diff --git a/nbs/common.base_auto.ipynb b/nbs/common.base_auto.ipynb
index c2626191d..e4b95be7a 100644
--- a/nbs/common.base_auto.ipynb
+++ b/nbs/common.base_auto.ipynb
@@ -529,12 +529,6 @@
    "outputs": [],
    "source": [
     "#| hide\n",
-    "\n",
-    "#| hide\n",
-    "import os\n",
-    "os.environ[\"PYTORCH_ENABLE_MPS_FALLBACK\"] = \"1\"\n",
-    "os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"0\"\n",
-    "\n",
     "import optuna\n",
     "import pandas as pd\n",
     "from neuralforecast.models.mlp import MLP\n",
@@ -647,7 +641,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "ea77450f",
+   "id": "463d4dc0-b25a-4ce6-9172-5690dc979f0b",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -657,8 +651,18 @@
     "from neuralforecast.models.mlp import MLP\n",
     "from neuralforecast.utils import AirPassengersDF as Y_df\n",
     "from neuralforecast.tsdataset import TimeSeriesDataset\n",
-    "from neuralforecast.losses.pytorch import MAE, MSE\n",
-    "\n",
+    "from neuralforecast.losses.pytorch import MAE, MSE"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "882c8331-440a-4758-a56c-07a78c0b1603",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#| hide\n",
+    "# Unit tests to guarantee that losses are correctly instantiated\n",
     "Y_train_df = Y_df[Y_df.ds<='1959-12-31'] # 132 train\n",
     "Y_test_df = Y_df[Y_df.ds>'1959-12-31']   # 12 test\n",
     "\n",
diff --git a/nbs/common.base_windows.ipynb b/nbs/common.base_windows.ipynb
index cab27b4df..0d8b4b3a2 100644
--- a/nbs/common.base_windows.ipynb
+++ b/nbs/common.base_windows.ipynb
@@ -817,16 +817,25 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "b2fd48a7",
+   "id": "8927f2e5-f376-4c99-bb8f-8cbb73efe01e",
    "metadata": {},
    "outputs": [],
    "source": [
     "#| hide\n",
-    "# add h=0,1 unit test for _parse_windows \n",
     "from neuralforecast.losses.pytorch import MAE\n",
     "from neuralforecast.utils import AirPassengersDF\n",
-    "from neuralforecast.tsdataset import TimeSeriesDataset, TimeSeriesDataModule\n",
-    "\n",
+    "from neuralforecast.tsdataset import TimeSeriesDataset, TimeSeriesDataModule"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "61490e69-f014-4087-83c5-540d5bd7d458",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#| hide\n",
+    "# add h=0,1 unit test for _parse_windows \n",
     "# Declare batch\n",
     "AirPassengersDF['x'] = np.array(len(AirPassengersDF))\n",
     "AirPassengersDF['x2'] = np.array(len(AirPassengersDF)) * 2\n",
diff --git a/nbs/common.scalers.ipynb b/nbs/common.scalers.ipynb
index 9d40327d2..dc177d735 100644
--- a/nbs/common.scalers.ipynb
+++ b/nbs/common.scalers.ipynb
@@ -40,19 +40,6 @@
     "![Figure 1. Illustration of temporal normalization (left), layer normalization (center) and batch normalization (right). The entries in green show the components used to compute the normalizing statistics.](imgs_models/temporal_norm.png)"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "f5400f41",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "#| hide\n",
-    "import os\n",
-    "os.environ[\"PYTORCH_ENABLE_MPS_FALLBACK\"] = \"1\"\n",
-    "os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"0\""
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": null,
diff --git a/nbs/core.ipynb b/nbs/core.ipynb
index 580e740b5..8fe799306 100644
--- a/nbs/core.ipynb
+++ b/nbs/core.ipynb
@@ -40,10 +40,6 @@
    "outputs": [],
    "source": [
     "#| hide\n",
-    "import os\n",
-    "os.environ[\"PYTORCH_ENABLE_MPS_FALLBACK\"] = \"1\"\n",
-    "os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"0\"\n",
-    "\n",
     "import shutil\n",
     "from fastcore.test import test_eq, test_fail\n",
     "from nbdev.showdoc import show_doc\n",
@@ -907,13 +903,23 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "8898e349-8000-4668-a1c5-52c03c69e85a",
+   "id": "5d6ef366-daec-4ec6-a2ae-199c6ea39a51",
    "metadata": {},
    "outputs": [],
    "source": [
     "#| hide\n",
     "import logging\n",
-    "import warnings\n",
+    "import warnings"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0ac1aa65-40a4-4909-bdfb-1439c30439b8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#| hide\n",
     "logging.getLogger(\"pytorch_lightning\").setLevel(logging.ERROR)\n",
     "warnings.filterwarnings(\"ignore\")"
    ]
diff --git a/nbs/examples/Neuralforecast_Map.ipynb b/nbs/examples/Neuralforecast_Map.ipynb
