ForceFieldDatasetParameters

Included in QATK.MLFF

class ForceFieldDatasetParameters(dataset_name=None, validation_fraction=None, isolated_atom_energies=None, energy_key=None, forces_key=None, stress_key=None, energy_weight=None, forces_weight=None, stress_weight=None, compute_stress=None, forces_cap=None, replay_finetuning_settings=None)

Constructor for ForceFieldDatasetParameters.

Parameters:
  • dataset_name (str) – Name of the dataset.

  • validation_fraction (float) – The fraction of the training data to use for validation.

  • isolated_atom_energies (dict of {Element: PhysicalQuantity of type energy}) – The energy of an isolated atom for each species.

  • energy_key (str) – The key for the energy in the dataset.

  • forces_key (str) – The key for the forces in the dataset.

  • stress_key (str) – The key for the stress in the dataset.

  • energy_weight (float) – The weight of the energy loss.

  • forces_weight (float) – The weight of the forces loss.

  • stress_weight (float) – The weight of the stress loss.

  • compute_stress (bool) – Whether to compute the stress.

  • forces_cap (PhysicalQuantity of type energy / length) – Configurations with max. force magnitudes on an atom larger than this value will be discarded from the training data.
    Default: None (no cap).

  • replay_finetuning_settings (MACEReplayFinetuningSettings or None) – Configuration for replay fine-tuning with data from foundation models.

computeStress()
Returns:

Whether to compute the stress.

Return type:

bool

datasetName()
Returns:

The name of the dataset.

Return type:

str

energyKey()
Returns:

The key for the energy in the dataset.

Return type:

str

energyWeight()
Returns:

The weight of the energy loss.

Return type:

float

forcesCap()
Returns:

The forces cap value.

Return type:

PhysicalQuantity of type energy / length or None

forcesKey()
Returns:

The key for the forces in the dataset.

Return type:

str

forcesWeight()
Returns:

The weight of the forces loss.

Return type:

float

hasReplayFinetuning()

Check if replay fine-tuning is enabled.

Returns:

True if replay fine-tuning is configured, False otherwise.

Return type:

bool

isolatedAtomEnergies()
Returns:

The energy of an isolated atom for each species.

Return type:

dict of {Element: PhysicalQuantity of type energy}

nlinfo()
Returns:

The nlinfo.

Return type:

dict

replayFinetuningSettings()
Returns:

The replay fine-tuning configuration settings.

Return type:

MACEReplayFinetuningSettings or None

stressKey()
Returns:

The key for the stress in the dataset.

Return type:

str

stressWeight()
Returns:

The weight of the stress loss.

Return type:

float

uniqueString()

Return a unique string representing the state of the object.

validationFraction()
Returns:

The fraction of the training data to use for validation.

Return type:

float