open-llm-leaderboard-old/details_abhishek__autotrain-xva0j-mixtral8x7b
收藏数据集概述
数据集创建背景
该数据集是在模型 abhishek/autotrain-xva0j-mixtral8x7b 在 Open LLM Leaderboard 上的评估运行期间自动创建的。
数据集组成
数据集由 63 个配置组成，每个配置对应一个评估任务。数据集从 1 次运行中创建，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_abhishek__autotrain-xva0j-mixtral8x7b", "harness_winogrande_5", split="train")
最新结果
这些是最新的结果，来自 2024-03-31T21:11:14.229112 的运行：
python { "all": { "acc": 0.6620050351391895, "acc_stderr": 0.031376062719000515, "acc_norm": 0.6748162944105474, "acc_norm_stderr": 0.032102797500686404, "mc1": 0.34394124847001223, "mc1_stderr": 0.01662908751427678, "mc2": 0.5012597449415515, "mc2_stderr": 0.01519301557942148 }, "harness|arc:challenge|25": { "acc": 0.5938566552901023, "acc_stderr": 0.014351656690097862, "acc_norm": 0.6279863481228669, "acc_norm_stderr": 0.014124597881844458 }, "harness|hellaswag|10": { "acc": 0.6461860187213703, "acc_stderr": 0.004771751187407021, "acc_norm": 0.844353714399522, "acc_norm_stderr": 0.0036177879347477483 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.35, "acc_stderr": 0.047937248544110224, "acc_norm": 0.35, "acc_norm_stderr": 0.047937248544110224 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6296296296296297, "acc_stderr": 0.041716541613545426, "acc_norm": 0.6296296296296297, "acc_norm_stderr": 0.041716541613545426 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7697368421052632, "acc_stderr": 0.03426059424403165, "acc_norm": 0.7697368421052632, "acc_norm_stderr": 0.03426059424403165 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.64, "acc_stderr": 0.048241815132442176, "acc_norm": 0.64, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7735849056603774, "acc_stderr": 0.02575755989310673, "acc_norm": 0.7735849056603774, "acc_norm_stderr": 0.02575755989310673 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7847222222222222, "acc_stderr": 0.03437079344106135, "acc_norm": 0.7847222222222222, "acc_norm_stderr": 0.03437079344106135 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "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": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6878612716763006, "acc_stderr": 0.035331333893236574, "acc_norm": 0.6878612716763006, "acc_norm_stderr": 0.035331333893236574 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4411764705882353, "acc_stderr": 0.049406356306056595, "acc_norm": 0.4411764705882353, "acc_norm_stderr": 0.049406356306056595 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.77, "acc_stderr": 0.04229525846816507, "acc_norm": 0.77, "acc_norm_stderr": 0.04229525846816507 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.6212765957446809, "acc_stderr": 0.03170995606040655, "acc_norm": 0.6212765957446809, "acc_norm_stderr": 0.03170995606040655 }, "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": 0.6620689655172414, "acc_stderr": 0.039417076320648906, "acc_norm": 0.6620689655172414, "acc_norm_stderr": 0.039417076320648906 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4444444444444444, "acc_stderr": 0.02559185776138218, "acc_norm": 0.4444444444444444, "acc_norm_stderr": 0.02559185776138218 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3888888888888889, "acc_stderr": 0.04360314860077459, "acc_norm": 0.3888888888888889, "acc_norm_stderr": 0.04360314860077459 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.41, "acc_stderr": 0.049431107042371025, "acc_norm": 0.41, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8064516129032258, "acc_stderr": 0.022475258525536057, "acc_norm": 0.8064516129032258, "acc_norm_stderr": 0.022475258525536057 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5172413793103449, "acc_stderr": 0.035158955511656986, "acc_norm": 0.5172413793103449, "acc_norm_stderr": 0.035158955511656986 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.68, "acc_stderr": 0.04688261722621505, "acc_norm": 0.68, "acc_norm_stderr": 0.04688261722621505 }, "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": 0.8282828282828283, "acc_stderr": 0.026869716187429903, "acc_norm": 0.8282828282828283, "acc_norm_stderr": 0.026869716187429903 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9067357512953368, "acc_stderr": 0.020986854593289736, "acc_norm": 0.9067357512953368, "acc_norm_stderr": 0.020986854593289736 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6487179487179487, "acc_stderr": 0.024203665177902803, "acc_norm": 0.6487179487179487, "acc_norm_stderr": 0.024203665177902803 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3851851851851852, "acc_stderr": 0.02967090612463088, "acc_norm": 0.3851851851851852, "acc_norm_stderr": 0.02967090612463088 }, "harness|hendry
