---
license: mit
base_model: [Wan-AI/Wan2.2-TI2V-5B]
tags: [robotics, world-action-model, fastwam, robotwin, joint]
---
# FastWAM-Joint RoboTwin — clean 50k reproduction (step_050000)
Fast-WAM **joint** variant (`create_fastwam_joint`: action attends to ALL video latent tokens),
built on Wan2.2-TI2V-5B video DiT + ActionDiT (MoT, ~6B params), trained on RoboTwin 2.0.

**Clean 50,000-step run** on 8 GPUs (effective batch 128), lr 1e-4 cosine (warmup 5%),
AdamW(0.9,0.95), weight_decay 1e-2, bf16, ZeRO-1. 3 cams (cam_high + L/R wrist, 240x320 each,
tiled), num_frames 33, action_video_freq_ratio 4 (32 actions / 9 video frames), action&state dim 14.

This matches the BadWAM (arXiv:2607.15207) reproduction recipe (8xH100 / 50k / batch16 / lr1e-4 cosine),
whose reported clean RoboTwin success rates are joint **90.9%** / idm 91.4% / action-only 92.1%.

Notes:
- LR decayed to the 1e-6 cosine floor by step 50k; resume-safe closed-form LambdaLR schedule.
- Run survived 3 clean watchdog auto-recoveries (transient rank SIGKILLs), each resuming full
  training state from the last checkpoint with correct LR and no loss spike.
- Files: fastwam_joint_step50000.pt (12 GB bf16 weights) + robotwin_joint_dataset_stats.json
  (normalization stats, REQUIRED for inference/eval).