open-llm-leaderboard-old/details_DrNicefellow__Mixtral-6x7B-Instruct-v0.1-bfloat16-Trimmed024567
收藏数据集概述
数据集名称
Evaluation run of DrNicefellow/Mixtral-6x7B-Instruct-v0.1-bfloat16-Trimmed024567
数据集描述
该数据集是在模型DrNicefellow/Mixtral-6x7B-Instruct-v0.1-bfloat16-Trimmed024567在Open LLM Leaderboard上的评估运行期间自动创建的。
数据集组成
数据集由63个配置组成，每个配置对应一个评估任务。数据集是从1次运行中创建的。每次运行都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_DrNicefellow__Mixtral-6x7B-Instruct-v0.1-bfloat16-Trimmed024567", "harness_winogrande_5", split="train")
最新结果
以下是2024-04-07T05:29:51.567355运行的最新结果：
python { "all": { "acc": 0.5248682126170723, "acc_stderr": 0.034301395522201024, "acc_norm": 0.5338495466936881, "acc_norm_stderr": 0.03512077124311037, "mc1": 0.3659730722154223, "mc1_stderr": 0.016862941684088376, "mc2": 0.5155182013224342, "mc2_stderr": 0.015280738776625028 }, "harness|arc:challenge|25": { "acc": 0.5110921501706485, "acc_stderr": 0.014607794914013048, "acc_norm": 0.5665529010238908, "acc_norm_stderr": 0.014481376224558902 }, "harness|hellaswag|10": { "acc": 0.5912168890659231, "acc_stderr": 0.004906043613013399, "acc_norm": 0.7884883489344752, "acc_norm_stderr": 0.004075456897370669 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.32, "acc_stderr": 0.04688261722621505, "acc_norm": 0.32, "acc_norm_stderr": 0.04688261722621505 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.4962962962962963, "acc_stderr": 0.04319223625811331, "acc_norm": 0.4962962962962963, "acc_norm_stderr": 0.04319223625811331 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5394736842105263, "acc_stderr": 0.04056242252249033, "acc_norm": 0.5394736842105263, "acc_norm_stderr": 0.04056242252249033 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.56, "acc_stderr": 0.04988876515698589, "acc_norm": 0.56, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5547169811320755, "acc_stderr": 0.030588052974270665, "acc_norm": 0.5547169811320755, "acc_norm_stderr": 0.030588052974270665 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5208333333333334, "acc_stderr": 0.04177578950739993, "acc_norm": 0.5208333333333334, "acc_norm_stderr": 0.04177578950739993 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.37, "acc_stderr": 0.048523658709391, "acc_norm": 0.37, "acc_norm_stderr": 0.048523658709391 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.43, "acc_stderr": 0.04975698519562428, "acc_norm": 0.43, "acc_norm_stderr": 0.04975698519562428 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.38, "acc_stderr": 0.04878317312145632, "acc_norm": 0.38, "acc_norm_stderr": 0.04878317312145632 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.45664739884393063, "acc_stderr": 0.03798106566014498, "acc_norm": 0.45664739884393063, "acc_norm_stderr": 0.03798106566014498 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.21568627450980393, "acc_stderr": 0.04092563958237657, "acc_norm": 0.21568627450980393, "acc_norm_stderr": 0.04092563958237657 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.69, "acc_stderr": 0.04648231987117316, "acc_norm": 0.69, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.48936170212765956, "acc_stderr": 0.03267862331014063, "acc_norm": 0.48936170212765956, "acc_norm_stderr": 0.03267862331014063 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.3684210526315789, "acc_stderr": 0.04537815354939392, "acc_norm": 0.3684210526315789, "acc_norm_stderr": 0.04537815354939392 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.503448275862069, "acc_stderr": 0.04166567577101579, "acc_norm": 0.503448275862069, "acc_norm_stderr": 0.04166567577101579 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.36772486772486773, "acc_stderr": 0.024833839825562427, "acc_norm": 0.36772486772486773, "acc_norm_stderr": 0.024833839825562427 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3412698412698413, "acc_stderr": 0.04240799327574924, "acc_norm": 0.3412698412698413, "acc_norm_stderr": 0.04240799327574924 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.35, "acc_stderr": 0.047937248544110196, "acc_norm": 0.35, "acc_norm_stderr": 0.047937248544110196 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6096774193548387, "acc_stderr": 0.027751256636969576, "acc_norm": 0.6096774193548387, "acc_norm_stderr": 0.027751256636969576 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.3891625615763547, "acc_stderr": 0.034304624161038716, "acc_norm": 0.3891625615763547, "acc_norm_stderr": 0.034304624161038716 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.59, "acc_stderr": 0.04943110704237102, "acc_norm": 0.59, "acc_norm_stderr": 0.04943110704237102 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6848484848484848, "acc_stderr": 0.0362773057502241, "acc_norm": 0.6848484848484848, "acc_norm_stderr": 0.0362773057502241 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.702020202020202, "acc_stderr": 0.03258630383836556, "acc_norm": 0.702020202020202, "acc_norm_stderr": 0.03258630383836556 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7616580310880829, "acc_stderr": 0.030748905363909895, "acc_norm": 0.7616580310880829, "acc_norm_stderr": 0.030748905363909895 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.4948717948717949, "acc_stderr": 0.025349672906838653, "acc_norm": 0.4948717948717949, "acc_norm_stderr": 0.0253496729068386
