five

open-llm-leaderboard-old/details_vicgalle__Unsafe-Llama-3-8B

收藏
Hugging Face2024-04-20 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_vicgalle__Unsafe-Llama-3-8B
下载链接
链接失效反馈
官方服务:
资源简介:
该数据集是在评估模型vicgalle/Unsafe-Llama-3-8B时自动创建的,用于Open LLM Leaderboard的评估。数据集包含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,每次运行的结果作为一个特定的分割存储,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,还有一个名为results的配置,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。

该数据集是在评估模型vicgalle/Unsafe-Llama-3-8B时自动创建的,用于Open LLM Leaderboard的评估。数据集包含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,每次运行的结果作为一个特定的分割存储,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,还有一个名为results的配置,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

数据集摘要

该数据集是在评估模型 vicgalle/Unsafe-Llama-3-8BOpen LLM Leaderboard 上的运行过程中自动创建的。数据集包含 63 个配置,每个配置对应一个评估任务。数据集从 1 次运行中创建,每个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。

数据集结构

数据集包含多个配置,每个配置对应不同的评估任务。以下是部分配置的详细信息:

配置示例

  • config_name: harness_arc_challenge_25

    • data_files:
      • split: 2024_04_20T03_11_22.791207
        • path: **/details_harness|arc:challenge|25_2024-04-20T03-11-22.791207.parquet
      • split: latest
        • path: **/details_harness|arc:challenge|25_2024-04-20T03-11-22.791207.parquet
  • config_name: harness_gsm8k_5

    • data_files:
      • split: 2024_04_20T03_11_22.791207
        • path: **/details_harness|gsm8k|5_2024-04-20T03-11-22.791207.parquet
      • split: latest
        • path: **/details_harness|gsm8k|5_2024-04-20T03-11-22.791207.parquet
  • config_name: harness_hellaswag_10

    • data_files:
      • split: 2024_04_20T03_11_22.791207
        • path: **/details_harness|hellaswag|10_2024-04-20T03-11-22.791207.parquet
      • split: latest
        • path: **/details_harness|hellaswag|10_2024-04-20T03-11-22.791207.parquet
  • config_name: harness_hendrycksTest_5

    • data_files:
      • split: 2024_04_20T03_11_22.791207
        • path:
          • **/details_harness|hendrycksTest-abstract_algebra|5_2024-04-20T03-11-22.791207.parquet
          • **/details_harness|hendrycksTest-anatomy|5_2024-04-20T03-11-22.791207.parquet
          • **/details_harness|hendrycksTest-astronomy|5_2024-04-20T03-11-22.791207.parquet
          • **/details_harness|hendrycksTest-business_ethics|5_2024-04-20T03-11-22.791207.parquet
          • **/details_harness|hendrycksTest-clinical_knowledge|5_2024-04-20T03-11-22.791207.parquet
          • **/details_harness|hendrycksTest-college_biology|5_2024-04-20T03-11-22.791207.parquet
          • **/details_harness|hendrycksTest-college_chemistry|5_2024-04-20T03-11-22.791207.parquet
          • **/details_harness|hendrycksTest-college_computer_science|5_2024-04-20T03-11-22.791207.parquet
          • **/details_harness|hendrycksTest-college_mathematics|5_2024-04-20T03-11-22.791207.parquet
          • **/details_harness|hendrycksTest-college_medicine|5_2024-04-20T03-11-22.791207.parquet
          • **/details_harness|hendrycksTest-college_physics|5_2024-04-20T03-11-22.791207.parquet
          • **/details_harness|hendrycksTest-computer_security|5_2024-04-20T03-11-22.791207.parquet
          • **/details_harness|hendrycksTest-conceptual_physics|5_2024-04-20T03-11-22.791207.parquet
          • **/details_harness|hendrycksTest-econometrics|5_2024-04-20T03-11-22.791207.parquet
          • **/details_harness|hendrycksTest-electrical_engineering|5_2024-04-20T03-11-22.791207.parquet
          • **/details_harness|hendrycksTest-elementary_mathematics|5_2024-04-20T03-11-22.791207.parquet
          • **/details_harness|hendrycksTest-formal_logic|5_2024-04-20T03-11-22.791207.parquet
          • **/details_harness|hendrycksTest-global_facts|5_2024-04-20T03-11-22.791207.parquet
          • **/details_harness|hendrycksTest-high_school_biology|5_2024-04-20T03-11-22.791207.parquet

最新结果

以下是 2024-04-20T03:11:22.791207 运行 的最新结果:

python { "all": { "acc": 0.6695181093158753, "acc_stderr": 0.03178052614925023, "acc_norm": 0.671944100954632, "acc_norm_stderr": 0.032416295516730045, "mc1": 0.35128518971848227, "mc1_stderr": 0.016711358163544403, "mc2": 0.5152137634663979, "mc2_stderr": 0.015138315333192051 }, "harness|arc:challenge|25": { "acc": 0.5870307167235495, "acc_stderr": 0.014388344935398324, "acc_norm": 0.6262798634812287, "acc_norm_stderr": 0.014137708601759084 }, "harness|hellaswag|10": { "acc": 0.5954989046006771, "acc_stderr": 0.004897921845492104, "acc_norm": 0.7972515435172276, "acc_norm_stderr": 0.0040122499391749165 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6444444444444445, "acc_stderr": 0.04135176749720386, "acc_norm": 0.6444444444444445, "acc_norm_stderr": 0.04135176749720386 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7039473684210527, "acc_stderr": 0.03715062154998905, "acc_norm": 0.7039473684210527, "acc_norm_stderr": 0.03715062154998905 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.69, "acc_stderr": 0.04648231987117316, "acc_norm": 0.69, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7471698113207547, "acc_stderr": 0.026749899771241207, "acc_norm": 0.7471698113207547, "acc_norm_stderr": 0.026749899771241207 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7986111111111112, "acc_stderr": 0.03353647469713839, "acc_norm": 0.7986111111111112, "acc_norm_stderr": 0.03353647469713839 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.49, "acc_stderr": 0.05024183937956911, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956911 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.58, "acc_stderr": 0.049604496374885836, "acc_norm": 0.58, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.38, "acc_stderr": 0.04878317312145633, "acc_norm": 0.38, "acc_norm_stderr": 0.04878317312145633 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6416184971098265, "acc_stderr": 0.03656343653353159, "acc_norm": 0.6416184971098265, "acc_norm_stderr": 0.03656343653353159 }, "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": 0.76, "acc_stderr": 0.04292346959909281, "acc_norm": 0.76, "acc_norm_stderr": 0.04292346959909281 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.6127659574468085, "acc_stderr": 0.03184389265339526, "acc_norm": 0.6127659574468085, "acc_norm_stderr": 0.03184389265339526 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5964912280701754, "acc_stderr": 0.04615186962583707, "acc_norm": 0.5964912280701754, "acc_norm_stderr": 0.04615186962583707 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6413793103448275, "acc_stderr": 0.039966295748767186, "acc_norm": 0.6413793103448275, "acc

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