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

## Facts

- Provider: Meta FAIR and Carnegie Mellon University (Chanussot et al.); ColabFit conversion
- License: CC-BY-4.0 (https://raw.githubusercontent.com/facebookresearch/fairchem/main/docs/catalysts/datasets/oc20.md)
- Size: 5 files
- Format: Parquet (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/colabfit/OC20_S2EF_train_2M
- Access: public, readable without an account
- DOI: https://doi.org/10.60732/672cc613
- Category: Chemistry & Materials
- Source: https://doi.org/10.1021/acscatal.0c04525
- Page: https://scigantic.com/archive/143aed65-e334-51e3-bb4f-8e9e68ea3841
- Keywords: Chemistry & Materials, DFT, interatomic potentials, Parquet, Hugging Face

## About

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.

## Load the data

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

## Data structure

File types in sampled files: Parquet

Example file: `co/co_0.parquet`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/143aed65-e334-51e3-bb4f-8e9e68ea3841
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/143aed65-e334-51e3-bb4f-8e9e68ea3841
- Over MCP: `get_schema_card` with id `143aed65-e334-51e3-bb4f-8e9e68ea3841` at https://api.scigantic.com/mcp

## Related topics

- [Parquet datasets](https://scigantic.com/topics/parquet)
- [Chemistry & Materials datasets](https://scigantic.com/topics/chemistry-and-materials)
- [DFT datasets](https://scigantic.com/topics/dft)
- [Interatomic potentials datasets](https://scigantic.com/topics/interatomic-potentials)
