open-llm-leaderboard-old/details_BFauber__opt125m_10e5_20ep
收藏数据集概述
数据集简介
该数据集是在模型BFauber/opt125m_10e5_20ep在Open LLM Leaderboard上的评估运行期间自动创建的。
数据集结构
- 配置数量：63个配置，每个配置对应一个评估任务。
- 运行次数：数据集由1次运行创建。每个运行在每个配置中作为一个特定的分割存在，分割名称使用运行的timestamp。
- 分割：每个配置包含多个分割，其中“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_BFauber__opt125m_10e5_20ep", "harness_winogrande_5", split="train")
最新结果
这些是最新的结果，来自2024-02-02T19:31:32.659309的运行： python { "all": { "acc": 0.23530235034095837, "acc_stderr": 0.029883235955403636, "acc_norm": 0.23550247007959293, "acc_norm_stderr": 0.030668377840836165, "mc1": 0.24112607099143207, "mc1_stderr": 0.014974827279752332, "mc2": 0.4648926603532375, "mc2_stderr": 0.01559555646787533 }, "harness|arc:challenge|25": { "acc": 0.22610921501706485, "acc_stderr": 0.012224202097063269, "acc_norm": 0.25426621160409557, "acc_norm_stderr": 0.012724999945157734 }, "harness|hellaswag|10": { "acc": 0.2847042421828321, "acc_stderr": 0.0045035118550500325, "acc_norm": 0.3084047002589126, "acc_norm_stderr": 0.004608907872957696 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.24, "acc_stderr": 0.04292346959909283, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909283 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.23703703703703705, "acc_stderr": 0.03673731683969506, "acc_norm": 0.23703703703703705, "acc_norm_stderr": 0.03673731683969506 }, "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": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.21132075471698114, "acc_stderr": 0.025125766484827845, "acc_norm": 0.21132075471698114, "acc_norm_stderr": 0.025125766484827845 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2361111111111111, "acc_stderr": 0.03551446610810826, "acc_norm": 0.2361111111111111, "acc_norm_stderr": 0.03551446610810826 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.2, "acc_stderr": 0.04020151261036845, "acc_norm": 0.2, "acc_norm_stderr": 0.04020151261036845 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.16, "acc_stderr": 0.0368452949177471, "acc_norm": 0.16, "acc_norm_stderr": 0.0368452949177471 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.21, "acc_stderr": 0.040936018074033256, "acc_norm": 0.21, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.20809248554913296, "acc_stderr": 0.030952890217749874, "acc_norm": 0.20809248554913296, "acc_norm_stderr": 0.030952890217749874 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.21568627450980393, "acc_stderr": 0.04092563958237654, "acc_norm": 0.21568627450980393, "acc_norm_stderr": 0.04092563958237654 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.25957446808510637, "acc_stderr": 0.02865917937429232, "acc_norm": 0.25957446808510637, "acc_norm_stderr": 0.02865917937429232 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.24561403508771928, "acc_stderr": 0.0404933929774814, "acc_norm": 0.24561403508771928, "acc_norm_stderr": 0.0404933929774814 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2620689655172414, "acc_stderr": 0.036646663372252565, "acc_norm": 0.2620689655172414, "acc_norm_stderr": 0.036646663372252565 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.25132275132275134, "acc_stderr": 0.022340482339643895, "acc_norm": 0.25132275132275134, "acc_norm_stderr": 0.022340482339643895 }, "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": 0.27419354838709675, "acc_stderr": 0.025378139970885193, "acc_norm": 0.27419354838709675, "acc_norm_stderr": 0.025378139970885193 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.15270935960591134, "acc_stderr": 0.02530890453938063, "acc_norm": 0.15270935960591134, "acc_norm_stderr": 0.02530890453938063 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.16, "acc_stderr": 0.0368452949177471, "acc_norm": 0.16, "acc_norm_stderr": 0.0368452949177471 }, "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": 0.17676767676767677, "acc_stderr": 0.027178752639044915, "acc_norm": 0.17676767676767677, "acc_norm_stderr": 0.027178752639044915 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.19689119170984457, "acc_stderr": 0.028697873971860657, "acc_norm": 0.19689119170984457, "acc_norm_stderr": 0.028697873971860657 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.2205128205128205, "acc_stderr": 0.021020672680827912, "acc_norm": 0.2205128205128205, "acc_norm_stderr": 0.021020672680827912 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.21481481481481482, "acc_stderr": 0.02504044387700068, "acc_norm": 0.21481481481481482, "acc_norm_stderr": 0.025040443
