open-llm-leaderboard-old/details_Xenon1__Xenon-2
收藏数据集概述
数据集名称
Evaluation run of Xenon1/Xenon-2
数据集摘要
该数据集是在模型 Xenon1/Xenon-2 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。每个运行可以在每个配置中作为一个特定的分割找到，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_Xenon1__Xenon-2", "harness_winogrande_5", split="train")
最新结果
以下是 2024-02-04T06:12:02.533173 运行 的最新结果：
python { "all": { "acc": 0.5979349234673121, "acc_stderr": 0.03314667589298127, "acc_norm": 0.6059085706273892, "acc_norm_stderr": 0.03386834152845098, "mc1": 0.4430844553243574, "mc1_stderr": 0.017389730346877103, "mc2": 0.6091942381109575, "mc2_stderr": 0.016102758925844906 }, "harness|arc:challenge|25": { "acc": 0.515358361774744, "acc_stderr": 0.014604496129394906, "acc_norm": 0.5750853242320819, "acc_norm_stderr": 0.014445698968520762 }, "harness|hellaswag|10": { "acc": 0.6417048396733719, "acc_stderr": 0.0047851950498891595, "acc_norm": 0.8328022306313483, "acc_norm_stderr": 0.0037238973056454845 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6, "acc_stderr": 0.04232073695151589, "acc_norm": 0.6, "acc_norm_stderr": 0.04232073695151589 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.625, "acc_stderr": 0.039397364351956274, "acc_norm": 0.625, "acc_norm_stderr": 0.039397364351956274 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.54, "acc_stderr": 0.05009082659620332, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6830188679245283, "acc_stderr": 0.02863723563980089, "acc_norm": 0.6830188679245283, "acc_norm_stderr": 0.02863723563980089 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7013888888888888, "acc_stderr": 0.03827052357950756, "acc_norm": 0.7013888888888888, "acc_norm_stderr": 0.03827052357950756 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.42, "acc_stderr": 0.04960449637488584, "acc_norm": 0.42, "acc_norm_stderr": 0.04960449637488584 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.54, "acc_stderr": 0.05009082659620333, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620333 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.36, "acc_stderr": 0.048241815132442176, "acc_norm": 0.36, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5780346820809249, "acc_stderr": 0.0376574669386515, "acc_norm": 0.5780346820809249, "acc_norm_stderr": 0.0376574669386515 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.43137254901960786, "acc_stderr": 0.04928099597287534, "acc_norm": 0.43137254901960786, "acc_norm_stderr": 0.04928099597287534 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.75, "acc_stderr": 0.04351941398892446, "acc_norm": 0.75, "acc_norm_stderr": 0.04351941398892446 }, "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": 0.046920083813689104, "acc_norm": 0.4649122807017544, "acc_norm_stderr": 0.046920083813689104 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5862068965517241, "acc_stderr": 0.041042692118062316, "acc_norm": 0.5862068965517241, "acc_norm_stderr": 0.041042692118062316 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.37037037037037035, "acc_stderr": 0.024870815251057086, "acc_norm": 0.37037037037037035, "acc_norm_stderr": 0.024870815251057086 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4523809523809524, "acc_stderr": 0.044518079590553275, "acc_norm": 0.4523809523809524, "acc_norm_stderr": 0.044518079590553275 }, "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": 0.6548387096774193, "acc_stderr": 0.02704574657353433, "acc_norm": 0.6548387096774193, "acc_norm_stderr": 0.02704574657353433 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.47783251231527096, "acc_stderr": 0.03514528562175008, "acc_norm": 0.47783251231527096, "acc_norm_stderr": 0.03514528562175008 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.6, "acc_stderr": 0.049236596391733084, "acc_norm": 0.6, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.696969696969697, "acc_stderr": 0.03588624800091706, "acc_norm": 0.696969696969697, "acc_norm_stderr": 0.03588624800091706 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7575757575757576, "acc_stderr": 0.030532892233932015, "acc_norm": 0.7575757575757576, "acc_norm_stderr": 0.030532892233932015 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.844559585492228, "acc_stderr": 0.02614848346915332, "acc_norm": 0.844559585492228, "acc_norm_stderr": 0.02614848346915332 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5769230769230769, "acc_stderr": 0.025049197876042345, "acc_norm": 0.5769230769230769, "acc_norm_stderr": 0.025049197876042345 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2851851851851852, "acc_stderr": 0.027528599210340492, "acc_norm": 0.2851851851851852, "acc_norm_stderr": 0.027528599210340492 }, "harness|hendrycksTest-high_school_microeconomics|
