open-llm-leaderboard/details_golaxy__goims
收藏数据集概述
数据集简介
该数据集是在评估模型 golaxy/goims 在 Open LLM Leaderboard 上的表现时自动创建的。数据集包含64个配置,每个配置对应一个评估任务。
数据集结构
数据集由2次运行结果组成,每次运行的结果可以在每个配置中作为特定的分片找到,分片名称使用运行的时间戳。"train" 分片始终指向最新的结果。
额外配置
一个额外的配置 "results" 存储所有运行的聚合结果,用于计算和显示在 Open LLM Leaderboard 上的聚合指标。
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_golaxy__goims", "harness_winogrande_5", split="train")
最新结果
以下是 最新结果 的示例: python { "all": { "em": 0.001572986577181208, "em_stderr": 0.00040584511324177333, "f1": 0.061753355704698, "f1_stderr": 0.0014402452492549395, "acc": 0.379924161053344, "acc_stderr": 0.009802745022083587 }, "harness|drop|3": { "em": 0.001572986577181208, "em_stderr": 0.00040584511324177333, "f1": 0.061753355704698, "f1_stderr": 0.0014402452492549395 }, "harness|gsm8k|5": { "acc": 0.06292645943896892, "acc_stderr": 0.006688762581532711 }, "harness|winogrande|5": { "acc": 0.696921862667719, "acc_stderr": 0.012916727462634463 } }
配置详情
以下是数据集的配置详情:
-
harness_arc_challenge_25
- 分片: 2023_08_09T10_57_12.922580
- 路径: **/details_harness|arc:challenge|25_2023-08-09T10:57:12.922580.parquet
- 分片: latest
- 路径: **/details_harness|arc:challenge|25_2023-08-09T10:57:12.922580.parquet
- 分片: 2023_08_09T10_57_12.922580
-
harness_drop_3
- 分片: 2023_10_17T02_18_23.733040
- 路径: **/details_harness|drop|3_2023-10-17T02-18-23.733040.parquet
- 分片: latest
- 路径: **/details_harness|drop|3_2023-10-17T02-18-23.733040.parquet
- 分片: 2023_10_17T02_18_23.733040
-
harness_gsm8k_5
- 分片: 2023_10_17T02_18_23.733040
- 路径: **/details_harness|gsm8k|5_2023-10-17T02-18-23.733040.parquet
- 分片: latest
- 路径: **/details_harness|gsm8k|5_2023-10-17T02-18-23.733040.parquet
- 分片: 2023_10_17T02_18_23.733040
-
harness_hellaswag_10
- 分片: 2023_08_09T10_57_12.922580
- 路径: **/details_harness|hellaswag|10_2023-08-09T10:57:12.922580.parquet
- 分片: latest
- 路径: **/details_harness|hellaswag|10_2023-08-09T10:57:12.922580.parquet
- 分片: 2023_08_09T10_57_12.922580
-
harness_hendrycksTest_5
- 分片: 2023_08_09T10_57_12.922580
- 路径:
- **/details_harness|hendrycksTest-abstract_algebra|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-anatomy|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-astronomy|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-college_biology|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-college_physics|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-computer_security|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-econometrics|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-global_facts|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-high_school_european_history|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-high_school_geography|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-high_school_physics|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-high_school_psychology|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-high_school_statistics|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-high_school_us_history|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-high_school_world_history|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-human_aging|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-human_sexuality|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-international_law|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-jurisprudence|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-logical_fallacies|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-machine_learning|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-management|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-marketing|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-medical_genetics|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-miscellaneous|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-moral_disputes|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-moral_scenarios|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-nutrition|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-philosophy|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-prehistory|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-professional_accounting|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-professional_law|5_2023-08-09T10:57:12.922580.parquet
- **/details_harness|hendrycksTest-professional_medicine|5_2023-08-09T10:57:12
- 路径:
- 分片: 2023_08_09T10_57_12.922580



