diff --git a/course_UvA-DL/01-introduction-to-pytorch/.meta.yml b/course_UvA-DL/01-introduction-to-pytorch/.meta.yml
index 34d1aed4a..ce7c76634 100644
--- a/course_UvA-DL/01-introduction-to-pytorch/.meta.yml
+++ b/course_UvA-DL/01-introduction-to-pytorch/.meta.yml
@@ -1,7 +1,7 @@
 title: "Tutorial 1: Introduction to PyTorch"
 author: Phillip Lippe
 created: 2021-08-27
-updated: 2021-11-29
+updated: 2023-01-04
 license: CC BY-SA
 description: |
   This tutorial will give a short introduction to PyTorch basics, and get you setup for writing your own neural networks.
diff --git a/course_UvA-DL/01-introduction-to-pytorch/Introduction_to_PyTorch.py b/course_UvA-DL/01-introduction-to-pytorch/Introduction_to_PyTorch.py
index 74454e209..b8ece34bb 100644
--- a/course_UvA-DL/01-introduction-to-pytorch/Introduction_to_PyTorch.py
+++ b/course_UvA-DL/01-introduction-to-pytorch/Introduction_to_PyTorch.py
@@ -455,7 +455,7 @@
 
 # Additionally, some operations on a GPU are implemented stochastic for efficiency
 # We want to ensure that all operations are deterministic on GPU (if used) for reproducibility
-torch.backends.cudnn.determinstic = True
+torch.backends.cudnn.deterministic = True
 torch.backends.cudnn.benchmark = False
 
 # %% [markdown]
diff --git a/course_UvA-DL/02-activation-functions/.meta.yml b/course_UvA-DL/02-activation-functions/.meta.yml
index 8fd86a8bc..9b435ff02 100644
--- a/course_UvA-DL/02-activation-functions/.meta.yml
+++ b/course_UvA-DL/02-activation-functions/.meta.yml
@@ -1,7 +1,7 @@
 title: "Tutorial 2: Activation Functions"
 author: Phillip Lippe
 created: 2021-08-27
-updated: 2021-08-27
+updated: 2023-01-04
 license: CC BY-SA
 description: |
   In this tutorial, we will take a closer look at (popular) activation functions and investigate their effect on optimization properties in neural networks.
diff --git a/course_UvA-DL/02-activation-functions/Activation_Functions.py b/course_UvA-DL/02-activation-functions/Activation_Functions.py
index 9645ff57f..539f8c014 100644
--- a/course_UvA-DL/02-activation-functions/Activation_Functions.py
+++ b/course_UvA-DL/02-activation-functions/Activation_Functions.py
@@ -64,7 +64,7 @@ def set_seed(seed):
 
 # Additionally, some operations on a GPU are implemented stochastic for efficiency
 # We want to ensure that all operations are deterministic on GPU (if used) for reproducibility
-torch.backends.cudnn.determinstic = True
+torch.backends.cudnn.deterministic = True
 torch.backends.cudnn.benchmark = False
 
 # Fetching the device that will be used throughout this notebook
diff --git a/course_UvA-DL/03-initialization-and-optimization/.meta.yml b/course_UvA-DL/03-initialization-and-optimization/.meta.yml
index 6e79e150f..82961aea1 100644
--- a/course_UvA-DL/03-initialization-and-optimization/.meta.yml
+++ b/course_UvA-DL/03-initialization-and-optimization/.meta.yml
@@ -1,7 +1,7 @@
 title: "Tutorial 3: Initialization and Optimization"
 author: Phillip Lippe
 created: 2021-08-27
-updated: 2021-11-29
+updated: 2023-01-04
 license: CC BY-SA
 tags:
   - Image
diff --git a/course_UvA-DL/03-initialization-and-optimization/Initialization_and_Optimization.py b/course_UvA-DL/03-initialization-and-optimization/Initialization_and_Optimization.py
index fdf27edbc..b653153f1 100644
--- a/course_UvA-DL/03-initialization-and-optimization/Initialization_and_Optimization.py
+++ b/course_UvA-DL/03-initialization-and-optimization/Initialization_and_Optimization.py
@@ -47,7 +47,7 @@
 pl.seed_everything(42)
 
