open-llm-leaderboard-old/details_pankajmathur__orca_mini_v3_7b
收藏数据集概述
数据集来源
该数据集是在评估模型 pankajmathur/orca_mini_v3_7b 在 Open LLM Leaderboard 上的自动创建的。
数据集结构
- 配置数量:64个配置,每个配置对应一个评估任务。
- 数据来源:数据集由2次运行结果组成,每次运行的结果作为一个特定的分割(split),分割名称使用运行的时间戳。
- 最新结果:"train" 分割始终指向最新的结果。
- 汇总结果:一个额外的配置 "results" 存储所有运行的汇总结果,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_pankajmathur__orca_mini_v3_7b", "harness_winogrande_5", split="train")
最新结果
以下是来自2023-10-24T09:53:37.786344运行的最新结果: python { "all": { "em": 0.08043204697986577, "em_stderr": 0.0027851341980506704, "f1": 0.15059563758389252, "f1_stderr": 0.0030534563383277672, "acc": 0.4069827001752661, "acc_stderr": 0.009686225873410097 }, "harness|drop|3": { "em": 0.08043204697986577, "em_stderr": 0.0027851341980506704, "f1": 0.15059563758389252, "f1_stderr": 0.0030534563383277672 }, "harness|gsm8k|5": { "acc": 0.0712661106899166, "acc_stderr": 0.007086462127954491 }, "harness|winogrande|5": { "acc": 0.7426992896606156, "acc_stderr": 0.012285989618865706 } }
配置详情
以下是部分配置及其数据文件路径:
-
config_name: harness_arc_challenge_25
- split: 2023_09_13T09_56_47.532864
- path: **/details_harness|arc:challenge|25_2023-09-13T09-56-47.532864.parquet
- split: latest
- path: **/details_harness|arc:challenge|25_2023-09-13T09-56-47.532864.parquet
- split: 2023_09_13T09_56_47.532864
-
config_name: harness_drop_3
- split: 2023_10_24T09_53_37.786344
- path: **/details_harness|drop|3_2023-10-24T09-53-37.786344.parquet
- split: latest
- path: **/details_harness|drop|3_2023-10-24T09-53-37.786344.parquet
- split: 2023_10_24T09_53_37.786344
-
config_name: harness_gsm8k_5
- split: 2023_10_24T09_53_37.786344
- path: **/details_harness|gsm8k|5_2023-10-24T09-53-37.786344.parquet
- split: latest
- path: **/details_harness|gsm8k|5_2023-10-24T09-53-37.786344.parquet
- split: 2023_10_24T09_53_37.786344
-
config_name: harness_hellaswag_10
- split: 2023_09_13T09_56_47.532864
- path: **/details_harness|hellaswag|10_2023-09-13T09-56-47.532864.parquet
- split: latest
- path: **/details_harness|hellaswag|10_2023-09-13T09-56-47.532864.parquet
- split: 2023_09_13T09_56_47.532864
-
config_name: harness_hendrycksTest_5
- split: 2023_09_13T09_56_47.532864
- path:
- **/details_harness|hendrycksTest-abstract_algebra|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-anatomy|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-astronomy|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-college_biology|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-college_physics|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-computer_security|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-econometrics|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-global_facts|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-high_school_computer_science|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-high_school_european_history|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-high_school_geography|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-high_school_mathematics|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-high_school_physics|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-high_school_psychology|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-high_school_statistics|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-high_school_us_history|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-high_school_world_history|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-human_aging|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-human_sexuality|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-international_law|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-jurisprudence|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-logical_fallacies|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-machine_learning|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-management|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-marketing|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-medical_genetics|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-miscellaneous|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-moral_disputes|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-moral_scenarios|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-nutrition|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-philosophy|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-prehistory|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-professional_accounting|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-professional_law|5_2023-09-13T09-56-47.532864.parquet
- **/details_harness|hendrycksTest-professional_medicine|5_2023-09-13T09-56-47.532864.par
- path:
- split: 2023_09_13T09_56_47.532864



