open-llm-leaderboard-old/details_Locutusque__Hyperion-3.0-Yi-34B

该数据集是在Open LLM Leaderboard上对模型Locutusque/Hyperion-3.0-Yi-34B进行评估时自动创建的。数据集包含63个配置，每个配置对应一个评估任务。数据集由1次运行创建，每次运行的结果作为特定配置中的一个分割，分割名称使用运行的时间戳。train分割始终指向最新的结果。此外，还有一个名为results的配置，存储了所有运行的聚合结果，并用于计算和显示Open LLM Leaderboard上的聚合指标。

原始信息汇总

数据集概述

数据集摘要

该数据集是在评估模型 Locutusque/Hyperion-3.0-Yi-34B 在 Open LLM Leaderboard 上的自动创建的。

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，每个运行可以在每个配置中作为一个特定的分片找到，分片名称使用运行的时间戳。
• "train" 分片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_Locutusque__Hyperion-3.0-Yi-34B", "harness_winogrande_5", split="train")

最新结果

这些是最新的结果，来自 2024-03-21T17:00:46.629310 的运行： python { "all": { "acc": 0.7544550658014192, "acc_stderr": 0.02829751963964748, "acc_norm": 0.7594893210634434, "acc_norm_stderr": 0.02882703593176765, "mc1": 0.4039167686658507, "mc1_stderr": 0.01717727682258428, "mc2": 0.5637641591908886, "mc2_stderr": 0.014721062007579585 }, "harness|arc:challenge|25": { "acc": 0.6151877133105802, "acc_stderr": 0.014218371065251102, "acc_norm": 0.6459044368600683, "acc_norm_stderr": 0.013975454122756558 }, "harness|hellaswag|10": { "acc": 0.6533559051981677, "acc_stderr": 0.004749286071559571, "acc_norm": 0.8561043616809401, "acc_norm_stderr": 0.0035026656741971468 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.7481481481481481, "acc_stderr": 0.03749850709174021, "acc_norm": 0.7481481481481481, "acc_norm_stderr": 0.03749850709174021 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.8947368421052632, "acc_stderr": 0.024974533450920697, "acc_norm": 0.8947368421052632, "acc_norm_stderr": 0.024974533450920697 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.79, "acc_stderr": 0.040936018074033256, "acc_norm": 0.79, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.8075471698113208, "acc_stderr": 0.024262979839372274, "acc_norm": 0.8075471698113208, "acc_norm_stderr": 0.024262979839372274 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8819444444444444, "acc_stderr": 0.026983346503309358, "acc_norm": 0.8819444444444444, "acc_norm_stderr": 0.026983346503309358 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.61, "acc_stderr": 0.04902071300001975, "acc_norm": 0.61, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.48, "acc_stderr": 0.05021167315686779, "acc_norm": 0.48, "acc_norm_stderr": 0.05021167315686779 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7341040462427746, "acc_stderr": 0.033687629322594316, "acc_norm": 0.7341040462427746, "acc_norm_stderr": 0.033687629322594316 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.49019607843137253, "acc_stderr": 0.04974229460422817, "acc_norm": 0.49019607843137253, "acc_norm_stderr": 0.04974229460422817 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.83, "acc_stderr": 0.03775251680686371, "acc_norm": 0.83, "acc_norm_stderr": 0.03775251680686371 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.7574468085106383, "acc_stderr": 0.028020226271200217, "acc_norm": 0.7574468085106383, "acc_norm_stderr": 0.028020226271200217 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5614035087719298, "acc_stderr": 0.04668000738510455, "acc_norm": 0.5614035087719298, "acc_norm_stderr": 0.04668000738510455 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.8206896551724138, "acc_stderr": 0.03196766433373187, "acc_norm": 0.8206896551724138, "acc_norm_stderr": 0.03196766433373187 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.656084656084656, "acc_stderr": 0.024464426625596437, "acc_norm": 0.656084656084656, "acc_norm_stderr": 0.024464426625596437 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5793650793650794, "acc_stderr": 0.04415438226743745, "acc_norm": 0.5793650793650794, "acc_norm_stderr": 0.04415438226743745 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.54, "acc_stderr": 0.05009082659620333, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620333 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8838709677419355, "acc_stderr": 0.018225757949432306, "acc_norm": 0.8838709677419355, "acc_norm_stderr": 0.018225757949432306 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.625615763546798, "acc_stderr": 0.03405155380561952, "acc_norm": 0.625615763546798, "acc_norm_stderr": 0.03405155380561952 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.82, "acc_stderr": 0.038612291966536955, "acc_norm": 0.82, "acc_norm_stderr": 0.038612291966536955 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8606060606060606, "acc_stderr": 0.027045948825865394, "acc_norm": 0.8606060606060606, "acc_norm_stderr": 0.027045948825865394 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8888888888888888, "acc_stderr": 0.02239078763821677, "acc_norm": 0.8888888888888888, "acc_norm_stderr": 0.02239078763821677 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9689119170984456, "acc_stderr": 0.012525310625527043, "acc_norm": 0.9689119170984456, "acc_norm_stderr": 0.012525310625527043 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.7923076923076923, "acc_stderr": 0.020567539567246787, "acc_norm": 0.7923076923076923, "acc_norm_stderr": 0.020567539567246787 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.4185185185185185, "acc_stderr": 0.030078013075022055, "acc_norm": 0.4185185185185185, "acc_norm_stderr": 0.030078013075022055 }, "harness|hendrycksTest-high_school_microeconomics|5": {