abehandlerorg/confounddataset

--- dataset_info: features: - name: text dtype: string - name: url dtype: string - name: crawl_date dtype: timestamp[ns, tz=UTC] - name: source_domain dtype: string - name: group dtype: string - name: id dtype: string - name: in_blocksbin dtype: int64 - name: in_noblocksbin dtype: int64 - name: tag dtype: string - name: minhash_count dtype: string splits: - name: train num_bytes: 646440922 num_examples: 185602 download_size: 352613159 dataset_size: 646440922 configs: - config_name: default data_files: - split: train path: data/train-* ---