open-llm-leaderboard/details_TheBloke__robin-33B-v2-fp16
收藏数据集概述
数据集简介
该数据集是在评估模型 TheBloke/robin-33B-v2-fp16 在 Open LLM Leaderboard 上的自动创建的。
数据集组成
- 数据集包含 61 个配置,每个配置对应一个评估任务。
- 数据集来自 1 次运行,每个运行可以在每个配置中作为一个特定的分片找到,分片名称使用运行的时间戳。
- "train" 分片总是指向最新的结果。
- 一个额外的配置 "results" 存储所有运行的聚合结果,用于计算和显示在 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_TheBloke__robin-33B-v2-fp16", "harness_truthfulqa_mc_0", split="train")
最新结果
这些是最新的结果,来自 2023-07-31T16:41:32.452325 的运行: python { "all": { "acc": 0.5493694357469432, "acc_stderr": 0.03462857618448208, "acc_norm": 0.5533043005336739, "acc_norm_stderr": 0.03460642548466365, "mc1": 0.3574051407588739, "mc1_stderr": 0.016776599676729398, "mc2": 0.5388029530988832, "mc2_stderr": 0.014742138833066059 }, "harness|arc:challenge|25": { "acc": 0.5947098976109215, "acc_stderr": 0.014346869060229321, "acc_norm": 0.6237201365187713, "acc_norm_stderr": 0.014157022555407156 }, "harness|hellaswag|10": { "acc": 0.6331408086038638, "acc_stderr": 0.004809626723626824, "acc_norm": 0.8362875921131249, "acc_norm_stderr": 0.0036925819391622834 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, # 其他任务的结果... }
配置详情
-
harness_arc_challenge_25
- 分片:2023_07_31T16_41_32.452325
- 路径:
**/details_harness|arc:challenge|25_2023-07-31T16:41:32.452325.parquet - 分片:latest
- 路径:
**/details_harness|arc:challenge|25_2023-07-31T16:41:32.452325.parquet
-
harness_hellaswag_10
- 分片:2023_07_31T16_41_32.452325
- 路径:
**/details_harness|hellaswag|10_2023-07-31T16:41:32.452325.parquet - 分片:latest
- 路径:
**/details_harness|hellaswag|10_2023-07-31T16:41:32.452325.parquet
-
harness_hendrycksTest_5
- 分片:2023_07_31T16_41_32.452325
- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-anatomy|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-astronomy|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-business_ethics|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-college_biology|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-college_chemistry|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-college_computer_science|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-college_mathematics|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-college_medicine|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-college_physics|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-computer_security|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-conceptual_physics|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-econometrics|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-electrical_engineering|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-elementary_mathematics|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-formal_logic|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-global_facts|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-high_school_biology|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-high_school_chemistry|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-high_school_computer_science|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-high_school_european_history|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-high_school_geography|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-high_school_mathematics|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-high_school_physics|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-high_school_psychology|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-high_school_statistics|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-high_school_us_history|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-high_school_world_history|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-human_aging|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-human_sexuality|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-international_law|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-jurisprudence|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-logical_fallacies|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-machine_learning|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-management|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-marketing|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-medical_genetics|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-miscellaneous|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-moral_disputes|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-moral_scenarios|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-nutrition|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-philosophy|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-prehistory|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-professional_accounting|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-professional_law|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-professional_medicine|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-professional_psychology|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-public_relations|5_2023-07-31T16:41:32.452325.parquet**/details_harness|hendrycksTest-security_studies|5_2023-07-31T16:41:32.452325.parquet



