open-llm-leaderboard-old/details_abhishek__autotrain-cei9g-ag3pe
收藏数据集概述
数据集来源
该数据集是在模型 abhishek/autotrain-cei9g-ag3pe 在 Open LLM Leaderboard 上的评估运行期间自动创建的。
数据集结构
- 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_abhishek__autotrain-cei9g-ag3pe", "harness_winogrande_5", split="train")
最新结果
以下是 2024-04-03T21:14:05.930463 运行 的最新结果: python { "all": { "acc": 0.6736877007607083, "acc_stderr": 0.0313355105728808, "acc_norm": 0.6746612110413659, "acc_norm_stderr": 0.03196744667705667, "mc1": 0.38555691554467564, "mc1_stderr": 0.017038839010591667, "mc2": 0.5284862927646511, "mc2_stderr": 0.015508123085277731 }, "harness|arc:challenge|25": { "acc": 0.5930034129692833, "acc_stderr": 0.01435639941800912, "acc_norm": 0.613481228668942, "acc_norm_stderr": 0.014230084761910473 }, "harness|hellaswag|10": { "acc": 0.6709818761202948, "acc_stderr": 0.004688963175758127, "acc_norm": 0.8478390758812986, "acc_norm_stderr": 0.003584427490579376 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.4, "acc_stderr": 0.04923659639173309, "acc_norm": 0.4, "acc_norm_stderr": 0.04923659639173309 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.674074074074074, "acc_stderr": 0.040491220417025055, "acc_norm": 0.674074074074074, "acc_norm_stderr": 0.040491220417025055 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7763157894736842, "acc_stderr": 0.03391160934343604, "acc_norm": 0.7763157894736842, "acc_norm_stderr": 0.03391160934343604 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.62, "acc_stderr": 0.04878317312145633, "acc_norm": 0.62, "acc_norm_stderr": 0.04878317312145633 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7169811320754716, "acc_stderr": 0.027724236492700918, "acc_norm": 0.7169811320754716, "acc_norm_stderr": 0.027724236492700918 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7986111111111112, "acc_stderr": 0.033536474697138406, "acc_norm": 0.7986111111111112, "acc_norm_stderr": 0.033536474697138406 }, "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": 0.53, "acc_stderr": 0.050161355804659205, "acc_norm": 0.53, "acc_norm_stderr": 0.050161355804659205 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.39, "acc_stderr": 0.04902071300001974, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001974 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6763005780346821, "acc_stderr": 0.03567603799639172, "acc_norm": 0.6763005780346821, "acc_norm_stderr": 0.03567603799639172 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4215686274509804, "acc_stderr": 0.04913595201274498, "acc_norm": 0.4215686274509804, "acc_norm_stderr": 0.04913595201274498 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.78, "acc_stderr": 0.04163331998932262, "acc_norm": 0.78, "acc_norm_stderr": 0.04163331998932262 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.625531914893617, "acc_stderr": 0.03163910665367291, "acc_norm": 0.625531914893617, "acc_norm_stderr": 0.03163910665367291 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5263157894736842, "acc_stderr": 0.046970851366478626, "acc_norm": 0.5263157894736842, "acc_norm_stderr": 0.046970851366478626 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6, "acc_stderr": 0.040824829046386284, "acc_norm": 0.6, "acc_norm_stderr": 0.040824829046386284 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4126984126984127, "acc_stderr": 0.02535574126305528, "acc_norm": 0.4126984126984127, "acc_norm_stderr": 0.02535574126305528 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.42063492063492064, "acc_stderr": 0.04415438226743744, "acc_norm": 0.42063492063492064, "acc_norm_stderr": 0.04415438226743744 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.44, "acc_stderr": 