open-llm-leaderboard/details_tiiuae__falcon-40b
收藏Hugging Face2023-12-03 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_tiiuae__falcon-40b
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tiiuae/falcon-40b进行评估时自动生成的。数据集包含124个配置,每个配置对应一个被评估的任务。数据集由6次运行生成,每次运行在每个配置中作为一个特定的分割,分割名称使用运行的时间戳。train分割始终指向最新的结果。此外,还有一个名为results的配置,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还提供了一个使用`datasets`库中的`load_dataset`函数加载运行细节的示例。
提供机构:
open-llm-leaderboard
原始信息汇总
数据集概述
数据集名称
Evaluation run of tiiuae/falcon-40b
数据集摘要
该数据集是在评估模型 tiiuae/falcon-40b 在 Open LLM Leaderboard 上的自动创建的。
数据集组成
- 该数据集包含 124 个配置,每个配置对应一个评估任务。
- 数据集从 6 次运行中创建。每个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 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-40b", "harness_gsm8k_5", split="train")
最新结果
以下是 2023-12-03T19:45:58.201621 运行 的最新结果: python { "all": { "acc": 0.21455648218347234, "acc_stderr": 0.011307604104052885 }, "harness|gsm8k|5": { "acc": 0.21455648218347234, "acc_stderr": 0.011307604104052885 } }
配置详情
-
config_name: harness_arc_challenge_25
- split: 2023_08_21T22_49_59.134750
- path: **/details_harness|arc:challenge|25_2023-08-21T22:49:59.134750.parquet
- split: latest
- path: **/details_harness|arc:challenge|25_2023-08-21T22:49:59.134750.parquet
- split: 2023_08_21T22_49_59.134750
-
config_name: harness_drop_3
- split: 2023_09_08T21_43_04.856041
- path: **/details_harness|drop|3_2023-09-08T21-43-04.856041.parquet
- split: latest
- path: **/details_harness|drop|3_2023-09-08T21-43-04.856041.parquet
- split: 2023_09_08T21_43_04.856041
-
config_name: harness_gsm8k_5
- split: 2023_09_08T21_43_04.856041
- path: **/details_harness|gsm8k|5_2023-09-08T21-43-04.856041.parquet
- split: 2023_12_03T19_45_58.201621
- path: **/details_harness|gsm8k|5_2023-12-03T19-45-58.201621.parquet
- split: latest
- path: **/details_harness|gsm8k|5_2023-12-03T19-45-58.201621.parquet
- split: 2023_09_08T21_43_04.856041
-
config_name: harness_hellaswag_10
- split: 2023_08_21T22_49_59.134750
- path: **/details_harness|hellaswag|10_2023-08-21T22:49:59.134750.parquet
- split: latest
- path: **/details_harness|hellaswag|10_2023-08-21T22:49:59.134750.parquet
- split: 2023_08_21T22_49_59.134750
-
config_name: harness_hendrycksTest_0
- split: 2023_08_21T11_07_51.058817
- path: **/details_harness|hendrycksTest-abstract_algebra|0_2023-08-21T11:07:51.058817.parquet
- split: 2023_08_21T11_30_10.858708
- path: **/details_harness|hendrycksTest-abstract_algebra|0_2023-08-21T11:30:10.858708.parquet
- split: latest
- path: **/details_harness|hendrycksTest-abstract_algebra|0_2023-08-21T11:30:10.858708.parquet
- split: 2023_08_21T11_07_51.058817
-
config_name: harness_hendrycksTest_5
- split: 2023_08_21T22_49_59.134750
- path: **/details_harness|hendrycksTest-abstract_algebra|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-anatomy|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-astronomy|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-business_ethics|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-college_biology|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-college_chemistry|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-college_computer_science|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-college_mathematics|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-college_medicine|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-college_physics|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-computer_security|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-conceptual_physics|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-econometrics|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-electrical_engineering|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-formal_logic|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-global_facts|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-high_school_biology|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-high_school_european_history|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-high_school_geography|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-high_school_physics|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-high_school_psychology|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-high_school_statistics|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-high_school_us_history|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-high_school_world_history|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-human_aging|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-human_sexuality|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-international_law|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-jurisprudence|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-logical_fallacies|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-machine_learning|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-management|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-marketing|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-medical_genetics|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-miscellaneous|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-moral_disputes|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-moral_scenarios|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-nutrition|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-philosophy|5_2023-08-21T22:49:59.134750.parquet
- path: **/details_harness|hendrycksTest-prehistory|5_2023-08-21T22:49:59.13475
- split: 2023_08_21T22_49_59.134750



