five

open-llm-leaderboard-old/details_Josephgflowers__Cinder-Phi-2-STEM-2.94B-Test

收藏
Hugging Face2024-02-18 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_Josephgflowers__Cinder-Phi-2-STEM-2.94B-Test
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Josephgflowers/Cinder-Phi-2-STEM-2.94B-Test时自动创建的,用于在Open LLM Leaderboard上进行评估。数据集包含63个配置,每个配置对应一个评估任务。数据集由1次运行生成,每次运行的结果作为一个特定的分割存储,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,results配置存储了所有运行的聚合结果,用于计算和显示在Open LLM Leaderboard上的聚合指标。

该数据集是在评估模型Josephgflowers/Cinder-Phi-2-STEM-2.94B-Test时自动创建的,用于在Open LLM Leaderboard上进行评估。数据集包含63个配置,每个配置对应一个评估任务。数据集由1次运行生成,每次运行的结果作为一个特定的分割存储,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,results配置存储了所有运行的聚合结果,用于计算和显示在Open LLM Leaderboard上的聚合指标。
提供机构:
open-llm-leaderboard-old
原始信息汇总

数据集概述

该数据集是在对模型 Josephgflowers/Cinder-Phi-2-STEM-2.94B-Test 进行评估运行期间自动创建的,用于 Open LLM Leaderboard

数据集组成

  • 数据集包含 63 个配置,每个配置对应一个评估任务。
  • 数据集由 1 次运行创建,每个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。

最新结果

以下是 2024-02-18T21:11:21.388297 运行的最新结果

python { "all": { "acc": 0.5404779880547149, "acc_stderr": 0.03420607205397175, "acc_norm": 0.5423995332876018, "acc_norm_stderr": 0.03492031397648617, "mc1": 0.31334149326805383, "mc1_stderr": 0.01623806506905961, "mc2": 0.4645879274122728, "mc2_stderr": 0.015303792729334064 }, "harness|arc:challenge|25": { "acc": 0.5401023890784983, "acc_stderr": 0.01456431885692485, "acc_norm": 0.5708191126279863, "acc_norm_stderr": 0.014464085894870655 }, "harness|hellaswag|10": { "acc": 0.5427205735909182, "acc_stderr": 0.004971534874389939, "acc_norm": 0.7220673172674766, "acc_norm_stderr": 0.0044706448452428976 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.33, "acc_stderr": 0.04725815626252606, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252606 }, # 其他任务的结果... }

配置详情

  • harness_arc_challenge_25

    • 分割:2024_02_18T21_11_21.388297
    • 路径:**/details_harness|arc:challenge|25_2024-02-18T21-11-21.388297.parquet
    • 分割:latest
    • 路径:**/details_harness|arc:challenge|25_2024-02-18T21-11-21.388297.parquet
  • harness_gsm8k_5

    • 分割:2024_02_18T21_11_21.388297
    • 路径:**/details_harness|gsm8k|5_2024-02-18T21-11-21.388297.parquet
    • 分割:latest
    • 路径:**/details_harness|gsm8k|5_2024-02-18T21-11-21.388297.parquet
  • harness_hellaswag_10

    • 分割:2024_02_18T21_11_21.388297
    • 路径:**/details_harness|hellaswag|10_2024-02-18T21-11-21.388297.parquet
    • 分割:latest
    • 路径:**/details_harness|hellaswag|10_2024-02-18T21-11-21.388297.parquet
  • harness_hendrycksTest_5

