open-llm-leaderboard-old/details_Joseph717171__Tess-10.7B-v2.0
收藏数据集概述
数据集简介
该数据集是在对模型Joseph717171/Tess-10.7B-v2.0进行评估运行期间自动创建的，用于Open LLM Leaderboard。
数据集结构
- 配置数量：63个配置，每个配置对应一个评估任务。
- 运行次数：数据集由1次运行创建，每个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。
- 训练分割："train"分割始终指向最新的结果。
- 结果配置：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_Joseph717171__Tess-10.7B-v2.0", "harness_winogrande_5", split="train")
最新结果
以下是2024-03-30T16:07:29.849184运行的最新结果：
python { "all": { "acc": 0.4992826261878715, "acc_stderr": 0.03426501694925459, "acc_norm": 0.5059033509632049, "acc_norm_stderr": 0.0350107347322564, "mc1": 0.2839657282741738, "mc1_stderr": 0.01578537085839673, "mc2": 0.4462553482634578, "mc2_stderr": 0.0158028727847505 }, "harness|arc:challenge|25": { "acc": 0.507679180887372, "acc_stderr": 0.01460966744089257, "acc_norm": 0.5511945392491467, "acc_norm_stderr": 0.014534599585097662 }, "harness|hellaswag|10": { "acc": 0.5668193586934873, "acc_stderr": 0.0049450236570322765, "acc_norm": 0.7439753037243577, "acc_norm_stderr": 0.004355436696716298 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.23, "acc_stderr": 0.04229525846816506, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816506 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.4222222222222222, "acc_stderr": 0.04266763404099582, "acc_norm": 0.4222222222222222, "acc_norm_stderr": 0.04266763404099582 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.506578947368421, "acc_stderr": 0.040685900502249704, "acc_norm": 0.506578947368421, "acc_norm_stderr": 0.040685900502249704 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.58, "acc_stderr": 0.049604496374885836, "acc_norm": 0.58, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5509433962264151, "acc_stderr": 0.030612730713641095, "acc_norm": 0.5509433962264151, "acc_norm_stderr": 0.030612730713641095 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5069444444444444, "acc_stderr": 0.04180806750294938, "acc_norm": 0.5069444444444444, "acc_norm_stderr": 0.04180806750294938 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.33, "acc_stderr": 0.04725815626252605, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252605 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.39, "acc_stderr": 0.04902071300001975, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.24, "acc_stderr": 0.04292346959909283, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909283 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5202312138728323, "acc_stderr": 0.03809342081273957, "acc_norm": 0.5202312138728323, "acc_norm_stderr": 0.03809342081273957 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.2549019607843137, "acc_stderr": 0.043364327079931785, "acc_norm": 0.2549019607843137, "acc_norm_stderr": 0.043364327079931785 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.6, "acc_stderr": 0.04923659639173309, "acc_norm": 0.6, "acc_norm_stderr": 0.04923659639173309 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.37872340425531914, "acc_stderr": 0.03170995606040655, "acc_norm": 0.37872340425531914, "acc_norm_stderr": 0.03170995606040655 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.37719298245614036, "acc_stderr": 0.04559522141958216, "acc_norm": 0.37719298245614036, "acc_norm_stderr": 0.04559522141958216 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.4827586206896552, "acc_stderr": 0.04164188720169377, "acc_norm": 0.4827586206896552, "acc_norm_stderr": 0.04164188720169377 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3412698412698413, "acc_stderr": 0.02441923496681906, "acc_norm": 0.3412698412698413, "acc_norm_stderr": 0.02441923496681906 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.2777777777777778, "acc_stderr": 0.04006168083848878, "acc_norm": 0.2777777777777778, "acc_norm_stderr": 0.04006168083848878 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.5838709677419355, "acc_stderr": 0.028040981380761547, "acc_norm": 0.5838709677419355, "acc_norm_stderr": 0.028040981380761547 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.41379310344827586, "acc_stderr": 0.03465304488406795, "acc_norm": 0.41379310344827586, "acc_norm_stderr": 0.03465304488406795 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.57, "acc_stderr": 0.049756985195624284, "acc_norm": 0.57, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6606060606060606, "acc_stderr": 0.036974422050315967, "acc_norm": 0.6606060606060606, "acc_norm_stderr": 0.036974422050315967 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.6363636363636364, "acc_stderr": 0.03427308652999934, "acc_norm": 0.6363636363636364, "acc_norm_stderr": 0.03427308652999934 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.6424870466321243, "acc_stderr": 0.034588160421810114, "acc_norm": 0.6424870466321243, "acc_norm_stderr": 0.034588160421810114 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5230769230769231, "acc_stderr": 0.025323990861736236, "acc_norm": 0.5230769230769231, "acc_norm_stderr": 0.025323990861736236 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2777777777777778, "acc_stderr": 0.02730914058823018, "acc
