open-llm-leaderboard-old/details_BarraHome__llama-3-orpo-v1-merged_16bit

该数据集是在模型BarraHome/llama-3-orpo-v1-merged_16bit的评估运行期间自动创建的，评估运行在Open LLM Leaderboard上进行。数据集由63个配置组成，每个配置对应一个评估任务。数据集是从1次运行中创建的，每次运行可以在每个配置中找到特定的分割，分割使用运行的时间戳命名。"train"分割始终指向最新的结果。此外，"results"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

该数据集是在对模型 BarraHome/llama-3-orpo-v1-merged_16bit 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 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。
• 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_BarraHome__llama-3-orpo-v1-merged_16bit", "harness_winogrande_5", split="train")

最新结果

以下是 2024-04-23T07:07:09.628312 运行的最新结果：

python { "all": { "acc": 0.24659169769633435, "acc_stderr": 0.03050677058585619, "acc_norm": 0.2484616907960142, "acc_norm_stderr": 0.031324730374514685, "mc1": 0.19461444308445533, "mc1_stderr": 0.013859398207029427, "mc2": 0.4092155740352721, "mc2_stderr": 0.015413008356981369 }, "harness|arc:challenge|25": { "acc": 0.18515358361774745, "acc_stderr": 0.011350774438389704, "acc_norm": 0.23293515358361774, "acc_norm_stderr": 0.012352507042617407 }, "harness|hellaswag|10": { "acc": 0.3147779326827325, "acc_stderr": 0.004634782156128603, "acc_norm": 0.4113722366062537, "acc_norm_stderr": 0.004910767540867424 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.22, "acc_stderr": 0.04163331998932268, "acc_norm": 0.22, "acc_norm_stderr": 0.04163331998932268 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.3037037037037037, "acc_stderr": 0.039725528847851375, "acc_norm": 0.3037037037037037, "acc_norm_stderr": 0.039725528847851375 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.25, "acc_stderr": 0.03523807393012047, "acc_norm": 0.25, "acc_norm_stderr": 0.03523807393012047 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.24528301886792453, "acc_stderr": 0.026480357179895678, "acc_norm": 0.24528301886792453, "acc_norm_stderr": 0.026480357179895678 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2986111111111111, "acc_stderr": 0.03827052357950756, "acc_norm": 0.2986111111111111, "acc_norm_stderr": 0.03827052357950756 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.26, "acc_stderr": 0.04408440022768079, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768079 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.18, "acc_stderr": 0.038612291966536955, "acc_norm": 0.18, "acc_norm_stderr": 0.038612291966536955 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.21, "acc_stderr": 0.040936018074033256, "acc_norm": 0.21, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.20809248554913296, "acc_stderr": 0.030952890217749874, "acc_norm": 0.20809248554913296, "acc_norm_stderr": 0.030952890217749874 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.21568627450980393, "acc_stderr": 0.04092563958237654, "acc_norm": 0.21568627450980393, "acc_norm_stderr": 0.04092563958237654 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.29, "acc_stderr": 0.04560480215720684, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720684 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.25957446808510637, "acc_stderr": 0.02865917937429232, "acc_norm": 0.25957446808510637, "acc_norm_stderr": 0.02865917937429232 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.23684210526315788, "acc_stderr": 0.039994238792813365, "acc_norm": 0.23684210526315788, "acc_norm_stderr": 0.039994238792813365 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2482758620689655, "acc_stderr": 0.036001056927277716, "acc_norm": 0.2482758620689655, "acc_norm_stderr": 0.036001056927277716 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2222222222222222, "acc_stderr": 0.021411684393694206, "acc_norm": 0.2222222222222222, "acc_norm_stderr": 0.021411684393694206 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.15873015873015872, "acc_stderr": 0.03268454013011742, "acc_norm": 0.15873015873015872, "acc_norm_stderr": 0.03268454013011742 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.18, "acc_stderr": 0.038612291966536934, "acc_norm": 0.18, "acc_norm_stderr": 0.038612291966536934 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.2064516129032258, "acc_stderr": 0.023025899617188712, "acc_norm": 0.2064516129032258, "acc_norm_stderr": 0.023025899617188712 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.1921182266009852, "acc_stderr": 0.027719315709614775, "acc_norm": 0.1921182266009852, "acc_norm_stderr": 0.027719315709614775 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.26666666666666666, "acc_stderr": 0.034531318018854146, "acc_norm": 0.26666666666666666, "acc_norm_stderr": 0.034531318018854146 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.22727272727272727, "acc_stderr": 0.029857515673386414, "acc_norm": 0.22727272727272727, "acc_norm_stderr": 0.029857515673386414 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.31088082901554404, "acc_stderr": 0.03340361906276587, "acc_norm": 0.31088082901554404, "acc_norm_stderr": 0.03340361906276587 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.25384615384615383, "acc_stderr": 0.022066054378726257, "acc_norm": 0.25384615384615383, "acc_norm_stderr": 0.022066054378726257 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.21481481481481482, "acc_stderr": 0.025040443877000683, "acc_norm": 0.21481481481481482, "acc_norm