span class="mord" style=""><span class="mord coloredeq eqh" style="">0</span></span></span><span class="msupsub"><span class="vlist-t"><span class="vlist-r"><span class="vlist" style="height:0.848448em;"><span style="top:-3.09734em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mtight">−</span><span class="mord mtight">4</span></span></span></span></span></span></span></span></span></span></span></span></span>。</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">206</span> <span class="n">optimizer</span><span class="o">.</span><span class="n">learning_rate</span> <span class="o">=</span> <span class="mf">6e-4</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><span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.8888799999999999em;vertical-align:-0.19444em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.05278em;">β</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.30110799999999993em;"><span style="top:-2.5500000000000003em;margin-left:-0.05278em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight">1</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mspace" style="margin-right:0.2777777777777778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2777777777777778em;"></span></span><span class="base"><span class="strut" style="height:0.8888799999999999em;vertical-align:-0.19444em;"></span><span class="mord coloredeq eqh" style=""><span class="mord" style="">0</span></span><span class="mord">.9</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.05278em;">β</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.30110799999999993em;"><span style="top:-2.5500000000000003em;margin-left:-0.05278em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight">2</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mspace" style="margin-right:0.2777777777777778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2777777777777778em;"></span></span><span class="base"><span class="strut" style="height:0.64444em;vertical-align:0em;"></span><span class="mord coloredeq eqh" style=""><span class="mord" style="">0</span></span><span class="mord">.95</span></span></span></span></span></p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">208</span> <span class="n">optimizer</span><span class="o">.</span><span class="n">betas</span> <span class="o">=</span> <span class="p">(</span><span class="mf">0.9</span><span class="p">,</span> <span class="mf">0.95</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><span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.43056em;vertical-align:0em;"></span><span class="mord mathnormal">ϵ</span><span class="mspace" style="margin-right:0.2777777777777778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2777777777777778em;"></span></span><span class="base"><span class="strut" style="height:0.848448em;vertical-align:0em;"></span><span class="mord"><span class="mord coloredeq eqf" style=""><span class="mord" style="">1</span><span class="mord" style=""><span class="mord coloredeq eqh" style="">0</span></span></span><span class="msupsub"><span class="vlist-t"><span class="vlist-r"><span class="vlist" style="height:0.848448em;"><span style="top:-3.09734em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mtight">−</span><span class="mord mtight">8</span></span></span></span></span></span></span></span></span></span></span></span></span></p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">210</span> <span class="n">optimizer</span><span class="o">.</span><span class="n">eps</span> <span class="o">=</span> <span class="mf">1e-8</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>权重衰减与梯度分离</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">212</span> <span class="n">optimizer</span><span class="o">.</span><span class="n">weight_decouple</span> <span class="o">=</span> <span class="kc">True</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>学习速率余弦衰减的优化步骤总数</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">214</span> <span class="n">optimizer</span><span class="o">.</span><span class="n">total_steps</span> <span class="o">=</span> <span class="n">c</span><span class="o">.</span><span class="n">epochs</span> <span class="o">*</span> <span class="nb">len</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">text</span><span class="o">.</span><span class="n">train</span><span class="p">)</span> <span class="o">//</span> <span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">batch_size</span> <span class="o">*</span> <span class="n">c</span><span class="o">.</span><span class="n">seq_len</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>预热优化步骤数</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">216</span> <span class="n">optimizer</span><span class="o">.</span><span class="n">warmup</span> <span class="o">=</span> <span class="n">c</span><span class="o">.</span><span class="n">warmup_steps</span> <span class="o">//</span> <span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">batch_size</span> <span class="o">*</span> <span class="n">c</span><span class="o">.</span><span class="n">seq_len</span><span class="p">)</span>
|
||||
<span class="lineno">217</span>
|
||||
<span class="lineno">218</span> <span class="k">return</span> <span class="n">optimizer</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-45'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-45'>#</a>
|
||||
</div>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">221</span><span class="k">def</span> <span class="nf">main</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>创建实验</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">223</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">"gpt"</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>创建配置</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">225</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-48'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-48'>#</a>
|
||||
</div>
|
||||
<p>覆盖配置</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">227</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> <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>使用角色等级分词器</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">229</span> <span class="s1">'tokenizer'</span><span class="p">:</span> <span class="s1">'character'</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>提示分隔符为空</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">231</span> <span class="s1">'prompt_separator'</span><span class="p">:</span> <span class="s1">''</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>开始采样提示</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">233</span> <span class="s1">'prompt'</span><span class="p">:</span> <span class="s1">'It is '</span><span class="p">,</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-52'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-52'>#</a>
|
||||
</div>
|
||||
<p>使用小莎士比亚数据集</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">235</span> <span class="s1">'text'</span><span class="p">:</span> <span class="s1">'tiny_shakespeare'</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>使用上下文大小为<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.64444em;vertical-align:0em;"></span><span class="mord coloredeq eqe" style=""><span class="mord" style="">128</span></span></span></span></span></span></p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">238</span> <span class="s1">'seq_len'</span><span class="p">:</span> <span class="mi">128</span><span class="p">,</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>为<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.64444em;vertical-align:0em;"></span><span class="mord">32</span></span></span></span></span>时代而训练</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">240</span> <span class="s1">'epochs'</span><span class="p">:</span> <span class="mi">32</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>批量大小<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.64444em;vertical-align:0em;"></span><span class="mord coloredeq eqe" style=""><span class="mord" style="">128</span></span></span></span></span></span></p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">242</span> <span class="s1">'batch_size'</span><span class="p">:</span> <span class="mi">128</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>在训练和验证之间切换每个纪元的<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.64444em;vertical-align:0em;"></span><span class="mord coloredeq eqf" style=""><span class="mord" style="">1</span><span class="mord" style=""><span class="mord coloredeq eqh" style="">0</span></span></span></span></span></span></span>次数</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">245</span> <span class="s1">'inner_iterations'</span><span class="p">:</span> <span class="mi">10</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>变压器配置</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">248</span> <span class="s1">'transformer.d_model'</span><span class="p">:</span> <span class="mi">512</span><span class="p">,</span>
|
||||
<span class="lineno">249</span> <span class="s1">'transformer.ffn.d_ff'</span><span class="p">:</span> <span class="mi">2048</span><span class="p">,</span>
|
||||
<span class="lineno">250</span> <span class="s1">'transformer.n_heads'</span><span class="p">:</span> <span class="mi">8</span><span class="p">,</span>
|
||||
<span class="lineno">251</span> <span class="s1">'transformer.n_layers'</span><span class="p">:</span> <span class="mi">6</span>
|
||||
<span class="lineno">252</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>设置用于保存和加载的模型</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">255</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-59'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-59'>#</a>
|
||||
</div>
|
||||
<p>开始实验</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">258</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-60'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-60'>#</a>
|
||||
</div>
|
||||
<p>跑步训练</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">260</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-61'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-61'>#</a>
|
||||
</div>
|
||||
<p></p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">264</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">265</span> <span class="n">main</span><span class="p">()</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='footer'>
|
||||
<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>
|
||||
Reference in New Issue
Block a user