open-llm-leaderboard-old/details_kyujinpy__PlatYi-34B-200k-Q-FastChat
收藏数据集概述
数据集摘要
该数据集是在对模型 kyujinpy/PlatYi-34B-200k-Q-FastChat 进行评估运行时自动创建的，评估结果发布在 Open LLM Leaderboard 上。
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，每次运行的详细结果可以在每个配置中找到，以运行的时间戳命名的特定分割形式存储。
- "train" 分割始终指向最新的结果。
- 额外的 "results" 配置存储所有运行的聚合结果，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_kyujinpy__PlatYi-34B-200k-Q-FastChat", "harness_winogrande_5", split="train")
最新结果
以下是 2023-12-10T08:30:20.014698 运行的最新结果：
python { "all": { "acc": 0.7630727247628006, "acc_stderr": 0.028221206890446823, "acc_norm": 0.770488792020382, "acc_norm_stderr": 0.028732290582792492, "mc1": 0.34761321909424725, "mc1_stderr": 0.016670769188897303, "mc2": 0.4838395775572536, "mc2_stderr": 0.014874467350764172 }, "harness|arc:challenge|25": { "acc": 0.613481228668942, "acc_stderr": 0.014230084761910471, "acc_norm": 0.6493174061433447, "acc_norm_stderr": 0.013944635930726097 }, "harness|hellaswag|10": { "acc": 0.6467835092611034, "acc_stderr": 0.004769924131304649, "acc_norm": 0.8445528779127663, "acc_norm_stderr": 0.003615898928269288 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.44, "acc_stderr": 0.04988876515698589, "acc_norm": 0.44, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.7185185185185186, "acc_stderr": 0.03885004245800253, "acc_norm": 0.7185185185185186, "acc_norm_stderr": 0.03885004245800253 }, "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": 0.79, "acc_stderr": 0.040936018074033256, "acc_norm": 0.79, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.8113207547169812, "acc_stderr": 0.02407999513006225, "acc_norm": 0.8113207547169812, "acc_norm_stderr": 0.02407999513006225 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8958333333333334, "acc_stderr": 0.025545239210256917, "acc_norm": 0.8958333333333334, "acc_norm_stderr": 0.025545239210256917 }, "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": 0.64, "acc_stderr": 0.048241815132442176, "acc_norm": 0.64, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7456647398843931, "acc_stderr": 0.0332055644308557, "acc_norm": 0.7456647398843931, "acc_norm_stderr": 0.0332055644308557 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.5686274509803921, "acc_stderr": 0.04928099597287534, "acc_norm": 0.5686274509803921, "acc_norm_stderr": 0.04928099597287534 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.8, "acc_stderr": 0.04020151261036846, "acc_norm": 0.8, "acc_norm_stderr": 0.04020151261036846 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.7829787234042553, "acc_stderr": 0.026947483121496228, "acc_norm": 0.7829787234042553, "acc_norm_stderr": 0.026947483121496228 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.6403508771929824, "acc_stderr": 0.04514496132873633, "acc_norm": 0.6403508771929824, "acc_norm_stderr": 0.04514496132873633 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.7517241379310344, "acc_stderr": 0.03600105692727771, "acc_norm": 0.7517241379310344, "acc_norm_stderr": 0.03600105692727771 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.7380952380952381, "acc_stderr": 0.022644212615525218, "acc_norm": 0.7380952380952381, "acc_norm_stderr": 0.022644212615525218 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5317460317460317, "acc_stderr": 0.04463112720677173, "acc_norm": 0.5317460317460317, "acc_norm_stderr": 0.04463112720677173 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.64, "acc_stderr": 0.04824181513244218, "acc_norm": 0.64, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.896774193548387, "acc_stderr": 0.017308381281034527, "acc_norm": 0.896774193548387, "acc_norm_stderr": 0.017308381281034527 }, "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": 0.83, "acc_stderr": 0.0377525168068637, "acc_norm": 0.83, "acc_norm_stderr": 0.0377525168068637 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8606060606060606, "acc_stderr": 0.027045948825865397, "acc_norm": 0.8606060606060606, "acc_norm_stderr": 0.027045948825865397 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.9444444444444444, "acc_stderr": 0.0163199507007674, "acc_norm": 0.9444444444444444, "acc_norm_stderr": 0.0163199507007674 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9637305699481865, "acc_stderr": 0.013492659751295127, "acc_norm": 0.9637305699481865, "acc_norm_stderr": 0.013492659751295127 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.8153846153846154, "acc_stderr": 0.0196716324131003, "acc_norm": 0.8153846153846154, "acc_norm_stderr": 0.0196716324131003 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.43703703703703706, "acc_stderr": 0.030242862397654, "acc_norm": 0.437037037037
