GR00T N1.7 ego + CloudWalk checkpoint (65k)
Inference-ready checkpoint from the mixed-data experiment at optimizer step 65,000.
Training mixture
- 65% retargeted tabletop ego data
- 35% CloudWalk bottle teleoperation data
- Global batch size 48 on 8 GPUs
- Selective MXFP8 action head with FP8 ZeRO-2 gradient transport
- AdamW, peak learning rate 1e-4, 5,000-step warmup, cosine decay
The objective is to preserve bottle-pickup performance while adding diverse ego-derived motion data to reduce overfitting and catastrophic forgetting.
Frozen CloudWalk probe at 65k
The fixed protocol uses 48 action chunks from 16 CloudWalk-v10 episodes, prompt grab the bottle, seed 0, four denoising steps, and complete 40x64 SONIC tensors.
- Centered cosine versus CloudWalk-v10 30k: 0.9899
- Linear CKA versus CloudWalk-v10 30k: 0.9842
- Centered cosine versus recorded targets: 0.9919
- Centered cosine versus canonical b48 reproduction: 0.9927
- Centered cosine versus NVIDIA base + SONIC metadata adapter: 0.5749
These are open-loop, in-distribution token-similarity results; they do not by themselves establish closed-loop or physical pickup success.
Contents
This repository contains model shards, processor/configuration metadata, statistics, trainer state, and experiment configuration. DeepSpeed optimizer/rank state is intentionally excluded because it is not required for inference or downstream fine-tuning from the consolidated model weights.
Use is subject to the upstream NVIDIA GR00T model terms and applicable dataset terms.
