From dd0db4aba295ec9f9a6b44b37c8ca2a05e2c0e36 Mon Sep 17 00:00:00 2001
From: Rich Lewis <2941720+lewisacidic@users.noreply.github.com>
Date: Fri, 9 Aug 2019 20:02:14 +0100
Subject: [PATCH] docs(trainer): fix gradient clipping entry (#85)

- replace copy and paste error
- write brief description
- add link to pytorch docs for specific clipping implementation
- add example configuration
---
 docs/Trainer/Training Loop.md | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/docs/Trainer/Training Loop.md b/docs/Trainer/Training Loop.md
index c2b6dc35..28812850 100644
--- a/docs/Trainer/Training Loop.md	
+++ b/docs/Trainer/Training Loop.md	
@@ -28,15 +28,18 @@ trainer = Trainer(enable_early_stop=True)
 ```
 
 ---
-#### Gradient Clipping 
-Use this to turn off early stopping and run training to the [max_epoch](#force-training-for-min-or-max-epochs)
+#### Gradient Clipping
+Gradient clipping may be enabled to avoid exploding gradients.
+Specifically, this will [clip the gradient norm computed over all model parameters *together*](https://pytorch.org/docs/stable/nn.html#torch.nn.utils.clip_grad_norm_).
+
 ``` {.python}
 # DEFAULT (ie: don't clip)
 trainer = Trainer(gradient_clip=0)
+
+# clip gradients with norm above 0.5
+trainer = Trainer(gradient_clip=0.5)
 ```
 
-
-
 ---
 #### Inspect gradient norms
 Looking at grad norms can help you figure out where training might be going wrong.