jihuny/llama_shp_10k_sky_active_rgopt_g03_l1e2

--- dataset_info: features: - name: prompt dtype: string - name: prompt_idx dtype: int32 - name: response_a dtype: string - name: response_b dtype: string - name: response_a_idx dtype: int32 - name: response_b_idx dtype: int32 - name: logprob_a dtype: float32 - name: logprob_b dtype: float32 - name: embedding_difference list: float32 length: 2048 - name: score_a dtype: float64 - name: score_b dtype: float64 - name: dpo_gopt_score dtype: float64 - name: rank dtype: int64 splits: - name: train num_bytes: 144644165 num_examples: 10000 download_size: 64618551 dataset_size: 144644165 configs: - config_name: default data_files: - split: train path: data/train-* ---