open-llm-leaderboard-old/details_uukuguy__speechless-llama2-hermes-orca-platypus-13b
收藏数据集概述
该数据集是在对模型 uukuguy/speechless-llama2-hermes-orca-platypus-13b 进行评估运行期间自动创建的,用于 Open LLM Leaderboard。
数据集组成
数据集由64个配置组成,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。
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 Open LLM Leaderboard 上的聚合指标。
加载数据示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_uukuguy__speechless-llama2-hermes-orca-platypus-13b", "harness_winogrande_5", split="train")
最新结果
以下是来自 2023-10-18T05:34:26.777818 运行的最新结果:
python { "all": { "em": 0.020763422818791948, "em_stderr": 0.0014602692459797255, "f1": 0.1284448406040266, "f1_stderr": 0.002326999769158526, "acc": 0.42460684800436577, "acc_stderr": 0.010144077147210034 }, "harness|drop|3": { "em": 0.020763422818791948, "em_stderr": 0.0014602692459797255, "f1": 0.1284448406040266, "f1_stderr": 0.002326999769158526 }, "harness|gsm8k|5": { "acc": 0.09704321455648218, "acc_stderr": 0.00815376827455472 }, "harness|winogrande|5": { "acc": 0.7521704814522494, "acc_stderr": 0.012134386019865348 } }
配置详情
-
config_name: harness_arc_challenge_25
- data_files:
- split: 2023_09_01T20_32_11.554116
- path: **/details_harness|arc:challenge|25_2023-09-01T20:32:11.554116.parquet
- split: latest
- path: **/details_harness|arc:challenge|25_2023-09-01T20:32:11.554116.parquet
- split: 2023_09_01T20_32_11.554116
- data_files:
-
config_name: harness_drop_3
- data_files:
- split: 2023_10_18T05_34_26.777818
- path: **/details_harness|drop|3_2023-10-18T05-34-26.777818.parquet
- split: latest
- path: **/details_harness|drop|3_2023-10-18T05-34-26.777818.parquet
- split: 2023_10_18T05_34_26.777818
- data_files:
-
config_name: harness_gsm8k_5
- data_files:
- split: 2023_10_18T05_34_26.777818
- path: **/details_harness|gsm8k|5_2023-10-18T05-34-26.777818.parquet
- split: latest
- path: **/details_harness|gsm8k|5_2023-10-18T05-34-26.777818.parquet
- split: 2023_10_18T05_34_26.777818
- data_files:
-
config_name: harness_hellaswag_10
- data_files:
- split: 2023_09_01T20_32_11.554116
- path: **/details_harness|hellaswag|10_2023-09-01T20:32:11.554116.parquet
- split: latest
- path: **/details_harness|hellaswag|10_2023-09-01T20:32:11.554116.parquet
- split: 2023_09_01T20_32_11.554116
- data_files:
-
config_name: harness_hendrycksTest_5
- data_files:
- split: 2023_09_01T20_32_11.554116
- path:
- **/details_harness|hendrycksTest-abstract_algebra|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-anatomy|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-astronomy|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-college_biology|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-college_physics|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-computer_security|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-econometrics|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-global_facts|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-high_school_computer_science|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-high_school_european_history|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-high_school_geography|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-high_school_mathematics|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-high_school_physics|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-high_school_psychology|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-high_school_statistics|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-high_school_us_history|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-high_school_world_history|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-human_aging|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-human_sexuality|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-international_law|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-jurisprudence|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-logical_fallacies|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-machine_learning|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-management|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-marketing|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-medical_genetics|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-miscellaneous|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-moral_disputes|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-moral_scenarios|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-nutrition|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-philosophy|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-prehistory|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-professional_accounting|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-professional_law|5_2023-09-01T20:32:11.554116.parquet
- **/details_harness|hendrycksTest-professional_medicine|5_2023-09-01T20:3
- path:
- split: 2023_09_01T20_32_11.554116
- data_files:



