---
license: apache-2.0
base_model: nvidia/GR00T-N1.7-3B
datasets:
- imstevenpmwork/super_chatton
library_name: lerobot
tags:
- robotics
- groot
- lerobot
- so-101
---

# GR00T-N1.7 finetuned on super_chatton

LeRobot-native finetune of [nvidia/GR00T-N1.7-3B](https://huggingface.co/nvidia/GR00T-N1.7-3B)
on [imstevenpmwork/super_chatton](https://huggingface.co/datasets/imstevenpmwork/super_chatton)
(SO-101 arm, 73,842 frames / 100 eps, 2 cams front+wrist, 30fps).

## Training
- 20,000 steps, batch 64, seed 42, adamw lr 1e-4 cosine (500 warmup), bf16
- chunk_size 16, n_action_steps 16
- use_relative_actions=true, relative_exclude_joints=['gripper']
- embodiment_tag=new_embodiment, policy training preset
- Final loss **0.016** (from 1.06), 17.3 epochs, single H100, 5h49m

## Usage
```python
from lerobot.policies.groot.modeling_groot import GrootPolicy
policy = GrootPolicy.from_pretrained("nvkartik/groot-n17-super-chatton")
```