five

open-llm-leaderboard/details_migtissera__Synthia-70B-v1.2

收藏
Hugging Face2023-10-17 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_migtissera__Synthia-70B-v1.2
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migtissera/Synthia-70B-v1.2时自动生成的,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分割中,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,还有一个名为results的配置,存储了所有运行的聚合结果,用于在Open LLM Leaderboard上计算和显示聚合指标。

该数据集是在评估模型migtissera/Synthia-70B-v1.2时自动生成的,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分割中,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,还有一个名为results的配置,存储了所有运行的聚合结果,用于在Open LLM Leaderboard上计算和显示聚合指标。
提供机构:
open-llm-leaderboard
原始信息汇总

数据集概述

该数据集是在评估模型 migtissera/Synthia-70B-v1.2Open LLM Leaderboard 上的自动创建的。

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。

额外配置

  • 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。

加载数据示例

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_migtissera__Synthia-70B-v1.2", "harness_winogrande_5", split="train")

最新结果

以下是 2023-10-17T14:51:20.480254 运行的最新结果: python { "all": { "em": 0.364618288590604, "em_stderr": 0.004929197624393639, "f1": 0.42417365771812215, "f1_stderr": 0.004776577842624861, "acc": 0.5759284047791582, "acc_stderr": 0.011665477241539865 }, "harness|drop|3": { "em": 0.364618288590604, "em_stderr": 0.004929197624393639, "f1": 0.42417365771812215, "f1_stderr": 0.004776577842624861 }, "harness|gsm8k|5": { "acc": 0.3191811978771797, "acc_stderr": 0.012840345676251651 }, "harness|winogrande|5": { "acc": 0.8326756116811366, "acc_stderr": 0.010490608806828079 } }

配置详情

配置列表

  • harness_arc_challenge_25
  • harness_drop_3
  • harness_gsm8k_5
  • harness_hellaswag_10
  • harness_hendrycksTest_5
  • harness_hendrycksTest_abstract_algebra_5
  • harness_hendrycksTest_anatomy_5
  • harness_hendrycksTest_astronomy_5
  • harness_hendrycksTest_business_ethics_5
  • harness_hendrycksTest_clinical_knowledge_5
  • harness_hendrycksTest_college_biology_5
  • harness_hendrycksTest_college_chemistry_5
  • harness_hendrycksTest_college_computer_science_5
  • harness_hendrycksTest_college_mathematics_5
  • harness_hendrycksTest_college_medicine_5
  • harness_hendrycksTest_college_physics_5
  • harness_hendrycksTest_computer_security_5
  • harness_hendrycksTest_conceptual_physics_5
  • harness_hendrycksTest_econometrics_5
  • harness_hendrycksTest_electrical_engineering_5
  • harness_hendrycksTest_elementary_mathematics_5
  • harness_hendrycksTest_formal_logic_5
  • harness_hendrycksTest_global_facts_5
  • harness_hendrycksTest_high_school_biology_5
  • harness_hendrycksTest_high_school_chemistry_5
  • harness_hendrycksTest_high_school_computer_science_5
  • harness_hendrycksTest_high_school_european_history_5
  • harness_hendrycksTest_high_school_geography_5
  • harness_hendrycksTest_high_school_government_and_politics_5
  • harness_hendrycksTest_high_school_macroeconomics_5
  • harness_hendrycksTest_high_school_mathematics_5
  • harness_hendrycksTest_high_school_microeconomics_5
  • harness_hendrycksTest_high_school_physics_5
  • harness_hendrycksTest_high_school_psychology_5
  • harness_hendrycksTest_high_school_statistics_5
  • harness_hendrycksTest_high_school_us_history_5
  • harness_hendrycksTest_high_school_world_history_5
  • harness_hendrycksTest_human_aging_5
  • harness_hendrycksTest_human_sexuality_5
  • harness_hendrycksTest_international_law_5
  • harness_hendrycksTest_jurisprudence_5
  • harness_hendrycksTest_logical_fallacies_5
  • harness_hendrycksTest_machine_learning_5
  • harness_hendrycksTest_management_5
  • harness_hendrycksTest_marketing_5
  • harness_hendrycksTest_medical_genetics_5
  • harness_hendrycksTest_miscellaneous_5
  • harness_hendrycksTest_moral_disputes_5
  • harness_hendrycksTest_moral_scenarios_5
  • harness_hendrycksTest_nutrition_5
  • harness_hendrycksTest_philosophy_5
  • harness_hendrycksTest_prehistory_5
  • harness_hendrycksTest_professional_accounting_5
  • harness_hendrycksTest_professional_law_5
  • harness_hendrycksTest_professional_medicine_5
  • harness_hendrycksTest_professional_psychology_5
  • harness_hendrycksTest_public_relations_5
  • harness_hendrycksTest_security_studies_5
  • harness_hendrycksTest_sociology_5
  • harness_hendrycksTest_us_foreign_policy_5
  • harness_hendrycksTest_virology_5
  • harness_hendrycksTest_world_religions_5

数据文件路径

每个配置包含多个数据文件路径,例如:

  • harness_arc_challenge_25 包含 details_harness|arc:challenge|25_2023-09-02T17:59:05.420313.parquet
  • harness_drop_3 包含 details_harness|drop|3_2023-10-17T14-51-20.480254.parquet
  • harness_gsm8k_5 包含 details_harness|gsm8k|5_2023-10-17T14-51-20.480254.parquet
  • harness_hellaswag_10 包含 details_harness|hellaswag|10_2023-09-02T17:59:05.420313.parquet
  • harness_hendrycksTest_5 包含多个文件路径,如 details_harness|hendrycksTest-abstract_algebra|5_2023-09-02T17:59:05.420313.parquet 等。

每个配置的数据文件路径分为两个分割:2023_09_02T17_59_05.420313latest

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