遇见数据集

open-llm-leaderboard/details_TheBloke__CodeLlama-34B-Python-fp16

收藏
Hugging Face2023-10-22 更新2024-03-04 收录
官方服务:

资源简介:

该数据集是在评估模型TheBloke/CodeLlama-34B-Python-fp16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split中,split以时间戳命名,train split始终指向最新结果。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。

This dataset was automatically generated during the evaluation of the model TheBloke/CodeLlama-34B-Python-fp16. It contains 64 configurations, each corresponding to one evaluation task. The dataset is generated from two runs, with results of each run stored in separate splits named after timestamps. The train split always points to the latest results. Additionally, there is a configuration named `results` that stores the aggregated results of all runs, which is used to calculate and display 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

数据集摘要

该数据集是在评估模型 TheBloke/CodeLlama-34B-Python-fp16 在 Open 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" 分割总是指向最新的结果。
  • 一个额外的配置 "results" 存储所有运行的聚合结果,用于计算和显示聚合指标在 Open LLM Leaderboard 上。

数据加载示例

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_TheBloke__CodeLlama-34B-Python-fp16", "harness_winogrande_5", split="train")

最新结果

这些是最新的结果,来自 2023-10-22T22:16:27.646288 的运行: python { "all": { "em": 0.0014681208053691276, "em_stderr": 0.0003921042190298454, "f1": 0.047479026845637595, "f1_stderr": 0.0011836496363564649, "acc": 0.46077036907609203, "acc_stderr": 0.011810507836002033 }, "harness|drop|3": { "em": 0.0014681208053691276, "em_stderr": 0.0003921042190298454, "f1": 0.047479026845637595, "f1_stderr": 0.0011836496363564649 }, "harness|gsm8k|5": { "acc": 0.2001516300227445, "acc_stderr": 0.011021119022510191 }, "harness|winogrande|5": { "acc": 0.7213891081294396, "acc_stderr": 0.012599896649493876 } }

配置详情

  • harness_arc_challenge_25

    • 分割: 2023_08_26T02_33_13.745130
    • 路径: **/details_harness|arc:challenge|25_2023-08-26T02:33:13.745130.parquet
    • 分割: latest
    • 路径: **/details_harness|arc:challenge|25_2023-08-26T02:33:13.745130.parquet
  • harness_drop_3

    • 分割: 2023_10_22T22_16_27.646288
    • 路径: **/details_harness|drop|3_2023-10-22T22-16-27.646288.parquet
    • 分割: latest
    • 路径: **/details_harness|drop|3_2023-10-22T22-16-27.646288.parquet
  • harness_gsm8k_5

    • 分割: 2023_10_22T22_16_27.646288
    • 路径: **/details_harness|gsm8k|5_2023-10-22T22-16-27.646288.parquet
    • 分割: latest
    • 路径: **/details_harness|gsm8k|5_2023-10-22T22-16-27.646288.parquet
  • harness_hellaswag_10

    • 分割: 2023_08_26T02_33_13.745130
    • 路径: **/details_harness|hellaswag|10_2023-08-26T02:33:13.745130.parquet
    • 分割: latest
    • 路径: **/details_harness|hellaswag|10_2023-08-26T02:33:13.745130.parquet
  • harness_hendrycksTest_5

    • 分割: 2023_08_26T02_33_13.745130
    • 路径:
      • **/details_harness|hendrycksTest-abstract_algebra|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-anatomy|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-astronomy|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-business_ethics|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-college_biology|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-college_chemistry|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-college_computer_science|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-college_mathematics|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-college_medicine|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-college_physics|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-computer_security|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-conceptual_physics|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-econometrics|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-electrical_engineering|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-formal_logic|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-global_facts|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-high_school_biology|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-high_school_european_history|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-high_school_geography|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-high_school_physics|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-high_school_psychology|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-high_school_statistics|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-high_school_us_history|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-high_school_world_history|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-human_aging|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-human_sexuality|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-international_law|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-jurisprudence|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-logical_fallacies|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-machine_learning|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-management|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-marketing|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-medical_genetics|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-miscellaneous|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-moral_disputes|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-moral_scenarios|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-nutrition|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-philosophy|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-prehistory|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-professional_accounting|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-professional_law|5_2023-08-26T02:33:13.745130.parquet
      • **/details_harness|hendrycksTest-professional_medicine|5_2023-08-26T02:33:13.745130.parquet
      • `**/details_harness|
二维码
社区交流群
二维码
科研交流群
商业服务