open-llm-leaderboard/details_CausalLM__35b-beta2ep
收藏Hugging Face2024-04-16 更新2024-06-12 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_CausalLM__35b-beta2ep
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CausalLM/35b-beta2ep进行评估时自动创建的。数据集由63个配置组成,每个配置对应一个评估任务。数据集从1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命名。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CausalLM/35b-beta2ep进行评估时自动创建的。数据集由63个配置组成,每个配置对应一个评估任务。数据集从1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命名。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
原始信息汇总
数据集概述
数据集名称
- Pretty Name: Evaluation run of CausalLM/35b-beta2ep
- Summary: Dataset automatically created during the evaluation run of model CausalLM/35b-beta2ep on the Open LLM Leaderboard.
数据集组成
- Components: Composed of 63 configurations, each corresponding to one evaluated task.
- Creation: Created from 1 run, with each run found as a specific split named using the timestamp of the run. The "train" split always points to the latest results.
- Additional Configuration: "results" stores all aggregated results of the run, used to compute and display aggregated metrics on the Open LLM Leaderboard.
数据集加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_CausalLM__35b-beta2ep", "harness_winogrande_5", split="train")
最新结果
- Latest Results: Available from run timestamp 2024-04-16T09:48:31.478421, including detailed metrics for various tasks.
数据集详细配置
配置列表
-
Config Name: harness_arc_challenge_25
- Data Files:
- Split: 2024_04_16T09_48_31.478421
- Path: /details_harness|arc:challenge|25_2024-04-16T09-48-31.478421.parquet
- Split: latest
- Path: /details_harness|arc:challenge|25_2024-04-16T09-48-31.478421.parquet
- Split: 2024_04_16T09_48_31.478421
- Data Files:
-
Config Name: harness_gsm8k_5
- Data Files:
- Split: 2024_04_16T09_48_31.478421
- Path: /details_harness|gsm8k|5_2024-04-16T09-48-31.478421.parquet
- Split: latest
- Path: /details_harness|gsm8k|5_2024-04-16T09-48-31.478421.parquet
- Split: 2024_04_16T09_48_31.478421
- Data Files:
-
Config Name: harness_hellaswag_10
- Data Files:
- Split: 2024_04_16T09_48_31.478421
- Path: /details_harness|hellaswag|10_2024-04-16T09-48-31.478421.parquet
- Split: latest
- Path: /details_harness|hellaswag|10_2024-04-16T09-48-31.478421.parquet
- Split: 2024_04_16T09_48_31.478421
- Data Files:
-
Config Name: harness_hendrycksTest_5
- Data Files:
- Split: 2024_04_16T09_48_31.478421
- Path:
- /details_harness|hendrycksTest-abstract_algebra|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-anatomy|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-astronomy|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-business_ethics|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-clinical_knowledge|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-college_biology|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-college_chemistry|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-college_computer_science|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-college_mathematics|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-college_medicine|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-college_physics|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-computer_security|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-conceptual_physics|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-econometrics|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-electrical_engineering|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-elementary_mathematics|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-formal_logic|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-global_facts|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-high_school_biology|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-high_school_chemistry|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-high_school_computer_science|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-high_school_european_history|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-high_school_geography|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-high_school_government_and_politics|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-high_school_macroeconomics|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-high_school_mathematics|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-high_school_microeconomics|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-high_school_physics|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-high_school_psychology|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-high_school_statistics|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-high_school_us_history|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-high_school_world_history|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-human_aging|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-human_sexuality|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-international_law|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-jurisprudence|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-logical_fallacies|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-machine_learning|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-management|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-marketing|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-medical_genetics|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-miscellaneous|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-moral_disputes|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-moral_scenarios|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-nutrition|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-philosophy|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-prehistory|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-professional_accounting|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-professional_law|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-professional_medicine|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-professional_psychology|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-public_relations|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-security_studies|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-sociology|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-us_foreign_policy|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-virology|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-world_religions|5_2024-04-16T09-48-31.478421.parquet
- Path:
- Split: latest
- Path:
- /details_harness|hendrycksTest-abstract_algebra|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-anatomy|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-astronomy|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-business_ethics|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-clinical_knowledge|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-college_biology|5_2024-04-16T09-48-31.478421.parquet
- /details_harness|hendrycksTest-college_chemistry|5_2024-04-16T09-48-31.478421.parquet
- **/
- Path:
- Split: 2024_04_16T09_48_31.478421
- Data Files:



