open-llm-leaderboard-old/details_core-3__kuno-royale-v3-7b
收藏数据集概述
数据集简介
该数据集是在对模型 core-3/kuno-royale-v3-7b 进行评估运行期间自动创建的,用于 Open LLM Leaderboard。
数据集结构
- 配置数量:63个配置,每个配置对应一个评估任务。
- 数据来源:数据集来自1次运行,每个运行结果作为一个特定的分割(split)存储,分割名称使用运行的时间戳。
- 最新结果:"train" 分割始终指向最新的结果。
- 汇总结果:一个额外的配置 "results" 存储所有运行的汇总结果,用于计算和显示在 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_core-3__kuno-royale-v3-7b", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-06T23:00:23.566088 运行的最新结果:
python { "all": { "acc": 0.6561030311416244, "acc_stderr": 0.03209866738970972, "acc_norm": 0.6556377479468806, "acc_norm_stderr": 0.03276600042080479, "mc1": 0.565483476132191, "mc1_stderr": 0.01735273874925956, "mc2": 0.7112523953784756, "mc2_stderr": 0.014775184778676297 }, "harness|arc:challenge|25": { "acc": 0.697098976109215, "acc_stderr": 0.013428241573185349, "acc_norm": 0.7175767918088737, "acc_norm_stderr": 0.013155456884097225 }, "harness|hellaswag|10": { "acc": 0.711113324039036, "acc_stderr": 0.004523188431142894, "acc_norm": 0.8822943636725752, "acc_norm_stderr": 0.003216006357760381 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.35, "acc_stderr": 0.047937248544110196, "acc_norm": 0.35, "acc_norm_stderr": 0.047937248544110196 }, ... }
配置详情
-
配置名称:harness_arc_challenge_25
- 数据文件:
- 分割:2024_03_06T23_00_23.566088
- 路径:
**/details_harness|arc:challenge|25_2024-03-06T23-00-23.566088.parquet
- 路径:
- 分割:latest
- 路径:
**/details_harness|arc:challenge|25_2024-03-06T23-00-23.566088.parquet
- 路径:
- 分割:2024_03_06T23_00_23.566088
- 数据文件:
-
配置名称:harness_gsm8k_5
- 数据文件:
- 分割:2024_03_06T23_00_23.566088
- 路径:
**/details_harness|gsm8k|5_2024-03-06T23-00-23.566088.parquet
- 路径:
- 分割:latest
- 路径:
**/details_harness|gsm8k|5_2024-03-06T23-00-23.566088.parquet
- 路径:
- 分割:2024_03_06T23_00_23.566088
- 数据文件:
-
配置名称:harness_hellaswag_10
- 数据文件:
- 分割:2024_03_06T23_00_23.566088
- 路径:
**/details_harness|hellaswag|10_2024-03-06T23-00-23.566088.parquet
- 路径:
- 分割:latest
- 路径:
**/details_harness|hellaswag|10_2024-03-06T23-00-23.566088.parquet
- 路径:
- 分割:2024_03_06T23_00_23.566088
- 数据文件:
-
配置名称:harness_hendrycksTest_5
- 数据文件:
- 分割:2024_03_06T23_00_23.566088
- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2024-03-06T23-00-23.566088.parquet**/details_harness|hendrycksTest-anatomy|5_2024-03-06T23-00-23.566088.parquet**/details_harness|hendrycksTest-astronomy|5_2024-03-06T23-00-23.566088.parquet**/details_harness|hendrycksTest-business_ethics|5_2024-03-06T23-00-23.566088.parquet**/details_harness|hendrycksTest-clinical_knowledge|5_2024-03-06T23-00-23.566088.parquet**/details_harness|hendrycksTest-college_biology|5_2024-03-06T23-00-23.566088.parquet**/details_harness|hendrycksTest-college_chemistry|5_2024-03-06T23-00-23.566088.parquet**/details_harness|hendrycksTest-college_computer_science|5_2024-03-06T23-00-23.566088.parquet**/details_harness|hendrycksTest-college_mathematics|5_2024-03-06T23-00-23.566088.parquet**/details_harness|hendrycksTest-college_medicine|5_2024-03-06T23-00-23.566088.parquet**/details_harness|hendrycksTest-college_physics|5_2024-03-06T23-00-23.566088.parquet**/details_harness|hendrycksTest-computer_security|5_2024-03-06T23-00-23.566088.parquet**/details_harness|hendrycksTest-conceptual_physics|5_2024-03-06T23-00-23.566088.parquet**/details_harness|hendrycksTest-econometrics|5_2024-03-06T23-00-23.566088.parquet**/details_harness|hendrycksTest-electrical_engineering|5_2024-03-06T23-00-23.566088.parquet**/details_harness|hendrycksTest-elementary_mathematics|5_2024-03-06T23-00-23.566088.parquet**/details_harness|hendrycksTest-formal_logic|5_2024-03-06T23-00-23.566088.parquet**/details_harness|hendrycksTest-global_facts|5_2024-03-06T23-00-23.566088.parquet**/details_harness|hendrycksTest-high_school_biology|5_2024-03-06T23-00-23.566088.parquet**/details_harness|hendrycksTest-high_school_chemistry|5_2024-03-06T23-00-23.566088.parquet- ...
- 路径:
- 分割:latest
- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2024-03-06T23-00-23.566088.parquet**/details_harness|hendrycksTest-anatomy|5_2024-03-06T23-00-23.566088.parquet**/details_harness|hendrycksTest-astronomy|5_2024-03-06T23-00-23.566088.parquet**/details_harness|hendrycksTest-business_ethics|5_2024-03-06T23-00-23.566088.parquet**/details_harness|hendrycksTest-clinical_knowledge|5_2024-03-06T23-00-23.566088.parquet**/details_harness|hendrycksTest-college_biology|5_2024-03-06T23-00-23.566088.parquet**/details_harness|hendrycksTest-college_chemistry|5_2024-03-06T23-00-23.566088.parquet**/details_harness|hendrycksTest-college_computer_science|5_2024-03-06T23-00-23.566088.parquet**/details_harness|hendrycksTest-college_mathematics|5_2024-03-06T23-00-23.566088.parquet**/details_harness|hendrycksTest-college_medicine|5_2024-03-06T23-00-23.566088.parquet**/details_harness|hendrycksTest-college_physics|5_2024-03-06T23-00-23.566088.parquet**/details_harness|hendrycksTest-computer_security|5_2024-03-06T23-00-23.566088.parquet**/details_harness|hendrycksTest-conceptual_physics|5_2024-03-06T23-00-23.566088.parquet**/details_harness|hendrycksTest-econometrics|5_2024-03-06T23-00-23.566088.parquet**/details_harness|hendrycksTest-electrical_engineering|5_2024-03-06T23-00-23.566088.parquet**/details_harness|hendrycksTest-elementary_mathematics|5_2024-03-06T23-00-23.566088.parquet**/details_harness|hendrycksTest-formal_logic|5_2024-03-06T23-00-23.566088.parquet**/details_harness|hendrycksTest-global_facts|5_2024-03-06T23-00-23.566088.parquet**/details_harness|hendrycksTest-high_school_biology|5_2024-03-06T23-00-23.566088.parquet**/details_harness|hendrycksTest-high_school_chemistry|5_2024-03-06T23-00-23.566088.parquet- ... }
- 路径:
- 分割:2024_03_06T23_00_23.566088
- 数据文件:



