nep.in
¶
This file specifies hyperparameters used for training neuroevolution potential (NEP) models, the functional form of which is outline here. The NEP approach was proposed in [Fan2021] (NEP1) and later improved in [Fan2022a] (NEP2) and [Fan2022b] (NEP3). Currently, we support NEP3 and NEP4 (to be published), which can be chosen by the version keyword.
File format¶
In this input file, blank lines and lines starting with #
are ignored.
One can thus write comments after #
.
All other lines need to be of the following form:
keyword parameter_1 parameter_2 ...
Keywords can appear in any order with the exception of the type_weight keyword, which cannot appear before the type keyword.
The type keyword does not have default parameters and must be set. All other keywords have default values.
Keywords¶
Keyword |
Brief description |
---|---|
select between NEP3 and NEP4 |
|
number of atom types and list of chemical species |
|
force weights for different atom types |
|
select to train potential, dipole, or polarizability |
|
select between training and prediction (inference) |
|
outer cutoff for the universal ZBL potential [Ziegler1985] |
|
radial (\(r_\mathrm{c}^\mathrm{R}\)) and angular (\(r_\mathrm{c}^\mathrm{A}\)) cutoffs |
|
size of radial (\(n_\mathrm{max}^\mathrm{R}\)) and angular (\(n_\mathrm{max}^\mathrm{A}\)) basis |
|
number of radial (\(N_\mathrm{bas}^\mathrm{R}\)) and angular (\(N_\mathrm{bas}^\mathrm{A}\)) basis functions |
|
expansion order for angular terms |
|
number of neurons in the hidden layer (\(N_\mathrm{neu}\)) |
|
weight of \(\mathcal{L}_1\)-norm regularization term |
|
weight of \(\mathcal{L}_2\)-norm regularization term |
|
weight of energy loss term |
|
weight of force loss term |
|
weight of virial loss term |
|
bias term that can be used to make smaller forces more accurate |
|
batch size for training |
|
population size used in the SNES algorithm [Schaul2011] |
|
number of generations used by the SNES algorithm [Schaul2011] |
Example¶
Here is an example nep.in
file using all the default parameters:
type 2 Te Pb # this is a mandatory keyword
version 4 # default
cutoff 8 4 # default
n_max 4 4 # default
basis_size 8 8 # default
l_max 4 2 0 # default
neuron 30 # default
lambda_e 1.0 # default
lambda_f 1.0 # default
lambda_v 0.1 # default
batch 1000 # default
population 50 # default
generation 100000 # default
The NEP tutorial illustrates the construction of a NEP model. More examples can be found in this repository.