five

open-llm-leaderboard-old/details_cognitivecomputations__WestLake-7B-v2-laser

收藏
Hugging Face2024-01-26 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_cognitivecomputations__WestLake-7B-v2-laser
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cognitivecomputations/WestLake-7B-v2-laser在Open LLM Leaderboard上的评估运行期间自动创建的。它由63个配置组成,每个配置对应一个被评估的任务。数据集是从2次运行中创建的,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。可以使用Python中的datasets库加载该数据集,如提供的代码片段所示。

该数据集是在模型cognitivecomputations/WestLake-7B-v2-laser在Open LLM Leaderboard上的评估运行期间自动创建的。它由63个配置组成,每个配置对应一个被评估的任务。数据集是从2次运行中创建的,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。可以使用Python中的datasets库加载该数据集,如提供的代码片段所示。
提供机构:
open-llm-leaderboard-old
原始信息汇总

数据集概述

数据集组成

该数据集是在模型 cognitivecomputations/WestLake-7B-v2-laser 的评估运行期间自动创建的,包含 63 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。

额外配置

一个额外的配置 "results" 存储了所有运行的聚合结果,用于计算并在 Open LLM Leaderboard 上显示聚合指标。

数据加载示例

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_cognitivecomputations__WestLake-7B-v2-laser", "harness_winogrande_5", split="train")

最新结果

以下是 最新结果 的摘要: python { "all": { "acc": 0.6534988071768002, "acc_stderr": 0.03210557694822227, "acc_norm": 0.6527320574852544, "acc_norm_stderr": 0.03278554506936746, "mc1": 0.5397796817625459, "mc1_stderr": 0.017448017223960867, "mc2": 0.67040243397608, "mc2_stderr": 0.015367489879684797 }, "harness|arc:challenge|25": { "acc": 0.7039249146757679, "acc_stderr": 0.01334091608524626, "acc_norm": 0.7329351535836177, "acc_norm_stderr": 0.012928933196496364 }, "harness|hellaswag|10": { "acc": 0.7180840470025891, "acc_stderr": 0.004490130691020432, "acc_norm": 0.8865763792073292, "acc_norm_stderr": 0.0031646183947831802 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.34, "acc_stderr": 0.04760952285695236, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695236 }, # 其他任务的结果... }

配置详情

  • config_name: harness_arc_challenge_25

    • split: 2024_01_26T03_20_53.277509
      • path: **/details_harness|arc:challenge|25_2024-01-26T03-20-53.277509.parquet
    • split: 2024_01_26T03_37_37.178822
      • path: **/details_harness|arc:challenge|25_2024-01-26T03-37-37.178822.parquet
    • split: latest
      • path: **/details_harness|arc:challenge|25_2024-01-26T03-37-37.178822.parquet
  • config_name: harness_gsm8k_5

    • split: 2024_01_26T03_20_53.277509
      • path: **/details_harness|gsm8k|5_2024-01-26T03-20-53.277509.parquet
    • split: 2024_01_26T03_37_37.178822
      • path: **/details_harness|gsm8k|5_2024-01-26T03-37-37.178822.parquet
    • split: latest
      • path: **/details_harness|gsm8k|5_2024-01-26T03-37-37.178822.parquet
  • config_name: harness_hellaswag_10

    • split: 2024_01_26T03_20_53.277509
      • path: **/details_harness|hellaswag|10_2024-01-26T03-20-53.277509.parquet
    • split: 2024_01_26T03_37_37.178822
      • path: **/details_harness|hellaswag|10_2024-01-26T03-37-37.178822.parquet
    • split: latest
      • path: **/details_harness|hellaswag|10_2024-01-26T03-37-37.178822.parquet
  • config_name: harness_hendrycksTest_5

    • split: 2024_01_26T03_20_53.277509
      • path:
        • **/details_harness|hendrycksTest-abstract_algebra|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-anatomy|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-astronomy|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-business_ethics|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-clinical_knowledge|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-college_biology|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-college_chemistry|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-college_computer_science|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-college_mathematics|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-college_medicine|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-college_physics|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-computer_security|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-conceptual_physics|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-econometrics|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-elementary_mathematics|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-formal_logic|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-global_facts|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-high_school_biology|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-high_school_chemistry|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-high_school_computer_science|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-high_school_european_history|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-high_school_geography|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-high_school_mathematics|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-high_school_physics|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-high_school_psychology|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-high_school_statistics|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-high_school_us_history|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-high_school_world_history|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-human_aging|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-human_sexuality|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-international_law|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-jurisprudence|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-logical_fallacies|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-machine_learning|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-management|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-marketing|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-medical_genetics|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-miscellaneous|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-moral_disputes|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-moral_scenarios|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-nutrition|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-philosophy|5_2024-01-26T03-20-53.277509.parquet
        • **/details_harness|hendrycksTest-prehistory|5_2024-01-26T03-20-53.277509.parquet
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