open-llm-leaderboard-old/details_pansophic__new_model_test
收藏数据集概述
该数据集是在模型pansophic/new_model_test的评估运行期间自动创建的，用于Open LLM Leaderboard。
数据集组成
- 数据集包含63个配置，每个配置对应一个评估任务。
- 数据集从1次运行中创建，每次运行可以在每个配置中找到特定的分割，分割名称使用运行的时间戳。
- "train"分割始终指向最新的结果。
- 额外的配置"results"存储所有运行的聚合结果，用于计算和显示Open LLM Leaderboard上的聚合指标。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_pansophic__new_model_test", "harness_winogrande_5", split="train")
最新结果
以下是2024-02-29T18:43:28.582907运行的最新结果：
python { "all": { "acc": 0.4639971505070735, "acc_stderr": 0.034656622817217424, "acc_norm": 0.4660219805936662, "acc_norm_stderr": 0.03536970907083775, "mc1": 0.31334149326805383, "mc1_stderr": 0.016238065069059615, "mc2": 0.5124518749351841, "mc2_stderr": 0.014906275227740079 }, "harness|arc:challenge|25": { "acc": 0.49402730375426623, "acc_stderr": 0.014610348300255795, "acc_norm": 0.5255972696245734, "acc_norm_stderr": 0.014592230885298962 }, "harness|hellaswag|10": { "acc": 0.5337582154949213, "acc_stderr": 0.004978395540514382, "acc_norm": 0.7365066719776937, "acc_norm_stderr": 0.004396273173717462 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.4148148148148148, "acc_stderr": 0.042561937679014075, "acc_norm": 0.4148148148148148, "acc_norm_stderr": 0.042561937679014075 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.45394736842105265, "acc_stderr": 0.04051646342874142, "acc_norm": 0.45394736842105265, "acc_norm_stderr": 0.04051646342874142 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.49, "acc_stderr": 0.05024183937956911, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956911 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.4981132075471698, "acc_stderr": 0.030772653642075664, "acc_norm": 0.4981132075471698, "acc_norm_stderr": 0.030772653642075664 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5069444444444444, "acc_stderr": 0.04180806750294938, "acc_norm": 0.5069444444444444, "acc_norm_stderr": 0.04180806750294938 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.38, "acc_stderr": 0.04878317312145633, "acc_norm": 0.38, "acc_norm_stderr": 0.04878317312145633 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.41040462427745666, "acc_stderr": 0.03750757044895537, "acc_norm": 0.41040462427745666, "acc_norm_stderr": 0.03750757044895537 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.23529411764705882, "acc_stderr": 0.04220773659171452, "acc_norm": 0.23529411764705882, "acc_norm_stderr": 0.04220773659171452 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.51, "acc_stderr": 0.05024183937956912, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.44680851063829785, "acc_stderr": 0.0325005368436584, "acc_norm": 0.44680851063829785, "acc_norm_stderr": 0.0325005368436584 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.3157894736842105, "acc_stderr": 0.04372748290278007, "acc_norm": 0.3157894736842105, "acc_norm_stderr": 0.04372748290278007 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5103448275862069, "acc_stderr": 0.04165774775728763, "acc_norm": 0.5103448275862069, "acc_norm_stderr": 0.04165774775728763 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.328042328042328, "acc_stderr": 0.02418049716437689, "acc_norm": 0.328042328042328, "acc_norm_stderr": 0.02418049716437689 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.373015873015873, "acc_stderr": 0.04325506042017086, "acc_norm": 0.373015873015873, "acc_norm_stderr": 0.04325506042017086 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.34, "acc_stderr": 0.047609522856952365, "acc_norm": 0.34, "acc_norm_stderr": 0.047609522856952365 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.5258064516129032, "acc_stderr": 0.02840609505765332, "acc_norm": 0.5258064516129032, "acc_norm_stderr": 0.02840609505765332 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.458128078817734, "acc_stderr": 0.03505630140785741, "acc_norm": 0.458128078817734, "acc_norm_stderr": 0.03505630140785741 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.45, "acc_stderr": 0.05, "acc_norm": 0.45, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6181818181818182, "acc_stderr": 0.03793713171165635, "acc_norm": 0.6181818181818182, "acc_norm_stderr": 0.03793713171165635 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.5757575757575758, "acc_stderr": 0.035212249088415845, "acc_norm": 0.5757575757575758, "acc_norm_stderr": 0.035212249088415845 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.6269430051813472, "acc_stderr": 0.03490205592048574, "acc_norm": 0.6269430051813472, "acc_norm_stderr": 0.03490205592048574 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.40512820512820513, "acc_stderr": 0.024890471769938145, "acc_norm": 0.40512820512820513, "acc_norm_stderr": 0.024890471769938145 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2962962962962963, "acc_stderr": 0.02784081149587193, "acc_norm": 0.2962962962962963, "acc_norm_stderr": 0.02784081149587193 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.42857
