open-llm-leaderboard-old/details_psyche__kollama2-7b-v3

该数据集是在模型 psyche/kollama2-7b-v3 在 Open LLM Leaderboard 上的评估过程中自动生成的。数据集包含 61 个配置，每个配置对应一个被评估的任务。它包含一次运行的结果，每次运行在每个配置中表示为特定的分割，分割名称由运行的时间戳命名。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。文件还提供了一个 Python 代码片段来加载数据集详细信息，并列出了特定运行的最新结果。

原始信息汇总

数据集概述

数据集摘要

该数据集是在模型psyche/kollama2-7b-v3在Open LLM Leaderboard上的评估运行期间自动创建的。

数据集组成

• 该数据集包含61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，每次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。
• 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2023-08-28T08:31:05.396495的最新结果：

python { "all": { "acc": 0.4080126650463043, "acc_stderr": 0.03490803118091981, "acc_norm": 0.41212249060720096, "acc_norm_stderr": 0.034895302556044526, "mc1": 0.2937576499388005, "mc1_stderr": 0.015945068581236618, "mc2": 0.42921423081004945, "mc2_stderr": 0.014206971382449723 }, "harness|arc:challenge|25": { "acc": 0.4539249146757679, "acc_stderr": 0.01454922110517187, "acc_norm": 0.4974402730375427, "acc_norm_stderr": 0.014611199329843784 }, "harness|hellaswag|10": { "acc": 0.5855407289384584, "acc_stderr": 0.004916216503770336, "acc_norm": 0.7845050786695877, "acc_norm_stderr": 0.004103249411456488 }, "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": 0.3925925925925926, "acc_stderr": 0.04218506215368879, "acc_norm": 0.3925925925925926, "acc_norm_stderr": 0.04218506215368879 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.35526315789473684, "acc_stderr": 0.038947344870133176, "acc_norm": 0.35526315789473684, "acc_norm_stderr": 0.038947344870133176 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.51, "acc_stderr": 0.05024183937956912, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.37735849056603776, "acc_stderr": 0.029832808114796005, "acc_norm": 0.37735849056603776, "acc_norm_stderr": 0.029832808114796005 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.4097222222222222, "acc_stderr": 0.04112490974670787, "acc_norm": 0.4097222222222222, "acc_norm_stderr": 0.04112490974670787 }, "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": 0.39, "acc_stderr": 0.04902071300001975, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.3236994219653179, "acc_stderr": 0.0356760379963917, "acc_norm": 0.3236994219653179, "acc_norm_stderr": 0.0356760379963917 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.19607843137254902, "acc_stderr": 0.03950581861179963, "acc_norm": 0.19607843137254902, "acc_norm_stderr": 0.03950581861179963 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.54, "acc_stderr": 0.05009082659620332, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.4127659574468085, "acc_stderr": 0.03218471141400351, "acc_norm": 0.4127659574468085, "acc_norm_stderr": 0.03218471141400351 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.30701754385964913, "acc_stderr": 0.04339138322579861, "acc_norm": 0.30701754385964913, "acc_norm_stderr": 0.04339138322579861 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.38620689655172413, "acc_stderr": 0.04057324734419034, "acc_norm": 0.38620689655172413, "acc_norm_stderr": 0.04057324734419034 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.23544973544973544, "acc_stderr": 0.021851509822031722, "acc_norm": 0.23544973544973544, "acc_norm_stderr": 0.021851509822031722 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3253968253968254, "acc_stderr": 0.04190596438871137, "acc_norm": 0.3253968253968254, "acc_norm_stderr": 0.04190596438871137 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.28, "acc_stderr": 0.04512608598542128, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542128 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.3935483870967742, "acc_stderr": 0.027791878753132274, "acc_norm": 0.3935483870967742, "acc_norm_stderr": 0.027791878753132274 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.3054187192118227, "acc_stderr": 0.03240661565868408, "acc_norm": 0.3054187192118227, "acc_norm_stderr": 0.03240661565868408 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.4909090909090909, "acc_stderr": 0.0390369864774844, "acc_norm": 0.4909090909090909, "acc_norm_stderr": 0.0390369864774844 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.41919191919191917, "acc_stderr": 0.035155207286704175, "acc_norm": 0.41919191919191917, "acc_norm_stderr": 0.035155207286704175 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.5958549222797928, "acc_stderr": 0.0354150857888402, "acc_norm": 0.5958549222797928, "acc_norm_stderr": 0.0354150857888402 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.3487179487179487, "acc_stderr": 0.02416278028401772, "acc_norm": 0.3487179487179487, "acc_norm_stderr": 0.02416278028401772 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.24444444444444444, "acc_stderr": 0.02620276653465215, "acc_norm": 0.24444444444444444, "acc_norm_stderr": 0.02620276653465215 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.3445378151260504