open-llm-leaderboard-old/details_andreaskoepf__llama2-13b-megacode2_min100
收藏Hugging Face2023-09-22 更新2024-06-22 收录
下载链接：
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_andreaskoepf__llama2-13b-megacode2_min100
下载链接
链接失效反馈官方服务：
资源简介：
该数据集是在模型[andreaskoepf/llama2-13b-megacode2_min100](https://huggingface.co/andreaskoepf/llama2-13b-megacode2_min100)在[Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)上的评估运行过程中自动创建的。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次运行创建，每次运行的结果都作为特定分割存储在配置中，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，并用于计算和显示[Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)上的聚合指标。
该数据集是在模型[andreaskoepf/llama2-13b-megacode2_min100](https://huggingface.co/andreaskoepf/llama2-13b-megacode2_min100)在[Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)上的评估运行过程中自动创建的。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次运行创建，每次运行的结果都作为特定分割存储在配置中，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，并用于计算和显示[Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)上的聚合指标。
提供机构：
open-llm-leaderboard-old
原始信息汇总
数据集概述
数据集简介
该数据集是在对模型 andreaskoepf/llama2-13b-megacode2_min100 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。
数据集结构
- 数据集包含 64 个配置，每个配置对应一个评估任务。
- 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拆分，拆分名称使用运行的时间戳。
- "train" 拆分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。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_andreaskoepf__llama2-13b-megacode2_min100", "harness_winogrande_5", split="train")
最新结果
以下是 2023-09-22T15:48:34.680007 运行的最新结果： python { "all": { "em": 0.0030411073825503355, "em_stderr": 0.0005638896908753115, "f1": 0.07890205536912773, "f1_stderr": 0.0016368809848969982, "acc": 0.4643729284759866, "acc_stderr": 0.010956919441194278 }, "harness|drop|3": { "em": 0.0030411073825503355, "em_stderr": 0.0005638896908753115, "f1": 0.07890205536912773, "f1_stderr": 0.0016368809848969982 }, "harness|gsm8k|5": { "acc": 0.15921152388172857, "acc_stderr": 0.010077966717551878 }, "harness|winogrande|5": { "acc": 0.7695343330702447, "acc_stderr": 0.01183587216483668 } }
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_08_17T10_46_30.131407
- path: **/details_harness|arc:challenge|25_2023-08-17T10:46:30.131407.parquet
- split: latest
- path: **/details_harness|arc:challenge|25_2023-08-17T10:46:30.131407.parquet
- split: 2023_08_17T10_46_30.131407
-
config_name: harness_drop_3
- split: 2023_09_22T15_48_34.680007
- path: **/details_harness|drop|3_2023-09-22T15-48-34.680007.parquet
- split: latest
- path: **/details_harness|drop|3_2023-09-22T15-48-34.680007.parquet
- split: 2023_09_22T15_48_34.680007
-
config_name: harness_gsm8k_5
- split: 2023_09_22T15_48_34.680007
- path: **/details_harness|gsm8k|5_2023-09-22T15-48-34.680007.parquet
- split: latest
- path: **/details_harness|gsm8k|5_2023-09-22T15-48-34.680007.parquet
- split: 2023_09_22T15_48_34.680007
-
config_name: harness_hellaswag_10
- split: 2023_08_17T10_46_30.131407
- path: **/details_harness|hellaswag|10_2023-08-17T10:46:30.131407.parquet
- split: latest
- path: **/details_harness|hellaswag|10_2023-08-17T10:46:30.131407.parquet
- split: 2023_08_17T10_46_30.131407
-
config_name: harness_hendrycksTest_5
- split: 2023_08_17T10_46_30.131407
- path:
- **/details_harness|hendrycksTest-abstract_algebra|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-anatomy|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-astronomy|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-college_biology|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-college_physics|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-computer_security|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-econometrics|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-global_facts|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-high_school_european_history|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-high_school_geography|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-high_school_physics|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-high_school_psychology|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-high_school_statistics|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-high_school_us_history|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-high_school_world_history|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-human_aging|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-human_sexuality|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-international_law|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-jurisprudence|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-logical_fallacies|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-machine_learning|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-management|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-marketing|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-medical_genetics|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-miscellaneous|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-moral_disputes|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-moral_scenarios|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-nutrition|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-philosophy|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-prehistory|5_2023-08-17T10:46:30.131407.parquet
- **/details_harness|hendrycksTest-professional_accounting|5_2023-08-17T10:46:30.131407.
- path:
- split: 2023_08_17T10_46_30.131407
