open-llm-leaderboard-old/details_NousResearch__Nous-Hermes-Llama2-70b
收藏数据集概述
数据集摘要
该数据集是在对模型 NousResearch/Nous-Hermes-Llama2-70b 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。
数据集组成
- 数据集由 60 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 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_NousResearch__Nous-Hermes-Llama2-70b", "harness_truthfulqa_mc_0", split="train")
最新结果
这些是最新结果的示例： python { "all": { "acc": 0.6957673179292897, "acc_stderr": 0.030886230677725023, "acc_norm": 0.6997447643290794, "acc_norm_stderr": 0.030857325329783844, "mc1": 0.39167686658506734, "mc1_stderr": 0.017087795881769632, "mc2": 0.5504358942461541, "mc2_stderr": 0.01494092300772985 }, "harness|arc:challenge|25": { "acc": 0.6313993174061433, "acc_stderr": 0.014097810678042196, "acc_norm": 0.6757679180887372, "acc_norm_stderr": 0.013678810399518826 }, "harness|hellaswag|10": { "acc": 0.6777534355706034, "acc_stderr": 0.004663817291468729, "acc_norm": 0.8680541724756025, "acc_norm_stderr": 0.0033774020414626227 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.33, "acc_stderr": 0.04725815626252606, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252606 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6370370370370371, "acc_stderr": 0.041539484047424, "acc_norm": 0.6370370370370371, "acc_norm_stderr": 0.041539484047424 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.8026315789473685, "acc_stderr": 0.03238981601699397, "acc_norm": 0.8026315789473685, "acc_norm_stderr": 0.03238981601699397 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.75, "acc_stderr": 0.04351941398892446, "acc_norm": 0.75, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.720754716981132, "acc_stderr": 0.027611163402399715, "acc_norm": 0.720754716981132, "acc_norm_stderr": 0.027611163402399715 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8402777777777778, "acc_stderr": 0.030635578972093274, "acc_norm": 0.8402777777777778, "acc_norm_stderr": 0.030635578972093274 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.47, "acc_stderr": 0.05016135580465919, "acc_norm": 0.47, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.53, "acc_stderr": 0.05016135580465919, "acc_norm": 0.53, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6705202312138728, "acc_stderr": 0.03583901754736412, "acc_norm": 0.6705202312138728, "acc_norm_stderr": 0.03583901754736412 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3627450980392157, "acc_stderr": 0.04784060704105653, "acc_norm": 0.3627450980392157, "acc_norm_stderr": 0.04784060704105653 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.77, "acc_stderr": 0.04229525846816506, "acc_norm": 0.77, "acc_norm_stderr": 0.04229525846816506 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.7148936170212766, "acc_stderr": 0.029513196625539355, "acc_norm": 0.7148936170212766, "acc_norm_stderr": 0.029513196625539355 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4298245614035088, "acc_stderr": 0.046570472605949625, "acc_norm": 0.4298245614035088, "acc_norm_stderr": 0.046570472605949625 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6344827586206897, "acc_stderr": 0.040131241954243856, "acc_norm": 0.6344827586206897, "acc_norm_stderr": 0.040131241954243856 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.43915343915343913, "acc_stderr": 0.02555992055053101, "acc_norm": 0.43915343915343913, "acc_norm_stderr": 0.02555992055053101 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.47619047619047616, "acc_stderr": 0.04467062628403273, "acc_norm": 0.47619047619047616, "acc_norm_stderr": 0.04467062628403273 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.53, "acc_stderr": 0.050161355804659205, "acc_norm": 0.53, "acc_norm_stderr": 0.050161355804659205 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8032258064516129, "acc_stderr": 0.022616409420742015, "acc_norm": 0.8032258064516129, "acc_norm_stderr": 0.022616409420742015 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5467980295566502, "acc_stderr": 0.03502544650845872, "acc_norm": 0.5467980295566502, "acc_norm_stderr": 0.03502544650845872 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.74, "acc_stderr": 0.044084400227680794, "acc_norm": 0.74, "acc_norm_stderr": 0.044084400227680794 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8484848484848485, "acc_stderr": 0.02799807379878168, "acc_norm": 0.8484848484848485, "acc_norm_stderr": 0.02799807379878168 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8737373737373737, "acc_stderr": 0.02366435940288022, "acc_norm": 0.8737373737373737, "acc_norm_stderr": 0.02366435940288022 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9378238341968912, "acc_stderr": 0.017426974154240528, "acc_norm": 0.9378238341968912, "acc_norm_stderr": 0.017426974154240528 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.7025641025641025, "acc_stderr": 0.023177408131465942, "acc_norm": 0.7025641025641025, "acc_norm_stderr": 0.023177408131465942 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3111111111111111, "acc_stderr": 0.02822644674968352, "acc_norm": 0.3111111111111111, "acc_norm_stderr": 0.02822644674968352 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.7605042016806722, "acc_stderr": 0.027
