---
title: "Post-Train NVIDIA Cosmos 3 in One Day Using Agent Skills"
description: "Adapting vision reasoning models for specialized physical AI video tasks often demands days of manual container configuration, training script authoring, and hyperparameter tuning. NVIDIA Cosmos 3 Nano, an omnimodal mixture-of-transformers model, pairs an autoregressive Reasoner tower with an iterative diffusion Generator tower for video question answering. By integrating NVIDIA TAO agent skills with a coding agent like Codex, developers can automate data patching, evaluation, and Low-Rank Adaptation (LoRA) post-training. In experiments using the Woven Traffic Safety dataset, LoRA fine-tuning boosted zero-shot baseline accuracy from 54.41% to 87.14% while using approximately seven times fewer GPU hours than full-parameter supervised fine-tuning. Combining this agent workflow with TAO AutoML further elevated model accuracy to 93.35% before automated deployment via NVIDIA NIM."
---

# Post-Train NVIDIA Cosmos 3 in One Day Using Agent Skills

[NVIDIA](https://yomu.fyi/company/nvidia-developer-blog) · Tanya Lenz · Jul 14, 2026

**Type:** Tutorial

## Summary

Adapting vision reasoning models for specialized physical AI video tasks often demands days of manual container configuration, training script authoring, and hyperparameter tuning. NVIDIA Cosmos 3 Nano, an omnimodal mixture-of-transformers model, pairs an autoregressive Reasoner tower with an iterative diffusion Generator tower for video question answering. By integrating NVIDIA TAO agent skills with a coding agent like Codex, developers can automate data patching, evaluation, and Low-Rank Adaptation (LoRA) post-training. In experiments using the Woven Traffic Safety dataset, LoRA fine-tuning boosted zero-shot baseline accuracy from 54.41% to 87.14% while using approximately seven times fewer GPU hours than full-parameter supervised fine-tuning. Combining this agent workflow with TAO AutoML further elevated model accuracy to 93.35% before automated deployment via NVIDIA NIM.

## Context

Adapting vision reasoning models to production video tasks typically consumes days of manual effort spent formatting data, configuring containers, writing training scripts, and sweeping hyperparameters.

## Approach / What changed

Automating Cosmos 3 Nano Reasoner post-training on the Woven Traffic Safety dataset using NVIDIA TAO agent skills, a coding agent like Codex, LoRA fine-tuning, TAO AutoML parameter sweeps, and NIM deployment.

## Takeaways

- LoRA post-training required approximately seven times fewer GPU hours than full-parameter supervised fine-tuning for Cosmos 3 Nano.
- LoRA adaptation raised zero-shot baseline exact-match accuracy from 54.41% to 87.14%, with TAO AutoML further pushing peak accuracy to 93.35%.
- Unlike Llama-style VLM NIMs that serve bare adapters, the Cosmos 3 Reasoner NIM requires a fused checkpoint merging base weights with the LoRA adapter.

**Tags:** [Deployment](https://yomu.fyi/topic/deployment), [Docker](https://yomu.fyi/topic/docker), [LLMs](https://yomu.fyi/topic/llm), [Machine Learning](https://yomu.fyi/topic/machine-learning), [Performance](https://yomu.fyi/topic/performance)

- Source: [NVIDIA](https://developer.nvidia.com/blog/post-train-nvidia-cosmos-3-in-one-day-using-agent-skills)
- Source URL: https://developer.nvidia.com/blog/post-train-nvidia-cosmos-3-in-one-day-using-agent-skills
- Ingested by Yomu: 2026-08-27T15:00:36.625Z

[Read original post](https://developer.nvidia.com/blog/post-train-nvidia-cosmos-3-in-one-day-using-agent-skills)