open-llm-leaderboard-old/details_cyberagent__calm2-7b-chat-dpo-experimental

该数据集是在评估模型cyberagent/calm2-7b-chat-dpo-experimental时自动创建的，评估在Open LLM Leaderboard上进行。数据集由63个配置组成，每个配置对应一个评估任务。数据集从1次运行中创建，每次运行可以在每个配置中找到，运行的时间戳作为分割名称。train分割始终指向最新结果。此外，一个名为results的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。

原始信息汇总

数据集概述

数据集简介

该数据集是在评估模型 cyberagent/calm2-7b-chat-dpo-experimental 在 Open LLM Leaderboard 上的运行过程中自动创建的。

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。
• 数据集来自 1 次运行，每个运行在每个配置中都有一个特定的分割，分割名称使用运行的时间戳。
• "train" 分割始终指向最新的结果。
• 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_cyberagent__calm2-7b-chat-dpo-experimental", "harness_winogrande_5", split="train")

最新结果

这些是最新结果，来自 2024-02-01T21:56:29.984219 的运行： python { "all": { "acc": 0.39856874794500985, "acc_stderr": 0.03441229732329181, "acc_norm": 0.4033694107520943, "acc_norm_stderr": 0.03524214558743911, "mc1": 0.2741738066095471, "mc1_stderr": 0.015616518497219373, "mc2": 0.43126020642044494, "mc2_stderr": 0.01476646245339252 }, "harness|arc:challenge|25": { "acc": 0.3856655290102389, "acc_stderr": 0.014224250973257172, "acc_norm": 0.4104095563139932, "acc_norm_stderr": 0.014374922192642662 }, "harness|hellaswag|10": { "acc": 0.5165305715992831, "acc_stderr": 0.0049870536525402675, "acc_norm": 0.6899024098785103, "acc_norm_stderr": 0.004615880352799746 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.4666666666666667, "acc_stderr": 0.043097329010363554, "acc_norm": 0.4666666666666667, "acc_norm_stderr": 0.043097329010363554 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.4342105263157895, "acc_stderr": 0.04033565667848319, "acc_norm": 0.4342105263157895, "acc_norm_stderr": 0.04033565667848319 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.4075471698113208, "acc_stderr": 0.030242233800854494, "acc_norm": 0.4075471698113208, "acc_norm_stderr": 0.030242233800854494 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.3819444444444444, "acc_stderr": 0.040629907841466674, "acc_norm": 0.3819444444444444, "acc_norm_stderr": 0.040629907841466674 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.28, "acc_stderr": 0.04512608598542124, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542124 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.39, "acc_stderr": 0.04902071300001974, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001974 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.36416184971098264, "acc_stderr": 0.036690724774169084, "acc_norm": 0.36416184971098264, "acc_norm_stderr": 0.036690724774169084 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.2647058823529412, "acc_stderr": 0.04389869956808779, "acc_norm": 0.2647058823529412, "acc_norm_stderr": 0.04389869956808779 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.47, "acc_stderr": 0.050161355804659205, "acc_norm": 0.47, "acc_norm_stderr": 0.050161355804659205 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.3404255319148936, "acc_stderr": 0.030976692998534436, "acc_norm": 0.3404255319148936, "acc_norm_stderr": 0.030976692998534436 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2719298245614035, "acc_stderr": 0.04185774424022056, "acc_norm": 0.2719298245614035, "acc_norm_stderr": 0.04185774424022056 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.3586206896551724, "acc_stderr": 0.039966295748767186, "acc_norm": 0.3586206896551724, "acc_norm_stderr": 0.039966295748767186 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2698412698412698, "acc_stderr": 0.022860838309232072, "acc_norm": 0.2698412698412698, "acc_norm_stderr": 0.022860838309232072 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.2698412698412698, "acc_stderr": 0.03970158273235173, "acc_norm": 0.2698412698412698, "acc_norm_stderr": 0.03970158273235173 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.38, "acc_stderr": 0.04878317312145632, "acc_norm": 0.38, "acc_norm_stderr": 0.04878317312145632 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.3870967741935484, "acc_stderr": 0.02770935967503249, "acc_norm": 0.3870967741935484, "acc_norm_stderr": 0.02770935967503249 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.3251231527093596, "acc_stderr": 0.032957975663112704, "acc_norm": 0.3251231527093596, "acc_norm_stderr": 0.032957975663112704 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.48484848484848486, "acc_stderr": 0.03902551007374448, "acc_norm": 0.48484848484848486, "acc_norm_stderr": 0.03902551007374448 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.48484848484848486, "acc_stderr": 0.03560716516531061, "acc_norm": 0.48484848484848486, "acc_norm_stderr": 0.03560716516531061 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.5129533678756477, "acc_stderr": 0.036072280610477486, "acc_norm": 0.5129533678756477, "acc_norm_stderr": 0.036072280610477486 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.33076923076923076, "acc_stderr": 0.02385479568097114, "acc_norm": 0.33076923076923076, "acc_norm_stderr": 0.02385479568097114 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.25555555555555554, "acc_stderr": 0.026593939101844082, "acc_norm": 0.25555555555555554, "acc_norm_stderr": 0.026593939101844082 }, "harness|hendrycksTest-high_school_microeconomics|