open-llm-leaderboard-old/details_leveldevai__TurdusDareBeagle-7B
收藏数据集概述
数据集简介
该数据集是在评估模型 leveldevai/TurdusDareBeagle-7B 的过程中自动创建的，用于 Open LLM Leaderboard。数据集包含63个配置，每个配置对应一个评估任务。
数据集结构
数据集由1次运行创建，每个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。
额外配置
一个额外的配置 "results" 存储了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_leveldevai__TurdusDareBeagle-7B", "harness_winogrande_5", split="train")
最新结果
以下是 最新结果 来自2024-01-18T12:52:49.102510 运行的结果：
python { "all": { "acc": 0.6547607632913887, "acc_stderr": 0.03205617544070551, "acc_norm": 0.6539975555906383, "acc_norm_stderr": 0.0327278172321473, "mc1": 0.5556915544675642, "mc1_stderr": 0.017394586250743183, "mc2": 0.6889794032014356, "mc2_stderr": 0.015072581970460247 }, "harness|arc:challenge|25": { "acc": 0.7030716723549488, "acc_stderr": 0.013352025976725223, "acc_norm": 0.726962457337884, "acc_norm_stderr": 0.013019332762635753 }, "harness|hellaswag|10": { "acc": 0.7157936666002789, "acc_stderr": 0.004501137895230723, "acc_norm": 0.8844851623182632, "acc_norm_stderr": 0.0031898897894046723 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6518518518518519, "acc_stderr": 0.041153246103369526, "acc_norm": 0.6518518518518519, "acc_norm_stderr": 0.041153246103369526 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7039473684210527, "acc_stderr": 0.03715062154998904, "acc_norm": 0.7039473684210527, "acc_norm_stderr": 0.03715062154998904 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.64, "acc_stderr": 0.04824181513244218, "acc_norm": 0.64, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.720754716981132, "acc_stderr": 0.027611163402399715, "acc_norm": 0.720754716981132, "acc_norm_stderr": 0.027611163402399715 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7777777777777778, "acc_stderr": 0.03476590104304134, "acc_norm": 0.7777777777777778, "acc_norm_stderr": 0.03476590104304134 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.47, "acc_stderr": 0.050161355804659205, "acc_norm": 0.47, "acc_norm_stderr": 0.050161355804659205 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.53, "acc_stderr": 0.050161355804659205, "acc_norm": 0.53, "acc_norm_stderr": 0.050161355804659205 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6705202312138728, "acc_stderr": 0.03583901754736412, "acc_norm": 0.6705202312138728, "acc_norm_stderr": 0.03583901754736412 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.43137254901960786, "acc_stderr": 0.04928099597287534, "acc_norm": 0.43137254901960786, "acc_norm_stderr": 0.04928099597287534 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.77, "acc_stderr": 0.04229525846816508, "acc_norm": 0.77, "acc_norm_stderr": 0.04229525846816508 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5829787234042553, "acc_stderr": 0.03223276266711712, "acc_norm": 0.5829787234042553, "acc_norm_stderr": 0.03223276266711712 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4824561403508772, "acc_stderr": 0.04700708033551038, "acc_norm": 0.4824561403508772, "acc_norm_stderr": 0.04700708033551038 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5655172413793104, "acc_stderr": 0.04130740879555498, "acc_norm": 0.5655172413793104, "acc_norm_stderr": 0.04130740879555498 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.42328042328042326, "acc_stderr": 0.025446365634406783, "acc_norm": 0.42328042328042326, "acc_norm_stderr": 0.025446365634406783 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.46825396825396826, "acc_stderr": 0.04463112720677172, "acc_norm": 0.46825396825396826, "acc_norm_stderr": 0.04463112720677172 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.33, "acc_stderr": 0.04725815626252604, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252604 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7870967741935484, "acc_stderr": 0.02328766512726854, "acc_norm": 0.7870967741935484, "acc_norm_stderr": 0.02328766512726854 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5024630541871922, "acc_stderr": 0.035179450386910616, "acc_norm": 0.5024630541871922, "acc_norm_stderr": 0.035179450386910616 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.7, "acc_stderr": 0.046056618647183814, "acc_norm": 0.7, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7818181818181819, "acc_stderr": 0.03225078108306289, "acc_norm": 0.7818181818181819, "acc_norm_stderr": 0.03225078108306289 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7929292929292929, "acc_stderr": 0.028869778460267045, "acc_norm": 0.7929292929292929, "acc_norm_stderr": 0.028869778460267045 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9067357512953368, "acc_stderr": 0.02098685459328974, "acc_norm": 0.9067357512953368, "acc_norm_stderr": 0.02098685459328974 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6615384615384615, "acc_stderr": 0.023991500500313036, "acc_norm": 0.6615384615384615, "acc_norm_stderr": 0.023991500500313036 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3296296296296296, "acc_stderr": 0.02866120111652457, "acc_norm": 0.3296296296296296, "acc_norm_stderr": 0.02866120111652457 },
