five

open-llm-leaderboard/details_postbot__distilgpt2-emailgen

收藏
Hugging Face2023-11-13 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_postbot__distilgpt2-emailgen
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上对模型postbot/distilgpt2-emailgen进行评估时自动创建的。数据集包含64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
原始信息汇总

数据集概述

该数据集是在对模型 postbot/distilgpt2-emailgen 进行评估运行期间自动创建的。数据集包含64个配置,每个配置对应一个评估任务。数据集来源于一次运行,每个运行结果以特定的时间戳命名,并作为每个配置中的一个分割。"train" 分割始终指向最新的结果。

数据集结构

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。

具体配置

  • harness_arc_challenge_25

    • 分割: 2023_11_13T13_25_05.974225, latest
    • 路径: **/details_harness|arc:challenge|25_2023-11-13T13-25-05.974225.parquet
  • harness_drop_3

    • 分割: 2023_11_13T13_25_05.974225, latest
    • 路径: **/details_harness|drop|3_2023-11-13T13-25-05.974225.parquet
  • harness_gsm8k_5

    • 分割: 2023_11_13T13_25_05.974225, latest
    • 路径: **/details_harness|gsm8k|5_2023-11-13T13-25-05.974225.parquet
  • harness_hellaswag_10

    • 分割: 2023_11_13T13_25_05.974225, latest
    • 路径: **/details_harness|hellaswag|10_2023-11-13T13-25-05.974225.parquet
  • harness_hendrycksTest_5

    • 分割: 2023_11_13T13_25_05.974225, latest
    • 路径:
      • **/details_harness|hendrycksTest-abstract_algebra|5_2023-11-13T13-25-05.974225.parquet
      • **/details_harness|hendrycksTest-anatomy|5_2023-11-13T13-25-05.974225.parquet
      • **/details_harness|hendrycksTest-astronomy|5_2023-11-13T13-25-05.974225.parquet
      • **/details_harness|hendrycksTest-business_ethics|5_2023-11-13T13-25-05.974225.parquet
      • **/details_harness|hendrycksTest-clinical_knowledge|5_2023-11-13T13-25-05.974225.parquet
      • **/details_harness|hendrycksTest-college_biology|5_2023-11-13T13-25-05.974225.parquet
      • **/details_harness|hendrycksTest-college_chemistry|5_2023-11-13T13-25-05.974225.parquet
      • **/details_harness|hendrycksTest-college_computer_science|5_2023-11-13T13-25-05.974225.parquet
      • **/details_harness|hendrycksTest-college_mathematics|5_2023-11-13T13-25-05.974225.parquet
      • **/details_harness|hendrycksTest-college_medicine|5_2023-11-13T13-25-05.974225.parquet
      • **/details_harness|hendrycksTest-college_physics|5_2023-11-13T13-25-05.974225.parquet
      • **/details_harness|hendrycksTest-computer_security|5_2023-11-13T13-25-05.974225.parquet

最新结果

以下是 2023-11-13T13:25:05.974225 运行的最新结果:

python { "all": { "acc": 0.2585985031430374, "acc_stderr": 0.03091312867789808, "acc_norm": 0.2592605342225761, "acc_norm_stderr": 0.03173517189546408, "mc1": 0.24357405140758873, "mc1_stderr": 0.015026354824910782, "mc2": 0.46170278335459186, "mc2_stderr": 0.01541047587026832, "em": 0.0, "em_stderr": 0.0, "f1": 0.011639052013422831, "f1_stderr": 0.0006056902097790024 }, "harness|arc:challenge|25": { "acc": 0.18600682593856654, "acc_stderr": 0.01137094018326675, "acc_norm": 0.2175767918088737, "acc_norm_stderr": 0.012057262020972497 }, "harness|hellaswag|10": { "acc": 0.2687711611232822, "acc_stderr": 0.004424146562746121, "acc_norm": 0.27524397530372435, "acc_norm_stderr": 0.004457243336616497 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.29, "acc_stderr": 0.04560480215720684, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720684 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.32592592592592595, "acc_stderr": 0.040491220417025055, "acc_norm": 0.32592592592592595, "acc_norm_stderr": 0.040491220417025055 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.17105263157894737, "acc_stderr": 0.030643607071677088, "acc_norm": 0.17105263157894737, "acc_norm_stderr": 0.030643607071677088 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.21, "acc_stderr": 0.040936018074033256, "acc_norm": 0.21, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.2188679245283019, "acc_stderr": 0.02544786382510861, "acc_norm": 0.2188679245283019, "acc_norm_stderr": 0.02544786382510861 }, "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": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "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": 0.23, "acc_stderr": 0.042295258468165065, "acc_norm": 0.23, "acc_norm_stderr": 0.042295258468165065 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.23699421965317918, "acc_stderr": 0.03242414757483098, "acc_norm": 0.23699421965317918, "acc_norm_stderr": 0.03242414757483098 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.24509803921568626, "acc_stderr": 0.04280105837364395, "acc_norm": 0.24509803921568626, "acc_norm_stderr": 0.04280105837364395 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.26, "acc_stderr": 0.044084400227680814, "acc_norm": 0.26, "acc_norm_stderr": 0.044084400227680814 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.225531914893617, "acc_stderr": 0.027321078417387533, "acc_norm": 0.225531914893617, "acc_norm_stderr": 0.027321078417387533 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2543859649122807, "acc_stderr": 0.04096985139843671, "acc_norm": 0.2543859649122807, "acc_norm_stderr": 0.04096985139843671 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2896551724137931, "acc_stderr": 0.03780019230438014, "acc_norm": 0.2896551724137931, "acc_norm_stderr": 0.03780019230438014 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.25396825396825395, "acc_stderr": 0.022418042891113942, "acc_norm": 0.25396825396825395, "acc_norm_stderr": 0.022418042891113942 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.15079365079365079, "acc_stderr": 0.03200686497287392, "acc_norm": 0.15079365079365079, "acc_norm_stderr": 0.03200686497287392 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "har

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