diff --git a/datasets/doc/source/how-to-use-with-pytorch.rst b/datasets/doc/source/how-to-use-with-pytorch.rst
index 613f00a9a059..4228ead2a281 100644
--- a/datasets/doc/source/how-to-use-with-pytorch.rst
+++ b/datasets/doc/source/how-to-use-with-pytorch.rst
@@ -63,7 +63,7 @@ expected by a model with a convolutional layer.
 
 If you want to divide the dataset, you can use (at any point before passing the dataset to the DataLoader)::
 
-  partition_train_test = partition.train_test_split(test_size=0.2)
+  partition_train_test = partition.train_test_split(test_size=0.2, seed=42)
   partition_train = partition_train_test["train"]
   partition_test = partition_train_test["test"]
 
diff --git a/datasets/e2e/pytorch/pytorch_test.py b/datasets/e2e/pytorch/pytorch_test.py
index 5bac8f770f23..1f5e4cbb3ad1 100644
--- a/datasets/e2e/pytorch/pytorch_test.py
+++ b/datasets/e2e/pytorch/pytorch_test.py
@@ -65,7 +65,7 @@ def _create_trainloader(self, batch_size: int) -> DataLoader:
         partition_id = 0
         fds = FederatedDataset(dataset=self.dataset_name, partitioners={"train": 100})
         partition = fds.load_partition(partition_id, "train")
-        partition_train_test = partition.train_test_split(test_size=0.2)
+        partition_train_test = partition.train_test_split(test_size=0.2, seed=42)
         partition_train_test = partition_train_test.map(
             lambda img: {"img": self.transforms(img)}, input_columns="img"
         )
diff --git a/datasets/e2e/scikit-learn/sklearn_test.py b/datasets/e2e/scikit-learn/sklearn_test.py
index e5e6d347ee37..7ce4659b6cd8 100644
--- a/datasets/e2e/scikit-learn/sklearn_test.py
+++ b/datasets/e2e/scikit-learn/sklearn_test.py
@@ -29,7 +29,7 @@ def _get_partition_data(self):
         fds = FederatedDataset(dataset=self.dataset_name, partitioners={"train": 10})
         partition = fds.load_partition(partition_id, "train")
         partition.set_format("numpy")
-        partition_train_test = partition.train_test_split(test_size=0.2)
+        partition_train_test = partition.train_test_split(test_size=0.2, seed=42)
         X_train, y_train = partition_train_test["train"]["image"], partition_train_test[
             "train"]["label"]
         X_test, y_test = partition_train_test["test"]["image"], partition_train_test[
diff --git a/dev/update-examples.sh b/dev/update-examples.sh
index c802e21503b7..07cb90932875 100755
--- a/dev/update-examples.sh
+++ b/dev/update-examples.sh
@@ -16,20 +16,47 @@ echo "---" >> $INDEX
 echo "maxdepth: 1" >> $INDEX
 echo "---" >> $INDEX
 
-rm -f "examples/doc/source/*.md"
+rm -f examples/doc/source/*.md
 
 cd examples/
 for d in $(printf '%s\n' */ | sort -V); do
   example=${d%/}
-  # For each example, copy the README into the source of the Example docs
-  [[ $example != doc ]] && cp $example/README.md $ROOT/examples/doc/source/$example.md 2>&1 >/dev/null
-  # For each example, copy all images of the _static folder into the examples
-  # docs static folder
-  [[ $example != doc ]] && [ -d "$example/_static" ] && {
-    cp $example/_static/**.{jpg,png,jpeg} $ROOT/examples/doc/source/_static/ 2>/dev/null || true
-  }
-  # For each example, insert the name of the example into the index file
-  [[ $example != doc ]] && (echo $INSERT_LINE; echo a; echo $example; echo .; echo wq) | ed $INDEX 2>&1 >/dev/null
+
+  if [[ $example != doc ]]; then
+
+    for file in $example/*.md; do
+      # For each example, copy the README into the source of the Example docs
+      if [[ $(basename "$file") = "README.md" ]]; then
+        cp $file $ROOT/examples/doc/source/$example.md 2>&1 >/dev/null
+      else
+        # If the example contains other markdown files, copy them to the source of the Example docs
+        cp $file $ROOT/examples/doc/source/$(basename "$file") 2>&1 >/dev/null
+      fi
+    done
+
+    gh_text="[<img src=\"_static/view-gh.png\" alt=\"View on GitHub\" width=\"200\"/>](https://github.com/adap/flower/blob/main/examples/$example)"
+    readme_file="$ROOT/examples/doc/source/$example.md"
+
+    if ! grep -Fq "$gh_text" "$readme_file"; then
+      awk -v text="$gh_text" '
+      /^# / && !found {
+        print $0 "\n" text;
+        found=1;
+        next;
+      }
+      { print }
