jihuny/ultrafeedback_iterative_dpo_iter4

--- dataset_info: features: - name: prompt dtype: string - name: chosen dtype: string - name: rejected dtype: string splits: - name: train num_bytes: 234216852 num_examples: 57705 download_size: 126807106 dataset_size: 234216852 configs: - config_name: default data_files: - split: train path: data/train-* ---This dataset contains three string-type features: prompt, chosen, and rejected. It only includes one training split (train), with a total of 57,705 samples and an overall size of 234,216,852 bytes.