TheFinAI/lm-eval-results-o1-private

该数据集是在对模型/gpfs/radev/project/xu_hua/lq62/ckpts/sft_stage1/checkpoint-1-4392/tfmr进行评估运行时自动创建的。数据集由118个配置组成，每个配置对应一个评估任务。数据集已从95次运行中创建，每次运行都可以在每个配置中找到特定的分割，分割名称使用运行的timestamp命名。"train"分割始终指向最新的结果。还有一个额外的配置"results"存储所有运行的聚合结果。要加载运行的详细信息，可以按照以下方式操作：例如，这是来自运行2025-04-07T01-06-54.224509的最新结果（注意，如果连续的评估没有覆盖相同的任务，则在repos中可能会有其他任务的结果。您可以在results中找到每个，每个评估的"latest"分割中）。

Dataset automatically created during the evaluation run of model /gpfs/radev/project/xu_hua/lq62/ckpts/sft_stage1/checkpoint-1-4392/tfmr. The dataset is composed of 118 configuration(s), each one corresponding to one of the evaluated tasks. The dataset has been created from 95 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run. The "train" split is always pointing to the latest results. An additional configuration "results" store all the aggregated results of the run. To load the details from a run, you can for instance do the following: These are the latest results from run 2025-04-07T01-06-54.224509 (note that there might be results for other tasks in the repos if successive evals didnt cover the same tasks. You find each in the results and the "latest" split for each eval):