open-llm-leaderboard-old/details_Cartinoe5930__DARE-Merging
收藏数据集概述
数据集简介
该数据集是在模型Cartinoe5930/DARE-Merging在Open LLM Leaderboard上的评估运行期间自动创建的。
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_Cartinoe5930__DARE-Merging", "harness_winogrande_5", split="train")
最新结果
以下是2024-01-23T15:09:50.545148运行的最新结果: python { "all": { "acc": 0.2372712195481079, "acc_stderr": 0.02996006519093449, "acc_norm": 0.23747207216886124, "acc_norm_stderr": 0.030741935495139164, "mc1": 0.2252141982864137, "mc1_stderr": 0.014623240768023493, "mc2": 0.48312740729573567, "mc2_stderr": 0.01641721201782194 }, "harness|arc:challenge|25": { "acc": 0.20051194539249148, "acc_stderr": 0.011700318050499377, "acc_norm": 0.2525597269624573, "acc_norm_stderr": 0.012696728980207706 }, "harness|hellaswag|10": { "acc": 0.2581159131647082, "acc_stderr": 0.004367037632204529, "acc_norm": 0.26110336586337385, "acc_norm_stderr": 0.004383384784038464 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.19, "acc_stderr": 0.03942772444036624, "acc_norm": 0.19, "acc_norm_stderr": 0.03942772444036624 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.2, "acc_stderr": 0.034554737023254366, "acc_norm": 0.2, "acc_norm_stderr": 0.034554737023254366 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.17763157894736842, "acc_stderr": 0.031103182383123398, "acc_norm": 0.17763157894736842, "acc_norm_stderr": 0.031103182383123398 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.26, "acc_stderr": 0.04408440022768079, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768079 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.2188679245283019, "acc_stderr": 0.02544786382510863, "acc_norm": 0.2188679245283019, "acc_norm_stderr": 0.02544786382510863 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2222222222222222, "acc_stderr": 0.03476590104304134, "acc_norm": 0.2222222222222222, "acc_norm_stderr": 0.03476590104304134 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.18, "acc_stderr": 0.038612291966536955, "acc_norm": 0.18, "acc_norm_stderr": 0.038612291966536955 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.15, "acc_stderr": 0.03588702812826372, "acc_norm": 0.15, "acc_norm_stderr": 0.03588702812826372 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.22, "acc_stderr": 0.04163331998932269, "acc_norm": 0.22, "acc_norm_stderr": 0.04163331998932269 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.2023121387283237, "acc_stderr": 0.030631145539198823, "acc_norm": 0.2023121387283237, "acc_norm_stderr": 0.030631145539198823 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.16666666666666666, "acc_stderr": 0.03708284662416542, "acc_norm": 0.16666666666666666, "acc_norm_stderr": 0.03708284662416542 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.2170212765957447, "acc_stderr": 0.02694748312149623, "acc_norm": 0.2170212765957447, "acc_norm_stderr": 0.02694748312149623 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.23684210526315788, "acc_stderr": 0.039994238792813365, "acc_norm": 0.23684210526315788, "acc_norm_stderr": 0.039994238792813365 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.22758620689655173, "acc_stderr": 0.03493950380131184, "acc_norm": 0.22758620689655173, "acc_norm_stderr": 0.03493950380131184 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.21693121693121692, "acc_stderr": 0.021227082449445062, "acc_norm": 0.21693121693121692, "acc_norm_stderr": 0.021227082449445062 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.2857142857142857, "acc_stderr": 0.040406101782088394, "acc_norm": 0.2857142857142857, "acc_norm_stderr": 0.040406101782088394 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.2, "acc_stderr": 0.04020151261036847, "acc_norm": 0.2, "acc_norm_stderr": 0.04020151261036847 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.20967741935483872, "acc_stderr": 0.023157879349083525, "acc_norm": 0.20967741935483872, "acc_norm_stderr": 0.023157879349083525 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.15270935960591134, "acc_stderr": 0.02530890453938063, "acc_norm": 0.15270935960591134, "acc_norm_stderr": 0.02530890453938063 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.24, "acc_stderr": 0.04292346959909284, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909284 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.21818181818181817, "acc_stderr": 0.03225078108306289, "acc_norm": 0.21818181818181817, "acc_norm_stderr": 0.03225078108306289 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.25757575757575757, "acc_stderr": 0.031156269519646836, "acc_norm": 0.25757575757575757, "acc_norm_stderr": 0.031156269519646836 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.19689119170984457, "acc_stderr": 0.028697873971860667, "acc_norm": 0.19689119170984457, "acc_norm_stderr": 0.028697873971860667 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.22564102564102564, "acc_stderr": 0.021193632525148543, "acc_norm": 0.22564102564102564, "acc_norm_stderr": 0.021193632525148543 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2111111111111111, "acc_stderr": 0.024882116857655075, "acc_norm": 0.2111111111111111, "acc_norm_stderr": 0.024882116857655075 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.20168067226890757, "acc_stderr": 0.026064313406304527, "acc_norm": 0.20168067226890757, "acc_norm_stderr": 0.026064313406304527 }, "harness|hendrycksTest-high_school_physics|5": { "acc": 0.23178807947019867, "acc_stderr": 0.034454062719870546, "acc_norm": 0.23178807947019867, "acc_norm_stderr": 0.034454062719870546 }, "harness|hendrycksTest-high_school_psychology|5": { "acc": 0.3284403669724771, "acc_stderr": 0.02013590279729839, "acc_norm": 0.3284403669724771, "acc_norm_stderr": 0.02013590279729839 }, "harness|hendrycksTest-high_school_statistics|5": { "acc": 0.1527777777777778, "acc_stderr": 0.024536326026134224, "acc_norm": 0.1527777777777778, "acc_norm_stderr": 0.024536326026134224 }, "harness|hendrycksTest-high_school_us_history|5": { "acc": 0.25, "acc_stderr": 0.03039153369274154, "acc_norm": 0.25, "acc_norm_stderr": 0.03039153369274154 }, "harness|hendrycksTest-high_school_world_history|5": { "acc": 0.270042194092827, "acc_stderr": 0.028900721906293426, "acc_norm": 0.270042194092827, "acc_norm_stderr": 0.028900721906293426 }, "harness|hendrycksTest-human_aging|5": { "acc": 0.3004484304932735, "acc_stderr": 0.03076935200822914, "acc_norm": 0.3004484304932735, "acc_norm_stderr": 0.03076935200822914 }, "harness|hendrycksTest-human_sexuality|5": { "acc": 0.2595419847328244, "acc_stderr": 0.03844876139785271, "acc_norm": 0.2595419847328244, "acc_norm_stderr": 0.03844876139785271 }, "harness|hendrycksTest-international_law|5": { "acc": 0.2231404958677686, "acc_stderr": 0.03800754475228733, "acc_norm": 0.2231404958677686, "acc_norm_stderr": 0.03800754475228733 }, "harness|hendrycksTest-jurisprudence|5": { "acc": 0.3148148148148148, "acc_stderr": 0.04489931073591312, "acc_norm": 0.3148148148148148, "acc_norm_stderr": 0.04489931073591312 }, "harness|hendrycksTest-logical_fallacies|5": { "acc": 0.2392638036809816, "acc_stderr": 0.03351953879521269, "acc_norm": 0.2392638036809816, "acc_norm_stderr": 0.03351953879521269 }, "harness|hendrycksTest-machine_learning|5": { "acc": 0.23214285714285715, "acc_stderr": 0.04007341809755806, "acc_norm": 0.23214285714285715, "acc_norm_stderr": 0.04007341809755806 }, "harness|hendrycksTest-management|5": { "acc": 0.1941747572815534, "acc_stderr": 0.03916667762822586, "acc_norm": 0.1941747572815534, "acc_norm_stderr": 0.03916667762822586 }, "harness|hendrycksTest-marketing|5": { "acc": 0.19658119658119658, "acc_stderr": 0.02603538609895129, "acc_norm": 0.19658119658119658, "acc_norm_stderr": 0.02603538609895129 }, "harness|hendrycksTest-medical_genetics|5": { "acc": 0.26, "acc_stderr": 0.04408440022768078, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768078 }, "harness|hendrycksTest-miscellaneous|5": { "acc": 0.22349936143039592, "acc_stderr": 0.014897235229450708, "acc_norm": 0.22349936143039592, "acc_norm_stderr": 0.014897235229450708 }, "harness|hendrycksTest-moral_disputes|5": { "acc": 0.2398843930635838, "acc_stderr": 0.02298959254312357, "acc_norm": 0.2398843930635838, "acc_norm_stderr": 0.02298959254312357 }, "harness|hendrycksTest-moral_scenarios|5": { "acc": 0.2424581005586592, "acc_stderr": 0.014333522059217889, "acc_norm": 0.2424581005586592, "acc_norm_stderr": 0.014333522059217889 }, "harness|hendrycksTest-nutrition|5": { "acc": 0.22875816993464052, "acc_stderr": 0.02405102973991225, "acc_norm": 0.22875816993464052, "acc_norm_stderr": 0.02405102973991225 }, "harness|hendrycksTest-philosophy|5": { "acc": 0.1864951768488746, "acc_stderr": 0.02212243977248077, "acc_norm": 0.1864951768488746, "acc_norm_stderr": 0.02212243977248077 }, "harness|hendrycksTest-prehistory|5": { "acc": 0.2654320987654321, "acc_stderr": 0.024569223600460842, "acc_norm": 0.2654320987654321, "acc_norm_stderr": 0.024569223600460842 }, "harness|hendrycksTest-professional_accounting|5": { "acc": 0.2553191489361702, "acc_stderr": 0.02601199293090201, "acc_norm": 0.2553191489361702, "acc_norm_stderr": 0.02601199293090201 }, "harness|hendrycksTest-professional_law|5": { "acc": 0.2438070404172099, "acc_stderr": 0.010966507972178475, "acc_norm": 0.2438070404172099, "acc_norm_stderr": 0.010966507972178475 }, "harness|hendrycksTest-professional_medicine|5": { "acc": 0.18382352941176472, "acc_stderr": 0.023529242185193106, "acc_norm": 0.18382352941176472, "acc_norm_stderr": 0.023529242185193106 }, "harness|hendrycksTest-professional_psychology|5": { "acc": 0.28594771241830064, "acc_stderr": 0.018280485072954673, "acc_norm": 0.28594771241830064, "acc_norm_stderr": 0.018280485072954673 }, "harness|hendrycksTest-public_relations|5": { "acc": 0.35454545454545455, "acc_stderr": 0.04582004841505416, "acc_norm": 0.35454545454545455, "acc_norm_stderr": 0.04582004841505416 }, "harness|hendrycksTest-security_studies|5": { "acc": 0.40408163265306124, "acc_stderr": 0.031414708025865885, "acc_norm": 0.40408163265306124, "acc_norm_stderr": 0.031414708025865885 }, "harness|hendrycksTest-sociology|5": { "acc": 0.263681592039801, "acc_stderr": 0.03115715086935557, "acc_norm": 0.263681592039801, "acc_norm_stderr": 0.03115715086935557 }, "harness|hendrycksTest-us_foreign_policy|5": { "acc": 0.26, "acc_stderr": 0.04408440022768079, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768079 }, "harness|hendrycksTest-virology|5": { "acc": 0.3493975903614458, "acc_stderr": 0.0371172519074075, "acc_norm": 0.3493975903614458, "acc_norm_stderr": 0.0371172519074075 }, "harness|hendrycksTest-world_religions|5": { "acc": 0.3216374269005848, "acc_stderr": 0.03582529442573122, "acc_norm": 0.3216374269005848, "acc_norm_stderr": 0.03582529442573122 }, "harness|truthfulqa:mc|0": { "mc1": 0.2252141982864137, "mc1_stderr": 0.014623240768023493, "mc2": 0.48312740729573567, "mc2_stderr": 0.01641721201782194 }, "harness|winogrande|5": { "acc": 0.5169692186266772, "acc_stderr": 0.014044390401612978 }, "harness|gsm8k|5": { "acc": 0.000758150113722517, "acc_stderr": 0.0007581501137225352 } }
数据集配置
-
harness_arc_challenge_25
- 分割: 2024_01_23T15_09_50.545148
- 路径:
**/details_harness|arc:challenge|25_2024-01-23T15-09-50.545148.parquet
- 路径:
- 分割: latest
- 路径:
**/details_harness|arc:challenge|25_2024-01-23T15-09-50.545148.parquet
- 路径:
- 分割: 2024_01_23T15_09_50.545148
-
harness_gsm8k_5
- 分割: 2024_01_23T15_09_50.545148
- 路径:
**/details_harness|gsm8k|5_2024-01-23T15-09-50.545148.parquet
- 路径:
- 分割: latest
- 路径:
**/details_harness|gsm8k|5_2024-01-23T15-09-50.545148.parquet
- 路径:
- 分割: 2024_01_23T15_09_50.545148
-
harness_hellaswag_10
- 分割: 2024_01_23T15_09_50.545148
- 路径:
**/details_harness|hellaswag|10_2024-01-23T15-09-50.545148.parquet
- 路径:
- 分割: latest
- 路径:
**/details_harness|hellaswag|10_2024-01-23T15-09-50.545148.parquet
- 路径:
- 分割: 2024_01_23T15_09_50.545148
-
harness_hendrycksTest_5
- 分割: 2024_01_23T15_09_50.545148
- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2024-01-23T15-09-50.545148.parquet**/details_harness|hendrycksTest-anatomy|5_2024-01-23T15-09-50.545148.parquet**/details_harness|hendrycksTest-astronomy|5_2024-01-23T15-09-50.545148.parquet**/details_harness|hendrycksTest-business_ethics|5_2024-01-23T15-09-50.545148.parquet**/details_harness|hendrycksTest-clinical_knowledge|5_2024-01-23T15-09-50.545148.parquet**/details_harness|hendrycksTest-college_biology|5_2024-01-23T15-09-50.545148.parquet**/details_harness|hendrycksTest-college_chemistry|5_2024-01-23T15-09-50.545148.parquet**/details_harness|hendrycksTest-college_computer_science|5_2024-01-23T15-09-50.545148.parquet**/details_harness|hendrycksTest-college_mathematics|5_2024-01-23T15-09-50.545148.parquet**/details_harness|hendrycksTest-college_medicine|5_2024-01-23T15-09-50.545148.parquet**/details_harness|hendrycksTest-college_physics|5_2024-01-23T15-09-50.545148.parquet**/details_harness|hendrycksTest-computer_security|5_2024-01-23T15-09-50.545148.parquet**/details_harness|hendrycksTest-conceptual_physics|5_2024-01-23T15-09-50.545148.parquet**/details_harness|hendrycksTest-econometrics|5_2024-01-23T15-09-50.545148.parquet**/details_harness|hendrycksTest-electrical_engineering|5_2024-01-23T15-09-50.545148.parquet**/details_harness|hendrycksTest-elementary_mathematics|5_2024-01-23T15-09-50.545148.parquet**/details_harness|hendrycksTest-formal_logic|5_2024-01-23T15-09-50.545148.parquet**/details_harness|hendrycksTest-global_facts|5_2024-01-23T15-09-50.545148.parquet**/details_harness|hendrycksTest-high_school_biology|5_2024-01-23T15-09-50.545148.parquet
- 路径:
- 分割: 2024_01_23T15_09_50.545148



