# Use custom loss function for training ML task
**URL:**
**Author:**  [@Roman](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FRoman)%5C
**Post date:** [November 4, 2021, 10:14am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fuse-custom-loss-function-for-training-ml-task%2F11351%2F1 "2021-11-04T10:14:44Z")
Hello.
I’d like to train BERT from stratch on my custom corpus for the Masked Language Modeling task. But corpus has one specific - it is sequence of the numbers and absolute value of the difference of two words corresponds to its proximity. Therefore I guess I should use this difference(or some similar) as loss function during training. Is it possible to use custom loss function training BERT model fo ML task?
---
**Author:**  [@sgugger](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fsgugger)%5C
**Post date:** [November 4, 2021, 11:54am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fuse-custom-loss-function-for-training-ml-task%2F11351%2F2 "2021-11-04T11:54:50Z")
You can compute the loss outside of your model since it returns the logits, and apply any function you like.
If you question was related to the `Trainer`, you should definte your subclass with a `compute_loss` method. There is an example in the [documentation](https://huggingface.co/transformers/main_classes/trainer.html) (scroll a bit down).
---
**Author:**  [@bui](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fbui)%5C
**Post date:** [March 17, 2022, 7:53am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fuse-custom-loss-function-for-training-ml-task%2F11351%2F3 "2022-03-17T07:53:39Z")
hi @sgugger,
in the link you attached above, I have a question related to the example.
why do we need this line of code when computing loss?
```auto
loss = loss_fct(logits.view(-1, self.model.config.num_labels), labels.view(-1))
```
I mean the .view() method. why do we have to reshape logits tensors?