open-llm-leaderboard-old/details_Sharathhebbar24__math_gpt2
收藏数据集概述
数据集来源
该数据集是在评估模型 Sharathhebbar24/math_gpt2 在 Open LLM Leaderboard 上的自动创建的。
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。
额外配置
一个额外的配置 "results" 存储了所有运行的聚合结果，用于计算和显示在 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_Sharathhebbar24__math_gpt2", "harness_winogrande_5", split="train")
最新结果
这些是最新的结果，来自 2024-01-26T07:09:19.520655 的运行：
python { "all": { "acc": 0.2537277677214805, "acc_stderr": 0.030414705424890588, "acc_norm": 0.25449605304374584, "acc_norm_stderr": 0.031197470483049602, "mc1": 0.24357405140758873, "mc1_stderr": 0.015026354824910782, "mc2": 0.39231215031317224, "mc2_stderr": 0.014532764644713165 }, "harness|arc:challenge|25": { "acc": 0.2090443686006826, "acc_stderr": 0.01188274698740645, "acc_norm": 0.24232081911262798, "acc_norm_stderr": 0.012521593295800116 }, "harness|hellaswag|10": { "acc": 0.29127663811989646, "acc_stderr": 0.004534221350046117, "acc_norm": 0.3088030272854013, "acc_norm_stderr": 0.004610554974411242 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.18, "acc_stderr": 0.03861229196653694, "acc_norm": 0.18, "acc_norm_stderr": 0.03861229196653694 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.2740740740740741, "acc_stderr": 0.03853254836552003, "acc_norm": 0.2740740740740741, "acc_norm_stderr": 0.03853254836552003 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.17763157894736842, "acc_stderr": 0.031103182383123398, "acc_norm": 0.17763157894736842, "acc_norm_stderr": 0.031103182383123398 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.2, "acc_stderr": 0.040201512610368445, "acc_norm": 0.2, "acc_norm_stderr": 0.040201512610368445 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.24528301886792453, "acc_stderr": 0.026480357179895702, "acc_norm": 0.24528301886792453, "acc_norm_stderr": 0.026480357179895702 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.22916666666666666, "acc_stderr": 0.035146974678623884, "acc_norm": 0.22916666666666666, "acc_norm_stderr": 0.035146974678623884 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.21, "acc_stderr": 0.04093601807403326, "acc_norm": 0.21, "acc_norm_stderr": 0.04093601807403326 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.24, "acc_stderr": 0.042923469599092816, "acc_norm": 0.24, "acc_norm_stderr": 0.042923469599092816 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.24, "acc_stderr": 0.042923469599092816, "acc_norm": 0.24, "acc_norm_stderr": 0.042923469599092816 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.24277456647398843, "acc_stderr": 0.0326926380614177, "acc_norm": 0.24277456647398843, "acc_norm_stderr": 0.0326926380614177 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.22549019607843138, "acc_stderr": 0.041583075330832865, "acc_norm": 0.22549019607843138, "acc_norm_stderr": 0.041583075330832865 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.16, "acc_stderr": 0.03684529491774708, "acc_norm": 0.16, "acc_norm_stderr": 0.03684529491774708 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.2680851063829787, "acc_stderr": 0.028957342788342347, "acc_norm": 0.2680851063829787, "acc_norm_stderr": 0.028957342788342347 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2631578947368421, "acc_stderr": 0.041424397194893624, "acc_norm": 0.2631578947368421, "acc_norm_stderr": 0.041424397194893624 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2482758620689655, "acc_stderr": 0.03600105692727771, "acc_norm": 0.2482758620689655, "acc_norm_stderr": 0.03600105692727771 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.24338624338624337, "acc_stderr": 0.022101128787415433, "acc_norm": 0.24338624338624337, "acc_norm_stderr": 0.022101128787415433 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.15079365079365079, "acc_stderr": 0.03200686497287392, "acc_norm": 0.15079365079365079, "acc_norm_stderr": 0.03200686497287392 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.18, "acc_stderr": 0.038612291966536934, "acc_norm": 0.18, "acc_norm_stderr": 0.038612291966536934 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.3096774193548387, "acc_stderr": 0.026302774983517414, "acc_norm": 0.3096774193548387, "acc_norm_stderr": 0.026302774983517414 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.26108374384236455, "acc_stderr": 0.030903796952114475, "acc_norm": 0.26108374384236455, "acc_norm_stderr": 0.030903796952114475 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.19, "acc_stderr": 0.039427724440366234, "acc_norm": 0.19, "acc_norm_stderr": 0.039427724440366234 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.21818181818181817, "acc_stderr": 0.03225078108306289, "acc_norm": 0.21818181818181817, "acc_norm_stderr": 0.03225078108306289 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.35353535353535354, "acc_stderr": 0.03406086723547153, "acc_norm": 0.35353535353535354, "acc_norm_stderr": 0.03406086723547153 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.36787564766839376, "acc_stderr": 0.03480175668466036, "acc_norm": 0.36787564766839376, "acc_norm_stderr": 0.03480175668466036 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.2923076923076923, "acc_stderr": 0.023060438380857733, "acc_norm": 0.2923076923076923, "acc_norm_stderr": 0.023060438380857733 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2740740740740741, "acc_stderr": 0.027195934804085626, "acc_norm": 0.2740740740740741, "acc_norm_stderr": 0.027195934804085626 }, "harness|hendrycksTest-high
