diff --git a/tutorials/W1D1_Generalization/W1D1_Tutorial5.ipynb b/tutorials/W1D1_Generalization/W1D1_Tutorial5.ipynb
index 9044dc409..677bf9598 100644
--- a/tutorials/W1D1_Generalization/W1D1_Tutorial5.ipynb
+++ b/tutorials/W1D1_Generalization/W1D1_Tutorial5.ipynb
@@ -38,7 +38,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "/tmp/ipykernel_204181/828212273.py:27: UserWarning: Creating a tensor from a list of numpy.ndarrays is extremely slow. Please consider converting the list to a single numpy.ndarray with numpy.array() before converting to a tensor. (Triggered internally at ../torch/csrc/utils/tensor_new.cpp:230.)\n",
+      "/tmp/ipykernel_210226/828212273.py:27: UserWarning: Creating a tensor from a list of numpy.ndarrays is extremely slow. Please consider converting the list to a single numpy.ndarray with numpy.array() before converting to a tensor. (Triggered internally at ../torch/csrc/utils/tensor_new.cpp:230.)\n",
       "  go_envelope_all.append(torch.tensor(go_envelope_condition, dtype=torch.float32))\n"
      ]
     },
@@ -102,6 +102,658 @@
   {
    "cell_type": "code",
    "execution_count": 4,
+   "id": "759ce5e6-97df-4f8f-a0ee-13b631a12705",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Normalized Go Envelope Tensor Shape: torch.Size([216, 296, 1])\n",
+      "Standardized Go Envelope Tensor Shape: torch.Size([216, 296, 1])\n",
+      "Normalized Plan Tensor Shape: torch.Size([216, 296, 15])\n",
+      "Standardized Plan Tensor Shape: torch.Size([216, 296, 15])\n",
+      "Normalized Muscle Tensor Shape: torch.Size([216, 296, 8])\n",
+      "Standardized Muscle Tensor Shape: torch.Size([216, 296, 8])\n",
+      "Sample normalized go envelope values: tensor([[nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan]])\n",
+      "Sample standardized go envelope values: tensor([[nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [inf],\n",
+      "        [-inf],\n",
+      "        [inf],\n",
+      "        [inf],\n",
+      "        [inf],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [-inf],\n",
+      "        [inf],\n",
+      "        [-inf],\n",
+      "        [nan],\n",
+      "        [inf],\n",
+      "        [inf],\n",
+      "        [inf],\n",
+      "        [-inf],\n",
+      "        [-inf],\n",
+      "        [inf],\n",
+      "        [nan],\n",
+      "        [inf],\n",
+      "        [-inf],\n",
+      "        [-inf],\n",
+      "        [inf],\n",
+      "        [inf],\n",
+      "        [inf],\n",
+      "        [nan],\n",
+      "        [-inf],\n",
+      "        [inf],\n",
+      "        [-inf],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [inf],\n",
+      "        [-inf],\n",
+      "        [inf],\n",
+      "        [-inf],\n",
+      "        [inf],\n",
+      "        [-inf],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan],\n",
+      "        [nan]])\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Normalization and standardization Functions\n",
+    "def normalize(tensor):\n",
+    "    # Scale data to the range [0, 1]\n",
+    "    min_val = tensor.min(dim=0, keepdim=True)[0]\n",
+    "    max_val = tensor.max(dim=0, keepdim=True)[0]\n",
+    "    normalized_tensor = (tensor - min_val) / (max_val - min_val)\n",
+    "    return normalized_tensor\n",
+    "\n",
+    "def standardize(tensor):\n",
+    "    # Standardize data to have mean=0 and std=1\n",
+    "    mean = tensor.mean(dim=0, keepdim=True)\n",
+    "    std = tensor.std(dim=0, keepdim=True)\n",
+    "    standardized_tensor = (tensor - mean) / std\n",
+    "    return standardized_tensor\n",
+    "\n",
+    "# Apply normalization and standardization\n",
+    "normalized_go_envelope = normalize(go_envelope_tensor)\n",
+    "standardized_go_envelope = standardize(go_envelope_tensor)\n",
+    "\n",
+    "normalized_plan = normalize(plan_tensor)\n",
+    "standardized_plan = standardize(plan_tensor)\n",
+    "\n",
+    "normalized_muscle = normalize(muscle_tensor)\n",
+    "standardized_muscle = standardize(muscle_tensor)\n",
+    "\n",
+    "# Print shapes and some sample data for verification\n",
+    "print(f\"Normalized Go Envelope Tensor Shape: {normalized_go_envelope.shape}\")\n",
+    "print(f\"Standardized Go Envelope Tensor Shape: {standardized_go_envelope.shape}\")\n",
+    "\n",
+    "print(f\"Normalized Plan Tensor Shape: {normalized_plan.shape}\")\n",
+    "print(f\"Standardized Plan Tensor Shape: {standardized_plan.shape}\")\n",
+    "\n",
+    "print(f\"Normalized Muscle Tensor Shape: {normalized_muscle.shape}\")\n",
+    "print(f\"Standardized Muscle Tensor Shape: {standardized_muscle.shape}\")\n",
+    "\n",
+    "# Example to print some values\n",
+    "print(\"Sample normalized go envelope values:\", normalized_go_envelope[0])\n",
+    "print(\"Sample standardized go envelope values:\", standardized_go_envelope[0])\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
    "id": "d84ac60b-be75-45af-8d22-eca9c41fec6c",
    "metadata": {},
    "outputs": [],
@@ -129,7 +781,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 6,
    "id": "e8ecaf47-96ba-4120-87e6-39b6c9d08188",
    "metadata": {},
    "outputs": [],
@@ -150,7 +802,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 7,
    "id": "160bdb5c-2056-40f8-a2f3-597a7e771c53",
    "metadata": {},
    "outputs": [
@@ -186,7 +838,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 8,
    "id": "1d4aab79-08da-4fc1-be1c-cc580a5f2d70",
    "metadata": {},
    "outputs": [
@@ -194,56 +846,56 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Epoch [0/500], Loss: 0.06945484131574631, Test Loss: 0.06215358525514603\n",
-      "Epoch [10/500], Loss: 0.021324191242456436, Test Loss: 0.0196370966732502\n",
-      "Epoch [20/500], Loss: 0.019416367635130882, Test Loss: 0.01877027191221714\n",
-      "Epoch [30/500], Loss: 0.01791669800877571, Test Loss: 0.016670530661940575\n",
-      "Epoch [40/500], Loss: 0.017395811155438423, Test Loss: 0.01648167334496975\n",
-      "Epoch [50/500], Loss: 0.01716764271259308, Test Loss: 0.016113314777612686\n",
-      "Epoch [60/500], Loss: 0.016996093094348907, Test Loss: 0.016008485108613968\n",
-      "Epoch [70/500], Loss: 0.016899049282073975, Test Loss: 0.015784764662384987\n",
-      "Epoch [80/500], Loss: 0.016822611913084984, Test Loss: 0.01577206887304783\n",
-      "Epoch [90/500], Loss: 0.016755780205130577, Test Loss: 0.01563873328268528\n",
-      "Epoch [100/500], Loss: 0.016685090959072113, Test Loss: 0.01555646862834692\n",
-      "Epoch [110/500], Loss: 0.01658358983695507, Test Loss: 0.015401231124997139\n",
-      "Epoch [120/500], Loss: 0.016355616971850395, Test Loss: 0.015009786002337933\n",
-      "Epoch [130/500], Loss: 0.01487487368285656, Test Loss: 0.02703819051384926\n",
