Open Catalyst 2020 (OC20) S2EF 2M Training Set, ColabFit Conversion

Provider
Meta FAIR and Carnegie Mellon University (Chanussot et al.); ColabFit conversion
License
CC-BY-4.0 (source)
Size
5 files
Format
Parquet (in sampled files)
Stored at
Hugging Face (https://huggingface.co/datasets/colabfit/OC20_S2EF_train_2M)
Access
Free and public. No account with the data provider is needed.
DOI
10.60732/672cc613
Category
Chemistry & Materials
Source
https://doi.org/10.1021/acscatal.0c04525

About Open Catalyst 2020 (OC20) S2EF 2M Training Set, ColabFit Conversion

The 2 million structure training split of the Open Catalyst 2020 (OC20) Structure to Energy and Forces (S2EF) task, the subset most papers use for ablations and for comparing interatomic potential architectures on catalyst surfaces. Configurations are adsorbate plus surface slab systems from DFT relaxations (RPBE, VASP), each labelled with total energy, adsorption energy and atomic forces, with OC20 mapping fields such as adsorbate id, Materials Project bulk id and Miller index. ColabFit's card counts 2,000,000 configurations and about 146 million atoms; the repository uses about 20 GB (measured 2026-11-14). This is the ColabFit Exchange conversion: configurations are Parquet files under co/ (structure, positions, cell, computed properties and metadata per row) with dataset-level information in ds.parquet; read them with pyarrow, pandas, polars or Hugging Face datasets, following the ColabFit configuration schema at materials.colabfit.org/docs. Upstream OC20 is released by Meta FAIR under CC-BY-4.0; cite Chanussot et al., ACS Catalysis 2021.

How to load Open Catalyst 2020 (OC20) S2EF 2M Training Set, ColabFit Conversion in Python

from datasets import load_dataset
ds = load_dataset("colabfit/OC20_S2EF_train_2M")
print(ds)

Data structure

File types in sampled files: Parquet

Files

Example file: co/co_0.parquet

Analyze this dataset without downloading it

On Scigantic, Open Catalyst 2020 (OC20) S2EF 2M Training Set, ColabFit Conversion opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.

This page is also available as Markdown and as JSON.

Related Chemistry & Materials datasets