open-llm-leaderboard-old/details_BramVanroy__GEITje-7B-ultra
收藏数据集概述
该数据集是在对模型 BramVanroy/GEITje-7B-ultra 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。
- 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。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_BramVanroy__GEITje-7B-ultra", "harness_winogrande_5", split="train")
最新结果
以下是 2024-04-16T14:19:37.799734 运行的最新结果:
python { "all": { "acc": 0.49973971348930274, "acc_stderr": 0.03462291331440178, "acc_norm": 0.505065908628368, "acc_norm_stderr": 0.03538808262883265, "mc1": 0.36474908200734396, "mc1_stderr": 0.01685096106172012, "mc2": 0.5335711894508678, "mc2_stderr": 0.015369322407193318 }, "harness|arc:challenge|25": { "acc": 0.42406143344709896, "acc_stderr": 0.014441889627464398, "acc_norm": 0.454778156996587, "acc_norm_stderr": 0.014551507060836352 }, "harness|hellaswag|10": { "acc": 0.5594503087034455, "acc_stderr": 0.004954384702021659, "acc_norm": 0.7550288787094205, "acc_norm_stderr": 0.004291911350430705 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.48148148148148145, "acc_stderr": 0.043163785995113245, "acc_norm": 0.48148148148148145, "acc_norm_stderr": 0.043163785995113245 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.46710526315789475, "acc_stderr": 0.040601270352363966, "acc_norm": 0.46710526315789475, "acc_norm_stderr": 0.040601270352363966 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.47, "acc_stderr": 0.05016135580465919, "acc_norm": 0.47, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5245283018867924, "acc_stderr": 0.030735822206205608, "acc_norm": 0.5245283018867924, "acc_norm_stderr": 0.030735822206205608 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5, "acc_stderr": 0.04181210050035455, "acc_norm": 0.5, "acc_norm_stderr": 0.04181210050035455 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.41, "acc_stderr": 0.04943110704237102, "acc_norm": 0.41, "acc_norm_stderr": 0.04943110704237102 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.32, "acc_stderr": 0.04688261722621505, "acc_norm": 0.32, "acc_norm_stderr": 0.04688261722621505 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.4624277456647399, "acc_stderr": 0.0380168510452446, "acc_norm": 0.4624277456647399, "acc_norm_stderr": 0.0380168510452446 }, "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": 0.66, "acc_stderr": 0.04760952285695237, "acc_norm": 0.66, "acc_norm_stderr": 0.04760952285695237 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.40425531914893614, "acc_stderr": 0.03208115750788684, "acc_norm": 0.40425531914893614, "acc_norm_stderr": 0.03208115750788684 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2982456140350877, "acc_stderr": 0.043036840335373146, "acc_norm": 0.2982456140350877, "acc_norm_stderr": 0.043036840335373146 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.47586206896551725, "acc_stderr": 0.041618085035015295, "acc_norm": 0.47586206896551725, "acc_norm_stderr": 0.041618085035015295 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3544973544973545, "acc_stderr": 0.024636830602842, "acc_norm": 0.3544973544973545, "acc_norm_stderr": 0.024636830602842 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3333333333333333, "acc_stderr": 0.04216370213557836, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.04216370213557836 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.34, "acc_stderr": 0.04760952285695236, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695236 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.5870967741935483, "acc_stderr": 0.028009138125400387, "acc_norm": 0.5870967741935483, "acc_norm_stderr": 0.028009138125400387 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4088669950738916, "acc_stderr": 0.034590588158832314, "acc_norm": 0.4088669950738916, "acc_norm_stderr": 0.034590588158832314 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.46, "acc_stderr": 0.05009082659620332, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6303030303030303, "acc_stderr": 0.03769430314512567, "acc_norm": 0.6303030303030303, "acc_norm_stderr": 0.03769430314512567 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.6666666666666666, "acc_stderr": 0.033586181457325226, "acc_norm": 0.6666666666666666, "acc_norm_stderr": 0.033586181457325226 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.6994818652849741, "acc_stderr": 0.0330881859441575, "acc_norm": 0.6994818652849741, "acc_norm_stderr": 0.0330881859441575 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.48205128205128206, "acc_stderr": 0.025334667080954942, "acc_norm": 0.48205128205128206, "acc_norm_stderr": 0.025334667080954942 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3, "acc_stderr": 0.027940457136228402, "acc_norm": 0.3, "acc_norm_stderr": 0.027940457136228402 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.5126050420168067, "acc_stderr": 0.03246816765752174, "acc_norm": 0.5126050420168067, "acc_norm_stderr": 0.03246816765752174 }, "harness|hendrycksTest-high_school_physics|5": { "acc": 0.3509933774834437, "acc_stderr": 0.03896981964257375, "acc_norm": 0.3509933774834437, "acc_norm_stderr": 0.03896981964257375 }, "harness|hendrycksTest-high_school_psychology|5": { "acc": 0.6311926605504588, "acc_stderr": 0.020686227560729558, "acc_norm": 0.6311926605504588, "acc_norm_stderr": 0.020686227560729558 }, "harness|hendrycksTest-high_school_statistics|5": { "acc": 0.4537037037037037, "acc_stderr": 0.03395322726375797, "acc_norm": 0.4537037037037037, "acc_norm_stderr": 0.03395322726375797 }, "harness|hendrycksTest-high_school_us_history|5": { "acc": 0.5931372549019608, "acc_stderr": 0.03447891136353382, "acc_norm": 0.5931372549019608, "acc_norm_stderr": 0.03447891136353382 }, "harness|hendrycksTest-high_school_world_history|5": { "acc": 0.5907172995780591, "acc_stderr": 0.03200704183359592, "acc_norm": 0.5907172995780591, "acc_norm_stderr": 0.03200704183359592 }, "harness|hendrycksTest-human_aging|5": { "acc": 0.5605381165919282, "acc_stderr": 0.03331092511038179, "acc_norm": 0.5605381165919282, "acc_norm_stderr": 0.03331092511038179 }, "harness|hendrycksTest-human_sexuality|5": { "acc": 0.6030534351145038, "acc_stderr": 0.04291135671009224, "acc_norm": 0.6030534351145038, "acc_norm_stderr": 0.04291135671009224 }, "harness|hendrycksTest-international_law|5": { "acc": 0.6363636363636364, "acc_stderr": 0.043913262867240704, "acc_norm": 0.6363636363636364, "acc_norm_stderr": 0.043913262867240704 }, "harness|hendrycksTest-jurisprudence|5": { "acc": 0.5648148148148148, "acc_stderr": 0.04792898170907062, "acc_norm": 0.5648148148148148, "acc_norm_stderr": 0.04792898170907062 }, "harness|hendrycksTest-logical_fallacies|5": { "acc": 0.5828220858895705, "acc_stderr": 0.038741028598180814, "acc_norm": 0.5828220858895705, "acc_norm_stderr": 0.038741028598180814 }, "harness|hendrycksTest-machine_learning|5": { "acc": 0.32142857142857145, "acc_stderr": 0.04432804055291519, "acc_norm": 0.32142857142857145, "acc_norm_stderr": 0.04432804055291519 }, "harness|hendrycksTest-management|5": { "acc": 0.6407766990291263, "acc_stderr": 0.04750458399041695, "acc_norm": 0.6407766990291263, "acc_norm_stderr": 0.04750458399041695 }, "harness|hendrycksTest-marketing|5": { "acc": 0.7521367521367521, "acc_stderr": 0.028286324075564386, "acc_norm": 0.7521367521367521, "acc_norm_stderr": 0.028286324075564386 }, "harness|hendrycksTest-medical_genetics|5": { "acc": 0.55, "acc_stderr": 0.05, "acc_norm": 0.55, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-miscellaneous|5": { "acc": 0.669220945083014, "acc_stderr": 0.016824818462563746, "acc_norm": 0.669220945083014, "acc_norm_stderr": 0.016824818462563746 }, "harness|hendrycksTest-moral_disputes|5": { "acc": 0.5635838150289018, "acc_stderr": 0.026700545424943677, "acc_norm": 0.5635838150289018, "acc_norm_stderr": 0.026700545424943677 }, "harness|hendrycksTest-moral_scenarios|5": { "acc": 0.23016759776536314, "acc_stderr": 0.01407833925342582, "acc_norm": 0.23016759776536314, "acc_norm_stderr": 0.01407833925342582 }, "harness|hendrycksTest-nutrition|5": { "acc": 0.5620915032679739, "acc_stderr": 0.02840830202033269, "acc_norm": 0.5620915032679739, "acc_norm_stderr": 0.02840830202033269 }, "harness|hendrycksTest-philosophy|5": { "acc": 0.5852090032154341, "acc_stderr": 0.027982680459759563, "acc_norm": 0.5852090032154341, "acc_norm_stderr": 0.027982680459759563 }, "harness|hendrycksTest-prehistory|5": { "acc": 0.5277777777777778, "acc_stderr": 0.027777777777777797, "acc_norm": 0.5277777777777778, "acc_norm_stderr": 0.027777777777777797 }, "harness|hendrycksTest-professional_accounting|5": { "acc": 0.36879432624113473, "acc_stderr": 0.02878222756134725, "acc_norm": 0.36879432624113473, "acc_norm_stderr": 0.02878222756134725 }, "harness|hendrycksTest-professional_law|5": { "acc": 0.33376792698826596, "acc_stderr": 0.012043812655846142, "acc_norm": 0.33376792698826596, "acc_norm_stderr": 0.012043812655846142 }, "harness|hendrycksTest-professional_medicine|5": { "acc": 0.4963235294117647, "acc_stderr": 0.030372015885428195, "acc_norm": 0.4963235294117647, "acc_norm_stderr": 0.030372015885428195 }, "harness|hendrycksTest-professional_psychology|5": { "acc": 0.4852941176470588, "acc_stderr": 0.020219083895133924, "acc_norm": 0.4852941176470588, "acc_norm_stderr": 0.020219083895133924 }, "harness|hendrycksTest-public_relations|5": { "acc": 0.5545454545454546, "acc_stderr": 0.047605488214603246, "acc_norm": 0.5545454545454546, "acc_norm_stderr": 