 # Ensure that all operations are deterministic on GPU (if used) for reproducibility
-torch.backends.cudnn.determinstic = True
+torch.backends.cudnn.deterministic = True
 torch.backends.cudnn.benchmark = False
 
 # Fetching the device that will be used throughout this notebook
@@ -937,8 +937,8 @@ def pathological_curve_loss(w1, w2):
 def plot_curve(
     curve_fn, x_range=(-5, 5), y_range=(-5, 5), plot_3d=False, cmap=cm.viridis, title="Pathological curvature"
 ):
-    fig = plt.figure()
-    ax = fig.gca(projection="3d") if plot_3d else fig.gca()
+    _ = plt.figure()
+    ax = plt.axes(projection="3d") if plot_3d else plt.axes()
 
     x = torch.arange(x_range[0], x_range[1], (x_range[1] - x_range[0]) / 100.0)
     y = torch.arange(y_range[0], y_range[1], (y_range[1] - y_range[0]) / 100.0)
diff --git a/course_UvA-DL/04-inception-resnet-densenet/.meta.yaml b/course_UvA-DL/04-inception-resnet-densenet/.meta.yaml
index 6c5fc5a64..06c537aa1 100644
--- a/course_UvA-DL/04-inception-resnet-densenet/.meta.yaml
+++ b/course_UvA-DL/04-inception-resnet-densenet/.meta.yaml
@@ -1,7 +1,7 @@
 title: "Tutorial 4: Inception, ResNet and DenseNet"
 author: Phillip Lippe
 created: 2021-08-27
-updated: 2021-11-29
+updated: 2023-01-04
 license: CC BY-SA
 tags:
   - Image
@@ -18,5 +18,6 @@ requirements:
   - matplotlib
   - seaborn
   - tabulate
+  - pytorch-lightning>=1.8
 accelerator:
   - GPU
diff --git a/course_UvA-DL/04-inception-resnet-densenet/Inception_ResNet_DenseNet.py b/course_UvA-DL/04-inception-resnet-densenet/Inception_ResNet_DenseNet.py
index 5420a9dbe..8e1f76f21 100644
--- a/course_UvA-DL/04-inception-resnet-densenet/Inception_ResNet_DenseNet.py
+++ b/course_UvA-DL/04-inception-resnet-densenet/Inception_ResNet_DenseNet.py
@@ -49,7 +49,7 @@
 pl.seed_everything(42)
 
 # Ensure that all operations are deterministic on GPU (if used) for reproducibility
-torch.backends.cudnn.determinstic = True
+torch.backends.cudnn.deterministic = True
 torch.backends.cudnn.benchmark = False
 
 device = torch.device("cuda:0") if torch.cuda.is_available() else torch.device("cpu")
@@ -348,7 +348,8 @@ def train_model(model_name, save_name=None, **kwargs):
     trainer = pl.Trainer(
         default_root_dir=os.path.join(CHECKPOINT_PATH, save_name),  # Where to save models
         # We run on a single GPU (if possible)
-        gpus=1 if str(device) == "cuda:0" else 0,
+        accelerator="gpu" if str(device).startswith("cuda") else "cpu",
+        devices=1,
         # How many epochs to train for if no patience is set
         max_epochs=180,
         callbacks=[
@@ -357,7 +358,7 @@ def train_model(model_name, save_name=None, **kwargs):
             ),  # Save the best checkpoint based on the maximum val_acc recorded. Saves only weights and not optimizer
             LearningRateMonitor("epoch"),
         ],  # Log learning rate every epoch
-        progress_bar_refresh_rate=1,
+        enable_progress_bar=True,
     )  # In case your notebook crashes due to the progress bar, consider increasing the refresh rate
     trainer.logger._log_graph = True  # If True, we plot the computation graph in tensorboard
     trainer.logger._default_hp_metric = None  # Optional logging argument that we don't need
diff --git a/course_UvA-DL/05-transformers-and-MH-attention/.meta.yml b/course_UvA-DL/05-transformers-and-MH-attention/.meta.yml
index ffd3f88c1..80b75e295 100644
--- a/course_UvA-DL/05-transformers-and-MH-attention/.meta.yml
+++ b/course_UvA-DL/05-transformers-and-MH-attention/.meta.yml
@@ -1,7 +1,7 @@
 title: "Tutorial 5: Transformers and Multi-Head Attention"
 author: Phillip Lippe
 created: 2021-06-30
-updated: 2021-11-29
+updated: 2023-01-04
 license: CC BY-SA
 build: 0
 tags:
@@ -19,5 +19,6 @@ requirements:
   - torchvision
   - matplotlib
   - seaborn
+  - pytorch-lightning>=1.8
 accelerator:
   - GPU
diff --git a/course_UvA-DL/05-transformers-and-MH-attention/Transformers_MHAttention.py b/course_UvA-DL/05-transformers-and-MH-attention/Transformers_MHAttention.py
index cca56f2ee..6a184384f 100644
--- a/course_UvA-DL/05-transformers-and-MH-attention/Transformers_MHAttention.py
+++ b/course_UvA-DL/05-transformers-and-MH-attention/Transformers_MHAttention.py
@@ -61,7 +61,7 @@
 pl.seed_everything(42)
 
