open-llm-leaderboard-old/details_Xenon1__Xenon-4
收藏数据集概述
数据集来源
该数据集是在对模型 Xenon1/Xenon-4 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。
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。
额外配置
一个额外的配置 "results" 存储了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-4", "harness_winogrande_5", split="train")
最新结果
最新运行结果
这些是最新的结果，来自 2024-02-04T06:47:30.573744 的运行：
python { "all": { "acc": 0.5969673597339272, "acc_stderr": 0.0332252879660183, "acc_norm": 0.6047382841391643, "acc_norm_stderr": 0.033940427206963365, "mc1": 0.4283965728274174, "mc1_stderr": 0.017323088597314754, "mc2": 0.613129800259979, "mc2_stderr": 0.016329535721420842 }, "harness|arc:challenge|25": { "acc": 0.5435153583617748, "acc_stderr": 0.014555949760496442, "acc_norm": 0.6015358361774744, "acc_norm_stderr": 0.014306946052735569 }, "harness|hellaswag|10": { "acc": 0.6468830910177256, "acc_stderr": 0.004769618829196511, "acc_norm": 0.8307110137422824, "acc_norm_stderr": 0.0037424055874098806 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.33, "acc_stderr": 0.04725815626252606, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252606 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5851851851851851, "acc_stderr": 0.04256193767901408, "acc_norm": 0.5851851851851851, "acc_norm_stderr": 0.04256193767901408 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6381578947368421, "acc_stderr": 0.03910525752849724, "acc_norm": 0.6381578947368421, "acc_norm_stderr": 0.03910525752849724 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.49, "acc_stderr": 0.05024183937956912, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6754716981132075, "acc_stderr": 0.028815615713432115, "acc_norm": 0.6754716981132075, "acc_norm_stderr": 0.028815615713432115 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6805555555555556, "acc_stderr": 0.038990736873573344, "acc_norm": 0.6805555555555556, "acc_norm_stderr": 0.038990736873573344 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.45, "acc_stderr": 0.05, "acc_norm": 0.45, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.55, "acc_stderr": 0.05, "acc_norm": 0.55, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.37, "acc_stderr": 0.04852365870939098, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939098 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5606936416184971, "acc_stderr": 0.03784271932887468, "acc_norm": 0.5606936416184971, "acc_norm_stderr": 0.03784271932887468 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4019607843137255, "acc_stderr": 0.04878608714466996, "acc_norm": 0.4019607843137255, "acc_norm_stderr": 0.04878608714466996 }, "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": 0.502127659574468, "acc_stderr": 0.03268572658667492, "acc_norm": 0.502127659574468, "acc_norm_stderr": 0.03268572658667492 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.47368421052631576, "acc_stderr": 0.046970851366478626, "acc_norm": 0.47368421052631576, "acc_norm_stderr": 0.046970851366478626 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6275862068965518, "acc_stderr": 0.04028731532947559, "acc_norm": 0.6275862068965518, "acc_norm_stderr": 0.04028731532947559 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3862433862433862, "acc_stderr": 0.025075981767601677, "acc_norm": 0.3862433862433862, "acc_norm_stderr": 0.025075981767601677 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.42857142857142855, "acc_stderr": 0.04426266681379909, "acc_norm": 0.42857142857142855, "acc_norm_stderr": 0.04426266681379909 }, "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": 0.6580645161290323, "acc_stderr": 0.026985289576552742, "acc_norm": 0.6580645161290323, "acc_norm_stderr": 0.026985289576552742 }, "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": 0.703030303030303, "acc_stderr": 0.0356796977226805, "acc_norm": 0.703030303030303, "acc_norm_stderr": 0.0356796977226805 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7474747474747475, "acc_stderr": 0.03095405547036589, "acc_norm": 0.7474747474747475, "acc_norm_stderr": 0.03095405547036589 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8393782383419689, "acc_stderr": 0.026499057701397457, "acc_norm": 0.8393782383419689, "acc_norm_stderr": 0.026499057701397457 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6, "acc_stderr": 0.02483881198803316, "acc_norm": 0.6, "acc_norm_stderr": 0.02483881198803316 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.28888888888888886, "acc_stderr": 0.027634907264178544, "acc_norm": 0.28888888888888886, "acc_norm_stderr": 0.027634907264178544 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.6470588235294118, "acc_stderr": 0.031041941304059278, "acc_norm": 0.6470588235294118, "acc_norm_stderr": 0.031041941304059278
