open-llm-leaderboard-old/details_Charlie911__zephyr-7b-beta-MultiLoRA-mmlu-merged

该数据集是在Open LLM Leaderboard上对模型Charlie911/zephyr-7b-beta-MultiLoRA-mmlu-merged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5次运行生成，每次运行的结果作为一个特定的分割存储在配置中，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，一个名为"results"的配置存储了所有运行的聚合结果，用于计算和显示在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

该数据集是在对模型 Charlie911/zephyr-7b-beta-MultiLoRA-mmlu-merged 进行评估运行时自动创建的，用于 Open LLM Leaderboard。

数据集组成

• 该数据集包含 63 个配置，每个配置对应一个评估任务。
• 数据集从 5 次运行中创建，每次运行可以在每个配置中找到一个特定的分割，分割名称使用运行的时间戳。
• "train" 分割始终指向最新的结果。
• 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_Charlie911__zephyr-7b-beta-MultiLoRA-mmlu-merged", "harness_winogrande_5", split="train")

最新结果

以下是 2024-02-20T19:06:56.636756 运行的最新结果：

python { "all": { "acc": 0.5831485221159624, "acc_stderr": 0.03371973400145409, "acc_norm": 0.5894635035320129, "acc_norm_stderr": 0.03443558652423577, "mc1": 0.34761321909424725, "mc1_stderr": 0.016670769188897303, "mc2": 0.5198213221982798, "mc2_stderr": 0.015594556548328408 }, "harness|arc:challenge|25": { "acc": 0.5418088737201365, "acc_stderr": 0.0145602203087147, "acc_norm": 0.5793515358361775, "acc_norm_stderr": 0.014426211252508397 }, "harness|hellaswag|10": { "acc": 0.6115315674168492, "acc_stderr": 0.004864058877626274, "acc_norm": 0.8142800238996216, "acc_norm_stderr": 0.003880857679279931 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5407407407407407, "acc_stderr": 0.04304979692464241, "acc_norm": 0.5407407407407407, "acc_norm_stderr": 0.04304979692464241 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5526315789473685, "acc_stderr": 0.04046336883978251, "acc_norm": 0.5526315789473685, "acc_norm_stderr": 0.04046336883978251 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.51, "acc_stderr": 0.05024183937956912, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6377358490566037, "acc_stderr": 0.029582245128384303, "acc_norm": 0.6377358490566037, "acc_norm_stderr": 0.029582245128384303 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6597222222222222, "acc_stderr": 0.039621355734862175, "acc_norm": 0.6597222222222222, "acc_norm_stderr": 0.039621355734862175 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.47, "acc_stderr": 0.050161355804659205, "acc_norm": 0.47, "acc_norm_stderr": 0.050161355804659205 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.41, "acc_stderr": 0.049431107042371025, "acc_norm": 0.41, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6011560693641619, "acc_stderr": 0.0373362665538351, "acc_norm": 0.6011560693641619, "acc_norm_stderr": 0.0373362665538351 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3627450980392157, "acc_stderr": 0.047840607041056527, "acc_norm": 0.3627450980392157, "acc_norm_stderr": 0.047840607041056527 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.71, "acc_stderr": 0.04560480215720684, "acc_norm": 0.71, "acc_norm_stderr": 0.04560480215720684 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.49361702127659574, "acc_stderr": 0.032683358999363366, "acc_norm": 0.49361702127659574, "acc_norm_stderr": 0.032683358999363366 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4649122807017544, "acc_stderr": 0.04692008381368909, "acc_norm": 0.4649122807017544, "acc_norm_stderr": 0.04692008381368909 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5310344827586206, "acc_stderr": 0.04158632762097828, "acc_norm": 0.5310344827586206, "acc_norm_stderr": 0.04158632762097828 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.34656084656084657, "acc_stderr": 0.02450877752102842, "acc_norm": 0.34656084656084657, "acc_norm_stderr": 0.02450877752102842 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3968253968253968, "acc_stderr": 0.0437588849272706, "acc_norm": 0.3968253968253968, "acc_norm_stderr": 0.0437588849272706 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7225806451612903, "acc_stderr": 0.025470196835900055, "acc_norm": 0.7225806451612903, "acc_norm_stderr": 0.025470196835900055 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.458128078817734, "acc_stderr": 0.03505630140785741, "acc_norm": 0.458128078817734, "acc_norm_stderr": 0.03505630140785741 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.64, "acc_stderr": 0.04824181513244218, "acc_norm": 0.64, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7090909090909091, "acc_stderr": 0.03546563019624336, "acc_norm": 0.7090909090909091, "acc_norm_stderr": 0.03546563019624336 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7323232323232324, "acc_stderr": 0.03154449888270285, "acc_norm": 0.7323232323232324, "acc_norm_stderr": 0.03154449888270285 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7979274611398963, "acc_stderr": 0.02897908979429673, "acc_norm": 0.7979274611398963, "acc_norm_stderr": 0.02897908979429673 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5666666666666667, "acc_stderr": 0.025124653525885113, "acc_norm": 0.5666666666666667, "acc_norm_stderr": 0.025124653525885113 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.35185185185185186, "acc_stderr": 0.029116617606083008,