five

open-llm-leaderboard-old/details_h2oai__h2o-danube-1.8b-chat

收藏
Hugging Face2024-02-01 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_h2oai__h2o-danube-1.8b-chat
下载链接
链接失效反馈
官方服务:
资源简介:
该数据集是在Open LLM Leaderboard上对h2oai/h2o-danube-1.8b-chat模型进行评估时自动生成的。数据集包含63个配置,每个配置对应一个评估任务。数据集由1次运行生成,每次运行的结果作为特定配置中的一个分割,分割名称使用运行的时间戳。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,用于计算和显示Open LLM Leaderboard上的聚合指标。

该数据集是在Open LLM Leaderboard上对h2oai/h2o-danube-1.8b-chat模型进行评估时自动生成的。数据集包含63个配置,每个配置对应一个评估任务。数据集由1次运行生成,每次运行的结果作为特定配置中的一个分割,分割名称使用运行的时间戳。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,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 h2oai/h2o-danube-1.8b-chatOpen LLM Leaderboard 上的自动创建的。数据集包含 63 个配置,每个配置对应一个评估任务。

数据集结构

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拆分,拆分名称使用运行的时间戳。"train" 拆分始终指向最新的结果。

配置详情

数据集包含多个配置,每个配置对应不同的任务和拆分。以下是部分配置的示例:

  • 配置名称: harness_arc_challenge_25

    • 数据文件:
      • 拆分: 2024_02_01T23_01_46.561658
        • 路径: **/details_harness|arc:challenge|25_2024-02-01T23-01-46.561658.parquet
      • 拆分: latest
        • 路径: **/details_harness|arc:challenge|25_2024-02-01T23-01-46.561658.parquet
  • 配置名称: harness_gsm8k_5

    • 数据文件:
      • 拆分: 2024_02_01T23_01_46.561658
        • 路径: **/details_harness|gsm8k|5_2024-02-01T23-01-46.561658.parquet
      • 拆分: latest
        • 路径: **/details_harness|gsm8k|5_2024-02-01T23-01-46.561658.parquet
  • 配置名称: harness_hellaswag_10

    • 数据文件:
      • 拆分: 2024_02_01T23_01_46.561658
        • 路径: **/details_harness|hellaswag|10_2024-02-01T23-01-46.561658.parquet
      • 拆分: latest
        • 路径: **/details_harness|hellaswag|10_2024-02-01T23-01-46.561658.parquet
  • 配置名称: harness_hendrycksTest_5

    • 数据文件:
      • 拆分: 2024_02_01T23_01_46.561658
        • 路径:
          • **/details_harness|hendrycksTest-abstract_algebra|5_2024-02-01T23-01-46.561658.parquet
          • **/details_harness|hendrycksTest-anatomy|5_2024-02-01T23-01-46.561658.parquet
          • **/details_harness|hendrycksTest-astronomy|5_2024-02-01T23-01-46.561658.parquet
          • **/details_harness|hendrycksTest-business_ethics|5_2024-02-01T23-01-46.561658.parquet
          • **/details_harness|hendrycksTest-clinical_knowledge|5_2024-02-01T23-01-46.561658.parquet
          • **/details_harness|hendrycksTest-college_biology|5_2024-02-01T23-01-46.561658.parquet
          • **/details_harness|hendrycksTest-college_chemistry|5_2024-02-01T23-01-46.561658.parquet
          • **/details_harness|hendrycksTest-college_computer_science|5_2024-02-01T23-01-46.561658.parquet
          • **/details_harness|hendrycksTest-college_mathematics|5_2024-02-01T23-01-46.561658.parquet
          • **/details_harness|hendrycksTest-college_medicine|5_2024-02-01T23-01-46.561658.parquet
          • **/details_harness|hendrycksTest-college_physics|5_2024-02-01T23-01-46.561658.parquet
          • **/details_harness|hendrycksTest-computer_security|5_2024-02-01T23-01-46.561658.parquet
          • **/details_harness|hendrycksTest-conceptual_physics|5_2024-02-01T23-01-46.561658.parquet
          • **/details_harness|hendrycksTest-econometrics|5_2024-02-01T23-01-46.561658.parquet
          • **/details_harness|hendrycksTest-electrical_engineering|5_2024-02-01T23-01-46.561658.parquet
          • **/details_harness|hendrycksTest-elementary_mathematics|5_2024-02-01T23-01-46.561658.parquet
          • **/details_harness|hendrycksTest-formal_logic|5_2024-02-01T23-01-46.561658.parquet
          • **/details_harness|hendrycksTest-global_facts|5_2024-02-01T23-01-46.561658.parquet

最新结果

以下是 2024-02-01T23:01:46.561658 运行的最新结果:

python { "all": { "acc": 0.3403400293103947, "acc_stderr": 0.03328323264170753, "acc_norm": 0.3412403351985156, "acc_norm_stderr": 0.03400489086266728, "mc1": 0.26805385556915545, "mc1_stderr": 0.015506204722834557, "mc2": 0.41637248299191104, "mc2_stderr": 0.01467700936265024 }, "harness|arc:challenge|25": { "acc": 0.3856655290102389, "acc_stderr": 0.01422425097325718, "acc_norm": 0.4112627986348123, "acc_norm_stderr": 0.014379441068522082 }, "harness|hellaswag|10": { "acc": 0.5066719776936865, "acc_stderr": 0.004989337148572074, "acc_norm": 0.6806413065126469, "acc_norm_stderr": 0.004652753439460153 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.27, "acc_stderr": 0.04461960433384741, "acc_norm": 0.27, "acc_norm_stderr": 0.04461960433384741 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.42962962962962964, "acc_stderr": 0.04276349494376599, "acc_norm": 0.42962962962962964, "acc_norm_stderr": 0.04276349494376599 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.3157894736842105, "acc_stderr": 0.0378272898086547, "acc_norm": 0.3157894736842105, "acc_norm_stderr": 0.0378272898086547 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.33, "acc_stderr": 0.04725815626252604, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252604 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.3471698113207547, "acc_stderr": 0.029300101705549652, "acc_norm": 0.3471698113207547, "acc_norm_stderr": 0.029300101705549652 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2638888888888889, "acc_stderr": 0.03685651095897532, "acc_norm": 0.2638888888888889, "acc_norm_stderr": 0.03685651095897532 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.24, "acc_stderr": 0.04292346959909283, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909283 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.28, "acc_stderr": 0.04512608598542127, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542127 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.31213872832369943, "acc_stderr": 0.035331333893236574, "acc_norm": 0.31213872832369943, "acc_norm_stderr": 0.035331333893236574 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.12745098039215685, "acc_stderr": 0.033182249219420756, "acc_norm": 0.12745098039215685, "acc_norm_stderr": 0.033182249219420756 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.2553191489361702, "acc_stderr": 0.02850485647051419, "acc_norm": 0.2553191489361702, "acc_norm_stderr": 0.02850485647051419 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2719298245614035, "acc_stderr": 0.041857744240220554, "acc_norm": 0.2719298245614035, "acc_norm_stderr": 0.041857744240220554 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.32413793103448274, "acc_stderr": 0.03900432069185553, "acc_norm": 0.32413793103448274, "acc_norm_stderr": 0.03

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