open-llm-leaderboard-old/details_brucethemoose__Yi-34B-200K-DARE-merge-v7
收藏数据集概述
数据集简介
该数据集是在评估模型brucethemoose/Yi-34B-200K-DARE-merge-v7在Open LLM Leaderboard上的自动创建的。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。
结果配置
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_brucethemoose__Yi-34B-200K-DARE-merge-v7", "harness_winogrande_5", split="train")
最新结果
这些是最新的结果，来自2024-01-13T18:00:33.123437的运行： python { "all": { "acc": 0.7681401846074161, "acc_stderr": 0.02789845201480161, "acc_norm": 0.7728973251356218, "acc_norm_stderr": 0.02841712456337832, "mc1": 0.4283965728274174, "mc1_stderr": 0.017323088597314754, "mc2": 0.5890169683214581, "mc2_stderr": 0.0152246570119347 }, "harness|arc:challenge|25": { "acc": 0.6527303754266212, "acc_stderr": 0.013913034529620453, "acc_norm": 0.6808873720136519, "acc_norm_stderr": 0.013621696119173304 }, "harness|hellaswag|10": { "acc": 0.6590320653256323, "acc_stderr": 0.004730658073041562, "acc_norm": 0.8598884684325832, "acc_norm_stderr": 0.003463933286063885 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.7407407407407407, "acc_stderr": 0.03785714465066653, "acc_norm": 0.7407407407407407, "acc_norm_stderr": 0.03785714465066653 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.875, "acc_stderr": 0.026913523521537846, "acc_norm": 0.875, "acc_norm_stderr": 0.026913523521537846 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.77, "acc_stderr": 0.04229525846816505, "acc_norm": 0.77, "acc_norm_stderr": 0.04229525846816505 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.8150943396226416, "acc_stderr": 0.02389335183446432, "acc_norm": 0.8150943396226416, "acc_norm_stderr": 0.02389335183446432 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.9097222222222222, "acc_stderr": 0.023964965777906935, "acc_norm": 0.9097222222222222, "acc_norm_stderr": 0.023964965777906935 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.62, "acc_stderr": 0.04878317312145633, "acc_norm": 0.62, "acc_norm_stderr": 0.04878317312145633 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.46, "acc_stderr": 0.05009082659620332, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7456647398843931, "acc_stderr": 0.0332055644308557, "acc_norm": 0.7456647398843931, "acc_norm_stderr": 0.0332055644308557 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.5588235294117647, "acc_stderr": 0.049406356306056595, "acc_norm": 0.5588235294117647, "acc_norm_stderr": 0.049406356306056595 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.84, "acc_stderr": 0.03684529491774709, "acc_norm": 0.84, "acc_norm_stderr": 0.03684529491774709 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.7829787234042553, "acc_stderr": 0.02694748312149623, "acc_norm": 0.7829787234042553, "acc_norm_stderr": 0.02694748312149623 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.6052631578947368, "acc_stderr": 0.045981880578165414, "acc_norm": 0.6052631578947368, "acc_norm_stderr": 0.045981880578165414 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.7862068965517242, "acc_stderr": 0.03416520447747548, "acc_norm": 0.7862068965517242, "acc_norm_stderr": 0.03416520447747548 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.7142857142857143, "acc_stderr": 0.023266512213730564, "acc_norm": 0.7142857142857143, "acc_norm_stderr": 0.023266512213730564 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5476190476190477, "acc_stderr": 0.044518079590553275, "acc_norm": 0.5476190476190477, "acc_norm_stderr": 0.044518079590553275 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.61, "acc_stderr": 0.04902071300001975, "acc_norm": 0.61, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.9096774193548387, "acc_stderr": 0.016306570644488323, "acc_norm": 0.9096774193548387, "acc_norm_stderr": 0.016306570644488323 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.6699507389162561, "acc_stderr": 0.033085304262282574, "acc_norm": 0.6699507389162561, "acc_norm_stderr": 0.033085304262282574 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.81, "acc_stderr": 0.03942772444036625, "acc_norm": 0.81, "acc_norm_stderr": 0.03942772444036625 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8606060606060606, "acc_stderr": 0.027045948825865394, "acc_norm": 0.8606060606060606, "acc_norm_stderr": 0.027045948825865394 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.9343434343434344, "acc_stderr": 0.017646526677233335, "acc_norm": 0.9343434343434344, "acc_norm_stderr": 0.017646526677233335 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9740932642487047, "acc_stderr": 0.01146452335695318, "acc_norm": 0.9740932642487047, "acc_norm_stderr": 0.01146452335695318 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.823076923076923, "acc_stderr": 0.019348070174396985, "acc_norm": 0.823076923076923, "acc_norm_stderr": 0.019348070174396985 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.43703703703703706, "acc_stderr": 0.030242862397654, "acc_norm": 0.43703703703703706, "acc_norm_stderr": 0.030242862397654 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.8529411764705882, "acc_stderr": 0
