# Train with MLM loss augmentation

**URL:** <https://discuss.huggingface.co/t/train-with-mlm-loss-augmentation/24240>\
**Category:** 🤗Transformers\
**Created:** [October 10, 2022, 7:47pm UTC](https://discuss.huggingface.co/t/train-with-mlm-loss-augmentation/24240 "2022-10-10T19:47:31Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![luffycodes](https://avatars.discourse-cdn.com/v4/letter/l/ccd318/32.png) [@luffycodes](https://discuss.huggingface.co/u/luffycodes)\
**Post date:** [October 10, 2022, 7:47pm UTC](https://discuss.huggingface.co/t/train-with-mlm-loss-augmentation/24240/1 "2022-10-10T19:47:31Z")

</div>

Is it possible to train an NER model with MLM loss too? Does the trainer api support two datacollators on two datasets?