open-llm-leaderboard-old/details_Qwen__Qwen1.5-110B-Chat
收藏数据集概述
数据集简介
该数据集是在模型 Qwen/Qwen1.5-110B-Chat 在 Open LLM Leaderboard 上的评估运行期间自动创建的。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
- 创建来源:1 次运行
- 数据分割:每个配置包含特定运行的分割,分割名称使用运行的时间戳。"train" 分割始终指向最新结果。
- 结果配置:"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_Qwen__Qwen1.5-110B-Chat", "harness_winogrande_5", split="train")
最新结果
以下是 2024-04-29T23:24:47.571769 运行的最新结果:
python { "all": { "acc": 0.7692881269814446, "acc_stderr": 0.028173432383328943, "acc_norm": 0.7804978698330614, "acc_norm_stderr": 0.02869203112550788, "mc1": 0.4528763769889841, "mc1_stderr": 0.01742558984831402, "mc2": 0.6586438050595372, "mc2_stderr": 0.015480188664437178 }, "harness|arc:challenge|25": { "acc": 0.7022184300341296, "acc_stderr": 0.013363080107244484, "acc_norm": 0.7201365187713311, "acc_norm_stderr": 0.01311904089772592 }, "harness|hellaswag|10": { "acc": 0.667396932881896, "acc_stderr": 0.004701828071992633, "acc_norm": 0.8467436765584545, "acc_norm_stderr": 0.003594981823319888 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.56, "acc_stderr": 0.049888765156985884, "acc_norm": 0.56, "acc_norm_stderr": 0.049888765156985884 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6518518518518519, "acc_stderr": 0.041153246103369526, "acc_norm": 0.6518518518518519, "acc_norm_stderr": 0.041153246103369526 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.9078947368421053, "acc_stderr": 0.02353268597044349, "acc_norm": 0.9078947368421053, "acc_norm_stderr": 0.02353268597044349 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.81, "acc_stderr": 0.03942772444036623, "acc_norm": 0.81, "acc_norm_stderr": 0.03942772444036623 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7811320754716982, "acc_stderr": 0.02544786382510861, "acc_norm": 0.7811320754716982, "acc_norm_stderr": 0.02544786382510861 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8888888888888888, "acc_stderr": 0.02628055093284806, "acc_norm": 0.8888888888888888, "acc_norm_stderr": 0.02628055093284806 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.6, "acc_stderr": 0.049236596391733084, "acc_norm": 0.6, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.69, "acc_stderr": 0.04648231987117316, "acc_norm": 0.69, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7572254335260116, "acc_stderr": 0.0326926380614177, "acc_norm": 0.7572254335260116, "acc_norm_stderr": 0.0326926380614177 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.5098039215686274, "acc_stderr": 0.04974229460422817, "acc_norm": 0.5098039215686274, "acc_norm_stderr": 0.04974229460422817 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.81, "acc_stderr": 0.03942772444036624, "acc_norm": 0.81, "acc_norm_stderr": 0.03942772444036624 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.851063829787234, "acc_stderr": 0.02327411784801046, "acc_norm": 0.851063829787234, "acc_norm_stderr": 0.02327411784801046 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.6403508771929824, "acc_stderr": 0.045144961328736334, "acc_norm": 0.6403508771929824, "acc_norm_stderr": 0.045144961328736334 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.7724137931034483, "acc_stderr": 0.03493950380131183, "acc_norm": 0.7724137931034483, "acc_norm_stderr": 0.03493950380131183 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.7645502645502645, "acc_stderr": 0.021851509822031694, "acc_norm": 0.7645502645502645, "acc_norm_stderr": 0.021851509822031694 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.6349206349206349, "acc_stderr": 0.043062412591271554, "acc_norm": 0.6349206349206349, "acc_norm_stderr": 0.043062412591271554 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.62, "acc_stderr": 0.04878317312145633, "acc_norm": 0.62, "acc_norm_stderr": 0.04878317312145633 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.9, "acc_stderr": 0.017066403719657255, "acc_norm": 0.9, "acc_norm_stderr": 0.017066403719657255 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.6945812807881774, "acc_stderr": 0.03240661565868408, "acc_norm": 0.6945812807881774, "acc_norm_stderr": 0.03240661565868408 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.83, "acc_stderr": 0.03775251680686371, "acc_norm": 0.83, "acc_norm_stderr": 0.03775251680686371 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8909090909090909, "acc_stderr": 0.02434383813514564, "acc_norm": 0.8909090909090909, "acc_norm_stderr": 0.02434383813514564 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.9141414141414141, "acc_stderr": 0.01996022556317289, "acc_norm": 0.9141414141414141, "acc_norm_stderr": 0.01996022556317289 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9740932642487047, "acc_stderr": 0.01146452335695318, "acc_norm": 0.9740932642487047, "acc_norm_stderr": 0.01146452335695318 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.7948717948717948, "acc_stderr": 0.02047323317355197, "acc_norm": 0.7948717948717948, "acc_norm_stderr": 0.02047323317355197 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.4777777777777778, "acc_stderr": 0.030455413985678408, "acc_norm": 0.4777777777777778, "acc_norm_stderr": 0.030455413985678408 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.8697478991596639, "acc_stderr": 0.0218632584948521, "acc_norm": 0.8697478991596639, "acc_norm_stderr": 0.0218632584948521 }, "harness|hendrycksTest-high_school_physics|5": { "acc": 0.6291390728476821, "acc_stderr": 0.03943966699183629, "acc_norm": 0.6291390728476821, "acc_norm_stderr": 0.03943966699183629 }, "harness|hendrycksTest-high_school_psychology|5": { "acc": 0.926605504587156, "acc_stderr": 0.011180976446357573, "acc_norm": 0.926605504587156, "acc_norm_stderr": 0.011180976446357573 }, "harness|hendrycksTest-high_school_statistics|5": { "acc": 0.7037037037037037, "acc_stderr": 0.031141447823536037, "acc_norm": 0.7037037037037037, "acc_norm_stderr": 0.031141447823536037 }, "harness|hendrycksTest-high_school_us_history|5": { "acc": 0.9166666666666666, "acc_stderr": 0.019398452135813905, "acc_norm": 0.9166666666666666, "acc_norm_stderr": 0.019398452135813905 }, "harness|hendrycksTest-high_school_world_history|5": { "acc": 0.9113924050632911, "acc_stderr": 0.01849831520686538, "acc_norm": 0.9113924050632911, "acc_norm_stderr": 0.01849831520686538 }, "harness|hendrycksTest-human_aging|5": { "acc": 0.8161434977578476, "acc_stderr": 0.025998379092356517, "acc_norm": 0.8161434977578476, "acc_norm_stderr": 0.025998379092356517 }, "harness|hendrycksTest-human_sexuality|5": { "acc": 0.8702290076335878, "acc_stderr": 0.029473649496907065, "acc_norm": 0.8702290076335878, "acc_norm_stderr": 0.029473649496907065 }, "harness|hendrycksTest-international_law|5": { "acc": 0.8842975206611571, "acc_stderr": 0.029199802455622793, "acc_norm": 0.8842975206611571, "acc_norm_stderr": 0.029199802455622793 }, "harness|hendrycksTest-jurisprudence|5": { "acc": 0.8148148148148148, "acc_stderr": 0.03755265865037181, "acc_norm": 0.8148148148148148, "acc_norm_stderr": 0.03755265865037181 }, "harness|hendrycksTest-logical_fallacies|5": { "acc": 0.8711656441717791, "acc_stderr": 0.026321383198783636, "acc_norm": 0.8711656441717791, "acc_norm_stderr": 0.026321383198783636 }, "harness|hendrycksTest-machine_learning|5": { "acc": 0.7053571428571429, "acc_stderr": 0.043270409325787296, "acc_norm": 0.7053571428571429, "acc_norm_stderr": 0.043270409325787296 }, "harness|hendrycksTest-management|5": { "acc": 0.8737864077669902, "acc_stderr": 0.03288180278808628, "acc_norm": 0.8737864077669902, "acc_norm_stderr": 0.03288180278808628 }, "harness|hendrycksTest-marketing|5": { "acc": 0.9316239316239316, "acc_stderr": 0.016534627684311364, "acc_norm": 0.9316239316239316, "acc_norm_stderr": 0.016534627684311364 }, "harness|hendrycksTest-medical_genetics|5": { "acc": 0.84, "acc_stderr": 0.036845294917747094, "acc_norm": 0.84, "acc_norm_stderr": 0.036845294917747094 }, "harness|hendrycksTest-miscellaneous|5": { "acc": 0.9386973180076629, "acc_stderr": 0.008578258902395436, "acc_norm": 0.9386973180076629, "acc_norm_stderr": 0.008578258902395436 }, "harness|hendrycksTest-moral_disputes|5": { "acc": 0.8034682080924855, "acc_stderr": 0.021393961404363847, "acc_norm": 0.8034682080924855, "acc_norm_stderr": 0.021393961404363847 }, "harness|hendrycksTest-moral_scenarios|5": { "acc": 0.7731843575418994, "acc_stderr": 0.014005843570897902, "acc_norm": 0.7731843575418994, "acc_norm_stderr": 0.014005843570897902 }, "harness|hendrycksTest-nutrition|5": { "acc": 0.8300653594771242, "acc_stderr": 0.021505383121231382, "acc_norm": 0.8300653594771242, "acc_norm_stderr": 0.021505383121231382 }, "harness|hendrycksTest-philosophy|5": { "acc": 0.8070739549839229, "acc_stderr": 0.022411516780911366, "acc_norm": 0.8070739549839229, "acc_norm_stderr": 0.022411516780911366 }, "harness|hendrycksTest-prehistory|5": { "acc": 0.8950617283950617, "acc_stderr": 0.01705266208188531, "acc_norm": 0.8950617283950617, "acc_norm_stderr": 0.01705266208188531 }, "harness|hendrycksTest-professional_accounting|5": { "acc": 0.6702127659574468, "acc_stderr": 0.028045946942042405, "acc_norm": 0.6702127659574468, "acc_norm_stderr": 0.028045946942042405 }, "harness|hendrycksTest-professional_law|5": { "acc": 0.621903520208605, "acc_stderr": 0.012384878406798095, "acc_norm": 0.621903520208605, "acc_norm_stderr": 0.012384878406798095 }, "harness|hendrycksTest-professional_medicine|5": { "acc": 0.8566176470588235, "acc_stderr": 0.02128907120544514, "acc_norm": 0.8566176470588235, "acc_norm_stderr": 0.02128907120544514 }, "harness|hendrycksTest-professional_psychology|5": { "acc": 0.8169934640522876, "acc_stderr": 0.01564306991127334, "acc_norm": 0.8169934640522876, "acc_norm_stderr": 0.01564306991127334 }, "harness|hendrycksTest-public_relations|5": { "acc": 0.7545454545454545, "acc_stderr": 0.041220665028782855, "acc_norm": 0.7545454545454545, "acc_norm_stderr": 0.041220665028782855 }, "harness|hendrycksTest-security_studies|5": { "acc": 0.7591836734693878, "acc_stderr": 0.02737294220178816, "acc_norm": 0.7591836734693878, "acc_norm_stderr": 0.02737294220178816 }, "harness|hendrycksTest-sociology|5": { "acc": 0.8805970149253731, "acc_stderr": 0.02292879327721974, "acc_norm": 0.8805970149253731, "acc_norm_stderr": 0.02292879327721974 }, "harness|hendrycksTest-us_foreign_policy|5": { "acc": 0.88, "acc_stderr": 0.03265986323710906, "acc_norm": 0.88, "acc_norm_stderr": 0.03265986323710906 }, "harness|hendrycksTest-virology|5": { "acc": 0.5240963855421686, "acc_stderr": 0.03887971849597264, "acc_norm": 0.5240963855421686, "acc_norm_stderr": 0.03887971849597264 }, "harness|hendrycksTest-world_religions|5": { "acc": 0.8596491228070176, "acc_stderr": 0.0266405825391332, "acc_norm": 0.8596491228070176, "acc_norm_stderr": 0.0266405825391332 }, "harness|truthfulqa:mc|0": { "mc1": 0.4528763769889841, "mc1_stderr": 0.01742558984831402, "mc2": 0.6586438050595372, "mc2_stderr": 0.015480188664437178 }, "harness|winogrande|5": { "acc": 0.7734806629834254, "acc_stderr": 0.011764149054698346 }, "harness|gsm8k|5": { "acc": 0.3009855951478393, "acc_stderr": 0.012634504465211185 } }
数据集配置
-
harness_arc_challenge_25
- 分割:2024_04_29T23_24_47.571769, latest
- 路径:
**/details_harness|arc:challenge|25_2024-04-29T23-24-47.571769.parquet
-
harness_gsm8k_5
- 分割:2024_04_29T23_24_47.571769, latest
- 路径:
**/details_harness|gsm8k|5_2024-04-29T23-24-47.571769.parquet
-
harness_hellaswag_10
- 分割:2024_04_29T23_24_47.571769, latest
- 路径:
**/details_harness|hellaswag|10_2024-04-29T23-24-47.571769.parquet
-
harness_hendrycksTest_5
- 分割:2024_04_29T23_24_47.571769, latest
- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-anatomy|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-astronomy|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-business_ethics|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-clinical_knowledge|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-college_biology|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-college_chemistry|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-college_computer_science|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-college_mathematics|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-college_medicine|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-college_physics|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-computer_security|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-conceptual_physics|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-econometrics|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-electrical_engineering|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-elementary_mathematics|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-formal_logic|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-global_facts|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-high_school_biology|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-high_school_chemistry|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-high_school_computer_science|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-high_school_european_history|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-high_school_geography|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-high_school_mathematics|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-high_school_microeconomics|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-high_school_physics|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-high_school_psychology|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-high_school_statistics|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-high_school_us_history|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-high_school_world_history|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-human_aging|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-human_sexuality|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-international_law|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-jurisprudence|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-logical_fallacies|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-machine_learning|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-management|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-marketing|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-medical_genetics|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-miscellaneous|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-moral_disputes|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-moral_scenarios|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-nutrition|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-philosophy|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-prehistory|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-professional_accounting|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-professional_law|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-professional_medicine|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-professional_psychology|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-public_relations|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-security_studies|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-sociology|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-us_foreign_policy|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-virology|5_2024-04-29T23-24-47.571769.parquet**/details_harness|hendrycksTest-world_religions|5_2024-04-29T23-24-47.571769.parquet



