diff --git a/README.md b/README.md
index 12e6252..96890d1 100644
--- a/README.md
+++ b/README.md
@@ -81,6 +81,14 @@ By default, the `scale` is 0.5, so if you wish to obtain better results (but use
 
 The input images and target masks should be in the `data/imgs` and `data/masks` folders respectively.
 
+### Pretrained model
+A [pretrained model](https://github.com/milesial/Pytorch-UNet/releases/tag/v1.0) is available for the Carvana dataset. It can also be loaded from torch.hub:
+
+```python
+net = torch.hub.load('milesial/Pytorch-UNet', 'unet_carvana')
+```
+The training was done with a 100% scale and bilinear upsampling.
+
 ## Tensorboard
 You can visualize in real time the train and test losses, the weights and gradients, along with the model predictions with tensorboard:
 
diff --git a/train.py b/train.py
index 200ccfa..c7bc600 100644
--- a/train.py
+++ b/train.py
@@ -130,7 +130,7 @@ def get_args():
                         help='Number of epochs', dest='epochs')
     parser.add_argument('-b', '--batch-size', metavar='B', type=int, nargs='?', default=1,
                         help='Batch size', dest='batchsize')
-    parser.add_argument('-l', '--learning-rate', metavar='LR', type=float, nargs='?', default=0.1,
+    parser.add_argument('-l', '--learning-rate', metavar='LR', type=float, nargs='?', default=0.0001,
                         help='Learning rate', dest='lr')
     parser.add_argument('-f', '--load', dest='load', type=str, default=False,
                         help='Load model from a .pth file')