-      "Epoch [140/500], Loss: 0.016456956043839455, Test Loss: 0.01516042836010456\n",
-      "Epoch [150/500], Loss: 0.016544444486498833, Test Loss: 0.015271191485226154\n",
-      "Epoch [160/500], Loss: 0.016446998342871666, Test Loss: 0.01525502372533083\n",
-      "Epoch [170/500], Loss: 0.016341326758265495, Test Loss: 0.01504436507821083\n",
-      "Epoch [180/500], Loss: 0.01623906008899212, Test Loss: 0.014940104447305202\n",
-      "Epoch [190/500], Loss: 0.016118096187710762, Test Loss: 0.014749975875020027\n",
-      "Epoch [200/500], Loss: 0.015950532630085945, Test Loss: 0.014500990509986877\n",
-      "Epoch [210/500], Loss: 0.01567700505256653, Test Loss: 0.014078512787818909\n",
-      "Epoch [220/500], Loss: 0.015037690289318562, Test Loss: 0.013052952475845814\n",
-      "Epoch [230/500], Loss: 0.02549377828836441, Test Loss: 0.014654227532446384\n",
-      "Epoch [240/500], Loss: 0.017849242314696312, Test Loss: 0.01578238233923912\n",
-      "Epoch [250/500], Loss: 0.01701129786670208, Test Loss: 0.016172470524907112\n",
-      "Epoch [260/500], Loss: 0.016579564660787582, Test Loss: 0.015089149586856365\n",
-      "Epoch [270/500], Loss: 0.01641070283949375, Test Loss: 0.01525115966796875\n",
-      "Epoch [280/500], Loss: 0.01629340648651123, Test Loss: 0.014967095106840134\n",
-      "Epoch [290/500], Loss: 0.01620139181613922, Test Loss: 0.014865301549434662\n",
-      "Epoch [300/500], Loss: 0.01611190102994442, Test Loss: 0.014730663038790226\n",
-      "Epoch [310/500], Loss: 0.016006972640752792, Test Loss: 0.014566123485565186\n",
-      "Epoch [320/500], Loss: 0.0158640518784523, Test Loss: 0.014335619285702705\n",
-      "Epoch [330/500], Loss: 0.015639012679457664, Test Loss: 0.013991651125252247\n",
-      "Epoch [340/500], Loss: 0.015176555141806602, Test Loss: 0.013243998400866985\n",
-      "Epoch [350/500], Loss: 0.013796578161418438, Test Loss: 0.0115931062027812\n",
-      "Epoch [360/500], Loss: 0.015857117250561714, Test Loss: 0.014362258836627007\n",
-      "Epoch [370/500], Loss: 0.01589975878596306, Test Loss: 0.014321285299956799\n",
-      "Epoch [380/500], Loss: 0.015759805217385292, Test Loss: 0.014182702638208866\n",
-      "Epoch [390/500], Loss: 0.015622653998434544, Test Loss: 0.013964013196527958\n",
-      "Epoch [400/500], Loss: 0.015410303138196468, Test Loss: 0.013604477979242802\n",
-      "Epoch [410/500], Loss: 0.01506776176393032, Test Loss: 0.013094850815832615\n",
-      "Epoch [420/500], Loss: 0.014383680187165737, Test Loss: 0.011991310864686966\n",
-      "Epoch [430/500], Loss: 0.013644035905599594, Test Loss: 0.010731290094554424\n",
-      "Epoch [440/500], Loss: 0.013392072170972824, Test Loss: 0.010501268319785595\n",
-      "Epoch [450/500], Loss: 0.013526298105716705, Test Loss: 0.010595179162919521\n",
-      "Epoch [460/500], Loss: 0.013375792652368546, Test Loss: 0.010180925950407982\n",
-      "Epoch [470/500], Loss: 0.013830088078975677, Test Loss: 0.010914870537817478\n",
-      "Epoch [480/500], Loss: 0.013349335640668869, Test Loss: 0.01034696213901043\n",
-      "Epoch [490/500], Loss: 0.013634550385177135, Test Loss: 0.011291691102087498\n"
+      "Epoch [0/500], Loss: 0.07742229849100113, Test Loss: 0.0727684423327446\n",
+      "Epoch [10/500], Loss: 0.021188165992498398, Test Loss: 0.019497007131576538\n",
+      "Epoch [20/500], Loss: 0.019121600314974785, Test Loss: 0.018268633633852005\n",
+      "Epoch [30/500], Loss: 0.017821267247200012, Test Loss: 0.017074184492230415\n",
+      "Epoch [40/500], Loss: 0.017489111050963402, Test Loss: 0.01645728014409542\n",
+      "Epoch [50/500], Loss: 0.017208021134138107, Test Loss: 0.016325168311595917\n",
+      "Epoch [60/500], Loss: 0.01704731211066246, Test Loss: 0.015920618548989296\n",
+      "Epoch [70/500], Loss: 0.016925005242228508, Test Loss: 0.01593983732163906\n",
+      "Epoch [80/500], Loss: 0.016836464405059814, Test Loss: 0.015746857970952988\n",
+      "Epoch [90/500], Loss: 0.016749737784266472, Test Loss: 0.01566593162715435\n",
+      "Epoch [100/500], Loss: 0.016630981117486954, Test Loss: 0.01548491045832634\n",
+      "Epoch [110/500], Loss: 0.016384156420826912, Test Loss: 0.015110716223716736\n",
+      "Epoch [120/500], Loss: 0.014861536212265491, Test Loss: 0.012818137183785439\n",
+      "Epoch [130/500], Loss: 0.01693863607943058, Test Loss: 0.01591598056256771\n",
+      "Epoch [140/500], Loss: 0.01698044128715992, Test Loss: 0.015897389501333237\n",
+      "Epoch [150/500], Loss: 0.01681746169924736, Test Loss: 0.015561999753117561\n",
+      "Epoch [160/500], Loss: 0.01668746955692768, Test Loss: 0.015545305795967579\n",
+      "Epoch [170/500], Loss: 0.01660947874188423, Test Loss: 0.015420910902321339\n",
+      "Epoch [180/500], Loss: 0.01655176468193531, Test Loss: 0.015375783666968346\n",
+      "Epoch [190/500], Loss: 0.01649635098874569, Test Loss: 0.015268080867826939\n",
+      "Epoch [200/500], Loss: 0.01643761247396469, Test Loss: 0.015201805159449577\n",
+      "Epoch [210/500], Loss: 0.016369910910725594, Test Loss: 0.01509227603673935\n",
+      "Epoch [220/500], Loss: 0.016286104917526245, Test Loss: 0.014971805736422539\n",
+      "Epoch [230/500], Loss: 0.01617460325360298, Test Loss: 0.014797219075262547\n",
+      "Epoch [240/500], Loss: 0.016011686995625496, Test Loss: 0.014544459991157055\n",
+      "Epoch [250/500], Loss: 0.015733210369944572, Test Loss: 0.01410460565239191\n",
+      "Epoch [260/500], Loss: 0.015061312355101109, Test Loss: 0.013038666918873787\n",
+      "Epoch [270/500], Loss: 0.013998611830174923, Test Loss: 0.013295283541083336\n",
+      "Epoch [280/500], Loss: 0.01632058620452881, Test Loss: 0.014859010465443134\n",
+      "Epoch [290/500], Loss: 0.016171246767044067, Test Loss: 0.014864007011055946\n",
+      "Epoch [300/500], Loss: 0.016083858907222748, Test Loss: 0.014676372520625591\n",
+      "Epoch [310/500], Loss: 0.015966173261404037, Test Loss: 0.01449656207114458\n",
+      "Epoch [320/500], Loss: 0.015819577500224113, Test Loss: 0.014210316352546215\n",
+      "Epoch [330/500], Loss: 0.015601351857185364, Test Loss: 0.013891666196286678\n",
+      "Epoch [340/500], Loss: 0.015251322649419308, Test Loss: 0.013362851925194263\n",
+      "Epoch [350/500], Loss: 0.01449844054877758, Test Loss: 0.0121900150552392\n",
+      "Epoch [360/500], Loss: 0.013566537760198116, Test Loss: 0.01274181716144085\n",
+      "Epoch [370/500], Loss: 0.015601711347699165, Test Loss: 0.013967408798635006\n",
+      "Epoch [380/500], Loss: 0.015554051846265793, Test Loss: 0.01384493988007307\n",
+      "Epoch [390/500], Loss: 0.015226305462419987, Test Loss: 0.013465745374560356\n",
+      "Epoch [400/500], Loss: 0.014765387400984764, Test Loss: 0.01260434091091156\n",
+      "Epoch [410/500], Loss: 0.013775410130620003, Test Loss: 0.011229578405618668\n",
