open-llm-leaderboard-old/details_pleisto__yuren-13b-chatml
收藏数据集概述
该数据集是在对模型 pleisto/yuren-13b-chatml 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一个特定的分割,分割名称使用运行的时间戳。
- "train" 分割始终指向最新的结果。
- 额外的 "results" 配置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。
最新结果
以下是 2024-02-02T14:25:58.778785 运行的最新结果:
python { "all": { "acc": 0.5609180402171289, "acc_stderr": 0.033689189023125767, "acc_norm": 0.5665108554666364, "acc_norm_stderr": 0.03439957265639205, "mc1": 0.29253365973072215, "mc1_stderr": 0.015925597445286165, "mc2": 0.42324311782084495, "mc2_stderr": 0.014813023987866733 }, "harness|arc:challenge|25": { "acc": 0.49658703071672355, "acc_stderr": 0.014611050403244077, "acc_norm": 0.5307167235494881, "acc_norm_stderr": 0.014583792546304037 }, "harness|hellaswag|10": { "acc": 0.5807608046205935, "acc_stderr": 0.004924261467934419, "acc_norm": 0.7803226448914559, "acc_norm_stderr": 0.004131818797713882 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.31, "acc_stderr": 0.046482319871173156, "acc_norm": 0.31, "acc_norm_stderr": 0.046482319871173156 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5259259259259259, "acc_stderr": 0.04313531696750574, "acc_norm": 0.5259259259259259, "acc_norm_stderr": 0.04313531696750574 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.4934210526315789, "acc_stderr": 0.04068590050224971, "acc_norm": 0.4934210526315789, "acc_norm_stderr": 0.04068590050224971 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.56, "acc_stderr": 0.04988876515698589, "acc_norm": 0.56, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5735849056603773, "acc_stderr": 0.03043779434298305, "acc_norm": 0.5735849056603773, "acc_norm_stderr": 0.03043779434298305 }, "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": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.47, "acc_stderr": 0.050161355804659205, "acc_norm": 0.47, "acc_norm_stderr": 0.050161355804659205 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5086705202312138, "acc_stderr": 0.03811890988940412, "acc_norm": 0.5086705202312138, "acc_norm_stderr": 0.03811890988940412 }, "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": 0.74, "acc_stderr": 0.04408440022768078, "acc_norm": 0.74, "acc_norm_stderr": 0.04408440022768078 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.425531914893617, "acc_stderr": 0.03232146916224467, "acc_norm": 0.425531914893617, "acc_norm_stderr": 0.03232146916224467 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.34210526315789475, "acc_stderr": 0.044629175353369376, "acc_norm": 0.34210526315789475, "acc_norm_stderr": 0.044629175353369376 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5103448275862069, "acc_stderr": 0.04165774775728763, "acc_norm": 0.5103448275862069, "acc_norm_stderr": 0.04165774775728763 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.32275132275132273, "acc_stderr": 0.024078943243597016, "acc_norm": 0.32275132275132273, "acc_norm_stderr": 0.024078943243597016 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3333333333333333, "acc_stderr": 0.04216370213557835, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.04216370213557835 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6645161290322581, "acc_stderr": 0.026860206444724356, "acc_norm": 0.6645161290322581, "acc_norm_stderr": 0.026860206444724356 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4187192118226601, "acc_stderr": 0.03471192860518468, "acc_norm": 0.4187192118226601, "acc_norm_stderr": 0.03471192860518468 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.61, "acc_stderr": 0.04902071300001975, "acc_norm": 0.61, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.703030303030303, "acc_stderr": 0.035679697722680495, "acc_norm": 0.703030303030303, "acc_norm_stderr": 0.035679697722680495 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7070707070707071, "acc_stderr": 0.03242497958178815, "acc_norm": 0.7070707070707071, "acc_norm_stderr": 0.03242497958178815 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7616580310880829, "acc_stderr": 0.030748905363909878, "acc_norm": 0.7616580310880829, "acc_norm_stderr": 0.030748905363909878 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5538461538461539, "acc_stderr": 0.02520357177302833, "acc_norm": 0.5538461538461539, "acc_norm_stderr": 0.02520357177302833 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3148148148148148, "acc_stderr": 0.028317533496066468, "acc_norm": 0.3148148148148148, "acc_norm_stderr": 0.028317533496066468 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.5672268907563025,