index c4482c319..efb83f54a 100644
--- a/nbs/examples/Neuralforecast_Map.ipynb
+++ b/nbs/examples/Neuralforecast_Map.ipynb
@@ -145,5 +145,5 @@
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }
diff --git a/nbs/losses.numpy.ipynb b/nbs/losses.numpy.ipynb
index 926292ab3..4622df90c 100644
--- a/nbs/losses.numpy.ipynb
+++ b/nbs/losses.numpy.ipynb
@@ -49,6 +49,7 @@
    "outputs": [],
    "source": [
     "#| hide\n",
+    "from IPython.display import Image\n",
     "from nbdev.showdoc import show_doc"
    ]
   },
@@ -59,7 +60,6 @@
    "outputs": [],
    "source": [
     "#| hide\n",
-    "from IPython.display import Image\n",
     "WIDTH = 600\n",
     "HEIGHT = 300"
    ]
diff --git a/nbs/models.hint.ipynb b/nbs/models.hint.ipynb
index af885136b..029046dfb 100644
--- a/nbs/models.hint.ipynb
+++ b/nbs/models.hint.ipynb
@@ -47,10 +47,6 @@
    "outputs": [],
    "source": [
     "#| hide\n",
-    "import os\n",
-    "os.environ[\"PYTORCH_ENABLE_MPS_FALLBACK\"] = \"1\"\n",
-    "os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"0\"\n",
-    "\n",
     "from nbdev.showdoc import show_doc\n",
     "from neuralforecast.losses.pytorch import GMM\n",
     "from neuralforecast import NeuralForecast\n",
diff --git a/nbs/models.ipynb b/nbs/models.ipynb
index 5bfca82cb..8cf4d228f 100644
--- a/nbs/models.ipynb
+++ b/nbs/models.ipynb
@@ -22,19 +22,6 @@
     "%autoreload 2"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "cd088010",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "#| hide\n",
-    "import os\n",
-    "os.environ[\"PYTORCH_ENABLE_MPS_FALLBACK\"] = \"1\"\n",
-    "os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"0\""
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -2222,7 +2209,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "fd3a085a",
+   "id": "db128f64-b311-479e-bf81-07c3bf9f1a5e",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2232,8 +2219,17 @@
     "import matplotlib.pyplot as plt\n",
     "\n",
     "from neuralforecast.tsdataset import TimeSeriesDataset\n",
-    "from neuralforecast.utils import AirPassengersDF as Y_df\n",
-    "\n",
+    "from neuralforecast.utils import AirPassengersDF as Y_df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1691fdcc-99e3-472b-ae26-03fb89847227",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#| hide\n",
     "# Split train/test and declare time series dataset\n",
     "Y_train_df = Y_df[Y_df.ds<='1959-12-31'] # 132 train\n",
     "Y_test_df = Y_df[Y_df.ds>'1959-12-31']   # 12 test\n",
@@ -2285,15 +2281,24 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "56493784",
+   "id": "0bd1d011-aafb-4b7c-a0a0-0f190b529fa8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#| hide\n",
+    "from neuralforecast.losses.pytorch import GMM, sCRPS"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b7e471ca-a633-4868-be0b-3f2992b6cdc1",
    "metadata": {},
    "outputs": [],
    "source": [
     "#| hide\n",
     "## TODO: Add unit tests for interactions between loss/valid_loss types\n",
     "## TODO: Unit tests (2 types of networks x 2 types of loss x 2 types of valid loss)\n",
-    "from neuralforecast.losses.pytorch import GMM, sCRPS\n",
-    "\n",
     "## Checking if base recurrent methods run point valid_loss correctly\n",
     "tcn_config = {\n",
     "       \"learning_rate\": tune.choice([1e-3]),                                     # Initial Learning rate\n",
diff --git a/nbs/models.nbeatsx.ipynb b/nbs/models.nbeatsx.ipynb
index 7f1264ea3..10d59d948 100644
--- a/nbs/models.nbeatsx.ipynb
+++ b/nbs/models.nbeatsx.ipynb
@@ -57,9 +57,6 @@
    "outputs": [],
    "source": [
     "#| hide\n",
-    "import os\n",
-    "os.environ[\"PYTORCH_ENABLE_MPS_FALLBACK\"] = \"1\"\n",
-    "\n",
     "from fastcore.test import test_eq, test_fail\n",
     "from nbdev.showdoc import show_doc\n",
     "from neuralforecast.utils import generate_series"
diff --git a/nbs/models.nhits.ipynb b/nbs/models.nhits.ipynb
index 3aa9e18da..3d9dbba74 100644
--- a/nbs/models.nhits.ipynb
+++ b/nbs/models.nhits.ipynb
@@ -52,18 +52,6 @@
     "![Figure 1. Neural Hierarchical Interpolation for Time Series (NHITS).](imgs_models/nhits.png)"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "#| hide\n",
-    "import os\n",
-    "os.environ[\"PYTORCH_ENABLE_MPS_FALLBACK\"] = \"1\"\n",
-    "os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"0\""
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": null,