open-llm-leaderboard/details_psyche__kollama2-7b
收藏资源简介:
该数据集是在Open LLM Leaderboard上对模型psyche/kollama2-7b进行评估时自动创建的。它由64个配置组成,每个配置对应一个被评估的任务。数据集由2次运行生成,每次运行在每个配置中表示为特定的分割,分割名称使用运行的时间戳。train分割始终指向最新的结果。此外,还有一个results配置存储了所有运行的聚合结果,这些结果用于计算和显示Open LLM Leaderboard上的聚合指标。可以使用`datasets`库中的`load_dataset`函数加载该数据集。
This dataset was automatically created during the evaluation of the model psyche/kollama2-7b on the Open LLM Leaderboard. It consists of 64 configurations, each corresponding to one evaluated task. The dataset is generated from two runs, where each run is represented as a specific split within each configuration, with split names using the run's timestamp. The train split always points to the most recent results. Additionally, there is a results configuration that stores the aggregated results from all runs, which are used to calculate and display the aggregate metrics on the Open LLM Leaderboard. This dataset can be loaded using the `load_dataset` function from the `datasets` library.
数据集概述
数据集简介
该数据集是在评估模型 psyche/kollama2-7b 在 Open LLM Leaderboard 上的自动创建的。数据集包含 64 个配置,每个配置对应一个评估任务。
数据集结构
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。
数据集加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_psyche__kollama2-7b", "harness_winogrande_5", split="train")
最新结果
以下是 2023-10-14T17:15:12.197275 运行 的最新结果: python { "all": { "em": 0.006396812080536913, "em_stderr": 0.0008164468837432388, "f1": 0.07105180369127512, "f1_stderr": 0.0016055423368099692, "acc": 0.3997180423570749, "acc_stderr": 0.009435490911643514 }, "harness|drop|3": { "em": 0.006396812080536913, "em_stderr": 0.0008164468837432388, "f1": 0.07105180369127512, "f1_stderr": 0.0016055423368099692 }, "harness|gsm8k|5": { "acc": 0.05989385898407885, "acc_stderr": 0.006536148151288735 }, "harness|winogrande|5": { "acc": 0.739542225730071, "acc_stderr": 0.012334833671998292 } }
配置详情
以下是数据集的配置详情:
-
config_name: harness_arc_challenge_25
- splits:
- 2023_07_26T11_31_26.569073
- latest
- paths:
- **/details_harness|arc:challenge|25_2023-07-26T11:31:26.569073.parquet
- splits:
-
config_name: harness_drop_3
- splits:
- 2023_10_14T17_15_12.197275
- latest
- paths:
- **/details_harness|drop|3_2023-10-14T17-15-12.197275.parquet
- splits:
-
config_name: harness_gsm8k_5
- splits:
- 2023_10_14T17_15_12.197275
- latest
- paths:
- **/details_harness|gsm8k|5_2023-10-14T17-15-12.197275.parquet
- splits:
-
config_name: harness_hellaswag_10
- splits:
- 2023_07_26T11_31_26.569073
- latest
- paths:
- **/details_harness|hellaswag|10_2023-07-26T11:31:26.569073.parquet
- splits:
-
config_name: harness_hendrycksTest_5
- splits:
- 2023_07_26T11_31_26.569073
- latest
- paths:
- **/details_harness|hendrycksTest-abstract_algebra|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-anatomy|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-astronomy|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-college_biology|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-college_physics|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-computer_security|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-econometrics|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-global_facts|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-high_school_computer_science|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-high_school_european_history|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-high_school_geography|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-high_school_mathematics|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-high_school_physics|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-high_school_psychology|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-high_school_statistics|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-high_school_us_history|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-high_school_world_history|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-human_aging|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-human_sexuality|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-international_law|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-jurisprudence|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-logical_fallacies|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-machine_learning|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-management|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-marketing|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-medical_genetics|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-miscellaneous|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-moral_disputes|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-moral_scenarios|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-nutrition|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-philosophy|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-prehistory|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-professional_accounting|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-professional_law|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-professional_medicine|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-professional_psychology|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-public_relations|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-security_studies|5_2023-07-26T11:31:26.569073.parquet
- **/details_harness|hendrycksTest-sociology|5_2023-07-26T11:31:2
- splits:



