cerebras.modelzoo.data.nlp.bert.config.SST2DataProcessorConfig#

class cerebras.modelzoo.data.nlp.bert.config.SST2DataProcessorConfig(batch_size: int = <object object at 0x7f0436677b60>, shuffle: bool = True, shuffle_seed: int = 0, num_workers: int = 0, prefetch_factor: int = 10, persistent_workers: bool = True, vocab_file: str = <object object at 0x7f0436677b60>, data_dir: Union[str, List[str]] = <object object at 0x7f0436677b60>, max_sequence_length: int = <object object at 0x7f0436677b60>, shuffle_buffer: Optional[int] = None, do_lower: bool = False, drop_last: bool = True)[source]#
batch_size: int = <object object>#

Batch size to be used

data_dir: Union[str, List[str]] = <object object>#

The path to the HDF5 files.

do_lower: bool = False#
drop_last: bool = True#

similar to the PyTorch drop_last setting except that samples that when set to True, samples that would have been dropped at the end of one epoch are yielded at the start of the next epoch so that there is no data loss. This is necessary for a data ordering that is independent of the distributed setup being used.

max_sequence_length: int = <object object>#
num_workers: int = 0#

The number of PyTorch processes used in the dataloader

persistent_workers: bool = True#

Whether or not to keep workers persistent between epochs

prefetch_factor: int = 10#

The number of batches to prefetch in the dataloader

shuffle: bool = True#

Whether or not to shuffle the dataset

shuffle_buffer: Optional[int] = None#

Size of shuffle buffer in samples.

shuffle_seed: int = 0#

Seed used for deterministic shuffling

vocab_file: str = <object object>#