megatron.data.dataset_utils.build_train_valid_test_datasets

megatron.data.dataset_utils.build_train_valid_test_datasets(data_prefix, data_impl, splits_string, train_valid_test_num_samples, max_seq_length, masked_lm_prob, short_seq_prob, seed, skip_warmup, binary_head=False, max_seq_length_dec=None, dataset_type='standard_bert')