open-llm-leaderboard-old/details_Locutusque__Hyperion-2.0-Yi-34B
收藏数据集概述
数据集简介
该数据集是在评估模型 Locutusque/Hyperion-2.0-Yi-34B 在 Open LLM Leaderboard 上的自动创建的。数据集包含 63 个配置，每个配置对应一个评估任务。
数据集结构
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。"train" 分割始终指向最新的结果。
额外配置
一个额外的配置 "results" 存储了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-2.0-Yi-34B", "harness_winogrande_5", split="train")
最新结果
以下是 最新结果 的摘要：
python { "all": { "acc": 0.7556279602672477, "acc_stderr": 0.028204936421836208, "acc_norm": 0.7605576976803771, "acc_norm_stderr": 0.02873099940778838, "mc1": 0.3953488372093023, "mc1_stderr": 0.017115815632418194, "mc2": 0.5529839160462177, "mc2_stderr": 0.01494979176313861 }, "harness|arc:challenge|25": { "acc": 0.6143344709897611, "acc_stderr": 0.014224250973257174, "acc_norm": 0.643344709897611, "acc_norm_stderr": 0.013998056902620194 }, "harness|hellaswag|10": { "acc": 0.6547500497908784, "acc_stderr": 0.004744780201276634, "acc_norm": 0.856602270464051, "acc_norm_stderr": 0.0034976171082184136 }, "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": 0.7703703703703704, "acc_stderr": 0.03633384414073465, "acc_norm": 0.7703703703703704, "acc_norm_stderr": 0.03633384414073465 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.8881578947368421, "acc_stderr": 0.02564834125169361, "acc_norm": 0.8881578947368421, "acc_norm_stderr": 0.02564834125169361 }, "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": 0.7849056603773585, "acc_stderr": 0.025288394502891366, "acc_norm": 0.7849056603773585, "acc_norm_stderr": 0.025288394502891366 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8819444444444444, "acc_stderr": 0.026983346503309354, "acc_norm": 0.8819444444444444, "acc_norm_stderr": 0.026983346503309354 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.51, "acc_stderr": 0.05024183937956912, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.63, "acc_stderr": 0.048523658709391, "acc_norm": 0.63, "acc_norm_stderr": 0.048523658709391 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.47, "acc_stderr": 0.05016135580465919, "acc_norm": 0.47, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7052023121387283, "acc_stderr": 0.03476599607516478, "acc_norm": 0.7052023121387283, "acc_norm_stderr": 0.03476599607516478 }, "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": 0.7659574468085106, "acc_stderr": 0.02767845257821239, "acc_norm": 0.7659574468085106, "acc_norm_stderr": 0.02767845257821239 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5350877192982456, "acc_stderr": 0.046920083813689104, "acc_norm": 0.5350877192982456, "acc_norm_stderr": 0.046920083813689104 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.8068965517241379, "acc_stderr": 0.032894455221274016, "acc_norm": 0.8068965517241379, "acc_norm_stderr": 0.032894455221274016 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.6428571428571429, "acc_stderr": 0.024677862841332783, "acc_norm": 0.6428571428571429, "acc_norm_stderr": 0.024677862841332783 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5873015873015873, "acc_stderr": 0.04403438954768176, "acc_norm": 0.5873015873015873, "acc_norm_stderr": 0.04403438954768176 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.51, "acc_stderr": 0.05024183937956911, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956911 }, "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": 0.6305418719211823, "acc_stderr": 0.03395970381998573, "acc_norm": 0.6305418719211823, "acc_norm_stderr": 0.03395970381998573 }, "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": 0.8727272727272727, "acc_stderr": 0.026024657651656194, "acc_norm": 0.8727272727272727, "acc_norm_stderr": 0.026024657651656194 }, "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": 0.9740932642487047, "acc_stderr": 0.01146452335695318, "acc_norm": 0.9740932642487047, "acc_norm_stderr": 0.01146452335695318 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.7948717948717948, "acc_stderr": 0.020473233173551965, "acc_norm": 0.7948717948717948, "acc_norm_stderr": 0.020473233173551965 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.44814814814814813, "acc_stderr": 0.030321167196316286, "acc_norm": 0.44814814814814813, "acc_norm_stderr": 0.030321167
