diff --git a/dalle2_pytorch/trainer.py b/dalle2_pytorch/trainer.py
index 73f6108..b02995e 100644
--- a/dalle2_pytorch/trainer.py
+++ b/dalle2_pytorch/trainer.py
@@ -451,6 +451,8 @@ class DecoderTrainer(nn.Module):
 
         lr, wd, eps = map(partial(cast_tuple, length = self.num_unets), (lr, wd, eps))
 
+        assert all([unet_lr < 1e-3 for unet_lr in lr]), 'your learning rate is too high, recommend sticking with 1e-4, at most 5e-4'
+
         optimizers = []
 
         for unet, unet_lr, unet_wd, unet_eps in zip(decoder.unets, lr, wd, eps):
diff --git a/dalle2_pytorch/version.py b/dalle2_pytorch/version.py
index 8e747cc..eebcbfe 100644
--- a/dalle2_pytorch/version.py
+++ b/dalle2_pytorch/version.py
@@ -1 +1 @@
-__version__ = '0.11.4'
+__version__ = '0.11.5'