open-llm-leaderboard-old/details_jsfs11__MixtureofMerges-MoE-2x7b-v6
收藏数据集概述
数据集简介
该数据集是在评估模型 jsfs11/MixtureofMerges-MoE-2x7b-v6 在 Open LLM Leaderboard 上的运行过程中自动创建的。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,每个运行的详细信息可以在每个配置中找到,并以运行的时间戳命名的特定分片存储。"train" 分片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。
最新结果
以下是 2024-03-03T01:36:30.504168 运行的最新结果:
python { "all": { "acc": 0.6517586409868475, "acc_stderr": 0.032053515470024045, "acc_norm": 0.6509408256393778, "acc_norm_stderr": 0.03272560737103458, "mc1": 0.6401468788249693, "mc1_stderr": 0.016801860466677157, "mc2": 0.7857876240805535, "mc2_stderr": 0.013571252828521445 }, "harness|arc:challenge|25": { "acc": 0.7141638225255973, "acc_stderr": 0.013203196088537372, "acc_norm": 0.7337883959044369, "acc_norm_stderr": 0.012915774781523198 }, "harness|hellaswag|10": { "acc": 0.7215694084843657, "acc_stderr": 0.00447310453702692, "acc_norm": 0.8915554670384386, "acc_norm_stderr": 0.0031030554162430556 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6370370370370371, "acc_stderr": 0.041539484047423976, "acc_norm": 0.6370370370370371, "acc_norm_stderr": 0.041539484047423976 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7105263157894737, "acc_stderr": 0.03690677986137283, "acc_norm": 0.7105263157894737, "acc_norm_stderr": 0.03690677986137283 }, "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": 0.6981132075471698, "acc_stderr": 0.02825420034443866, "acc_norm": 0.6981132075471698, "acc_norm_stderr": 0.02825420034443866 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7986111111111112, "acc_stderr": 0.033536474697138406, "acc_norm": 0.7986111111111112, "acc_norm_stderr": 0.033536474697138406 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.49, "acc_stderr": 0.05024183937956912, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.56, "acc_stderr": 0.04988876515698589, "acc_norm": 0.56, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.653179190751445, "acc_stderr": 0.036291466701596636, "acc_norm": 0.653179190751445, "acc_norm_stderr": 0.036291466701596636 }, "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": 0.5659574468085107, "acc_stderr": 0.03240038086792747, "acc_norm": 0.5659574468085107, "acc_norm_stderr": 0.03240038086792747 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.49122807017543857, "acc_stderr": 0.04702880432049615, "acc_norm": 0.49122807017543857, "acc_norm_stderr": 0.04702880432049615 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5517241379310345, "acc_stderr": 0.04144311810878152, "acc_norm": 0.5517241379310345, "acc_norm_stderr": 0.04144311810878152 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.41005291005291006, "acc_stderr": 0.02533120243894443, "acc_norm": 0.41005291005291006, "acc_norm_stderr": 0.02533120243894443 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.47619047619047616, "acc_stderr": 0.04467062628403273, "acc_norm": 0.47619047619047616, "acc_norm_stderr": 0.04467062628403273 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7838709677419354, "acc_stderr": 0.02341529343356853, "acc_norm": 0.7838709677419354, "acc_norm_stderr": 0.02341529343356853 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5073891625615764, "acc_stderr": 0.035176035403610105, "acc_norm": 0.5073891625615764, "acc_norm_stderr": 0.035176035403610105 }, "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": 0.7696969696969697, "acc_stderr": 0.0328766675860349, "acc_norm": 0.7696969696969697, "acc_norm_stderr": 0.0328766675860349 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.797979797979798, "acc_stderr": 0.02860620428922987, "acc_norm": 0.797979797979798, "acc_norm_stderr": 0.02860620428922987 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9015544041450777, "acc_stderr": 0.02150024957603346, "acc_norm": 0.9015544041450777, "acc_norm_stderr": 0.02150024957603346 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6512820512820513, "acc_stderr": 0.02416278028401772, "acc_norm": 0.6512820512820513, "acc_norm_stderr": 0.02416278028401772 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3296296296296296, "acc_stderr": 0.028661201116524575, "acc_norm": 0.3296296296296296, "acc_norm_stderr": 0.028661201116524575 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.6764705882352942, "acc_stderr": 0.0