 # Ensure that all operations are deterministic on GPU (if used) for reproducibility
-torch.backends.cudnn.determinstic = True
+torch.backends.cudnn.deterministic = True
 torch.backends.cudnn.benchmark = False
 
 device = torch.device("cuda:0") if torch.cuda.is_available() else torch.device("cpu")
@@ -979,10 +979,11 @@ def train_reverse(**kwargs):
     trainer = pl.Trainer(
         default_root_dir=root_dir,
         callbacks=[ModelCheckpoint(save_weights_only=True, mode="max", monitor="val_acc")],
-        gpus=1 if str(device).startswith("cuda") else 0,
+        accelerator="gpu" if str(device).startswith("cuda") else "cpu",
+        devices=1,
         max_epochs=10,
         gradient_clip_val=5,
-        progress_bar_refresh_rate=1,
+        enable_progress_bar=True,
     )
     trainer.logger._default_hp_metric = None  # Optional logging argument that we don't need
 
@@ -1439,10 +1440,11 @@ def train_anomaly(**kwargs):
     trainer = pl.Trainer(
         default_root_dir=root_dir,
         callbacks=[ModelCheckpoint(save_weights_only=True, mode="max", monitor="val_acc")],
-        gpus=1 if str(device).startswith("cuda") else 0,
+        accelerator="gpu" if str(device).startswith("cuda") else "cpu",
+        devices=1,
         max_epochs=100,
         gradient_clip_val=2,
-        progress_bar_refresh_rate=1,
+        enable_progress_bar=True,
     )
     trainer.logger._default_hp_metric = None  # Optional logging argument that we don't need
 
diff --git a/course_UvA-DL/06-graph-neural-networks/.meta.yml b/course_UvA-DL/06-graph-neural-networks/.meta.yml
index 080e06fc7..fc1dc3c66 100644
--- a/course_UvA-DL/06-graph-neural-networks/.meta.yml
+++ b/course_UvA-DL/06-graph-neural-networks/.meta.yml
@@ -1,7 +1,7 @@
 title: "Tutorial 6: Basics of Graph Neural Networks"
 author: Phillip Lippe
 created: 2021-06-07
-updated: 2021-12-04
+updated: 2023-01-04
 license: CC BY-SA
 build: 0
 tags:
@@ -19,10 +19,11 @@ description: |
   The full list of tutorials can be found at https://uvadlc-notebooks.rtfd.io.
 requirements:
   - torch-scatter
-  - torch-sparse<0.6.13
+  - torch-sparse
   - torch-cluster
   - torch-spline-conv
-  - torch-geometric==2.0.2
+  - torch-geometric
+  - pytorch-lightning>=1.8
 pip__find-link:
   # - https://pytorch-geometric.com/whl/torch-1.8.0+cu101.html
   - https://pytorch-geometric.com/whl/torch-%(TORCH_MAJOR_DOT_MINOR)s.0+%(DEVICE)s.html
diff --git a/course_UvA-DL/06-graph-neural-networks/GNN_overview.py b/course_UvA-DL/06-graph-neural-networks/GNN_overview.py
index 2f0d7c487..4e8bc83e7 100644
--- a/course_UvA-DL/06-graph-neural-networks/GNN_overview.py
+++ b/course_UvA-DL/06-graph-neural-networks/GNN_overview.py
@@ -39,7 +39,7 @@
 pl.seed_everything(42)
 
 # Ensure that all operations are deterministic on GPU (if used) for reproducibility
-torch.backends.cudnn.determinstic = True
+torch.backends.cudnn.deterministic = True
 torch.backends.cudnn.benchmark = False
 
 # %% [markdown]
@@ -634,7 +634,7 @@ def test_step(self, batch, batch_idx):
 # Additionally to the Lightning module, we define a training function below.
 # As we have a single graph, we use a batch size of 1 for the data loader and share the same data loader for the train,
 # validation, and test set (the mask is picked inside the Lightning module).
-# Besides, we set the argument `progress_bar_refresh_rate` to zero as it usually shows the progress per epoch,
+# Besides, we set the argument `enable_progress_bar` to False as it usually shows the progress per epoch,
 # but an epoch only consists of a single step.
 # If you have downloaded the pre-trained models in the beginning of the tutorial, we load those instead of training from scratch.
 # Finally, we test the model and return the results.
@@ -651,9 +651,10 @@ def train_node_classifier(model_name, dataset, **model_kwargs):
     trainer = pl.Trainer(
         default_root_dir=root_dir,
         callbacks=[ModelCheckpoint(save_weights_only=True, mode="max", monitor="val_acc")],
-        gpus=AVAIL_GPUS,
+        accelerator="gpu" if AVAIL_GPUS > 0 else "cpu",
+        devices=max(1, AVAIL_GPUS),
         max_epochs=200,
-        progress_bar_refresh_rate=0,
+        enable_progress_bar=False,
     )  # 0 because epoch size is 1
     trainer.logger._default_hp_metric = None  # Optional logging argument that we don't need
 
@@ -932,9 +933,10 @@ def train_graph_classifier(model_name, **model_kwargs):
     trainer = pl.Trainer(
         default_root_dir=root_dir,
         callbacks=[ModelCheckpoint(save_weights_only=True, mode="max", monitor="val_acc")],
-        gpus=AVAIL_GPUS,
+        accelerator="gpu" if AVAIL_GPUS > 0 else "cpu",
+        devices=max(1, AVAIL_GPUS),
         max_epochs=500,
-        progress_bar_refresh_rate=0,
+        enable_progress_bar=False,
     )
     trainer.logger._default_hp_metric = None
 
diff --git a/course_UvA-DL/07-deep-energy-based-generative-models/.meta.yml b/course_UvA-DL/07-deep-energy-based-generative-models/.meta.yml
index a7f682590..ab105f312 100644
--- a/course_UvA-DL/07-deep-energy-based-generative-models/.meta.yml
+++ b/course_UvA-DL/07-deep-energy-based-generative-models/.meta.yml
@@ -1,7 +1,7 @@
 title: "Tutorial 7: Deep Energy-Based Generative Models"
 author: Phillip Lippe
 created: 2021-07-12
-updated: 2021-07-12
+updated: 2023-01-04
 license: CC BY-SA
 build: 0
 tags:
@@ -22,6 +22,7 @@ requirements:
   - torchvision
   - matplotlib
   - tensorboard
+  - pytorch-lightning>=1.8
 accelerator:
   - CPU
   - GPU
diff --git a/course_UvA-DL/07-deep-energy-based-generative-models/Deep_Energy_Models.py b/course_UvA-DL/07-deep-energy-based-generative-models/Deep_Energy_Models.py
index 2d29e6dfb..a43a468cd 100644
--- a/course_UvA-DL/07-deep-energy-based-generative-models/Deep_Energy_Models.py
+++ b/course_UvA-DL/07-deep-energy-based-generative-models/Deep_Energy_Models.py
@@ -44,7 +44,7 @@
 pl.seed_everything(42)
 
 # Ensure that all operations are deterministic on GPU (if used) for reproducibility
-torch.backends.cudnn.determinstic = True
+torch.backends.cudnn.deterministic = True
 torch.backends.cudnn.benchmark = False
 
 device = torch.device("cuda:0") if torch.cuda.is_available() else torch.device("cpu")
@@ -640,7 +640,8 @@ def train_model(**kwargs):
     # Create a PyTorch Lightning trainer with the generation callback
     trainer = pl.Trainer(
         default_root_dir=os.path.join(CHECKPOINT_PATH, "MNIST"),
-        gpus=1 if str(device).startswith("cuda") else 0,
+        accelerator="gpu" if str(device).startswith("cuda") else "cpu",
+        devices=1,
         max_epochs=60,
         gradient_clip_val=0.1,
         callbacks=[
@@ -650,7 +651,7 @@ def train_model(**kwargs):
             OutlierCallback(),
             LearningRateMonitor("epoch"),
         ],
-        progress_bar_refresh_rate=1,
+        enable_progress_bar=True,
     )
     # Check whether pretrained model exists. If yes, load it and skip training
     pretrained_filename = os.path.join(CHECKPOINT_PATH, "MNIST.ckpt")
diff --git a/course_UvA-DL/08-deep-autoencoders/.meta.yml b/course_UvA-DL/08-deep-autoencoders/.meta.yml
index f6029b206..ca54ef5a0 100644
--- a/course_UvA-DL/08-deep-autoencoders/.meta.yml
+++ b/course_UvA-DL/08-deep-autoencoders/.meta.yml
@@ -1,7 +1,7 @@
 title: "Tutorial 8: Deep Autoencoders"
 author: Phillip Lippe
 created: 2021-07-12
-updated: 2021-07-12
+updated: 2023-01-04
 license: CC BY-SA
 build: 0
 tags:
@@ -22,6 +22,7 @@ requirements:
   - torchvision
   - matplotlib
   - seaborn
+  - pytorch-lightning>=1.8
 accelerator:
   - CPU
   - GPU
diff --git a/course_UvA-DL/08-deep-autoencoders/Deep_Autoencoders.py b/course_UvA-DL/08-deep-autoencoders/Deep_Autoencoders.py
index 8a1bf840b..cbe9b9653 100644
--- a/course_UvA-DL/08-deep-autoencoders/Deep_Autoencoders.py
+++ b/course_UvA-DL/08-deep-autoencoders/Deep_Autoencoders.py
@@ -41,7 +41,7 @@
 pl.seed_everything(42)
 
 # Ensure that all operations are deterministic on GPU (if used) for reproducibility
-torch.backends.cudnn.determinstic = True
+torch.backends.cudnn.deterministic = True
 torch.backends.cudnn.benchmark = False
 
 device = torch.device("cuda:0") if torch.cuda.is_available() else torch.device("cpu")
@@ -385,7 +385,8 @@ def train_cifar(latent_dim):
     # Create a PyTorch Lightning trainer with the generation callback
     trainer = pl.Trainer(
         default_root_dir=os.path.join(CHECKPOINT_PATH, "cifar10_%i" % latent_dim),
-        gpus=1 if str(device).startswith("cuda") else 0,
+        accelerator="gpu" if str(device).startswith("cuda") else "cpu",
+        devices=1,
         max_epochs=500,
         callbacks=[
             ModelCheckpoint(save_weights_only=True),
diff --git a/course_UvA-DL/09-normalizing-flows/.meta.yml b/course_UvA-DL/09-normalizing-flows/.meta.yml
index ffa0437d0..cf386b0e6 100644
--- a/course_UvA-DL/09-normalizing-flows/.meta.yml
+++ b/course_UvA-DL/09-normalizing-flows/.meta.yml
@@ -1,7 +1,7 @@
 title: "Tutorial 9: Normalizing Flows for Image Modeling"
 author: Phillip Lippe
 created: 2021-06-07
-updated: 2021-06-16
+updated: 2023-01-04
 license: CC BY-SA
 build: 0
 tags:
@@ -25,6 +25,7 @@ requirements:
   - matplotlib
   - seaborn
   - tabulate
+  - pytorch-lightning>=1.8
 accelerator:
   - CPU
   - GPU
diff --git a/course_UvA-DL/09-normalizing-flows/NF_image_modeling.py b/course_UvA-DL/09-normalizing-flows/NF_image_modeling.py
index 253149d1b..860f25271 100644
--- a/course_UvA-DL/09-normalizing-flows/NF_image_modeling.py
+++ b/course_UvA-DL/09-normalizing-flows/NF_image_modeling.py
@@ -44,7 +44,7 @@
 pl.seed_everything(42)
 
 # Ensure that all operations are deterministic on GPU (if used) for reproducibility
-torch.backends.cudnn.determinstic = True
+torch.backends.cudnn.deterministic = True
 torch.backends.cudnn.benchmark = False
 
 # Fetching the device that will be used throughout this notebook
@@ -490,7 +490,7 @@ def visualize_dequantization(quants, prior=None):
     # Prior over discrete values. If not given, a uniform is assumed
     if prior is None:
         prior = np.ones(quants, dtype=np.float32) / quants
-    prior = prior / prior.sum() * quants  # In the following, we assume 1 for each value means uniform distribution
+    prior = prior / prior.sum()  # Ensure proper categorical distribution
 
     inp = torch.arange(-4, 4, 0.01).view(-1, 1, 1, 1)  # Possible continuous values we want to consider
     ldj = torch.zeros(inp.shape[0])
@@ -798,21 +798,24 @@ def forward(self, x):
 
 
 class LayerNormChannels(nn.Module):
-    def __init__(self, c_in):
-        """This module applies layer norm across channels in an image.
-
-        Has been shown to work well with ResNet connections.
-        Args:
-            c_in: Number of channels of the input
+    def __init__(self, c_in, eps=1e-5):
+        """
+        This module applies layer norm across channels in an image.
+        Inputs:
+            c_in - Number of channels of the input
+            eps - Small constant to stabilize std
         """
         super().__init__()
-        self.layer_norm = nn.LayerNorm(c_in)
+        self.gamma = nn.Parameter(torch.ones(1, c_in, 1, 1))
+        self.beta = nn.Parameter(torch.zeros(1, c_in, 1, 1))
+        self.eps = eps
 
     def forward(self, x):
-        x = x.permute(0, 2, 3, 1)
-        x = self.layer_norm(x)
-        x = x.permute(0, 3, 1, 2)
-        return x
+        mean = x.mean(dim=1, keepdim=True)
+        var = x.var(dim=1, unbiased=False, keepdim=True)
+        y = (x - mean) / torch.sqrt(var + self.eps)
+        y = y * self.gamma + self.beta
+        return y
 
 
 class GatedConv(nn.Module):
@@ -825,7 +828,8 @@ def __init__(self, c_in, c_hidden):
         """
         super().__init__()
         self.net = nn.Sequential(
-            nn.Conv2d(c_in, c_hidden, kernel_size=3, padding=1),
+            ConcatELU(),
+            nn.Conv2d(2 * c_in, c_hidden, kernel_size=3, padding=1),
             ConcatELU(),
             nn.Conv2d(2 * c_hidden, 2 * c_in, kernel_size=1),
         )
@@ -918,7 +922,8 @@ def train_flow(flow, model_name="MNISTFlow"):
     # Create a PyTorch Lightning trainer
     trainer = pl.Trainer(
         default_root_dir=os.path.join(CHECKPOINT_PATH, model_name),
-        gpus=1 if torch.cuda.is_available() else 0,
+        accelerator="gpu" if str(device).startswith("cuda") else "cpu",
+        devices=1,
         max_epochs=200,
         gradient_clip_val=1.0,
         callbacks=[
diff --git a/course_UvA-DL/11-vision-transformer/.meta.yml b/course_UvA-DL/11-vision-transformer/.meta.yml
index 22fdd1323..9be56a10e 100644
--- a/course_UvA-DL/11-vision-transformer/.meta.yml
+++ b/course_UvA-DL/11-vision-transformer/.meta.yml
@@ -1,7 +1,7 @@
 title: "Tutorial 11: Vision Transformers"
 author: Phillip Lippe
 created: 2021-08-21
-updated: 2021-08-21
+updated: 2023-01-04
 license: CC BY-SA
 description: |
   In this tutorial, we will take a closer look at a recent new trend: Transformers for Computer Vision.
@@ -17,6 +17,7 @@ requirements:
   - torchvision
   - matplotlib
   - seaborn
+  - pytorch-lightning>=1.8
 accelerator:
   - CPU
   - GPU
diff --git a/course_UvA-DL/11-vision-transformer/Vision_Transformer.py b/course_UvA-DL/11-vision-transformer/Vision_Transformer.py
index 169cd9cc8..480115726 100644
--- a/course_UvA-DL/11-vision-transformer/Vision_Transformer.py
+++ b/course_UvA-DL/11-vision-transformer/Vision_Transformer.py
@@ -39,7 +39,7 @@
 pl.seed_everything(42)
 
 # Ensure that all operations are deterministic on GPU (if used) for reproducibility
-torch.backends.cudnn.determinstic = True
+torch.backends.cudnn.deterministic = True
 torch.backends.cudnn.benchmark = False
 
 device = torch.device("cuda:0") if torch.cuda.is_available() else torch.device("cpu")
@@ -378,13 +378,14 @@ def test_step(self, batch, batch_idx):
 def train_model(**kwargs):
     trainer = pl.Trainer(
         default_root_dir=os.path.join(CHECKPOINT_PATH, "ViT"),
-        gpus=1 if str(device) == "cuda:0" else 0,
+        accelerator="gpu" if str(device).startswith("cuda") else "cpu",
+        devices=1,
         max_epochs=180,
         callbacks=[
             ModelCheckpoint(save_weights_only=True, mode="max", monitor="val_acc"),
             LearningRateMonitor("epoch"),
         ],
-        progress_bar_refresh_rate=1,
+        enable_progress_bar=True,
     )
     trainer.logger._log_graph = True  # If True, we plot the computation graph in tensorboard
     trainer.logger._default_hp_metric = None  # Optional logging argument that we don't need
diff --git a/course_UvA-DL/12-meta-learning/.meta.yml b/course_UvA-DL/12-meta-learning/.meta.yml
index d5257ab16..7b640478f 100644
--- a/course_UvA-DL/12-meta-learning/.meta.yml
+++ b/course_UvA-DL/12-meta-learning/.meta.yml
@@ -1,7 +1,7 @@
 title: "Tutorial 12: Meta-Learning - Learning to Learn"
 author: Phillip Lippe
 created: 2021-08-21
-updated: 2021-08-21
+updated: 2023-01-04
 license: CC BY-SA
 tags:
   - Few-shot-learning
@@ -23,6 +23,7 @@ requirements:
   - torchvision
   - matplotlib
   - seaborn
+  - pytorch-lightning>=1.8
 accelerator:
   - CPU
   - GPU
diff --git a/course_UvA-DL/12-meta-learning/Meta_Learning.py b/course_UvA-DL/12-meta-learning/Meta_Learning.py
index 1ec243525..0cc1273f5 100644
--- a/course_UvA-DL/12-meta-learning/Meta_Learning.py
+++ b/course_UvA-DL/12-meta-learning/Meta_Learning.py
@@ -60,7 +60,7 @@
 pl.seed_everything(42)
 
 # Ensure that all operations are deterministic on GPU (if used) for reproducibility
-torch.backends.cudnn.determinstic = True
+torch.backends.cudnn.deterministic = True
 torch.backends.cudnn.benchmark = False
 
 device = torch.device("cuda:0") if torch.cuda.is_available() else torch.device("cpu")
@@ -555,13 +555,14 @@ def validation_step(self, batch, batch_idx):
 def train_model(model_class, train_loader, val_loader, **kwargs):
     trainer = pl.Trainer(
         default_root_dir=os.path.join(CHECKPOINT_PATH, model_class.__name__),
-        gpus=1 if str(device) == "cuda:0" else 0,
+        accelerator="gpu" if str(device).startswith("cuda") else "cpu",
+        devices=1,
         max_epochs=200,
         callbacks=[
             ModelCheckpoint(save_weights_only=True, mode="max", monitor="val_acc"),
             LearningRateMonitor("epoch"),
         ],
-        progress_bar_refresh_rate=0,
+        enable_progress_bar=False,
     )
     trainer.logger._default_hp_metric = None