RACE2_vlabench / README.md
SeonghoonYu's picture
Add files using upload-large-folder tool
e76a747 verified
|
Raw History Blame Contribute Delete
1.93 kB
---
license: mit
tags:
- robotics
- vlabench
- pi0.5
- race2
---
# RACE2 on VLABench — checkpoints and data
Artifacts of the RACE2 (transition-aware fine-tuning of pi0.5) experiments on the VLABench
primitive tasks. Code: [Seonghoon-Yu/VLABench](https://github.com/Seonghoon-Yu/VLABench).
## Data
| folder | contents |
|---|---|
| `data/vlabench_phase_5000/` | 5,000 freshly generated expert demonstrations (500 per task, LeRobot v2.0, same schema as `SeonghoonYu/vlabench_primitive_ft_lerobot_224`) with **generator-logged transition labels**: `labels/vlabench_phase_cps.npz` (reference phase boundaries, 4.49/ep) and `labels/vlabench_phase_pelt.npz` (PELT labels on the same episodes, 3.81/ep). See [`data/vlabench_phase_5000/README.md`](data/vlabench_phase_5000/README.md). |
The original training set (5,000 episodes, PELT labels) is `SeonghoonYu/vlabench_primitive_ft_lerobot_224`.
## Checkpoints
| folder | run |
|---|---|
| `teacher_official/` | pi0.5 VLABench teacher (official) |
| `plainft_h{10,15,20,25,30}_40k/` | PlainFT baseline, action horizon H, 40k steps |
| `h{10,15,20,25,30,35}_40k/` | RACE2, action horizon H, 40k steps |
| `acot_h{10,20}_40k/` | ACoT-VLA reproduction (JAX/orbax checkpoint; see its README) |
| `ablation/abl_*_h20_40k/` | RACE2 ablations at H20 (actionhead, nojitter, notf, speedcp, timing_only, vlmhead, …) |
| `h25_support/`, `h30_h35_support/` | openpi overlays (configs, CPS assets, serving entrypoint) needed to load the H25 / H30–H35 checkpoints |
Each run folder carries its `assets/` (norm stats), weights, and where available `README.md`,
`training_config.json`, `provenance.json` and `logs/`.
## Download
```python
from huggingface_hub import snapshot_download
snapshot_download("SeonghoonYu/RACE2_vlabench", allow_patterns="data/vlabench_phase_5000/*",
local_dir="/path/to/lerobot/SeonghoonYu") # -> .../SeonghoonYu/data/vlabench_phase_5000
```