open-llm-leaderboard/details_TigerResearch__tigerbot-70b-chat
收藏数据集概述
数据集简介
该数据集是在评估模型 TigerResearch/tigerbot-70b-chat 的过程中自动创建的,用于 Open LLM Leaderboard。
数据集组成
数据集包含 64 个配置,每个配置对应一个评估任务。数据集由 4 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,用于计算并在 Open LLM Leaderboard 上显示聚合指标。
数据加载示例
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_TigerResearch__tigerbot-70b-chat", "harness_winogrande_5", split="train")
最新结果
以下是 最新结果 的示例: python { "all": { "em": 0.43791946308724833, "em_stderr": 0.005080846199755935, "f1": 0.47991820469798696, "f1_stderr": 0.004915876956213108, "acc": 0.6161274146961446, "acc_stderr": 0.012720219505629717 }, "harness|drop|3": { "em": 0.43791946308724833, "em_stderr": 0.005080846199755935, "f1": 0.47991820469798696, "f1_stderr": 0.004915876956213108 }, "harness|gsm8k|5": { "acc": 0.4564063684609553, "acc_stderr": 0.013720038270485325 }, "harness|winogrande|5": { "acc": 0.7758484609313339, "acc_stderr": 0.011720400740774106 } }
配置详情
以下是数据集的配置详情:
-
config_name: harness_arc_challenge_25
- split: 2023_09_13T04_03_35.733983
- path: **/details_harness|arc:challenge|25_2023-09-13T04-03-35.733983.parquet
- split: 2023_09_13T04_21_04.931146
- path: **/details_harness|arc:challenge|25_2023-09-13T04-21-04.931146.parquet
- split: latest
- path: **/details_harness|arc:challenge|25_2023-09-13T04-21-04.931146.parquet
- split: 2023_09_13T04_03_35.733983
-
config_name: harness_drop_3
- split: 2023_10_24T02_18_07.282954
- path: **/details_harness|drop|3_2023-10-24T02-18-07.282954.parquet
- split: 2023_10_25T05_20_39.857272
- path: **/details_harness|drop|3_2023-10-25T05-20-39.857272.parquet
- split: latest
- path: **/details_harness|drop|3_2023-10-25T05-20-39.857272.parquet
- split: 2023_10_24T02_18_07.282954
-
config_name: harness_gsm8k_5
- split: 2023_10_24T02_18_07.282954
- path: **/details_harness|gsm8k|5_2023-10-24T02-18-07.282954.parquet
- split: 2023_10_25T05_20_39.857272
- path: **/details_harness|gsm8k|5_2023-10-25T05-20-39.857272.parquet
- split: latest
- path: **/details_harness|gsm8k|5_2023-10-25T05-20-39.857272.parquet
- split: 2023_10_24T02_18_07.282954
-
config_name: harness_hellaswag_10
- split: 2023_09_13T04_03_35.733983
- path: **/details_harness|hellaswag|10_2023-09-13T04-03-35.733983.parquet
- split: 2023_09_13T04_21_04.931146
- path: **/details_harness|hellaswag|10_2023-09-13T04-21-04.931146.parquet
- split: latest
- path: **/details_harness|hellaswag|10_2023-09-13T04-21-04.931146.parquet
- split: 2023_09_13T04_03_35.733983
-
config_name: harness_hendrycksTest_5
- split: 2023_09_13T04_03_35.733983
- path: **/details_harness|hendrycksTest-abstract_algebra|5_2023-09-13T04-03-35.733983.parquet
- path: **/details_harness|hendrycksTest-anatomy|5_2023-09-13T04-03-35.733983.parquet
- path: **/details_harness|hendrycksTest-astronomy|5_2023-09-13T04-03-35.733983.parquet
- path: **/details_harness|hendrycksTest-business_ethics|5_2023-09-13T04-03-35.733983.parquet
- path: **/details_harness|hendrycksTest-clinical_knowledge|5_2023-09-13T04-03-35.733983.parquet
- path: **/details_harness|hendrycksTest-college_biology|5_2023-09-13T04-03-35.733983.parquet
- path: **/details_harness|hendrycksTest-college_chemistry|5_2023-09-13T04-03-35.733983.parquet
- path: **/details_harness|hendrycksTest-college_computer_science|5_2023-09-13T04-03-35.733983.parquet
- path: **/details_harness|hendrycksTest-college_mathematics|5_2023-09-13T04-03-35.733983.parquet
- path: **/details_harness|hendrycksTest-college_medicine|5_2023-09-13T04-03-35.733983.parquet
- path: **/details_harness|hendrycksTest-college_physics|5_2023-09-13T04-03-35.733983.parquet
- path: **/details_harness|hendrycksTest-computer_security|5_2023-09-13T04-03-35.733983.parquet
- path: **/details_harness|hendrycksTest-conceptual_physics|5_2023-09-13T04-03-35.733983.parquet
- path: **/details_harness|hendrycksTest-econometrics|5_2023-09-13T04-03-35.733983.parquet
- path: **/details_harness|hendrycksTest-electrical_engineering|5_2023-09-13T04-03-35.733983.parquet
- path: **/details_harness|hendrycksTest-elementary_mathematics|5_2023-09-13T04-03-35.733983.parquet
- path: **/details_harness|hendrycksTest-formal_logic|5_2023-09-13T04-03-35.733983.parquet
- path: **/details_harness|hendrycksTest-global_facts|5_2023-09-13T04-03-35.733983.parquet
- path: **/details_harness|hendrycksTest-high_school_biology|5_2023-09-13T04-03-35.733983.parquet
- path: **/details_harness|hendrycksTest-high_school_chemistry|5_2023-09-13T04-03-35.733983.parquet
- path: **/details_harness|hendrycksTest-high_school_computer_science|5_2023-09-13T04-03-35.733983.parquet
- path: **/details_harness|hendrycksTest-high_school_european_history|5_2023-09-13T04-03-35.733983.parquet
- path: **/details_harness|hendrycksTest-high_school_geography|5_2023-09-13T04-03-35.733983.parquet
- path: **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-09-13T04-03-35.733983.parquet
- path: **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-09-13T04-03-35.733983.parquet
- path: **/details_harness|hendrycksTest-high_school_mathematics|5_2023-09-13T04-03-35.733983.parquet
- path: **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-09-13T04-03-35.733983.parquet
- path: **/details_harness|hendrycksTest-high_school_physics|5_2023-09-13T04-03-35.733983.parquet
- path: **/details_harness|hendrycksTest-high_school_psychology|5_2023-09-13T04-03-35.733983.parquet
- path: **/details_harness|hendrycksTest-high_school_statistics|5_2023-09-13T04-03-35.733983.parquet
- path: **/details_harness|hendrycksTest-high_school_us_history|5_2023-09-13T04-03-35.733983.parquet
- path: **/details_harness|hendrycksTest-high_school_world_history|5_2023-09-13T04-03-35.733983.parquet
- path: **/details_harness|hendrycksTest-human_aging|5_2023-09-13T04-03-35.733983.parquet
- path: **/details_harness|hendrycksTest-human_sexuality|5_2023-09-13T04-03-35.733983.parquet
- path: **/details_harness|hendrycksTest-international_law|5_2023-09-13T04-03-35.733983.parquet
- path: **/details_harness|hendrycksTest-jurisprudence|5_2023-09-13T04-03-35.733983.parquet
- path: **/details_harness|hendrycksTest-logical_fallacies|5_2023-09-13T04-03-35.733983.parquet
- path: **/details_harness|hendrycksTest-machine_learning|5_2023-09-13T04-03-35.733983.parquet
- path: **/details_harness|hendrycksTest-management|5_2023-09-13T04-03-35.733983.parquet
- path: **/details_harness|hendrycksTest-marketing|5_2023-09-13T04-03-35.733983.parquet
- path: **/details_harness|hendrycksTest-medical_genetics|5_2023-09-13T04-03-35.733983.parquet
- path: **/details_harness|hendrycksTest-miscellaneous|5_2023-09-13T04-03-35
- split: 2023_09_13T04_03_35.733983