+      ' "$readme_file" > tmpfile && mv tmpfile "$readme_file"
+    fi
+    
+    # For each example, copy all images of the _static folder into the examples
+    # docs static folder
+    [ -d "$example/_static" ] && {
+      cp $example/_static/**.{jpg,png,jpeg} $ROOT/examples/doc/source/_static/ 2>/dev/null || true
+    }
+    # For each example, insert the name of the example into the index file
+    (echo $INSERT_LINE; echo a; echo $example; echo .; echo wq) | ed $INDEX 2>&1 >/dev/null
+
+  fi
 done
 
 echo "\`\`\`" >> $INDEX
diff --git a/doc/source/tutorial-series-get-started-with-flower-pytorch.ipynb b/doc/source/tutorial-series-get-started-with-flower-pytorch.ipynb
index 2b8dd382bb79..6f3d24286c99 100644
--- a/doc/source/tutorial-series-get-started-with-flower-pytorch.ipynb
+++ b/doc/source/tutorial-series-get-started-with-flower-pytorch.ipynb
@@ -145,7 +145,7 @@
     "    for partition_id in range(NUM_CLIENTS):\n",
     "        partition = fds.load_partition(partition_id, \"train\")\n",
     "        partition = partition.with_transform(apply_transforms)\n",
-    "        partition = partition.train_test_split(train_size=0.8)\n",
+    "        partition = partition.train_test_split(train_size=0.8, seed=42)\n",
     "        trainloaders.append(DataLoader(partition[\"train\"], batch_size=BATCH_SIZE))\n",
     "        valloaders.append(DataLoader(partition[\"test\"], batch_size=BATCH_SIZE))\n",
     "    testset = fds.load_split(\"test\").with_transform(apply_transforms)\n",
diff --git a/examples/advanced-pytorch/client.py b/examples/advanced-pytorch/client.py
index d4c8abe3d404..7c1420a2cecd 100644
--- a/examples/advanced-pytorch/client.py
+++ b/examples/advanced-pytorch/client.py
@@ -46,7 +46,7 @@ def fit(self, parameters, config):
         batch_size: int = config["batch_size"]
         epochs: int = config["local_epochs"]
 
-        train_valid = self.trainset.train_test_split(self.validation_split)
+        train_valid = self.trainset.train_test_split(self.validation_split, seed=42)
         trainset = train_valid["train"]
         valset = train_valid["test"]
 
diff --git a/examples/advanced-pytorch/utils.py b/examples/advanced-pytorch/utils.py
index fd9dab19a70d..c47b4fa38593 100644
--- a/examples/advanced-pytorch/utils.py
+++ b/examples/advanced-pytorch/utils.py
@@ -14,7 +14,7 @@ def load_partition(partition_id, toy: bool = False):
     fds = FederatedDataset(dataset="cifar10", partitioners={"train": 10})
     partition = fds.load_partition(partition_id)
     # Divide data on each node: 80% train, 20% test
-    partition_train_test = partition.train_test_split(test_size=0.2)
+    partition_train_test = partition.train_test_split(test_size=0.2, seed=42)
     partition_train_test = partition_train_test.with_transform(apply_transforms)
     return partition_train_test["train"], partition_train_test["test"]
 
diff --git a/examples/advanced-tensorflow/client.py b/examples/advanced-tensorflow/client.py
index 17d1d2306270..b658a1f9ea04 100644
--- a/examples/advanced-tensorflow/client.py
+++ b/examples/advanced-tensorflow/client.py
@@ -123,7 +123,7 @@ def load_partition(idx: int):
     partition.set_format("numpy")
 
     # Divide data on each node: 80% train, 20% test
-    partition = partition.train_test_split(test_size=0.2)
+    partition = partition.train_test_split(test_size=0.2, seed=42)
     x_train, y_train = partition["train"]["img"] / 255.0, partition["train"]["label"]
     x_test, y_test = partition["test"]["img"] / 255.0, partition["test"]["label"]
     return x_train, y_train, x_test, y_test
diff --git a/examples/app-pytorch/client.py b/examples/app-pytorch/client.py
index ebbe977ecab1..eb84968bb986 100644
--- a/examples/app-pytorch/client.py
+++ b/examples/app-pytorch/client.py
@@ -18,7 +18,6 @@
 
 # Define FlowerClient and client_fn
 class FlowerClient(NumPyClient):
-
     def fit(self, parameters, config):
         set_weights(net, parameters)
         results = train(net, trainloader, testloader, epochs=1, device=DEVICE)
diff --git a/examples/custom-mods/README.md b/examples/custom-mods/README.md
index b0ad668c2dec..6b03abcfbfe0 100644
--- a/examples/custom-mods/README.md
+++ b/examples/custom-mods/README.md
@@ -288,7 +288,7 @@ $ tree .
 pip install -r requirements.txt
 ```
 
-For [W&B](wandb.ai) you will also need a valid account.
+For [W&B](https://wandb.ai) you will also need a valid account.
 
 ### Start the long-running Flower server (SuperLink)
 
@@ -328,7 +328,7 @@ flower-server-app server:app --insecure
 
 ### Check the results
 
-For W&B, you will need to login to the [website](wandb.ai).
+For W&B, you will need to login to the [website](https://wandb.ai).
 
 For TensorBoard, you will need to run the following command in your terminal:
 
diff --git a/examples/custom-mods/client.py b/examples/custom-mods/client.py
index 2b87a24da19d..614daef6bcf6 100644
--- a/examples/custom-mods/client.py
+++ b/examples/custom-mods/client.py
@@ -86,7 +86,6 @@ def wandb_mod(msg: Message, context: Context, app: ClientAppCallable) -> Message
 
         # if the `ClientApp` just processed a "fit" message, let's log some metrics to W&B
         if reply.metadata.message_type == MessageType.TRAIN and reply.has_content():
-
             metrics = reply.content.configs_records
 
             results_to_log = dict(metrics.get("fitres.metrics", ConfigsRecord()))
diff --git a/examples/doc/source/_static/.gitignore b/examples/doc/source/_static/.gitignore
index c2412a5912cc..887023baf484 100644
--- a/examples/doc/source/_static/.gitignore
+++ b/examples/doc/source/_static/.gitignore
@@ -3,3 +3,4 @@
 !favicon.ico
 !flower-logo.png
 !tmux_jtop_view.gif
+!view-gh.png
diff --git a/examples/doc/source/_static/view-gh.png b/examples/doc/source/_static/view-gh.png
new file mode 100644
index 000000000000..afc3f07bc2d5
Binary files /dev/null and b/examples/doc/source/_static/view-gh.png differ
diff --git a/examples/embedded-devices/client_pytorch.py b/examples/embedded-devices/client_pytorch.py
index 6bd69c16567e..411052bfb1ea 100644
--- a/examples/embedded-devices/client_pytorch.py
+++ b/examples/embedded-devices/client_pytorch.py
@@ -108,7 +108,7 @@ def apply_transforms(batch):
     for partition_id in range(NUM_CLIENTS):
         partition = fds.load_partition(partition_id, "train")
         # Divide data on each node: 90% train, 10% test
-        partition = partition.train_test_split(test_size=0.1)
+        partition = partition.train_test_split(test_size=0.1, seed=42)
         partition = partition.with_transform(apply_transforms)
         trainsets.append(partition["train"])
         validsets.append(partition["test"])
diff --git a/examples/embedded-devices/client_tf.py b/examples/embedded-devices/client_tf.py
index 49c63ce5d9dc..3df75f76312b 100644
--- a/examples/embedded-devices/client_tf.py
+++ b/examples/embedded-devices/client_tf.py
@@ -44,7 +44,7 @@ def prepare_dataset(use_mnist: bool):
         partition = fds.load_partition(partition_id, "train")
         partition.set_format("numpy")
         # Divide data on each node: 90% train, 10% test
-        partition = partition.train_test_split(test_size=0.1)
+        partition = partition.train_test_split(test_size=0.1, seed=42)
         x_train, y_train = (
             partition["train"][img_key] / 255.0,
             partition["train"]["label"],
diff --git a/examples/fl-dp-sa/fl_dp_sa/task.py b/examples/fl-dp-sa/fl_dp_sa/task.py
index 3d506263d5a3..64ba10f20376 100644
--- a/examples/fl-dp-sa/fl_dp_sa/task.py
+++ b/examples/fl-dp-sa/fl_dp_sa/task.py
@@ -42,7 +42,7 @@ def load_data(partition_id):
     fds = FederatedDataset(dataset="mnist", partitioners={"train": 100})
     partition = fds.load_partition(partition_id)
     # Divide data on each node: 80% train, 20% test
-    partition_train_test = partition.train_test_split(test_size=0.2)
+    partition_train_test = partition.train_test_split(test_size=0.2, seed=42)
     pytorch_transforms = Compose([ToTensor(), Normalize((0.5,), (0.5,))])
 
     def apply_transforms(batch):
diff --git a/examples/flower-via-docker-compose/helpers/load_data.py b/examples/flower-via-docker-compose/helpers/load_data.py
index 1f2784946868..b7d6b0de26c5 100644
--- a/examples/flower-via-docker-compose/helpers/load_data.py
+++ b/examples/flower-via-docker-compose/helpers/load_data.py
@@ -25,7 +25,7 @@ def load_data(data_sampling_percentage=0.5, client_id=1, total_clients=2):
     partition.set_format("numpy")
 
     # Divide data on each client: 80% train, 20% test
-    partition = partition.train_test_split(test_size=0.2)
+    partition = partition.train_test_split(test_size=0.2, seed=42)
     x_train, y_train = partition["train"]["img"] / 255.0, partition["train"]["label"]
     x_test, y_test = partition["test"]["img"] / 255.0, partition["test"]["label"]
 
diff --git a/examples/pytorch-from-centralized-to-federated/cifar.py b/examples/pytorch-from-centralized-to-federated/cifar.py
index 277a21da2e70..c592b63b0042 100644
--- a/examples/pytorch-from-centralized-to-federated/cifar.py
+++ b/examples/pytorch-from-centralized-to-federated/cifar.py
@@ -56,7 +56,7 @@ def load_data(partition_id: int):
     fds = FederatedDataset(dataset="cifar10", partitioners={"train": 10})
     partition = fds.load_partition(partition_id)
     # Divide data on each node: 80% train, 20% test
-    partition_train_test = partition.train_test_split(test_size=0.2)
+    partition_train_test = partition.train_test_split(test_size=0.2, seed=42)
     pytorch_transforms = Compose(
         [ToTensor(), Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))]
     )
diff --git a/examples/quickstart-huggingface/client.py b/examples/quickstart-huggingface/client.py
index 9be08d0cbcf4..db8bf51d36da 100644
--- a/examples/quickstart-huggingface/client.py
+++ b/examples/quickstart-huggingface/client.py
@@ -22,7 +22,7 @@ def load_data(partition_id):
     fds = FederatedDataset(dataset="imdb", partitioners={"train": 1_000})
     partition = fds.load_partition(partition_id)
     # Divide data: 80% train, 20% test
-    partition_train_test = partition.train_test_split(test_size=0.2)
+    partition_train_test = partition.train_test_split(test_size=0.2, seed=42)
 
     tokenizer = AutoTokenizer.from_pretrained(CHECKPOINT)
 
diff --git a/examples/quickstart-mlcube/dev/mnist.py b/examples/quickstart-mlcube/dev/mnist.py
index e52e2cba85c7..55fb8fae62a7 100644
--- a/examples/quickstart-mlcube/dev/mnist.py
+++ b/examples/quickstart-mlcube/dev/mnist.py
@@ -36,6 +36,7 @@ def create_directory(path: str) -> None:
 
 def download(task_args: List[str]) -> None:
     """Task: download.
+
     Input parameters:
         --data_dir
     """
@@ -81,6 +82,7 @@ def download(task_args: List[str]) -> None:
 
 def train(task_args: List[str]) -> None:
     """Task: train.
+
     Input parameters:
         --data_dir, --log_dir, --model_dir, --parameters_file
     """
@@ -175,6 +177,7 @@ def train(task_args: List[str]) -> None:
 
 def evaluate(task_args: List[str]) -> None:
     """Task: train.
+
     Input parameters:
         --data_dir, --log_dir, --model_dir, --parameters_file
     """
diff --git a/examples/quickstart-mlx/client.py b/examples/quickstart-mlx/client.py
index faba2b94d6bd..344cfc65e42d 100644
--- a/examples/quickstart-mlx/client.py
+++ b/examples/quickstart-mlx/client.py
@@ -107,7 +107,7 @@ def evaluate(self, parameters, config):
 
     fds = FederatedDataset(dataset="mnist", partitioners={"train": 3})
     partition = fds.load_partition(partition_id=args.partition_id)
-    partition_splits = partition.train_test_split(test_size=0.2)
+    partition_splits = partition.train_test_split(test_size=0.2, seed=42)
 
     partition_splits["train"].set_format("numpy")
     partition_splits["test"].set_format("numpy")
diff --git a/examples/quickstart-pytorch-lightning/mnist.py b/examples/quickstart-pytorch-lightning/mnist.py
index 95342f4fb9b3..2f6100fe94cc 100644
--- a/examples/quickstart-pytorch-lightning/mnist.py
+++ b/examples/quickstart-pytorch-lightning/mnist.py
@@ -82,9 +82,11 @@ def load_data(partition):
 
     partition = partition.with_transform(apply_transforms)
     # 20 % for on federated evaluation
-    partition_full = partition.train_test_split(test_size=0.2)
+    partition_full = partition.train_test_split(test_size=0.2, seed=42)
     # 60 % for the federated train and 20 % for the federated validation (both in fit)
-    partition_train_valid = partition_full["train"].train_test_split(train_size=0.75)
+    partition_train_valid = partition_full["train"].train_test_split(
+        train_size=0.75, seed=42
+    )
     trainloader = DataLoader(
         partition_train_valid["train"],
         batch_size=32,
diff --git a/examples/quickstart-pytorch/client.py b/examples/quickstart-pytorch/client.py
index e58dbf7ea0bc..be4be88b8f8d 100644
--- a/examples/quickstart-pytorch/client.py
+++ b/examples/quickstart-pytorch/client.py
@@ -74,7 +74,7 @@ def load_data(partition_id):
     fds = FederatedDataset(dataset="cifar10", partitioners={"train": 3})
     partition = fds.load_partition(partition_id)
     # Divide data on each node: 80% train, 20% test
-    partition_train_test = partition.train_test_split(test_size=0.2)
+    partition_train_test = partition.train_test_split(test_size=0.2, seed=42)
     pytorch_transforms = Compose(
         [ToTensor(), Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))]
     )
diff --git a/examples/quickstart-tensorflow/client.py b/examples/quickstart-tensorflow/client.py
index 6ef11898f0b0..a906e9865d3b 100644
--- a/examples/quickstart-tensorflow/client.py
+++ b/examples/quickstart-tensorflow/client.py
@@ -30,7 +30,7 @@
 partition.set_format("numpy")
 
 # Divide data on each node: 80% train, 20% test
-partition = partition.train_test_split(test_size=0.2)
+partition = partition.train_test_split(test_size=0.2, seed=42)
 x_train, y_train = partition["train"]["img"] / 255.0, partition["train"]["label"]
 x_test, y_test = partition["test"]["img"] / 255.0, partition["test"]["label"]
 
diff --git a/examples/simulation-pytorch/sim.ipynb b/examples/simulation-pytorch/sim.ipynb
index 6dda1ef9319d..d225069cb444 100644
--- a/examples/simulation-pytorch/sim.ipynb
+++ b/examples/simulation-pytorch/sim.ipynb
@@ -497,7 +497,7 @@
     "        client_dataset = dataset.load_partition(int(cid), \"train\")\n",
     "\n",
     "        # Now let's split it into train (90%) and validation (10%)\n",
-    "        client_dataset_splits = client_dataset.train_test_split(test_size=0.1)\n",
+    "        client_dataset_splits = client_dataset.train_test_split(test_size=0.1, seed=42)\n",
     "\n",
     "        trainset = client_dataset_splits[\"train\"]\n",
     "        valset = client_dataset_splits[\"test\"]\n",
diff --git a/examples/simulation-pytorch/sim.py b/examples/simulation-pytorch/sim.py
index 6fb750f2e59c..db68e75653fc 100644
--- a/examples/simulation-pytorch/sim.py
+++ b/examples/simulation-pytorch/sim.py
@@ -94,7 +94,7 @@ def client_fn(cid: str) -> fl.client.Client:
         client_dataset = dataset.load_partition(int(cid), "train")
 
         # Now let's split it into train (90%) and validation (10%)
-        client_dataset_splits = client_dataset.train_test_split(test_size=0.1)
+        client_dataset_splits = client_dataset.train_test_split(test_size=0.1, seed=42)
 
         trainset = client_dataset_splits["train"]
         valset = client_dataset_splits["test"]
diff --git a/examples/simulation-tensorflow/sim.ipynb b/examples/simulation-tensorflow/sim.ipynb
index 797e2dcc603e..26b7260b5f1c 100644
--- a/examples/simulation-tensorflow/sim.ipynb
+++ b/examples/simulation-tensorflow/sim.ipynb
@@ -179,7 +179,7 @@
     "        client_dataset = dataset.load_partition(int(cid), \"train\")\n",
     "\n",
     "        # Now let's split it into train (90%) and validation (10%)\n",
-    "        client_dataset_splits = client_dataset.train_test_split(test_size=0.1)\n",
+    "        client_dataset_splits = client_dataset.train_test_split(test_size=0.1, seed=42)\n",
     "\n",
     "        trainset = client_dataset_splits[\"train\"].to_tf_dataset(\n",
     "            columns=\"image\", label_cols=\"label\", batch_size=32\n",
diff --git a/examples/simulation-tensorflow/sim.py b/examples/simulation-tensorflow/sim.py
index e94e5ec96850..4014e3c6be72 100644
--- a/examples/simulation-tensorflow/sim.py
+++ b/examples/simulation-tensorflow/sim.py
@@ -83,7 +83,7 @@ def client_fn(cid: str) -> fl.client.Client:
         client_dataset = dataset.load_partition(int(cid), "train")
 
         # Now let's split it into train (90%) and validation (10%)
-        client_dataset_splits = client_dataset.train_test_split(test_size=0.1)
+        client_dataset_splits = client_dataset.train_test_split(test_size=0.1, seed=42)
 
         trainset = client_dataset_splits["train"].to_tf_dataset(
             columns="image", label_cols="label", batch_size=32
diff --git a/examples/vertical-fl/README.md b/examples/vertical-fl/README.md
index 78588180d3d6..d8c599d617c4 100644
--- a/examples/vertical-fl/README.md
+++ b/examples/vertical-fl/README.md
@@ -123,7 +123,7 @@ In `task.py`, you'll find the preprocessing functions we'll apply to our data:
   'Adult' for ages between 11 and 40, and 'Elderly' for those over 40. If the age
   isn't listed, we'll label it as 'Unknown'.
 
-  ```python3
+  ```python
     def _bin_age(age_series):
         bins = [-np.inf, 10, 40, np.inf]
         labels = ["Child", "Adult", "Elderly"]
@@ -138,7 +138,7 @@ In `task.py`, you'll find the preprocessing functions we'll apply to our data:
   understand social status and family roles, simplifying rare titles into a single
   'Rare' category and converting any French titles to their English equivalents.
 
-  ```python3
+  ```python
     def _extract_title(name_series):
         titles = name_series.str.extract(" ([A-Za-z]+)\.", expand=False)
         rare_titles = {
@@ -170,7 +170,7 @@ In `task.py`, you'll find the preprocessing functions we'll apply to our data:
   'Pclass', 'Embarked', 'Title', 'Cabin', and the binned 'Age' into One-Hot
   encodings.
 
-  ```python3
+  ```python
     def _create_features(df):
         # Convert 'Age' to numeric, coercing errors to NaN
         df["Age"] = pd.to_numeric(df["Age"], errors="coerce")
@@ -190,7 +190,7 @@ In `task.py`, you'll find the preprocessing functions we'll apply to our data:
 In `task.py`, we also partition our data for our 3 clients to mirror real-life
 collaborations where different organizations hold different feature sets:
 
-```python3
+```python
 def _partition_data(df, all_keywords):
     partitions = []
     keywords_sets = [{"Parch", "Cabin", "Pclass"}, {"Sex", "Title"}]
@@ -236,7 +236,7 @@ collective intelligence without sharing sensitive information.
 
 Note that our final data processing function looks like that:
 
-```python3
+```python
 def get_partitions_and_label():
     df = pd.read_csv("_static/data/train.csv")
     processed_df = df.dropna(subset=["Embarked", "Fare"]).copy()
@@ -259,7 +259,7 @@ Each client's model is a neural network designed to operate on a distinct subset
 of features held by a client. In this example we will use simple linear
 regression models.
 
-```python3
+```python
 class ClientModel(nn.Module):
     def __init__(self, input_size):
         super(ClientModel, self).__init__()
@@ -281,7 +281,7 @@ The server's model acts as the central aggregator in the VFL system. It's also a
 neural network but with a slightly different architecture tailored to its role
 in aggregating the client models' outputs.
 
-```python3
+```python
 class ServerModel(nn.Module):
     def __init__(self):
         super(ServerModel, self).__init__()
@@ -305,7 +305,7 @@ a probability score indicative of the likelihood of survival.
 The strategy we will write to perform the aggregation will inherit from `FedAvg`
 and set the following additional attributes:
 
-```python3
+```python
 self.model = ServerModel(12)
 self.initial_parameters = ndarrays_to_parameters(
     [val.cpu().numpy() for _, val in self.model.state_dict().items()]
@@ -319,7 +319,7 @@ With `labels` given as an argument to the strategy.
 
 We then redefine the `aggregate_fit` method:
 
-```python3
+```python
 def aggregate_fit(
     self,
     rnd,
@@ -406,7 +406,7 @@ The last thing we have to do is to redefine the `aggregate_evaluate` function to
 disable distributed evaluation (as the clients do not hold any labels to test
 their local models).
 
-```python3
+```python
 def aggregate_evaluate(
     self,
     rnd,
@@ -420,7 +420,7 @@ def aggregate_evaluate(
 
 Our `FlowerClient` class is going to be quite straight forward.
 
-```python3
+```python
 class FlowerClient(fl.client.NumPyClient):
     def __init__(self, cid, data):
         self.cid = cid
@@ -487,7 +487,7 @@ the `aggregate_evaluate` function of the strategy.
 Putting everything together, to start our simulation we use the following
 function:
 
-```python3
+```python
 hist = fl.simulation.start_simulation(
     client_fn=client_fn,
     num_clients=3,
diff --git a/examples/vit-finetune/client.py b/examples/vit-finetune/client.py
index 68d98926feeb..bf91fa0c4328 100644
--- a/examples/vit-finetune/client.py
+++ b/examples/vit-finetune/client.py
@@ -8,9 +8,7 @@
 
 
 class FedViTClient(NumPyClient):
-
     def __init__(self, trainset):
-
         self.trainset = trainset
         self.model = get_model()
 
diff --git a/examples/vit-finetune/main.py b/examples/vit-finetune/main.py
index 1257246304a1..c629a6f68980 100644
--- a/examples/vit-finetune/main.py
+++ b/examples/vit-finetune/main.py
@@ -19,7 +19,6 @@
 
 
 def main():
-
     args = parser.parse_args()
 
     # To control the degree of parallelism
diff --git a/examples/whisper-federated-finetuning/utils.py b/examples/whisper-federated-finetuning/utils.py
index 21fe0309151c..117cf7100ddd 100644
--- a/examples/whisper-federated-finetuning/utils.py
+++ b/examples/whisper-federated-finetuning/utils.py
@@ -107,10 +107,10 @@ def prepare_silences_dataset(train_dataset, ratio_silence: float = 0.1) -> Datas
     """Generate silences for the train set.
 
     One of the classes in the SpeechCommands datatset is `silence`. However, the dataset
-    does not include clips of silence. It does however include 5 long files with different
-    background sounds. The taks of this function is to extract several (defined by `ratio_silence`)
-    one-second long clips from those background audio files. Later, those audio clips will be
-    included into the training set.
+    does not include clips of silence. It does however include 5 long files with
+    different background sounds. The taks of this function is to extract several
+    (defined by `ratio_silence`) one-second long clips from those background audio
+    files. Later, those audio clips will be included into the training set.
     """
     # retrieve original silence audio clips
     silences = [d for d in train_dataset if d["label"] == 35]
@@ -138,9 +138,9 @@ def prepare_silences_dataset(train_dataset, ratio_silence: float = 0.1) -> Datas
 def construct_client_mapping(full_trainset, num_clients: int = 100):
     """Create a mapping to partition the dataset into `num_client` buckets.
 
-    These buckets contain the same number of `spekaer_id` but likely different
-    number of training exampes since each `speaker_id` in SpeechCommands does
-    provide different amounts of data to the dataset.
+    These buckets contain the same number of `spekaer_id` but likely different number of
+    training exampes since each `speaker_id` in SpeechCommands does provide different
+    amounts of data to the dataset.
     """
     client_ids = list(set(full_trainset["speaker_id"]))
     client_ids.remove(
@@ -191,7 +191,7 @@ def set_params(model: torch.nn.ModuleList, params: List[fl.common.NDArrays]):
 
 
 def get_model(device, num_classes, compile: bool = True):
-    """Create model: Whisper-tiny Encoder + classification head"""
+    """Create model: Whisper-tiny Encoder + classification head."""
     encoder = WhisperForConditionalGeneration.from_pretrained(
         "openai/whisper-tiny"
     ).get_encoder()
diff --git a/src/py/flwr/cli/new/templates/app/code/task.pytorch.py.tpl b/src/py/flwr/cli/new/templates/app/code/task.pytorch.py.tpl
index 85460564b6ef..b30c65a285b5 100644
--- a/src/py/flwr/cli/new/templates/app/code/task.pytorch.py.tpl
+++ b/src/py/flwr/cli/new/templates/app/code/task.pytorch.py.tpl
@@ -39,7 +39,7 @@ def load_data(partition_id, num_partitions):
     fds = FederatedDataset(dataset="cifar10", partitioners={"train": num_partitions})
     partition = fds.load_partition(partition_id)
     # Divide data on each node: 80% train, 20% test
-    partition_train_test = partition.train_test_split(test_size=0.2)
+    partition_train_test = partition.train_test_split(test_size=0.2, seed=42)
     pytorch_transforms = Compose(
         [ToTensor(), Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))]
     )
diff --git a/src/py/flwr/client/app.py b/src/py/flwr/client/app.py
index 1720405ab867..4fa9c80c6cdf 100644
--- a/src/py/flwr/client/app.py
+++ b/src/py/flwr/client/app.py
@@ -456,12 +456,13 @@ def _load_client_app() -> ClientApp:
                     continue
 
                 log(INFO, "")
-                log(
-                    INFO,
-                    "[RUN %s, ROUND %s]",
-                    message.metadata.run_id,
-                    message.metadata.group_id,
-                )
+                if len(message.metadata.group_id) > 0:
+                    log(
+                        INFO,
+                        "[RUN %s, ROUND %s]",
+                        message.metadata.run_id,
+                        message.metadata.group_id,
+                    )
                 log(
                     INFO,
                     "Received: %s message %s",
diff --git a/src/py/flwr/common/retry_invoker.py b/src/py/flwr/common/retry_invoker.py
index 7cec319e7906..d12124b89840 100644
--- a/src/py/flwr/common/retry_invoker.py
+++ b/src/py/flwr/common/retry_invoker.py
@@ -261,6 +261,7 @@ def try_call_event_handler(
             try:
                 ret = target(*args, **kwargs)
             except self.recoverable_exceptions as err:
+                state.exception = err
                 # Check if giveup event should be triggered
                 max_tries_exceeded = try_cnt == self.max_tries
                 max_time_exceeded = (