open-llm-leaderboard/details_itsliupeng__llama2_7b_mmlu
收藏Hugging Face2023-10-25 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_itsliupeng__llama2_7b_mmlu
下载链接
链接失效反馈官方服务:
资源简介:
该数据集是在评估模型itsliupeng/llama2_7b_mmlu时自动创建的,用于Open LLM Leaderboard的评估。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,"results"配置存储了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。
This dataset was automatically created during the evaluation of the model itsliupeng/llama2_7b_mmlu, and is intended for use in evaluations for the Open LLM Leaderboard. The dataset consists of 64 configurations, each corresponding to a single evaluation task. The dataset is generated from two runs, with the results of each run serving as a data split within a specific configuration, where the split name uses the timestamp of the corresponding run. The "train" split always points to the most recent results. Additionally, the "results" configuration stores the aggregated results from all runs, which are used to calculate and display the aggregated metrics on the Open LLM Leaderboard.
提供机构:
open-llm-leaderboard原始信息汇总
数据集概述
数据集基本信息
- 名称: Evaluation run of itsliupeng/llama2_7b_mmlu
- 来源: 自动创建于模型 itsliupeng/llama2_7b_mmlu 在 Open LLM Leaderboard 的评估运行期间。
- 组成: 包含 64 个配置,每个配置对应一个评估任务。
- 创建方式: 从 2 次运行中创建,每次运行在每个配置中作为一个特定的分割存在,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: "results" 配置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_itsliupeng__llama2_7b_mmlu", "harness_winogrande_5", split="train")
最新结果
- 最新结果: 来自 2023-10-25T10:05:20.920502 运行的最新结果如下: python { "all": { "em": 0.0012583892617449664, "em_stderr": 0.0003630560893119021, "f1": 0.05594588926174501, "f1_stderr": 0.0013036425627808016, "acc": 0.41156271672651484, "acc_stderr": 0.009842322182656855 }, "harness|drop|3": { "em": 0.0012583892617449664, "em_stderr": 0.0003630560893119021, "f1": 0.05594588926174501, "f1_stderr": 0.0013036425627808016 }, "harness|gsm8k|5": { "acc": 0.07884761182714177, "acc_stderr": 0.00742339051987324 }, "harness|winogrande|5": { "acc": 0.744277821625888, "acc_stderr": 0.012261253845440473 } }
配置详情
-
配置名称: harness_arc_challenge_25
- 数据文件:
- 分割: 2023_10_10T15_25_23.413789
- 路径: **/details_harness|arc:challenge|25_2023-10-10T15-25-23.413789.parquet
- 分割: latest
- 路径: **/details_harness|arc:challenge|25_2023-10-10T15-25-23.413789.parquet
- 分割: 2023_10_10T15_25_23.413789
- 数据文件:
-
配置名称: harness_drop_3
- 数据文件:
- 分割: 2023_10_25T10_05_20.920502
- 路径: **/details_harness|drop|3_2023-10-25T10-05-20.920502.parquet
- 分割: latest
- 路径: **/details_harness|drop|3_2023-10-25T10-05-20.920502.parquet
- 分割: 2023_10_25T10_05_20.920502
- 数据文件:
-
配置名称: harness_gsm8k_5
- 数据文件:
- 分割: 2023_10_25T10_05_20.920502
- 路径: **/details_harness|gsm8k|5_2023-10-25T10-05-20.920502.parquet
- 分割: latest
- 路径: **/details_harness|gsm8k|5_2023-10-25T10-05-20.920502.parquet
- 分割: 2023_10_25T10_05_20.920502
- 数据文件:
-
配置名称: harness_hellaswag_10
- 数据文件:
- 分割: 2023_10_10T15_25_23.413789
- 路径: **/details_harness|hellaswag|10_2023-10-10T15-25-23.413789.parquet
- 分割: latest
- 路径: **/details_harness|hellaswag|10_2023-10-10T15-25-23.413789.parquet
- 分割: 2023_10_10T15_25_23.413789
- 数据文件:
-
配置名称: harness_hendrycksTest_5
- 数据文件:
- 分割: 2023_10_10T15_25_23.413789
- 路径:
- **/details_harness|hendrycksTest-abstract_algebra|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-anatomy|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-astronomy|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-college_biology|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-college_physics|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-computer_security|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-econometrics|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-global_facts|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-high_school_computer_science|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-high_school_european_history|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-high_school_geography|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-high_school_mathematics|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-high_school_physics|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-high_school_psychology|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-high_school_statistics|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-high_school_us_history|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-high_school_world_history|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-human_aging|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-human_sexuality|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-international_law|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-jurisprudence|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-logical_fallacies|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-machine_learning|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-management|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-marketing|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-medical_genetics|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-miscellaneous|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-moral_disputes|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-moral_scenarios|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-nutrition|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-philosophy|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-prehistory|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-professional_accounting|5_2023-10-10T15-25-23.413789.parquet
- **/details_harness|hendrycksTest-professional_law|5_2023-10-10T15-25-23.413789.parquet
- **/details
- 路径:
- 分割: 2023_10_10T15_25_23.413789
- 数据文件:



