open-llm-leaderboard-old/details_quantumaikr__KoreanLM-hf
收藏Hugging Face2023-10-15 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_quantumaikr__KoreanLM-hf
下载链接
链接失效反馈官方服务:
资源简介:
该数据集是在Open LLM Leaderboard上对模型quantumaikr/KoreanLM-hf进行评估时自动创建的。数据集由64个配置组成,每个配置对应一个评估任务。数据集由2次运行生成,每次运行的结果作为特定配置中的一个分割,分割名称使用运行的时间戳。train分割始终指向最新的结果。此外,还有一个名为results的配置存储了所有运行的聚合结果,并用于在Open LLM Leaderboard上计算和显示聚合指标。
该数据集是在Open LLM Leaderboard上对模型quantumaikr/KoreanLM-hf进行评估时自动创建的。数据集由64个配置组成,每个配置对应一个评估任务。数据集由2次运行生成,每次运行的结果作为特定配置中的一个分割,分割名称使用运行的时间戳。train分割始终指向最新的结果。此外,还有一个名为results的配置存储了所有运行的聚合结果,并用于在Open LLM Leaderboard上计算和显示聚合指标。
提供机构:
open-llm-leaderboard-old
原始信息汇总
数据集概述
该数据集是在评估模型 quantumaikr/KoreanLM-hf 在 Open LLM Leaderboard 上的运行过程中自动创建的。
数据集组成
- 该数据集包含 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。
最新结果
- 最新结果来自 2023-10-15T23:49:19.113066 运行,具体结果如下: python { "all": { "em": 0.16222734899328858, "em_stderr": 0.0037754156899711395, "f1": 0.21587562919463021, "f1_stderr": 0.0038257903227116702, "acc": 0.36591394188393417, "acc_stderr": 0.008953706481200412 }, "harness|drop|3": { "em": 0.16222734899328858, "em_stderr": 0.0037754156899711395, "f1": 0.21587562919463021, "f1_stderr": 0.0038257903227116702 }, "harness|gsm8k|5": { "acc": 0.03411675511751327, "acc_stderr": 0.005000212600773284 }, "harness|winogrande|5": { "acc": 0.6977111286503551, "acc_stderr": 0.012907200361627538 } }
配置详情
-
harness_arc_challenge_25
- 分割:2023_07_24T15_37_48.867178
- 路径:
**/details_harness|arc:challenge|25_2023-07-24T15:37:48.867178.parquet
- 路径:
- 分割:latest
- 路径:
**/details_harness|arc:challenge|25_2023-07-24T15:37:48.867178.parquet
- 路径:
- 分割:2023_07_24T15_37_48.867178
-
harness_drop_3
- 分割:2023_10_15T23_49_19.113066
- 路径:
**/details_harness|drop|3_2023-10-15T23-49-19.113066.parquet
- 路径:
- 分割:latest
- 路径:
**/details_harness|drop|3_2023-10-15T23-49-19.113066.parquet
- 路径:
- 分割:2023_10_15T23_49_19.113066
-
harness_gsm8k_5
- 分割:2023_10_15T23_49_19.113066
- 路径:
**/details_harness|gsm8k|5_2023-10-15T23-49-19.113066.parquet
- 路径:
- 分割:latest
- 路径:
**/details_harness|gsm8k|5_2023-10-15T23-49-19.113066.parquet
- 路径:
- 分割:2023_10_15T23_49_19.113066
-
harness_hellaswag_10
- 分割:2023_07_24T15_37_48.867178
- 路径:
**/details_harness|hellaswag|10_2023-07-24T15:37:48.867178.parquet
- 路径:
- 分割:latest
- 路径:
**/details_harness|hellaswag|10_2023-07-24T15:37:48.867178.parquet
- 路径:
- 分割:2023_07_24T15_37_48.867178
-
harness_hendrycksTest_5
- 分割:2023_07_24T15_37_48.867178
- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-anatomy|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-astronomy|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-business_ethics|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-college_biology|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-college_chemistry|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-college_computer_science|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-college_mathematics|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-college_medicine|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-college_physics|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-computer_security|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-conceptual_physics|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-econometrics|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-electrical_engineering|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-elementary_mathematics|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-formal_logic|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-global_facts|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-high_school_biology|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-high_school_chemistry|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-high_school_computer_science|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-high_school_european_history|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-high_school_geography|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-high_school_mathematics|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-high_school_physics|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-high_school_psychology|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-high_school_statistics|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-high_school_us_history|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-high_school_world_history|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-human_aging|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-human_sexuality|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-international_law|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-jurisprudence|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-logical_fallacies|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-machine_learning|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-management|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-marketing|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-medical_genetics|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-miscellaneous|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-moral_disputes|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-moral_scenarios|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-nutrition|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-philosophy|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-prehistory|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-professional_accounting|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-professional_law|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-professional_medicine|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-professional_psychology|5_2023-07-24T15:37:48.867178.parquet**/details_harness|hendrycksTest-public_relations|5_2023-07-24T15:37:48.867178.parquet- `**/
- 路径:
- 分割:2023_07_24T15_37_48.867178



