five

open-llm-leaderboard-old/details_Josephgflowers__Tinyllama-616M-Cinder

收藏
Hugging Face2024-03-31 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_Josephgflowers__Tinyllama-616M-Cinder
下载链接
链接失效反馈
官方服务:
资源简介:
该数据集是在模型Josephgflowers/Tinyllama-616M-Cinder的评估运行期间自动创建的,用于在Open LLM Leaderboard上进行评估。数据集由63个配置组成,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。此外,"results"配置存储了所有运行的聚合结果,并用于计算和显示Open LLM Leaderboard上的聚合指标。

该数据集是在模型Josephgflowers/Tinyllama-616M-Cinder的评估运行期间自动创建的,用于在Open LLM Leaderboard上进行评估。数据集由63个配置组成,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。此外,"results"配置存储了所有运行的聚合结果,并用于计算和显示Open LLM Leaderboard上的聚合指标。
提供机构:
open-llm-leaderboard-old
原始信息汇总

数据集概述

该数据集是在对模型 Josephgflowers/Tinyllama-616M-Cinder 进行评估运行期间自动创建的,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。数据集从 1 次运行中创建,每次运行的详细结果可以在每个配置中找到,并以运行的时间戳命名。"train" 分割始终指向最新的结果。

数据集结构

配置

  • 配置名称: harness_arc_challenge_25

    • 数据文件:
      • 分割: 2024_03_31T05_02_45.586654
        • 路径: **/details_harness|arc:challenge|25_2024-03-31T05-02-45.586654.parquet
      • 分割: latest
        • 路径: **/details_harness|arc:challenge|25_2024-03-31T05-02-45.586654.parquet
  • 配置名称: harness_gsm8k_5

    • 数据文件:
      • 分割: 2024_03_31T05_02_45.586654
        • 路径: **/details_harness|gsm8k|5_2024-03-31T05-02-45.586654.parquet
      • 分割: latest
        • 路径: **/details_harness|gsm8k|5_2024-03-31T05-02-45.586654.parquet
  • 配置名称: harness_hellaswag_10

    • 数据文件:
      • 分割: 2024_03_31T05_02_45.586654
        • 路径: **/details_harness|hellaswag|10_2024-03-31T05-02-45.586654.parquet
      • 分割: latest
        • 路径: **/details_harness|hellaswag|10_2024-03-31T05-02-45.586654.parquet
  • 配置名称: harness_hendrycksTest_5

    • 数据文件:
      • 分割: 2024_03_31T05_02_45.586654
        • 路径:
          • **/details_harness|hendrycksTest-abstract_algebra|5_2024-03-31T05-02-45.586654.parquet
          • **/details_harness|hendrycksTest-anatomy|5_2024-03-31T05-02-45.586654.parquet
          • **/details_harness|hendrycksTest-astronomy|5_2024-03-31T05-02-45.586654.parquet
          • **/details_harness|hendrycksTest-business_ethics|5_2024-03-31T05-02-45.586654.parquet
          • **/details_harness|hendrycksTest-clinical_knowledge|5_2024-03-31T05-02-45.586654.parquet
          • **/details_harness|hendrycksTest-college_biology|5_2024-03-31T05-02-45.586654.parquet
          • **/details_harness|hendrycksTest-college_chemistry|5_2024-03-31T05-02-45.586654.parquet
          • **/details_harness|hendrycksTest-college_computer_science|5_2024-03-31T05-02-45.586654.parquet
          • **/details_harness|hendrycksTest-college_mathematics|5_2024-03-31T05-02-45.586654.parquet
          • **/details_harness|hendrycksTest-college_medicine|5_2024-03-31T05-02-45.586654.parquet
          • **/details_harness|hendrycksTest-college_physics|5_2024-03-31T05-02-45.586654.parquet
          • **/details_harness|hendrycksTest-computer_security|5_2024-03-31T05-02-45.586654.parquet
          • **/details_harness|hendrycksTest-conceptual_physics|5_2024-03-31T05-02-45.586654.parquet
          • **/details_harness|hendrycksTest-econometrics|5_2024-03-31T05-02-45.586654.parquet
          • **/details_harness|hendrycksTest-electrical_engineering|5_2024-03-31T05-02-45.586654.parquet
          • **/details_harness|hendrycksTest-elementary_mathematics|5_2024-03-31T05-02-45.586654.parquet
          • **/details_harness|hendrycksTest-formal_logic|5_2024-03-31T05-02-45.586654.parquet
          • **/details_harness|hendrycksTest-global_facts|5_2024-03-31T05-02-45.586654.parquet

最新结果

以下是 最新结果 的摘要:

python { "all": { "acc": 0.25024089617746503, "acc_stderr": 0.030587439859005337, "acc_norm": 0.25084872224031984, "acc_norm_stderr": 0.03139528132826798, "mc1": 0.2386780905752754, "mc1_stderr": 0.014922629695456421, "mc2": 0.43410131367024446, "mc2_stderr": 0.015406538697451911 }, "harness|arc:challenge|25": { "acc": 0.2431740614334471, "acc_stderr": 0.01253655414458709, "acc_norm": 0.2645051194539249, "acc_norm_stderr": 0.012889272949313368 }, "harness|hellaswag|10": { "acc": 0.317167894841665, "acc_stderr": 0.004644223294727728, "acc_norm": 0.3639713204540928, "acc_norm_stderr": 0.004801572028920792 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.23, "acc_stderr": 0.042295258468165044, "acc_norm": 0.23, "acc_norm_stderr": 0.042295258468165044 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.28888888888888886, "acc_stderr": 0.03915450630414251, "acc_norm": 0.28888888888888886, "acc_norm_stderr": 0.03915450630414251 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.18421052631578946, "acc_stderr": 0.0315469804508223, "acc_norm": 0.18421052631578946, "acc_norm_stderr": 0.0315469804508223 }, "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": 0.2188679245283019, "acc_stderr": 0.025447863825108614, "acc_norm": 0.2188679245283019, "acc_norm_stderr": 0.025447863825108614 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2152777777777778, "acc_stderr": 0.034370793441061344, "acc_norm": 0.2152777777777778, "acc_norm_stderr": 0.034370793441061344 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.2, "acc_stderr": 0.040201512610368466, "acc_norm": 0.2, "acc_norm_stderr": 0.040201512610368466 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.28, "acc_stderr": 0.04512608598542128, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542128 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.27167630057803466, "acc_stderr": 0.03391750322321659, "acc_norm": 0.27167630057803466, "acc_norm_stderr": 0.03391750322321659 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.27450980392156865, "acc_stderr": 0.044405219061793275, "acc_norm": 0.27450980392156865, "acc_norm_stderr": 0.044405219061793275 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.23, "acc_stderr": 0.04229525846816505, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816505 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.24680851063829787, "acc_stderr": 0.0281854413012341, "acc_norm": 0.24680851063829787, "acc_norm_stderr": 0.0281854413012341 }, "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": 0.25517241379310346, "acc_stderr": 0.03632984052707842, "acc_norm": 0.25517241379310346, "acc_norm_stderr": 0.03632984052707842 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.25396825396825395, "acc_stderr": 0.02241804289111

5,000+
优质数据集
54 个
任务类型
进入经典数据集
二维码
社区交流群

面向社区/商业的数据集话题

二维码
科研交流群

面向高校/科研机构的开源数据集话题

数据驱动未来

携手共赢发展

商业合作