0.047605488214603246 }, "harness|hendrycksTest-security_studies|5": { "acc": 0.5673469387755102, "acc_stderr": 0.031717528240626645, "acc_norm": 0.5673469387755102, "acc_norm_stderr": 0.031717528240626645 }, "harness|hendrycksTest-sociology|5": { "acc": 0.7014925373134329, "acc_stderr": 0.03235743789355043, "acc_norm": 0.7014925373134329, "acc_norm_stderr": 0.03235743789355043 }, "harness|hendrycksTest-us_foreign_policy|5": { "acc": 0.7, "acc_stderr": 0.046056618647183814, "acc_norm": 0.7, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-virology|5": { "acc": 0.4457831325301205, "acc_stderr": 0.03869543323472101, "acc_norm": 0.4457831325301205, "acc_norm_stderr": 0.03869543323472101 }, "harness|hendrycksTest-world_religions|5": { "acc": 0.6432748538011696, "acc_stderr": 0.03674013002860954, "acc_norm": 0.6432748538011696, "acc_norm_stderr": 0.03674013002860954 }, "harness|truthfulqa:mc|0": { "mc1": 0.36474908200734396, "mc1_stderr": 0.01685096106172012, "mc2": 0.5335711894508678, "mc2_stderr": 0.015369322407193318 }, "harness|winogrande|5": { "acc": 0.7174427782162589, "acc_stderr": 0.012654062850971388 }, "harness|gsm8k|5": { "acc": 0.19408642911296436, "acc_stderr": 0.010893918308192424 } }
配置详情
-
config_name: harness_arc_challenge_25
- 数据文件:
- 分割: 2024_04_16T14_19_37.799734
- 路径: **/details_harness|arc:challenge|25_2024-04-16T14-19-37.799734.parquet
- 分割: latest
- 路径: **/details_harness|arc:challenge|25_2024-04-16T14-19-37.799734.parquet
- 分割: 2024_04_16T14_19_37.799734
- 数据文件:
-
config_name: harness_gsm8k_5
- 数据文件:
- 分割: 2024_04_16T14_19_37.799734
- 路径: **/details_harness|gsm8k|5_2024-04-16T14-19-37.799734.parquet
- 分割: latest
- 路径: **/details_harness|gsm8k|5_2024-04-16T14-19-37.799734.parquet
- 分割: 2024_04_16T14_19_37.799734
- 数据文件:
-
config_name: harness_hellaswag_10
- 数据文件:
- 分割: 2024_04_16T14_19_37.799734
- 路径: **/details_harness|hellaswag|10_2024-04-16T14-19-37.799734.parquet
- 分割: latest
- 路径: **/details_harness|hellaswag|10_2024-04-16T14-19-37.799734.parquet
- 分割: 2024_04_16T14_19_37.799734
- 数据文件:
-
config_name: harness_hendrycksTest_5
- 数据文件:
- 分割: 2024_04_16T14_19_37.799734
- 路径:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-global_facts|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-high_school_computer_science|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-high_school_european_history|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-high_school_geography|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-high_school_mathematics|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-high_school_physics|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-high_school_psychology|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-high_school_statistics|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-high_school_us_history|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-high_school_world_history|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-human_aging|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-human_sexuality|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-international_law|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-jurisprudence|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-logical_fallacies|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-machine_learning|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-management|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-marketing|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-medical_genetics|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-miscellaneous|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-moral_disputes|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-moral_scenarios|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-nutrition|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-philosophy|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-prehistory|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-professional_accounting|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-professional_law|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-professional_medicine|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-professional_psychology|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-public_relations|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-security_studies|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-sociology|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-us_foreign_policy|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-virology|5_2024-04-16T14-19-37.799734.parquet
- **/details_harness|hendrycksTest-world_religions|5_2024-04-16T14-19-37.799734.parquet
- 路径:
- 分割: 2024_04_16T14_19_37.799734
- 数据文件:



