open-llm-leaderboard-old/details_ABX-AI__Silver-Sun-11B
收藏数据集概述
数据集简介
该数据集是在对模型ABX-AI/Silver-Sun-11B进行评估运行期间自动创建的，用于Open LLM Leaderboard。
数据集组成
数据集包含63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，每次运行的详细信息可以在每个配置中找到，以运行的时间戳命名的特定分割形式存储。"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，用于计算并在Open LLM Leaderboard上显示聚合指标。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_ABX-AI__Silver-Sun-11B", "harness_winogrande_5", split="train")
最新结果
这些是最新的结果，来自2024-04-09T11:23:48.663620的运行：
python { "all": { "acc": 0.6613299971122604, "acc_stderr": 0.03117186211934933, "acc_norm": 0.6730584240663938, "acc_norm_stderr": 0.03199188346673098, "mc1": 0.47613219094247244, "mc1_stderr": 0.017483547156961578, "mc2": 0.618855922705881, "mc2_stderr": 0.015586954390037554 }, "harness|arc:challenge|25": { "acc": 0.6680887372013652, "acc_stderr": 0.013760988200880533, "acc_norm": 0.6979522184300341, "acc_norm_stderr": 0.013417519144716413 }, "harness|hellaswag|10": { "acc": 0.692989444333798, "acc_stderr": 0.004603111343213067, "acc_norm": 0.8791077474606652, "acc_norm_stderr": 0.0032533576201717973 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6074074074074074, "acc_stderr": 0.04218506215368879, "acc_norm": 0.6074074074074074, "acc_norm_stderr": 0.04218506215368879 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7697368421052632, "acc_stderr": 0.03426059424403165, "acc_norm": 0.7697368421052632, "acc_norm_stderr": 0.03426059424403165 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.73, "acc_stderr": 0.044619604333847394, "acc_norm": 0.73, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7018867924528301, "acc_stderr": 0.02815283794249386, "acc_norm": 0.7018867924528301, "acc_norm_stderr": 0.02815283794249386 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7777777777777778, "acc_stderr": 0.034765901043041336, "acc_norm": 0.7777777777777778, "acc_norm_stderr": 0.034765901043041336 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.4, "acc_stderr": 0.04923659639173309, "acc_norm": 0.4, "acc_norm_stderr": 0.04923659639173309 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.51, "acc_stderr": 0.05024183937956913, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956913 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6820809248554913, "acc_stderr": 0.0355068398916558, "acc_norm": 0.6820809248554913, "acc_norm_stderr": 0.0355068398916558 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.39215686274509803, "acc_stderr": 0.04858083574266345, "acc_norm": 0.39215686274509803, "acc_norm_stderr": 0.04858083574266345 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.79, "acc_stderr": 0.040936018074033256, "acc_norm": 0.79, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.6, "acc_stderr": 0.03202563076101735, "acc_norm": 0.6, "acc_norm_stderr": 0.03202563076101735 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5350877192982456, "acc_stderr": 0.046920083813689104, "acc_norm": 0.5350877192982456, "acc_norm_stderr": 0.046920083813689104 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6206896551724138, "acc_stderr": 0.04043461861916747, "acc_norm": 0.6206896551724138, "acc_norm_stderr": 0.04043461861916747 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.48148148148148145, "acc_stderr": 0.025733641991838987, "acc_norm": 0.48148148148148145, "acc_norm_stderr": 0.025733641991838987 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4603174603174603, "acc_stderr": 0.04458029125470973, "acc_norm": 0.4603174603174603, "acc_norm_stderr": 0.04458029125470973 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8451612903225807, "acc_stderr": 0.020579287326583227, "acc_norm": 0.8451612903225807, "acc_norm_stderr": 0.020579287326583227 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4975369458128079, "acc_stderr": 0.03517945038691063, "acc_norm": 0.4975369458128079, "acc_norm_stderr": 0.03517945038691063 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.71, "acc_stderr": 0.045604802157206845, "acc_norm": 0.71, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.806060606060606, "acc_stderr": 0.03087414513656208, "acc_norm": 0.806060606060606, "acc_norm_stderr": 0.03087414513656208 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8838383838383839, "acc_stderr": 0.02282888177524938, "acc_norm": 0.8838383838383839, "acc_norm_stderr": 0.02282888177524938 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9119170984455959, "acc_stderr": 0.02045374660160103, "acc_norm": 0.9119170984455959, "acc_norm_stderr": 0.02045374660160103 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6717948717948717, "acc_stderr": 0.023807633198657262, "acc_norm": 0.6717948717948717, "acc_norm_stderr": 0.023807633198657262 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.34814814814814815, "acc_stderr": 0.029045600290616255, "acc_norm": 0.34814814814814815, "acc_norm_stderr": 0.029045600290616255 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.7100840336134454, "acc_stderr": 0.029472485833136098, "acc_norm
