open-llm-leaderboard-old/details_Josephgflowers__Tinyllama-320M-Cinder-v1

该数据集是在评估模型Josephgflowers/Tinyllama-320M-Cinder-v1时自动创建的，包含了63个配置，每个配置对应一个评估任务。数据集由1次运行生成，每次运行的结果存储为特定的分割，分割名称使用运行的时间戳。此外，数据集还包含一个名为“results”的配置，用于存储所有运行的聚合结果，并在Open LLM Leaderboard上显示聚合指标。

原始信息汇总

数据集概述

数据集摘要

该数据集是在评估模型 Josephgflowers/Tinyllama-320M-Cinder-v1 在 Open LLM Leaderboard 上的自动创建的。

数据集组成

• 该数据集包含 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作为一个特定的分片找到，分片名称使用运行的时间戳。
• "train" 分片始终指向最新的结果。
• 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_Josephgflowers__Tinyllama-320M-Cinder-v1", "harness_winogrande_5", split="train")

最新结果

这些是最新的结果，来自 2024-03-24T22:37:34.732835 的运行： python { "all": { "acc": 0.2459273540509439, "acc_stderr": 0.030291521467678335, "acc_norm": 0.2466523223666807, "acc_norm_stderr": 0.031097669192170465, "mc1": 0.24724602203182375, "mc1_stderr": 0.015102404797359652, "mc2": 0.44303938803798537, "mc2_stderr": 0.015148288982349819 }, "harness|arc:challenge|25": { "acc": 0.22098976109215018, "acc_stderr": 0.01212492920681826, "acc_norm": 0.2773037542662116, "acc_norm_stderr": 0.013082095839059374 }, "harness|hellaswag|10": { "acc": 0.28281218880701053, "acc_stderr": 0.004494454911844641, "acc_norm": 0.2967536347341167, "acc_norm_stderr": 0.004558933822995543 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.24, "acc_stderr": 0.04292346959909282, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909282 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.2518518518518518, "acc_stderr": 0.037498507091740206, "acc_norm": 0.2518518518518518, "acc_norm_stderr": 0.037498507091740206 }, "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": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.2641509433962264, "acc_stderr": 0.02713429162874171, "acc_norm": 0.2641509433962264, "acc_norm_stderr": 0.02713429162874171 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2222222222222222, "acc_stderr": 0.03476590104304133, "acc_norm": 0.2222222222222222, "acc_norm_stderr": 0.03476590104304133 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.14, "acc_stderr": 0.03487350880197768, "acc_norm": 0.14, "acc_norm_stderr": 0.03487350880197768 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.22, "acc_stderr": 0.041633319989322695, "acc_norm": 0.22, "acc_norm_stderr": 0.041633319989322695 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.2138728323699422, "acc_stderr": 0.031265112061730424, "acc_norm": 0.2138728323699422, "acc_norm_stderr": 0.031265112061730424 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.22549019607843138, "acc_stderr": 0.041583075330832865, "acc_norm": 0.22549019607843138, "acc_norm_stderr": 0.041583075330832865 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.2, "acc_stderr": 0.04020151261036843, "acc_norm": 0.2, "acc_norm_stderr": 0.04020151261036843 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.3148936170212766, "acc_stderr": 0.030363582197238167, "acc_norm": 0.3148936170212766, "acc_norm_stderr": 0.030363582197238167 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2543859649122807, "acc_stderr": 0.040969851398436695, "acc_norm": 0.2543859649122807, "acc_norm_stderr": 0.040969851398436695 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.23448275862068965, "acc_stderr": 0.035306258743465914, "acc_norm": 0.23448275862068965, "acc_norm_stderr": 0.035306258743465914 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.25396825396825395, "acc_stderr": 0.02241804289111394, "acc_norm": 0.25396825396825395, "acc_norm_stderr": 0.02241804289111394 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.16666666666666666, "acc_stderr": 0.03333333333333337, "acc_norm": 0.16666666666666666, "acc_norm_stderr": 0.03333333333333337 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.14, "acc_stderr": 0.0348735088019777, "acc_norm": 0.14, "acc_norm_stderr": 0.0348735088019777 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.2806451612903226, "acc_stderr": 0.025560604721022895, "acc_norm": 0.2806451612903226, "acc_norm_stderr": 0.025560604721022895 }, "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": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.24848484848484848, "acc_stderr": 0.03374402644139405, "acc_norm": 0.24848484848484848, "acc_norm_stderr": 0.03374402644139405 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.2727272727272727, "acc_stderr": 0.03173071239071724, "acc_norm": 0.2727272727272727, "acc_norm_stderr": 0.03173071239071724 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.37823834196891193, "acc_stderr": 0.0349980727619334, "acc_norm": 0.37823834196891193, "acc_norm_stderr": 0.0349980727619334 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.3128205128205128, "acc_stderr": 0.02350757902064534, "acc_norm": 0.3128205128205128, "acc_norm_stderr": 0.02350757902064534 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.26296296296296295, "acc_stderr": 0.02684205787383371, "acc_norm": 0.26296296296296295, "acc_norm_stderr": 0.02684205787383371 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.31512605042016806, "acc_stderr": 0.03017680828897434, "acc_norm": 0.31512605042016806, "acc_norm_stderr": 0.03017680828897434 }, "harness|hendrycksTest-high_school_physics|5": { "acc": 0.19205298013245034, "acc_stderr": 0.03216298420593614, "acc_norm": 0.19205298013245034, "acc_norm_stderr": 0.03216298420593614 }, "harness|hendrycksTest-high_school_psychology|5": { "acc": 0.21284403669724772, "acc_stderr": 0.017549376389313694, "acc_norm": 0.21284403669724772, "acc_norm_stderr": 0.017549376389313694 }, "harness|hendrycksTest-high_school_statistics|5": { "acc": 0.27314814814814814, "acc_stderr": 0.03038805130167812, "acc_norm": 0.27314814814814814, "acc_norm_stderr": 0.03038805130167812 }, "harness|hendrycksTest-high_school_us_history|5": { "acc": 0.24019607843137256, "acc_stderr": 0.02998373305591361, "acc_norm": 0.24019607843137256, "acc_norm_stderr": 0.02998373305591361 }, "harness|hendrycksTest-high_school_world_history|5": { "acc": 0.3037974683544304, "acc_stderr": 0.029936696387138605, "acc_norm": 0.3037974683544304, "acc_norm_stderr": 0.029936696387138605 }, "harness|hendrycksTest-human_aging|5": { "acc": 0.17040358744394618, "acc_stderr": 0.025234593447136165, "acc_norm": 0.17040358744394618, "acc_norm_stderr": 0.025234593447136165 }, "harness|hendrycksTest-human_sexuality|5": { "acc": 0.24427480916030533, "acc_stderr": 0.037683359597287434, "acc_norm": 0.24427480916030533, "acc_norm_stderr": 0.037683359597287434 }, "harness|hendrycksTest-international_law|5": { "acc": 0.3305785123966942, "acc_stderr": 0.04294340845212094, "acc_norm": 0.3305785123966942, "acc_norm_stderr": 0.04294340845212094 }, "harness|hendrycksTest-jurisprudence|5": { "acc": 0.24074074074074073, "acc_stderr": 0.041331194402438376, "acc_norm": 0.24074074074074073, "acc_norm_stderr": 0.041331194402438376 }, "harness|hendrycksTest-logical_fallacies|5": { "acc": 0.22699386503067484, "acc_stderr": 0.03291099578615767, "acc_norm": 0.22699386503067484, "acc_norm_stderr": 0.03291099578615767 }, "harness|hendrycksTest-machine_learning|5": { "acc": 0.21428571428571427, "acc_stderr": 0.03894641120044792, "acc_norm": 0.21428571428571427, "acc_norm_stderr": 0.03894641120044792 }, "harness|hendrycksTest-management|5": { "acc": 0.1941747572815534, "acc_stderr": 0.03916667762822584, "acc_norm": 0.1941747572815534, "acc_norm_stderr": 0.03916667762822584 }, "harness|hendrycksTest-marketing|5": { "acc": 0.20512820512820512, "acc_stderr": 0.02645350805404034, "acc_norm": 0.20512820512820512, "acc_norm_stderr": 0.02645350805404034 }, "harness|hendrycksTest-medical_genetics|5": { "acc": 0.26, "acc_stderr": 0.0440844002276808, "acc_norm": 0.26, "acc_norm_stderr": 0.0440844002276808 }, "harness|hendrycksTest-miscellaneous|5": { "acc": 0.2503192848020434, "acc_stderr": 0.015491088951494583, "acc_norm": 0.2503192848020434, "acc_norm_stderr": 0.015491088951494583 }, "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": 0.2581005586592179, "acc_stderr": 0.014635185616527829, "acc_norm": 0.2581005586592179, "acc_norm_stderr": 0.014635185616527829 }, "harness|hendrycksTest-nutrition|5": { "acc": 0.23202614379084968, "acc_stderr": 0.024170840879341016, "acc_norm": 0.23202614379084968, "acc_norm_stderr": 0.024170840879341016 }, "harness|hendrycksTest-philosophy|5": { "acc": 0.24115755627009647, "acc_stderr": 0.024296594034763426, "acc_norm": 0.24115755627009647, "acc_norm_stderr": 0.024296594034763426 }, "harness|hendrycksTest-prehistory|5": { "acc": 0.30246913580246915, "acc_stderr": 0.025557653981868055, "acc_norm": 0.30246913580246915, "acc_norm_stderr": 0.025557653981868055 }, "harness|hendrycksTest-professional_accounting|5": { "acc": 0.25177304964539005, "acc_stderr": 0.0258921511567094, "acc_norm": 0.25177304964539005, "acc_norm_stderr": 0.0258921511567094 }, "harness|hendrycksTest-professional_law|5": { "acc": 0.25554106910039115, "acc_stderr": 0.01113985783359851, "acc_norm": 0.25554106910039115, "acc_norm_stderr": 0.01113985783359851 }, "harness|hendrycksTest-professional_medicine|5": { "acc": 0.20588235294117646, "acc_stderr": 0.024562204314142317, "acc_norm": 0.20588235294117646, "acc_norm_stderr": 0.024562204314142317 }, "harness|hendrycksTest-professional_psychology|5": { "acc": 0.2369281045751634, "acc_stderr": 0.01720166216978978, "acc_norm": 0.2369281045751634, "acc_norm_stderr": 0.01720166216978978 }, "harness|hendrycksTest-public_relations|5": { "acc": 0.2545454545454545, "acc_stderr": 0.04172343038705383, "acc_norm": 0.2545454545454545, "acc_norm_stderr": 0.04172343038705383 }, "harness|hendrycksTest-security_studies|5": { "acc": 0.24081632653061225, "acc_stderr": 0.027372942201788163, "acc_norm": 0.24081632653061225, "acc_norm_stderr": 0.027372942201788163 }, "harness|hendrycksTest-sociology|5": { "acc": 0.27860696517412936, "acc_stderr": 0.031700561834973086, "acc_norm": 0.27860696517412936, "acc_norm_stderr": 0.031700561834973086 }, "harness|hendrycksTest-us_foreign_policy|5": { "acc": 0.22, "acc_stderr": 0.04163331998932269, "acc_norm": 0.22, "acc_norm_stderr": 0.04163331998932269 }, "harness|hendrycksTest-virology|5": { "acc": 0.21686746987951808, "acc_stderr": 0.03208284450356365, "acc_norm": 0.21686746987951808, "acc_norm_stderr": 0.03208284450356365 }, "harness|hendrycksTest-world_religions|5": { "acc": 0.23976608187134502, "acc_stderr": 0.03274485211946956, "acc_norm": 0.23976608187134502, "acc_norm_stderr": 0.03274485211946956 }, "harness|truthfulqa:mc|0": { "mc1": 0.24724602203182375, "mc1_stderr": 0.015102404797359652, "mc2": 0.44303938803798537, "mc2_stderr": 0.015148288982349819 }, "harness|winogrande|5": { "acc": 0.5193370165745856, "acc_stderr": 0.014041972733712972 }, "harness|gsm8k|5": { "acc": 0.0, "acc_stderr": 0.0 } }

