open-llm-leaderboard-old/details_uukuguy__speechless-zephyr-code-functionary-7b
收藏数据集概述
数据集简介
该数据集是在评估模型uukuguy/speechless-zephyr-code-functionary-7b在Open LLM Leaderboard上的运行过程中自动创建的。
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_uukuguy__speechless-zephyr-code-functionary-7b", "harness_winogrande_5", split="train")
最新结果
这些是最新的结果，来自2024-01-23T12:18:03.845597的运行： python { "all": { "acc": 0.6448787410516414, "acc_stderr": 0.03224509099981482, "acc_norm": 0.649790965396691, "acc_norm_stderr": 0.032889685494221804, "mc1": 0.30599755201958384, "mc1_stderr": 0.01613222972815504, "mc2": 0.44994239471775765, "mc2_stderr": 0.014464163311832926 }, "harness|arc:challenge|25": { "acc": 0.5878839590443686, "acc_stderr": 0.014383915302225403, "acc_norm": 0.6151877133105802, "acc_norm_stderr": 0.014218371065251102 }, "harness|hellaswag|10": { "acc": 0.6409081856203943, "acc_stderr": 0.004787537385153, "acc_norm": 0.8387771360286795, "acc_norm_stderr": 0.0036698484004877773 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6444444444444445, "acc_stderr": 0.04135176749720385, "acc_norm": 0.6444444444444445, "acc_norm_stderr": 0.04135176749720385 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6644736842105263, "acc_stderr": 0.03842498559395268, "acc_norm": 0.6644736842105263, "acc_norm_stderr": 0.03842498559395268 }, "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": 0.7094339622641509, "acc_stderr": 0.02794321998933714, "acc_norm": 0.7094339622641509, "acc_norm_stderr": 0.02794321998933714 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7291666666666666, "acc_stderr": 0.03716177437566017, "acc_norm": 0.7291666666666666, "acc_norm_stderr": 0.03716177437566017 }, "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": 0.55, "acc_stderr": 0.049999999999999996, "acc_norm": 0.55, "acc_norm_stderr": 0.049999999999999996 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.38, "acc_stderr": 0.04878317312145633, "acc_norm": 0.38, "acc_norm_stderr": 0.04878317312145633 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6416184971098265, "acc_stderr": 0.03656343653353159, "acc_norm": 0.6416184971098265, "acc_norm_stderr": 0.03656343653353159 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.39215686274509803, "acc_stderr": 0.04858083574266346, "acc_norm": 0.39215686274509803, "acc_norm_stderr": 0.04858083574266346 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.78, "acc_stderr": 0.04163331998932261, "acc_norm": 0.78, "acc_norm_stderr": 0.04163331998932261 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5659574468085107, "acc_stderr": 0.03240038086792747, "acc_norm": 0.5659574468085107, "acc_norm_stderr": 0.03240038086792747 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5, "acc_stderr": 0.047036043419179864, "acc_norm": 0.5, "acc_norm_stderr": 0.047036043419179864 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5448275862068965, "acc_stderr": 0.04149886942192117, "acc_norm": 0.5448275862068965, "acc_norm_stderr": 0.04149886942192117 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3941798941798942, "acc_stderr": 0.02516798233389414, "acc_norm": 0.3941798941798942, "acc_norm_stderr": 0.02516798233389414 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.42063492063492064, "acc_stderr": 0.04415438226743744, "acc_norm": 0.42063492063492064, "acc_norm_stderr": 0.04415438226743744 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.4, "acc_stderr": 0.049236596391733084, "acc_norm": 0.4, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7677419354838709, "acc_stderr": 0.024022256130308235, "acc_norm": 0.7677419354838709, "acc_norm_stderr": 0.024022256130308235 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5369458128078818, "acc_stderr": 0.035083705204426656, "acc_norm": 0.5369458128078818, "acc_norm_stderr": 0.035083705204426656 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.72, "acc_stderr": 0.04512608598542127, "acc_norm": 0.72, "acc_norm_stderr": 0.04512608598542127 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7575757575757576, "acc_stderr": 0.03346409881055953, "acc_norm": 0.7575757575757576, "acc_norm_stderr": 0.03346409881055953 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7828282828282829, "acc_stderr": 0.02937661648494563, "acc_norm": 0.7828282828282829, "acc_norm_stderr": 0.02937661648494563 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8963730569948186, "acc_stderr": 0.02199531196364424, "acc_norm": 0.8963730569948186, "acc_norm_stderr": 0.02199531196364424 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6692307692307692, "acc_stderr": 0.023854795680971128, "acc_norm": 0.6692307692307692, "acc_norm_stderr": 0.023854795680971128 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.34814814814814815, "acc_stderr": 0.029045600290616258, "acc_norm": 0.34814814814814815, "acc_norm_stderr": 0.029045600290616258 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.6596638655462185, "acc_stderr": 0.03077805742293
