<?xml version="1.0" encoding="UTF-8"?><oembed><type>video</type><version>1.0</version><html>&lt;iframe src=&quot;https://www.loom.com/embed/7bba9630f99745b6aeb53c9377bec8a5&quot; frameborder=&quot;0&quot; width=&quot;1662&quot; height=&quot;1246&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1246</height><width>1662</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1246</thumbnail_height><thumbnail_width>1662</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/7bba9630f99745b6aeb53c9377bec8a5-6b9803b8ea3cbb82.gif</thumbnail_url><duration>121.82</duration><title>Quick Tour of Fine Tuning Triage Demo 🚀</title><description>I give you a quick tour of getting started with our training template, starting from the Quick Start and pasting the starting command, then naming your app and choosing the triage template. I show the project in VS Code, where trainer.ts holds the training config, and I run pnpm dev to start the anonymous workspace and access the studio. Training takes about seven minutes. When it finishes, you can review the loss curve and metrics, and see timestamped logs, then chat with the base model versus your fine tuned adapter. No action is explicitly requested from viewers.</description></oembed>