open-llm-leaderboard-old/details_fhai50032__BeagleLake-7B
收藏数据集概述
数据集简介
该数据集是在评估模型 fhai50032/BeagleLake-7B 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找到特定的分片,分片名称使用运行的时间戳。"train" 分片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_fhai50032__BeagleLake-7B", "harness_winogrande_5", split="train")
最新结果
以下是 最新结果 的摘要:
python { "all": { "acc": 0.6468122209110102, "acc_stderr": 0.032180093524919205, "acc_norm": 0.6474338424936177, "acc_norm_stderr": 0.03283953683706756, "mc1": 0.4908200734394125, "mc1_stderr": 0.01750055072481975, "mc2": 0.6491975727907208, "mc2_stderr": 0.015417969486375667 }, "harness|arc:challenge|25": { "acc": 0.6655290102389079, "acc_stderr": 0.013787460322441374, "acc_norm": 0.7039249146757679, "acc_norm_stderr": 0.01334091608524625 }, "harness|hellaswag|10": { "acc": 0.6981676956781517, "acc_stderr": 0.004581147247963204, "acc_norm": 0.8738299143596893, "acc_norm_stderr": 0.0033136235601649304 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, # 其他任务的结果... }
配置详情
-
config_name: harness_arc_challenge_25
- data_files:
- split: 2024_02_03T22_36_10.253997
- path: **/details_harness|arc:challenge|25_2024-02-03T22-36-10.253997.parquet
- split: latest
- path: **/details_harness|arc:challenge|25_2024-02-03T22-36-10.253997.parquet
- split: 2024_02_03T22_36_10.253997
- data_files:
-
config_name: harness_gsm8k_5
- data_files:
- split: 2024_02_03T22_36_10.253997
- path: **/details_harness|gsm8k|5_2024-02-03T22-36-10.253997.parquet
- split: latest
- path: **/details_harness|gsm8k|5_2024-02-03T22-36-10.253997.parquet
- split: 2024_02_03T22_36_10.253997
- data_files:
-
config_name: harness_hellaswag_10
- data_files:
- split: 2024_02_03T22_36_10.253997
- path: **/details_harness|hellaswag|10_2024-02-03T22-36-10.253997.parquet
- split: latest
- path: **/details_harness|hellaswag|10_2024-02-03T22-36-10.253997.parquet
- split: 2024_02_03T22_36_10.253997
- data_files:
-
config_name: harness_hendrycksTest_5
- data_files:
- split: 2024_02_03T22_36_10.253997
- path:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-global_facts|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-high_school_computer_science|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-high_school_european_history|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-high_school_geography|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-high_school_mathematics|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-high_school_physics|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-high_school_psychology|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-high_school_statistics|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-high_school_us_history|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-high_school_world_history|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-human_aging|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-human_sexuality|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-international_law|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-jurisprudence|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-logical_fallacies|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-machine_learning|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-management|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-marketing|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-medical_genetics|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-miscellaneous|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-moral_disputes|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-moral_scenarios|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-nutrition|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-philosophy|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-prehistory|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-professional_accounting|5_2024-02-03T22-36-10.253997.parquet
- **/details_harness|hendrycksTest-professional_law|5_2024-02-03T22-36-1
- path:
- split: 2024_02_03T22_36_10.253997
- data_files:



