open-llm-leaderboard-old/details_marcchew__test1
收藏Hugging Face2023-12-03 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_marcchew__test1
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marcchew/test1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3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,还有一个名为results的配置,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。
该数据集是在Open LLM Leaderboard上对模型marcchew/test1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3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,还有一个名为results的配置,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。
提供机构:
open-llm-leaderboard-old
原始信息汇总
数据集概述
该数据集是在模型 marcchew/test1 在 Open LLM Leaderboard 上的评估运行期间自动创建的。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 3 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
以下是加载特定运行详细信息的示例代码:
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_marcchew__test1", "harness_gsm8k_5", split="train")
最新结果
以下是 最新结果 from run 2023-12-03T19:35:56.043440 的示例:
python { "all": { "acc": 0.0, "acc_stderr": 0.0 }, "harness|gsm8k|5": { "acc": 0.0, "acc_stderr": 0.0 } }
配置详情
以下是数据集的配置详情:
-
config_name: harness_arc_challenge_25
- split: 2023_09_01T15_41_12.486637
- path: **/details_harness|arc:challenge|25_2023-09-01T15:41:12.486637.parquet
- split: latest
- path: **/details_harness|arc:challenge|25_2023-09-01T15:41:12.486637.parquet
- split: 2023_09_01T15_41_12.486637
-
config_name: harness_drop_3
- split: 2023_10_13T02_23_20.616276
- path: **/details_harness|drop|3_2023-10-13T02-23-20.616276.parquet
- split: latest
- path: **/details_harness|drop|3_2023-10-13T02-23-20.616276.parquet
- split: 2023_10_13T02_23_20.616276
-
config_name: harness_gsm8k_5
- split: 2023_10_13T02_23_20.616276
- path: **/details_harness|gsm8k|5_2023-10-13T02-23-20.616276.parquet
- split: 2023_12_03T19_35_56.043440
- path: **/details_harness|gsm8k|5_2023-12-03T19-35-56.043440.parquet
- split: latest
- path: **/details_harness|gsm8k|5_2023-12-03T19-35-56.043440.parquet
- split: 2023_10_13T02_23_20.616276
-
config_name: harness_hellaswag_10
- split: 2023_09_01T15_41_12.486637
- path: **/details_harness|hellaswag|10_2023-09-01T15:41:12.486637.parquet
- split: latest
- path: **/details_harness|hellaswag|10_2023-09-01T15:41:12.486637.parquet
- split: 2023_09_01T15_41_12.486637
-
config_name: harness_hendrycksTest_5
- split: 2023_09_01T15_41_12.486637
- path:
- **/details_harness|hendrycksTest-abstract_algebra|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-anatomy|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-astronomy|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-college_biology|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-college_physics|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-computer_security|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-econometrics|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-global_facts|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-high_school_computer_science|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-high_school_european_history|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-high_school_geography|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-high_school_mathematics|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-high_school_physics|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-high_school_psychology|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-high_school_statistics|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-high_school_us_history|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-high_school_world_history|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-human_aging|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-human_sexuality|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-international_law|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-jurisprudence|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-logical_fallacies|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-machine_learning|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-management|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-marketing|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-medical_genetics|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-miscellaneous|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-moral_disputes|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-moral_scenarios|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-nutrition|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-philosophy|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-prehistory|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-professional_accounting|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-professional_law|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-professional_medicine|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-professional_psychology|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-public_relations|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-security_studies|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-sociology|5_2023-09-01T15:41:12.486637.parquet
- **/details_harness|hendrycksTest-us_foreign_policy|5_2023-09-01T15:41:12.486637.parquet
- path:
- split: 2023_09_01T15_41_12.486637



