jz666/llama3-ultrafeedback-templated-ppl-margin-5

--- dataset_info: features: - name: prompt_id dtype: string - name: prompt dtype: string - name: all_generated_responses sequence: string - name: all_rm_scores sequence: float64 - name: chosen list: - name: content dtype: string - name: role dtype: string - name: rejected list: - name: content dtype: string - name: role dtype: string - name: ppl_chosen dtype: float64 - name: nll_chosen dtype: float64 - name: ppl_rejected dtype: float64 - name: nll_rejected dtype: float64 splits: - name: train num_bytes: 884573190 num_examples: 59876 - name: test num_bytes: 28746644 num_examples: 1961 - name: train_correct_q1 num_bytes: 89851929.68100742 num_examples: 6082 - name: train_correct_q2 num_bytes: 89837156.2627764 num_examples: 6081 - name: train_correct_q3 num_bytes: 89837156.2627764 num_examples: 6081 - name: train_correct_q4 num_bytes: 89837156.2627764 num_examples: 6081 - name: train_correct_q5 num_bytes: 89837156.2627764 num_examples: 6081 - name: train_wrong_q1 num_bytes: 86941566.2894983 num_examples: 5885 - name: train_wrong_q2 num_bytes: 86941566.2894983 num_examples: 5885 - name: train_wrong_q3 num_bytes: 86941566.2894983 num_examples: 5885 - name: train_wrong_q4 num_bytes: 86926792.87126729 num_examples: 5884 - name: train_wrong_q5 num_bytes: 86926792.87126729 num_examples: 5884 - name: train_all_q1 num_bytes: 176926456.7345848 num_examples: 11976 - name: train_all_q2 num_bytes: 176911683.3163538 num_examples: 11975 - name: train_all_q3 num_bytes: 176911683.3163538 num_examples: 11975 - name: train_all_q4 num_bytes: 176911683.3163538 num_examples: 11975 - name: train_all_q5 num_bytes: 176911683.3163538 num_examples: 11975 download_size: 1236032568 dataset_size: 2681771863.3431425 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* - split: train_correct_q1 path: data/train_correct_q1-* - split: train_correct_q2 path: data/train_correct_q2-* - split: train_correct_q3 path: data/train_correct_q3-* - split: train_correct_q4 path: data/train_correct_q4-* - split: train_correct_q5 path: data/train_correct_q5-* - split: train_wrong_q1 path: data/train_wrong_q1-* - split: train_wrong_q2 path: data/train_wrong_q2-* - split: train_wrong_q3 path: data/train_wrong_q3-* - split: train_wrong_q4 path: data/train_wrong_q4-* - split: train_wrong_q5 path: data/train_wrong_q5-* - split: train_all_q1 path: data/train_all_q1-* - split: train_all_q2 path: data/train_all_q2-* - split: train_all_q3 path: data/train_all_q3-* - split: train_all_q4 path: data/train_all_q4-* - split: train_all_q5 path: data/train_all_q5-* ---