This repository contains the final checkpoint for a Pi0.5 (pi05) policy fine-tune trained on aswinkumar99/task1task3-50-all for SO101 sponge pick-and-place experiments.

Dataset meaning: Task 1 + Task 3 combined (50/50, all layouts).

This pi05 policy is a fine-tune of lerobot/pi05_base, as recorded by both the launch command (--policy.path=lerobot/pi05_base) and the saved training config (pretrained_path: lerobot/pi05_base).

Training Setup

Dataset repo: aswinkumar99/task1task3-50-all
Local dataset root during training: /root/datasets_combined/aswinkumar99/task1task3-50-all
Output directory during training: /root/outputs_matrix/pi05/task1task3-50-all_bs32_s20000
Batch size: 32
Training steps: 20000
Checkpoint save frequency: 5000
Data loader workers: 8
WandB project: so101-layout-generalization
GPU: NVIDIA H200
Python: CPython 3.10.12
CUDA: 13.1
Training start: 2026-04-24T22:17:34.101253
Training end: 2026-04-25T02:45:16.420034
Approximate training duration: 4h 27m 42s
Base model: lerobot/pi05_base
Observation camera rename map: {"observation.images.overhead": "observation.images.base_0_rgb", "observation.images.wrist": "observation.images.right_wrist_0_rgb"}
Action chunk size: 50
Action steps predicted: 50

Exact Training Command

bash

lerobot-train \
  --dataset.repo_id=aswinkumar99/task1task3-50-all \
  --dataset.root=/root/datasets_combined/aswinkumar99/task1task3-50-all \
  --dataset.video_backend=torchcodec \
  --output_dir=/root/outputs_matrix/pi05/task1task3-50-all_bs32_s20000 \
  --job_name=pi05_task1task3-50-all_bs32 \
  --batch_size=32 \
  --steps=20000 \
  --log_freq=200 \
  --save_freq=5000 \
  --save_checkpoint=true \
  --num_workers=8 \
  --wandb.enable=true \
  --wandb.project=so101-layout-generalization \
  --wandb.mode=online \
  --wandb.disable_artifact=true \
  --policy.path=lerobot/pi05_base \
  --policy.device=cuda \
  --policy.push_to_hub=false \
  --rename_map={"observation.images.overhead": "observation.images.base_0_rgb", "observation.images.wrist": "observation.images.right_wrist_0_rgb"}

Repository Contents

pretrained_model/: final downloadable model artifacts for inference/loading
training_state/: optimizer, RNG, scheduler/state, and step information for resuming or auditability

Notes

This repo stores the final checkpoint (step 20000) that was uploaded from the cloud training workspace.
Intermediate checkpoints (every 5000 steps) are archived to Google Drive as tarballs and are not pushed to the Hub.
The checkpoint was trained with LeRobot tooling via lerobot-train.
For SO101 experiments in this workspace, the dataset source was created by Aswinkumar.

Creator

Aswinkumar

Website: aswinkumar.me
Hugging Face repo: https://huggingface.co/aswinkumar99/LeRobot-SO101-Pi05-task1task3-50-all_bs32_s20000

aswinkumar99/LeRobot-SO101-Pi05-task1task3-50-all_bs32_s20000

LeRobot SO101 Pi05 task1task3-50-all_bs32_s20000

Summary

Training Setup

Exact Training Command

Repository Contents

Notes

Creator

aswinkumar99/
LeRobot-SO101-Pi05-task1task3-50-all_bs32_s20000