open-llm-leaderboard/details_AI-Sweden-Models__gpt-sw3-20b-instruct
收藏数据集概述
该数据集是在对模型 AI-Sweden-Models/gpt-sw3-20b-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 64 个配置，每个配置对应一个评估任务。
- 数据集来自 1 次运行，每次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。
- 额外的 "results" 配置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_AI-Sweden-Models__gpt-sw3-20b-instruct_public", "harness_winogrande_5", split="train")
最新结果
以下是 2023-11-18T19:55:37.406086 运行 的最新结果：
python { "all": { "acc": 0.320676822366553, "acc_stderr": 0.03280575656070825, "acc_norm": 0.3219577309602372, "acc_norm_stderr": 0.03355424008379778, "mc1": 0.25458996328029376, "mc1_stderr": 0.015250117079156494, "mc2": 0.4101922343540469, "mc2_stderr": 0.014529149906569373, "em": 0.014471476510067114, "em_stderr": 0.0012230118709417176, "f1": 0.051461828859060935, "f1_stderr": 0.0016503207117057528 }, "harness|arc:challenge|25": { "acc": 0.42150170648464164, "acc_stderr": 0.014430197069326012, "acc_norm": 0.431740614334471, "acc_norm_stderr": 0.014474591427196207 }, "harness|hellaswag|10": { "acc": 0.5312686715793666, "acc_stderr": 0.004980014536539819, "acc_norm": 0.7109141605257917, "acc_norm_stderr": 0.004524113671259695 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.28, "acc_stderr": 0.04512608598542128, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542128 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.3333333333333333, "acc_stderr": 0.04072314811876837, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.04072314811876837 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.2565789473684211, "acc_stderr": 0.0355418036802569, "acc_norm": 0.2565789473684211, "acc_norm_stderr": 0.0355418036802569 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.33, "acc_stderr": 0.04725815626252604, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252604 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.3283018867924528, "acc_stderr": 0.02890159361241178, "acc_norm": 0.3283018867924528, "acc_norm_stderr": 0.02890159361241178 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2569444444444444, "acc_stderr": 0.03653946969442099, "acc_norm": 0.2569444444444444, "acc_norm_stderr": 0.03653946969442099 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.21, "acc_stderr": 0.040936018074033256, "acc_norm": 0.21, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.23, "acc_stderr": 0.042295258468165044, "acc_norm": 0.23, "acc_norm_stderr": 0.042295258468165044 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.34, "acc_stderr": 0.047609522856952365, "acc_norm": 0.34, "acc_norm_stderr": 0.047609522856952365 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.2658959537572254, "acc_stderr": 0.033687629322594316, "acc_norm": 0.2658959537572254, "acc_norm_stderr": 0.033687629322594316 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.16666666666666666, "acc_stderr": 0.03708284662416544, "acc_norm": 0.16666666666666666, "acc_norm_stderr": 0.03708284662416544 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.34893617021276596, "acc_stderr": 0.031158522131357783, "acc_norm": 0.34893617021276596, "acc_norm_stderr": 0.031158522131357783 }, "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": 0.3310344827586207, "acc_stderr": 0.03921545312467122, "acc_norm": 0.3310344827586207, "acc_norm_stderr": 0.03921545312467122 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.25925925925925924, "acc_stderr": 0.02256989707491841, "acc_norm": 0.25925925925925924, "acc_norm_stderr": 0.02256989707491841 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.20634920634920634, "acc_stderr": 0.036196045241242515, "acc_norm": 0.20634920634920634, "acc_norm_stderr": 0.036196045241242515 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.3161290322580645, "acc_stderr": 0.026450874489042774, "acc_norm": 0.3161290322580645, "acc_norm_stderr": 0.026450874489042774 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.31527093596059114, "acc_stderr": 0.03269080871970187, "acc_norm": 0.31527093596059114, "acc_norm_stderr": 0.03269080871970187 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.36, "acc_stderr": 0.048241815132442176, "acc_norm": 0.36, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.41818181818181815, "acc_stderr": 0.03851716319398394, "acc_norm": 0.41818181818181815, "acc_norm_stderr": 0.03851716319398394 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.29797979797979796, "acc_stderr": 0.03258630383836556, "acc_norm": 0.29797979797979796, "acc_norm_stderr": 0.03258630383836556 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.33678756476683935, "acc_stderr": 0.03410780251836184, "acc_norm": 0.33678756476683935, "acc_norm_stderr": 0.03410780251836184 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.26153846153846155, "acc_stderr": 0.02228214120420442, "acc_norm": 0.261538461538461
