open-llm-leaderboard/details_tiiuae__falcon-11B
收藏Hugging Face2024-05-10 更新2024-06-12 收录
下载链接：
https://hf-mirror.com/datasets/open-llm-leaderboard/details_tiiuae__falcon-11B
下载链接
链接失效反馈官方服务：
资源简介：
该数据集是在模型tiiuae/falcon-11B在Open LLM Leaderboard上的评估运行期间自动创建的。数据集由63个配置组成，每个配置对应一个被评估的任务。数据集是从2次运行中生成的，每次运行在每个配置中表示为特定的分割。train分割始终指向最新的结果。一个名为results的额外配置存储了所有运行的聚合结果，这些结果用于计算和显示Open LLM Leaderboard上的聚合指标。README还提供了如何使用Python中的datasets库加载数据集的示例。
该数据集是在模型tiiuae/falcon-11B在Open LLM Leaderboard上的评估运行期间自动创建的。数据集由63个配置组成，每个配置对应一个被评估的任务。数据集是从2次运行中生成的，每次运行在每个配置中表示为特定的分割。train分割始终指向最新的结果。一个名为results的额外配置存储了所有运行的聚合结果，这些结果用于计算和显示Open LLM Leaderboard上的聚合指标。README还提供了如何使用Python中的datasets库加载数据集的示例。
提供机构：
open-llm-leaderboard
原始信息汇总
数据集概述
该数据集是在评估模型 tiiuae/falcon-11B 在 Open LLM Leaderboard 上的自动创建的。
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。
- 数据集从 2 次运行中创建。每次运行可以在每个配置中作为一个特定的分片找到，分片名称使用运行的时间戳。
- "train" 分片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_tiiuae__falcon-11B_private", "harness_winogrande_5", split="train")
最新结果
以下是 2024-05-10T12:57:08.635343 运行 的最新结果： python { "all": { "acc": 0.7829518547750592, "acc_stderr": 0.01158587171020941 }, "harness|winogrande|5": { "acc": 0.7829518547750592, "acc_stderr": 0.01158587171020941 } }
配置详情
-
config_name: harness_arc_challenge_25
- 分片: 2024_05_10T12_22_42.795732
- 路径: **/details_harness|arc:challenge|25_2024-05-10T12-22-42.795732.parquet
- 分片: latest
- 路径: **/details_harness|arc:challenge|25_2024-05-10T12-22-42.795732.parquet
- 分片: 2024_05_10T12_22_42.795732
-
config_name: harness_gsm8k_5
- 分片: 2024_05_10T12_22_42.795732
- 路径: **/details_harness|gsm8k|5_2024-05-10T12-22-42.795732.parquet
- 分片: latest
- 路径: **/details_harness|gsm8k|5_2024-05-10T12-22-42.795732.parquet
- 分片: 2024_05_10T12_22_42.795732
-
config_name: harness_hellaswag_10
- 分片: 2024_05_10T12_22_42.795732
- 路径: **/details_harness|hellaswag|10_2024-05-10T12-22-42.795732.parquet
- 分片: latest
- 路径: **/details_harness|hellaswag|10_2024-05-10T12-22-42.795732.parquet
- 分片: 2024_05_10T12_22_42.795732
-
config_name: harness_hendrycksTest_5
- 分片: 2024_05_10T12_22_42.795732
- 路径:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-global_facts|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-high_school_computer_science|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-high_school_european_history|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-high_school_geography|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-high_school_mathematics|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-high_school_physics|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-high_school_psychology|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-high_school_statistics|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-high_school_us_history|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-high_school_world_history|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-human_aging|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-human_sexuality|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-international_law|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-jurisprudence|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-logical_fallacies|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-machine_learning|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-management|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-marketing|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-medical_genetics|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-miscellaneous|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-moral_disputes|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-moral_scenarios|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-nutrition|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-philosophy|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-prehistory|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-professional_accounting|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-professional_law|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-professional_medicine|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-professional_psychology|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-public_relations|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-security_studies|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-sociology|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-us_foreign_policy|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-virology|5_2024-05-10T12-22-42.795732.parquet
- **/details_harness|hendrycksTest-world_religions|5_2024-05-10T12-22-42.795732.parquet
- 路径:
- 分片: latest
- 路径:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-05-10T1
- 路径:
- 分片: 2024_05_10T12_22_42.795732