+      "Epoch [420/500], Loss: 0.013510041870176792, Test Loss: 0.010720356367528439\n",
+      "Epoch [430/500], Loss: 0.013304662890732288, Test Loss: 0.01072752010077238\n",
+      "Epoch [440/500], Loss: 0.013398389331996441, Test Loss: 0.011271395720541477\n",
+      "Epoch [450/500], Loss: 0.013416752219200134, Test Loss: 0.010849958285689354\n",
+      "Epoch [460/500], Loss: 0.013317599892616272, Test Loss: 0.010567201301455498\n",
+      "Epoch [470/500], Loss: 0.013105758465826511, Test Loss: 0.010510857217013836\n",
+      "Epoch [480/500], Loss: 0.013195441104471684, Test Loss: 0.010664255358278751\n",
+      "Epoch [490/500], Loss: 0.01362114492803812, Test Loss: 0.010563290677964687\n"
      ]
     }
    ],
diff --git a/tutorials/W1D1_Generalization/W1D1_Tutorial6.ipynb b/tutorials/W1D1_Generalization/W1D1_Tutorial6.ipynb
new file mode 100644
index 000000000..649d68499
--- /dev/null
+++ b/tutorials/W1D1_Generalization/W1D1_Tutorial6.ipynb
@@ -0,0 +1,960 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "12bb9e08-6996-4d6b-8b80-a7a26191c9d6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Imports\n",
+    "import scipy.io\n",
+    "import numpy as np\n",
+    "import torch\n",
+    "import torch.nn as nn\n",
+    "import torch.optim as optim"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "2baca459-5a6a-489b-90d3-dffa0a4893e5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Load the .mat file\n",
+    "data = scipy.io.loadmat('data/condsForSimJ2moMuscles.mat')\n",
+    "\n",
+    "# Extract condsForSim struct\n",
+    "conds_for_sim = data['condsForSim']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "50c15d51-8e59-4305-a2bc-e270ac349085",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/tmp/ipykernel_268751/1417502240.py:30: UserWarning: Creating a tensor from a list of numpy.ndarrays is extremely slow. Please consider converting the list to a single numpy.ndarray with numpy.array() before converting to a tensor. (Triggered internally at ../torch/csrc/utils/tensor_new.cpp:230.)\n",
+      "  go_envelope_all.append(torch.tensor(go_envelope_condition, dtype=torch.float32))\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Go Envelope Tensor Shape: torch.Size([216, 296, 1])\n",
+      "Plan Tensor Shape: torch.Size([216, 296, 15])\n",
+      "Muscle Tensor Shape: torch.Size([216, 296, 2])\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Initialize lists to store data for all conditions\n",
+    "go_envelope_all = []\n",
+    "plan_all = []\n",
+    "muscle_all = []\n",
+    "\n",
+    "# Get the number of conditions (rows) and delay durations (columns)\n",
+    "num_conditions, num_delays = conds_for_sim.shape\n",
+    "\n",
+    "# Loop through each condition and extract data\n",
+    "for i in range(num_conditions):  # 27 conditions\n",
+    "    go_envelope_condition = []\n",
+    "    plan_condition = []\n",
+    "    muscle_condition = []\n",
+    "\n",
+    "    for j in range(num_delays):  # 8 delay durations\n",
+    "        condition = conds_for_sim[i, j]\n",
+    "\n",
+    "        go_envelope = condition['goEnvelope']\n",
+    "        plan = condition['plan']\n",
+    "        muscle = condition['muscle']\n",
+    "\n",
+    "        # Select only muscles 5 and 6 \n",
+    "        selected_muscle_data = muscle[:, [4, 5]]  # Select columns for muscle 5 and 6, which show the nicest multiphasic activity\n",
+    "\n",
+    "        go_envelope_condition.append(go_envelope)\n",
+    "        plan_condition.append(plan)\n",
+    "        muscle_condition.append(selected_muscle_data)\n",
+    "\n",
+    "    # Stack data for each condition\n",
+    "    go_envelope_all.append(torch.tensor(go_envelope_condition, dtype=torch.float32))\n",
+    "    plan_all.append(torch.tensor(plan_condition, dtype=torch.float32))\n",
+    "    muscle_all.append(torch.tensor(muscle_condition, dtype=torch.float32))\n",
+    "\n",
+    "# Stack data for all conditions\n",
+    "go_envelope_tensor = torch.stack(go_envelope_all)\n",
+    "plan_tensor = torch.stack(plan_all)\n",
+    "muscle_tensor = torch.stack(muscle_all)\n",
+    "\n",
+    "# Reshape to merge the first two dimensions\n",
+    "go_envelope_tensor = go_envelope_tensor.reshape(-1, *go_envelope_tensor.shape[2:])\n",
+    "plan_tensor = plan_tensor.reshape(-1, *plan_tensor.shape[2:])\n",
+    "muscle_tensor = muscle_tensor.reshape(-1, *muscle_tensor.shape[2:])\n",
+    "\n",
+    "# Print shapes\n",
+    "print(f\"Go Envelope Tensor Shape: {go_envelope_tensor.shape}\")\n",
+    "print(f\"Plan Tensor Shape: {plan_tensor.shape}\")\n",
+    "print(f\"Muscle Tensor Shape: {muscle_tensor.shape}\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "b9515c13-74d5-4fb5-8614-53fbb8dcfe06",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Normalized Go Envelope Tensor Shape: torch.Size([216, 296, 1])\n",
+      "Normalized Plan Tensor Shape: torch.Size([216, 296, 15])\n",
+      "Normalized Muscle Tensor Shape: torch.Size([216, 296, 2])\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Normalize and standardize a tensor\n",
+    "def normalize_and_standardize(tensor):\n",
+    "    # Normalize: Scale to 0-1 range\n",
+    "    min_val = tensor.min()\n",
+    "    max_val = tensor.max()\n",
+    "    tensor = (tensor - min_val) / (max_val - min_val)\n",
+    "\n",
+    "    # Standardize: Shift to zero mean and unit variance\n",
+    "    mean = tensor.mean()\n",
+    "    std = tensor.std()\n",
+    "    tensor = (tensor - mean) / std\n",
+    "\n",
+    "    return tensor\n",
+    "\n",
+    "# Apply the function to each tensor\n",
+    "normalized_go_envelope_tensor = normalize_and_standardize(go_envelope_tensor)\n",
+    "normalized_plan_tensor = normalize_and_standardize(plan_tensor)\n",
+    "normalized_muscle_tensor = normalize_and_standardize(muscle_tensor)\n",
+    "\n",
+    "# Print shapes to confirm\n",
+    "print(f\"Normalized Go Envelope Tensor Shape: {normalized_go_envelope_tensor.shape}\")\n",
+    "print(f\"Normalized Plan Tensor Shape: {normalized_plan_tensor.shape}\")\n",
+    "print(f\"Normalized Muscle Tensor Shape: {normalized_muscle_tensor.shape}\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "7e2b6a95-49a0-4f10-8f63-3b85a7f7d7be",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import torch\n",
+    "import torch.nn as nn\n",
+    "\n",
+    "class SimpleRNN(nn.Module):\n",
+    "    def __init__(self, input_size, hidden_size, output_size, g, h, tau=50):\n",
+    "        super(SimpleRNN, self).__init__()\n",
+    "        self.hidden_size = hidden_size\n",
+    "        self.tau = tau  # Time constant\n",
+    "\n",
+    "        # Weight initialization\n",
+    "        self.J = nn.Parameter(torch.randn(hidden_size, hidden_size) * (g / torch.sqrt(torch.tensor(hidden_size, dtype=torch.float))))\n",
+    "        self.B = nn.Parameter(torch.randn(hidden_size, input_size) * (h / torch.sqrt(torch.tensor(input_size, dtype=torch.float)))) \n",
+    "        self.w = nn.Parameter(torch.zeros(output_size, hidden_size))\n",
+    "        self.bx = nn.Parameter(torch.zeros(hidden_size))\n",
+    "        self.bz = nn.Parameter(torch.zeros(output_size))\n",
+    "\n",
+    "        # Nonlinearity\n",
+    "        self.nonlinearity = torch.tanh\n",
+    "    \n",
+    "    def forward(self, x, hidden):\n",
+    "        timestep = self.tau / 10  # Timestep for Euler integration\n",
+    "        for _ in range(int(1 / timestep)):  # Adjust the range for simulation duration\n",
+    "            hidden_update = torch.matmul(self.J, hidden.T)\n",
+    "            input_update = torch.matmul(self.B, x.T)\n",
+    "            new_hidden = self.nonlinearity(hidden_update + input_update + self.bx.unsqueeze(1))\n",
+    "            new_hidden = new_hidden.T\n",
+    "\n",
+    "            # Euler integration for continuous-time update\n",
+    "            hidden = hidden + (timestep / self.tau) * (-hidden + new_hidden)\n",
+    "        \n",
+    "        output = torch.matmul(self.w, hidden.T) + self.bz.unsqueeze(1)\n",
+    "        output = output.T\n",
+    "        return output, hidden\n",
+    "    \n",
+    "    def init_hidden(self):\n",
+    "        # Initialize hidden state with an additional batch dimension\n",
+    "        return torch.zeros(1, self.hidden_size)\n",
+    "\n",
+    "# Hyperparameters\n",
+    "input_size = 7  \n",
+    "hidden_size = 300\n",
+    "output_size = 2  # Number of muscles\n",
+    "g = 1.1  # g value\n",
+    "h = 1.0  # h value\n",
+    "\n",
+    "# Model instantiation\n",
+    "model = SimpleRNN(input_size, hidden_size, output_size, g, h)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "de475624-9823-4fd4-a591-960795badf82",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import torch\n",
+    "import torch.nn as nn\n",
+    "\n",
+    "class ComplicatedRNN(nn.Module):\n",
+    "    def __init__(self, input_size, hidden_size, output_size, g, h, tau=50):\n",
+    "        super(ComplicatedRNN, self).__init__()\n",
+    "        self.hidden_size = hidden_size\n",
+    "        self.tau = tau  # Time constant\n",
+    "\n",
+    "        # Modified weight initialization for a more chaotic regime (g >> 1)\n",
+    "        # Adjust the scale factor as per the specific requirements of the model\n",
+    "        self.J = nn.Parameter(torch.randn(hidden_size, hidden_size) * (g / torch.sqrt(torch.tensor(hidden_size, dtype=torch.float))))\n",
+    "        self.B = nn.Parameter(torch.randn(hidden_size, input_size) * (h / torch.sqrt(torch.tensor(input_size, dtype=torch.float)))) \n",
+    "        self.w = nn.Parameter(torch.zeros(output_size, hidden_size))\n",
+    "        self.bx = nn.Parameter(torch.zeros(hidden_size))\n",
+    "        self.bz = nn.Parameter(torch.zeros(output_size))\n",
+    "\n",
+    "        # Nonlinearity remains the same\n",
+    "        self.nonlinearity = torch.tanh\n",
+    "    \n",
+    "    def forward(self, x, hidden):\n",
+    "        timestep = self.tau / 10  # Timestep for Euler integration\n",
+    "        for _ in range(int(1 / timestep)):  # Adjust the range for simulation duration\n",
+    "            hidden_update = torch.matmul(self.J, hidden.T)\n",
+    "            input_update = torch.matmul(self.B, x.T)\n",
+    "            new_hidden = self.nonlinearity(hidden_update + input_update + self.bx.unsqueeze(1))\n",
+    "            new_hidden = new_hidden.T\n",
+    "\n",
+    "            # Euler integration for continuous-time update\n",
+    "            hidden = hidden + (timestep / self.tau) * (-hidden + new_hidden)\n",
+    "        \n",
+    "        output = torch.matmul(self.w, hidden.T) + self.bz.unsqueeze(1)\n",
+    "        output = output.T\n",
+    "    \n",
+    "        return output, hidden\n",
+    "\n",
+    "    def init_hidden(self):\n",
+    "        # Initialize hidden state with an additional batch dimension\n",
+    "        return torch.zeros(1, self.hidden_size)\n",
+    "\n",
+    "input_size = 7\n",
+    "hidden_size = 300\n",
+    "output_size = 2 # Number of muscles\n",
+    "g = 10.0 # Significantly larger g value for complicated model\n",
+    "h = 1.0 # h value remains the same\n",
+    "\n",
+    "complicated_model = ComplicatedRNN(input_size, hidden_size, output_size, g, h)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "711bd5b4-d92c-43e4-b3c6-fb0a6fabb369",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Prepare data for training\n",
+    "# Assuming that 'normalized_plan_tensor' is your input data and 'normalized_muscle_tensor' is your target data\n",
+    "X_train = normalized_plan_tensor\n",
+    "y_train = normalized_muscle_tensor"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "2c626ab3-d0fa-4180-a639-1e986caf435b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Convert datasets to TensorDataset and DataLoader for batch processing\n",
+    "from torch.utils.data import TensorDataset, DataLoader\n",
+    "\n",
+    "batch_size = 64  # You can adjust this based on your data size and memory constraints\n",
+    "train_data = TensorDataset(X_train, y_train)\n",
+    "train_loader = DataLoader(train_data, batch_size=batch_size, shuffle=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "72179104-fa01-47b6-87ea-22b40e5f544f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Loss Function and Optimizer\n",
+    "criterion = nn.MSELoss()  # Mean Squared Error Loss for regression tasks\n",
+    "optimizer = optim.Adam(model.parameters(), lr=0.001)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "b46e0da9-238e-4bc8-a2be-a4dbc562731c",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/samuele/.local/lib/python3.10/site-packages/torch/nn/modules/loss.py:536: UserWarning: Using a target size (torch.Size([64, 2])) that is different to the input size (torch.Size([1, 2])). This will likely lead to incorrect results due to broadcasting. Please ensure they have the same size.\n",
+      "  return F.mse_loss(input, target, reduction=self.reduction)\n",
+      "/home/samuele/.local/lib/python3.10/site-packages/torch/nn/modules/loss.py:536: UserWarning: Using a target size (torch.Size([24, 2])) that is different to the input size (torch.Size([1, 2])). This will likely lead to incorrect results due to broadcasting. Please ensure they have the same size.\n",
+      "  return F.mse_loss(input, target, reduction=self.reduction)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1, Loss: 0.7935759276151657\n",
+      "Epoch 2, Loss: 0.6920289844274521\n",
