open-llm-leaderboard-old/details_Felladrin__Minueza-32M-Base
收藏数据集概述
数据集名称
Evaluation run of Felladrin/Minueza-32M-Base
数据集描述
该数据集是在模型 Felladrin/Minueza-32M-Base 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一个特定的分割,分割名称使用运行的时间戳。
- "train" 分割始终指向最新的结果。
额外配置
- 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_Felladrin__Minueza-32M-Base", "harness_winogrande_5", split="train")
最新结果
这些是最新结果的示例: python { "all": { "acc": 0.24752258552248374, "acc_stderr": 0.030252830829249223, "acc_norm": 0.24764798996528117, "acc_norm_stderr": 0.03102991624039624, "mc1": 0.26805385556915545, "mc1_stderr": 0.015506204722834553, "mc2": 0.47454377774666195, "mc2_stderr": 0.015653794086918325 }, "harness|arc:challenge|25": { "acc": 0.1680887372013652, "acc_stderr": 0.010927715046124858, "acc_norm": 0.21331058020477817, "acc_norm_stderr": 0.011970971742326334 }, "harness|hellaswag|10": { "acc": 0.2610037841067516, "acc_stderr": 0.004382844128643407, "acc_norm": 0.2638916550487951, "acc_norm_stderr": 0.00439840499293385 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.21, "acc_stderr": 0.040936018074033256, "acc_norm": 0.21, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.2740740740740741, "acc_stderr": 0.03853254836552003, "acc_norm": 0.2740740740740741, "acc_norm_stderr": 0.03853254836552003 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.19078947368421054, "acc_stderr": 0.031975658210325, "acc_norm": 0.19078947368421054, "acc_norm_stderr": 0.031975658210325 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.2, "acc_stderr": 0.040201512610368445, "acc_norm": 0.2, "acc_norm_stderr": 0.040201512610368445 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.2188679245283019, "acc_stderr": 0.02544786382510861, "acc_norm": 0.2188679245283019, "acc_norm_stderr": 0.02544786382510861 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.19444444444444445, "acc_stderr": 0.03309615177059004, "acc_norm": 0.19444444444444445, "acc_norm_stderr": 0.03309615177059004 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.15, "acc_stderr": 0.035887028128263714, "acc_norm": 0.15, "acc_norm_stderr": 0.035887028128263714 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.23, "acc_stderr": 0.04229525846816506, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816506 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.1791907514450867, "acc_stderr": 0.029242513059063294, "acc_norm": 0.1791907514450867, "acc_norm_stderr": 0.029242513059063294 }, "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": 0.17, "acc_stderr": 0.03775251680686371, "acc_norm": 0.17, "acc_norm_stderr": 0.03775251680686371 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.2680851063829787, "acc_stderr": 0.028957342788342343, "acc_norm": 0.2680851063829787, "acc_norm_stderr": 0.028957342788342343 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.24561403508771928, "acc_stderr": 0.04049339297748141, "acc_norm": 0.24561403508771928, "acc_norm_stderr": 0.04049339297748141 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2206896551724138, "acc_stderr": 0.03455930201924811, "acc_norm": 0.2206896551724138, "acc_norm_stderr": 0.03455930201924811 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2566137566137566, "acc_stderr": 0.022494510767503154, "acc_norm": 0.2566137566137566, "acc_norm_stderr": 0.022494510767503154 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.15079365079365079, "acc_stderr": 0.03200686497287392, "acc_norm": 0.15079365079365079, "acc_norm_stderr": 0.03200686497287392 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.3161290322580645, "acc_stderr": 0.02645087448904277, "acc_norm": 0.3161290322580645, "acc_norm_stderr": 0.02645087448904277 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.2955665024630542, "acc_stderr": 0.032104944337514575, "acc_norm": 0.2955665024630542, "acc_norm_stderr": 0.032104944337514575 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.34, "acc_stderr": 0.047609522856952344, "acc_norm": 0.34, "acc_norm_stderr": 0.047609522856952344 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.2787878787878788, "acc_stderr": 0.035014387062967806, "acc_norm": 0.2787878787878788, "acc_norm_stderr": 0.035014387062967806 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.23232323232323232, "acc_stderr": 0.030088629490217483, "acc_norm": 0.23232323232323232, "acc_norm_stderr": 0.030088629490217483 