five

open-llm-leaderboard-old/details_DrNicefellow__Mistral-1-from-Mixtral-8x7B-v0.1

收藏
Hugging Face2024-04-15 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_DrNicefellow__Mistral-1-from-Mixtral-8x7B-v0.1
下载链接
链接失效反馈
官方服务:
资源简介:
数据集是在评估模型DrNicefellow/Mistral-1-from-Mixtral-8x7B-v0.1时自动创建的,评估在Open LLM Leaderboard上进行。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,每次运行可以在每个配置的特定分割中找到,分割以运行的时间戳命名。train分割始终指向最新结果。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。

数据集是在评估模型DrNicefellow/Mistral-1-from-Mixtral-8x7B-v0.1时自动创建的,评估在Open LLM Leaderboard上进行。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,每次运行可以在每个配置的特定分割中找到,分割以运行的时间戳命名。train分割始终指向最新结果。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

数据集简介

该数据集是在评估模型DrNicefellow/Mistral-1-from-Mixtral-8x7B-v0.1Open LLM Leaderboard上的自动创建的。

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。
  • 数据集由1次运行创建,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。
  • 一个额外的配置"results"存储所有运行的聚合结果,用于计算和显示在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_DrNicefellow__Mistral-1-from-Mixtral-8x7B-v0.1", "harness_winogrande_5", split="train")

最新结果

以下是最新结果来自2024-04-15T11:15:25.413522的摘要: python { "all": { "acc": 0.24638682973542, "acc_stderr": 0.03027593109624199, "acc_norm": 0.24754912726025233, "acc_norm_stderr": 0.03108475528941473, "mc1": 0.2386780905752754, "mc1_stderr": 0.014922629695456416, "mc2": 0.48096228097027055, "mc2_stderr": 0.016148972368879536 }, "harness|arc:challenge|25": { "acc": 0.2158703071672355, "acc_stderr": 0.012022975360030674, "acc_norm": 0.28668941979522183, "acc_norm_stderr": 0.013214986329274758 }, "harness|hellaswag|10": { "acc": 0.2581159131647082, "acc_stderr": 0.004367037632204526, "acc_norm": 0.2634933280223063, "acc_norm_stderr": 0.004396273173717454 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.22, "acc_stderr": 0.04163331998932268, "acc_norm": 0.22, "acc_norm_stderr": 0.04163331998932268 }, # 其他任务的结果... }

配置详情

  • config_name: harness_arc_challenge_25

    • split: 2024_04_15T11_15_25.413522
      • path: **/details_harness|arc:challenge|25_2024-04-15T11-15-25.413522.parquet
    • split: latest
      • path: **/details_harness|arc:challenge|25_2024-04-15T11-15-25.413522.parquet
  • config_name: harness_gsm8k_5

    • split: 2024_04_15T11_15_25.413522
      • path: **/details_harness|gsm8k|5_2024-04-15T11-15-25.413522.parquet
    • split: latest
      • path: **/details_harness|gsm8k|5_2024-04-15T11-15-25.413522.parquet
  • config_name: harness_hellaswag_10

    • split: 2024_04_15T11_15_25.413522
      • path: **/details_harness|hellaswag|10_2024-04-15T11-15-25.413522.parquet
    • split: latest
      • path: **/details_harness|hellaswag|10_2024-04-15T11-15-25.413522.parquet
  • config_name: harness_hendrycksTest_5

    • split: 2024_04_15T11_15_25.413522
      • path:
        • **/details_harness|hendrycksTest-abstract_algebra|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-anatomy|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-astronomy|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-business_ethics|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-clinical_knowledge|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-college_biology|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-college_chemistry|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-college_computer_science|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-college_mathematics|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-college_medicine|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-college_physics|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-computer_security|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-conceptual_physics|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-econometrics|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-electrical_engineering|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-elementary_mathematics|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-formal_logic|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-global_facts|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-high_school_biology|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-high_school_chemistry|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-high_school_computer_science|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-high_school_european_history|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-high_school_geography|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-high_school_mathematics|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-high_school_physics|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-high_school_psychology|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-high_school_statistics|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-high_school_us_history|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-high_school_world_history|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-human_aging|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-human_sexuality|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-international_law|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-jurisprudence|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-logical_fallacies|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-machine_learning|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-management|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-marketing|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-medical_genetics|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-miscellaneous|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-moral_disputes|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-moral_scenarios|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-nutrition|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-philosophy|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-prehistory|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-professional_accounting|5_2024-04-15T11-15-25.413522.parquet
        • **/details_harness|hendrycksTest-professional_law|5_
二维码
社区交流群
二维码
科研交流群
商业服务