smolvla_finetune_arrange_chocolate

5,000-step fine-tune of the 20k checkpoint of smolvla_3cam_50ep_arrange_chocolate, on makermods/arrange_chocolate_finetune.

Training

Policy	SmolVLA (smolvla)
Base	/home/makermods/.cache/huggingface/lerobot/outputs/train/smolvla_arrange_chocolate_20260827_204344/run/checkpoints/020000/pretrained_model
Dataset	makermods/arrange_chocolate_finetune
Steps	5000
Batch size	64
LR	1e-05 -> 2.5e-06 (cosine_decay_with_warmup)
Warmup steps	200
Cameras	front, top, wrist (3x 480x640)
Checkpoints	10 (every 500 steps)

Layout

The final checkpoint is at the repo root, so this repo loads directly as a policy. Every intermediate checkpoint is under checkpoints/<step>/, each with pretrained_model/ and training_state/ (resumable).

rename_map is empty and the camera keys are the real dataset keys (observation.images.front / .top / .wrist), so lerobot-eval, lerobot-rollout and policy_server.py load this checkpoint without a rewrite.