open-llm-leaderboard-old/details_perlthoughts__Falkor-7b
收藏数据集概述
该数据集是在对模型 perlthoughts/Falkor-7b 进行评估时自动创建的,用于 Open LLM Leaderboard。数据集包含 63 个配置,每个配置对应一个评估任务。
数据集结构
- 配置数量:63 个配置
- 创建来源:来自 1 次运行,每个运行在每个配置中作为一个特定的分割存在,分割名称使用运行的时间戳。
- 最新结果:"train" 分割始终指向最新的结果。
- 汇总结果:一个额外的配置 "results" 存储所有运行的汇总结果,用于计算和显示在 Open LLM Leaderboard 上的聚合指标。
加载数据示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_perlthoughts__Falkor-7b", "harness_winogrande_5", split="train")
最新结果
以下是 2023-12-09T15:28:39.767223 运行的最新结果:
python { "all": { "acc": 0.6427907257764981, "acc_stderr": 0.032414118407172746, "acc_norm": 0.6442720295040886, "acc_norm_stderr": 0.03307021882829144, "mc1": 0.46878824969400246, "mc1_stderr": 0.017469364874577547, "mc2": 0.6307542042080609, "mc2_stderr": 0.015278403284571293 }, "harness|arc:challenge|25": { "acc": 0.6544368600682594, "acc_stderr": 0.013896938461145682, "acc_norm": 0.6825938566552902, "acc_norm_stderr": 0.013602239088038169 }, "harness|hellaswag|10": { "acc": 0.6762597092212707, "acc_stderr": 0.004669459891917688, "acc_norm": 0.8583947420832504, "acc_norm_stderr": 0.003479322860225654 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6, "acc_stderr": 0.042320736951515885, "acc_norm": 0.6, "acc_norm_stderr": 0.042320736951515885 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6842105263157895, "acc_stderr": 0.0378272898086547, "acc_norm": 0.6842105263157895, "acc_norm_stderr": 0.0378272898086547 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.59, "acc_stderr": 0.049431107042371025, "acc_norm": 0.59, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6792452830188679, "acc_stderr": 0.028727502957880267, "acc_norm": 0.6792452830188679, "acc_norm_stderr": 0.028727502957880267 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7361111111111112, "acc_stderr": 0.03685651095897532, "acc_norm": 0.7361111111111112, "acc_norm_stderr": 0.03685651095897532 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.53, "acc_stderr": 0.05016135580465919, "acc_norm": 0.53, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.36, "acc_stderr": 0.048241815132442176, "acc_norm": 0.36, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6358381502890174, "acc_stderr": 0.03669072477416907, "acc_norm": 0.6358381502890174, "acc_norm_stderr": 0.03669072477416907 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4019607843137255, "acc_stderr": 0.048786087144669955, "acc_norm": 0.4019607843137255, "acc_norm_stderr": 0.048786087144669955 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.73, "acc_stderr": 0.04461960433384739, "acc_norm": 0.73, "acc_norm_stderr": 0.04461960433384739 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5617021276595745, "acc_stderr": 0.03243618636108102, "acc_norm": 0.5617021276595745, "acc_norm_stderr": 0.03243618636108102 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4473684210526316, "acc_stderr": 0.04677473004491199, "acc_norm": 0.4473684210526316, "acc_norm_stderr": 0.04677473004491199 }, "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": 0.3994708994708995, "acc_stderr": 0.025225450284067884, "acc_norm": 0.3994708994708995, "acc_norm_stderr": 0.025225450284067884 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.46825396825396826, "acc_stderr": 0.04463112720677171, "acc_norm": 0.46825396825396826, "acc_norm_stderr": 0.04463112720677171 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7903225806451613, "acc_stderr": 0.02315787934908353, "acc_norm": 0.7903225806451613, "acc_norm_stderr": 0.02315787934908353 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.49261083743842365, "acc_stderr": 0.035176035403610084, "acc_norm": 0.49261083743842365, "acc_norm_stderr": 0.035176035403610084 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.69, "acc_stderr": 0.04648231987117316, "acc_norm": 0.69, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7818181818181819, "acc_stderr": 0.03225078108306289, "acc_norm": 0.7818181818181819, "acc_norm_stderr": 0.03225078108306289 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.797979797979798, "acc_stderr": 0.028606204289229872, "acc_norm": 0.797979797979798, "acc_norm_stderr": 0.028606204289229872 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8911917098445595, "acc_stderr": 0.022473253332768776, "acc_norm": 0.8911917098445595, "acc_norm_stderr": 0.022473253332768776 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6692307692307692, "acc_stderr": 0.023854795680971125, "acc_norm": 0.6692307692307692, "acc_norm_stderr": 0.023854795680971125 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.37777777777777777, "acc_stderr": 0.029560707392465725, "acc_norm": 0.37777777777777777, "acc_norm_stderr": 0.029560707392465725 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.7184873949579832, "acc_stderr": 0.029213549414372177, "acc_norm": 0.7184873949579832, "acc_norm_stderr": 0.029213549414372177 }, "harness|hendrycksTest-high_school_physics|5": { "acc": 0.41721854304635764, "acc_stderr": 0.040261414976346104, "acc_norm": 0.41721854304635764, "acc_norm_stderr": 0.040261414976346104 }, "harness|hendrycksTest-high_school_psychology|5": { "acc": 0.8440366972477065, "acc_stderr": 0.015555802713590172, "acc_norm": 0.8440366972477065, "acc_norm_stderr": 0.015555802713590172 }, "harness|hendrycksTest-high_school_statistics|5": { "acc": 0.5648148148148148, "acc_stderr": 0.033812000056435254, "acc_norm": 0.5648148148148148, "acc_norm_stderr": 0.033812000056435254 }, "harness|hendrycksTest-high_school_us_history|5": { "acc": 0.8137254901960784, "acc_stderr": 0.027325470966716312, "acc_norm": 0.8137254901960784, "acc_norm_stderr": 0.027325470966716312 }, "harness|hendrycksTest-high_school_world_history|5": { "acc": 0.7974683544303798, "acc_stderr": 0.026160568246601436, "acc_norm": 0.7974683544303798, "acc_norm_stderr": 0.026160568246601436 }, "harness|hendrycksTest-human_aging|5": { "acc": 0.6860986547085202, "acc_stderr": 0.031146796482972465, "acc_norm": 0.6860986547085202, "acc_norm_stderr": 0.031146796482972465 }, "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": 0.7933884297520661, "acc_stderr": 0.03695980128098824, "acc_norm": 0.7933884297520661, "acc_norm_stderr": 0.03695980128098824 }, "harness|hendrycksTest-jurisprudence|5": { "acc": 0.8055555555555556, "acc_stderr": 0.038260763248848646, "acc_norm": 0.8055555555555556, "acc_norm_stderr": 0.038260763248848646 }, "harness|hendrycksTest-logical_fallacies|5": { "acc": 0.7361963190184049, "acc_stderr": 0.034624199316156234, "acc_norm": 0.7361963190184049, "acc_norm_stderr": 0.034624199316156234 }, "harness|hendrycksTest-machine_learning|5": { "acc": 0.48214285714285715, "acc_stderr": 0.047427623612430116, "acc_norm": 0.48214285714285715, "acc_norm_stderr": 0.047427623612430116 }, "harness|hendrycksTest-management|5": { "acc": 0.7766990291262136, "acc_stderr": 0.04123553189891431, "acc_norm": 0.7766990291262136, "acc_norm_stderr": 0.04123553189891431 }, "harness|hendrycksTest-marketing|5": { "acc": 0.8717948717948718, "acc_stderr": 0.02190190511507332, "acc_norm": 0.8717948717948718, "acc_norm_stderr": 0.02190190511507332 }, "harness|hendrycksTest-medical_genetics|5": { "acc": 0.71, "acc_stderr": 0.045604802157206845, "acc_norm": 0.71, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-miscellaneous|5": { "acc": 0.8263090676883781, "acc_stderr": 0.013547415658662257, "acc_norm": 0.8263090676883781, "acc_norm_stderr": 0.013547415658662257 }, "harness|hendrycksTest-moral_disputes|5": { "acc": 0.7138728323699421, "acc_stderr": 0.02433214677913413, "acc_norm": 0.7138728323699421, "acc_norm_stderr": 0.02433214677913413 }, "harness|hendrycksTest-moral_scenarios|5": { "acc": 0.39888268156424583, "acc_stderr": 0.01637696614261008, "acc_norm": 0.39888268156424583, "acc_norm_stderr": 0.01637696614261008 }, "harness|hendrycksTest-nutrition|5": { "acc": 0.7189542483660131, "acc_stderr": 0.025738854797818733, "acc_norm": 0.7189542483660131, "acc_norm_stderr": 0.025738854797818733 }, "harness|hendrycksTest-philosophy|5": { "acc": 0.7202572347266881, "acc_stderr": 0.025494259350694912, "acc_norm": 0.7202572347266881, "acc_norm_stderr": 0.025494259350694912 }, "harness|hendrycksTest-prehistory|5": { "acc": 0.7191358024691358, "acc_stderr": 0.025006469755799215, "acc_norm": 0.7191358024691358, "acc_norm_stderr": 0.025006469755799215 }, "harness|hendrycksTest-professional_accounting|5": { "acc": 0.46099290780141844, "acc_stderr": 0.029736592526424438, "acc_norm": 0.46099290780141844, "acc_norm_stderr": 0.029736592526424438 }, "harness|hendrycksTest-professional_law|5": { "acc": 0.45827900912646674, "acc_stderr": 0.01272570165695364, "acc_norm": 0.45827900912646674, "acc_norm_stderr": 0.01272570165695364 }, "harness|hendrycksTest-professional_medicine|5": { "acc": 0.6507352941176471, "acc_stderr": 0.028959755196824873, "acc_norm": 0.6507352941176471, "acc_norm_stderr": 0.028959755196824873 }, "harness|hendrycksTest-professional_psychology|5": { "acc": 0.6470588235294118, "acc_stderr": 0.019333142020797164, "acc_norm": 0.6470588235294118, "acc_norm_stderr": 0.019333142020797164 }, "harness|hendrycksTest-public_relations|5": { "acc": 0.6727272727272727, "acc_stderr": 0.0449429086625209, "acc_norm": 0.6727272727272727, "acc_norm_stderr": 0.0449429086625209 }, "harness|hendrycksTest-security_studies|5": { "acc": 0.7306122448979592, "acc_stderr": 0.02840125202902294, "acc_norm": 0.7306122448979592, "acc_norm_stderr": 0.02840125202902294 }, "harness|hendrycksTest-sociology|5": { "acc": 0.835820895522388, "acc_stderr": 0.026193923544454125, "acc_norm": 0.835820895522388, "acc_norm_stderr": 0.026193923544454125 }, "harness|hendrycksTest-us_foreign_policy|5": { "acc": 0.83, "acc_stderr": 0.0377525168068637, "acc_norm": 0.83, "acc_norm_stderr": 0.0377525168068637 }, "harness|hendrycksTest-virology|5": { "acc": 0.5180722891566265, "acc_stderr": 0.03889951252827216, "acc_norm": 0.5180722891566265, "acc_norm_stderr": 0.03889951252827216 }, "harness|hendrycksTest-world_religions|5": { "acc": 0.8070175438596491, "acc_stderr": 0.030267457554898458, "acc_norm": 0.8070175438596491, "acc_norm_stderr": 0.030267457554898458 }, "harness|truthfulqa:mc|0": { "mc1": 0.46878824969400246, "mc1_stderr": 0.017469364874577547, "mc2": 0.6307542042080609, "mc2_stderr": 0.015278403284571293 }, "harness|winogrande|5": { "acc": 0.8034727703235991, "acc_stderr": 0.011168120593569563 }, "harness|gsm8k|5": { "acc": 0.6050037907505686, "acc_stderr": 0.013465354969973205 } }
配置详情
-
harness_arc_challenge_25
- 分割:2023_12_09T15_28_39.767223
- 路径:
**/details_harness|arc:challenge|25_2023-12-09T15-28-39.767223.parquet - 分割:latest
- 路径:
**/details_harness|arc:challenge|25_2023-12-09T15-28-39.767223.parquet
-
harness_gsm8k_5
- 分割:2023_12_09T15_28_39.767223
- 路径:
**/details_harness|gsm8k|5_2023-12-09T15-28-39.767223.parquet - 分割:latest
- 路径:
**/details_harness|gsm8k|5_2023-12-09T15-28-39.767223.parquet
-
harness_hellaswag_10
- 分割:2023_12_09T15_28_39.767223
- 路径:
**/details_harness|hellaswag|10_2023-12-09T15-28-39.767223.parquet - 分割:latest
- 路径:
**/details_harness|hellaswag|10_2023-12-09T15-28-39.767223.parquet
-
harness_hendrycksTest_5
- 分割:2023_12_09T15_28_39.767223
- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-anatomy|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-astronomy|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-business_ethics|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-clinical_knowledge|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-college_biology|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-college_chemistry|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-college_computer_science|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-college_mathematics|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-college_medicine|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-college_physics|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-computer_security|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-conceptual_physics|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-econometrics|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-electrical_engineering|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-elementary_mathematics|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-formal_logic|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-global_facts|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-high_school_biology|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-high_school_chemistry|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-high_school_computer_science|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-high_school_european_history|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-high_school_geography|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-high_school_mathematics|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-high_school_physics|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-high_school_psychology|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-high_school_statistics|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-high_school_us_history|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-high_school_world_history|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-human_aging|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-human_sexuality|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-international_law|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-jurisprudence|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-logical_fallacies|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-machine_learning|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-management|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-marketing|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-medical_genetics|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-miscellaneous|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-moral_disputes|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-moral_scenarios|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-nutrition|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-philosophy|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-prehistory|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-professional_accounting|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-professional_law|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-professional_medicine|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-professional_psychology|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-public_relations|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-security_studies|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-sociology|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-us_foreign_policy|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-virology|5_2023-12-09T15-28-39.767223.parquet**/details_harness|hendrycksTest-world_religions|5_2023-12-09T15-28-39.767223.parquet



