open-llm-leaderboard-old/details_INSAIT-Institute__BgGPT-7B-Instruct-v0.1
收藏数据集概述
该数据集是在评估模型INSAIT-Institute/BgGPT-7B-Instruct-v0.1的过程中自动创建的，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。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_INSAIT-Institute__BgGPT-7B-Instruct-v0.1", "harness_winogrande_5", split="train")
最新结果
以下是2024-02-18T17:19:30.595727运行的最新结果：
python { "all": { "acc": 0.5988578948188136, "acc_stderr": 0.03314721162029684, "acc_norm": 0.6004390874684334, "acc_norm_stderr": 0.03381955360558513, "mc1": 0.37576499388004897, "mc1_stderr": 0.016954584060214297, "mc2": 0.5368100172224678, "mc2_stderr": 0.015301815507488754 }, "harness|arc:challenge|25": { "acc": 0.568259385665529, "acc_stderr": 0.014474591427196202, "acc_norm": 0.6023890784982935, "acc_norm_stderr": 0.01430175222327954 }, "harness|hellaswag|10": { "acc": 0.6171081457876917, "acc_stderr": 0.004850988215167536, "acc_norm": 0.8159729137621987, "acc_norm_stderr": 0.003867143274914471 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.26, "acc_stderr": 0.0440844002276808, "acc_norm": 0.26, "acc_norm_stderr": 0.0440844002276808 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5555555555555556, "acc_stderr": 0.04292596718256981, "acc_norm": 0.5555555555555556, "acc_norm_stderr": 0.04292596718256981 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6644736842105263, "acc_stderr": 0.038424985593952694, "acc_norm": 0.6644736842105263, "acc_norm_stderr": 0.038424985593952694 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.56, "acc_stderr": 0.0498887651569859, "acc_norm": 0.56, "acc_norm_stderr": 0.0498887651569859 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6679245283018868, "acc_stderr": 0.028985455652334395, "acc_norm": 0.6679245283018868, "acc_norm_stderr": 0.028985455652334395 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6805555555555556, "acc_stderr": 0.038990736873573344, "acc_norm": 0.6805555555555556, "acc_norm_stderr": 0.038990736873573344 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.45, "acc_stderr": 0.05, "acc_norm": 0.45, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.37, "acc_stderr": 0.048523658709391, "acc_norm": 0.37, "acc_norm_stderr": 0.048523658709391 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5895953757225434, "acc_stderr": 0.03750757044895537, "acc_norm": 0.5895953757225434, "acc_norm_stderr": 0.03750757044895537 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3137254901960784, "acc_stderr": 0.04617034827006716, "acc_norm": 0.3137254901960784, "acc_norm_stderr": 0.04617034827006716 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.71, "acc_stderr": 0.045604802157206845, "acc_norm": 0.71, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5106382978723404, "acc_stderr": 0.03267862331014063, "acc_norm": 0.5106382978723404, "acc_norm_stderr": 0.03267862331014063 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4649122807017544, "acc_stderr": 0.046920083813689104, "acc_norm": 0.4649122807017544, "acc_norm_stderr": 0.046920083813689104 }, "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": 0.42857142857142855, "acc_stderr": 0.025487187147859372, "acc_norm": 0.42857142857142855, "acc_norm_stderr": 0.025487187147859372 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3333333333333333, "acc_stderr": 0.04216370213557836, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.04216370213557836 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7193548387096774, "acc_stderr": 0.02556060472102289, "acc_norm": 0.7193548387096774, "acc_norm_stderr": 0.02556060472102289 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.45320197044334976, "acc_stderr": 0.03502544650845872, "acc_norm": 0.45320197044334976, "acc_norm_stderr": 0.03502544650845872 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.62, "acc_stderr": 0.04878317312145633, "acc_norm": 0.62, "acc_norm_stderr": 0.04878317312145633 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7454545454545455, "acc_stderr": 0.03401506715249039, "acc_norm": 0.7454545454545455, "acc_norm_stderr": 0.03401506715249039 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7373737373737373, "acc_stderr": 0.03135305009533086, "acc_norm": 0.7373737373737373, "acc_norm_stderr": 0.03135305009533086 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8497409326424871, "acc_stderr": 0.025787723180723875, "acc_norm": 0.8497409326424871, "acc_norm_stderr": 0.025787723180723875 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5871794871794872, "acc_stderr": 0.0249626835643318, "acc_norm": 0.5871794871794872, "acc_norm_stderr": 0.0249626835643318 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3333333333333333, "acc_stderr": 0.028742040903948496, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.028742040903948496 }, "harness|hend
