open-llm-leaderboard-old/details_jordiclive__gpt4all-alpaca-oa-codealpaca-lora-13b
收藏数据集概述
该数据集是在评估模型 jordiclive/gpt4all-alpaca-oa-codealpaca-lora-13b 在 Open LLM Leaderboard 上的运行过程中自动创建的。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次运行创建,每次运行可以在每个配置中找到特定的分割,分割名称使用运行的时间戳。"train" 分割始终指向最新的结果。
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_jordiclive__gpt4all-alpaca-oa-codealpaca-lora-13b", "harness_winogrande_5", split="train")
最新结果
以下是 最新结果 的示例:
python { "all": { "em": 0.0019924496644295304, "em_stderr": 0.000456667646266702, "f1": 0.05642302852349, "f1_stderr": 0.0012977737732540458, "acc": 0.41872834230806744, "acc_stderr": 0.009633077195432445 }, "harness|drop|3": { "em": 0.0019924496644295304, "em_stderr": 0.000456667646266702, "f1": 0.05642302852349, "f1_stderr": 0.0012977737732540458 }, "harness|gsm8k|5": { "acc": 0.0758150113722517, "acc_stderr": 0.0072912057231625796 }, "harness|winogrande|5": { "acc": 0.7616416732438832, "acc_stderr": 0.011974948667702311 } }
配置详情
数据集包含多个配置,每个配置对应不同的任务和数据文件路径。以下是部分配置的示例:
-
config_name:
harness_arc_challenge_25- data_files:
- split:
2023_08_09T17_57_53.688517- path:
**/details_harness|arc:challenge|25_2023-08-09T17:57:53.688517.parquet
- path:
- split:
latest- path:
**/details_harness|arc:challenge|25_2023-08-09T17:57:53.688517.parquet
- path:
- split:
- data_files:
-
config_name:
harness_drop_3- data_files:
- split:
2023_09_22T20_03_30.331669- path:
**/details_harness|drop|3_2023-09-22T20-03-30.331669.parquet
- path:
- split:
latest- path:
**/details_harness|drop|3_2023-09-22T20-03-30.331669.parquet
- path:
- split:
- data_files:
-
config_name:
harness_gsm8k_5- data_files:
- split:
2023_09_22T20_03_30.331669- path:
**/details_harness|gsm8k|5_2023-09-22T20-03-30.331669.parquet
- path:
- split:
latest- path:
**/details_harness|gsm8k|5_2023-09-22T20-03-30.331669.parquet
- path:
- split:
- data_files:
-
config_name:
harness_hellaswag_10- data_files:
- split:
2023_08_09T17_57_53.688517- path:
**/details_harness|hellaswag|10_2023-08-09T17:57:53.688517.parquet
- path:
- split:
latest- path:
**/details_harness|hellaswag|10_2023-08-09T17:57:53.688517.parquet
- path:
- split:
- data_files:
-
config_name:
harness_hendrycksTest_5- data_files:
- split:
2023_08_09T17_57_53.688517- path:
**/details_harness|hendrycksTest-abstract_algebra|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-anatomy|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-astronomy|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-business_ethics|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-college_biology|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-college_chemistry|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-college_computer_science|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-college_mathematics|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-college_medicine|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-college_physics|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-computer_security|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-conceptual_physics|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-econometrics|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-electrical_engineering|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-formal_logic|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-global_facts|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-high_school_biology|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-high_school_european_history|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-high_school_geography|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-high_school_physics|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-high_school_psychology|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-high_school_statistics|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-high_school_us_history|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-high_school_world_history|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-human_aging|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-human_sexuality|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-international_law|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-jurisprudence|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-logical_fallacies|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-machine_learning|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-management|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-marketing|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-medical_genetics|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-miscellaneous|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-moral_disputes|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-moral_scenarios|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-nutrition|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-philosophy|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-prehistory|5_2023-08-09T17:57:53.688517.parquet**/details_harness|hendrycksTest-professional_accounting|5_2023-08-09T17:57:53.688517.parquet- `**/details_harness|hendrycksTest-professional_law|5_2023-08-09T17:
- path:
- split:
- data_files:



