five

open-llm-leaderboard/details_uukuguy__speechless-codellama-orca-platypus-13b-0.10e

收藏
Hugging Face2023-10-24 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_uukuguy__speechless-codellama-orca-platypus-13b-0.10e
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 uukuguy/speechless-codellama-orca-platypus-13b-0.10e 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,每个配置对应一个评估任务。它由4次运行创建,每次运行作为每个配置中的一个特定分割,使用运行的时间戳命名。train 分割始终指向最新的结果。一个额外的配置 results 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。README 还提供了如何使用 Python 代码加载运行中的详细信息的示例,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

数据集简介

该数据集是在评估模型 uukuguy/speechless-codellama-orca-platypus-13b-0.10e 的过程中自动创建的,用于 Open LLM Leaderboard 的评估。

数据集结构

  • 配置数量:64个配置,每个配置对应一个评估任务。
  • 运行次数:数据集包含4次运行结果,每次运行的结果作为特定分片存储,分片名称使用运行的时间戳。
  • 最新结果:"train" 分片始终指向最新的结果。
  • 汇总结果:额外配置 "results" 存储所有运行的汇总结果,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_uukuguy__speechless-codellama-orca-platypus-13b-0.10e", "harness_winogrande_5", split="train")

最新结果

以下是2023年10月24日14:54:29.987056运行的最新结果: python { "all": { "em": 0.0, "em_stderr": 0.0, "f1": 8.913590604026845e-05, "f1_stderr": 2.996167513080367e-05, "acc": 0.24861878453038674, "acc_stderr": 0.007026135605808221 }, "harness|drop|3": { "em": 0.0, "em_stderr": 0.0, "f1": 8.913590604026845e-05, "f1_stderr": 2.996167513080367e-05 }, "harness|gsm8k|5": { "acc": 0.0, "acc_stderr": 0.0 }, "harness|winogrande|5": { "acc": 0.4972375690607735, "acc_stderr": 0.014052271211616441 } }

配置详情

以下是部分配置及其数据文件路径:

  • config_name: harness_arc_challenge_25

    • split: 2023_09_04T08_11_13.966337
      • path: **/details_harness|arc:challenge|25_2023-09-04T08:11:13.966337.parquet
    • split: 2023_09_12T14_48_20.175227
      • path: **/details_harness|arc:challenge|25_2023-09-12T14-48-20.175227.parquet
    • split: latest
      • path: **/details_harness|arc:challenge|25_2023-09-12T14-48-20.175227.parquet
  • config_name: harness_drop_3

    • split: 2023_10_17T17_09_41.931905
      • path: **/details_harness|drop|3_2023-10-17T17-09-41.931905.parquet
    • split: 2023_10_24T14_54_29.987056
      • path: **/details_harness|drop|3_2023-10-24T14-54-29.987056.parquet
    • split: latest
      • path: **/details_harness|drop|3_2023-10-24T14-54-29.987056.parquet
  • config_name: harness_gsm8k_5

    • split: 2023_10_17T17_09_41.931905
      • path: **/details_harness|gsm8k|5_2023-10-17T17-09-41.931905.parquet
    • split: 2023_10_24T14_54_29.987056
      • path: **/details_harness|gsm8k|5_2023-10-24T14-54-29.987056.parquet
    • split: latest
      • path: **/details_harness|gsm8k|5_2023-10-24T14-54-29.987056.parquet
  • config_name: harness_hellaswag_10

    • split: 2023_09_04T08_11_13.966337
      • path: **/details_harness|hellaswag|10_2023-09-04T08:11:13.966337.parquet
    • split: 2023_09_12T14_48_20.175227
      • path: **/details_harness|hellaswag|10_2023-09-12T14-48-20.175227.parquet
    • split: latest
      • path: **/details_harness|hellaswag|10_2023-09-12T14-48-20.175227.parquet
  • config_name: harness_hendrycksTest_5

    • split: 2023_09_04T08_11_13.966337
      • path: **/details_harness|hendrycksTest-abstract_algebra|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-anatomy|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-astronomy|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-business_ethics|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-clinical_knowledge|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-college_biology|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-college_chemistry|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-college_computer_science|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-college_mathematics|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-college_medicine|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-college_physics|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-computer_security|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-conceptual_physics|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-econometrics|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-electrical_engineering|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-elementary_mathematics|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-formal_logic|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-global_facts|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-high_school_biology|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-high_school_chemistry|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-high_school_computer_science|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-high_school_european_history|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-high_school_geography|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-high_school_mathematics|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-high_school_physics|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-high_school_psychology|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-high_school_statistics|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-high_school_us_history|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-high_school_world_history|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-human_aging|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-human_sexuality|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-international_law|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-jurisprudence|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-logical_fallacies|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-machine_learning|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-management|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-marketing|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-medical_genetics|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-miscellaneous|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-moral_disputes|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-moral_scenarios|5_2023-09-04T08:11:13.966337.parquet
      • path: **/details_harness|hendrycksTest-nutrition|5_2023-09-04T08:11:13.966337.parquet
      • path:
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