--- language: - en license: mit tags: - ACT - LeRobot - robotics - imitation-learning - behavior-cloning - so101 pipeline_tag: reinforcement-learning library_name: lerobot --- # LeRobot SO101 ACT task2task3-all_bs32_s60000 ## Summary This repository contains the final checkpoint for a ACT policy trained on `aswinkumar99/task2task3-all` for SO101 sponge pick-and-place experiments. Dataset meaning: Task 2 + Task 3 combined (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/task2task3-all` - Local dataset root during training: `/home/riftuser/datasets_combined/aswinkumar99/task2task3-all` - Output directory during training: `/home/riftuser/outputs_matrix/act/task2task3-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: `2026-04-24T06:40:40.756268+00:00` - Training end: `2026-04-24T09:52:13` - Approximate training duration: `3h 11m 32s` - 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/task2task3-all \ --dataset.root=/home/riftuser/datasets_combined/aswinkumar99/task2task3-all \ --dataset.video_backend=torchcodec \ --output_dir=/home/riftuser/outputs_matrix/act/task2task3-all_bs32_s60000 \ --job_name=act_task2task3-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](https://aswinkumar.me) - Hugging Face repo: