Lixing-Li/Abyme-Training-Dataset-Test-Scored-Iteration-0

--- dataset_info: features: - name: index dtype: int64 - name: prompt dtype: string - name: status dtype: string - name: output dtype: string - name: error dtype: string - name: metrics struct: - name: actual_latency_seconds dtype: float64 - name: total_llm_calls dtype: int64 - name: max_tree_depth dtype: int64 - name: max_subproblems dtype: int64 - name: max_output_chars dtype: int64 - name: theoretical_parallel_latency dtype: float64 - name: trace_tree struct: - name: prompt dtype: string - name: fragment dtype: string - name: main_problem dtype: string - name: parent_problem dtype: string - name: output dtype: string - name: type dtype: string - name: status dtype: string - name: difficulty dtype: int64 - name: depth dtype: int64 - name: index dtype: int64 - name: latency dtype: float64 - name: error_message dtype: string - name: is_cancelled dtype: bool - name: past list: - name: prompt dtype: string - name: fragment dtype: string - name: main_problem dtype: string - name: parent_problem dtype: string - name: output dtype: string - name: type dtype: string - name: status dtype: string - name: difficulty dtype: int64 - name: depth dtype: int64 - name: index dtype: int64 - name: latency dtype: float64 - name: error_message dtype: string - name: is_cancelled dtype: bool - name: past list: 'null' - name: subproblems list: - name: prompt dtype: string - name: fragment dtype: string - name: main_problem dtype: string - name: parent_problem dtype: string - name: output dtype: string - name: type dtype: string - name: status dtype: string - name: difficulty dtype: int64 - name: depth dtype: int64 - name: index dtype: int64 - name: latency dtype: float64 - name: error_message dtype: string - name: is_cancelled dtype: bool - name: past list: - name: prompt dtype: string - name: fragment dtype: string - name: main_problem dtype: string - name: parent_problem dtype: string - name: output dtype: string - name: type dtype: string - name: status dtype: string - name: difficulty dtype: int64 - name: depth dtype: int64 - name: index dtype: int64 - name: latency dtype: float64 - name: error_message dtype: string - name: is_cancelled dtype: bool - name: past list: 'null' - name: subproblems list: - name: prompt dtype: string - name: fragment dtype: string - name: main_problem dtype: string - name: parent_problem dtype: string - name: output dtype: string - name: type dtype: string - name: status dtype: string - name: difficulty dtype: int64 - name: depth dtype: int64 - name: index dtype: int64 - name: latency dtype: float64 - name: error_message dtype: string - name: is_cancelled dtype: bool - name: past list: - name: prompt dtype: string - name: fragment dtype: string - name: main_problem dtype: string - name: parent_problem dtype: string - name: output dtype: string - name: type dtype: string - name: status dtype: string - name: difficulty dtype: int64 - name: depth dtype: int64 - name: index dtype: int64 - name: latency dtype: float64 - name: error_message dtype: string - name: is_cancelled dtype: bool - name: past list: 'null' - name: subproblems list: - name: prompt dtype: string - name: fragment dtype: string - name: main_problem dtype: string - name: parent_problem dtype: string - name: output dtype: string - name: type dtype: string - name: status dtype: string - name: difficulty dtype: int64 - name: depth dtype: int64 - name: index dtype: int64 - name: latency dtype: float64 - name: error_message dtype: string - name: is_cancelled dtype: bool - name: past list: - name: prompt dtype: string - name: fragment dtype: string - name: main_problem dtype: string - name: parent_problem dtype: string - name: output dtype: string - name: type dtype: string - name: status dtype: string - name: difficulty dtype: int64 - name: depth dtype: int64 - name: index dtype: int64 - name: latency dtype: float64 - name: error_message dtype: string - name: is_cancelled dtype: bool - name: past list: 'null' - name: subproblems list: - name: prompt dtype: string - name: fragment dtype: string - name: main_problem dtype: string - name: parent_problem dtype: string - name: output dtype: string - name: type dtype: string - name: status dtype: string - name: difficulty dtype: int64 - name: depth dtype: int64 - name: index dtype: int64 - name: latency dtype: float64 - name: error_message dtype: string - name: is_cancelled dtype: bool - name: past list: - name: prompt dtype: string - name: fragment dtype: string - name: main_problem dtype: string - name: parent_problem dtype: string - name: output dtype: string - name: type dtype: string - name: status dtype: string - name: difficulty dtype: int64 - name: depth dtype: int64 - name: index dtype: int64 - name: latency dtype: float64 - name: error_message dtype: string - name: is_cancelled dtype: bool - name: past list: 'null' - name: subproblems list: - name: prompt dtype: string - name: fragment dtype: string - name: main_problem dtype: string - name: parent_problem dtype: string - name: output dtype: string - name: type dtype: string - name: status dtype: string - name: difficulty dtype: int64 - name: depth dtype: int64 - name: index dtype: int64 - name: latency dtype: float64 - name: error_message dtype: string - name: is_cancelled dtype: bool - name: past list: 'null' - name: subproblems list: 'null' - name: subproblems list: - name: prompt dtype: string - name: fragment dtype: string - name: main_problem dtype: string - name: parent_problem dtype: string - name: output dtype: string - name: type dtype: string - name: status dtype: string - name: difficulty dtype: int64 - name: depth dtype: int64 - name: index dtype: int64 - name: latency dtype: float64 - name: error_message dtype: string - name: is_cancelled dtype: bool - name: past list: 'null' - name: subproblems list: 'null' - name: subproblems list: - name: prompt dtype: string - name: fragment dtype: string - name: main_problem dtype: string - name: parent_problem dtype: string - name: output dtype: string - name: type dtype: string - name: status dtype: string - name: difficulty dtype: int64 - name: depth dtype: int64 - name: index dtype: int64 - name: latency dtype: float64 - name: error_message dtype: string - name: is_cancelled dtype: bool - name: past list: - name: prompt dtype: string - name: fragment dtype: string - name: main_problem dtype: string - name: parent_problem dtype: string - name: output dtype: string - name: type dtype: string - name: status dtype: string - name: difficulty dtype: int64 - name: depth dtype: int64 - name: index dtype: int64 - name: latency dtype: float64 - name: error_message dtype: string - name: is_cancelled dtype: bool - name: past list: 'null' - name: subproblems list: - name: prompt dtype: string - name: fragment dtype: string - name: main_problem dtype: string - name: parent_problem dtype: string - name: output dtype: string - name: type dtype: string - name: status dtype: string - name: difficulty dtype: int64 - name: depth dtype: int64 - name: index dtype: int64 - name: latency dtype: float64 - name: error_message dtype: string - name: is_cancelled dtype: bool - name: past list: 'null' - name: subproblems list: 'null' - name: subproblems list: - name: prompt dtype: string - name: fragment dtype: string - name: main_problem dtype: string - name: parent_problem dtype: string - name: output dtype: string - name: type dtype: string - name: status dtype: string - name: difficulty dtype: int64 - name: depth dtype: int64 - name: index dtype: int64 - name: latency dtype: float64 - name: error_message dtype: string - name: is_cancelled dtype: bool - name: past list: 'null' - name: subproblems list: 'null' - name: subproblems list: - name: prompt dtype: string - name: fragment dtype: string - name: main_problem dtype: string - name: parent_problem dtype: string - name: output dtype: string - name: type dtype: string - name: status dtype: string - name: difficulty dtype: int64 - name: depth dtype: int64 - name: index dtype: int64 - name: latency dtype: float64 - name: error_message dtype: string - name: is_cancelled dtype: bool - name: past list: - name: prompt dtype: string - name: fragment dtype: string - name: main_problem dtype: string - name: parent_problem dtype: string - name: output dtype: string - name: type dtype: string - name: status dtype: string - name: difficulty dtype: int64 - name: depth dtype: int64 - name: index dtype: int64 - name: latency dtype: float64 - name: error_message dtype: string - name: is_cancelled dtype: bool - name: past list: 'null' - name: subproblems list: - name: prompt dtype: string - name: fragment dtype: string - name: main_problem dtype: string - name: parent_problem dtype: string - name: output dtype: string - name: type dtype: string - name: status dtype: string - name: difficulty dtype: int64 - name: depth dtype: int64 - name: index dtype: int64 - name: latency dtype: float64 - name: error_message dtype: string - name: is_cancelled dtype: bool - name: past list: 'null' - name: subproblems list: 'null' - name: subproblems list: - name: prompt dtype: string - name: fragment dtype: string - name: main_problem dtype: string - name: parent_problem dtype: string - name: output dtype: string - name: type dtype: string - name: status dtype: string - name: difficulty dtype: int64 - name: depth dtype: int64 - name: index dtype: int64 - name: latency dtype: float64 - name: error_message dtype: string - name: is_cancelled dtype: bool - name: past list: - name: prompt dtype: string - name: fragment dtype: string - name: main_problem dtype: string - name: parent_problem dtype: string - name: output dtype: string - name: type dtype: string - name: status dtype: string - name: difficulty dtype: int64 - name: depth dtype: int64 - name: index dtype: int64 - name: latency dtype: float64 - name: error_message dtype: string - name: is_cancelled dtype: bool - name: past list: 'null' - name: subproblems list: - name: prompt dtype: string - name: fragment dtype: string - name: main_problem dtype: string - name: parent_problem dtype: string - name: output dtype: string - name: type dtype: string - name: status dtype: string - name: difficulty dtype: int64 - name: depth dtype: int64 - name: index dtype: int64 - name: latency dtype: float64 - name: error_message dtype: string - name: is_cancelled dtype: bool - name: past list: 'null' - name: subproblems list: 'null' - name: subproblems list: - name: prompt dtype: string - name: fragment dtype: string - name: main_problem dtype: string - name: parent_problem dtype: string - name: output dtype: string - name: type dtype: string - name: status dtype: string - name: difficulty dtype: int64 - name: depth dtype: int64 - name: index dtype: int64 - name: latency dtype: float64 - name: error_message dtype: string - name: is_cancelled dtype: bool - name: past list: 'null' - name: subproblems list: 'null' - name: subproblems list: - name: prompt dtype: string - name: fragment dtype: string - name: main_problem dtype: string - name: parent_problem dtype: string - name: output dtype: string - name: type dtype: string - name: status dtype: string - name: difficulty dtype: int64 - name: depth dtype: int64 - name: index dtype: int64 - name: latency dtype: float64 - name: error_message dtype: string - name: is_cancelled dtype: bool - name: past list: - name: prompt dtype: string - name: fragment dtype: string - name: main_problem dtype: string - name: parent_problem dtype: string - name: output dtype: string - name: type dtype: string - name: status dtype: string - name: difficulty dtype: int64 - name: depth dtype: int64 - name: index dtype: int64 - name: latency dtype: float64 - name: error_message dtype: string - name: is_cancelled dtype: bool - name: past list: 'null' - name: subproblems list: - name: prompt dtype: string - name: fragment dtype: string - name: main_problem dtype: string - name: parent_problem dtype: string - name: output dtype: string - name: type dtype: string - name: status dtype: string - name: difficulty dtype: int64 - name: depth dtype: int64 - name: index dtype: int64 - name: latency dtype: float64 - name: error_message dtype: string - name: is_cancelled dtype: bool - name: past list: 'null' - name: subproblems list: 'null' - name: subproblems list: - name: prompt dtype: string - name: fragment dtype: string - name: main_problem dtype: string - name: parent_problem dtype: string - name: output dtype: string - name: type dtype: string - name: status dtype: string - name: difficulty dtype: int64 - name: depth dtype: int64 - name: index dtype: int64 - name: latency dtype: float64 - name: error_message dtype: string - name: is_cancelled dtype: bool - name: past list: - name: prompt dtype: string - name: fragment dtype: string - name: main_problem dtype: string - name: parent_problem dtype: string - name: output dtype: string - name: type dtype: string - name: status dtype: string - name: difficulty dtype: int64 - name: depth dtype: int64 - name: index dtype: int64 - name: latency dtype: float64 - name: error_message dtype: string - name: is_cancelled dtype: bool - name: past list: 'null' - name: subproblems list: - name: prompt dtype: string - name: fragment dtype: string - name: main_problem dtype: string - name: parent_problem dtype: string - name: output dtype: string - name: type dtype: string - name: status dtype: string - name: difficulty dtype: int64 - name: depth dtype: int64 - name: index dtype: int64 - name: latency dtype: float64 - name: error_message dtype: string - name: is_cancelled dtype: bool - name: past list: - name: prompt dtype: string - name: fragment dtype: string - name: main_problem dtype: string - name: parent_problem dtype: string - name: output dtype: string - name: type dtype: string - name: status dtype: string - name: difficulty dtype: int64 - name: depth dtype: int64 - name: index dtype: int64 - name: latency dtype: float64 - name: error_message dtype: string - name: is_cancelled dtype: bool - name: past list: 'null' - name: subproblems list: - name: prompt dtype: string - name: fragment dtype: string - name: main_problem dtype: string - name: parent_problem dtype: string - name: output dtype: string - name: type dtype: string - name: status dtype: string - name: difficulty dtype: int64 - name: depth dtype: int64 - name: index dtype: int64 - name: latency dtype: float64 - name: error_message dtype: string - name: is_cancelled dtype: bool - name: past list: 'null' - name: subproblems list: 'null' - name: subproblems list: 'null' - name: subproblems list: - name: prompt dtype: string - name: fragment dtype: string - name: main_problem dtype: string - name: parent_problem dtype: string - name: output dtype: string - name: type dtype: string - name: status dtype: string - name: difficulty dtype: int64 - name: depth dtype: int64 - name: index dtype: int64 - name: latency dtype: float64 - name: error_message dtype: string - name: is_cancelled dtype: bool - name: past list: - name: prompt dtype: string - name: fragment dtype: string - name: main_problem dtype: string - name: parent_problem dtype: string - name: output dtype: string - name: type dtype: string - name: status dtype: string - name: difficulty dtype: int64 - name: depth dtype: int64 - name: index dtype: int64 - name: latency dtype: float64 - name: error_message dtype: string - name: is_cancelled dtype: bool - name: past list: 'null' - name: subproblems list: - name: prompt dtype: string - name: fragment dtype: string - name: main_problem dtype: string - name: parent_problem dtype: string - name: output dtype: string - name: type dtype: string - name: status dtype: string - name: difficulty dtype: int64 - name: depth dtype: int64 - name: index dtype: int64 - name: latency dtype: float64 - name: error_message dtype: string - name: is_cancelled dtype: bool - name: past list: 'null' - name: subproblems list: 'null' - name: subproblems list: 'null' - name: subproblems list: 'null' - name: problem_index dtype: int64 - name: level_num dtype: int64 - name: type dtype: string - name: ground_truth dtype: string - name: original_problem dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 5242220 num_examples: 100 download_size: 2488083 dataset_size: 5242220 configs: - config_name: default data_files: - split: train path: data/train-* ---