open-llm-leaderboard-old/details_nlpguy__AlloyIngot

Name: open-llm-leaderboard-old/details_nlpguy__AlloyIngot
Creator: open-llm-leaderboard-old
Published: 2024-02-13 15:00:31
License: 暂无描述

Hugging Face2024-02-13 更新2024-06-22 收录

下载链接：

https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_nlpguy__AlloyIngot

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nlpguy/AlloyIngot进行评估时自动生成的。它包含63个配置，每个配置对应一个被评估的任务。数据集包括一次运行的结果，每次运行在每个配置中表示为特定的分割，分割名称由运行的时间戳命名。train分割始终指向最新的结果。一个额外的results配置汇总了所有运行结果，用于计算和显示Open LLM Leaderboard上的指标。可以使用datasets库中的load_dataset函数加载数据集，指定配置和分割。

提供机构：

open-llm-leaderboard-old

原始信息汇总

数据集概述

数据集信息

名称: Evaluation run of nlpguy/AlloyIngot
来源: 自动创建于模型 nlpguy/AlloyIngot 在 Open LLM Leaderboard 的评估运行期间。
组成: 包含 63 个配置，每个配置对应一个评估任务。
创建: 从 1 次运行中创建，每个运行在每个配置中作为一个特定的分割存在，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: "results" 配置存储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。

数据加载示例

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_nlpguy__AlloyIngot", "harness_winogrande_5", split="train")

