five

open-llm-leaderboard/details_jondurbin__airoboros-l2-70b-gpt4-m2.0

收藏
Hugging Face2023-10-23 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_jondurbin__airoboros-l2-70b-gpt4-m2.0
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 jondurbin/airoboros-l2-70b-gpt4-m2.0 在 Open LLM Leaderboard 上的评估运行期间自动生成的。数据集由 64 个配置组成,每个配置对应一个被评估的任务。数据集是从 3 次运行中创建的,每次运行在每个配置中表示为特定的分割,分割名称使用运行的时间戳。train 分割始终指向最新的结果。此外,还有一个 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。README 还提供了如何使用 Python 代码加载运行中的数据集详细信息的示例,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

数据集名称

Evaluation run of jondurbin/airoboros-l2-70b-gpt4-m2.0

数据集摘要

该数据集是在模型jondurbin/airoboros-l2-70b-gpt4-m2.0Open LLM Leaderboard上的评估运行期间自动创建的。

数据集组成

  • 数据集由64个配置组成,每个配置对应一个评估任务。
  • 数据集从3次运行中创建,每次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。
  • 额外的配置"results"存储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。

数据加载示例

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_jondurbin__airoboros-l2-70b-gpt4-m2.0", "harness_winogrande_5", split="train")

最新结果

以下是2023-10-23T01:01:59.537351运行的最新结果: python { "all": { "em": 0.19955956375838926, "em_stderr": 0.004092987650196818, "f1": 0.2619746224832211, "f1_stderr": 0.004049847572493045, "acc": 0.5449064818543622, "acc_stderr": 0.011200400992385444 }, "harness|drop|3": { "em": 0.19955956375838926, "em_stderr": 0.004092987650196818, "f1": 0.2619746224832211, "f1_stderr": 0.004049847572493045 }, "harness|gsm8k|5": { "acc": 0.2539802880970432, "acc_stderr": 0.011989952209548084 }, "harness|winogrande|5": { "acc": 0.8358326756116812, "acc_stderr": 0.010410849775222804 } }

配置详情

  • harness_arc_challenge_25

    • 分割:2023_08_09T22_06_19.540113
      • 路径:**/details_harness|arc:challenge|25_2023-08-09T22:06:19.540113.parquet
    • 分割:2023_08_10T00_00_29.305175
      • 路径:**/details_harness|arc:challenge|25_2023-08-10T00:00:29.305175.parquet
    • 分割:latest
      • 路径:**/details_harness|arc:challenge|25_2023-08-10T00:00:29.305175.parquet
  • harness_drop_3

    • 分割:2023_10_23T01_01_59.537351
      • 路径:**/details_harness|drop|3_2023-10-23T01-01-59.537351.parquet
    • 分割:latest
      • 路径:**/details_harness|drop|3_2023-10-23T01-01-59.537351.parquet
  • harness_gsm8k_5

    • 分割:2023_10_23T01_01_59.537351
      • 路径:**/details_harness|gsm8k|5_2023-10-23T01-01-59.537351.parquet
    • 分割:latest
      • 路径:**/details_harness|gsm8k|5_2023-10-23T01-01-59.537351.parquet
  • harness_hellaswag_10

    • 分割:2023_08_09T22_06_19.540113
      • 路径:**/details_harness|hellaswag|10_2023-08-09T22:06:19.540113.parquet
    • 分割:2023_08_10T00_00_29.305175
      • 路径:**/details_harness|hellaswag|10_2023-08-10T00:00:29.305175.parquet
    • 分割:latest
      • 路径:**/details_harness|hellaswag|10_2023-08-10T00:00:29.305175.parquet
  • harness_hendrycksTest_5

    • 分割:2023_08_09T22_06_19.540113
      • 路径:**/details_harness|hendrycksTest-abstract_algebra|5_2023-08-09T22:06:19.540113.parquet
      • 路径:**/details_harness|hendrycksTest-anatomy|5_2023-08-09T22:06:19.540113.parquet
      • 路径:**/details_harness|hendrycksTest-astronomy|5_2023-08-09T22:06:19.540113.parquet
      • 路径:**/details_harness|hendrycksTest-business_ethics|5_2023-08-09T22:06:19.540113.parquet
      • 路径:**/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-09T22:06:19.540113.parquet
      • 路径:**/details_harness|hendrycksTest-college_biology|5_2023-08-09T22:06:19.540113.parquet
      • 路径:**/details_harness|hendrycksTest-college_chemistry|5_2023-08-09T22:06:19.540113.parquet
      • 路径:**/details_harness|hendrycksTest-college_computer_science|5_2023-08-09T22:06:19.540113.parquet
      • 路径:**/details_harness|hendrycksTest-college_mathematics|5_2023-08-09T22:06:19.540113.parquet
      • 路径:**/details_harness|hendrycksTest-college_medicine|5_2023-08-09T22:06:19.540113.parquet
      • 路径:**/details_harness|hendrycksTest-college_physics|5_2023-08-09T22:06:19.540113.parquet
      • 路径:**/details_harness|hendrycksTest-computer_security|5_2023-08-09T22:06:19.540113.parquet
      • 路径:**/details_harness|hendrycksTest-conceptual_physics|5_2023-08-09T22:06:19.540113.parquet
      • 路径:**/details_harness|hendrycksTest-econometrics|5_2023-08-09T22:06:19.540113.parquet
      • 路径:**/details_harness|hendrycksTest-electrical_engineering|5_2023-08-09T22:06:19.540113.parquet
      • 路径:**/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-09T22:06:19.540113.parquet
      • 路径:**/details_harness|hendrycksTest-formal_logic|5_2023-08-09T22:06:19.540113.parquet
      • 路径:**/details_harness|hendrycksTest-global_facts|5_2023-08-09T22:06:19.540113.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_biology|5_2023-08-09T22:06:19.540113.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-09T22:06:19.540113.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-09T22:06:19.540113.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_european_history|5_2023-08-09T22:06:19.540113.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_geography|5_2023-08-09T22:06:19.540113.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-09T22:06:19.540113.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-09T22:06:19.540113.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-09T22:06:19.540113.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-09T22:06:19.540113.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_physics|5_2023-08-09T22:06:19.540113.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_psychology|5_2023-08-09T22:06:19.540113.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_statistics|5_2023-08-09T22:06:19.540113.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_us_history|5_2023-08-09T22:06:19.540113.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_world_history|5_2023-08-09T22:06:19.540113.parquet
      • 路径:**/details_harness|hendrycksTest-human_aging|5_2023-08-09T22:06:19.540113.parquet
      • 路径:**/details_harness|hendrycksTest-human_sexuality|5_2023-08-09T22:06:19.540113.parquet
      • 路径:**/details_harness|hendrycksTest-international_law|5_2023-08-09T22:06:19.540113.parquet
      • 路径:**/details_harness|hendrycksTest-jurisprudence|5_2023-08-09T22:06:19.540113.parquet
      • 路径:**/details_harness|hendrycksTest-logical_fallacies|5_2023-08-09T22:06:19.540113.parquet
      • 路径:**/details_harness|hendrycksTest-machine_learning|5_2023-08-09T22:06:19.540113.parquet
      • 路径:**/details_harness|hendrycksTest-management|5_2023-08-09T22:06:19.540113.parquet
      • 路径:**/details_harness|hendrycksTest-marketing|5_2023-08-09T22:06:19.540113.parquet
      • 路径:**/details_harness|hendrycksTest-medical_genetics|5_2023-08-09T22:06:19.540113.parquet
      • 路径:**/details_harness|hendrycksTest-miscellaneous|5_2023-08-09T22:06:19.540113.parquet
      • 路径:`**/details_harness|hendrycksTest-moral_disputes|5_2023-08
二维码
社区交流群
二维码
科研交流群
商业服务