gilinca/test3

--- dataset_info: - config_name: big-parquet features: - name: id dtype: int64 - name: value dtype: float64 - name: category dtype: large_string - name: text dtype: large_string splits: - name: train_1000000 num_bytes: 203000000 num_examples: 1000000 - name: train_10000000 num_bytes: 2030000000 num_examples: 10000000 - name: train_10000001 num_bytes: 2030000203 num_examples: 10000001 download_size: 283030641 dataset_size: 4263000203 - config_name: big-parquet-streamlined features: - name: id dtype: int64 - name: value dtype: float64 - name: category dtype: large_string - name: text dtype: large_string splits: - name: train_10000000 num_bytes: 2030000000 num_examples: 10000000 download_size: 134774103 dataset_size: 2030000000 - config_name: big-parquet-workflow features: - name: id dtype: int64 - name: value dtype: float64 - name: category dtype: large_string - name: text dtype: large_string splits: - name: train_1000000_100 num_bytes: 203020300 num_examples: 1000100 - name: train num_bytes: 2030060900 num_examples: 10000300 download_size: 148253056 dataset_size: 2233081200 configs: - config_name: big-parquet data_files: - split: train_1000000 path: big-parquet/train_1000000-* - split: train_10000000 path: big-parquet/train_10000000-* - split: train_10000001 path: big-parquet/train_10000001-* - config_name: big-parquet-streamlined data_files: - split: train_10000000 path: big-parquet-streamlined/train_10000000-* - config_name: big-parquet-workflow data_files: - split: train_1000000_100 path: big-parquet-workflow/train_1000000_100-* - split: train path: big-parquet-workflow/train-* ---