0.04988876515698589, "acc_norm": 0.44, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7967741935483871, "acc_stderr": 0.02289168798455495, "acc_norm": 0.7967741935483871, "acc_norm_stderr": 0.02289168798455495 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4729064039408867, "acc_stderr": 0.03512819077876105, "acc_norm": 0.4729064039408867, "acc_norm_stderr": 0.03512819077876105 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.66, "acc_stderr": 0.04760952285695237, "acc_norm": 0.66, "acc_norm_stderr": 0.04760952285695237 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7696969696969697, "acc_stderr": 0.03287666758603489, "acc_norm": 0.7696969696969697, "acc_norm_stderr": 0.03287666758603489 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8686868686868687, "acc_stderr": 0.02406315641682252, "acc_norm": 0.8686868686868687, "acc_norm_stderr": 0.02406315641682252 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9222797927461139, "acc_stderr": 0.01932180555722315, "acc_norm": 0.9222797927461139, "acc_norm_stderr": 0.01932180555722315 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6564102564102564, "acc_stderr": 0.024078696580635477, "acc_norm": 0.6564102564102564, "acc_norm_stderr": 0.024078696580635477 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.37407407407407406, "acc_stderr": 0.029502861128955286, "acc_norm": 0.37407407407407406, "acc_norm_stderr": 0.029502861128955286 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.7310924369747899, "acc_stderr": 0.028801392193631273, "acc_norm": 0.7310924369747899, "acc_norm_stderr": 0.028801392193631273 }, "harness|hendrycksTest-high_school_physics|5": { "acc": 0.4105960264900662, "acc_stderr": 0.04016689594849927, "acc_norm": 0.4105960264900662, "acc_norm_stderr": 0.04016689594849927 }, "harness|hendrycksTest-high_school_psychology|5": { "acc": 0.8422018348623853, "acc_stderr": 0.015630022970092444, "acc_norm": 0.8422018348623853, "acc_norm_stderr": 0.015630022970092444 }, "harness|hendrycksTest-high_school_statistics|5": { "acc": 0.5, "acc_stderr": 0.034099716973523674, "acc_norm": 0.5, "acc_norm_stderr": 0.034099716973523674 }, "harness|hendrycksTest-high_school_us_history|5": { "acc": 0.8529411764705882, "acc_stderr": 0.02485747808025046, "acc_norm": 0.8529411764705882, "acc_norm_stderr": 0.02485747808025046 }, "harness|hendrycksTest-high_school_world_history|5": { "acc": 0.8649789029535865, "acc_stderr": 0.022245776632003694, "acc_norm": 0.8649789029535865, "acc_norm_stderr": 0.022245776632003694 }, "harness|hendrycksTest-human_aging|5": { "acc": 0.726457399103139, "acc_stderr": 0.029918586707798827, "acc_norm": 0.726457399103139, "acc_norm_stderr": 0.029918586707798827 }, "harness|hendrycksTest-human_sexuality|5": { "acc": 0.7709923664122137, "acc_stderr": 0.036853466317118506, "acc_norm": 0.7709923664122137, "acc_norm_stderr": 0.036853466317118506 }, "harness|hendrycksTest-international_law|5": { "acc": 0.8760330578512396, "acc_stderr": 0.030083098716035202, "acc_norm": 0.8760330578512396, "acc_norm_stderr": 0.030083098716035202 }, "harness|hendrycksTest-jurisprudence|5": { "acc": 0.8148148148148148, "acc_stderr": 0.03755265865037182, "acc_norm": 0.8148148148148148, "acc_norm_stderr": 0.03755265865037182 }, "harness|hendrycksTest-logical_fallacies|5": { "acc": 0.7791411042944786, "acc_stderr": 0.03259177392742178, "acc_norm": 0.7791411042944786, "acc_norm_stderr": 0.03259177392742178 }, "harness|hendrycksTest-machine_learning|5": { "acc": 0.45535714285714285, "acc_stderr": 0.04726835553719099, "acc_norm": 0.45535714285714285, "acc_norm_stderr": 0.04726835553719099 }, "harness|hendrycksTest-management|5": { "acc": 