EvaluationLoopTrainingCallback

class EvaluationLoopTrainingCallback(factory: CoreTriplesFactory, frequency: int = 1, prefix: str | None = None, evaluator: str | Evaluator | type[Evaluator] | None = None, evaluator_kwargs: Mapping[str, Any] | None = None, additional_filter_triples: Tensor | CoreTriplesFactory | Sequence[Tensor | CoreTriplesFactory] | None = None, **kwargs)[source]

Bases: TrainingCallback

A callback for regular evaluation using new-style evaluation loops.

Initialize the callback.

Parameters:

  • factory (CoreTriplesFactory) – the triples factory comprising the evaluation triples

  • frequency (int) – the evaluation frequency

  • prefix (str | None) – a prefix to use for logging (e.g., to distinguish between different splits)

  • evaluator (HintOrType[Evaluator]) – the evaluator, or a hint thereof

  • evaluator_kwargs (OptionalKwargs) – additional keyword-based parameters used for the evaluation instantiation

  • additional_filter_triples (AdditionalFilterTriplesHint) – additional filter triples to use for creating the filter

  • kwargs – additional keyword-based parameters passed to EvaluationLoop.evaluate()

Attributes Summary

evaluation_loop

Return the evaluation loop instance (lazy-initialization).

Methods Summary

post_epoch(epoch, epoch_loss, **kwargs)

Call after epoch.

Attributes Documentation

evaluation_loop

Return the evaluation loop instance (lazy-initialization).

Methods Documentation

post_epoch(epoch: int, epoch_loss: float, **kwargs: Any) → None[source]

Call after epoch.

Parameters:
Return type:

None