open-llm-leaderboard-old/details_adamo1139__Yi-34B-200K-AEZAKMI-RAW-2301
收藏数据集概述
数据集简介
该数据集是在对模型 adamo1139/Yi-34B-200K-AEZAKMI-RAW-2301 进行评估运行期间自动创建的，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 1 次运行中创建，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_adamo1139__Yi-34B-200K-AEZAKMI-RAW-2301", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-26T02:39:52.943697 运行的最新结果：
python { "all": { "acc": 0.7432390573583032, "acc_stderr": 0.028856954294040817, "acc_norm": 0.749080934110935, "acc_norm_stderr": 0.02939165201523678, "mc1": 0.40024479804161567, "mc1_stderr": 0.017151605555749138, "mc2": 0.568876394941753, "mc2_stderr": 0.015032807114194642 }, "harness|arc:challenge|25": { "acc": 0.6160409556313993, "acc_stderr": 0.01421244498065189, "acc_norm": 0.6604095563139932, "acc_norm_stderr": 0.013839039762820169 }, "harness|hellaswag|10": { "acc": 0.6509659430392352, "acc_stderr": 0.0047569058196499725, "acc_norm": 0.847042421828321, "acc_norm_stderr": 0.0035921097436286183 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.4, "acc_stderr": 0.049236596391733084, "acc_norm": 0.4, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6888888888888889, "acc_stderr": 0.03999262876617722, "acc_norm": 0.6888888888888889, "acc_norm_stderr": 0.03999262876617722 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.875, "acc_stderr": 0.026913523521537846, "acc_norm": 0.875, "acc_norm_stderr": 0.026913523521537846 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.75, "acc_stderr": 0.04351941398892446, "acc_norm": 0.75, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.8, "acc_stderr": 0.024618298195866514, "acc_norm": 0.8, "acc_norm_stderr": 0.024618298195866514 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8819444444444444, "acc_stderr": 0.026983346503309375, "acc_norm": 0.8819444444444444, "acc_norm_stderr": 0.026983346503309375 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.54, "acc_stderr": 0.05009082659620332, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.59, "acc_stderr": 0.04943110704237101, "acc_norm": 0.59, "acc_norm_stderr": 0.04943110704237101 }, "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": 0.7167630057803468, "acc_stderr": 0.034355680560478746, "acc_norm": 0.7167630057803468, "acc_norm_stderr": 0.034355680560478746 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.5098039215686274, "acc_stderr": 0.04974229460422817, "acc_norm": 0.5098039215686274, "acc_norm_stderr": 0.04974229460422817 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.81, "acc_stderr": 0.039427724440366234, "acc_norm": 0.81, "acc_norm_stderr": 0.039427724440366234 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.7489361702127659, "acc_stderr": 0.02834696377716245, "acc_norm": 0.7489361702127659, "acc_norm_stderr": 0.02834696377716245 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.543859649122807, "acc_stderr": 0.046854730419077895, "acc_norm": 0.543859649122807, "acc_norm_stderr": 0.046854730419077895 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.7172413793103448, "acc_stderr": 0.037528339580033376, "acc_norm": 0.7172413793103448, "acc_norm_stderr": 0.037528339580033376 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.6613756613756614, "acc_stderr": 0.024373197867983053, "acc_norm": 0.6613756613756614, "acc_norm_stderr": 0.024373197867983053 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5396825396825397, "acc_stderr": 0.04458029125470973, "acc_norm": 0.5396825396825397, "acc_norm_stderr": 0.04458029125470973 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8806451612903226, "acc_stderr": 0.01844341132531541, "acc_norm": 0.8806451612903226, "acc_norm_stderr": 0.01844341132531541 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.6650246305418719, "acc_stderr": 0.033208527423483104, "acc_norm": 0.6650246305418719, "acc_norm_stderr": 0.033208527423483104 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.76, "acc_stderr": 0.04292346959909282, "acc_norm": 0.76, "acc_norm_stderr": 0.04292346959909282 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8545454545454545, "acc_stderr": 0.027530196355066584, "acc_norm": 0.8545454545454545, "acc_norm_stderr": 0.027530196355066584 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.9292929292929293, "acc_stderr": 0.018263105420199488, "acc_norm": 0.9292929292929293, "acc_norm_stderr": 0.018263105420199488 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9689119170984456, "acc_stderr": 0.012525310625527029, "acc_norm": 0.9689119170984456, "acc_norm_stderr": 0.012525310625527029 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.8025641025641026, "acc_stderr": 0.02018264696867483, "acc_norm": 0.8025641025641026, "acc_norm_stderr": 0.02018264696867483 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3888888888888889, "acc_stderr": 0.029723278961476664, "acc_norm": 0.3888888
