A single training/test example for simple sequence classification.

Writes InputFeature to TF example file.

A single set of features of data.

A single set of features of data.

Fake example so the num input examples is a multiple of the batch size. When running eval/predict on the TPU, we need to pad the number of exampl

Fake example so the num input examples is a multiple of the batch size. When running eval/predict on the TPU, we need to pad the number of examples

A basic Adam optimizer that includes "correct" L2 weight decay.

Runs basic tokenization (punctuation splitting, lower casing, etc.).

Configuration for `BertModel`.

A single training/test example for simple sequence classification.

A single set of features of data.

A single set of features of data.

A single set of features of data.

A single training/test example for simple sequence classification. For examples without an answer, the start and end position are -1.

A single training instance (sentence pair).

A single training instance (sentence pair).

Runs WordPiece tokenziation.

BERT model ("Bidirectional Encoder Representations from Transformers"). Example usage: ```python # Already been converted into WordPiece token

Processor for the CoLA data set (GLUE version).

Base class for data converters for sequence classification data sets.

Base class for data converters for sequence classification data sets.

Runs end-to-end tokenziation.

Processor for the MultiNLI data set (GLUE version).

Processor for the MRPC data set (GLUE version).

Processor for the CoLA data set (GLUE version).

Processor for the XNLI data set.