open-llm-leaderboard-old/details_grimjim__zephyr-wizard-kuno-royale-BF16-merge-7B
收藏数据集概述
数据集创建
该数据集是在对模型 grimjim/zephyr-wizard-kuno-royale-BF16-merge-7B 进行评估运行期间自动创建的,评估结果展示在 Open LLM Leaderboard 上。
数据集组成
数据集由 63 个配置组成,每个配置对应一个评估任务。数据集从 2 次运行中创建,每次运行可以在每个配置中作为一个特定的分割找到,分割名称使用运行的时间戳。"train" 分割总是指向最新的结果。
额外配置
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_grimjim__zephyr-wizard-kuno-royale-BF16-merge-7B", "harness_winogrande_5", split="train")
最新结果
以下是 最新结果 的摘要:
python { "all": { "acc": 0.6518072975845732, "acc_stderr": 0.032222749090259295, "acc_norm": 0.6529517003279462, "acc_norm_stderr": 0.03287423194881161, "mc1": 0.4847001223990208, "mc1_stderr": 0.017495304473187902, "mc2": 0.6554539254831887, "mc2_stderr": 0.015190228666259653 }, "harness|arc:challenge|25": { "acc": 0.6621160409556314, "acc_stderr": 0.013822047922283512, "acc_norm": 0.6877133105802048, "acc_norm_stderr": 0.013542598541688067 }, "harness|hellaswag|10": { "acc": 0.6972714598685521, "acc_stderr": 0.0045849979353604405, "acc_norm": 0.8689504082852022, "acc_norm_stderr": 0.0033676492203621195 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.4, "acc_stderr": 0.049236596391733084, "acc_norm": 0.4, "acc_norm_stderr": 0.049236596391733084 }, # 其他任务的结果... }
配置详情
-
config_name: harness_arc_challenge_25
- splits:
- 2024_04_19T21_59_19.193146
- 2024_04_23T10_25_17.043076
- latest
- paths:
- **/details_harness|arc:challenge|25_2024-04-19T21-59-19.193146.parquet
- **/details_harness|arc:challenge|25_2024-04-23T10-25-17.043076.parquet
- splits:
-
config_name: harness_gsm8k_5
- splits:
- 2024_04_19T21_59_19.193146
- 2024_04_23T10_25_17.043076
- latest
- paths:
- **/details_harness|gsm8k|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|gsm8k|5_2024-04-23T10-25-17.043076.parquet
- splits:
-
config_name: harness_hellaswag_10
- splits:
- 2024_04_19T21_59_19.193146
- 2024_04_23T10_25_17.043076
- latest
- paths:
- **/details_harness|hellaswag|10_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hellaswag|10_2024-04-23T10-25-17.043076.parquet
- splits:
-
config_name: harness_hendrycksTest_5
- splits:
- 2024_04_19T21_59_19.193146
- 2024_04_23T10_25_17.043076
- latest
- paths:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-global_facts|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-high_school_computer_science|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-high_school_european_history|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-high_school_geography|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-high_school_mathematics|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-high_school_physics|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-high_school_psychology|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-high_school_statistics|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-high_school_us_history|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-high_school_world_history|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-human_aging|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-human_sexuality|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-international_law|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-jurisprudence|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-logical_fallacies|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-machine_learning|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-management|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-marketing|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-medical_genetics|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-miscellaneous|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-moral_disputes|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-moral_scenarios|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-nutrition|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-philosophy|5_2024-04-19T21-59-19.193146.parquet
- **/details_harness|hendrycksTest-prehistory|5_2024-
- splits:



