quynong/dataset-stratified-5folds
收藏资源简介:
--- dataset_info: features: - name: language dtype: string - name: source_text dtype: string - name: privacy_mask list: - name: _fix_status dtype: string - name: end dtype: int64 - name: label dtype: string - name: start dtype: int64 - name: value dtype: string splits: - name: fold_0_train num_bytes: 14232433 num_examples: 9965 - name: fold_0_test num_bytes: 3559179 num_examples: 2492 - name: fold_1_train num_bytes: 14232433 num_examples: 9965 - name: fold_1_test num_bytes: 3559179 num_examples: 2492 - name: fold_2_train num_bytes: 14233861 num_examples: 9966 - name: fold_2_test num_bytes: 3557751 num_examples: 2491 - name: fold_3_train num_bytes: 14233861 num_examples: 9966 - name: fold_3_test num_bytes: 3557751 num_examples: 2491 - name: fold_4_train num_bytes: 14233861 num_examples: 9966 - name: fold_4_test num_bytes: 3557751 num_examples: 2491 download_size: 40112945 dataset_size: 88958060 configs: - config_name: default data_files: - split: fold_0_train path: data/fold_0_train-* - split: fold_0_test path: data/fold_0_test-* - split: fold_1_train path: data/fold_1_train-* - split: fold_1_test path: data/fold_1_test-* - split: fold_2_train path: data/fold_2_train-* - split: fold_2_test path: data/fold_2_test-* - split: fold_3_train path: data/fold_3_train-* - split: fold_3_test path: data/fold_3_test-* - split: fold_4_train path: data/fold_4_train-* - split: fold_4_test path: data/fold_4_test-* ---