0.8252427184466019, "acc_stderr": 0.03760178006026621, "acc_norm": 0.8252427184466019, "acc_norm_stderr": 0.03760178006026621 }, "harness|hendrycksTest-marketing|5": { "acc": 0.9017094017094017, "acc_stderr": 0.019503444900757567, "acc_norm": 0.9017094017094017, "acc_norm_stderr": 0.019503444900757567 }, "harness|hendrycksTest-medical_genetics|5": { "acc": 0.78, "acc_stderr": 0.04163331998932261, "acc_norm": 0.78, "acc_norm_stderr": 0.04163331998932261 }, "harness|hendrycksTest-miscellaneous|5": { "acc": 0.8454661558109834, "acc_stderr": 0.012925773495095962, "acc_norm": 0.8454661558109834, "acc_norm_stderr": 0.012925773495095962 }, "harness|hendrycksTest-moral_disputes|5": { "acc": 0.7485549132947977, "acc_stderr": 0.023357365785874037, "acc_norm": 0.7485549132947977, "acc_norm_stderr": 0.023357365785874037 }, "harness|hendrycksTest-moral_scenarios|5": { "acc": 0.43575418994413406, "acc_stderr": 0.01658388195860239, "acc_norm": 0.43575418994413406, "acc_norm_stderr": 0.01658388195860239 }, "harness|hendrycksTest-nutrition|5": { "acc": 0.7549019607843137, "acc_stderr": 0.02463004897982478, "acc_norm": 0.7549019607843137, "acc_norm_stderr": 0.02463004897982478 }, "harness|hendrycksTest-philosophy|5": { "acc": 0.7620578778135049, "acc_stderr": 0.024185150647818707, "acc_norm": 0.7620578778135049, "acc_norm_stderr": 0.024185150647818707 }, "harness|hendrycksTest-prehistory|5": { "acc": 0.7901234567901234, "acc_stderr": 0.022658344085981375, "acc_norm": 0.7901234567901234, "acc_norm_stderr": 0.022658344085981375 }, "harness|hendrycksTest-professional_accounting|5": { "acc": 0.5212765957446809, "acc_stderr": 0.029800481645628693, "acc_norm": 0.5212765957446809, "acc_norm_stderr": 0.029800481645628693 }, "harness|hendrycksTest-professional_law|5": { "acc": 0.4934810951760104, "acc_stderr": 0.012769150688867503, "acc_norm": 0.4934810951760104, "acc_norm_stderr": 0.012769150688867503 }, "harness|hendrycksTest-professional_medicine|5": { "acc": 0.7205882352941176, "acc_stderr": 0.027257202606114948, "acc_norm": 0.7205882352941176, "acc_norm_stderr": 0.027257202606114948 }, "harness|hendrycksTest-professional_psychology|5": { "acc": 0.7254901960784313, "acc_stderr": 0.018054027458815198, "acc_norm": 0.7254901960784313, "acc_norm_stderr": 0.018054027458815198 }, "harness|hendrycksTest-public_relations|5": { "acc": 0.6818181818181818, "acc_stderr": 0.04461272175910507, "acc_norm": 0.6818181818181818, "acc_norm_stderr": 0.04461272175910507 }, "harness|hendrycksTest-security_studies|5": { "acc": 0.7795918367346939, "acc_stderr": 0.02653704531214529, "acc_norm": 0.7795918367346939, "acc_norm_stderr": 0.02653704531214529 }, "harness|hendrycksTest-sociology|5": { "acc": 0.8756218905472637, "acc_stderr": 0.023335401790166327, "acc_norm": 0.8756218905472637, "acc_norm_stderr": 0.023335401790166327 }, "harness|hendrycksTest-us_foreign_policy|5": { "acc": 0.87, "acc_stderr": 0.033799766898963086, "acc_norm": 0.87, "acc_norm_stderr": 0.033799766898963086 }, "harness|hendrycksTest-virology|5": { "acc": 0.5120481927710844, "acc_stderr": 0.03891364495835817, "acc_norm": 0.5120481927710844, "acc_norm_stderr": 0.03891364495835817 }, "harness|hendrycksTest-world_religions|5": { "acc": 0.8654970760233918, "acc_stderr": 0.026168221344662297, "acc_norm": 0.8654970760233918, "acc_norm_stderr": 0.026168221344662297 }, "harness|truthfulqa:mc|0": { "mc1": 0.38555691554467564, "mc1_stderr": 0.017038839010591667, "mc2": 0.5284862927646511, "mc2_stderr": 0.015508123085277731 }, "harness|winogrande|5": { "acc": 0.7829518547750592, "acc_stderr": 0.011585871710209408 }, "harness|gsm8k|5": { "acc": 0.7043214556482184, "acc_stderr": 0.012570068947898779 } }