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.21761658031088082, "acc_stderr": 0.02977866303775296, "acc_norm": 0.21761658031088082, "acc_norm_stderr": 0.02977866303775296 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.27692307692307694, "acc_stderr": 0.022688042352424994, "acc_norm": 0.27692307692307694, "acc_norm_stderr": 0.022688042352424994 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.24814814814814815, "acc_stderr": 0.026335739404055803, "acc_norm": 0.24814814814814815, "acc_norm_stderr": 0.026335739404055803 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.36554621848739494, "acc_stderr": 0.031282177063684614, "acc_norm": 0.36554621848739494, "acc_norm_stderr": 0.031282177063684614 }, "harness|hendrycksTest-high_school_physics|5": { "acc": 0.2251655629139073, "acc_stderr": 0.03410435282008936, "acc_norm": 0.2251655629139073, "acc_norm_stderr": 0.03410435282008936 }, "harness|hendrycksTest-high_school_psychology|5": { "acc": 0.22201834862385322, "acc_stderr": 0.017818849564796624, "acc_norm": 0.22201834862385322, "acc_norm_stderr": 0.017818849564796624 }, "harness|hendrycksTest-high_school_statistics|5": { "acc": 0.4722222222222222, "acc_stderr": 0.0340470532865388, "acc_norm": 0.4722222222222222, "acc_norm_stderr": 0.0340470532865388 }, "harness|hendrycksTest-high_school_us_history|5": { "acc": 0.2549019607843137, "acc_stderr": 0.030587591351604246, "acc_norm": 0.2549019607843137, "acc_norm_stderr": 0.030587591351604246 }, "harness|hendrycksTest-high_school_world_history|5": { "acc": 0.25316455696202533, "acc_stderr": 0.028304657943035296, "acc_norm": 0.25316455696202533, "acc_norm_stderr": 0.028304657943035296 }, "harness|hendrycksTest-human_aging|5": { "acc": 0.21973094170403587, "acc_stderr": 0.027790177064383605, "acc_norm": 0.21973094170403587, "acc_norm_stderr": 0.027790177064383605 }, "harness|hendrycksTest-human_sexuality|5": { "acc": 0.25190839694656486, "acc_stderr": 0.03807387116306086, "acc_norm": 0.25190839694656486, "acc_norm_stderr": 0.03807387116306086 }, "harness|hendrycksTest-international_law|5": { "acc": 0.24793388429752067, "acc_stderr": 0.03941897526516303, "acc_norm": 0.24793388429752067, "acc_norm_stderr": 0.03941897526516303 }, "harness|hendrycksTest-jurisprudence|5": { "acc": 0.21296296296296297, "acc_stderr": 0.03957835471980979, "acc_norm": 0.21296296296296297, "acc_norm_stderr": 0.03957835471980979 }, "harness|hendrycksTest-logical_fallacies|5": { "acc": 0.22085889570552147, "acc_stderr": 0.03259177392742178, "acc_norm": 0.22085889570552147, "acc_norm_stderr": 0.03259177392742178 }, "harness|hendrycksTest-machine_learning|5": { "acc": 0.23214285714285715, "acc_stderr": 0.040073418097558065, "acc_norm": 0.23214285714285715, "acc_norm_stderr": 0.040073418097558065 }, "harness|hendrycksTest-management|5": { "acc": 0.17475728155339806, "acc_stderr": 0.037601780060266224, "acc_norm": 0.17475728155339806, "acc_norm_stderr": 0.037601780060266224 }, "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": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-miscellaneous|5": { "acc": 0.2835249042145594, "acc_stderr": 0.016117318166832272, "acc_norm": 0.2835249042145594, "acc_norm_stderr": 0.016117318166832272 }, "harness|hendrycksTest-moral_disputes|5": { "acc": 0.24566473988439305, "acc_stderr": 0.02317629820399201, "acc_norm": 0.24566473988439305, "acc_norm_stderr": 0.02317629820399201 }, "harness|hendrycksTest-moral_scenarios|5": { "acc": 0.24804469273743016, "acc_stderr": 0.014444157808261431, "acc_norm": 0.24804469273743016, "acc_norm_stderr": 0.014444157808261431 }, "harness|hendrycksTest-nutrition|5": { "acc": 0.238562091503268, "acc_stderr": 0.024404394928087873, "acc_norm": 0.238562091503268, "acc_norm_stderr": 0.024404394928087873 }, "harness|hendrycksTest-philosophy|5": { "acc": 0.2990353697749196, "acc_stderr": 0.026003301117885135, "acc_norm": 0.2990353697749196, "acc_norm_stderr": 0.026003301117885135 }, "harness|hendrycksTest-prehistory|5": { "acc": 0.27469135802469136, "acc_stderr": 0.024836057868294677, "acc_norm": 0.27469135802469136, "acc_norm_stderr": 0.024836057868294677 }, "harness|hendrycksTest-professional_accounting|5": { "acc": 0.26595744680851063, "acc_stderr": 0.026358065698880592, "acc_norm": 0.26595744680851063, "acc_norm_stderr": 0.026358065698880592 }, "harness|hendrycksTest-professional_law|5": { "acc": 0.23859191655801826, "acc_stderr": 