open-llm-leaderboard/details_Yukang__Llama-2-7b-longlora-32k-ft
收藏Hugging Face2023-12-03 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_Yukang__Llama-2-7b-longlora-32k-ft
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Yukang/Llama-2-7b-longlora-32k-ft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。数据集是从4次运行中创建的,每次运行的结果都作为特定的分割存储在配置中,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上的聚合指标。
This dataset was automatically created during the evaluation of the model Yukang/Llama-2-7b-longlora-32k-ft on the Open LLM Leaderboard. The dataset consists of 64 configurations, each corresponding to one evaluation task. The dataset is constructed from 4 runs, with the results of each run stored as a specific split within the corresponding configuration, where the split name uses the timestamp of the run. The "train" split always points to the most recent evaluation results. In addition, there is a configuration named "results" that stores the aggregated results of all runs, and is 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
数据集简介
该数据集是在评估模型 Yukang/Llama-2-7b-longlora-32k-ft 在 Open LLM Leaderboard 上的自动创建的。
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。
- 数据集从 4 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" 分割总是指向最新的结果。
- 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。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_Yukang__Llama-2-7b-longlora-32k-ft", "harness_gsm8k_5", split="train")
最新结果
最新结果来自 2023-12-03T15:57:17.629936 运行,具体如下: python { "all": { "acc": 0.0, "acc_stderr": 0.0 }, "harness|gsm8k|5": { "acc": 0.0, "acc_stderr": 0.0 } }
配置详情
以下是部分配置及其数据文件路径:
配置:harness_arc_challenge_25
- 分割:2023_10_10T13_03_11.726005
- 路径:
**/details_harness|arc:challenge|25_2023-10-10T13-03-11.726005.parquet
- 路径:
- 分割:latest
- 路径:
**/details_harness|arc:challenge|25_2023-10-10T13-03-11.726005.parquet
- 路径:
配置:harness_drop_3
- 分割:2023_11_04T20_34_41.636751
- 路径:
**/details_harness|drop|3_2023-11-04T20-34-41.636751.parquet
- 路径:
- 分割:2023_11_06T19_21_33.792030
- 路径:
**/details_harness|drop|3_2023-11-06T19-21-33.792030.parquet
- 路径:
- 分割:latest
- 路径:
**/details_harness|drop|3_2023-11-06T19-21-33.792030.parquet
- 路径:
配置:harness_gsm8k_5
- 分割:2023_11_04T20_34_41.636751
- 路径:
**/details_harness|gsm8k|5_2023-11-04T20-34-41.636751.parquet
- 路径:
- 分割:2023_11_06T19_21_33.792030
- 路径:
**/details_harness|gsm8k|5_2023-11-06T19-21-33.792030.parquet
- 路径:
- 分割:2023_12_03T15_57_17.629936
- 路径:
**/details_harness|gsm8k|5_2023-12-03T15-57-17.629936.parquet
- 路径:
- 分割:latest
- 路径:
**/details_harness|gsm8k|5_2023-12-03T15-57-17.629936.parquet
- 路径:
配置:harness_hellaswag_10
- 分割:2023_10_10T13_03_11.726005
- 路径:
**/details_harness|hellaswag|10_2023-10-10T13-03-11.726005.parquet
- 路径:
- 分割:latest
- 路径:
**/details_harness|hellaswag|10_2023-10-10T13-03-11.726005.parquet
- 路径:
配置:harness_hendrycksTest_5
- 分割:2023_10_10T13_03_11.726005
- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-anatomy|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-astronomy|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-business_ethics|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-clinical_knowledge|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-college_biology|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-college_chemistry|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-college_computer_science|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-college_mathematics|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-college_medicine|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-college_physics|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-computer_security|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-conceptual_physics|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-econometrics|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-electrical_engineering|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-elementary_mathematics|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-formal_logic|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-global_facts|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-high_school_biology|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-high_school_chemistry|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-high_school_computer_science|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-high_school_european_history|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-high_school_geography|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-high_school_mathematics|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-high_school_physics|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-high_school_psychology|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-high_school_statistics|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-high_school_us_history|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-high_school_world_history|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-human_aging|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-human_sexuality|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-international_law|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-jurisprudence|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-logical_fallacies|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-machine_learning|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-management|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-marketing|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-medical_genetics|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-miscellaneous|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-moral_disputes|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-moral_scenarios|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-nutrition|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-philosophy|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-prehistory|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-professional_accounting|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-professional_law|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-professional_medicine|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-professional_psychology|5_2023-10-10T13-03-11.726005.parquet**/details_harness|hendrycksTest-public_relations|5_2023-10-10T13-03-11.726005.parquet- `**/details_harness|hendrycksTest-security_studies|5_2023-10-10T13-03
- 路径:



