open-llm-leaderboard/details_Deathsquad10__TinyMix
收藏数据集概述
数据集简介
该数据集是在评估模型 Deathsquad10/TinyMix 在 Open LLM Leaderboard 上的自动创建的。数据集包含 63 个配置,每个配置对应一个评估任务。
数据集结构
数据集由 1 次运行创建,每个运行可以在每个配置中作为一个特定的分割找到,分割名称使用运行的时间戳。"train" 分割始终指向最新的结果。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_Deathsquad10__TinyMix", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-22T07:33:50.470953 运行的最新结果:
python { "all": { "acc": 0.2489144031638606, "acc_stderr": 0.03053022089324822, "acc_norm": 0.24899337938303814, "acc_norm_stderr": 0.03128050158553742, "mc1": 0.2423500611995104, "mc1_stderr": 0.015000674373570345, "mc2": 0.3942236565680581, "mc2_stderr": 0.014438664977073284 }, "harness|arc:challenge|25": { "acc": 0.28498293515358364, "acc_stderr": 0.013191348179838792, "acc_norm": 0.3199658703071672, "acc_norm_stderr": 0.013631345807016193 }, "harness|hellaswag|10": { "acc": 0.40450109539932283, "acc_stderr": 0.004897921845492105, "acc_norm": 0.5369448317068313, "acc_norm_stderr": 0.00497614145773687 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.27, "acc_stderr": 0.044619604333847394, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847394 }, # 其他任务的结果... }
配置详情
-
config_name: harness_arc_challenge_25
- split: 2024_03_22T07_33_50.470953
- path: **/details_harness|arc:challenge|25_2024-03-22T07-33-50.470953.parquet
- split: latest
- path: **/details_harness|arc:challenge|25_2024-03-22T07-33-50.470953.parquet
- split: 2024_03_22T07_33_50.470953
-
config_name: harness_gsm8k_5
- split: 2024_03_22T07_33_50.470953
- path: **/details_harness|gsm8k|5_2024-03-22T07-33-50.470953.parquet
- split: latest
- path: **/details_harness|gsm8k|5_2024-03-22T07-33-50.470953.parquet
- split: 2024_03_22T07_33_50.470953
-
config_name: harness_hellaswag_10
- split: 2024_03_22T07_33_50.470953
- path: **/details_harness|hellaswag|10_2024-03-22T07-33-50.470953.parquet
- split: latest
- path: **/details_harness|hellaswag|10_2024-03-22T07-33-50.470953.parquet
- split: 2024_03_22T07_33_50.470953
-
config_name: harness_hendrycksTest_5
- split: 2024_03_22T07_33_50.470953
- path:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-global_facts|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-high_school_computer_science|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-high_school_european_history|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-high_school_geography|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-high_school_mathematics|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-high_school_physics|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-high_school_psychology|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-high_school_statistics|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-high_school_us_history|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-high_school_world_history|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-human_aging|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-human_sexuality|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-international_law|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-jurisprudence|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-logical_fallacies|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-machine_learning|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-management|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-marketing|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-medical_genetics|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-miscellaneous|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-moral_disputes|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-moral_scenarios|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-nutrition|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-philosophy|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-prehistory|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-professional_accounting|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-professional_law|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-professional_medicine|5_2024-03-22T07-33-50.470953.parquet
- **/details_harness|hendrycksTest-professional_psychology|5_2024-03-22T07-3
- path:
- split: 2024_03_22T07_33_50.470953



