π0.5 · SO-101 pick & place (2-task) — full fine-tune, 10,000 steps
A π0.5 (pi05) vision-language-action policy
fine-tuned on an SO-101 arm for a two-task cup manipulation setup: pick a cup up from the table and
place it onto a blue circle.
The entire model was trained — PaliGemma VLM (vision encoder + language model) and the action
expert together (train_expert_only=false, freeze_vision_encoder=false).
- Base model:
lerobot/pi05_base— the last pre-relative-actions revision, matching LeRobot0.4.x - Dataset:
aailabkaist/so101_recovery_2task(749 episodes · 151,255 frames · 30 fps · 8 operators) - Checkpoint: step 10,000 of a 10,000-step run (batch 64 → 640,000 samples ≈ 4.2 epochs)
- Framework: LeRobot
- Robot: SO-101, 6-DoF, two RGB cameras (
front,wrist, 480×640) - Siblings:
expert 5K·expert 10K·full 5K— see the two-task collection
Task and data
Two instructions, both used at training time verbatim:
pick up the cup near the blue circle
place the cup on the blue circle
Pick-episode cup start positions (394 episodes, per-operator colors, anonymized). The cups form a ring around the blue circle rather than covering the workspace uniformly.
Place-episode transport vectors, start → placed (350 of 355 place episodes — 5 excluded where the cup is fully occluded by the gripper in the start frame). Endpoints converge tightly on the blue circle; the release target is nearly constant across the dataset.
Training
| Trainable parameters | 3.617 B (100 %) |
| Frozen | none |
| Steps | 10,000 (run stopped early at 10K; config said 20K) |
| Batch size | 64 |
| Precision | bfloat16, gradient_checkpointing=true |
| Optimizer | AdamW · lr 2.5e-5 · wd 0.01 · betas (0.9, 0.95) · grad-clip 1.0 |
| Schedule | cosine decay with warmup — auto-scaled by LeRobot (20K steps < 30K decay): warmup 1,000→666, decay 30,000→20,000; peak 2.5e-5, LR at this checkpoint ≈1.4e-5 (configured floor 2.5e-6 never reached — run stopped at 10K) |
| Chunk | chunk_size=50, n_action_steps=50, n_obs_steps=1 |
| Seed | 1000 |
| Hardware | 1× NVIDIA RTX PRO 6000 Blackwell (96 GB) |
| VRAM / speed | 45.4 GB · 4.93 s/step |
| Final loss at this checkpoint | 0.039 |
Interactive training curves for this run — loss · LR · grad-norm · epochs (this variant's W&B run · project overview):
Both runs used identical data, batch size and dtype — the only difference is what was trainable, so
the two curves are directly comparable. expert-only is essentially flat after warmup (~step 1K):
0.129 → 0.087 over the remaining ~3.8 epochs; full fine-tuning keeps descending. The run was stopped
at 10K rather than the configured 20K on the strength of these curves.
Usage
from lerobot.policies.pi05.modeling_pi05 import PI05Policy
policy = PI05Policy.from_pretrained("aailabkaist/pi05_recovery_2task_full_10k")
Or serve it for async inference:
python -m lerobot.async_inference.policy_server --host=0.0.0.0 --port=8080 --fps=30
python -m lerobot.async_inference.robot_client \
--server_address=<host>:8080 \
--policy_type=pi05 --pretrained_name_or_path=aailabkaist/pi05_recovery_2task_full_10k \
--task="pick up the cup near the blue circle" \
--actions_per_chunk=50 --chunk_size_threshold=0.2 \
--aggregate_fn_name=weighted_average --fps=30
A single-task variant of this setup — one instruction covering the whole pick-and-place motion, with a plain white cup — lives in the SO-101 · cup → blue circle (single-task) collection.