knightnemo
/

robotwin-icl-v3-arx-x5-vam-ti2v5b-openwam-eef-mask-v3-no-ref-train20-100k

imitation-learning

Model card Files Files and versions

robotwin-icl-v3-arx-x5-vam-ti2v5b-openwam-eef-mask-v3-no-ref-train20-100k / README.md

knightnemo's picture

Add model card

5b4fe06 verified 2 months ago

|

History Blame Contribute Delete

791 Bytes

library_name: pytorch
tags:
  - robotwin
  - vam
  - wan2.2
  - imitation-learning
  - robotics
  - mask-v3
  - no-reference

RoboTwin ICL V3 Mask No-Reference Checkpoint

This repository contains the 100k-step checkpoint for the RoboTwin ICL paired-v3 VAM training run with v3 masking and no reference video.

Checkpoint

File: step-100000.safetensors
Dataset: robotwin-icl-paired-v3
Target robot: arx-x5
Task split: train20
Mask variant: v3
Reference setting: no reference video (full_reference_video=false)
Action expert style: openwam
Action/proprio space: eef
Training budget: 100k steps, 2 nodes x 8 GPUs
W&B run: https://wandb.ai/wuji-tech/vam_icl/runs/80vlexr0

The original local checkpoint path and run metadata are recorded in training_metadata.json.