diff --git a/denoising_diffusion_pytorch/denoising_diffusion_pytorch.py b/denoising_diffusion_pytorch/denoising_diffusion_pytorch.py
index 5c177ad..c7a3958 100644
--- a/denoising_diffusion_pytorch/denoising_diffusion_pytorch.py
+++ b/denoising_diffusion_pytorch/denoising_diffusion_pytorch.py
@@ -694,7 +694,7 @@ class Trainer(object):
         self.step = data['step']
         self.ema.load_state_dict(data['ema'])
 
-        if exists(self.accelerator.scaler):
+        if exists(self.accelerator.scaler) and exists(data['scaler']):
             self.accelerator.scaler.load_state_dict(data['scaler'])
 
     def train(self):
diff --git a/setup.py b/setup.py
index 839be57..771f361 100644
--- a/setup.py
+++ b/setup.py
@@ -3,7 +3,7 @@ from setuptools import setup, find_packages
 setup(
   name = 'denoising-diffusion-pytorch',
   packages = find_packages(),
-  version = '0.24.0',
+  version = '0.24.1',
   license='MIT',
   description = 'Denoising Diffusion Probabilistic Models - Pytorch',
   author = 'Phil Wang',