open-llm-leaderboard-old/details_steve-cse__MelloGPT
收藏数据集概述
该数据集是在对模型 steve-cse/MelloGPT 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。
- "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_steve-cse__MelloGPT", "harness_winogrande_5", split="train")
最新结果
以下是 2023-12-16T18:07:59.704375 运行的最新结果：
python { "all": { "acc": 0.5580941639624716, "acc_stderr": 0.03400113351875304, "acc_norm": 0.5629530798562845, "acc_norm_stderr": 0.03471812426856797, "mc1": 0.38555691554467564, "mc1_stderr": 0.017038839010591673, "mc2": 0.5560955080575972, "mc2_stderr": 0.014788612119825833 }, "harness|arc:challenge|25": { "acc": 0.5247440273037542, "acc_stderr": 0.014593487694937738, "acc_norm": 0.53839590443686, "acc_norm_stderr": 0.01456824555029636 }, "harness|hellaswag|10": { "acc": 0.5646285600477993, "acc_stderr": 0.004947922692688834, "acc_norm": 0.761202947619996, "acc_norm_stderr": 0.004254771367531346 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.39, "acc_stderr": 0.04902071300001975, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.4074074074074074, "acc_stderr": 0.04244633238353229, "acc_norm": 0.4074074074074074, "acc_norm_stderr": 0.04244633238353229 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5460526315789473, "acc_stderr": 0.04051646342874142, "acc_norm": 0.5460526315789473, "acc_norm_stderr": 0.04051646342874142 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.49, "acc_stderr": 0.05024183937956911, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956911 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6113207547169811, "acc_stderr": 0.030000485448675986, "acc_norm": 0.6113207547169811, "acc_norm_stderr": 0.030000485448675986 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6041666666666666, "acc_stderr": 0.04089465449325582, "acc_norm": 0.6041666666666666, "acc_norm_stderr": 0.04089465449325582 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.4, "acc_stderr": 0.049236596391733084, "acc_norm": 0.4, "acc_norm_stderr": 0.049236596391733084 }, "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": 0.5549132947976878, "acc_stderr": 0.03789401760283648, "acc_norm": 0.5549132947976878, "acc_norm_stderr": 0.03789401760283648 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.30392156862745096, "acc_stderr": 0.045766654032077636, "acc_norm": 0.30392156862745096, "acc_norm_stderr": 0.045766654032077636 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.7, "acc_stderr": 0.046056618647183814, "acc_norm": 0.7, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.48936170212765956, "acc_stderr": 0.03267862331014063, "acc_norm": 0.48936170212765956, "acc_norm_stderr": 0.03267862331014063 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.3508771929824561, "acc_stderr": 0.04489539350270699, "acc_norm": 0.3508771929824561, "acc_norm_stderr": 0.04489539350270699 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5586206896551724, "acc_stderr": 0.04137931034482757, "acc_norm": 0.5586206896551724, "acc_norm_stderr": 0.04137931034482757 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3783068783068783, "acc_stderr": 0.024976954053155254, "acc_norm": 0.3783068783068783, "acc_norm_stderr": 0.024976954053155254 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.36507936507936506, "acc_stderr": 0.043062412591271526, "acc_norm": 0.36507936507936506, "acc_norm_stderr": 0.043062412591271526 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "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": 0.43349753694581283, "acc_stderr": 0.03486731727419872, "acc_norm": 0.43349753694581283, "acc_norm_stderr": 0.03486731727419872 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.54, "acc_stderr": 0.05009082659620332, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6727272727272727, "acc_stderr": 0.03663974994391244, "acc_norm": 0.6727272727272727, "acc_norm_stderr": 0.03663974994391244 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7272727272727273, "acc_stderr": 0.03173071239071724, "acc_norm": 0.7272727272727273, "acc_norm_stderr": 0.03173071239071724 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7409326424870466, "acc_stderr": 0.031618779179354115, "acc_norm": 0.7409326424870466, "acc_norm_stderr": 0.031618779179354115 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5307692307692308, "acc_stderr": 0.025302958890850154, "acc_norm": 0.5307692307692308, "acc_norm_stderr": 0.025302958890850154 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3074074074074074, "acc_stderr": 0.028133252578815635, "acc_norm": 0.3074074074074074, "acc_norm_stderr": 0.028133252578815635 }, "harness|hendrycksTest-
