five

open-llm-leaderboard/details_psmathur__orca_mini_v3_13b

收藏
Hugging Face2023-10-18 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_psmathur__orca_mini_v3_13b
下载链接
链接失效反馈
官方服务:
资源简介:
该数据集是在Open LLM Leaderboard上对模型psmathur/orca_mini_v3_13b进行评估时自动创建的。数据集由64个配置组成,每个配置对应一个评估任务。数据集由2次运行生成,每次运行的结果作为特定配置中的一个分割,分割名称使用运行的时间戳。train分割始终指向最新结果。此外,results配置存储了所有运行的聚合结果,并用于计算和显示Open LLM Leaderboard上的聚合指标。

This dataset was automatically created during the evaluation of the model psmathur/orca_mini_v3_13b on the Open LLM Leaderboard. It consists of 64 configurations, each corresponding to one evaluation task. The dataset is generated from two runs, with the results of each run serving as a split under the corresponding configuration, and the split names use the timestamp of the run. The train split always points to the most recent results. In addition, the results configuration stores the aggregated results from all runs, which are used to calculate and display the aggregate 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 psmathur/orca_mini_v3_13bOpen LLM Leaderboard 上的自动创建的。数据集包含 64 个配置,每个配置对应一个评估任务。

数据集结构

数据集由 2 次运行创建,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" 分割总是指向最新的结果。

数据加载示例

以下是加载数据集的示例代码: python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_psmathur__orca_mini_v3_13b", "harness_winogrande_5", split="train")

最新结果

以下是 最新结果 的摘要: python { "all": { "em": 0.15383808724832215, "em_stderr": 0.0036948628598682874, "f1": 0.22225880872483197, "f1_stderr": 0.0037670501187578413, "acc": 0.44797935342421163, "acc_stderr": 0.010609253699619367 }, "harness|drop|3": { "em": 0.15383808724832215, "em_stderr": 0.0036948628598682874, "f1": 0.22225880872483197, "f1_stderr": 0.0037670501187578413 }, "harness|gsm8k|5": { "acc": 0.13115996967399546, "acc_stderr": 0.00929849923558785 }, "harness|winogrande|5": { "acc": 0.7647987371744278, "acc_stderr": 0.011920008163650884 } }

配置详情

以下是数据集的配置详情:

  • config_name: harness_arc_challenge_25

    • data_files:
      • split: 2023_08_09T21_34_12.529590
        • path: **/details_harness|arc:challenge|25_2023-08-09T21:34:12.529590.parquet
      • split: latest
        • path: **/details_harness|arc:challenge|25_2023-08-09T21:34:12.529590.parquet
  • config_name: harness_drop_3

    • data_files:
      • split: 2023_10_18T15_47_49.456107
        • path: **/details_harness|drop|3_2023-10-18T15-47-49.456107.parquet
      • split: latest
        • path: **/details_harness|drop|3_2023-10-18T15-47-49.456107.parquet
  • config_name: harness_gsm8k_5

    • data_files:
      • split: 2023_10_18T15_47_49.456107
        • path: **/details_harness|gsm8k|5_2023-10-18T15-47-49.456107.parquet
      • split: latest
        • path: **/details_harness|gsm8k|5_2023-10-18T15-47-49.456107.parquet
  • config_name: harness_hellaswag_10

    • data_files:
      • split: 2023_08_09T21_34_12.529590
        • path: **/details_harness|hellaswag|10_2023-08-09T21:34:12.529590.parquet
      • split: latest
        • path: **/details_harness|hellaswag|10_2023-08-09T21:34:12.529590.parquet
  • config_name: harness_hendrycksTest_5

    • data_files:
      • split: 2023_08_09T21_34_12.529590
        • path:
          • **/details_harness|hendrycksTest-abstract_algebra|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-anatomy|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-astronomy|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-business_ethics|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-college_biology|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-college_chemistry|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-college_computer_science|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-college_mathematics|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-college_medicine|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-college_physics|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-computer_security|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-conceptual_physics|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-econometrics|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-electrical_engineering|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-formal_logic|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-global_facts|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-high_school_biology|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-high_school_european_history|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-high_school_geography|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-high_school_physics|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-high_school_psychology|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-high_school_statistics|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-high_school_us_history|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-high_school_world_history|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-human_aging|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-human_sexuality|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-international_law|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-jurisprudence|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-logical_fallacies|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-machine_learning|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-management|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-marketing|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-medical_genetics|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-miscellaneous|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-moral_disputes|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-moral_scenarios|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-nutrition|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-philosophy|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-prehistory|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-professional_accounting|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-professional_law|5_2023-08-09T21:34:12.529590.parquet
          • **/details_harness|hendrycksTest-professional_medicine|5_2023-08-09
二维码
社区交流群
二维码
科研交流群
商业服务