<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Order Matters on Haxlys's Blog</title><link>https://hugo-blog-static-site.haxlys.workers.dev/mental_models/order-matters/</link><description>Recent content in Order Matters on Haxlys's Blog</description><generator>Hugo -- 0.152.2</generator><language>kr-ko</language><lastBuildDate>Sat, 27 Jun 2026 17:42:59 +0900</lastBuildDate><atom:link href="https://hugo-blog-static-site.haxlys.workers.dev/mental_models/order-matters/index.xml" rel="self" type="application/rss+xml"/><item><title>The annotated PyTorch training loop - PyTorch 학습 루프의 순서가 중요한 이유</title><link>https://hugo-blog-static-site.haxlys.workers.dev/posts/annotated-pytorch-training-loop/</link><pubDate>Sat, 27 Jun 2026 17:42:59 +0900</pubDate><guid>https://hugo-blog-static-site.haxlys.workers.dev/posts/annotated-pytorch-training-loop/</guid><description>idlemachines의 The annotated PyTorch training loop를 바탕으로 PyTorch 학습 루프의 각 줄이 하는 일, 순서가 바뀌면 생기는 문제, 검증과 GPU 효율화 포인트를 한국어로 해설한다.</description></item></channel></rss>