最新结果

时间戳: 2024-02-13T14:57:48.240090
结果: 包含多个任务的评估结果，例如：
- harness|arc:challenge|25:
  - acc: 0.7192832764505119
  - acc_norm: 0.7397610921501706
- harness|hellaswag|10:
  - acc: 0.7204740091615216
  - acc_norm: 0.8904600677155945
- harness|hendrycksTest-abstract_algebra|5:
  - acc: 0.35
  - acc_norm: 0.35
- harness|hendrycksTest-anatomy|5:
  - acc: 0.6592592592592592
  - acc_norm: 0.6592592592592592
- harness|hendrycksTest-astronomy|5:
  - acc: 0.7105263157894737
  - acc_norm: 0.7105263157894737
- harness|hendrycksTest-business_ethics|5:
  - acc: 0.64
  - acc_norm: 0.64
- harness|hendrycksTest-clinical_knowledge|5:
  - acc: 0.7018867924528301
  - acc_norm: 0.7018867924528301
- harness|hendrycksTest-college_biology|5:
  - acc: 0.7777777777777778
  - acc_norm: 0.7777777777777778
- harness|hendrycksTest-college_chemistry|5:
  - acc: 0.5
  - acc_norm: 0.5
- harness|hendrycksTest-college_computer_science|5:
  - acc: 0.56
  - acc_norm: 0.56
- harness|hendrycksTest-college_mathematics|5:
  - acc: 0.31
  - acc_norm: 0.31
- harness|hendrycksTest-college_medicine|5:
  - acc: 0.6705202312138728
  - acc_norm: 0.6705202312138728
- harness|hendrycksTest-college_physics|5:
  - acc: 0.39215686274509803
  - acc_norm: 0.39215686274509803
- harness|hendrycksTest-computer_security|5:
  - acc: 0.75
  - acc_norm: 0.75
- harness|hendrycksTest-conceptual_physics|5:
  - acc: 0.5659574468085107
  - acc_norm: 0.5659574468085107
- harness|hendrycksTest-econometrics|5:
  - acc: 0.4473684210526316
  - acc_norm: 0.4473684210526316
- harness|hendrycksTest-electrical_engineering|5:
  - acc: 0.5586206896551724
  - acc_norm: 0.5586206896551724
- harness|hendrycksTest-elementary_mathematics|5:
  - acc: 0.4074074074074074
  - acc_norm: 0.4074074074074074
- harness|hendrycksTest-formal_logic|5:
  - acc: 0.48412698412698413
  - acc_norm: 0.48412698412698413
- harness|hendrycksTest-global_facts|5:
  - acc: 0.31
  - acc_norm: 0.31
- harness|hendrycksTest-high_school_biology|5:
  - acc: 0.7903225806451613
  - acc_norm: 0.7903225806451613
- harness|hendrycksTest-high_school_chemistry|5:
  - acc: 0.5073891625615764
  - acc_norm: 0.5073891625615764
- harness|hendrycksTest-high_school_computer_science|5:
  - acc: 0.71
  - acc_norm: 0.71
- harness|hendrycksTest-high_school_european_history|5:
  - acc: 0.7515151515151515
  - acc_norm: 0.7515151515151515
- harness|hendrycksTest-high_school_geography|5:
  - acc: 0.8131313131313131
  - acc_norm: 0.8131313131313131
- harness|hendrycksTest-high_school_government_and_politics|5:
  - acc: 0.9067357512953368
  - acc_norm: 0.9067357512953368
- harness|hendrycksTest-high_school_macroeconomics|5:
  - acc: 0.6717948717948717
  - acc_norm: 0.6717948717948717
- harness|hendrycksTest-high_school_mathematics|5:
  - acc: 0.32592592592592595
  - acc_norm: 0.32592592592592595
- harness|hendrycksTest-high_school_microeconomics|5:
  - acc: 0.6638655462184874
  - acc_norm: 0.6638655462184874
- harness|hendrycksTest-high_school_physics|5:
  - acc: 0.3973509933774834
  - acc_norm: 0.3973509933774834
- harness|hendrycksTest-high_school_psychology|5:
  - acc: 0.8385321100917431
  - acc_norm: 0.8385321100917431
- harness|hendrycksTest-high_school_statistics|5:
  - acc: 0.5046296296296297
  - acc_norm: 0.5046296296296297
- harness|hendrycksTest-high_school_us_history|5:
  - acc: 0.8382352941176471
  - acc_norm: 0.8382352941176471
- harness|hendrycksTest-high_school_world_history|5:
  - acc: 0.8059071729957806
  - acc_norm: 0.8059071729957806
- harness|hendrycksTest-human_aging|5:
  - acc: 0.6860986547085202
  - acc_norm: 0.6860986547085202
- harness|hendrycksTest-human_sexuality|5:
  - acc: 0.8015267175572519
  - acc_norm: 0.8015267175572519
- harness|hendrycksTest-international_law|5:
  - acc: 0.7851239669421488
  - acc_norm: 0.7851239669421488
- harness|hendrycksTest-jurisprudence|5:
  - acc: 0.7962962962962963
  - acc_norm: 0.7962962962962963
- harness|hendrycksTest-logical_fallacies|5:
  - acc: 0.7730061349693251
  - acc_norm: 0.7730061349693251
- harness|hendrycksTest-machine_learning|5:
  - acc: 0.42857142857142855
  - acc_norm: 0.42857142857142855
- harness|hendrycksTest-management|5:
  - acc: 0.7572815533980582
  - acc_norm: 0.7572815533980582
- harness|hendrycksTest-marketing|5:
  - acc: 0.8803418803418803
  - acc_norm: 0.8803418803418803
- harness|hendrycksTest-medical_genetics|5:
  - acc: 0.71
  - acc_norm: 0.71
- harness|hendrycksTest-miscellaneous|5:
  - acc: 0.8237547892720306
  - acc_norm: 0.8237547892720306
- harness|hendrycksTest-moral_disputes|5:
  - acc: 0.7456647398843931
  - acc_norm: 0.7456647398843931
- harness|hendrycksTest-moral_scenarios|5:
  - acc: 0.45027932960893857
  - acc_norm: 0.45027932960893857
- harness|hendrycksTest-nutrition|5:
  - acc: 0.7320261437908496
  - acc_norm: 0.7320261437908496
- harness|hendrycksTest-philosophy|5:
  - acc: 0.7106109324758842
  - acc_norm: 0.7106109324758842
- harness|hendrycksTest-prehistory|5:
  - acc: 0.7469135802469136
  - acc_norm: 0.7469135802469136
- harness|hendrycksTest-professional_accounting|5:
  - acc: 0.4858156028368794
  - acc_norm: 0.4858156028368794
- harness|hendrycksTest-professional_law|5:
  - acc: 0.47522816166883963
  - acc_norm: 0.47522816166883963
- harness|hendrycksTest-professional_medicine|5:
  - acc: 0.6764705882352942
  - acc_norm: 0.6764705882352942
- harness|hendrycksTest-professional_psychology|5:
  - acc: 0.6715686274509803
  - acc_norm: 0.6715686274509803
- harness|hendrycksTest-public_relations|5:
  - acc: 0.6818181818181818
  - acc_norm: 0.6818181818181818
- harness|hendrycksTest-security_studies|5:
  - acc: 0.7428571428571429
  - acc_norm: 0.7428571428571429
- harness|hendrycksTest-sociology|5:
  - acc: 0.835820895522388
  - acc_norm: 0.835820895522388
- harness|hendrycksTest-us_foreign_policy|5:

5,000+

优质数据集

54 个

任务类型

进入经典数据集