+      "Epoch 3, Loss: 0.7398229837417603\n",
+      "Epoch 4, Loss: 0.6482370048761368\n",
+      "Epoch 5, Loss: 0.6573842614889145\n",
+      "Epoch 6, Loss: 0.7131140679121017\n",
+      "Epoch 7, Loss: 0.7308777570724487\n",
+      "Epoch 8, Loss: 0.6652112305164337\n",
+      "Epoch 9, Loss: 0.667251855134964\n",
+      "Epoch 10, Loss: 0.6554328501224518\n",
+      "Epoch 11, Loss: 0.6719786077737808\n",
+      "Epoch 12, Loss: 0.6412559151649475\n",
+      "Epoch 13, Loss: 0.6577332764863968\n",
+      "Epoch 14, Loss: 0.6826722845435143\n",
+      "Epoch 15, Loss: 0.6730566173791885\n",
+      "Epoch 16, Loss: 0.6750237941741943\n",
+      "Epoch 17, Loss: 0.6717002838850021\n",
+      "Epoch 18, Loss: 0.6032176986336708\n",
+      "Epoch 19, Loss: 0.6918650567531586\n",
+      "Epoch 20, Loss: 0.6837166324257851\n",
+      "Epoch 21, Loss: 0.6371837109327316\n",
+      "Epoch 22, Loss: 0.6939346790313721\n",
+      "Epoch 23, Loss: 0.6163643524050713\n",
+      "Epoch 24, Loss: 0.6930471509695053\n",
+      "Epoch 25, Loss: 0.6808096617460251\n",
+      "Epoch 26, Loss: 0.6641812026500702\n",
+      "Epoch 27, Loss: 0.7106741070747375\n",
+      "Epoch 28, Loss: 0.644190602004528\n",
+      "Epoch 29, Loss: 0.5723693408071995\n",
+      "Epoch 30, Loss: 0.6105481833219528\n",
+      "Epoch 31, Loss: 0.7502300888299942\n",
+      "Epoch 32, Loss: 0.6825971379876137\n",
+      "Epoch 33, Loss: 0.6341610997915268\n",
+      "Epoch 34, Loss: 0.5883132964372635\n",
+      "Epoch 35, Loss: 0.5604974143207073\n",
+      "Epoch 36, Loss: 0.6791626065969467\n",
+      "Epoch 37, Loss: 0.6531880497932434\n",
+      "Epoch 38, Loss: 0.6104335337877274\n",
+      "Epoch 39, Loss: 0.6113221794366837\n",
+      "Epoch 40, Loss: 0.5920990854501724\n",
+      "Epoch 41, Loss: 0.6436745747923851\n",
+      "Epoch 42, Loss: 0.5849806293845177\n",
+      "Epoch 43, Loss: 0.6086705178022385\n",
+      "Epoch 44, Loss: 0.5708582252264023\n",
+      "Epoch 45, Loss: 0.6552574709057808\n",
+      "Epoch 46, Loss: 0.5992646589875221\n",
+      "Epoch 47, Loss: 0.6171543002128601\n",
+      "Epoch 48, Loss: 0.6398012563586235\n",
+      "Epoch 49, Loss: 0.6719635352492332\n",
+      "Epoch 50, Loss: 0.5893900841474533\n",
+      "Epoch 51, Loss: 0.5296908281743526\n",
+      "Epoch 52, Loss: 0.6000862792134285\n",
+      "Epoch 53, Loss: 0.6392865404486656\n",
+      "Epoch 54, Loss: 0.6425042971968651\n",
+      "Epoch 55, Loss: 0.5828995034098625\n",
+      "Epoch 56, Loss: 0.5533675253391266\n",
+      "Epoch 57, Loss: 0.6369968876242638\n",
+      "Epoch 58, Loss: 0.5219818353652954\n",
+      "Epoch 59, Loss: 0.5605112537741661\n",
+      "Epoch 60, Loss: 0.5958641543984413\n",
+      "Epoch 61, Loss: 0.5781441479921341\n",
+      "Epoch 62, Loss: 0.5671888068318367\n",
+      "Epoch 63, Loss: 0.6519509702920914\n",
+      "Epoch 64, Loss: 0.553830161690712\n",
+      "Epoch 65, Loss: 0.5396606102585793\n",
+      "Epoch 66, Loss: 0.5298810452222824\n",
+      "Epoch 67, Loss: 0.536168746650219\n",
+      "Epoch 68, Loss: 0.5398459807038307\n",
+      "Epoch 69, Loss: 0.5343874990940094\n",
+      "Epoch 70, Loss: 0.5629830732941628\n",
+      "Epoch 71, Loss: 0.5859672576189041\n",
+      "Epoch 72, Loss: 0.5781515389680862\n",
+      "Epoch 73, Loss: 0.5557334646582603\n",
+      "Epoch 74, Loss: 0.6301153525710106\n",
+      "Epoch 75, Loss: 0.49188049510121346\n",
+      "Epoch 76, Loss: 0.6070103198289871\n",
+      "Epoch 77, Loss: 0.5299219042062759\n",
+      "Epoch 78, Loss: 0.5488025024533272\n",
+      "Epoch 79, Loss: 0.5074497535824776\n",
+      "Epoch 80, Loss: 0.5872437730431557\n",
+      "Epoch 81, Loss: 0.5662587508559227\n",
+      "Epoch 82, Loss: 0.5456828102469444\n",
+      "Epoch 83, Loss: 0.4886764921247959\n",
+      "Epoch 84, Loss: 0.5128987804055214\n",
+      "Epoch 85, Loss: 0.47813088074326515\n",
+      "Epoch 86, Loss: 0.5360578745603561\n",
+      "Epoch 87, Loss: 0.5093661323189735\n",
+      "Epoch 88, Loss: 0.5664857774972916\n",
+      "Epoch 89, Loss: 0.5394406616687775\n",
+      "Epoch 90, Loss: 0.5693044662475586\n",
+      "Epoch 91, Loss: 0.5394747704267502\n",
+      "Epoch 92, Loss: 0.5579681396484375\n",
+      "Epoch 93, Loss: 0.5293252915143967\n",
+      "Epoch 94, Loss: 0.4774884432554245\n",
+      "Epoch 95, Loss: 0.528400145471096\n",
+      "Epoch 96, Loss: 0.4745129980146885\n",
+      "Epoch 97, Loss: 0.5012770518660545\n",
+      "Epoch 98, Loss: 0.47556065395474434\n",
+      "Epoch 99, Loss: 0.5331674963235855\n",
+      "Epoch 100, Loss: 0.5354291871190071\n",
+      "Epoch 101, Loss: 0.5558453872799873\n",
+      "Epoch 102, Loss: 0.5521730110049248\n",
+      "Epoch 103, Loss: 0.5012309327721596\n",
+      "Epoch 104, Loss: 0.47141486778855324\n",
+      "Epoch 105, Loss: 0.5214555710554123\n",
+      "Epoch 106, Loss: 0.5277099832892418\n",
+      "Epoch 107, Loss: 0.5560920834541321\n",
+      "Epoch 108, Loss: 0.5310847163200378\n",
+      "Epoch 109, Loss: 0.5473720505833626\n",
+      "Epoch 110, Loss: 0.521634541451931\n",
+      "Epoch 111, Loss: 0.5754187926650047\n",
+      "Epoch 112, Loss: 0.49151940643787384\n",
+      "Epoch 113, Loss: 0.5166146159172058\n",
+      "Epoch 114, Loss: 0.5455936938524246\n",
+      "Epoch 115, Loss: 0.48646243661642075\n",
+      "Epoch 116, Loss: 0.6126626655459404\n",
+      "Epoch 117, Loss: 0.5159473270177841\n",
+      "Epoch 118, Loss: 0.4937717318534851\n",
+      "Epoch 119, Loss: 0.46163133904337883\n",
+      "Epoch 120, Loss: 0.5491314232349396\n",
+      "Epoch 121, Loss: 0.4664374925196171\n",
+      "Epoch 122, Loss: 0.511654406785965\n",
+      "Epoch 123, Loss: 0.5659694820642471\n",
+      "Epoch 124, Loss: 0.5251843854784966\n",
+      "Epoch 125, Loss: 0.49194004386663437\n",
+      "Epoch 126, Loss: 0.48286963254213333\n",
+      "Epoch 127, Loss: 0.47869592159986496\n",
+      "Epoch 128, Loss: 0.46164538338780403\n",
+      "Epoch 129, Loss: 0.5170556679368019\n",
+      "Epoch 130, Loss: 0.5608800873160362\n",
+      "Epoch 131, Loss: 0.5144810080528259\n",
+      "Epoch 132, Loss: 0.5633302703499794\n",
+      "Epoch 133, Loss: 0.48222847282886505\n",
+      "Epoch 134, Loss: 0.45533521845936775\n",
+      "Epoch 135, Loss: 0.5845294892787933\n",
+      "Epoch 136, Loss: 0.5442659109830856\n",
+      "Epoch 137, Loss: 0.45829829573631287\n",
+      "Epoch 138, Loss: 0.4628197029232979\n",
+      "Epoch 139, Loss: 0.483731709420681\n",
+      "Epoch 140, Loss: 0.5394167751073837\n",
+      "Epoch 141, Loss: 0.5344710424542427\n",
+      "Epoch 142, Loss: 0.5117827951908112\n",
+      "Epoch 143, Loss: 0.5031494051218033\n",
+      "Epoch 144, Loss: 0.5059430561959743\n",
+      "Epoch 145, Loss: 0.505917489528656\n",
+      "Epoch 146, Loss: 0.4993027150630951\n",
