molmoact2_ring_insert_norm_fix

Fine-tuned MolmoAct2 (action-expert-only) on SO101 data, with SO101 gripper normalization fix.

Base model	allenai/MolmoAct2
Dataset	villekuosmanen/armnetbench_ring_insert
Task	ring_insert
Action dim	6 (single-arm)
Cameras	top, wrist, front
Normalization	MEAN_STD (action + state + gripper), IDENTITY (visual)
Training	Isambard GH200, batch 64, bf16, gradient checkpointing
W&B project	molmoact2_ring_insert
W&B run	qdvlslmq

Checkpoints

Step	Path
002000	checkpoints/002000/pretrained_model/

The latest step (002000) is also copied to the repository root for direct loading.

Usage

from lerobot.policies.molmoact2.modeling_molmoact2 import MolmoAct2Policy
policy = MolmoAct2Policy.from_pretrained("pravsels/molmoact2_ring_insert_norm_fix")