molmoact2_telearms_v4 (final checkpoint, step 100,000)

MolmoAct2 full fine-tune of allenai/MolmoAct2-BimanualYAM on mliu48/telearms-yam-cube-v4 (53,832 simulated bimanual YAM demonstrations, 48 tasks, 30 Hz, 3 × 224×224 cameras).

• Trainer: allenai/molmoact2 experiments/launch_scripts/train_lerobot.py (upstream 6070080), converted with olmo.hf_model.convert_molmoact2_to_hf.
• Full fine-tune (LLM, ViT, connector, LM head, action expert), unpacked + dynamic sequence length.
• 16 × H100 (2 nodes × 8), batch 16/GPU (global 256), 100k-step schedule; LRs: LLM 2e-5, ViT 1e-5, connector 1e-5, action expert 1e-4 (upstream full-FT recipe × sqrt(256/64)).
• Mixture tag telearms_yam_sim: absolute joint-pose control, 14-D state/action (per arm 6 joints + gripper), cameras [camera_front, camera_left, camera_right] (same order as BimanualYAM's [top, left, right]), 30-step action chunks.
• norm_stats.json holds this dataset's absolute action/state statistics (tag telearms_yam_sim).
• Token embedding / LM head have 155,648 rows (base checkpoint: 154,624): the trainer adds special tokens at fine-tuning start; the bundled tokenizer matches.
• Not yet evaluated in simulation.