haoranli-ml/sanity_check_subset_with_step_summaries

--- dataset_info: features: - name: index dtype: int64 - name: row_id dtype: int64 - name: problem dtype: string - name: answer dtype: string - name: source list: string - name: mean_reward dtype: float64 - name: full_response dtype: string - name: full_reasoning dtype: string - name: model dtype: string - name: prefix dtype: string - name: prefix_end_index dtype: int64 - name: num_thoughts dtype: int64 - name: prefix_type dtype: string - name: prefix_type_description dtype: string - name: suffix_num list: int64 - name: suffix_model list: string - name: pending list: bool - name: pending_model list: 'null' - name: suffix_response list: string - name: suffix_summary list: string - name: self_summary list: string - name: suffix_reasoning list: string - name: finish_reason list: string - name: budget_used list: int64 - name: escalation list: int64 - name: usage list: - name: completion_tokens dtype: int64 - name: prompt_tokens dtype: int64 - name: total_tokens dtype: int64 - name: error list: 'null' - name: error_type list: 'null' - name: prefix_model dtype: string - name: gemini_summary_of_future dtype: string - name: gemini_summary_list list: string - name: prefix_len dtype: int64 - name: sum_w_prefix dtype: string - name: sum_w_prefix_reward dtype: float64 - name: sum_wo_prefix dtype: string - name: sum_wo_prefix_reward dtype: float64 - name: strategy_summary list: string - name: continuation_summary list: string - name: prefix_steps list: string - name: suffix_variants list: - name: id dtype: int64 - name: steps list: string - name: dedup_note dtype: string splits: - name: train num_bytes: 96437 num_examples: 1 download_size: 99676 dataset_size: 96437 configs: - config_name: default data_files: - split: train path: data/train-* ---