QuestionAnsweringTask

class flash.text.question_answering.model.QuestionAnsweringTask(backbone='sshleifer/tiny-distilbert-base-cased-distilled-squad', max_source_length=384, max_target_length=30, padding='max_length', doc_stride=128, loss_fn=None, optimizer='Adam', lr_scheduler=None, metrics=None, learning_rate=None, enable_ort=False, n_best_size=20, version_2_with_negative=True, null_score_diff_threshold=0.0, use_stemmer=True)

The QuestionAnsweringTask is a Task for extractive question answering. For more details, see question_answering.

You can change the backbone to any question answering model from HuggingFace/transformers using the backbone argument.

Note

When changing the backbone, make sure you pass in the same backbone to the Task and the DataModule object! Since this is a QuestionAnswering task, make sure you use a QuestionAnswering model.

Parameters

• backbone (str) – backbone model to use for the task.

• max_source_length (int) – Max length of the sequence to be considered during tokenization.

• max_target_length (int) – Max length of each answer to be produced.

• padding (Union[str, bool]) – Padding type during tokenization.

• doc_stride (int) – The stride amount to be taken when splitting up a long document into chunks.

• loss_fn (Union[Callable, Mapping, Sequence, None]) – Loss function for training.

• optimizer (TypeVar(OPTIMIZER_TYPE, str, Callable, Tuple[str, Dict[str, Any]], None)) – Optimizer to use for training.

• lr_scheduler (Optional[TypeVar(LR_SCHEDULER_TYPE, str, Callable, Tuple[str, Dict[str, Any]], Tuple[str, Dict[str, Any], Dict[str, Any]], None)]) – The LR scheduler to use during training.

• metrics (Optional[TypeVar(METRICS_TYPE, Metric, Mapping, Sequence, None)]) – Metrics to compute for training and evaluation. Defauls to calculating the ROUGE metric. Changing this argument currently has no effect.

• learning_rate (Optional[float]) – Learning rate to use for training, defaults to 3e-4

• enable_ort (bool) – Enable Torch ONNX Runtime Optimization: https://onnxruntime.ai/docs/#onnx-runtime-for-training

• n_best_size (int) – The total number of n-best predictions to generate when looking for an answer.

• version_2_with_negative (bool) – If true, some of the examples do not have an answer.

• max_answer_length – The maximum length of an answer that can be generated. This is needed because the start and end predictions are not conditioned on one another.

• null_score_diff_threshold (float) – The threshold used to select the null answer: if the best answer has a score that is less than the score of the null answer minus this threshold, the null answer is selected for this example. Only useful when version_2_with_negative=True.

• use_stemmer (bool) – Whether Porter stemmer should be used to strip word suffixes to improve matching.

classmethod available_finetuning_strategies(cls)

Returns a list containing the keys of the available Finetuning Strategies.

Return type

List[str]

classmethod available_lr_schedulers(cls)

Returns a list containing the keys of the available LR schedulers.

Return type

List[str]

classmethod available_optimizers(cls)

Returns a list containing the keys of the available Optimizers.

Return type

List[str]

classmethod available_outputs(cls)

Returns the list of available outputs (that can be used during prediction or serving) for this Task.

Examples

..testsetup:

>>> from flash import Task

>>> print(Task.available_outputs())
['preds', 'raw']

Return type

List[str]

modules_to_freeze()

Return the module attributes of the model to be frozen.

Return type

Union[Module, Iterable[Union[Module, Iterable]]]

property task: Optional[str]

Override to define AutoConfig task specific parameters stored within the model.

Return type

Optional[str]