five

open-llm-leaderboard/details_PY007__TinyLlama-1.1B-Chat-v0.3

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_PY007__TinyLlama-1.1B-Chat-v0.3
下载链接
链接失效反馈
官方服务:
资源简介:
该数据集是在评估模型PY007/TinyLlama-1.1B-Chat-v0.3时自动创建的,主要用于Open LLM Leaderboard的评估任务。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2次运行生成,每次运行的结果存储在不同的split中,split以运行的时间戳命名。此外,数据集还包含一个名为"results"的配置,用于存储所有运行的聚合结果,并用于计算和展示在Open LLM Leaderboard上的聚合指标。

Automatically created during the evaluation of the model PY007/TinyLlama-1.1B-Chat-v0.3, this dataset is primarily designed for evaluation tasks on the Open LLM Leaderboard. The dataset consists of 64 configurations, each corresponding to one evaluation task. It is generated from two runs, with the results of each run stored in a separate split named after the run's timestamp. In addition, the dataset also includes a configuration named "results", which is used to store the aggregated results of all runs and to calculate and display the aggregated metrics on the Open LLM Leaderboard.
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 PY007/TinyLlama-1.1B-Chat-v0.3Open LLM Leaderboard 上的运行过程中自动创建的。

数据集结构

  • 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。
  • 一个额外的配置 "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_PY007__TinyLlama-1.1B-Chat-v0.3", "harness_winogrande_5", split="train")

最新结果

以下是 2023-10-23T05:46:52.405812 运行 的最新结果: python { "all": { "em": 0.0035654362416107383, "em_stderr": 0.0006104082299890309, "f1": 0.04627936241610745, "f1_stderr": 0.0012734567743311978, "acc": 0.2918883921652635, "acc_stderr": 0.00807629623065548 }, "harness|drop|3": { "em": 0.0035654362416107383, "em_stderr": 0.0006104082299890309, "f1": 0.04627936241610745, "f1_stderr": 0.0012734567743311978 }, "harness|gsm8k|5": { "acc": 0.006823351023502654, "acc_stderr": 0.002267537102254483 }, "harness|winogrande|5": { "acc": 0.5769534333070244, "acc_stderr": 0.013885055359056474 } }

配置详情

  • harness_arc_challenge_25

    • 分割:2023_10_04T07_14_39.217680
      • 路径:**/details_harness|arc:challenge|25_2023-10-04T07-14-39.217680.parquet
    • 分割:latest
      • 路径:**/details_harness|arc:challenge|25_2023-10-04T07-14-39.217680.parquet
  • harness_drop_3

    • 分割:2023_10_23T05_46_52.405812
      • 路径:**/details_harness|drop|3_2023-10-23T05-46-52.405812.parquet
    • 分割:latest
      • 路径:**/details_harness|drop|3_2023-10-23T05-46-52.405812.parquet
  • harness_gsm8k_5

    • 分割:2023_10_23T05_46_52.405812
      • 路径:**/details_harness|gsm8k|5_2023-10-23T05-46-52.405812.parquet
    • 分割:latest
      • 路径:**/details_harness|gsm8k|5_2023-10-23T05-46-52.405812.parquet
  • harness_hellaswag_10

    • 分割:2023_10_04T07_14_39.217680
      • 路径:**/details_harness|hellaswag|10_2023-10-04T07-14-39.217680.parquet
    • 分割:latest
      • 路径:**/details_harness|hellaswag|10_2023-10-04T07-14-39.217680.parquet
  • harness_hendrycksTest_5

    • 分割:2023_10_04T07_14_39.217680
      • 路径:
        • **/details_harness|hendrycksTest-abstract_algebra|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-anatomy|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-astronomy|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-business_ethics|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-clinical_knowledge|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-college_biology|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-college_chemistry|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-college_computer_science|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-college_mathematics|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-college_medicine|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-college_physics|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-computer_security|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-conceptual_physics|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-econometrics|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-electrical_engineering|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-elementary_mathematics|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-formal_logic|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-global_facts|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-high_school_biology|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-high_school_chemistry|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-high_school_computer_science|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-high_school_european_history|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-high_school_geography|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-high_school_mathematics|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-high_school_physics|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-high_school_psychology|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-high_school_statistics|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-high_school_us_history|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-high_school_world_history|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-human_aging|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-human_sexuality|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-international_law|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-jurisprudence|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-logical_fallacies|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-machine_learning|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-management|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-marketing|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-medical_genetics|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-miscellaneous|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-moral_disputes|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-moral_scenarios|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-nutrition|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-philosophy|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-prehistory|5_2023-10-04T07-14-39.217680.parquet
        • **/details_harness|hendrycksTest-professional_accounting|5_2023-10-04T07-14-39.217680.parquet
        • `**/details_harness|hendrycksTest-professional_law|5_2023-10-04T07
二维码
社区交流群
二维码
科研交流群
商业服务