VLABench/pi0-fast-ft-primitive-10task-deltachunk

Model

1

stars

3

commits

2

linked in READMEs

Nov 12, 2025

updated

README

Pi0-fast delta action chunk trained on VLABench datasets.

This repository provides the Pi0-fast model trained with the whole VLABench's official primitive tasks dataset. To be noticed, this config corresponds to the delta chunk, which is state[1:] - state[:-1] instead of state - state[0].

Evaluation

To run this checkpoint, please clone this repo: https://github.com/Shiduo-zh/openpi, and checkout to the branch main. Assume that you download this checkpoints and put it in the directory checkpoints, to run the policy as server, please run:

bash vla_bench_scipts/serve_policy.sh pi0_ft_vlabench_primitive_aligned checkpoints/VLABench/pi0-fast-ft-primitive-10task-deltachunk/29999/

After serving the policy, open another terminal and run:

bash vla_bench_scipts/multi_run_vlabench.sh <Your path to store the evaluate results>

Train

To reproduce the training result, please run the training script with the config pi0_ft_vlabench_primitive_aligned.

XLA_PYTHON_CLIENT_MEM_FRACTION=0.95 uv run scripts/train.py pi0_ft_vlabench_primitive_aligned --exp-name=pi0_ft_vlabench_primitive_aligned --overwrite

Our checkpoint is trained on 8 H100 for 30k iterations, with 5000 episodes data acrossing 10 tasks.

Reference Results

The reference success rate of this model is:

Trackadd_condimentinsert_flowerselect_bookselect_chemistry_tubeselect_drinkselect_fruitselect_mahjongselect_paintingselect_pokerselect_toyAvg_SR
track_1_in_distribution0.480.380.240.620.180.760.520.460.780.70.512
track_2_cross_category0.02?0.040.140.060.740.250.460.720.440.342
track_3_common_sense0.440.360.160.880.180.560.020.480.340.520.417
track_4_semantic_instruction0.420.340.180.60.080.620.50.50.70.480.442
track_6_unseen_texture0.560.320.240.520.240.60.360.380.540.580.444

Contributors

CyberDJ

3 commits

VLABench/pi0-fast-ft-primitive-10task-deltachunk

Model

1

stars

3

commits

2

linked in READMEs

Nov 12, 2025

updated

README

Pi0-fast delta action chunk trained on VLABench datasets.

This repository provides the Pi0-fast model trained with the whole VLABench's official primitive tasks dataset. To be noticed, this config corresponds to the delta chunk, which is state[1:] - state[:-1] instead of state - state[0].

Evaluation

To run this checkpoint, please clone this repo: https://github.com/Shiduo-zh/openpi, and checkout to the branch main. Assume that you download this checkpoints and put it in the directory checkpoints, to run the policy as server, please run:

bash vla_bench_scipts/serve_policy.sh pi0_ft_vlabench_primitive_aligned checkpoints/VLABench/pi0-fast-ft-primitive-10task-deltachunk/29999/

After serving the policy, open another terminal and run:

bash vla_bench_scipts/multi_run_vlabench.sh <Your path to store the evaluate results>

Train

To reproduce the training result, please run the training script with the config pi0_ft_vlabench_primitive_aligned.

XLA_PYTHON_CLIENT_MEM_FRACTION=0.95 uv run scripts/train.py pi0_ft_vlabench_primitive_aligned --exp-name=pi0_ft_vlabench_primitive_aligned --overwrite

Our checkpoint is trained on 8 H100 for 30k iterations, with 5000 episodes data acrossing 10 tasks.

Reference Results

The reference success rate of this model is:

Trackadd_condimentinsert_flowerselect_bookselect_chemistry_tubeselect_drinkselect_fruitselect_mahjongselect_paintingselect_pokerselect_toyAvg_SR
track_1_in_distribution0.480.380.240.620.180.760.520.460.780.70.512
track_2_cross_category0.02?0.040.140.060.740.250.460.720.440.342
track_3_common_sense0.440.360.160.880.180.560.020.480.340.520.417
track_4_semantic_instruction0.420.340.180.60.080.620.50.50.70.480.442
track_6_unseen_texture0.560.320.240.520.240.60.360.380.540.580.444

Contributors

CyberDJ

3 commits