parameterlab/scaling_mia_the_pile_00_DM_Mathematics

--- dataset_info: features: - name: text dtype: string - name: meta struct: - name: pile_set_name dtype: string splits: - name: train num_bytes: 521694320 num_examples: 63503 - name: validation num_bytes: 16489512 num_examples: 2007 - name: test num_bytes: 15791152 num_examples: 1922 download_size: 279645764 dataset_size: 553974984 configs: - config_name: default data_files: - split: train path: data/train-* - split: validation path: data/validation-* - split: test path: data/test-* ---