five

open-llm-leaderboard/details_bongchoi__test-llama2-7b

收藏
Hugging Face2023-09-16 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_bongchoi__test-llama2-7b
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 bongchoi/test-llama2-7b 在 Open LLM Leaderboard 上的评估运行期间自动创建的。数据集由 64 个配置组成,每个配置对应一个被评估的任务。数据集是从 2 次运行中生成的,每次运行在每个配置中表示为特定的分割,分割名称使用运行的时间戳。train 分割始终指向最新的结果。一个名为 results 的额外配置存储了所有运行的聚合结果,这些结果用于计算和显示 Open LLM Leaderboard 上的聚合指标。README 还提供了如何使用 `datasets` 库中的 `load_dataset` 函数加载数据集的示例,并包含了特定运行的最新结果。
提供机构:
open-llm-leaderboard
原始信息汇总

数据集概述

该数据集是在对模型 bongchoi/test-llama2-7b 进行评估运行期间自动创建的,用于 Open LLM Leaderboard

数据集组成

  • 数据集包含 64 个配置,每个配置对应一个评估任务。
  • 数据集从 2 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。
  • 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。

最新结果

以下是 2023-09-16T19:36:12.019633 运行的最新结果

python { "all": { "em": 0.001363255033557047, "em_stderr": 0.0003778609196461104, "f1": 0.05606543624161075, "f1_stderr": 0.0013211107078874738, "acc": 0.4057988012013119, "acc_stderr": 0.00970458141675358 }, "harness|drop|3": { "em": 0.001363255033557047, "em_stderr": 0.0003778609196461104, "f1": 0.05606543624161075, "f1_stderr": 0.0013211107078874738 }, "harness|gsm8k|5": { "acc": 0.0712661106899166, "acc_stderr": 0.007086462127954491 }, "harness|winogrande|5": { "acc": 0.7403314917127072, "acc_stderr": 0.012322700705552667 } }

配置详情

以下是数据集的部分配置详情:

  • harness_arc_challenge_25

    • 分割:2023_08_29T04_25_39.762695
    • 路径:**/details_harness|arc:challenge|25_2023-08-29T04:25:39.762695.parquet
    • 分割:latest
    • 路径:**/details_harness|arc:challenge|25_2023-08-29T04:25:39.762695.parquet
  • harness_drop_3

    • 分割:2023_09_16T19_36_12.019633
    • 路径:**/details_harness|drop|3_2023-09-16T19-36-12.019633.parquet
    • 分割:latest
    • 路径:**/details_harness|drop|3_2023-09-16T19-36-12.019633.parquet
  • harness_gsm8k_5

    • 分割:2023_09_16T19_36_12.019633
    • 路径:**/details_harness|gsm8k|5_2023-09-16T19-36-12.019633.parquet
    • 分割:latest
    • 路径:**/details_harness|gsm8k|5_2023-09-16T19-36-12.019633.parquet
  • harness_hellaswag_10

    • 分割:2023_08_29T04_25_39.762695
    • 路径:**/details_harness|hellaswag|10_2023-08-29T04:25:39.762695.parquet
    • 分割:latest
    • 路径:**/details_harness|hellaswag|10_2023-08-29T04:25:39.762695.parquet
  • harness_hendrycksTest_5

    • 分割:2023_08_29T04_25_39.762695
    • 路径:
      • **/details_harness|hendrycksTest-abstract_algebra|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-anatomy|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-astronomy|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-business_ethics|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-college_biology|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-college_chemistry|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-college_computer_science|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-college_mathematics|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-college_medicine|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-college_physics|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-computer_security|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-conceptual_physics|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-econometrics|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-electrical_engineering|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-formal_logic|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-global_facts|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-high_school_biology|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-high_school_european_history|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-high_school_geography|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-high_school_physics|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-high_school_psychology|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-high_school_statistics|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-high_school_us_history|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-high_school_world_history|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-human_aging|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-human_sexuality|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-international_law|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-jurisprudence|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-logical_fallacies|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-machine_learning|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-management|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-marketing|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-medical_genetics|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-miscellaneous|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-moral_disputes|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-moral_scenarios|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-nutrition|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-philosophy|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-prehistory|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-professional_accounting|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-professional_law|5_2023-08-29T04:25:39.762695.parquet
      • **/details_harness|hendrycksTest-professional_medicine|5_2023-08-29T04:25:39.762695.parquet
      • `**/details_harness|hendrycksTest-professional_psychology|5_2023-
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