pi05_atomic65_from_base
A π0.5 checkpoint (openpi, JAX) fine-tuned from pi05_base on RoboCasa365 atomic tasks only. It contains no composite-task data.
This is a research checkpoint and has not been evaluated yet.
| openpi config | pi05_atomic65_from_base, a copy of pi05_pretrain_human300 (openpi RoboCasa fork) with only the data changed |
| Model | Pi0Config(pi05=True, max_token_len=200) |
| Init | gs://openpi-assets/checkpoints/pi05_base/params |
| Data | 65 RoboCasa365 atomic tasks: get_ds_soup(split="pretrain", task_set="all_atomic_tasks", source="human"), i.e. human demos, pretrain split, filter key 100_demos (~100 demos per task) |
| Norm stats | combined from each dataset's meta/stats.json (assets/norm_stats.json) |
| Batch | 64 (2×A100 80GB, FSDP 2) |
| LR | cosine: warmup 1k, peak 2.5e-5, decay over 100k steps to 2.5e-6. The run stops at 10k steps, so the LR is still near peak (≈2.49e-5 at 5k, ≈2.45e-5 at 10k) |
Layout
| Folder | Train step | Contents |
|---|---|---|
5000/ |
5,000 | params/ (orbax OCDBT), assets/norm_stats.json |
9999/ |
10,000 (openpi saves the last step as num_train_steps - 1); added when training finishes |
params/ (orbax OCDBT), assets/norm_stats.json |
The optimizer state (train_state) is not included.
Usage
Download one step folder and serve it with openpi:
hf download ducido/pi05_atomic65_from_base --include "5000/*" --local-dir ckpt
uv run scripts/serve_policy.py policy:checkpoint --policy.config=pi05_atomic65_from_base --policy.dir=ckpt/5000
License
These weights are derived from openpi's pi05_base (Physical Intelligence), which builds on PaliGemma. Use is subject to the license terms of those upstream weights, including the Gemma Terms of Use.