配置详情

• config_name: harness_arc_challenge_25

  • 分片: 2024_03_24T22_37_34.732835
    • 路径: **/details_harness|arc:challenge|25_2024-03-24T22-37-34.732835.parquet
  • 分片: latest
    • 路径: **/details_harness|arc:challenge|25_2024-03-24T22-37-34.732835.parquet

• config_name: harness_gsm8k_5

  • 分片: 2024_03_24T22_37_34.732835
    • 路径: **/details_harness|gsm8k|5_2024-03-24T22-37-34.732835.parquet
  • 分片: latest
    • 路径: **/details_harness|gsm8k|5_2024-03-24T22-37-34.732835.parquet

• config_name: harness_hellaswag_10

  • 分片: 2024_03_24T22_37_34.732835
    • 路径: **/details_harness|hellaswag|10_2024-03-24T22-37-34.732835.parquet
  • 分片: latest
    • 路径: **/details_harness|hellaswag|10_2024-03-24T22-37-34.732835.parquet

• config_name: harness_hendrycksTest_5

  • 分片: 2024_03_24T22_37_34.732835
    • 路径:
      • **/details_harness|hendrycksTest-abstract_algebra|5_2024-03-24T22-37-34.732835.parquet
      • **/details_harness|hendrycksTest-anatomy|5_2024-03-24T22-37-34.732835.parquet
      • **/details_harness|hendrycksTest-astronomy|5_2024-03-24T22-37-34.732835.parquet
      • **/details_harness|hendrycksTest-business_ethics|5_2024-03-24T22-37-34.732835.parquet
      • **/details_harness|hendrycksTest-clinical_knowledge|5_2024-03-24T22-37-34.732835.parquet
      • **/details_harness|hendrycksTest-college_biology|5_2024-03-24T22-37-34.732835.parquet
      • **/details_harness|hendrycksTest-college_chemistry|5_2024-03-24T22-37-34.732835.parquet
      • **/details_harness|hendrycksTest-college_computer_science|5_2024-03-24T22-37-34.732835.parquet
      • **/details_harness|hendrycksTest-college_mathematics|5_2024-03-24T22-37-34.732835.parquet
      • **/details_harness|hendrycksTest-college_medicine|5_2024-03-24T22-37-34.732835.parquet
      • **/details_harness|hendrycksTest-college_physics|5_2024-03-24T22-37-34.732835.parquet
      • **/details_harness|hendrycksTest-computer_security|5_2024-03-24T22-37-34.732835.parquet
      • **/details_harness|hendrycksTest-conceptual_physics|5_2024-03-24T22-37-34.732835.parquet
      • **/details_harness|hendrycksTest-econometrics|5_2024-03-24T22-37-34.732835.parquet
      • **/details_harness|hendrycksTest-electrical_engineering|5_2024-03-24T22-37-34.732835.parquet
      • **/details_harness|hendrycksTest-elementary_mathematics|5_2024-03-24T22-37-34.732835.parquet
      • **/details_harness|hendrycksTest-formal_logic|5_2024-03-24T22-37-34.732835.parquet
      • **/details_harness|hendrycksTest-global_facts|5_2024-03-24T22-37-34.732835.parquet