NEPSettings

NEPSettings#

pydantic model autoplex.settings.NEPSettings[source]#

Model describing the hyperparameters for the NEP fits.

field version: int = 4#: Version of the NEP model

field type: list[int | str] [Optional]#: Mandatory Parameter. Number of atom types and list of chemical species. Number of atom types must be an integer, followed by chemical symbols of species as in periodic table for which model needs to be trained, separated by comma. Default is [1, ‘X’] as a placeholder. Example: [2, ‘Pb’, ‘Te’]

field type_weight: float = 1.0#: Weights for different chemical species

field model_type: int = 0#: Type of model that is being trained. Can be 0 (potential), 1 (dipole), 2 (polarizability)

field prediction: int = 0#: Mode of NEP run. Set 0 for training and 1 for inference

field cutoff: list[int, int] [Optional]#: Radial and angular cutoff. First element is for radial cutoff and second element is for angular cutoff

field n_max: list[int, int] [Optional]#: Number of radial and angular descriptors. First element is for radial and second element is for angular.

field basis_size: list[int, int] [Optional]#: Number of basis functions that are used to build the radial and angular descriptor. First element is for radial descriptor and second element is for angular descriptor

field l_max: list[int] [Optional]#: The maximum expansion order for the angular terms. First element is for three-body, second element is for four-body and third element is for five-body

field neuron: int = 80#: Number of neurons in the hidden layer.

field lambda_1: float = 0.0#: Weight for the L1 regularization term.

field lambda_e: float = 1.0#: Weight for the energy loss term.

field lambda_f: float = 1.0#: Weight for the force loss term.

field lambda_v: float = 0.1#: Weight for the virial loss term.

field force_delta: int = 0#: Sets bias the on the loss function to put more emphasis on obtaining accurate predictions for smaller forces.

field batch: int = 1000#: Batch size for training.

field population: int = 60#: Size of the population used by the SNES algorithm.

field generation: int = 100000#: Number of generations used by the SNES algorithm.

field zbl: int = 2#: Cutoff to use in universal ZBL potential at short distances. Acceptable values are in range 1 to 2.5.