# Why "loss.backward()" didn't update parameters' gradient?

**URL:** <https://discuss.pytorch.org/t/why-loss-backward-didnt-update-parameters-gradient/19515>\
**Category:** autograd\
**Created:** [June 11, 2018, 12:36pm UTC](https://discuss.pytorch.org/t/why-loss-backward-didnt-update-parameters-gradient/19515 "2018-06-11T12:36:51Z")\
**Posts on this page:** 1\
**Showing post:** 14

<div class="post-metadata">

**Author:** ![ptrblck](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/ptrblck/32/1823_2.png) [@ptrblck](https://discuss.pytorch.org/u/ptrblck)\
**Post date:** [August 31, 2020, 1:19am UTC](https://discuss.pytorch.org/t/why-loss-backward-didnt-update-parameters-gradient/19515/14 "2020-08-31T01:19:46Z")

</div>

Double post with answer from [here](https://discuss.pytorch.org/t/why-by-adding-second-loss-and-applying-the-back-ward-generated-gradient-is-as-same-as-before/94625/2).

---

_[View the full topic](https://discuss.pytorch.org/t/why-loss-backward-didnt-update-parameters-gradient/19515)._