Software Development

DeePMD Train

Train DeePMD-kit models with progressive disclosure. Use when the user wants to train a DeePMD-kit potential, prepare an input.json, choose between model families such as se_e2_a/DeepPot-SE, DPA3, DPA4/SeZM, and DPA4C, run `dp train`, monitor learning curves, freeze checkpoints, or test trained models. Start with model selection and read only the selected model reference under `models/` when model-specific configuration is needed.

Publisher / source

deepmodeling/deepmd-kit (found on GitHub top repositories)

Upstream record

deepmodeling/deepmd-kit

Version

Version 1

Published

2026-11-07

Publication review

Approved for publication · recorded passed scan 2026-11-07

Content fingerprint

34c3f9ffa61889f2e12a7662c7d7f579fc30839a8071ed898c14c87816b8e50a