    • 分割:2024_02_18T21_11_21.388297
    • 路径:
      • **/details_harness|hendrycksTest-abstract_algebra|5_2024-02-18T21-11-21.388297.parquet
      • **/details_harness|hendrycksTest-anatomy|5_2024-02-18T21-11-21.388297.parquet
      • **/details_harness|hendrycksTest-astronomy|5_2024-02-18T21-11-21.388297.parquet
      • **/details_harness|hendrycksTest-business_ethics|5_2024-02-18T21-11-21.388297.parquet
      • **/details_harness|hendrycksTest-clinical_knowledge|5_2024-02-18T21-11-21.388297.parquet
      • **/details_harness|hendrycksTest-college_biology|5_2024-02-18T21-11-21.388297.parquet
      • **/details_harness|hendrycksTest-college_chemistry|5_2024-02-18T21-11-21.388297.parquet
      • **/details_harness|hendrycksTest-college_computer_science|5_2024-02-18T21-11-21.388297.parquet
      • **/details_harness|hendrycksTest-college_mathematics|5_2024-02-18T21-11-21.388297.parquet
      • **/details_harness|hendrycksTest-college_medicine|5_2024-02-18T21-11-21.388297.parquet
      • **/details_harness|hendrycksTest-college_physics|5_2024-02-18T21-11-21.388297.parquet
      • **/details_harness|hendrycksTest-computer_security|5_2024-02-18T21-11-21.388297.parquet
      • **/details_harness|hendrycksTest-conceptual_physics|5_2024-02-18T21-11-21.388297.parquet
      • **/details_harness|hendrycksTest-econometrics|5_2024-02-18T21-11-21.388297.parquet
      • **/details_harness|hendrycksTest-electrical_engineering|5_2024-02-18T21-11-21.388297.parquet
      • **/details_harness|hendrycksTest-elementary_mathematics|5_2024-02-18T21-11-21.388297.parquet
      • **/details_harness|hendrycksTest-formal_logic|5_2024-02-18T21-11-21.388297.parquet
      • **/details_harness|hendrycksTest-global_facts|5_2024-02-18T21-11-21.388297.parquet
    • 分割:latest
    • 路径:
      • **/details_harness|hendrycksTest-abstract_algebra|5_2024-02-18T21-11-21.388297.parquet
      • **/details_harness|hendrycksTest-anatomy|5_2024-02-18T21-11-21.388297.parquet
      • **/details_harness|hendrycksTest-astronomy|5_2024-02-18T21-11-21.388297.parquet
      • **/details_harness|hendrycksTest-business_ethics|5_2024-02-18T21-11-21.388297.parquet
      • **/details_harness|hendrycksTest-clinical_knowledge|5_2024-02-18T21-11-21.388297.parquet
      • **/details_harness|hendrycksTest-college_biology|5_2024-02-18T21-11-21.388297.parquet
      • **/details_harness|hendrycksTest-college_chemistry|5_2024-02-18T21-11-21.388297.parquet
      • **/details_harness|hendrycksTest-college_computer_science|5_2024-02-18T21-11-21.388297.parquet
      • **/details_harness|hendrycksTest-college_mathematics|5_2024-02-18T21-11-21.388297.parquet
      • **/details_harness|hendrycksTest-college_medicine|5_2024-02-18T21-11-21.388297.parquet
      • **/details_harness|hendrycksTest-college_physics|5_2024-02-18T21-11-21.388297.parquet
      • **/details_harness|hendrycksTest-computer_security|5_2024-02-18T21-11-21.388297.parquet
      • **/details_harness|hendrycksTest-conceptual_physics|5_2024-02-18T21-11-21.388297.parquet
      • **/details_harness|hendrycksTest-econometrics|5_2024-02-18T21-11-21.388297.parquet
      • **/details_harness|hendrycksTest-electrical_engineering|5_2024-02-18T21-11-21.388297.parquet
      • **/details_harness|hendrycksTest-elementary_mathematics|5_2024-02-18T21-11-21.388297.parquet
      • **/details_harness|hendrycksTest-formal_logic|5_2024-02-18T21-11-21.388297.parquet
      • **/details_harness|hendrycksTest-global_facts|5_2024-02-18T21-11-21.388297.parquet }

加载数据集示例

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_Josephgflowers__Cinder-Phi-2-STEM-2.94B-Test", "harness_winogrande_5", split="train")

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