Built site for gh-pages
This commit is contained in:
@@ -434,7 +434,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<div id="quarto-sidebar-glass" class="quarto-sidebar-collapse-item" data-bs-toggle="collapse" data-bs-target=".quarto-sidebar-collapse-item"></div>
|
||||
<!-- margin-sidebar -->
|
||||
<div id="quarto-margin-sidebar" class="sidebar margin-sidebar">
|
||||
<nav id="TOC" role="doc-toc" class="toc-active">
|
||||
<nav id="TOC" role="doc-toc" class="toc-active" data-toc-expanded="2">
|
||||
<h2 id="toc-title">On this page</h2>
|
||||
|
||||
<ul>
|
||||
@@ -962,11 +962,13 @@ Tip
|
||||
<span id="cb36-8"><a href="#cb36-8" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">vllm_gpu_memory_utilization</span><span class="kw">:</span><span class="at"> </span><span class="fl">0.15</span></span>
|
||||
<span id="cb36-9"><a href="#cb36-9" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">num_generations</span><span class="kw">:</span><span class="at"> </span><span class="dv">4</span></span>
|
||||
<span id="cb36-10"><a href="#cb36-10" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">reward_funcs</span><span class="kw">:</span><span class="at"> </span><span class="kw">[</span><span class="st">"rewards.rand_reward_func"</span><span class="kw">]</span><span class="co"> # format: '{file_name}.{fn_name}'</span></span>
|
||||
<span id="cb36-11"><a href="#cb36-11" aria-hidden="true" tabindex="-1"></a><span class="fu">datasets</span><span class="kw">:</span></span>
|
||||
<span id="cb36-12"><a href="#cb36-12" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> </span><span class="fu">path</span><span class="kw">:</span><span class="at"> openai/gsm8k</span></span>
|
||||
<span id="cb36-13"><a href="#cb36-13" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">name</span><span class="kw">:</span><span class="at"> main</span></span>
|
||||
<span id="cb36-14"><a href="#cb36-14" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">type</span><span class="kw">:</span><span class="at"> rewards.oai_gsm8k_transform</span><span class="co"> # format: '{file_name}.{fn_name}'</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
<span id="cb36-11"><a href="#cb36-11" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">reward_weights</span><span class="kw">:</span><span class="at"> </span><span class="kw">[</span><span class="fl">1.0</span><span class="kw">]</span></span>
|
||||
<span id="cb36-12"><a href="#cb36-12" aria-hidden="true" tabindex="-1"></a><span class="fu">datasets</span><span class="kw">:</span></span>
|
||||
<span id="cb36-13"><a href="#cb36-13" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="kw">-</span><span class="at"> </span><span class="fu">path</span><span class="kw">:</span><span class="at"> openai/gsm8k</span></span>
|
||||
<span id="cb36-14"><a href="#cb36-14" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">name</span><span class="kw">:</span><span class="at"> main</span></span>
|
||||
<span id="cb36-15"><a href="#cb36-15" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">type</span><span class="kw">:</span><span class="at"> rewards.oai_gsm8k_transform</span><span class="co"> # format: '{file_name}.{fn_name}'</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
<p>To see other examples of custom reward functions, please see <a href="https://github.com/huggingface/trl/blob/main/docs/source/grpo_trainer.md#using-a-custom-reward-function">TRL GRPO Docs</a>.</p>
|
||||
<p>To see description of the configs, please see <a href="https://github.com/axolotl-ai-cloud/axolotl/blob/main/src/axolotl/utils/config/models/input/v0_4_1/trl.py">TRLConfig</a>.</p>
|
||||
</section>
|
||||
<section id="using-local-dataset-files" class="level3">
|
||||
<h3 class="anchored" data-anchor-id="using-local-dataset-files">Using local dataset files</h3>
|
||||
|
||||
Reference in New Issue
Block a user