This repository contains the final checkpoint for a ACT policy 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 ACT policy was trained for this dataset configuration and was not initialized from a published ACT base checkpoint. The visual backbone uses ImageNet-initialized ResNet-18 weights (ResNet18_Weights.IMAGENET1K_V1) as recorded in the training config.

Training Setup

Dataset repo: aswinkumar99/task1task3-50-all
Local dataset root during training: /home/riftuser/datasets_combined/aswinkumar99/task1task3-50-all
Output directory during training: /home/riftuser/outputs_matrix/act/task1task3-50-all_bs32_s60000
Batch size: 32
Training steps: 60000
Checkpoint save frequency: 15000
Data loader workers: 8
WandB project: so101-layout-generalization
GPU: NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition
Python: CPython 3.12.13
CUDA: 12.9
Training start: 2026-04-24T07:17:07.570018+00:00
Training end: 2026-04-24T10:23:08
Approximate training duration: 3h 6m 0s
Vision backbone: resnet18
Observation cameras: observation.images.overhead, observation.images.wrist
Action chunk size: 100
Action steps predicted: 100

Exact Training Command

bash

lerobot-train \
  --dataset.repo_id=aswinkumar99/task1task3-50-all \
  --dataset.root=/home/riftuser/datasets_combined/aswinkumar99/task1task3-50-all \
  --dataset.video_backend=torchcodec \
  --output_dir=/home/riftuser/outputs_matrix/act/task1task3-50-all_bs32_s60000 \
  --job_name=act_task1task3-50-all_bs32 \
  --batch_size=32 \
  --steps=60000 \
  --log_freq=200 \
  --save_freq=15000 \
  --save_checkpoint=true \
  --num_workers=8 \
  --wandb.enable=true \
  --wandb.project=so101-layout-generalization \
  --wandb.mode=online \
  --wandb.disable_artifact=true \
  --policy.type=act \
  --policy.device=cuda \
  --policy.push_to_hub=false

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 that was uploaded from the cloud training workspace.
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-ACT-task1task3-50-all_bs32_s60000

aswinkumar99/LeRobot-SO101-ACT-task1task3-50-all_bs32_s60000

LeRobot SO101 ACT task1task3-50-all_bs32_s60000

Summary

Training Setup

Exact Training Command

Repository Contents

Notes

Creator

aswinkumar99/
LeRobot-SO101-ACT-task1task3-50-all_bs32_s60000