open-llm-leaderboard-old/details_Sao10K__BrainDerp
收藏数据集概述
该数据集是在模型 Sao10K/BrainDerp 在 Open LLM Leaderboard 上的评估运行期间自动创建的。
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。
- 数据集从 2 次运行中创建,每次运行在每个配置中作为一个特定的分割存在,分割名称使用运行的时间戳。
- "train" 分割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_Sao10K__BrainDerp", "harness_winogrande_5", split="train")
最新结果
以下是 2023-10-24T00:03:05.483075 运行 的最新结果: python { "all": { "em": 0.031774328859060404, "em_stderr": 0.00179624735213122, "f1": 0.15481229026845572, "f1_stderr": 0.002609735138062246, "acc": 0.4205614858545465, "acc_stderr": 0.009806536501080007 }, "harness|drop|3": { "em": 0.031774328859060404, "em_stderr": 0.00179624735213122, "f1": 0.15481229026845572, "f1_stderr": 0.002609735138062246 }, "harness|gsm8k|5": { "acc": 0.08263836239575435, "acc_stderr": 0.00758408922014814 }, "harness|winogrande|5": { "acc": 0.7584846093133386, "acc_stderr": 0.012028983782011874 } }
配置详情
配置列表
harness_arc_challenge_25harness_drop_3harness_gsm8k_5harness_hellaswag_10harness_hendrycksTest_5harness_hendrycksTest_abstract_algebra_5harness_hendrycksTest_anatomy_5harness_hendrycksTest_astronomy_5harness_hendrycksTest_business_ethics_5harness_hendrycksTest_clinical_knowledge_5harness_hendrycksTest_college_biology_5harness_hendrycksTest_college_chemistry_5harness_hendrycksTest_college_computer_science_5harness_hendrycksTest_college_mathematics_5harness_hendrycksTest_college_medicine_5harness_hendrycksTest_college_physics_5harness_hendrycksTest_computer_security_5harness_hendrycksTest_conceptual_physics_5harness_hendrycksTest_econometrics_5harness_hendrycksTest_electrical_engineering_5harness_hendrycksTest_elementary_mathematics_5
数据文件路径
每个配置包含多个分割,每个分割对应一个特定的时间戳,路径如下:
harness_arc_challenge_252023_10_04T06_59_16.770544:**/details_harness|arc:challenge|25_2023-10-04T06-59-16.770544.parquetlatest:**/details_harness|arc:challenge|25_2023-10-04T06-59-16.770544.parquet
harness_drop_32023_10_24T00_03_05.483075:**/details_harness|drop|3_2023-10-24T00-03-05.483075.parquetlatest:**/details_harness|drop|3_2023-10-24T00-03-05.483075.parquet
harness_gsm8k_52023_10_24T00_03_05.483075:**/details_harness|gsm8k|5_2023-10-24T00-03-05.483075.parquetlatest:**/details_harness|gsm8k|5_2023-10-24T00-03-05.483075.parquet
harness_hellaswag_102023_10_04T06_59_16.770544:**/details_harness|hellaswag|10_2023-10-04T06-59-16.770544.parquetlatest:**/details_harness|hellaswag|10_2023-10-04T06-59-16.770544.parquet
harness_hendrycksTest_52023_10_04T06_59_16.770544: 多个路径latest: 多个路径
harness_hendrycksTest_abstract_algebra_52023_10_04T06_59_16.770544:**/details_harness|hendrycksTest-abstract_algebra|5_2023-10-04T06-59-16.770544.parquetlatest:**/details_harness|hendrycksTest-abstract_algebra|5_2023-10-04T06-59-16.770544.parquet
harness_hendrycksTest_anatomy_52023_10_04T06_59_16.770544:**/details_harness|hendrycksTest-anatomy|5_2023-10-04T06-59-16.770544.parquetlatest:**/details_harness|hendrycksTest-anatomy|5_2023-10-04T06-59-16.770544.parquet
harness_hendrycksTest_astronomy_52023_10_04T06_59_16.770544:**/details_harness|hendrycksTest-astronomy|5_2023-10-04T06-59-16.770544.parquetlatest:**/details_harness|hendrycksTest-astronomy|5_2023-10-04T06-59-16.770544.parquet
harness_hendrycksTest_business_ethics_52023_10_04T06_59_16.770544:**/details_harness|hendrycksTest-business_ethics|5_2023-10-04T06-59-16.770544.parquetlatest:**/details_harness|hendrycksTest-business_ethics|5_2023-10-04T06-59-16.770544.parquet
harness_hendrycksTest_clinical_knowledge_52023_10_04T06_59_16.770544:**/details_harness|hendrycksTest-clinical_knowledge|5_2023-10-04T06-59-16.770544.parquetlatest:**/details_harness|hendrycksTest-clinical_knowledge|5_2023-10-04T06-59-16.770544.parquet
harness_hendrycksTest_college_biology_52023_10_04T06_59_16.770544:**/details_harness|hendrycksTest-college_biology|5_2023-10-04T06-59-16.770544.parquetlatest:**/details_harness|hendrycksTest-college_biology|5_2023-10-04T06-59-16.770544.parquet
harness_hendrycksTest_college_chemistry_52023_10_04T06_59_16.770544:**/details_harness|hendrycksTest-college_chemistry|5_2023-10-04T06-59-16.770544.parquetlatest:**/details_harness|hendrycksTest-college_chemistry|5_2023-10-04T06-59-16.770544.parquet
harness_hendrycksTest_college_computer_science_52023_10_04T06_59_16.770544:**/details_harness|hendrycksTest-college_computer_science|5_2023-10-04T06-59-16.770544.parquetlatest:**/details_harness|hendrycksTest-college_computer_science|5_2023-10-04T06-59-16.770544.parquet
harness_hendrycksTest_college_mathematics_52023_10_04T06_59_16.770544:**/details_harness|hendrycksTest-college_mathematics|5_2023-10-04T06-59-16.770544.parquetlatest:**/details_harness|hendrycksTest-college_mathematics|5_2023-10-04T06-59-16.770544.parquet
harness_hendrycksTest_college_medicine_52023_10_04T06_59_16.770544:**/details_harness|hendrycksTest-college_medicine|5_2023-10-04T06-59-16.770544.parquetlatest:**/details_harness|hendrycksTest-college_medicine|5_2023-10-04T06-59-16.770544.parquet
harness_hendrycksTest_college_physics_52023_10_04T06_59_16.770544:**/details_harness|hendrycksTest-college_physics|5_2023-10-04T06-59-16.770544.parquetlatest:**/details_harness|hendrycksTest-college_physics|5_2023-10-04T06-59-16.770544.parquet
harness_hendrycksTest_computer_security_52023_10_04T06_59_16.770544:**/details_harness|hendrycksTest-computer_security|5_2023-10-04T06-59-16.770544.parquetlatest:**/details_harness|hendrycksTest-computer_security|5_2023-10-04T06-59-16.770544.parquet
harness_hendrycksTest_conceptual_physics_52023_10_04T06_59_16.770544:**/details_harness|hendrycksTest-conceptual_physics|5_2023-10-04T06-59-16.770544.parquetlatest:**/details_harness|hendrycksTest-conceptual_physics|5_2023-10-04T06-59-16.770544.parquet
harness_hendrycksTest_econometrics_52023_10_04T06_59_16.770544:**/details_harness|hendrycksTest-econometrics|5_2023-10-04T06-59-16.770544.parquetlatest:**/details_harness|hendrycksTest-econometrics|5_2023-10-04T06-59-16.770544.parquet
harness_hendrycksTest_electrical_engineering_52023_10_04T06_59_16.770544:**/details_harness|hendrycksTest-electrical_engineering|5_2023-10-04T06-59-16.770544.parquetlatest:**/details_harness|hendrycksTest-electrical_engineering|5_2023-10-04T06-59-16.770544.parquet
- `harness_hendrycksTest_elementary_mathematics