+      "Epoch 147, Loss: 0.5030878558754921\n",
+      "Epoch 148, Loss: 0.48781536519527435\n",
+      "Epoch 149, Loss: 0.457742303609848\n",
+      "Epoch 150, Loss: 0.5202512145042419\n",
+      "Epoch 151, Loss: 0.4840250536799431\n",
+      "Epoch 152, Loss: 0.5050239115953445\n",
+      "Epoch 153, Loss: 0.5108627080917358\n",
+      "Epoch 154, Loss: 0.5077801197767258\n",
+      "Epoch 155, Loss: 0.471999391913414\n",
+      "Epoch 156, Loss: 0.44989699870347977\n",
+      "Epoch 157, Loss: 0.4968614727258682\n",
+      "Epoch 158, Loss: 0.4768465831875801\n",
+      "Epoch 159, Loss: 0.44585394486784935\n",
+      "Epoch 160, Loss: 0.4668637439608574\n",
+      "Epoch 161, Loss: 0.53073950111866\n",
+      "Epoch 162, Loss: 0.49748802930116653\n",
+      "Epoch 163, Loss: 0.4688042029738426\n",
+      "Epoch 164, Loss: 0.47902732342481613\n",
+      "Epoch 165, Loss: 0.5464531257748604\n",
+      "Epoch 166, Loss: 0.49027299880981445\n",
+      "Epoch 167, Loss: 0.525591529905796\n",
+      "Epoch 168, Loss: 0.47375189512968063\n",
+      "Epoch 169, Loss: 0.4482397958636284\n",
+      "Epoch 170, Loss: 0.5003442466259003\n",
+      "Epoch 171, Loss: 0.44263309612870216\n",
+      "Epoch 172, Loss: 0.5119856297969818\n",
+      "Epoch 173, Loss: 0.5216193944215775\n",
+      "Epoch 174, Loss: 0.522923618555069\n",
+      "Epoch 175, Loss: 0.4900999516248703\n",
+      "Epoch 176, Loss: 0.48769107460975647\n",
+      "Epoch 177, Loss: 0.4666164442896843\n",
+      "Epoch 178, Loss: 0.4702208563685417\n",
+      "Epoch 179, Loss: 0.4564842954277992\n",
+      "Epoch 180, Loss: 0.46819256991147995\n",
+      "Epoch 181, Loss: 0.4982581064105034\n",
+      "Epoch 182, Loss: 0.49784307926893234\n",
+      "Epoch 183, Loss: 0.44782593473792076\n",
+      "Epoch 184, Loss: 0.48838846385478973\n",
+      "Epoch 185, Loss: 0.4465550146996975\n",
+      "Epoch 186, Loss: 0.49545595049858093\n",
+      "Epoch 187, Loss: 0.4627245292067528\n",
+      "Epoch 188, Loss: 0.4693310111761093\n",
+      "Epoch 189, Loss: 0.5173218324780464\n",
+      "Epoch 190, Loss: 0.4896280765533447\n",
+      "Epoch 191, Loss: 0.46565286070108414\n",
+      "Epoch 192, Loss: 0.5412594303488731\n",
+      "Epoch 193, Loss: 0.46252138167619705\n",
+      "Epoch 194, Loss: 0.5765400677919388\n",
+      "Epoch 195, Loss: 0.5264268815517426\n",
+      "Epoch 196, Loss: 0.5092506408691406\n",
+      "Epoch 197, Loss: 0.5018178224563599\n",
+      "Epoch 198, Loss: 0.5484926849603653\n",
+      "Epoch 199, Loss: 0.49209095537662506\n",
+      "Epoch 200, Loss: 0.48782479763031006\n",
+      "Epoch 201, Loss: 0.45111341029405594\n",
+      "Epoch 202, Loss: 0.4434959851205349\n",
+      "Epoch 203, Loss: 0.47081730514764786\n",
+      "Epoch 204, Loss: 0.4690076410770416\n",
+      "Epoch 205, Loss: 0.518307201564312\n",
+      "Epoch 206, Loss: 0.49604639410972595\n",
+      "Epoch 207, Loss: 0.473017618060112\n",
+      "Epoch 208, Loss: 0.4699573591351509\n",
+      "Epoch 209, Loss: 0.51186603307724\n",
+      "Epoch 210, Loss: 0.4695538580417633\n",
+      "Epoch 211, Loss: 0.517631471157074\n",
+      "Epoch 212, Loss: 0.48688697069883347\n",
+      "Epoch 213, Loss: 0.4950114041566849\n",
+      "Epoch 214, Loss: 0.4858812168240547\n",
+      "Epoch 215, Loss: 0.46237554401159286\n",
+      "Epoch 216, Loss: 0.5871907845139503\n",
+      "Epoch 217, Loss: 0.46684500575065613\n",
+      "Epoch 218, Loss: 0.4667687490582466\n",
+      "Epoch 219, Loss: 0.4732024744153023\n",
+      "Epoch 220, Loss: 0.47017788141965866\n",
+      "Epoch 221, Loss: 0.43647684529423714\n",
+      "Epoch 222, Loss: 0.5100738257169724\n",
+      "Epoch 223, Loss: 0.44505608454346657\n",
+      "Epoch 224, Loss: 0.4381622150540352\n",
+      "Epoch 225, Loss: 0.48807067424058914\n",
+      "Epoch 226, Loss: 0.5446464493870735\n",
+      "Epoch 227, Loss: 0.5156442224979401\n",
+      "Epoch 228, Loss: 0.47173336148262024\n",
+      "Epoch 229, Loss: 0.4949176460504532\n",
+      "Epoch 230, Loss: 0.5285792946815491\n",
+      "Epoch 231, Loss: 0.5427089333534241\n",
+      "Epoch 232, Loss: 0.49280649051070213\n",
+      "Epoch 233, Loss: 0.4929331764578819\n",
+      "Epoch 234, Loss: 0.4635517820715904\n",
+      "Epoch 235, Loss: 0.47221238166093826\n",
+      "Epoch 236, Loss: 0.5402342900633812\n",
+      "Epoch 237, Loss: 0.5121470764279366\n",
+      "Epoch 238, Loss: 0.5187357366085052\n",
+      "Epoch 239, Loss: 0.5136171132326126\n",
+      "Epoch 240, Loss: 0.46641460806131363\n",
+      "Epoch 241, Loss: 0.49208052456378937\n",
+      "Epoch 242, Loss: 0.4770965129137039\n",
+      "Epoch 243, Loss: 0.4415730610489845\n",
+      "Epoch 244, Loss: 0.4955950975418091\n",
+      "Epoch 245, Loss: 0.46542347222566605\n",
+      "Epoch 246, Loss: 0.48886801302433014\n",
+      "Epoch 247, Loss: 0.4870700463652611\n",
+      "Epoch 248, Loss: 0.45627693086862564\n",
+      "Epoch 249, Loss: 0.5032604038715363\n",
+      "Epoch 250, Loss: 0.4566391706466675\n",
+      "Finished Training\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1000x600 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "# Training Loop\n",
+    "num_epochs = 250  # The number of times the entire dataset is passed through the network\n",
+    "epoch_losses = []  # List to store average loss of each epoch\n",
+    "\n",
+    "for epoch in range(num_epochs):\n",
+    "    running_loss = 0.0\n",
+    "    for inputs, targets in train_loader:\n",
+    "        optimizer.zero_grad()\n",
+    "        h = model.init_hidden()\n",
+    "\n",
+    "        # Process each time step\n",
+    "        for t in range(inputs.shape[1]):  # iterate over time steps\n",
+    "            output, h = model(inputs[:, t, :], h)\n",
+    "\n",
+    "        # Compute loss using the last output (if your task is many-to-one)\n",
+    "        loss = criterion(output, targets[:, -1, :])\n",
+    "        loss.backward()\n",
+    "        optimizer.step()\n",
+    "\n",
+    "        running_loss += loss.item()\n",
+    "\n",
+    "    avg_loss = running_loss / len(train_loader)\n",
+    "    epoch_losses.append(avg_loss)\n",
+    "    print(f'Epoch {epoch + 1}, Loss: {avg_loss}')\n",
+    "\n",
+    "print('Finished Training')\n",
+    "\n",
+    "# Plotting\n",
+    "plt.figure(figsize=(10, 6))\n",
+    "plt.plot(range(1, num_epochs + 1), epoch_losses, label='Training Loss')\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.ylabel('Loss')\n",
+    "plt.title('Training Loss Over Epochs')\n",
+    "plt.legend()\n",
+    "plt.show()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "21dd9a5b-0e80-4464-aa8e-9ec54d225646",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1, Loss: 0.7205749005079269\n",
+      "Epoch 2, Loss: 0.6714087128639221\n",
+      "Epoch 3, Loss: 0.6538456007838249\n",
+      "Epoch 4, Loss: 0.6780925467610359\n",
+      "Epoch 5, Loss: 0.6583075970411301\n",
+      "Epoch 6, Loss: 0.760643795132637\n",
+      "Epoch 7, Loss: 0.7337100505828857\n",
+      "Epoch 8, Loss: 0.7637397348880768\n",
+      "Epoch 9, Loss: 0.6507012248039246\n",
+      "Epoch 10, Loss: 0.6706947758793831\n",
+      "Epoch 11, Loss: 0.7026693820953369\n",
+      "Epoch 12, Loss: 0.7958869636058807\n",
+      "Epoch 13, Loss: 0.7023506462574005\n",
+      "Epoch 14, Loss: 0.7687423676252365\n",
+      "Epoch 15, Loss: 0.7000135183334351\n",
+      "Epoch 16, Loss: 0.6597461774945259\n",
+      "Epoch 17, Loss: 0.7268760949373245\n",
+      "Epoch 18, Loss: 0.7524468153715134\n",
+      "Epoch 19, Loss: 0.7063141465187073\n",
+      "Epoch 20, Loss: 0.7392593324184418\n",
+      "Epoch 21, Loss: 0.7214491367340088\n",
+      "Epoch 22, Loss: 0.754235178232193\n",
+      "Epoch 23, Loss: 0.7253281325101852\n",
+      "Epoch 24, Loss: 0.696549654006958\n",
+      "Epoch 25, Loss: 0.8609312176704407\n",
+      "Epoch 26, Loss: 0.6951945871114731\n",
+      "Epoch 27, Loss: 0.69309501349926\n",
+      "Epoch 28, Loss: 0.7275056838989258\n",
+      "Epoch 29, Loss: 0.796893760561943\n",
+      "Epoch 30, Loss: 0.6937407553195953\n",
+      "Epoch 31, Loss: 0.698080763220787\n",
+      "Epoch 32, Loss: 0.7193515747785568\n",
+      "Epoch 33, Loss: 0.6967144012451172\n",
+      "Epoch 34, Loss: 0.6566696465015411\n",
+      "Epoch 35, Loss: 0.7964757680892944\n",
+      "Epoch 36, Loss: 0.8061037361621857\n",
+      "Epoch 37, Loss: 0.7979170307517052\n",
+      "Epoch 38, Loss: 0.7368465960025787\n",
+      "Epoch 39, Loss: 0.6875014901161194\n",
+      "Epoch 40, Loss: 0.7030366957187653\n",
+      "Epoch 41, Loss: 0.6643220409750938\n",
+      "Epoch 42, Loss: 0.7269061654806137\n",
+      "Epoch 43, Loss: 0.735651284456253\n",
+      "Epoch 44, Loss: 0.6566457971930504\n",
+      "Epoch 45, Loss: 0.7260578945279121\n",
+      "Epoch 46, Loss: 0.7321755588054657\n",
+      "Epoch 47, Loss: 0.7829726785421371\n",
+      "Epoch 48, Loss: 0.6937808990478516\n",
+      "Epoch 49, Loss: 0.7425165623426437\n",
+      "Epoch 50, Loss: 0.6644666120409966\n",
+      "Epoch 51, Loss: 0.7199816405773163\n",
+      "Epoch 52, Loss: 0.6612266600131989\n",
+      "Epoch 53, Loss: 0.6891779452562332\n",
+      "Epoch 54, Loss: 0.7219838201999664\n",
+      "Epoch 55, Loss: 0.6851117461919785\n",
+      "Epoch 56, Loss: 0.6567785665392876\n",
+      "Epoch 57, Loss: 0.7459307909011841\n",
+      "Epoch 58, Loss: 0.6680298745632172\n",
+      "Epoch 59, Loss: 0.7578147947788239\n",
+      "Epoch 60, Loss: 0.7957419455051422\n",
+      "Epoch 61, Loss: 0.7350637316703796\n",
+      "Epoch 62, Loss: 0.6774612441658974\n",
+      "Epoch 63, Loss: 0.7323035448789597\n",
+      "Epoch 64, Loss: 0.6989059597253799\n",
+      "Epoch 65, Loss: 0.6728527024388313\n",
+      "Epoch 66, Loss: 0.7352995127439499\n",
+      "Epoch 67, Loss: 0.7304141744971275\n",
+      "Epoch 68, Loss: 0.734475165605545\n",
+      "Epoch 69, Loss: 0.6773841753602028\n",
+      "Epoch 70, Loss: 0.6949855834245682\n",
+      "Epoch 71, Loss: 0.6982422024011612\n",
+      "Epoch 72, Loss: 0.6592853739857674\n",
+      "Epoch 73, Loss: 0.7010123282670975\n",
+      "Epoch 74, Loss: 0.6976350247859955\n",
+      "Epoch 75, Loss: 0.7237774431705475\n",
+      "Epoch 76, Loss: 0.6649914085865021\n",
+      "Epoch 77, Loss: 0.6892912089824677\n",
+      "Epoch 78, Loss: 0.788253590464592\n",
+      "Epoch 79, Loss: 0.6967570930719376\n",
+      "Epoch 80, Loss: 0.7258572727441788\n",
+      "Epoch 81, Loss: 0.7506677508354187\n",
+      "Epoch 82, Loss: 0.7351827919483185\n",
+      "Epoch 83, Loss: 0.7600408643484116\n",
+      "Epoch 84, Loss: 0.7593263685703278\n",
+      "Epoch 85, Loss: 0.7382380962371826\n",
+      "Epoch 86, Loss: 0.7219966799020767\n",
+      "Epoch 87, Loss: 0.7902801409363747\n",
+      "Epoch 88, Loss: 0.7638328969478607\n",
+      "Epoch 89, Loss: 0.6752466261386871\n",
+      "Epoch 90, Loss: 0.7368026897311211\n",
+      "Epoch 91, Loss: 0.694749504327774\n",
+      "Epoch 92, Loss: 0.7510038614273071\n",
+      "Epoch 93, Loss: 0.7702030539512634\n",
+      "Epoch 94, Loss: 0.723219484090805\n",
+      "Epoch 95, Loss: 0.7279299646615982\n",
+      "Epoch 96, Loss: 0.7254779785871506\n",
+      "Epoch 97, Loss: 0.6970109194517136\n",
+      "Epoch 98, Loss: 0.6682631224393845\n",
+      "Epoch 99, Loss: 0.7311507910490036\n",
+      "Epoch 100, Loss: 0.6898983865976334\n",
+      "Epoch 101, Loss: 0.7247211635112762\n",
+      "Epoch 102, Loss: 0.7252713441848755\n",
+      "Epoch 103, Loss: 0.698613315820694\n",
+      "Epoch 104, Loss: 0.764925479888916\n",
+      "Epoch 105, Loss: 0.729946106672287\n",
+      "Epoch 106, Loss: 0.6973292976617813\n",
+      "Epoch 107, Loss: 0.6858086585998535\n",
+      "Epoch 108, Loss: 0.6846723333001137\n",
+      "Epoch 109, Loss: 0.6964010298252106\n",
+      "Epoch 110, Loss: 0.6615613922476768\n",
+      "Epoch 111, Loss: 0.7014753818511963\n",
+      "Epoch 112, Loss: 0.7561346590518951\n",
+      "Epoch 113, Loss: 0.6927345246076584\n",
+      "Epoch 114, Loss: 0.6896161735057831\n",
+      "Epoch 115, Loss: 0.7666801512241364\n",
+      "Epoch 116, Loss: 0.6852125823497772\n",
+      "Epoch 117, Loss: 0.718915194272995\n",
+      "Epoch 118, Loss: 0.7499804049730301\n",
+      "Epoch 119, Loss: 0.7903169691562653\n",
+      "Epoch 120, Loss: 0.7245521545410156\n",
+      "Epoch 121, Loss: 0.7681371867656708\n",
+      "Epoch 122, Loss: 0.6957640647888184\n",
+      "Epoch 123, Loss: 0.6909486949443817\n",
+      "Epoch 124, Loss: 0.6884673833847046\n",
+      "Epoch 125, Loss: 0.7300683856010437\n",
+      "Epoch 126, Loss: 0.701806053519249\n",
+      "Epoch 127, Loss: 0.7047831416130066\n",
+      "Epoch 128, Loss: 0.653191365301609\n",
+      "Epoch 129, Loss: 0.688704177737236\n",
+      "Epoch 130, Loss: 0.7264336496591568\n",
+      "Epoch 131, Loss: 0.749444454908371\n",
+      "Epoch 132, Loss: 0.6835757717490196\n",
+      "Epoch 133, Loss: 0.7176914513111115\n",
+      "Epoch 134, Loss: 0.7553784847259521\n",
+      "Epoch 135, Loss: 0.6862582564353943\n",
+      "Epoch 136, Loss: 0.7326899021863937\n",
+      "Epoch 137, Loss: 0.6528855636715889\n",
+      "Epoch 138, Loss: 0.7201268225908279\n",
+      "Epoch 139, Loss: 0.6972662061452866\n",
+      "Epoch 140, Loss: 0.757376179099083\n",
+      "Epoch 141, Loss: 0.7276921421289444\n",
+      "Epoch 142, Loss: 0.6935149133205414\n",
+      "Epoch 143, Loss: 0.789639413356781\n",
+      "Epoch 144, Loss: 0.7357824742794037\n",
+      "Epoch 145, Loss: 0.693398579955101\n",
+      "Epoch 146, Loss: 0.7301877439022064\n",
+      "Epoch 147, Loss: 0.6938806474208832\n",
