---
library_name: peft
license: apache-2.0
base_model: lerobot/smolvla_base
pipeline_tag: robotics
tags:
  - base_model:adapter:lerobot/smolvla_base
  - lora
  - peft
  - lerobot
  - smolvla
  - robotics
  - so101
  - imitation-learning
  - isaaclab
  - sim
  - code-as-policies
  - CoRL2026
datasets:
  - CoRL2026-CSI/Isaaclab-so101_11task_baseCaP_3300epi_10fps
---

# IsaacLab-smolVLA-SO101-Multitask-8epoch

[lerobot/smolvla_base](https://huggingface.co/lerobot/smolvla_base) 를 IsaacLab 시뮬레이션 SO101 11-task 데이터셋
[CoRL2026-CSI/Isaaclab-so101_11task_baseCaP_3300epi_10fps](https://huggingface.co/datasets/CoRL2026-CSI/Isaaclab-so101_11task_baseCaP_3300epi_10fps)
으로 8 epoch 파인튜닝한 SmolVLA 정책.

이 체크포인트는 **LoRA adapter** 입니다 (`adapter_model.safetensors`). base 모델 `lerobot/smolvla_base` 와 함께 로드됩니다.

## Model details

- **Base model**: `lerobot/smolvla_base` (SmolVLM2-500M-Video-Instruct VLM + action expert)
- **Robot**: SO101 (6-DOF, gripper 포함) — IsaacLab 시뮬레이션
- **Cameras**: `top`, `left_wrist` (480×640) — 정책 키 `camera1`(left_wrist) / `camera2`(top) 로 rename
- **Inputs**: `observation.state`[6] + 카메라 2개 + language instruction (task)
- **Output**: `action`[6] (joint position)
- **Action chunking**: `chunk_size=50`, `n_action_steps=50`

## Fine-tuning strategy (PEFT / LoRA)

핵심: **action expert 와 projection 레이어는 full fine-tune, VLM backbone 은 q/v_proj 에만 LoRA, 그 외 VLM 은 완전 freeze.**

### Trainable / Frozen breakdown

| 모듈 | 상태 | 설명 |
|---|---|---|
| VLM `q_proj`, `v_proj` (attention query/value projection) | 🔵 **LoRA 학습** | base weight 는 frozen, 저랭크 adapter(A·B)만 학습 |
| VLM 그 외 전부 — `k_proj`, `o_proj`, MLP(`gate/up/down_proj`), token/position embeddings, **vision encoder(SigLIP)**, LayerNorm | ❄️ **완전 Frozen** | LoRA 도 안 붙고 full 학습도 아님 |
| Action expert (`lm_expert`) 전체 — attention(q/k/v/o_proj), MLP(gate/up/down_proj), LayerNorm | 🔥 **Full fine-tune** | 전체 weight 직접 학습 |
| `state_proj` (state → token embedding) | 🔥 **Full fine-tune** | |
| `action_in_proj`, `action_out_proj` (action ↔ expert hidden) | 🔥 **Full fine-tune** | |
| `action_time_mlp_in`, `action_time_mlp_out` (flow-matching time embedding) | 🔥 **Full fine-tune** | |

> 즉 frozen 인 것은 **VLM backbone 의 대부분(vision encoder 포함) + VLM 의 k_proj/o_proj/MLP/embedding/LayerNorm**.
> 학습되는 것은 **VLM q/v_proj 의 LoRA adapter + action expert 전체 + 모든 projection 레이어**.

### LoRA / PEFT config

| 항목 | 값 |
|---|---|
| PEFT method | `LORA` |
| rank `r` | 32 |
| `lora_alpha` | 8 |
| `lora_dropout` | 0.0 |
| `bias` | none |
| `use_rslora` / `use_dora` | false / false |
| `target_modules` (LoRA 적용) | `.*vlm_with_expert\.vlm\..*(q_proj\|v_proj)` |
| `modules_to_save` (full fine-tune) | `lm_expert`, `state_proj`, `action_in_proj`, `action_out_proj`, `action_time_mlp_in`, `action_time_mlp_out` |

저장된 adapter 텐서: 267개 (LoRA A/B 112개 — VLM q_proj·v_proj / full-trained 155개 — expert·projection).

## Training hyperparameters

| 항목 | 값 |
|---|---|
| Dataset | [Isaaclab-so101_11task_baseCaP_3300epi_10fps](https://huggingface.co/datasets/CoRL2026-CSI/Isaaclab-so101_11task_baseCaP_3300epi_10fps) — 3,300 episodes / 1,175,352 frames / 11 tasks / 10 fps |
| Epochs | 8 |
| Steps | 36,800 |
| Global batch size | 256 (micro batch 64 × 4 GPU × grad_accum 1) |
| Optimizer | AdamW — lr `1e-4`, weight_decay `1e-10`, grad_clip_norm `10.0` |
| LR scheduler | cosine_decay_with_warmup — warmup 1,000 / decay 30,000 / peak_lr `1e-4` / decay_lr `2.5e-6` |
| Seed | 1000 |
| Dataloader workers | 24 |
| Mixed precision | no (bf16 inference) |
| Image augmentation | ColorJitter (brightness/contrast/saturation/hue) + SharpnessJitter, max 3 random — **기하학적 변형(회전/이동/반전) 없음** (VLA 좌우 의미 보존) |
| Hardware | 4 × NVIDIA H100 80GB |
| Training time | 약 11시간 12분 |
| Final loss | 0.016 (grad_norm 0.21) |

## Camera rename

| Dataset key | Policy key |
|---|---|
| `observation.images.left_wrist` | `observation.images.camera1` |
| `observation.images.top` | `observation.images.camera2` |

## Usage

```python
from lerobot.policies.smolvla.modeling_smolvla import SmolVLAPolicy

policy = SmolVLAPolicy.from_pretrained("CoRL2026-CSI/IsaacLab-smolVLA-SO101-Multitask-8epoch")
```

## Citation / Acknowledgement

Built on top of [LeRobot](https://github.com/huggingface/lerobot) and the
[SmolVLA](https://huggingface.co/lerobot/smolvla_base) base checkpoint. Project: CoRL 2026 CSI submission.

### Framework versions

- PEFT 0.19.1
- LeRobot 0.5.2