# Trainer Loads old TrainingArguments

**URL:** <https://discuss.huggingface.co/t/trainer-loads-old-trainingarguments/61772>\
**Category:** 🤗Transformers\
**Created:** [November 10, 2023, 8:36am UTC](https://discuss.huggingface.co/t/trainer-loads-old-trainingarguments/61772 "2023-11-10T08:36:40Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![boda](https://avatars.discourse-cdn.com/v4/letter/b/ecae2f/32.png) [@boda](https://discuss.huggingface.co/u/boda)\
**Post date:** [November 10, 2023, 8:36am UTC](https://discuss.huggingface.co/t/trainer-loads-old-trainingarguments/61772/1 "2023-11-10T08:36:40Z")

</div>

I am trying to resume training from a checkpoint. But then the trainer ignores my current training arguments, and instead train with the training arguments that is stored with the checkpoint. I am using SFT Trainer.