0.010885929742002221, "acc_norm": 0.23859191655801826, "acc_norm_stderr": 0.010885929742002221 }, "harness|hendrycksTest-professional_medicine|5": { "acc": 0.4485294117647059, "acc_stderr": 0.030211479609121593, "acc_norm": 0.4485294117647059, "acc_norm_stderr": 0.030211479609121593 }, "harness|hendrycksTest-professional_psychology|5": { "acc": 0.2238562091503268, "acc_stderr": 0.016863008585416617, "acc_norm": 0.2238562091503268, "acc_norm_stderr": 0.016863008585416617 }, "harness|hendrycksTest-public_relations|5": { "acc": 0.22727272727272727, "acc_stderr": 0.04013964554072774, "acc_norm": 0.22727272727272727, "acc_norm_stderr": 0.04013964554072774 }, "harness|hendrycksTest-security_studies|5": { "acc": 0.23673469387755103, "acc_stderr": 0.02721283588407316, "acc_norm": 0.23673469387755103, "acc_norm_stderr": 0.02721283588407316 }, "harness|hendrycksTest-sociology|5": { "acc": 0.23880597014925373, "acc_stderr": 0.030147775935409224, "acc_norm": 0.23880597014925373, "acc_norm_stderr": 0.030147775935409224 }, "harness|hendrycksTest-us_foreign_policy|5": { "acc": 0.26, "acc_stderr": 0.04408440022768078, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768078 }, "harness|hendrycksTest-virology|5": { "acc": 0.25301204819277107, "acc_stderr": 0.03384429155233135, "acc_norm": 0.25301204819277107, "acc_norm_stderr": 0.03384429155233135 }, "harness|hendrycksTest-world_religions|5": { "acc": 0.21052631578947367, "acc_stderr": 0.0312678171466318, "acc_norm": 0.21052631578947367, "acc_norm_stderr": 0.0312678171466318 }, "harness|truthfulqa:mc|0": { "mc1": 0.26805385556915545, "mc1_stderr": 0.015506204722834553, "mc2": 0.47454377774666195, "mc2_stderr": 0.015653794086918325 }, "harness|winogrande|5": { "acc": 0.531965272296764, "acc_stderr": 0.014023739221166386 }, "harness|gsm8k|5": { "acc": 0.0037907505686125853, "acc_stderr": 0.001692700740150178 } }
配置详情
-
config_name: harness_arc_challenge_25
- 数据文件:
- 分割: 2024_02_29T16_20_03.165457
- 路径:
**/details_harness|arc:challenge|25_2024-02-29T16-20-03.165457.parquet
- 路径:
- 分割: latest
- 路径:
**/details_harness|arc:challenge|25_2024-02-29T16-20-03.165457.parquet
- 路径:
- 分割: 2024_02_29T16_20_03.165457
- 数据文件:
-
config_name: harness_gsm8k_5
- 数据文件:
- 分割: 2024_02_29T16_20_03.165457
- 路径:
**/details_harness|gsm8k|5_2024-02-29T16-20-03.165457.parquet
- 路径:
- 分割: latest
- 路径:
**/details_harness|gsm8k|5_2024-02-29T16-20-03.165457.parquet
- 路径:
- 分割: 2024_02_29T16_20_03.165457
- 数据文件:
-
config_name: harness_hellaswag_10
- 数据文件:
- 分割: 2024_02_29T16_20_03.165457
- 路径:
**/details_harness|hellaswag|10_2024-02-29T16-20-03.165457.parquet
- 路径:
- 分割: latest
- 路径:
**/details_harness|hellaswag|10_2024-02-29T16-20-03.165457.parquet
- 路径:
- 分割: 2024_02_29T16_20_03.165457
- 数据文件:
-
config_name: harness_hendrycksTest_5
- 数据文件:
- 分割: 2024_02_29T16_20_03.165457
- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2024-02-29T16-20-03.165457.parquet**/details_harness|hendrycksTest-anatomy|5_2024-02-29T16-20-03.165457.parquet**/details_harness|hendrycksTest-astronomy|5_2024-02-29T16-20-03.165457.parquet**/details_harness|hendrycksTest-business_ethics|5_2024-02-29T16-20-03.165457.parquet**/details_harness|hendrycksTest-clinical_knowledge|5_2024-02-29T16-20-03.165457.parquet**/details_harness|hendrycksTest-college_biology|5_2024-02-29T16-20-03.165457.parquet**/details_harness|hendrycksTest-college_chemistry|5_2024-02-29T16-20-03.165457.parquet**/details_harness|hendrycksTest-college_computer_science|5_2024-02-29T16-20-03.165457.parquet**/details_harness|hendrycksTest-college_mathematics|5_2024-02-29T16-20-03.165457.parquet**/details_harness|hendrycksTest-college_medicine|5_2024-02-29T16-20-03.165457.parquet**/details_harness|hendrycksTest-college_physics|5_2024-02-29T16-20-03.165457.parquet**/details_harness|hendrycksTest-computer_security|5_2024-02-29T16-20-03.165457.parquet**/details_harness|hendrycksTest-conceptual_physics|5_2024-02-29T16-20-03.165457.parquet**/details_harness|hendrycksTest-econometrics|5_2024-02-29T16-20-03.165457.parquet**/details_harness|hendrycksTest-electrical_engineering|5_2024-02-29T16-20-03.165457.parquet**/details_harness|hendrycksTest-elementary_mathematics|5_2024-02-29T16-20-03.165457.parquet**/details_harness|hendrycksTest-formal_logic|5_2024-02-29T16-20-03.165457.parquet**/details_harness|hendrycksTest-global_facts|5_2024-02-29T16-20-03.165457.parquet
- 路径:
- 分割: 2024_02_29T16_20_03.165457
- 数据文件:



