diff --git a/examples/siamese_glvq_iris.py b/examples/siamese_glvq_iris.py
index b00e308..ff63da9 100644
--- a/examples/siamese_glvq_iris.py
+++ b/examples/siamese_glvq_iris.py
@@ -51,8 +51,7 @@ if __name__ == "__main__":
     # Hyperparameters
     hparams = dict(
         distribution=[1, 2, 3],
-        proto_lr=0.01,
-        bb_lr=0.01,
+        lr=0.01,
     )
 
     # Initialize the backbone
diff --git a/examples/siamese_gtlvq_iris.py b/examples/siamese_gtlvq_iris.py
index 4f036d1..35405e1 100644
--- a/examples/siamese_gtlvq_iris.py
+++ b/examples/siamese_gtlvq_iris.py
@@ -51,8 +51,7 @@ if __name__ == "__main__":
     # Hyperparameters
     hparams = dict(
         distribution=[1, 2, 3],
-        proto_lr=0.01,
-        bb_lr=0.01,
+        lr=0.01,
         input_dim=2,
         latent_dim=1,
     )
diff --git a/examples/warm_starting.py b/examples/warm_starting.py
index a9e17dc..22acf51 100644
--- a/examples/warm_starting.py
+++ b/examples/warm_starting.py
@@ -55,7 +55,9 @@ if __name__ == "__main__":
 
     # Setup trainer for GNG
     trainer = pl.Trainer(
-        max_epochs=1000,
+        accelerator="cpu",
+        max_epochs=50 if args.fast_dev_run else
+        1000,  # 10 epochs fast dev run reproducible DIV error.
         callbacks=[
             es,
         ],
diff --git a/glvq_iris.ckpt b/glvq_iris.ckpt
new file mode 100644
index 0000000..4579313
Binary files /dev/null and b/glvq_iris.ckpt differ
diff --git a/iris.pth b/iris.pth
new file mode 100644
index 0000000..7e485c0
Binary files /dev/null and b/iris.pth differ
diff --git a/prototorch/models/glvq.py b/prototorch/models/glvq.py
index 2ca9834..8f77fdd 100644
--- a/prototorch/models/glvq.py
+++ b/prototorch/models/glvq.py
@@ -123,26 +123,6 @@ class SiameseGLVQ(GLVQ):
         self.backbone = backbone
         self.both_path_gradients = both_path_gradients
 
-    def configure_optimizers(self):
-        proto_opt = self.optimizer(self.proto_layer.parameters(),
-                                   lr=self.hparams["proto_lr"])
-        # Only add a backbone optimizer if backbone has trainable parameters
-        bb_params = list(self.backbone.parameters())
-        if (bb_params):
-            bb_opt = self.optimizer(bb_params, lr=self.hparams["bb_lr"])
-            optimizers = [proto_opt, bb_opt]
-        else:
-            optimizers = [proto_opt]
-        if self.lr_scheduler is not None:
-            schedulers = []
-            for optimizer in optimizers:
-                scheduler = self.lr_scheduler(optimizer,
-                                              **self.lr_scheduler_kwargs)
-                schedulers.append(scheduler)
-            return optimizers, schedulers
-        else:
-            return optimizers
-
     def compute_distances(self, x):
         protos, _ = self.proto_layer()
         x, protos = (arr.view(arr.size(0), -1) for arr in (x, protos))
diff --git a/prototorch/models/unsupervised.py b/prototorch/models/unsupervised.py
index 8833de2..80d7d85 100644
--- a/prototorch/models/unsupervised.py
+++ b/prototorch/models/unsupervised.py
@@ -63,7 +63,7 @@ class KohonenSOM(NonGradientMixin, UnsupervisedPrototypeModel):
             strict=False,
         )
 
-    def training_epoch_end(self, training_step_outputs):
+    def on_training_epoch_end(self, training_step_outputs):
         self._sigma = self.hparams.sigma * np.exp(
             -self.current_epoch / self.trainer.max_epochs)