open-llm-leaderboard-old/details_Weyaxi__HelpSteer-filtered-Solar-Instruct
收藏数据集概述
数据集摘要
该数据集是在模型Weyaxi/HelpSteer-filtered-Solar-Instruct的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_Weyaxi__HelpSteer-filtered-Solar-Instruct", "harness_winogrande_5", split="train")
最新结果
以下是2024-01-15T17:25:12.047837的最新结果：
python { "all": { "acc": 0.6427219840393912, "acc_stderr": 0.0319380448227668, "acc_norm": 0.6461776033755803, "acc_norm_stderr": 0.032576281401967964, "mc1": 0.33047735618115054, "mc1_stderr": 0.0164667696136983, "mc2": 0.46234588692773587, "mc2_stderr": 0.015244437978733195 }, "harness|arc:challenge|25": { "acc": 0.5878839590443686, "acc_stderr": 0.014383915302225407, "acc_norm": 0.6313993174061433, "acc_norm_stderr": 0.0140978106780422 }, "harness|hellaswag|10": { "acc": 0.6395140410276837, "acc_stderr": 0.0047916019756127646, "acc_norm": 0.8305118502290381, "acc_norm_stderr": 0.0037441574425365583 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.33, "acc_stderr": 0.04725815626252605, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252605 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5777777777777777, "acc_stderr": 0.04266763404099582, "acc_norm": 0.5777777777777777, "acc_norm_stderr": 0.04266763404099582 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6973684210526315, "acc_stderr": 0.03738520676119668, "acc_norm": 0.6973684210526315, "acc_norm_stderr": 0.03738520676119668 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.65, "acc_stderr": 0.0479372485441102, "acc_norm": 0.65, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6792452830188679, "acc_stderr": 0.028727502957880274, "acc_norm": 0.6792452830188679, "acc_norm_stderr": 0.028727502957880274 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7361111111111112, "acc_stderr": 0.03685651095897532, "acc_norm": 0.7361111111111112, "acc_norm_stderr": 0.03685651095897532 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.44, "acc_stderr": 0.04988876515698589, "acc_norm": 0.44, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795 }, "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": 0.6242774566473989, "acc_stderr": 0.036928207672648664, "acc_norm": 0.6242774566473989, "acc_norm_stderr": 0.036928207672648664 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.30392156862745096, "acc_stderr": 0.04576665403207763, "acc_norm": 0.30392156862745096, "acc_norm_stderr": 0.04576665403207763 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.79, "acc_stderr": 0.040936018074033256, "acc_norm": 0.79, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5872340425531914, "acc_stderr": 0.03218471141400351, "acc_norm": 0.5872340425531914, "acc_norm_stderr": 0.03218471141400351 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4473684210526316, "acc_stderr": 0.046774730044912, "acc_norm": 0.4473684210526316, "acc_norm_stderr": 0.046774730044912 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6137931034482759, "acc_stderr": 0.04057324734419035, "acc_norm": 0.6137931034482759, "acc_norm_stderr": 0.04057324734419035 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.42592592592592593, "acc_stderr": 0.025467149045469536, "acc_norm": 0.42592592592592593, "acc_norm_stderr": 0.025467149045469536 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4126984126984127, "acc_stderr": 0.04403438954768177, "acc_norm": 0.4126984126984127, "acc_norm_stderr": 0.04403438954768177 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.4, "acc_stderr": 0.04923659639173309, "acc_norm": 0.4, "acc_norm_stderr": 0.04923659639173309 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7806451612903226, "acc_stderr": 0.023540799358723295, "acc_norm": 0.7806451612903226, "acc_norm_stderr": 0.023540799358723295 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.43349753694581283, "acc_stderr": 0.03486731727419872, "acc_norm": 0.43349753694581283, "acc_norm_stderr": 0.03486731727419872 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.67, "acc_stderr": 0.047258156262526094, "acc_norm": 0.67, "acc_norm_stderr": 0.047258156262526094 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7878787878787878, "acc_stderr": 0.031922715695482995, "acc_norm": 0.7878787878787878, "acc_norm_stderr": 0.031922715695482995 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8535353535353535, "acc_stderr": 0.025190921114603915, "acc_norm": 0.8535353535353535, "acc_norm_stderr": 0.025190921114603915 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8963730569948186, "acc_stderr": 0.021995311963644234, "acc_norm": 0.8963730569948186, "acc_norm_stderr": 0.021995311963644234 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6666666666666666, "acc_stderr": 0.023901157979402534, "acc_norm": 0.6666666666666666, "acc_norm_stderr": 0.023901157979402534 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3592592592592593, "acc_stderr": 0.02925290592725198, "acc_norm": 0.3592592592592593, "acc_norm_stderr": 0
