five

open-llm-leaderboard/details_lu-vae__llama2-13B-sharegpt4-orca-openplatypus-8w

收藏
Hugging Face2023-10-25 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_lu-vae__llama2-13B-sharegpt4-orca-openplatypus-8w
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 lu-vae/llama2-13B-sharegpt4-orca-openplatypus-8w 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,每个配置对应一个特定的评估任务。它包含来自 2 次运行的数据,每次运行在每个配置中表示为特定的拆分。train 拆分始终指向最新结果。一个名为 results 的额外配置存储了所有运行的聚合结果,这些结果用于计算和显示 Open LLM Leaderboard 上的指标。README 还提供了如何使用 Python 代码加载数据集的示例,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

该数据集是在模型 lu-vae/llama2-13B-sharegpt4-orca-openplatypus-8w 的评估运行期间自动创建的,用于 Open LLM Leaderboard

数据集组成

  • 数据集包含 64 个配置,每个配置对应一个评估任务。
  • 数据集从 2 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 "results" 配置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_lu-vae__llama2-13B-sharegpt4-orca-openplatypus-8w", "harness_winogrande_5", split="train")

最新结果

以下是 2023-10-25T02:53:14.013945 运行的最新结果

python { "all": { "em": 0.002936241610738255, "em_stderr": 0.0005541113054709996, "f1": 0.0881931627516778, "f1_stderr": 0.0017824166498732977, "acc": 0.43444724154830167, "acc_stderr": 0.01050882298494655 }, "harness|drop|3": { "em": 0.002936241610738255, "em_stderr": 0.0005541113054709996, "f1": 0.0881931627516778, "f1_stderr": 0.0017824166498732977 }, "harness|gsm8k|5": { "acc": 0.11751326762699014, "acc_stderr": 0.008870331256489993 }, "harness|winogrande|5": { "acc": 0.7513812154696132, "acc_stderr": 0.012147314713403108 } }

配置详情

  • harness_arc_challenge_25

    • 分割:2023_09_14T08_19_15.271974
      • 路径:**/details_harness|arc:challenge|25_2023-09-14T08-19-15.271974.parquet
    • 分割:latest
      • 路径:**/details_harness|arc:challenge|25_2023-09-14T08-19-15.271974.parquet
  • harness_drop_3

    • 分割:2023_10_25T02_53_14.013945
      • 路径:**/details_harness|drop|3_2023-10-25T02-53-14.013945.parquet
    • 分割:latest
      • 路径:**/details_harness|drop|3_2023-10-25T02-53-14.013945.parquet
  • harness_gsm8k_5

    • 分割:2023_10_25T02_53_14.013945
      • 路径:**/details_harness|gsm8k|5_2023-10-25T02-53-14.013945.parquet
    • 分割:latest
      • 路径:**/details_harness|gsm8k|5_2023-10-25T02-53-14.013945.parquet
  • harness_hellaswag_10

    • 分割:2023_09_14T08_19_15.271974
      • 路径:**/details_harness|hellaswag|10_2023-09-14T08-19-15.271974.parquet
    • 分割:latest
      • 路径:**/details_harness|hellaswag|10_2023-09-14T08-19-15.271974.parquet
  • harness_hendrycksTest_5

    • 分割:2023_09_14T08_19_15.271974
      • 路径:**/details_harness|hendrycksTest-abstract_algebra|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-anatomy|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-astronomy|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-business_ethics|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-clinical_knowledge|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-college_biology|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-college_chemistry|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-college_computer_science|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-college_mathematics|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-college_medicine|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-college_physics|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-computer_security|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-conceptual_physics|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-econometrics|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-electrical_engineering|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-elementary_mathematics|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-formal_logic|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-global_facts|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_biology|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_chemistry|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_computer_science|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_european_history|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_geography|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_mathematics|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_physics|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_psychology|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_statistics|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_us_history|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_world_history|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-human_aging|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-human_sexuality|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-international_law|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-jurisprudence|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-logical_fallacies|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-machine_learning|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-management|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-marketing|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-medical_genetics|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-miscellaneous|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-moral_disputes|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-moral_scenarios|5_2023-09-14T08-19-15.271974.parquet
      • 路径:**/details_harness|hendrycksTest-nutrition|5_2023-09-14T08-19-15.271974.parquet
      • 路径:`**/details_harness|hendrycksTest-philosophy|5_2023-09-14T08-19-1
二维码
社区交流群
二维码
科研交流群
商业服务