+      "Epoch 148, Loss: 0.6945963725447655\n",
+      "Epoch 149, Loss: 0.7544803321361542\n",
+      "Epoch 150, Loss: 0.7374766767024994\n",
+      "Epoch 151, Loss: 0.7989955693483353\n",
+      "Epoch 152, Loss: 0.7371083945035934\n",
+      "Epoch 153, Loss: 0.7295102179050446\n",
+      "Epoch 154, Loss: 0.691999077796936\n",
+      "Epoch 155, Loss: 0.687791645526886\n",
+      "Epoch 156, Loss: 0.6899265199899673\n",
+      "Epoch 157, Loss: 0.7919392883777618\n",
+      "Epoch 158, Loss: 0.7332639396190643\n",
+      "Epoch 159, Loss: 0.736820325255394\n",
+      "Epoch 160, Loss: 0.6824376210570335\n",
+      "Epoch 161, Loss: 0.7261136919260025\n",
+      "Epoch 162, Loss: 0.6583062037825584\n",
+      "Epoch 163, Loss: 0.6652703210711479\n",
+      "Epoch 164, Loss: 0.7202188521623611\n",
+      "Epoch 165, Loss: 0.7329401820898056\n",
+      "Epoch 166, Loss: 0.6624360606074333\n",
+      "Epoch 167, Loss: 0.6910209953784943\n",
+      "Epoch 168, Loss: 0.730846680700779\n",
+      "Epoch 169, Loss: 0.7889405190944672\n",
+      "Epoch 170, Loss: 0.6645579040050507\n",
+      "Epoch 171, Loss: 0.8065831512212753\n",
+      "Epoch 172, Loss: 0.6626589968800545\n",
+      "Epoch 173, Loss: 0.7008005231618881\n",
+      "Epoch 174, Loss: 0.6636189892888069\n",
+      "Epoch 175, Loss: 0.6580931916832924\n",
+      "Epoch 176, Loss: 0.7607488036155701\n",
+      "Epoch 177, Loss: 0.7004559934139252\n",
+      "Epoch 178, Loss: 0.8048572838306427\n",
+      "Epoch 179, Loss: 0.7230100482702255\n",
+      "Epoch 180, Loss: 0.7095790356397629\n",
+      "Epoch 181, Loss: 0.6991759389638901\n",
+      "Epoch 182, Loss: 0.7245756387710571\n",
+      "Epoch 183, Loss: 0.7290528044104576\n",
+      "Epoch 184, Loss: 0.6941248327493668\n",
+      "Epoch 185, Loss: 0.758852630853653\n",
+      "Epoch 186, Loss: 0.6615615338087082\n",
+      "Epoch 187, Loss: 0.6859711185097694\n",
+      "Epoch 188, Loss: 0.7349532246589661\n",
+      "Epoch 189, Loss: 0.6563279628753662\n",
+      "Epoch 190, Loss: 0.6893051564693451\n",
+      "Epoch 191, Loss: 0.7603576332330704\n",
+      "Epoch 192, Loss: 0.7294857054948807\n",
+      "Epoch 193, Loss: 0.7287163585424423\n",
+      "Epoch 194, Loss: 0.7241926789283752\n",
+      "Epoch 195, Loss: 0.7060024365782738\n",
+      "Epoch 196, Loss: 0.6631852611899376\n",
+      "Epoch 197, Loss: 0.6486880257725716\n",
+      "Epoch 198, Loss: 0.750431016087532\n",
+      "Epoch 199, Loss: 0.7485257089138031\n",
+      "Epoch 200, Loss: 0.7264596521854401\n",
+      "Epoch 201, Loss: 0.6920607686042786\n",
+      "Epoch 202, Loss: 0.6686745807528496\n",
+      "Epoch 203, Loss: 0.6903162896633148\n",
+      "Epoch 204, Loss: 0.7638599723577499\n",
+      "Epoch 205, Loss: 0.8316691443324089\n",
+      "Epoch 206, Loss: 0.7185866087675095\n",
+      "Epoch 207, Loss: 0.697209358215332\n",
+      "Epoch 208, Loss: 0.7227450981736183\n",
+      "Epoch 209, Loss: 0.7401970475912094\n",
+      "Epoch 210, Loss: 0.731600284576416\n",
+      "Epoch 211, Loss: 0.6923322975635529\n",
+      "Epoch 212, Loss: 0.7962312251329422\n",
+      "Epoch 213, Loss: 0.6918545514345169\n",
+      "Epoch 214, Loss: 0.8281133025884628\n",
+      "Epoch 215, Loss: 0.7319207042455673\n",
+      "Epoch 216, Loss: 0.6966025829315186\n",
+      "Epoch 217, Loss: 0.7650987058877945\n",
+      "Epoch 218, Loss: 0.7560551166534424\n",
+      "Epoch 219, Loss: 0.6673862859606743\n",
+      "Epoch 220, Loss: 0.7638867646455765\n",
+      "Epoch 221, Loss: 0.6800968125462532\n",
+      "Epoch 222, Loss: 0.6698581948876381\n",
+      "Epoch 223, Loss: 0.7723892331123352\n",
+      "Epoch 224, Loss: 0.7632861137390137\n",
+      "Epoch 225, Loss: 0.7263539135456085\n",
+      "Epoch 226, Loss: 0.7300300598144531\n",
+      "Epoch 227, Loss: 0.7057671397924423\n",
+      "Epoch 228, Loss: 0.7899964824318886\n",
+      "Epoch 229, Loss: 0.7029763907194138\n",
+      "Epoch 230, Loss: 0.7013672441244125\n",
+      "Epoch 231, Loss: 0.6882044523954391\n",
+      "Epoch 232, Loss: 0.6917248368263245\n",
+      "Epoch 233, Loss: 0.7118381857872009\n",
+      "Epoch 234, Loss: 0.6570834591984749\n",
+      "Epoch 235, Loss: 0.734198123216629\n",
+      "Epoch 236, Loss: 0.8040710985660553\n",
+      "Epoch 237, Loss: 0.7562407851219177\n",
+      "Epoch 238, Loss: 0.7956227660179138\n",
+      "Epoch 239, Loss: 0.7199804484844208\n",
+      "Epoch 240, Loss: 0.6757364124059677\n",
+      "Epoch 241, Loss: 0.6883690059185028\n",
+      "Epoch 242, Loss: 0.6643754541873932\n",
+      "Epoch 243, Loss: 0.7324996739625931\n",
+      "Epoch 244, Loss: 0.7612148076295853\n",
+      "Epoch 245, Loss: 0.6640724241733551\n",
+      "Epoch 246, Loss: 0.7330870851874352\n",
+      "Epoch 247, Loss: 0.75765161216259\n",
+      "Epoch 248, Loss: 0.7243641316890717\n",
+      "Epoch 249, Loss: 0.6994045376777649\n",
+      "Epoch 250, Loss: 0.6954774186015129\n",
+      "Finished Training\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1000x600 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "# Training Loop\n",
+    "num_epochs = 250  # The number of times the entire dataset is passed through the network\n",
+    "epoch_losses = []  # List to store average loss of each epoch\n",
+    "\n",
+    "for epoch in range(num_epochs):\n",
+    "    running_loss = 0.0\n",
+    "    for inputs, targets in train_loader:\n",
+    "        optimizer.zero_grad()\n",
+    "        h = model.init_hidden()\n",
+    "\n",
+    "        # Process each time step\n",
+    "        for t in range(inputs.shape[1]):  # iterate over time steps\n",
+    "            output, h = complicated_model(inputs[:, t, :], h)\n",
+    "\n",
+    "        # Compute loss using the last output (if your task is many-to-one)\n",
+    "        loss = criterion(output, targets[:, -1, :])\n",
+    "        loss.backward()\n",
+    "        optimizer.step()\n",
+    "\n",
+    "        running_loss += loss.item()\n",
+    "\n",
+    "    avg_loss = running_loss / len(train_loader)\n",
+    "    epoch_losses.append(avg_loss)\n",
+    "    print(f'Epoch {epoch + 1}, Loss: {avg_loss}')\n",
+    "\n",
+    "print('Finished Training')\n",
+    "\n",
+    "# Plotting\n",
+    "plt.figure(figsize=(10, 6))\n",
+    "plt.plot(range(1, num_epochs + 1), epoch_losses, label='Training Loss')\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.ylabel('Loss')\n",
+    "plt.title('Training Loss Over Epochs')\n",
+    "plt.legend()\n",
+    "plt.show()\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/tutorials/W1D1_Generalization/simple_model_checkpoint.pth b/tutorials/W1D1_Generalization/simple_model_checkpoint.pth
deleted file mode 100644
index eeba2a007..000000000
Binary files a/tutorials/W1D1_Generalization/simple_model_checkpoint.pth and /dev/null differ