open-llm-leaderboard-old/details_arvindanand__ValidateAI-2-33B-AT
收藏数据集概述
数据集简介
该数据集是在评估模型 arvindanand/ValidateAI-2-33B-AT 在 Open LLM Leaderboard 上的自动创建的。数据集包含 63 个配置，每个配置对应一个评估任务。
数据集结构
- 配置数量：63 个配置
- 数据来源：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。
- 最新结果："train" 分割总是指向最新的结果。
- 结果汇总：一个额外的配置 "results" 存储所有运行的汇总结果，用于计算和显示在 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_arvindanand__ValidateAI-2-33B-AT", "harness_winogrande_5", split="train")
最新结果
以下是 2024-04-11T10:40:11.745619 运行的最新结果：
python { "all": { "acc": 0.438052988517656, "acc_stderr": 0.0346314972067509, "acc_norm": 0.438872048721612, "acc_norm_stderr": 0.035346165655504726, "mc1": 0.29008567931456547, "mc1_stderr": 0.01588623687420952, "mc2": 0.444421475747165, "mc2_stderr": 0.015059232903143193 }, "harness|arc:challenge|25": { "acc": 0.42918088737201365, "acc_stderr": 0.014464085894870653, "acc_norm": 0.4598976109215017, "acc_norm_stderr": 0.014564318856924848 }, "harness|hellaswag|10": { "acc": 0.47102170882294364, "acc_stderr": 0.004981394110706142, "acc_norm": 0.6288587930691097, "acc_norm_stderr": 0.004821228034624855 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.3333333333333333, "acc_stderr": 0.04072314811876837, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.04072314811876837 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.48026315789473684, "acc_stderr": 0.040657710025626057, "acc_norm": 0.48026315789473684, "acc_norm_stderr": 0.040657710025626057 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.47, "acc_stderr": 0.05016135580465919, "acc_norm": 0.47, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.4075471698113208, "acc_stderr": 0.030242233800854498, "acc_norm": 0.4075471698113208, "acc_norm_stderr": 0.030242233800854498 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.3611111111111111, "acc_stderr": 0.04016660030451232, "acc_norm": 0.3611111111111111, "acc_norm_stderr": 0.04016660030451232 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.46, "acc_stderr": 0.05009082659620332, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.32, "acc_stderr": 0.04688261722621504, "acc_norm": 0.32, "acc_norm_stderr": 0.04688261722621504 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.36416184971098264, "acc_stderr": 0.03669072477416907, "acc_norm": 0.36416184971098264, "acc_norm_stderr": 0.03669072477416907 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.28431372549019607, "acc_stderr": 0.04488482852329017, "acc_norm": 0.28431372549019607, "acc_norm_stderr": 0.04488482852329017 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.73, "acc_stderr": 0.044619604333847394, "acc_norm": 0.73, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.39148936170212767, "acc_stderr": 0.031907012423268113, "acc_norm": 0.39148936170212767, "acc_norm_stderr": 0.031907012423268113 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.3157894736842105, "acc_stderr": 0.043727482902780064, "acc_norm": 0.3157894736842105, "acc_norm_stderr": 0.043727482902780064 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.4827586206896552, "acc_stderr": 0.04164188720169377, "acc_norm": 0.4827586206896552, "acc_norm_stderr": 0.04164188720169377 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3941798941798942, "acc_stderr": 0.025167982333894143, "acc_norm": 0.3941798941798942, "acc_norm_stderr": 0.025167982333894143 }, "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": 0.22, "acc_stderr": 0.041633319989322695, "acc_norm": 0.22, "acc_norm_stderr": 0.041633319989322695 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.4612903225806452, "acc_stderr": 0.028358634859836928, "acc_norm": 0.4612903225806452, "acc_norm_stderr": 0.028358634859836928 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.3103448275862069, "acc_stderr": 0.03255086769970103, "acc_norm": 0.3103448275862069, "acc_norm_stderr": 0.03255086769970103 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.66, "acc_stderr": 0.04760952285695237, "acc_norm": 0.66, "acc_norm_stderr": 0.04760952285695237 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.5393939393939394, "acc_stderr": 0.03892207016552012, "acc_norm": 0.5393939393939394, "acc_norm_stderr": 0.03892207016552012 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.4797979797979798, "acc_stderr": 0.0355944356556392, "acc_norm": 0.4797979797979798, "acc_norm_stderr": 0.0355944356556392 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.39378238341968913, "acc_stderr": 0.03526077095548237, "acc_norm": 0.39378238341968913, "acc_norm_stderr": 0.03526077095548237 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.36153846153846153, "acc_stderr": 0.024359581465396987, "acc_norm": 0.36153846153846153, "acc_norm_stderr": 0.024359581465396987 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3592592592592593, "acc_stderr": 0.029252905927251
