asgard-robot/groot-condiment-handover

GROOT Condiment Handover Model - Step 2000

Model Card Summary

• Checkpoint: Step 2000 (Final checkpoint)
• Base Model: nvidia/GR00T-N1.5-3B
• Task: Condiment handover on ASGARD so101_follower robot
• Training Status: Completed successfully
• Final Loss: ~0.006

Model Details

Model Architecture

This is a fine-tuned NVIDIA GR00T N1.5-3B model specifically trained for condiment handover tasks.

• Model Type: GROOT (Generalist Robot 00 Technology)
• Policy Type: GR00T N1.5-3B
• Robot Embodiment: asgard_so101 (single-arm 6 degrees of freedom)
• Action Dimensions: 6 (joint positions + gripper)
• Observation: Dual camera RGB (640×480×3 each)

Training Components

Frozen (Not Trained):

• ❌ LLM (tune_llm=false) - Language model kept frozen
• ❌ Vision Encoder (tune_visual=false) - Visual features frozen

Trainable Components:

• ✅ Diffusion Transformer (tune_diffusion_model=true) - Action generation
• ✅ Projector (tune_projector=true) - Vision-language to action mapping

Training Strategy

• Approach: Full fine-tuning (no LoRA)
• Rationale: 4× H100 GPUs with 320GB total VRAM allows full parameter updates
• Precision: bf16 (mixed precision training)

Training Details

Dataset Information

Parameter	Value	Description
Dataset Repository	asgard-robot/asgard_training_data_condiment	Hugging Face dataset
Dataset Version	v3.0	LeRobot format tag
Total Episodes	40	Number of demonstrations
Total Frames	31,522	Total training samples
Avg Frames/Episode	~788	Average trajectory length
Episode Duration	~26 seconds	At 30 FPS
Robot Type	so101_follower	Single-arm 6 DOF
Task	Condiment handover	Primary objective
Format	LeRobot v3.0	Parquet + MP4 videos (AV1 codec)

Training Hyperparameters

Parameter	Value	Justification
Total Training Steps	2,000	Full training cycle
Number of Epochs	~32	Effective epochs (31,522 frames ÷ 512 batch)
Checkpoints Saved	5	Steps: 400, 800, 1200, 1600, 2000
Learning Rate	1e-4	GROOT recommended value
Weight Decay	1e-5	L2 regularization
Gradient Clip Norm	1.0	Training stability
Warmup Ratio	0.05	Gradual learning rate ramp
Batch Size (per GPU)	128	Maximum VRAM utilization
Effective Batch Size	512	128 × 4 GPUs
Num Workers	16	DataLoader parallel loading
Video Backend	torchcodec	AV1 codec decoder
Mixed Precision	bf16	Memory efficient training

Hardware Configuration

Component	Specification	Utilization
GPUs	4× NVIDIA H100 PCIe	All 4 GPUs used
VRAM per GPU	80GB	~79.65GB usable
Total VRAM	320GB	Peak usage: ~60-70GB per GPU
CPUs	124 AMD EPYC 9554 (64-Core)	Data loading
System RAM	708GB	Adequate for data loading
Storage	1.5TB ephemeral	Checkpoint storage

Usage

Load Model

from lerobot import Policy

policy = Policy.from_pretrained("asgard-robot/groot-condiment-handover")

Run Inference

# The model expects observations with:
# - observation.images.wrist1: RGB camera (640×480×3)
# - observation.images.realsense: RGB camera (640×480×3)
# - observation.state: 6D joint positions

action = policy(observation)
# Returns: 6D action space (joint positions + gripper)

Action Space

The model outputs actions for 6 degrees of freedom:

1. shoulder_pan.pos
2. shoulder_lift.pos
3. elbow_flex.pos
4. wrist_flex.pos
5. wrist_roll.pos
6. gripper.pos

Citation

@software{groot_condiment_model_2024,
  author = {ASGARD Team},
  title = {GROOT Condiment Handover Model - Step 2000},
  model = {asgard-robot/groot-condiment-handover},
  year = {2024},
  month = {October},
  checkpoint = {2000},
  base_model = {nvidia/GR00T-N1.5-3B},
  dataset = {asgard-robot/asgard_training_data_condiment},
  training_hardware = {4× NVIDIA H100 PCIe GPUs}
}

Acknowledgments

• Base Model: NVIDIA GR00T N1.5-3B
• Framework: LeRobot (ASGARD teleop control branch)
• Dataset: ASGARD Robot Datasets
• Hardware: Shadeform H100 Multi-GPU Cluster