From 62d7f97b688981d823419e2d0c8ec97d31a74e7f Mon Sep 17 00:00:00 2001
From: dreivmeister <93375746+dreivmeister@users.noreply.github.com>
Date: Wed, 12 Jul 2023 23:51:52 +0200
Subject: [PATCH] Update training.md

---
 docs/src/training/training.md | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/docs/src/training/training.md b/docs/src/training/training.md
index 3070494188..623b4788fc 100644
--- a/docs/src/training/training.md
+++ b/docs/src/training/training.md
@@ -61,8 +61,8 @@ then the derivative of the loss with respect to it is `∂f_∂θ = grads[1].lay
 It is important that the execution of the model takes place inside the call to `gradient`,
 in order for the influence of the model's parameters to be observed by Zygote.
 
-It is also important that every `update!` step receives a newly gradient computed gradient,
-as this will be change whenever the model's parameters are changed, and for each new data point.
+It is also important that every `update!` step receives a newly computed gradient,
+as it will change whenever the model's parameters are changed, and for each new data point.
 
 !!! compat "Implicit gradients"
     Flux ≤ 0.14 used Zygote's "implicit" mode, in which `gradient` takes a zero-argument function.