open-llm-leaderboard/details_vanillaOVO__correction_1
收藏资源简介:
该数据集是在Open LLM Leaderboard上对模型vanillaOVO/correction_1进行评估时自动创建的。数据集包含63个配置,每个配置对应一个评估任务。数据集由1次运行生成,每次运行的结果作为特定配置中的一个分割,分割名称使用运行的时间戳。train分割始终指向最新结果。此外,results配置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。
该数据集是在Open LLM Leaderboard上对模型vanillaOVO/correction_1进行评估时自动创建的。数据集包含63个配置,每个配置对应一个评估任务。数据集由1次运行生成,每次运行的结果作为特定配置中的一个分割,分割名称使用运行的时间戳。train分割始终指向最新结果。此外,results配置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。
数据集概述
数据集组成
- 该数据集包含63个配置,每个配置对应一个评估任务。
- 数据集是从1次运行中创建的,每个运行可以在每个配置中找到一个特定的分割,分割名称使用运行的时间戳。
- "train"分割始终指向最新的结果。
- 一个额外的配置"results"存储所有运行的聚合结果,用于计算和显示在Open LLM Leaderboard上的聚合指标。
最新结果
- 以下是2024-03-27T17:47:43.731567运行的最新结果:
python { "all": { "acc": 0.63686068515643, "acc_stderr": 0.03236847187748598, "acc_norm": 0.6406611225738374, "acc_norm_stderr": 0.033058516894310476, "mc1": 0.4969400244798042, "mc1_stderr": 0.01750317326096062, "mc2": 0.6591639079987147, "mc2_stderr": 0.015796990567396845 }, "harness|arc:challenge|25": { "acc": 0.681740614334471, "acc_stderr": 0.013611993916971453, "acc_norm": 0.71160409556314, "acc_norm_stderr": 0.013238394422428175 }, "harness|hellaswag|10": { "acc": 0.7289384584744075, "acc_stderr": 0.004435993492583879, "acc_norm": 0.8858793069109739, "acc_norm_stderr": 0.003173079807440182 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6148148148148148, "acc_stderr": 0.04203921040156279, "acc_norm": 0.6148148148148148, "acc_norm_stderr": 0.04203921040156279 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6973684210526315, "acc_stderr": 0.03738520676119669, "acc_norm": 0.6973684210526315, "acc_norm_stderr": 0.03738520676119669 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.65, "acc_stderr": 0.0479372485441102, "acc_norm": 0.65, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.690566037735849, "acc_stderr": 0.028450154794118637, "acc_norm": 0.690566037735849, "acc_norm_stderr": 0.028450154794118637 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7569444444444444, "acc_stderr": 0.03586879280080341, "acc_norm": 0.7569444444444444, "acc_norm_stderr": 0.03586879280080341 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.51, "acc_stderr": 0.05024183937956912, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956912 }, "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": 0.6069364161849711, "acc_stderr": 0.0372424959581773, "acc_norm": 0.6069364161849711, "acc_norm_stderr": 0.0372424959581773 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3627450980392157, "acc_stderr": 0.047840607041056527, "acc_norm": 0.3627450980392157, "acc_norm_stderr": 0.047840607041056527 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.75, "acc_stderr": 0.04351941398892446, "acc_norm": 0.75, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5446808510638298, "acc_stderr": 0.03255525359340355, "acc_norm": 0.5446808510638298, "acc_norm_stderr": 0.03255525359340355 }, "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": 0.5379310344827586, "acc_stderr": 0.04154659671707548, "acc_norm": 0.5379310344827586, "acc_norm_stderr": 0.04154659671707548 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.43386243386243384, "acc_stderr": 0.02552503438247489, "acc_norm": 0.43386243386243384, "acc_norm_stderr": 0.02552503438247489 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4523809523809524, "acc_stderr": 0.044518079590553275, "acc_norm": 0.4523809523809524, "acc_norm_stderr": 0.044518079590553275 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.37, "acc_stderr": 0.04852365870939098, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939098 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7806451612903226, "acc_stderr": 0.023540799358723295, "acc_norm": 0.7806451612903226, "acc_norm_stderr": 0.023540799358723295 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.49261083743842365, "acc_stderr": 0.035176035403610084, "acc_norm": 0.49261083743842365, "acc_norm_stderr": 0.035176035403610084 }, "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": 0.8, "acc_stderr": 0.031234752377721175, "acc_norm": 0.8, "acc_norm_stderr": 0.031234752377721175 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7828282828282829, "acc_stderr": 0.02937661648494562, "acc_norm": 0.7828282828282829, "acc_norm_stderr": 0.02937661648494562 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8860103626943006, "acc_stderr": 0.022935144053919436, "acc_norm": 0.8860103626943006, "acc_norm_stderr": 0.022935144053919436 }, "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": 0.32592592592592595, "acc_stderr": 0.028578348365473082, "acc_norm": 0.32592592592592595, "acc_norm_stderr": 0.028578348365473082 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.7058823529411765, "acc_stderr": 0.029597329730978082, "acc_norm": 0.7058823529411765, "acc_norm_stderr": 0.029597329730978082 }, "harness|hendrycksTest-high_school_physics|5": { "acc": 0.357615894039735



