# Seq2SeqTrainingAguments

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fseq2seqtrainingaguments%2F30489%3E%5C
**Category:** Beginners\
**Created:** [January 26, 2023, 2:43pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fseq2seqtrainingaguments%2F30489 "2023-01-26T14:43:54Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![qqqube](https://avatars.discourse-cdn.com/v4/letter/q/a587f6/32.png) [@qqqube](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fqqqube)%5C
**Post date:** [January 26, 2023, 2:43pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fseq2seqtrainingaguments%2F30489%2F1 "2023-01-26T14:43:54Z")

</div>

I’m a little confused about the purpose of `predict_with_generate`. My training losses are always better when I set this to true but I’m under the impression that it’s not supposed to affect training at all.

Also, if I do not specify a `compute_metrics` function in the `Seq2SeqTrainer` but keep `predict_with_generate` set to True, are the training/validation losses computed differently?