open-llm-leaderboard-old/details_s3nh__nsfw-noromaid-mistral-instruct
收藏数据集概述
该数据集是在对模型 s3nh/nsfw-noromaid-mistral-instruct 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。
- 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 2024-01-08T10:52:46.659107 运行的最新结果：
json { "all": { "acc": 0.4636397253806667, "acc_stderr": 0.03433097238406634, "acc_norm": 0.4705183598294859, "acc_norm_stderr": 0.03515170311421716, "mc1": 0.2252141982864137, "mc1_stderr": 0.014623240768023495, "mc2": 0.3349241921724532, "mc2_stderr": 0.013441943397542705 }, "harness|arc:challenge|25": { "acc": 0.4786689419795222, "acc_stderr": 0.014598087973127106, "acc_norm": 0.5179180887372014, "acc_norm_stderr": 0.014602005585490976 }, "harness|hellaswag|10": { "acc": 0.5367456681935869, "acc_stderr": 0.0049762883216818215, "acc_norm": 0.7539334793865764, "acc_norm_stderr": 0.004298374936365623 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.28, "acc_stderr": 0.045126085985421296, "acc_norm": 0.28, "acc_norm_stderr": 0.045126085985421296 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.45185185185185184, "acc_stderr": 0.04299268905480864, "acc_norm": 0.45185185185185184, "acc_norm_stderr": 0.04299268905480864 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5592105263157895, "acc_stderr": 0.04040311062490437, "acc_norm": 0.5592105263157895, "acc_norm_stderr": 0.04040311062490437 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.49, "acc_stderr": 0.05024183937956911, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956911 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5245283018867924, "acc_stderr": 0.030735822206205615, "acc_norm": 0.5245283018867924, "acc_norm_stderr": 0.030735822206205615 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5555555555555556, "acc_stderr": 0.041553199555931467, "acc_norm": 0.5555555555555556, "acc_norm_stderr": 0.041553199555931467 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.4624277456647399, "acc_stderr": 0.0380168510452446, "acc_norm": 0.4624277456647399, "acc_norm_stderr": 0.0380168510452446 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.19607843137254902, "acc_stderr": 0.039505818611799616, "acc_norm": 0.19607843137254902, "acc_norm_stderr": 0.039505818611799616 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.61, "acc_stderr": 0.04902071300001975, "acc_norm": 0.61, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.4425531914893617, "acc_stderr": 0.032469569197899575, "acc_norm": 0.4425531914893617, "acc_norm_stderr": 0.032469569197899575 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.3157894736842105, "acc_stderr": 0.043727482902780064, "acc_norm": 0.3157894736842105, "acc_norm_stderr": 0.043727482902780064 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.46206896551724136, "acc_stderr": 0.04154659671707548, "acc_norm": 0.46206896551724136, "acc_norm_stderr": 0.04154659671707548 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3412698412698413, "acc_stderr": 0.024419234966819074, "acc_norm": 0.3412698412698413, "acc_norm_stderr": 0.024419234966819074 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.23809523809523808, "acc_stderr": 0.03809523809523811, "acc_norm": 0.23809523809523808, "acc_norm_stderr": 0.03809523809523811 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.37, "acc_stderr": 0.048523658709391, "acc_norm": 0.37, "acc_norm_stderr": 0.048523658709391 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.45806451612903226, "acc_stderr": 0.028343787250540618, "acc_norm": 0.45806451612903226, "acc_norm_stderr": 0.028343787250540618 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.39901477832512317, "acc_stderr": 0.03445487686264716, "acc_norm": 0.39901477832512317, "acc_norm_stderr": 0.03445487686264716 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.41, "acc_stderr": 0.04943110704237102, "acc_norm": 0.41, "acc_norm_stderr": 0.04943110704237102 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.2787878787878788, "acc_stderr": 0.03501438706296781, "acc_norm": 0.2787878787878788, "acc_norm_stderr": 0.03501438706296781 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.6060606060606061, "acc_stderr": 0.03481285338232963, "acc_norm": 0.6060606060606061, "acc_norm_stderr": 0.03481285338232963 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.6683937823834197, "acc_stderr": 0.03397636541089118, "acc_norm": 0.6683937823834197, "acc_norm_stderr": 0.03397636541089118 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.4641025641025641, "acc_stderr": 0.025285585990017848, "acc_norm": 0.4641025641025641, "acc_norm_stderr": 0.025285585990017848 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2851851851851852, "acc_stderr": 0.027528599210340492, "acc_norm": 0.2851851851851852, "acc_norm_stderr": 0.027528599210340492 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.46218487394957986, "acc_stderr": 0.03
